summaryrefslogtreecommitdiffstats
path: root/block
diff options
context:
space:
mode:
Diffstat (limited to 'block')
-rw-r--r--block/blk-core.c31
-rw-r--r--block/blk-merge.c5
-rw-r--r--block/blk-settings.c20
-rw-r--r--block/blk-sysfs.c11
-rw-r--r--block/blk-timeout.c13
-rw-r--r--block/blk.h7
-rw-r--r--block/bsg.c3
-rw-r--r--block/cfq-iosched.c66
-rw-r--r--block/compat_ioctl.c2
-rw-r--r--block/elevator.c8
-rw-r--r--block/genhd.c12
-rw-r--r--block/scsi_ioctl.c13
12 files changed, 116 insertions, 75 deletions
diff --git a/block/blk-core.c b/block/blk-core.c
index cce7a88dc612..648f15cb41f1 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -28,22 +28,14 @@
#include <linux/task_io_accounting_ops.h>
#include <linux/blktrace_api.h>
#include <linux/fault-inject.h>
-#include <trace/block.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/block.h>
#include "blk.h"
-DEFINE_TRACE(block_plug);
-DEFINE_TRACE(block_unplug_io);
-DEFINE_TRACE(block_unplug_timer);
-DEFINE_TRACE(block_getrq);
-DEFINE_TRACE(block_sleeprq);
-DEFINE_TRACE(block_rq_requeue);
-DEFINE_TRACE(block_bio_backmerge);
-DEFINE_TRACE(block_bio_frontmerge);
-DEFINE_TRACE(block_bio_queue);
-DEFINE_TRACE(block_rq_complete);
-DEFINE_TRACE(block_remap); /* Also used in drivers/md/dm.c */
EXPORT_TRACEPOINT_SYMBOL_GPL(block_remap);
+EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
static int __make_request(struct request_queue *q, struct bio *bio);
@@ -643,7 +635,7 @@ static inline void blk_free_request(struct request_queue *q, struct request *rq)
}
static struct request *
-blk_alloc_request(struct request_queue *q, int rw, int priv, gfp_t gfp_mask)
+blk_alloc_request(struct request_queue *q, int flags, int priv, gfp_t gfp_mask)
{
struct request *rq = mempool_alloc(q->rq.rq_pool, gfp_mask);
@@ -652,7 +644,7 @@ blk_alloc_request(struct request_queue *q, int rw, int priv, gfp_t gfp_mask)
blk_rq_init(q, rq);
- rq->cmd_flags = rw | REQ_ALLOCED;
+ rq->cmd_flags = flags | REQ_ALLOCED;
if (priv) {
if (unlikely(elv_set_request(q, rq, gfp_mask))) {
@@ -792,6 +784,8 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
if (priv)
rl->elvpriv++;
+ 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);
@@ -1275,7 +1269,7 @@ static inline void blk_partition_remap(struct bio *bio)
bio->bi_bdev = bdev->bd_contains;
trace_block_remap(bdev_get_queue(bio->bi_bdev), bio,
- bdev->bd_dev, bio->bi_sector,
+ bdev->bd_dev,
bio->bi_sector - p->start_sect);
}
}
@@ -1444,8 +1438,7 @@ static inline void __generic_make_request(struct bio *bio)
goto end_io;
if (old_sector != -1)
- trace_block_remap(q, bio, old_dev, bio->bi_sector,
- old_sector);
+ trace_block_remap(q, bio, old_dev, old_sector);
trace_block_bio_queue(q, bio);
@@ -1770,10 +1763,10 @@ static int __end_that_request_first(struct request *req, int error,
} else {
int idx = bio->bi_idx + next_idx;
- if (unlikely(bio->bi_idx >= bio->bi_vcnt)) {
+ if (unlikely(idx >= bio->bi_vcnt)) {
blk_dump_rq_flags(req, "__end_that");
printk(KERN_ERR "%s: bio idx %d >= vcnt %d\n",
- __func__, bio->bi_idx, bio->bi_vcnt);
+ __func__, idx, bio->bi_vcnt);
break;
}
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 63760ca3da0f..23d2a6fe34a3 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -402,7 +402,10 @@ static int attempt_merge(struct request_queue *q, struct request *req,
elv_merge_requests(q, req, next);
- blk_account_io_merge(req);
+ /*
+ * 'next' is going away, so update stats accordingly
+ */
+ blk_account_io_merge(next);
req->ioprio = ioprio_best(req->ioprio, next->ioprio);
if (blk_rq_cpu_valid(next))
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 69c42adde52b..57af728d94bb 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -156,26 +156,28 @@ EXPORT_SYMBOL(blk_queue_make_request);
/**
* blk_queue_bounce_limit - set bounce buffer limit for queue
- * @q: the request queue for the device
- * @dma_addr: bus address limit
+ * @q: the request queue for the device
+ * @dma_mask: the maximum address the device can handle
*
* 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 @dma_addr.
+ * buffers for doing I/O to pages residing above @dma_mask.
**/
-void blk_queue_bounce_limit(struct request_queue *q, u64 dma_addr)
+void blk_queue_bounce_limit(struct request_queue *q, u64 dma_mask)
{
- unsigned long b_pfn = dma_addr >> PAGE_SHIFT;
+ unsigned long b_pfn = dma_mask >> PAGE_SHIFT;
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 (b_pfn < (min_t(u64, 0x100000000UL, BLK_BOUNCE_HIGH) >> PAGE_SHIFT))
+ /*
+ * 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 (b_pfn < (min_t(u64, 0xffffffffUL, BLK_BOUNCE_HIGH) >> PAGE_SHIFT))
dma = 1;
q->bounce_pfn = max_low_pfn;
#else
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index cac4e9febe6a..26f9ec28f56c 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -209,14 +209,10 @@ static ssize_t queue_iostats_store(struct request_queue *q, const char *page,
ssize_t ret = queue_var_store(&stats, page, count);
spin_lock_irq(q->queue_lock);
- elv_quiesce_start(q);
-
if (stats)
queue_flag_set(QUEUE_FLAG_IO_STAT, q);
else
queue_flag_clear(QUEUE_FLAG_IO_STAT, q);
-
- elv_quiesce_end(q);
spin_unlock_irq(q->queue_lock);
return ret;
@@ -387,16 +383,21 @@ struct kobj_type blk_queue_ktype = {
int blk_register_queue(struct gendisk *disk)
{
int ret;
+ struct device *dev = disk_to_dev(disk);
struct request_queue *q = disk->queue;
if (WARN_ON(!q))
return -ENXIO;
+ ret = blk_trace_init_sysfs(dev);
+ if (ret)
+ return ret;
+
if (!q->request_fn)
return 0;
- ret = kobject_add(&q->kobj, kobject_get(&disk_to_dev(disk)->kobj),
+ ret = kobject_add(&q->kobj, kobject_get(&dev->kobj),
"%s", "queue");
if (ret < 0)
return ret;
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index bbbdc4b8ccf2..1ec0d503cacd 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -211,6 +211,12 @@ void blk_abort_queue(struct request_queue *q)
struct request *rq, *tmp;
LIST_HEAD(list);
+ /*
+ * Not a request based block device, nothing to abort
+ */
+ if (!q->request_fn)
+ return;
+
spin_lock_irqsave(q->queue_lock, flags);
elv_abort_queue(q);
@@ -224,6 +230,13 @@ void blk_abort_queue(struct request_queue *q)
list_for_each_entry_safe(rq, tmp, &list, timeout_list)
blk_abort_request(rq);
+ /*
+ * Occasionally, blk_abort_request() will return without
+ * deleting the element from the list. Make sure we add those back
+ * instead of leaving them on the local stack list.
+ */
+ list_splice(&list, &q->timeout_list);
+
spin_unlock_irqrestore(q->queue_lock, flags);
}
diff --git a/block/blk.h b/block/blk.h
index 5dfc41267a08..79c85f7c9ff5 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -114,12 +114,7 @@ static inline int blk_cpu_to_group(int cpu)
static inline int blk_do_io_stat(struct request *rq)
{
- struct gendisk *disk = rq->rq_disk;
-
- if (!disk || !disk->queue)
- return 0;
-
- return blk_queue_io_stat(disk->queue) && (rq->cmd_flags & REQ_ELVPRIV);
+ return rq->rq_disk && blk_rq_io_stat(rq);
}
#endif
diff --git a/block/bsg.c b/block/bsg.c
index 206060e795da..dd81be455e00 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -315,6 +315,7 @@ out:
blk_put_request(rq);
if (next_rq) {
blk_rq_unmap_user(next_rq->bio);
+ next_rq->bio = NULL;
blk_put_request(next_rq);
}
return ERR_PTR(ret);
@@ -448,6 +449,7 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
hdr->dout_resid = rq->data_len;
hdr->din_resid = rq->next_rq->data_len;
blk_rq_unmap_user(bidi_bio);
+ rq->next_rq->bio = NULL;
blk_put_request(rq->next_rq);
} else if (rq_data_dir(rq) == READ)
hdr->din_resid = rq->data_len;
@@ -466,6 +468,7 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
blk_rq_unmap_user(bio);
if (rq->cmd != rq->__cmd)
kfree(rq->cmd);
+ rq->bio = NULL;
blk_put_request(rq);
return ret;
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 0d3b70de3d80..a55a9bd75bd1 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -154,6 +154,8 @@ struct cfq_queue {
unsigned long rb_key;
/* prio tree member */
struct rb_node p_node;
+ /* prio tree root we belong to, if any */
+ struct rb_root *p_root;
/* sorted list of pending requests */
struct rb_root sort_list;
/* if fifo isn't expired, next request to serve */
@@ -558,10 +560,10 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
}
static struct cfq_queue *
-cfq_prio_tree_lookup(struct cfq_data *cfqd, int ioprio, sector_t sector,
- struct rb_node **ret_parent, struct rb_node ***rb_link)
+cfq_prio_tree_lookup(struct cfq_data *cfqd, struct rb_root *root,
+ sector_t sector, struct rb_node **ret_parent,
+ struct rb_node ***rb_link)
{
- struct rb_root *root = &cfqd->prio_trees[ioprio];
struct rb_node **p, *parent;
struct cfq_queue *cfqq = NULL;
@@ -584,34 +586,38 @@ cfq_prio_tree_lookup(struct cfq_data *cfqd, int ioprio, sector_t sector,
else
break;
p = n;
+ cfqq = NULL;
}
*ret_parent = parent;
if (rb_link)
*rb_link = p;
- return NULL;
+ return cfqq;
}
static void cfq_prio_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
- struct rb_root *root = &cfqd->prio_trees[cfqq->ioprio];
struct rb_node **p, *parent;
struct cfq_queue *__cfqq;
- if (!RB_EMPTY_NODE(&cfqq->p_node))
- rb_erase_init(&cfqq->p_node, root);
+ if (cfqq->p_root) {
+ rb_erase(&cfqq->p_node, cfqq->p_root);
+ cfqq->p_root = NULL;
+ }
if (cfq_class_idle(cfqq))
return;
if (!cfqq->next_rq)
return;
- __cfqq = cfq_prio_tree_lookup(cfqd, cfqq->ioprio, cfqq->next_rq->sector,
+ cfqq->p_root = &cfqd->prio_trees[cfqq->org_ioprio];
+ __cfqq = cfq_prio_tree_lookup(cfqd, cfqq->p_root, cfqq->next_rq->sector,
&parent, &p);
- BUG_ON(__cfqq);
-
- rb_link_node(&cfqq->p_node, parent, p);
- rb_insert_color(&cfqq->p_node, root);
+ if (!__cfqq) {
+ rb_link_node(&cfqq->p_node, parent, p);
+ rb_insert_color(&cfqq->p_node, cfqq->p_root);
+ } else
+ cfqq->p_root = NULL;
}
/*
@@ -656,8 +662,10 @@ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
if (!RB_EMPTY_NODE(&cfqq->rb_node))
cfq_rb_erase(&cfqq->rb_node, &cfqd->service_tree);
- if (!RB_EMPTY_NODE(&cfqq->p_node))
- rb_erase_init(&cfqq->p_node, &cfqd->prio_trees[cfqq->ioprio]);
+ if (cfqq->p_root) {
+ rb_erase(&cfqq->p_node, cfqq->p_root);
+ cfqq->p_root = NULL;
+ }
BUG_ON(!cfqd->busy_queues);
cfqd->busy_queues--;
@@ -947,20 +955,24 @@ static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd,
return cfqd->last_position - rq->sector;
}
+#define CIC_SEEK_THR 8 * 1024
+#define CIC_SEEKY(cic) ((cic)->seek_mean > CIC_SEEK_THR)
+
static inline int cfq_rq_close(struct cfq_data *cfqd, struct request *rq)
{
struct cfq_io_context *cic = cfqd->active_cic;
+ sector_t sdist = cic->seek_mean;
if (!sample_valid(cic->seek_samples))
- return 0;
+ sdist = CIC_SEEK_THR;
- return cfq_dist_from_last(cfqd, rq) <= cic->seek_mean;
+ return cfq_dist_from_last(cfqd, rq) <= sdist;
}
static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
struct cfq_queue *cur_cfqq)
{
- struct rb_root *root = &cfqd->prio_trees[cur_cfqq->ioprio];
+ struct rb_root *root = &cfqd->prio_trees[cur_cfqq->org_ioprio];
struct rb_node *parent, *node;
struct cfq_queue *__cfqq;
sector_t sector = cfqd->last_position;
@@ -972,8 +984,7 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
* First, if we find a request starting at the end of the last
* request, choose it.
*/
- __cfqq = cfq_prio_tree_lookup(cfqd, cur_cfqq->ioprio,
- sector, &parent, NULL);
+ __cfqq = cfq_prio_tree_lookup(cfqd, root, sector, &parent, NULL);
if (__cfqq)
return __cfqq;
@@ -1039,9 +1050,6 @@ static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
return cfqq;
}
-
-#define CIC_SEEKY(cic) ((cic)->seek_mean > (8 * 1024))
-
static void cfq_arm_slice_timer(struct cfq_data *cfqd)
{
struct cfq_queue *cfqq = cfqd->active_queue;
@@ -1908,7 +1916,9 @@ cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_io_context *cic,
sector_t sdist;
u64 total;
- if (cic->last_request_pos < rq->sector)
+ if (!cic->last_request_pos)
+ sdist = 0;
+ else if (cic->last_request_pos < rq->sector)
sdist = rq->sector - cic->last_request_pos;
else
sdist = cic->last_request_pos - rq->sector;
@@ -2443,12 +2453,22 @@ static void cfq_exit_queue(struct elevator_queue *e)
static void *cfq_init_queue(struct request_queue *q)
{
struct cfq_data *cfqd;
+ int i;
cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node);
if (!cfqd)
return NULL;
cfqd->service_tree = CFQ_RB_ROOT;
+
+ /*
+ * Not strictly needed (since RB_ROOT just clears the node and we
+ * zeroed cfqd on alloc), but better be safe in case someone decides
+ * to add magic to the rb code
+ */
+ for (i = 0; i < CFQ_PRIO_LISTS; i++)
+ cfqd->prio_trees[i] = RB_ROOT;
+
INIT_LIST_HEAD(&cfqd->cic_list);
cfqd->queue = q;
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index f87615dea46b..f8c218cd08e1 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -568,7 +568,7 @@ static int compat_blk_trace_setup(struct block_device *bdev, char __user *arg)
memcpy(&buts.name, &cbuts.name, 32);
mutex_lock(&bdev->bd_mutex);
- ret = do_blk_trace_setup(q, b, bdev->bd_dev, &buts);
+ ret = do_blk_trace_setup(q, b, bdev->bd_dev, bdev, &buts);
mutex_unlock(&bdev->bd_mutex);
if (ret)
return ret;
diff --git a/block/elevator.c b/block/elevator.c
index 7073a9072577..e220f0c543e3 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -33,17 +33,16 @@
#include <linux/compiler.h>
#include <linux/delay.h>
#include <linux/blktrace_api.h>
-#include <trace/block.h>
#include <linux/hash.h>
#include <linux/uaccess.h>
+#include <trace/events/block.h>
+
#include "blk.h"
static DEFINE_SPINLOCK(elv_list_lock);
static LIST_HEAD(elv_list);
-DEFINE_TRACE(block_rq_abort);
-
/*
* Merge hash stuff.
*/
@@ -55,9 +54,6 @@ static const int elv_hash_shift = 6;
#define rq_hash_key(rq) ((rq)->sector + (rq)->nr_sectors)
#define ELV_ON_HASH(rq) (!hlist_unhashed(&(rq)->hash))
-DEFINE_TRACE(block_rq_insert);
-DEFINE_TRACE(block_rq_issue);
-
/*
* Query io scheduler to see if the current process issuing bio may be
* merged with rq.
diff --git a/block/genhd.c b/block/genhd.c
index a9ec910974c1..1a4916e01732 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -98,7 +98,7 @@ void disk_part_iter_init(struct disk_part_iter *piter, struct gendisk *disk,
if (flags & DISK_PITER_REVERSE)
piter->idx = ptbl->len - 1;
- else if (flags & DISK_PITER_INCL_PART0)
+ else if (flags & (DISK_PITER_INCL_PART0 | DISK_PITER_INCL_EMPTY_PART0))
piter->idx = 0;
else
piter->idx = 1;
@@ -134,7 +134,8 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter)
/* determine iteration parameters */
if (piter->flags & DISK_PITER_REVERSE) {
inc = -1;
- if (piter->flags & DISK_PITER_INCL_PART0)
+ if (piter->flags & (DISK_PITER_INCL_PART0 |
+ DISK_PITER_INCL_EMPTY_PART0))
end = -1;
else
end = 0;
@@ -150,7 +151,10 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter)
part = rcu_dereference(ptbl->part[piter->idx]);
if (!part)
continue;
- if (!(piter->flags & DISK_PITER_INCL_EMPTY) && !part->nr_sects)
+ if (!part->nr_sects &&
+ !(piter->flags & DISK_PITER_INCL_EMPTY) &&
+ !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 &&
+ piter->idx == 0))
continue;
get_device(part_to_dev(part));
@@ -1011,7 +1015,7 @@ static int diskstats_show(struct seq_file *seqf, void *v)
"\n\n");
*/
- disk_part_iter_init(&piter, gp, DISK_PITER_INCL_PART0);
+ disk_part_iter_init(&piter, gp, DISK_PITER_INCL_EMPTY_PART0);
while ((hd = disk_part_iter_next(&piter))) {
cpu = part_stat_lock();
part_round_stats(cpu, hd);
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 84b7f8709f41..82a0ca2f6729 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -290,6 +290,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
if (hdr->iovec_count) {
const int size = sizeof(struct sg_iovec) * hdr->iovec_count;
+ size_t iov_data_len;
struct sg_iovec *iov;
iov = kmalloc(size, GFP_KERNEL);
@@ -304,8 +305,18 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
goto out;
}
+ /* SG_IO howto says that the shorter of the two wins */
+ iov_data_len = iov_length((struct iovec *)iov,
+ hdr->iovec_count);
+ if (hdr->dxfer_len < iov_data_len) {
+ hdr->iovec_count = iov_shorten((struct iovec *)iov,
+ hdr->iovec_count,
+ hdr->dxfer_len);
+ iov_data_len = hdr->dxfer_len;
+ }
+
ret = blk_rq_map_user_iov(q, rq, NULL, iov, hdr->iovec_count,
- hdr->dxfer_len, GFP_KERNEL);
+ iov_data_len, GFP_KERNEL);
kfree(iov);
} else if (hdr->dxfer_len)
ret = blk_rq_map_user(q, rq, NULL, hdr->dxferp, hdr->dxfer_len,