Merge branch 'for-linus' of git://git.kernel.dk/linux-2.6-block

* 'for-linus' of git://git.kernel.dk/linux-2.6-block: (34 commits)
  cfq-iosched: Fix the incorrect timeslice accounting with forced_dispatch
  loop: Update mtime when writing using aops
  block: expose the statistics in blkio.time and blkio.sectors for the root cgroup
  backing-dev: Handle class_create() failure
  Block: Fix block/elevator.c elevator_get() off-by-one error
  drbd: lc_element_by_index() never returns NULL
  cciss: unlock on error path
  cfq-iosched: Do not merge queues of BE and IDLE classes
  cfq-iosched: Add additional blktrace log messages in CFQ for easier debugging
  i2o: Remove the dangerous kobj_to_i2o_device macro
  block: remove 16 bytes of padding from struct request on 64bits
  cfq-iosched: fix a kbuild regression
  block: make CONFIG_BLK_CGROUP visible
  Remove GENHD_FL_DRIVERFS
  block: Export max number of segments and max segment size in sysfs
  block: Finalize conversion of block limits functions
  block: Fix overrun in lcm() and move it to lib
  vfs: improve writeback_inodes_wb()
  paride: fix off-by-one test
  drbd: fix al-to-on-disk-bitmap for 4k logical_block_size
  ...

Documentation/DocBook/tracepoint.tmpl

@@ -16,6 +16,15 @@
      </address>
     </affiliation>
    </author>
+   <author>
+    <firstname>William</firstname>
+    <surname>Cohen</surname>
+    <affiliation>
+     <address>
+      <email>wcohen@redhat.com</email>
+     </address>
+    </affiliation>
+   </author>
   </authorgroup>
 
   <legalnotice>
@@ -91,4 +100,8 @@
 !Iinclude/trace/events/signal.h
   </chapter>
 
+  <chapter id="block">
+   <title>Block IO</title>
+!Iinclude/trace/events/block.h
+  </chapter>
 </book>

Documentation/block/biodoc.txt

@@ -1162,8 +1162,8 @@ where a driver received a request ala this before:
 
 As mentioned, there is no virtual mapping of a bio. For DMA, this is
 not a problem as the driver probably never will need a virtual mapping.
-Instead it needs a bus mapping (pci_map_page for a single segment or
-use blk_rq_map_sg for scatter gather) to be able to ship it to the driver. For
+Instead it needs a bus mapping (dma_map_page for a single segment or
+use dma_map_sg for scatter gather) to be able to ship it to the driver. For
 PIO drivers (or drivers that need to revert to PIO transfer once in a
 while (IDE for example)), where the CPU is doing the actual data
 transfer a virtual mapping is needed. If the driver supports highmem I/O,

block/Kconfig

@@ -78,8 +78,9 @@ config BLK_DEV_INTEGRITY
 	Protection.  If in doubt, say N.
 
 config BLK_CGROUP
-	tristate
+	tristate "Block cgroup support"
 	depends on CGROUPS
+	depends on CFQ_GROUP_IOSCHED
 	default n
 	---help---
 	Generic block IO controller cgroup interface. This is the common

block/blk-settings.c

@@ -8,6 +8,7 @@
 #include <linux/blkdev.h>
 #include <linux/bootmem.h>	/* for max_pfn/max_low_pfn */
 #include <linux/gcd.h>
+#include <linux/lcm.h>
 #include <linux/jiffies.h>
 #include <linux/gfp.h>
 
@@ -462,16 +463,6 @@ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
 }
 EXPORT_SYMBOL(blk_queue_stack_limits);
 
-static unsigned int lcm(unsigned int a, unsigned int b)
-{
-	if (a && b)
-		return (a * b) / gcd(a, b);
-	else if (b)
-		return b;
-
-	return a;
-}
-
 /**
  * blk_stack_limits - adjust queue_limits for stacked devices
  * @t:	the stacking driver limits (top device)

block/blk-sysfs.c

@@ -107,6 +107,19 @@ static ssize_t queue_max_sectors_show(struct request_queue *q, char *page)
 	return queue_var_show(max_sectors_kb, (page));
 }
 
+static ssize_t queue_max_segments_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(queue_max_segments(q), (page));
+}
+
+static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page)
+{
+	if (test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags))
+		return queue_var_show(queue_max_segment_size(q), (page));
+
+	return queue_var_show(PAGE_CACHE_SIZE, (page));
+}
+
 static ssize_t queue_logical_block_size_show(struct request_queue *q, char *page)
 {
 	return queue_var_show(queue_logical_block_size(q), page);
@@ -281,6 +294,16 @@ static struct queue_sysfs_entry queue_max_hw_sectors_entry = {
 	.show = queue_max_hw_sectors_show,
 };
 
+static struct queue_sysfs_entry queue_max_segments_entry = {
+	.attr = {.name = "max_segments", .mode = S_IRUGO },
+	.show = queue_max_segments_show,
+};
+
+static struct queue_sysfs_entry queue_max_segment_size_entry = {
+	.attr = {.name = "max_segment_size", .mode = S_IRUGO },
+	.show = queue_max_segment_size_show,
+};
+
 static struct queue_sysfs_entry queue_iosched_entry = {
 	.attr = {.name = "scheduler", .mode = S_IRUGO | S_IWUSR },
 	.show = elv_iosched_show,
@@ -356,6 +379,8 @@ static struct attribute *default_attrs[] = {
 	&queue_ra_entry.attr,
 	&queue_max_hw_sectors_entry.attr,
 	&queue_max_sectors_entry.attr,
+	&queue_max_segments_entry.attr,
+	&queue_max_segment_size_entry.attr,
 	&queue_iosched_entry.attr,
 	&queue_hw_sector_size_entry.attr,
 	&queue_logical_block_size_entry.attr,

block/cfq-iosched.c

@@ -48,6 +48,7 @@ static const int cfq_hist_divisor = 4;
 #define CFQ_SERVICE_SHIFT       12
 
 #define CFQQ_SEEK_THR		(sector_t)(8 * 100)
+#define CFQQ_CLOSE_THR		(sector_t)(8 * 1024)
 #define CFQQ_SECT_THR_NONROT	(sector_t)(2 * 32)
 #define CFQQ_SEEKY(cfqq)	(hweight32(cfqq->seek_history) > 32/8)
 
@@ -948,6 +949,11 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
 	unsigned int major, minor;
 
 	cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key));
+	if (cfqg && !cfqg->blkg.dev && bdi->dev && dev_name(bdi->dev)) {
+		sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+		cfqg->blkg.dev = MKDEV(major, minor);
+		goto done;
+	}
 	if (cfqg || !create)
 		goto done;
 
@@ -1518,7 +1524,8 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd,
 				   struct cfq_queue *cfqq)
 {
 	if (cfqq) {
-		cfq_log_cfqq(cfqd, cfqq, "set_active");
+		cfq_log_cfqq(cfqd, cfqq, "set_active wl_prio:%d wl_type:%d",
+				cfqd->serving_prio, cfqd->serving_type);
 		cfqq->slice_start = 0;
 		cfqq->dispatch_start = jiffies;
 		cfqq->allocated_slice = 0;
@@ -1661,9 +1668,9 @@ static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd,
 }
 
 static inline int cfq_rq_close(struct cfq_data *cfqd, struct cfq_queue *cfqq,
-			       struct request *rq, bool for_preempt)
+			       struct request *rq)
 {
-	return cfq_dist_from_last(cfqd, rq) <= CFQQ_SEEK_THR;
+	return cfq_dist_from_last(cfqd, rq) <= CFQQ_CLOSE_THR;
 }
 
 static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
@@ -1690,7 +1697,7 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
 	 * will contain the closest sector.
 	 */
 	__cfqq = rb_entry(parent, struct cfq_queue, p_node);
-	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq, false))
+	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
 		return __cfqq;
 
 	if (blk_rq_pos(__cfqq->next_rq) < sector)
@@ -1701,7 +1708,7 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
 		return NULL;
 
 	__cfqq = rb_entry(node, struct cfq_queue, p_node);
-	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq, false))
+	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
 		return __cfqq;
 
 	return NULL;
@@ -1722,6 +1729,8 @@ static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
 {
 	struct cfq_queue *cfqq;
 
+	if (cfq_class_idle(cur_cfqq))
+		return NULL;
 	if (!cfq_cfqq_sync(cur_cfqq))
 		return NULL;
 	if (CFQQ_SEEKY(cur_cfqq))
@@ -1788,7 +1797,11 @@ static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	 * Otherwise, we do only if they are the last ones
 	 * in their service tree.
 	 */
-	return service_tree->count == 1 && cfq_cfqq_sync(cfqq);
+	if (service_tree->count == 1 && cfq_cfqq_sync(cfqq))
+		return 1;
+	cfq_log_cfqq(cfqd, cfqq, "Not idling. st->count:%d",
+			service_tree->count);
+	return 0;
 }
 
 static void cfq_arm_slice_timer(struct cfq_data *cfqd)
@@ -1833,8 +1846,11 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	 * time slice.
 	 */
 	if (sample_valid(cic->ttime_samples) &&
-	    (cfqq->slice_end - jiffies < cic->ttime_mean))
+	    (cfqq->slice_end - jiffies < cic->ttime_mean)) {
+		cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%d",
+				cic->ttime_mean);
 		return;
+	}
 
 	cfq_mark_cfqq_wait_request(cfqq);
 
@@ -2042,6 +2058,7 @@ static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
 		slice = max(slice, 2 * cfqd->cfq_slice_idle);
 
 	slice = max_t(unsigned, slice, CFQ_MIN_TT);
+	cfq_log(cfqd, "workload slice:%d", slice);
 	cfqd->workload_expires = jiffies + slice;
 	cfqd->noidle_tree_requires_idle = false;
 }
@@ -2189,10 +2206,13 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd)
 	struct cfq_queue *cfqq;
 	int dispatched = 0;
 
-	while ((cfqq = cfq_get_next_queue_forced(cfqd)) != NULL)
+	/* Expire the timeslice of the current active queue first */
+	cfq_slice_expired(cfqd, 0);
+	while ((cfqq = cfq_get_next_queue_forced(cfqd)) != NULL) {
+		__cfq_set_active_queue(cfqd, cfqq);
 		dispatched += __cfq_forced_dispatch_cfqq(cfqq);
+	}
 
-	cfq_slice_expired(cfqd, 0);
 	BUG_ON(cfqd->busy_queues);
 
 	cfq_log(cfqd, "forced_dispatch=%d", dispatched);
@@ -3104,7 +3124,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	 * if this request is as-good as one we would expect from the
 	 * current cfqq, let it preempt
 	 */
-	if (cfq_rq_close(cfqd, cfqq, rq, true))
+	if (cfq_rq_close(cfqd, cfqq, rq))
 		return true;
 
 	return false;
@@ -3308,6 +3328,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 		if (cfq_should_wait_busy(cfqd, cfqq)) {
 			cfqq->slice_end = jiffies + cfqd->cfq_slice_idle;
 			cfq_mark_cfqq_wait_busy(cfqq);
+			cfq_log_cfqq(cfqd, cfqq, "will busy wait");
 		}
 
 		/*

block/elevator.c

@@ -154,7 +154,7 @@ static struct elevator_type *elevator_get(const char *name)
 
 		spin_unlock(&elv_list_lock);
 
-		sprintf(elv, "%s-iosched", name);
+		snprintf(elv, sizeof(elv), "%s-iosched", name);
 
 		request_module("%s", elv);
 		spin_lock(&elv_list_lock);

drivers/block/DAC960.c

@@ -2533,7 +2533,6 @@ static bool DAC960_RegisterBlockDevice(DAC960_Controller_T *Controller)
   	Controller->RequestQueue[n] = RequestQueue;
   	blk_queue_bounce_limit(RequestQueue, Controller->BounceBufferLimit);
   	RequestQueue->queuedata = Controller;
-  	blk_queue_max_hw_segments(RequestQueue, Controller->DriverScatterGatherLimit);
 	blk_queue_max_segments(RequestQueue, Controller->DriverScatterGatherLimit);
 	blk_queue_max_hw_sectors(RequestQueue, Controller->MaxBlocksPerCommand);
 	disk->queue = RequestQueue;

drivers/block/drbd/drbd_actlog.c

@@ -536,7 +536,9 @@ static void atodb_endio(struct bio *bio, int error)
 	put_ldev(mdev);
 }
 
+/* sector to word */
 #define S2W(s)	((s)<<(BM_EXT_SHIFT-BM_BLOCK_SHIFT-LN2_BPL))
+
 /* activity log to on disk bitmap -- prepare bio unless that sector
  * is already covered by previously prepared bios */
 static int atodb_prepare_unless_covered(struct drbd_conf *mdev,
@@ -546,13 +548,20 @@ static int atodb_prepare_unless_covered(struct drbd_conf *mdev,
 {
 	struct bio *bio;
 	struct page *page;
-	sector_t on_disk_sector = enr + mdev->ldev->md.md_offset
-				      + mdev->ldev->md.bm_offset;
+	sector_t on_disk_sector;
 	unsigned int page_offset = PAGE_SIZE;
 	int offset;
 	int i = 0;
 	int err = -ENOMEM;
 
+	/* We always write aligned, full 4k blocks,
+	 * so we can ignore the logical_block_size (for now) */
+	enr &= ~7U;
+	on_disk_sector = enr + mdev->ldev->md.md_offset
+			     + mdev->ldev->md.bm_offset;
+
+	D_ASSERT(!(on_disk_sector & 7U));
+
 	/* Check if that enr is already covered by an already created bio.
 	 * Caution, bios[] is not NULL terminated,
 	 * but only initialized to all NULL.
@@ -588,7 +597,7 @@ static int atodb_prepare_unless_covered(struct drbd_conf *mdev,
 
 	offset = S2W(enr);
 	drbd_bm_get_lel(mdev, offset,
-			min_t(size_t, S2W(1), drbd_bm_words(mdev) - offset),
+			min_t(size_t, S2W(8), drbd_bm_words(mdev) - offset),
 			kmap(page) + page_offset);
 	kunmap(page);
 
@@ -597,7 +606,7 @@ static int atodb_prepare_unless_covered(struct drbd_conf *mdev,
 	bio->bi_bdev = mdev->ldev->md_bdev;
 	bio->bi_sector = on_disk_sector;
 
-	if (bio_add_page(bio, page, MD_SECTOR_SIZE, page_offset) != MD_SECTOR_SIZE)
+	if (bio_add_page(bio, page, 4096, page_offset) != 4096)
 		goto out_put_page;
 
 	atomic_inc(&wc->count);
@@ -1327,7 +1336,7 @@ int drbd_rs_del_all(struct drbd_conf *mdev)
 		/* ok, ->resync is there. */
 		for (i = 0; i < mdev->resync->nr_elements; i++) {
 			e = lc_element_by_index(mdev->resync, i);
-			bm_ext = e ? lc_entry(e, struct bm_extent, lce) : NULL;
+			bm_ext = lc_entry(e, struct bm_extent, lce);
 			if (bm_ext->lce.lc_number == LC_FREE)
 				continue;
 			if (bm_ext->lce.lc_number == mdev->resync_wenr) {

drivers/block/drbd/drbd_bitmap.c

@@ -67,7 +67,7 @@ struct drbd_bitmap {
 	size_t   bm_words;
 	size_t   bm_number_of_pages;
 	sector_t bm_dev_capacity;
-	struct semaphore bm_change; /* serializes resize operations */
+	struct mutex bm_change; /* serializes resize operations */
 
 	atomic_t bm_async_io;
 	wait_queue_head_t bm_io_wait;
@@ -115,7 +115,7 @@ void drbd_bm_lock(struct drbd_conf *mdev, char *why)
 		return;
 	}
 
-	trylock_failed = down_trylock(&b->bm_change);
+	trylock_failed = !mutex_trylock(&b->bm_change);
 
 	if (trylock_failed) {
 		dev_warn(DEV, "%s going to '%s' but bitmap already locked for '%s' by %s\n",
@@ -126,7 +126,7 @@ void drbd_bm_lock(struct drbd_conf *mdev, char *why)
 		    b->bm_task == mdev->receiver.task ? "receiver" :
 		    b->bm_task == mdev->asender.task  ? "asender"  :
 		    b->bm_task == mdev->worker.task   ? "worker"   : "?");
-		down(&b->bm_change);
+		mutex_lock(&b->bm_change);
 	}
 	if (__test_and_set_bit(BM_LOCKED, &b->bm_flags))
 		dev_err(DEV, "FIXME bitmap already locked in bm_lock\n");
@@ -148,7 +148,7 @@ void drbd_bm_unlock(struct drbd_conf *mdev)
 
 	b->bm_why  = NULL;
 	b->bm_task = NULL;
-	up(&b->bm_change);
+	mutex_unlock(&b->bm_change);
 }
 
 /* word offset to long pointer */
@@ -296,7 +296,7 @@ int drbd_bm_init(struct drbd_conf *mdev)
 	if (!b)
 		return -ENOMEM;
 	spin_lock_init(&b->bm_lock);
-	init_MUTEX(&b->bm_change);
+	mutex_init(&b->bm_change);
 	init_waitqueue_head(&b->bm_io_wait);
 
 	mdev->bitmap = b;