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

* 'for-linus' of git://git.kernel.dk/linux-2.6-block:
  loop: mutex already unlocked in loop_clr_fd()
  cfq-iosched: don't let idling interfere with plugging
  block: remove unused REQ_UNPLUG
  cfq-iosched: kill two unused cfqq flags
  cfq-iosched: change dispatch logic to deal with single requests at the time
  mflash: initial support
  cciss: change to discover first memory BAR
  cciss: kernel scan thread for MSA2012
  cciss: fix residual count for block pc requests
  block: fix inconsistency in I/O stat accounting code
  block: elevator quiescing helpers

Documentation/blockdev/00-INDEX

@@ -8,6 +8,8 @@ cpqarray.txt
 	- info on using Compaq's SMART2 Intelligent Disk Array Controllers.
 floppy.txt
 	- notes and driver options for the floppy disk driver.
+mflash.txt
+	- info on mGine m(g)flash driver for linux.
 nbd.txt
 	- info on a TCP implementation of a network block device.
 paride.txt

Documentation/blockdev/mflash.txt

+This document describes m[g]flash support in linux.
+
+Contents
+  1. Overview
+  2. Reserved area configuration
+  3. Example of mflash platform driver registration
+
+1. Overview
+
+Mflash and gflash are embedded flash drive. The only difference is mflash is
+MCP(Multi Chip Package) device. These two device operate exactly same way.
+So the rest mflash repersents mflash and gflash altogether.
+
+Internally, mflash has nand flash and other hardware logics and supports
+2 different operation (ATA, IO) modes. ATA mode doesn't need any new
+driver and currently works well under standard IDE subsystem. Actually it's
+one chip SSD. IO mode is ATA-like custom mode for the host that doesn't have
+IDE interface.
+
+Followings are brief descriptions about IO mode.
+A. IO mode based on ATA protocol and uses some custom command. (read confirm,
+write confirm)
+B. IO mode uses SRAM bus interface.
+C. IO mode supports 4kB boot area, so host can boot from mflash.
+
+2. Reserved area configuration
+If host boot from mflash, usually needs raw area for boot loader image. All of
+the mflash's block device operation will be taken this value as start offset.
+Note that boot loader's size of reserved area and kernel configuration value
+must be same.
+
+3. Example of mflash platform driver registration
+Working mflash is very straight forward. Adding platform device stuff to board
+configuration file is all. Here is some pseudo example.
+
+static struct mg_drv_data mflash_drv_data = {
+	/* If you want to polling driver set to 1 */
+	.use_polling = 0,
+	/* device attribution */
+	.dev_attr = MG_BOOT_DEV
+};
+
+static struct resource mg_mflash_rsc[] = {
+	/* Base address of mflash */
+	[0] = {
+		.start = 0x08000000,
+		.end = 0x08000000 + SZ_64K - 1,
+		.flags = IORESOURCE_MEM
+	},
+	/* mflash interrupt pin */
+	[1] = {
+		.start = IRQ_GPIO(84),
+		.end = IRQ_GPIO(84),
+		.flags = IORESOURCE_IRQ
+	},
+	/* mflash reset pin */
+	[2] = {
+		.start = 43,
+		.end = 43,
+		.name = MG_RST_PIN,
+		.flags = IORESOURCE_IO
+	},
+	/* mflash reset-out pin
+	 * If you use mflash as storage device (i.e. other than MG_BOOT_DEV),
+	 * should assign this */
+	[3] = {
+		.start = 51,
+		.end = 51,
+		.name = MG_RSTOUT_PIN,
+		.flags = IORESOURCE_IO
+	}
+};
+
+static struct platform_device mflash_dev = {
+	.name = MG_DEV_NAME,
+	.id = -1,
+	.dev = {
+		.platform_data = &mflash_drv_data,
+	},
+	.num_resources = ARRAY_SIZE(mg_mflash_rsc),
+	.resource = mg_mflash_rsc
+};
+
+platform_device_register(&mflash_dev);

block/blk-core.c

@@ -64,12 +64,11 @@ static struct workqueue_struct *kblockd_workqueue;
 
 static void drive_stat_acct(struct request *rq, int new_io)
 {
-	struct gendisk *disk = rq->rq_disk;
 	struct hd_struct *part;
 	int rw = rq_data_dir(rq);
 	int cpu;
 
-	if (!blk_fs_request(rq) || !disk || !blk_do_io_stat(disk->queue))
+	if (!blk_fs_request(rq) || !blk_do_io_stat(rq))
 		return;
 
 	cpu = part_stat_lock();
@@ -1124,8 +1123,6 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 
 	if (bio_sync(bio))
 		req->cmd_flags |= REQ_RW_SYNC;
-	if (bio_unplug(bio))
-		req->cmd_flags |= REQ_UNPLUG;
 	if (bio_rw_meta(bio))
 		req->cmd_flags |= REQ_RW_META;
 	if (bio_noidle(bio))
@@ -1675,9 +1672,7 @@ EXPORT_SYMBOL(blkdev_dequeue_request);
 
 static void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
-	struct gendisk *disk = req->rq_disk;
-
-	if (!disk || !blk_do_io_stat(disk->queue))
+	if (!blk_do_io_stat(req))
 		return;
 
 	if (blk_fs_request(req)) {
@@ -1694,9 +1689,7 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes)
 
 static void blk_account_io_done(struct request *req)
 {
-	struct gendisk *disk = req->rq_disk;
-
-	if (!disk || !blk_do_io_stat(disk->queue))
+	if (!blk_do_io_stat(req))
 		return;
 
 	/*
@@ -1711,7 +1704,7 @@ static void blk_account_io_done(struct request *req)
 		int cpu;
 
 		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(disk, req->sector);
+		part = disk_map_sector_rcu(req->rq_disk, req->sector);
 
 		part_stat_inc(cpu, part, ios[rw]);
 		part_stat_add(cpu, part, ticks[rw], duration);

block/blk-merge.c

@@ -338,6 +338,22 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	return 1;
 }
 
+static void blk_account_io_merge(struct request *req)
+{
+	if (blk_do_io_stat(req)) {
+		struct hd_struct *part;
+		int cpu;
+
+		cpu = part_stat_lock();
+		part = disk_map_sector_rcu(req->rq_disk, req->sector);
+
+		part_round_stats(cpu, part);
+		part_dec_in_flight(part);
+
+		part_stat_unlock();
+	}
+}
+
 /*
  * Has to be called with the request spinlock acquired
  */
@@ -386,18 +402,7 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 
 	elv_merge_requests(q, req, next);
 
-	if (req->rq_disk) {
-		struct hd_struct *part;
-		int cpu;
-
-		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, req->sector);
-
-		part_round_stats(cpu, part);
-		part_dec_in_flight(part);
-
-		part_stat_unlock();
-	}
+	blk_account_io_merge(req);
 
 	req->ioprio = ioprio_best(req->ioprio, next->ioprio);
 	if (blk_rq_cpu_valid(next))

block/blk-sysfs.c

@@ -209,10 +209,14 @@ 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_quisce_start(q);
+
 	if (stats)
 		queue_flag_set(QUEUE_FLAG_IO_STAT, q);
 	else
 		queue_flag_clear(QUEUE_FLAG_IO_STAT, q);
+
+	elv_quisce_end(q);
 	spin_unlock_irq(q->queue_lock);
 
 	return ret;

block/blk.h

@@ -70,6 +70,10 @@ void blk_queue_congestion_threshold(struct request_queue *q);
 
 int blk_dev_init(void);
 
+void elv_quisce_start(struct request_queue *q);
+void elv_quisce_end(struct request_queue *q);
+
+
 /*
  * Return the threshold (number of used requests) at which the queue is
  * considered to be congested.  It include a little hysteresis to keep the
@@ -108,12 +112,14 @@ static inline int blk_cpu_to_group(int cpu)
 #endif
 }
 
-static inline int blk_do_io_stat(struct request_queue *q)
+static inline int blk_do_io_stat(struct request *rq)
 {
-	if (q)
-		return blk_queue_io_stat(q);
+	struct gendisk *disk = rq->rq_disk;
 
-	return 0;
+	if (!disk || !disk->queue)
+		return 0;
+
+	return blk_queue_io_stat(disk->queue) && (rq->cmd_flags & REQ_ELVPRIV);
 }
 
 #endif

block/cfq-iosched.c

@@ -160,6 +160,7 @@ struct cfq_queue {
 
 	unsigned long slice_end;
 	long slice_resid;
+	unsigned int slice_dispatch;
 
 	/* pending metadata requests */
 	int meta_pending;
@@ -176,13 +177,12 @@ struct cfq_queue {
 enum cfqq_state_flags {
 	CFQ_CFQQ_FLAG_on_rr = 0,	/* on round-robin busy list */
 	CFQ_CFQQ_FLAG_wait_request,	/* waiting for a request */
+	CFQ_CFQQ_FLAG_must_dispatch,	/* must be allowed a dispatch */
 	CFQ_CFQQ_FLAG_must_alloc,	/* must be allowed rq alloc */
 	CFQ_CFQQ_FLAG_must_alloc_slice,	/* per-slice must_alloc flag */
-	CFQ_CFQQ_FLAG_must_dispatch,	/* must dispatch, even if expired */
 	CFQ_CFQQ_FLAG_fifo_expire,	/* FIFO checked in this slice */
 	CFQ_CFQQ_FLAG_idle_window,	/* slice idling enabled */
 	CFQ_CFQQ_FLAG_prio_changed,	/* task priority has changed */
-	CFQ_CFQQ_FLAG_queue_new,	/* queue never been serviced */
 	CFQ_CFQQ_FLAG_slice_new,	/* no requests dispatched in slice */
 	CFQ_CFQQ_FLAG_sync,		/* synchronous queue */
 };
@@ -203,13 +203,12 @@ static inline int cfq_cfqq_##name(const struct cfq_queue *cfqq)		\
 
 CFQ_CFQQ_FNS(on_rr);
 CFQ_CFQQ_FNS(wait_request);
+CFQ_CFQQ_FNS(must_dispatch);
 CFQ_CFQQ_FNS(must_alloc);
 CFQ_CFQQ_FNS(must_alloc_slice);
-CFQ_CFQQ_FNS(must_dispatch);
 CFQ_CFQQ_FNS(fifo_expire);
 CFQ_CFQQ_FNS(idle_window);
 CFQ_CFQQ_FNS(prio_changed);
-CFQ_CFQQ_FNS(queue_new);
 CFQ_CFQQ_FNS(slice_new);
 CFQ_CFQQ_FNS(sync);
 #undef CFQ_CFQQ_FNS
@@ -774,10 +773,15 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd,
 	if (cfqq) {
 		cfq_log_cfqq(cfqd, cfqq, "set_active");
 		cfqq->slice_end = 0;
+		cfqq->slice_dispatch = 0;
+
+		cfq_clear_cfqq_wait_request(cfqq);
+		cfq_clear_cfqq_must_dispatch(cfqq);
 		cfq_clear_cfqq_must_alloc_slice(cfqq);
 		cfq_clear_cfqq_fifo_expire(cfqq);
 		cfq_mark_cfqq_slice_new(cfqq);
-		cfq_clear_cfqq_queue_new(cfqq);
+
+		del_timer(&cfqd->idle_slice_timer);
 	}
 
 	cfqd->active_queue = cfqq;
@@ -795,7 +799,6 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	if (cfq_cfqq_wait_request(cfqq))
 		del_timer(&cfqd->idle_slice_timer);
 
-	cfq_clear_cfqq_must_dispatch(cfqq);
 	cfq_clear_cfqq_wait_request(cfqq);
 
 	/*
@@ -924,7 +927,6 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	    (sample_valid(cic->ttime_samples) && cic->ttime_mean > 2))
 		return;
 
-	cfq_mark_cfqq_must_dispatch(cfqq);
 	cfq_mark_cfqq_wait_request(cfqq);
 
 	/*
@@ -1010,7 +1012,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 	/*
 	 * The active queue has run out of time, expire it and select new.
 	 */
-	if (cfq_slice_used(cfqq))
+	if (cfq_slice_used(cfqq) && !cfq_cfqq_must_dispatch(cfqq))
 		goto expire;
 
 	/*
@@ -1053,66 +1055,6 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 	return cfqq;
 }
 
-/*
- * Dispatch some requests from cfqq, moving them to the request queue
- * dispatch list.
- */
-static int
-__cfq_dispatch_requests(struct cfq_data *cfqd, struct cfq_queue *cfqq,
-			int max_dispatch)
-{
-	int dispatched = 0;
-
-	BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list));
-
-	do {
-		struct request *rq;
-
-		/*
-		 * follow expired path, else get first next available
-		 */
-		rq = cfq_check_fifo(cfqq);
-		if (rq == NULL)
-			rq = cfqq->next_rq;
-
-		/*
-		 * finally, insert request into driver dispatch list
-		 */
-		cfq_dispatch_insert(cfqd->queue, rq);
-
-		dispatched++;
-
-		if (!cfqd->active_cic) {
-			atomic_inc(&RQ_CIC(rq)->ioc->refcount);
-			cfqd->active_cic = RQ_CIC(rq);
-		}
-
-		if (RB_EMPTY_ROOT(&cfqq->sort_list))
-			break;
-
-		/*
-		 * If there is a non-empty RT cfqq waiting for current
-		 * cfqq's timeslice to complete, pre-empt this cfqq
-		 */
-		if (!cfq_class_rt(cfqq) && cfqd->busy_rt_queues)
-			break;
-
-	} while (dispatched < max_dispatch);
-
-	/*
-	 * expire an async queue immediately if it has used up its slice. idle
-	 * queue always expire after 1 dispatch round.
-	 */
-	if (cfqd->busy_queues > 1 && ((!cfq_cfqq_sync(cfqq) &&
-	    dispatched >= cfq_prio_to_maxrq(cfqd, cfqq)) ||
-	    cfq_class_idle(cfqq))) {
-		cfqq->slice_end = jiffies + 1;
-		cfq_slice_expired(cfqd, 0);
-	}
-
-	return dispatched;
-}
-
 static int __cfq_forced_dispatch_cfqq(struct cfq_queue *cfqq)
 {
 	int dispatched = 0;
@@ -1146,11 +1088,45 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd)
 	return dispatched;
 }
 
+/*
+ * Dispatch a request from cfqq, moving them to the request queue
+ * dispatch list.
+ */
+static void cfq_dispatch_request(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	struct request *rq;
+
+	BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list));
+
+	/*
+	 * follow expired path, else get first next available
+	 */
+	rq = cfq_check_fifo(cfqq);
+	if (!rq)
+		rq = cfqq->next_rq;
+
+	/*
+	 * insert request into driver dispatch list
+	 */
+	cfq_dispatch_insert(cfqd->queue, rq);
+
+	if (!cfqd->active_cic) {
+		struct cfq_io_context *cic = RQ_CIC(rq);
+
+		atomic_inc(&cic->ioc->refcount);
+		cfqd->active_cic = cic;
+	}
+}
+
+/*
+ * Find the cfqq that we need to service and move a request from that to the
+ * dispatch list
+ */
 static int cfq_dispatch_requests(struct request_queue *q, int force)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct cfq_queue *cfqq;
-	int dispatched;
+	unsigned int max_dispatch;
 
 	if (!cfqd->busy_queues)
 		return 0;
@@ -1158,29 +1134,63 @@ static int cfq_dispatch_requests(struct request_queue *q, int force)
 	if (unlikely(force))
 		return cfq_forced_dispatch(cfqd);
 
-	dispatched = 0;
-	while ((cfqq = cfq_select_queue(cfqd)) != NULL) {
-		int max_dispatch;
+	cfqq = cfq_select_queue(cfqd);
+	if (!cfqq)
+		return 0;
+
+	/*
+	 * If this is an async queue and we have sync IO in flight, let it wait
+	 */
+	if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq))
+		return 0;
+
+	max_dispatch = cfqd->cfq_quantum;
+	if (cfq_class_idle(cfqq))
+		max_dispatch = 1;
 
-		max_dispatch = cfqd->cfq_quantum;
+	/*
+	 * Does this cfqq already have too much IO in flight?
+	 */
+	if (cfqq->dispatched >= max_dispatch) {
+		/*
+		 * idle queue must always only have a single IO in flight
+		 */
 		if (cfq_class_idle(cfqq))
-			max_dispatch = 1;
+			return 0;
 
-		if (cfqq->dispatched >= max_dispatch && cfqd->busy_queues > 1)
-			break;
+		/*
+		 * We have other queues, don't allow more IO from this one
+		 */
+		if (cfqd->busy_queues > 1)
+			return 0;
 
-		if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq))
-			break;
+		/*
+		 * we are the only queue, allow up to 4 times of 'quantum'
+		 */
+		if (cfqq->dispatched >= 4 * max_dispatch)
+			return 0;
+	}
 
-		cfq_clear_cfqq_must_dispatch(cfqq);
-		cfq_clear_cfqq_wait_request(cfqq);
-		del_timer(&cfqd->idle_slice_timer);
+	/*
+	 * Dispatch a request from this cfqq
+	 */
+	cfq_dispatch_request(cfqd, cfqq);
+	cfqq->slice_dispatch++;
+	cfq_clear_cfqq_must_dispatch(cfqq);
 
-		dispatched += __cfq_dispatch_requests(cfqd, cfqq, max_dispatch);
+	/*
+	 * expire an async queue immediately if it has used up its slice. idle
+	 * queue always expire after 1 dispatch round.
+	 */
+	if (cfqd->busy_queues > 1 && ((!cfq_cfqq_sync(cfqq) &&
+	    cfqq->slice_dispatch >= cfq_prio_to_maxrq(cfqd, cfqq)) ||
+	    cfq_class_idle(cfqq))) {
+		cfqq->slice_end = jiffies + 1;
+		cfq_slice_expired(cfqd, 0);
 	}
 
-	cfq_log(cfqd, "dispatched=%d", dispatched);
-	return dispatched;
+	cfq_log(cfqd, "dispatched a request");
+	return 1;
 }
 
 /*
@@ -1506,7 +1516,6 @@ cfq_find_alloc_queue(struct cfq_data *cfqd, int is_sync,
 		cfqq->cfqd = cfqd;
 
 		cfq_mark_cfqq_prio_changed(cfqq);
-		cfq_mark_cfqq_queue_new(cfqq);
 
 		cfq_init_prio_data(cfqq, ioc);
 
@@ -1893,15 +1902,13 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 
 	if (cfqq == cfqd->active_queue) {
 		/*
-		 * if we are waiting for a request for this queue, let it rip
-		 * immediately and flag that we must not expire this queue
-		 * just now
+		 * Remember that we saw a request from this process, but
+		 * don't start queuing just yet. Otherwise we risk seeing lots
+		 * of tiny requests, because we disrupt the normal plugging
+		 * and merging.
 		 */
-		if (cfq_cfqq_wait_request(cfqq)) {
+		if (cfq_cfqq_wait_request(cfqq))
 			cfq_mark_cfqq_must_dispatch(cfqq);
-			del_timer(&cfqd->idle_slice_timer);
-			blk_start_queueing(cfqd->queue);
-		}
 	} else if (cfq_should_preempt(cfqd, cfqq, rq)) {
 		/*
 		 * not the active queue - expire current slice if it is
@@ -1910,7 +1917,6 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		 * this new queue is RT and the current one is BE
 		 */
 		cfq_preempt_queue(cfqd, cfqq);
-		cfq_mark_cfqq_must_dispatch(cfqq);
 		blk_start_queueing(cfqd->queue);
 	}
 }
@@ -2171,6 +2177,12 @@ static void cfq_idle_slice_timer(unsigned long data)
 	if (cfqq) {
 		timed_out = 0;
 
+		/*
+		 * We saw a request before the queue expired, let it through
+		 */
+		if (cfq_cfqq_must_dispatch(cfqq))
+			goto out_kick;
+
 		/*
 		 * expired
 		 */
@@ -2187,10 +2199,8 @@ static void cfq_idle_slice_timer(unsigned long data)
 		/*
 		 * not expired and it has a request pending, let it dispatch
 		 */
-		if (!RB_EMPTY_ROOT(&cfqq->sort_list)) {
-			cfq_mark_cfqq_must_dispatch(cfqq);
+		if (!RB_EMPTY_ROOT(&cfqq->sort_list))
 			goto out_kick;
-		}
 	}
 expire:
 	cfq_slice_expired(cfqd, timed_out);

block/elevator.c

@@ -573,7 +573,7 @@ void elv_requeue_request(struct request_queue *q, struct request *rq)
 	elv_insert(q, rq, ELEVATOR_INSERT_REQUEUE);
 }
 
-static void elv_drain_elevator(struct request_queue *q)
+void elv_drain_elevator(struct request_queue *q)
 {
 	static int printed;
 	while (q->elevator->ops->elevator_dispatch_fn(q, 1))
@@ -587,6 +587,31 @@ static void elv_drain_elevator(struct request_queue *q)
 	}
 }
 
+/*
+ * Call with queue lock held, interrupts disabled
+ */
+void elv_quisce_start(struct request_queue *q)
+{
+	queue_flag_set(QUEUE_FLAG_ELVSWITCH, q);
+
+	/*
+	 * make sure we don't have any requests in flight
+	 */
+	elv_drain_elevator(q);
+	while (q->rq.elvpriv) {
+		blk_start_queueing(q);
+		spin_unlock_irq(q->queue_lock);
+		msleep(10);
+		spin_lock_irq(q->queue_lock);
+		elv_drain_elevator(q);
+	}
+}
+
+void elv_quisce_end(struct request_queue *q)
+{
+	queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
+}
+
 void elv_insert(struct request_queue *q, struct request *rq, int where)
 {
 	struct list_head *pos;
@@ -1101,18 +1126,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	 * Turn on BYPASS and drain all requests w/ elevator private data
 	 */
 	spin_lock_irq(q->queue_lock);
-
-	queue_flag_set(QUEUE_FLAG_ELVSWITCH, q);
-
-	elv_drain_elevator(q);
-
-	while (q->rq.elvpriv) {
-		blk_start_queueing(q);
-		spin_unlock_irq(q->queue_lock);
-		msleep(10);
-		spin_lock_irq(q->queue_lock);
-		elv_drain_elevator(q);
-	}
+	elv_quisce_start(q);
 
 	/*
 	 * Remember old elevator.
@@ -1136,7 +1150,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	 */
 	elevator_exit(old_elevator);
 	spin_lock_irq(q->queue_lock);
-	queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
+	elv_quisce_end(q);
 	spin_unlock_irq(q->queue_lock);
 
 	blk_add_trace_msg(q, "elv switch: %s", e->elevator_type->elevator_name);

drivers/block/Kconfig

@@ -410,6 +410,23 @@ config ATA_OVER_ETH
 	This driver provides Support for ATA over Ethernet block
 	devices like the Coraid EtherDrive (R) Storage Blade.
 
+config MG_DISK
+	tristate "mGine mflash, gflash support"
+	depends on ARM && ATA && GPIOLIB
+	help
+	  mGine mFlash(gFlash) block device driver
+
+config MG_DISK_RES
+	int "Size of reserved area before MBR"
+	depends on MG_DISK
+	default 0
+	help
+	  Define size of reserved area that usually used for boot. Unit is KB.
+	  All of the block device operation will be taken this value as start
+	  offset
+	  Examples:
+			1024 => 1 MB
+
 config SUNVDC
 	tristate "Sun Virtual Disk Client support"
 	depends on SUN_LDOMS

drivers/block/Makefile

@@ -21,6 +21,7 @@ obj-$(CONFIG_BLK_CPQ_CISS_DA)  += cciss.o
 obj-$(CONFIG_BLK_DEV_DAC960)	+= DAC960.o
 obj-$(CONFIG_XILINX_SYSACE)	+= xsysace.o
 obj-$(CONFIG_CDROM_PKTCDVD)	+= pktcdvd.o
+obj-$(CONFIG_MG_DISK)		+= mg_disk.o
 obj-$(CONFIG_SUNVDC)		+= sunvdc.o
 
 obj-$(CONFIG_BLK_DEV_UMEM)	+= umem.o

drivers/block/cciss.c

@@ -51,6 +51,7 @@
 #include <scsi/scsi_ioctl.h>
 #include <linux/cdrom.h>
 #include <linux/scatterlist.h>
+#include <linux/kthread.h>
 
 #define CCISS_DRIVER_VERSION(maj,min,submin) ((maj<<16)|(min<<8)|(submin))
 #define DRIVER_NAME "HP CISS Driver (v 3.6.20)"
@@ -186,6 +187,8 @@ static int sendcmd_withirq(__u8 cmd, int ctlr, void *buff, size_t size,
 			   __u8 page_code, int cmd_type);
 
 static void fail_all_cmds(unsigned long ctlr);
+static int scan_thread(void *data);
+static int check_for_unit_attention(ctlr_info_t *h, CommandList_struct *c);
 
 #ifdef CONFIG_PROC_FS
 static void cciss_procinit(int i);
@@ -735,6 +738,12 @@ static int cciss_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return 0;
 }
 
+static void check_ioctl_unit_attention(ctlr_info_t *host, CommandList_struct *c)
+{
+	if (c->err_info->CommandStatus == CMD_TARGET_STATUS &&
+			c->err_info->ScsiStatus != SAM_STAT_CHECK_CONDITION)
+		(void)check_for_unit_attention(host, c);
+}
 /*
  * ioctl
  */
@@ -1029,6 +1038,8 @@ static int cciss_ioctl(struct block_device *bdev, fmode_t mode,
 					 iocommand.buf_size,
 					 PCI_DMA_BIDIRECTIONAL);
 
+			check_ioctl_unit_attention(host, c);
+
 			/* Copy the error information out */
 			iocommand.error_info = *(c->err_info);
 			if (copy_to_user
@@ -1180,6 +1191,7 @@ static int cciss_ioctl(struct block_device *bdev, fmode_t mode,
 					(dma_addr_t) temp64.val, buff_size[i],
 					PCI_DMA_BIDIRECTIONAL);
 			}
+			check_ioctl_unit_attention(host, c);
 			/* Copy the error information out */
 			ioc->error_info = *(c->err_info);
 			if (copy_to_user(argp, ioc, sizeof(*ioc))) {
@@ -1287,6 +1299,7 @@ static void cciss_softirq_done(struct request *rq)
 {
 	CommandList_struct *cmd = rq->completion_data;
 	ctlr_info_t *h = hba[cmd->ctlr];
+	unsigned int nr_bytes;
 	unsigned long flags;
 	u64bit temp64;
 	int i, ddir;
@@ -1308,7 +1321,14 @@ static void cciss_softirq_done(struct request *rq)
 	printk("Done with %p\n", rq);
 #endif				/* CCISS_DEBUG */
 
-	if (blk_end_request(rq, (rq->errors == 0) ? 0 : -EIO, blk_rq_bytes(rq)))
+	/*
+	 * Store the full size and set the residual count for pc requests
+	 */
+	nr_bytes = blk_rq_bytes(rq);
+	if (blk_pc_request(rq))
+		rq->data_len = cmd->err_info->ResidualCnt;
+
+	if (blk_end_request(rq, (rq->errors == 0) ? 0 : -EIO, nr_bytes))
 		BUG();
 
 	spin_lock_irqsave(&h->lock, flags);
@@ -2585,12 +2605,14 @@ static inline unsigned int make_status_bytes(unsigned int scsi_status_byte,
 		((driver_byte & 0xff) << 24);
 }
 
-static inline int evaluate_target_status(CommandList_struct *cmd)
+static inline int evaluate_target_status(ctlr_info_t *h,
+			CommandList_struct *cmd, int *retry_cmd)
 {
 	unsigned char sense_key;
 	unsigned char status_byte, msg_byte, host_byte, driver_byte;
 	int error_value;
 
+	*retry_cmd = 0;
 	/* If we get in here, it means we got "target status", that is, scsi status */
 	status_byte = cmd->err_info->ScsiStatus;
 	driver_byte = DRIVER_OK;
@@ -2618,6 +2640,11 @@ static inline int evaluate_target_status(CommandList_struct *cmd)
 	if (((sense_key == 0x0) || (sense_key == 0x1)) && !blk_pc_request(cmd->rq))
 		error_value = 0;
 
+	if (check_for_unit_attention(h, cmd)) {
+		*retry_cmd = !blk_pc_request(cmd->rq);
+		return 0;
+	}
+
 	if (!blk_pc_request(cmd->rq)) { /* Not SG_IO or similar? */
 		if (error_value != 0)
 			printk(KERN_WARNING "cciss: cmd %p has CHECK CONDITION"
@@ -2657,7 +2684,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 
 	switch (cmd->err_info->CommandStatus) {
 	case CMD_TARGET_STATUS:
-		rq->errors = evaluate_target_status(cmd);
+		rq->errors = evaluate_target_status(h, cmd, &retry_cmd);
 		break;
 	case CMD_DATA_UNDERRUN:
 		if (blk_fs_request(cmd->rq)) {
@@ -3008,6 +3035,63 @@ static irqreturn_t do_cciss_intr(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static int scan_thread(void *data)
+{
+	ctlr_info_t *h = data;
+	int rc;
+	DECLARE_COMPLETION_ONSTACK(wait);
+	h->rescan_wait = &wait;
+
+	for (;;) {
+		rc = wait_for_completion_interruptible(&wait);
+		if (kthread_should_stop())
+			break;
+		if (!rc)
+			rebuild_lun_table(h, 0);
+	}
+	return 0;
+}
+
+static int check_for_unit_attention(ctlr_info_t *h, CommandList_struct *c)
+{
+	if (c->err_info->SenseInfo[2] != UNIT_ATTENTION)
+		return 0;
+
+	switch (c->err_info->SenseInfo[12]) {
+	case STATE_CHANGED:
+		printk(KERN_WARNING "cciss%d: a state change "
+			"detected, command retried\n", h->ctlr);
+		return 1;
+	break;
+	case LUN_FAILED:
+		printk(KERN_WARNING "cciss%d: LUN failure "
+			"detected, action required\n", h->ctlr);
+		return 1;
+	break;
+	case REPORT_LUNS_CHANGED:
+		printk(KERN_WARNING "cciss%d: report LUN data "
+			"changed\n", h->ctlr);
+		if (h->rescan_wait)
+			complete(h->rescan_wait);
+		return 1;
+	break;
+	case POWER_OR_RESET:
+		printk(KERN_WARNING "cciss%d: a power on "
+			"or device reset detected\n", h->ctlr);
+		return 1;
+	break;
+	case UNIT_ATTENTION_CLEARED:
+		printk(KERN_WARNING "cciss%d: unit attention "
+		    "cleared by another initiator\n", h->ctlr);
+		return 1;
+	break;
+	default:
+		printk(KERN_WARNING "cciss%d: unknown "
+			"unit attention detected\n", h->ctlr);
+				return 1;
+	}
+}
+
 /*
  *  We cannot read the structure directly, for portability we must use
  *   the io functions.
@@ -3181,12 +3265,21 @@ static int __devinit cciss_pci_init(ctlr_info_t *c, struct pci_dev *pdev)
  */
 	cciss_interrupt_mode(c, pdev, board_id);
 
-	/*
-	 * Memory base addr is first addr , the second points to the config
-	 *   table
-	 */
+	/* find the memory BAR */
+	for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
+		if (pci_resource_flags(pdev, i) & IORESOURCE_MEM)
+			break;
+	}
+	if (i == DEVICE_COUNT_RESOURCE) {
+		printk(KERN_WARNING "cciss: No memory BAR found\n");
+		err = -ENODEV;
+		goto err_out_free_res;
+	}
+
+	c->paddr = pci_resource_start(pdev, i); /* addressing mode bits
+						 * already removed
+						 */
 
-	c->paddr = pci_resource_start(pdev, 0);	/* addressing mode bits already removed */
 #ifdef CCISS_DEBUG
 	printk("address 0 = %lx\n", c->paddr);
 #endif				/* CCISS_DEBUG */
@@ -3753,6 +3846,11 @@ static int __devinit cciss_init_one(struct pci_dev *pdev,
 	hba[i]->busy_initializing = 0;
 
 	rebuild_lun_table(hba[i], 1);
+	hba[i]->cciss_scan_thread = kthread_run(scan_thread, hba[i],
+				"cciss_scan%02d", i);
+	if (IS_ERR(hba[i]->cciss_scan_thread))
+		return PTR_ERR(hba[i]->cciss_scan_thread);
+
 	return 1;
 
 clean4:
@@ -3828,6 +3926,7 @@ static void __devexit cciss_remove_one(struct pci_dev *pdev)
 		printk(KERN_ERR "cciss: Unable to remove device \n");
 		return;
 	}
+
 	tmp_ptr = pci_get_drvdata(pdev);
 	i = tmp_ptr->ctlr;
 	if (hba[i] == NULL) {
@@ -3836,6 +3935,8 @@ static void __devexit cciss_remove_one(struct pci_dev *pdev)
 		return;
 	}
 
+	kthread_stop(hba[i]->cciss_scan_thread);
+
 	remove_proc_entry(hba[i]->devname, proc_cciss);
 	unregister_blkdev(hba[i]->major, hba[i]->devname);
 

drivers/block/cciss.h

@@ -121,6 +121,8 @@ struct ctlr_info
 	struct sendcmd_reject_list scsi_rejects;
 #endif
 	unsigned char alive;
+	struct completion *rescan_wait;
+	struct task_struct *cciss_scan_thread;
 };
 
 /*  Defining the diffent access_menthods */

drivers/block/cciss_cmd.h

@@ -25,6 +25,29 @@
 #define CMD_TIMEOUT             0x000B
 #define CMD_UNABORTABLE		0x000C
 
+/* Unit Attentions ASC's as defined for the MSA2012sa */
+#define POWER_OR_RESET			0x29
+#define STATE_CHANGED			0x2a
+#define UNIT_ATTENTION_CLEARED		0x2f
+#define LUN_FAILED			0x3e
+#define REPORT_LUNS_CHANGED		0x3f
+
+/* Unit Attentions ASCQ's as defined for the MSA2012sa */
+
+	/* These ASCQ's defined for ASC = POWER_OR_RESET */
+#define POWER_ON_RESET			0x00
+#define POWER_ON_REBOOT			0x01
+#define SCSI_BUS_RESET			0x02
+#define MSA_TARGET_RESET		0x03
+#define CONTROLLER_FAILOVER		0x04
+#define TRANSCEIVER_SE			0x05
+#define TRANSCEIVER_LVD			0x06
+
+	/* These ASCQ's defined for ASC = STATE_CHANGED */
+#define RESERVATION_PREEMPTED		0x03
+#define ASYM_ACCESS_CHANGED		0x06
+#define LUN_CAPACITY_CHANGED		0x09
+
 //transfer direction
 #define XFER_NONE               0x00
 #define XFER_WRITE              0x01

drivers/block/loop.c

@@ -1431,6 +1431,7 @@ static int lo_open(struct block_device *bdev, fmode_t mode)
 static int lo_release(struct gendisk *disk, fmode_t mode)
 {
 	struct loop_device *lo = disk->private_data;
+	int err;
 
 	mutex_lock(&lo->lo_ctl_mutex);
 
@@ -1442,7 +1443,9 @@ static int lo_release(struct gendisk *disk, fmode_t mode)
 		 * In autoclear mode, stop the loop thread
 		 * and remove configuration after last close.
 		 */
-		loop_clr_fd(lo, NULL);
+		err = loop_clr_fd(lo, NULL);
+		if (!err)
+			goto out_unlocked;
 	} else {
 		/*
 		 * Otherwise keep thread (if running) and config,
@@ -1453,7 +1456,7 @@ static int lo_release(struct gendisk *disk, fmode_t mode)
 
 out:
 	mutex_unlock(&lo->lo_ctl_mutex);
-
+out_unlocked:
 	return 0;
 }
 

include/linux/blkdev.h

@@ -117,7 +117,6 @@ enum rq_flag_bits {
 	__REQ_RW_META,		/* metadata io request */
 	__REQ_COPY_USER,	/* contains copies of user pages */
 	__REQ_INTEGRITY,	/* integrity metadata has been remapped */
-	__REQ_UNPLUG,		/* unplug queue on submission */
 	__REQ_NOIDLE,		/* Don't anticipate more IO after this one */
 	__REQ_NR_BITS,		/* stops here */
 };
@@ -145,7 +144,6 @@ enum rq_flag_bits {
 #define REQ_RW_META	(1 << __REQ_RW_META)
 #define REQ_COPY_USER	(1 << __REQ_COPY_USER)
 #define REQ_INTEGRITY	(1 << __REQ_INTEGRITY)
-#define REQ_UNPLUG	(1 << __REQ_UNPLUG)
 #define REQ_NOIDLE	(1 << __REQ_NOIDLE)
 
 #define BLK_MAX_CDB	16

include/linux/elevator.h

@@ -116,6 +116,7 @@ extern void elv_abort_queue(struct request_queue *);
 extern void elv_completed_request(struct request_queue *, struct request *);
 extern int elv_set_request(struct request_queue *, struct request *, gfp_t);
 extern void elv_put_request(struct request_queue *, struct request *);
+extern void elv_drain_elevator(struct request_queue *);
 
 /*
  * io scheduler registration

include/linux/mg_disk.h

+/*
+ *  include/linux/mg_disk.c
+ *
+ *  Support for the mGine m[g]flash IO mode.
+ *  Based on legacy hd.c
+ *
+ * (c) 2008 mGine Co.,LTD
+ * (c) 2008 unsik Kim <donari75@gmail.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ */
+
+#ifndef __MG_DISK_H__
+#define __MG_DISK_H__
+
+#include <linux/blkdev.h>
+#include <linux/ata.h>
+
+/* name for block device */
+#define MG_DISK_NAME "mgd"
+/* name for platform device */
+#define MG_DEV_NAME "mg_disk"
+
+#define MG_DISK_MAJ 0
+#define MG_DISK_MAX_PART 16
+#define MG_SECTOR_SIZE 512
+#define MG_MAX_SECTS 256
+
+/* Register offsets */
+#define MG_BUFF_OFFSET			0x8000
+#define MG_STORAGE_BUFFER_SIZE		0x200
+#define MG_REG_OFFSET			0xC000
+#define MG_REG_FEATURE			(MG_REG_OFFSET + 2)	/* write case */
+#define MG_REG_ERROR			(MG_REG_OFFSET + 2)	/* read case */
+#define MG_REG_SECT_CNT			(MG_REG_OFFSET + 4)
+#define MG_REG_SECT_NUM			(MG_REG_OFFSET + 6)
+#define MG_REG_CYL_LOW			(MG_REG_OFFSET + 8)
+#define MG_REG_CYL_HIGH			(MG_REG_OFFSET + 0xA)
+#define MG_REG_DRV_HEAD			(MG_REG_OFFSET + 0xC)
+#define MG_REG_COMMAND			(MG_REG_OFFSET + 0xE)	/* write case */
+#define MG_REG_STATUS			(MG_REG_OFFSET + 0xE)	/* read  case */
+#define MG_REG_DRV_CTRL			(MG_REG_OFFSET + 0x10)
+#define MG_REG_BURST_CTRL		(MG_REG_OFFSET + 0x12)
+
+/* "Drive Select/Head Register" bit values */
+#define MG_REG_HEAD_MUST_BE_ON		0xA0 /* These 2 bits are always on */
+#define MG_REG_HEAD_DRIVE_MASTER	(0x00 | MG_REG_HEAD_MUST_BE_ON)
+#define MG_REG_HEAD_DRIVE_SLAVE		(0x10 | MG_REG_HEAD_MUST_BE_ON)
+#define MG_REG_HEAD_LBA_MODE		(0x40 | MG_REG_HEAD_MUST_BE_ON)
+
+
+/* "Device Control Register" bit values */
+#define MG_REG_CTRL_INTR_ENABLE			0x0
+#define MG_REG_CTRL_INTR_DISABLE		(0x1<<1)
+#define MG_REG_CTRL_RESET			(0x1<<2)
+#define MG_REG_CTRL_INTR_POLA_ACTIVE_HIGH	0x0
+#define MG_REG_CTRL_INTR_POLA_ACTIVE_LOW	(0x1<<4)
+#define MG_REG_CTRL_DPD_POLA_ACTIVE_LOW		0x0
+#define MG_REG_CTRL_DPD_POLA_ACTIVE_HIGH	(0x1<<5)
+#define MG_REG_CTRL_DPD_DISABLE			0x0
+#define MG_REG_CTRL_DPD_ENABLE			(0x1<<6)
+
+/* Status register bit */
+/* error bit in status register */
+#define MG_REG_STATUS_BIT_ERROR			0x01
+/* corrected error in status register */
+#define MG_REG_STATUS_BIT_CORRECTED_ERROR	0x04
+/* data request bit in status register */
+#define MG_REG_STATUS_BIT_DATA_REQ		0x08
+/* DSC - Drive Seek Complete */
+#define MG_REG_STATUS_BIT_SEEK_DONE		0x10
+/* DWF - Drive Write Fault */
+#define MG_REG_STATUS_BIT_WRITE_FAULT		0x20
+#define MG_REG_STATUS_BIT_READY			0x40
+#define MG_REG_STATUS_BIT_BUSY			0x80
+
+/* handy status */
+#define MG_STAT_READY	(MG_REG_STATUS_BIT_READY | MG_REG_STATUS_BIT_SEEK_DONE)
+#define MG_READY_OK(s)	(((s) & (MG_STAT_READY | \
+				(MG_REG_STATUS_BIT_BUSY | \
+				 MG_REG_STATUS_BIT_WRITE_FAULT | \
+				 MG_REG_STATUS_BIT_ERROR))) == MG_STAT_READY)
+
+/* Error register */
+#define MG_REG_ERR_AMNF		0x01
+#define MG_REG_ERR_ABRT		0x04
+#define MG_REG_ERR_IDNF		0x10
+#define MG_REG_ERR_UNC		0x40
+#define MG_REG_ERR_BBK		0x80
+
+/* error code for others */
+#define MG_ERR_NONE		0
+#define MG_ERR_TIMEOUT		0x100
+#define MG_ERR_INIT_STAT	0x101
+#define MG_ERR_TRANSLATION	0x102
+#define MG_ERR_CTRL_RST		0x103
+#define MG_ERR_INV_STAT		0x104
+#define MG_ERR_RSTOUT		0x105
+
+#define MG_MAX_ERRORS	6	/* Max read/write errors */
+
+/* command */
+#define MG_CMD_RD 0x20
+#define MG_CMD_WR 0x30
+#define MG_CMD_SLEEP 0x99
+#define MG_CMD_WAKEUP 0xC3
+#define MG_CMD_ID 0xEC
+#define MG_CMD_WR_CONF 0x3C
+#define MG_CMD_RD_CONF 0x40
+
+/* operation mode */
+#define MG_OP_CASCADE (1 << 0)
+#define MG_OP_CASCADE_SYNC_RD (1 << 1)
+#define MG_OP_CASCADE_SYNC_WR (1 << 2)
+#define MG_OP_INTERLEAVE (1 << 3)
+
+/* synchronous */
+#define MG_BURST_LAT_4 (3 << 4)
+#define MG_BURST_LAT_5 (4 << 4)
+#define MG_BURST_LAT_6 (5 << 4)
+#define MG_BURST_LAT_7 (6 << 4)
+#define MG_BURST_LAT_8 (7 << 4)
+#define MG_BURST_LEN_4 (1 << 1)
+#define MG_BURST_LEN_8 (2 << 1)
+#define MG_BURST_LEN_16 (3 << 1)
+#define MG_BURST_LEN_32 (4 << 1)
+#define MG_BURST_LEN_CONT (0 << 1)
+
+/* timeout value (unit: ms) */
+#define MG_TMAX_CONF_TO_CMD	1
+#define MG_TMAX_WAIT_RD_DRQ	10
+#define MG_TMAX_WAIT_WR_DRQ	500
+#define MG_TMAX_RST_TO_BUSY	10
+#define MG_TMAX_HDRST_TO_RDY	500
+#define MG_TMAX_SWRST_TO_RDY	500
+#define MG_TMAX_RSTOUT		3000
+
+/* device attribution */
+/* use mflash as boot device */
+#define MG_BOOT_DEV		(1 << 0)
+/* use mflash as storage device */
+#define MG_STORAGE_DEV		(1 << 1)
+/* same as MG_STORAGE_DEV, but bootloader already done reset sequence */
+#define MG_STORAGE_DEV_SKIP_RST	(1 << 2)
+
+#define MG_DEV_MASK (MG_BOOT_DEV | MG_STORAGE_DEV | MG_STORAGE_DEV_SKIP_RST)
+
+/* names of GPIO resource */
+#define MG_RST_PIN	"mg_rst"
+/* except MG_BOOT_DEV, reset-out pin should be assigned */
+#define MG_RSTOUT_PIN	"mg_rstout"
+
+/* private driver data */
+struct mg_drv_data {
+	/* disk resource */
+	u32 use_polling;
+
+	/* device attribution */
+	u32 dev_attr;
+
+	/* internally used */
+	struct mg_host *host;
+};
+
+/* main structure for mflash driver */
+struct mg_host {
+	struct device *dev;
+
+	struct request_queue *breq;
+	spinlock_t lock;
+	struct gendisk *gd;
+
+	struct timer_list timer;
+	void (*mg_do_intr) (struct mg_host *);
+
+	u16 id[ATA_ID_WORDS];
+
+	u16 cyls;
+	u16 heads;
+	u16 sectors;
+	u32 n_sectors;
+	u32 nres_sectors;
+
+	void __iomem *dev_base;
+	unsigned int irq;
+	unsigned int rst;
+	unsigned int rstout;
+
+	u32 major;
+	u32 error;
+};
+
+/*
+ * Debugging macro and defines
+ */
+#undef DO_MG_DEBUG
+#ifdef DO_MG_DEBUG
+#  define MG_DBG(fmt, args...) \
+	printk(KERN_DEBUG "%s:%d "fmt, __func__, __LINE__, ##args)
+#else /* CONFIG_MG_DEBUG */
+#  define MG_DBG(fmt, args...) do { } while (0)
+#endif /* CONFIG_MG_DEBUG */
+
+#endif