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

Pull block bits from Jens Axboe:
 "As vacation is coming up, thought I'd better get rid of my pending
  changes in my for-linus branch for this iteration.  It contains:

   - Two patches for mtip32xx.  Killing a non-compliant sysfs interface
     and moving it to debugfs, where it belongs.

   - A few patches from Asias.  Two legit bug fixes, and one killing an
     interface that is no longer in use.

   - A patch from Jan, making the annoying partition ioctl warning a bit
     less annoying, by restricting it to !CAP_SYS_RAWIO only.

   - Three bug fixes for drbd from Lars Ellenberg.

   - A fix for an old regression for umem, it hasn't really worked since
     the plugging scheme was changed in 3.0.

   - A few fixes from Tejun.

   - A splice fix from Eric Dumazet, fixing an issue with pipe
     resizing."

* 'for-linus' of git://git.kernel.dk/linux-block:
  scsi: Silence unnecessary warnings about ioctl to partition
  block: Drop dead function blk_abort_queue()
  block: Mitigate lock unbalance caused by lock switching
  block: Avoid missed wakeup in request waitqueue
  umem: fix up unplugging
  splice: fix racy pipe->buffers uses
  drbd: fix null pointer dereference with on-congestion policy when diskless
  drbd: fix list corruption by failing but already aborted reads
  drbd: fix access of unallocated pages and kernel panic
  xen/blkfront: Add WARN to deal with misbehaving backends.
  blkcg: drop local variable @q from blkg_destroy()
  mtip32xx: Create debugfs entries for troubleshooting
  mtip32xx: Remove 'registers' and 'flags' from sysfs
  blkcg: fix blkg_alloc() failure path
  block: blkcg_policy_cfq shouldn't be used if !CONFIG_CFQ_GROUP_IOSCHED
  block: fix return value on cfq_init() failure
  mtip32xx: Remove version.h header file inclusion
  xen/blkback: Copy id field when doing BLKIF_DISCARD.

Documentation/ABI/testing/sysfs-block-rssd

@@ -1,26 +1,5 @@
-What:           /sys/block/rssd*/registers
-Date:           March 2012
-KernelVersion:  3.3
-Contact:        Asai Thambi S P <asamymuthupa@micron.com>
-Description:    This is a read-only file. Dumps below driver information and
-                hardware registers.
-                    - S ACTive
-                    - Command Issue
-                    - Completed
-                    - PORT IRQ STAT
-                    - HOST IRQ STAT
-                    - Allocated
-                    - Commands in Q
-
 What:           /sys/block/rssd*/status
 Date:           April 2012
 KernelVersion:  3.4
 Contact:        Asai Thambi S P <asamymuthupa@micron.com>
 Description:    This is a read-only file. Indicates the status of the device.
-
-What:           /sys/block/rssd*/flags
-Date:           May 2012
-KernelVersion:  3.5
-Contact:        Asai Thambi S P <asamymuthupa@micron.com>
-Description:    This is a read-only file. Dumps the flags in port and driver
-                data structure

block/blk-cgroup.c

@@ -125,12 +125,8 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q)
 
 		blkg->pd[i] = pd;
 		pd->blkg = blkg;
-	}
-
-	/* invoke per-policy init */
-	for (i = 0; i < BLKCG_MAX_POLS; i++) {
-		struct blkcg_policy *pol = blkcg_policy[i];
 
+		/* invoke per-policy init */
 		if (blkcg_policy_enabled(blkg->q, pol))
 			pol->pd_init_fn(blkg);
 	}
@@ -245,10 +241,9 @@ EXPORT_SYMBOL_GPL(blkg_lookup_create);
 
 static void blkg_destroy(struct blkcg_gq *blkg)
 {
-	struct request_queue *q = blkg->q;
 	struct blkcg *blkcg = blkg->blkcg;
 
-	lockdep_assert_held(q->queue_lock);
+	lockdep_assert_held(blkg->q->queue_lock);
 	lockdep_assert_held(&blkcg->lock);
 
 	/* Something wrong if we are trying to remove same group twice */

block/blk-core.c

@@ -361,9 +361,10 @@ EXPORT_SYMBOL(blk_put_queue);
  */
 void blk_drain_queue(struct request_queue *q, bool drain_all)
 {
+	int i;
+
 	while (true) {
 		bool drain = false;
-		int i;
 
 		spin_lock_irq(q->queue_lock);
 
@@ -408,6 +409,18 @@ void blk_drain_queue(struct request_queue *q, bool drain_all)
 			break;
 		msleep(10);
 	}
+
+	/*
+	 * With queue marked dead, any woken up waiter will fail the
+	 * allocation path, so the wakeup chaining is lost and we're
+	 * left with hung waiters. We need to wake up those waiters.
+	 */
+	if (q->request_fn) {
+		spin_lock_irq(q->queue_lock);
+		for (i = 0; i < ARRAY_SIZE(q->rq.wait); i++)
+			wake_up_all(&q->rq.wait[i]);
+		spin_unlock_irq(q->queue_lock);
+	}
 }
 
 /**
@@ -467,7 +480,6 @@ void blk_cleanup_queue(struct request_queue *q)
 	/* mark @q DEAD, no new request or merges will be allowed afterwards */
 	mutex_lock(&q->sysfs_lock);
 	queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q);
-
 	spin_lock_irq(lock);
 
 	/*
@@ -485,10 +497,6 @@ void blk_cleanup_queue(struct request_queue *q)
 	queue_flag_set(QUEUE_FLAG_NOMERGES, q);
 	queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
 	queue_flag_set(QUEUE_FLAG_DEAD, q);
-
-	if (q->queue_lock != &q->__queue_lock)
-		q->queue_lock = &q->__queue_lock;
-
 	spin_unlock_irq(lock);
 	mutex_unlock(&q->sysfs_lock);
 
@@ -499,6 +507,11 @@ void blk_cleanup_queue(struct request_queue *q)
 	del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer);
 	blk_sync_queue(q);
 
+	spin_lock_irq(lock);
+	if (q->queue_lock != &q->__queue_lock)
+		q->queue_lock = &q->__queue_lock;
+	spin_unlock_irq(lock);
+
 	/* @q is and will stay empty, shutdown and put */
 	blk_put_queue(q);
 }

block/blk-timeout.c

@@ -197,44 +197,3 @@ void blk_add_timer(struct request *req)
 		mod_timer(&q->timeout, expiry);
 }
 
-/**
- * blk_abort_queue -- Abort all request on given queue
- * @queue:	pointer to queue
- *
- */
-void blk_abort_queue(struct request_queue *q)
-{
-	unsigned long flags;
-	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);
-
-	/*
-	 * Splice entries to local list, to avoid deadlocking if entries
-	 * get readded to the timeout list by error handling
-	 */
-	list_splice_init(&q->timeout_list, &list);
-
-	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);
-
-}
-EXPORT_SYMBOL_GPL(blk_abort_queue);

block/cfq-iosched.c

@@ -17,8 +17,6 @@
 #include "blk.h"
 #include "blk-cgroup.h"
 
-static struct blkcg_policy blkcg_policy_cfq __maybe_unused;
-
 /*
  * tunables
  */
@@ -418,11 +416,6 @@ static inline struct cfq_group *pd_to_cfqg(struct blkg_policy_data *pd)
 	return pd ? container_of(pd, struct cfq_group, pd) : NULL;
 }
 
-static inline struct cfq_group *blkg_to_cfqg(struct blkcg_gq *blkg)
-{
-	return pd_to_cfqg(blkg_to_pd(blkg, &blkcg_policy_cfq));
-}
-
 static inline struct blkcg_gq *cfqg_to_blkg(struct cfq_group *cfqg)
 {
 	return pd_to_blkg(&cfqg->pd);
@@ -572,6 +565,13 @@ static inline void cfqg_stats_update_avg_queue_size(struct cfq_group *cfqg) { }
 
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
 
+static struct blkcg_policy blkcg_policy_cfq;
+
+static inline struct cfq_group *blkg_to_cfqg(struct blkcg_gq *blkg)
+{
+	return pd_to_cfqg(blkg_to_pd(blkg, &blkcg_policy_cfq));
+}
+
 static inline void cfqg_get(struct cfq_group *cfqg)
 {
 	return blkg_get(cfqg_to_blkg(cfqg));
@@ -3951,10 +3951,11 @@ static void cfq_exit_queue(struct elevator_queue *e)
 
 	cfq_shutdown_timer_wq(cfqd);
 
-#ifndef CONFIG_CFQ_GROUP_IOSCHED
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+	blkcg_deactivate_policy(q, &blkcg_policy_cfq);
+#else
 	kfree(cfqd->root_group);
 #endif
-	blkcg_deactivate_policy(q, &blkcg_policy_cfq);
 	kfree(cfqd);
 }
 
@@ -4194,14 +4195,15 @@ static int __init cfq_init(void)
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
 	if (!cfq_group_idle)
 		cfq_group_idle = 1;
-#else
-		cfq_group_idle = 0;
-#endif
 
 	ret = blkcg_policy_register(&blkcg_policy_cfq);
 	if (ret)
 		return ret;
+#else
+	cfq_group_idle = 0;
+#endif
 
+	ret = -ENOMEM;
 	cfq_pool = KMEM_CACHE(cfq_queue, 0);
 	if (!cfq_pool)
 		goto err_pol_unreg;
@@ -4215,13 +4217,17 @@ static int __init cfq_init(void)
 err_free_pool:
 	kmem_cache_destroy(cfq_pool);
 err_pol_unreg:
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
 	blkcg_policy_unregister(&blkcg_policy_cfq);
+#endif
 	return ret;
 }
 
 static void __exit cfq_exit(void)
 {
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
 	blkcg_policy_unregister(&blkcg_policy_cfq);
+#endif
 	elv_unregister(&iosched_cfq);
 	kmem_cache_destroy(cfq_pool);
 }

block/scsi_ioctl.c

@@ -721,11 +721,14 @@ int scsi_verify_blk_ioctl(struct block_device *bd, unsigned int cmd)
 		break;
 	}
 
+	if (capable(CAP_SYS_RAWIO))
+		return 0;
+
 	/* In particular, rule out all resets and host-specific ioctls.  */
 	printk_ratelimited(KERN_WARNING
 			   "%s: sending ioctl %x to a partition!\n", current->comm, cmd);
 
-	return capable(CAP_SYS_RAWIO) ? 0 : -ENOIOCTLCMD;
+	return -ENOIOCTLCMD;
 }
 EXPORT_SYMBOL(scsi_verify_blk_ioctl);
 

drivers/block/drbd/drbd_bitmap.c

@@ -1475,10 +1475,17 @@ void _drbd_bm_set_bits(struct drbd_conf *mdev, const unsigned long s, const unsi
 		first_word = 0;
 		spin_lock_irq(&b->bm_lock);
 	}
-
 	/* last page (respectively only page, for first page == last page) */
 	last_word = MLPP(el >> LN2_BPL);
-	bm_set_full_words_within_one_page(mdev->bitmap, last_page, first_word, last_word);
+
+	/* consider bitmap->bm_bits = 32768, bitmap->bm_number_of_pages = 1. (or multiples).
+	 * ==> e = 32767, el = 32768, last_page = 2,
+	 * and now last_word = 0.
+	 * We do not want to touch last_page in this case,
+	 * as we did not allocate it, it is not present in bitmap->bm_pages.
+	 */
+	if (last_word)
+		bm_set_full_words_within_one_page(mdev->bitmap, last_page, first_word, last_word);
 
 	/* possibly trailing bits.
 	 * example: (e & 63) == 63, el will be e+1.

drivers/block/drbd/drbd_req.c

@@ -472,12 +472,17 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 		req->rq_state |= RQ_LOCAL_COMPLETED;
 		req->rq_state &= ~RQ_LOCAL_PENDING;
 
-		D_ASSERT(!(req->rq_state & RQ_NET_MASK));
+		if (req->rq_state & RQ_LOCAL_ABORTED) {
+			_req_may_be_done(req, m);
+			break;
+		}
 
 		__drbd_chk_io_error(mdev, false);
 
 	goto_queue_for_net_read:
 
+		D_ASSERT(!(req->rq_state & RQ_NET_MASK));
+
 		/* no point in retrying if there is no good remote data,
 		 * or we have no connection. */
 		if (mdev->state.pdsk != D_UP_TO_DATE) {
@@ -765,6 +770,40 @@ static int drbd_may_do_local_read(struct drbd_conf *mdev, sector_t sector, int s
 	return 0 == drbd_bm_count_bits(mdev, sbnr, ebnr);
 }
 
+static void maybe_pull_ahead(struct drbd_conf *mdev)
+{
+	int congested = 0;
+
+	/* If I don't even have good local storage, we can not reasonably try
+	 * to pull ahead of the peer. We also need the local reference to make
+	 * sure mdev->act_log is there.
+	 * Note: caller has to make sure that net_conf is there.
+	 */
+	if (!get_ldev_if_state(mdev, D_UP_TO_DATE))
+		return;
+
+	if (mdev->net_conf->cong_fill &&
+	    atomic_read(&mdev->ap_in_flight) >= mdev->net_conf->cong_fill) {
+		dev_info(DEV, "Congestion-fill threshold reached\n");
+		congested = 1;
+	}
+
+	if (mdev->act_log->used >= mdev->net_conf->cong_extents) {
+		dev_info(DEV, "Congestion-extents threshold reached\n");
+		congested = 1;
+	}
+
+	if (congested) {
+		queue_barrier(mdev); /* last barrier, after mirrored writes */
+
+		if (mdev->net_conf->on_congestion == OC_PULL_AHEAD)
+			_drbd_set_state(_NS(mdev, conn, C_AHEAD), 0, NULL);
+		else  /*mdev->net_conf->on_congestion == OC_DISCONNECT */
+			_drbd_set_state(_NS(mdev, conn, C_DISCONNECTING), 0, NULL);
+	}
+	put_ldev(mdev);
+}
+
 static int drbd_make_request_common(struct drbd_conf *mdev, struct bio *bio, unsigned long start_time)
 {
 	const int rw = bio_rw(bio);
@@ -972,29 +1011,8 @@ allocate_barrier:
 		_req_mod(req, queue_for_send_oos);
 
 	if (remote &&
-	    mdev->net_conf->on_congestion != OC_BLOCK && mdev->agreed_pro_version >= 96) {
-		int congested = 0;
-
-		if (mdev->net_conf->cong_fill &&
-		    atomic_read(&mdev->ap_in_flight) >= mdev->net_conf->cong_fill) {
-			dev_info(DEV, "Congestion-fill threshold reached\n");
-			congested = 1;
-		}
-
-		if (mdev->act_log->used >= mdev->net_conf->cong_extents) {
-			dev_info(DEV, "Congestion-extents threshold reached\n");
-			congested = 1;
-		}
-
-		if (congested) {
-			queue_barrier(mdev); /* last barrier, after mirrored writes */
-
-			if (mdev->net_conf->on_congestion == OC_PULL_AHEAD)
-				_drbd_set_state(_NS(mdev, conn, C_AHEAD), 0, NULL);
-			else  /*mdev->net_conf->on_congestion == OC_DISCONNECT */
-				_drbd_set_state(_NS(mdev, conn, C_DISCONNECTING), 0, NULL);
-		}
-	}
+	    mdev->net_conf->on_congestion != OC_BLOCK && mdev->agreed_pro_version >= 96)
+		maybe_pull_ahead(mdev);
 
 	spin_unlock_irq(&mdev->req_lock);
 	kfree(b); /* if someone else has beaten us to it... */

drivers/block/mtip32xx/mtip32xx.c

@@ -37,6 +37,7 @@
 #include <linux/kthread.h>
 #include <../drivers/ata/ahci.h>
 #include <linux/export.h>
+#include <linux/debugfs.h>
 #include "mtip32xx.h"
 
 #define HW_CMD_SLOT_SZ		(MTIP_MAX_COMMAND_SLOTS * 32)
@@ -85,6 +86,7 @@ static int instance;
  * allocated in mtip_init().
  */
 static int mtip_major;
+static struct dentry *dfs_parent;
 
 static DEFINE_SPINLOCK(rssd_index_lock);
 static DEFINE_IDA(rssd_index_ida);
@@ -2546,7 +2548,7 @@ static struct scatterlist *mtip_hw_get_scatterlist(struct driver_data *dd,
 }
 
 /*
- * Sysfs register/status dump.
+ * Sysfs status dump.
  *
  * @dev  Pointer to the device structure, passed by the kernrel.
  * @attr Pointer to the device_attribute structure passed by the kernel.
@@ -2555,45 +2557,68 @@ static struct scatterlist *mtip_hw_get_scatterlist(struct driver_data *dd,
  * return value
  *	The size, in bytes, of the data copied into buf.
  */
-static ssize_t mtip_hw_show_registers(struct device *dev,
+static ssize_t mtip_hw_show_status(struct device *dev,
 				struct device_attribute *attr,
 				char *buf)
 {
-	u32 group_allocated;
 	struct driver_data *dd = dev_to_disk(dev)->private_data;
 	int size = 0;
+
+	if (test_bit(MTIP_DDF_OVER_TEMP_BIT, &dd->dd_flag))
+		size += sprintf(buf, "%s", "thermal_shutdown\n");
+	else if (test_bit(MTIP_DDF_WRITE_PROTECT_BIT, &dd->dd_flag))
+		size += sprintf(buf, "%s", "write_protect\n");
+	else
+		size += sprintf(buf, "%s", "online\n");
+
+	return size;
+}
+
+static DEVICE_ATTR(status, S_IRUGO, mtip_hw_show_status, NULL);
+
+static ssize_t mtip_hw_read_registers(struct file *f, char __user *ubuf,
+				  size_t len, loff_t *offset)
+{
+	struct driver_data *dd =  (struct driver_data *)f->private_data;
+	char buf[MTIP_DFS_MAX_BUF_SIZE];
+	u32 group_allocated;
+	int size = *offset;
 	int n;
 
-	size += sprintf(&buf[size], "Hardware\n--------\n");
-	size += sprintf(&buf[size], "S ACTive      : [ 0x");
+	if (!len || size)
+		return 0;
+
+	if (size < 0)
+		return -EINVAL;
+
+	size += sprintf(&buf[size], "H/ S ACTive      : [ 0x");
 
 	for (n = dd->slot_groups-1; n >= 0; n--)
 		size += sprintf(&buf[size], "%08X ",
 					 readl(dd->port->s_active[n]));
 
 	size += sprintf(&buf[size], "]\n");
-	size += sprintf(&buf[size], "Command Issue : [ 0x");
+	size += sprintf(&buf[size], "H/ Command Issue : [ 0x");
 
 	for (n = dd->slot_groups-1; n >= 0; n--)
 		size += sprintf(&buf[size], "%08X ",
 					readl(dd->port->cmd_issue[n]));
 
 	size += sprintf(&buf[size], "]\n");
-	size += sprintf(&buf[size], "Completed     : [ 0x");
+	size += sprintf(&buf[size], "H/ Completed     : [ 0x");
 
 	for (n = dd->slot_groups-1; n >= 0; n--)
 		size += sprintf(&buf[size], "%08X ",
 				readl(dd->port->completed[n]));
 
 	size += sprintf(&buf[size], "]\n");
-	size += sprintf(&buf[size], "PORT IRQ STAT : [ 0x%08X ]\n",
+	size += sprintf(&buf[size], "H/ PORT IRQ STAT : [ 0x%08X ]\n",
 				readl(dd->port->mmio + PORT_IRQ_STAT));
-	size += sprintf(&buf[size], "HOST IRQ STAT : [ 0x%08X ]\n",
+	size += sprintf(&buf[size], "H/ HOST IRQ STAT : [ 0x%08X ]\n",
 				readl(dd->mmio + HOST_IRQ_STAT));
 	size += sprintf(&buf[size], "\n");
 
-	size += sprintf(&buf[size], "Local\n-----\n");
-	size += sprintf(&buf[size], "Allocated    : [ 0x");
+	size += sprintf(&buf[size], "L/ Allocated     : [ 0x");
 
 	for (n = dd->slot_groups-1; n >= 0; n--) {
 		if (sizeof(long) > sizeof(u32))
@@ -2605,7 +2630,7 @@ static ssize_t mtip_hw_show_registers(struct device *dev,
 	}
 	size += sprintf(&buf[size], "]\n");
 
-	size += sprintf(&buf[size], "Commands in Q: [ 0x");
+	size += sprintf(&buf[size], "L/ Commands in Q : [ 0x");
 
 	for (n = dd->slot_groups-1; n >= 0; n--) {
 		if (sizeof(long) > sizeof(u32))
@@ -2617,44 +2642,53 @@ static ssize_t mtip_hw_show_registers(struct device *dev,
 	}
 	size += sprintf(&buf[size], "]\n");
 
-	return size;
+	*offset = size <= len ? size : len;
+	size = copy_to_user(ubuf, buf, *offset);
+	if (size)
+		return -EFAULT;
+
+	return *offset;
 }
 
-static ssize_t mtip_hw_show_status(struct device *dev,
-				struct device_attribute *attr,
-				char *buf)
+static ssize_t mtip_hw_read_flags(struct file *f, char __user *ubuf,
+				  size_t len, loff_t *offset)
 {
-	struct driver_data *dd = dev_to_disk(dev)->private_data;
-	int size = 0;
+	struct driver_data *dd =  (struct driver_data *)f->private_data;
+	char buf[MTIP_DFS_MAX_BUF_SIZE];
+	int size = *offset;
 
-	if (test_bit(MTIP_DDF_OVER_TEMP_BIT, &dd->dd_flag))
-		size += sprintf(buf, "%s", "thermal_shutdown\n");
-	else if (test_bit(MTIP_DDF_WRITE_PROTECT_BIT, &dd->dd_flag))
-		size += sprintf(buf, "%s", "write_protect\n");
-	else
-		size += sprintf(buf, "%s", "online\n");
-
-	return size;
-}
+	if (!len || size)
+		return 0;
 
-static ssize_t mtip_hw_show_flags(struct device *dev,
-				struct device_attribute *attr,
-				char *buf)
-{
-	struct driver_data *dd = dev_to_disk(dev)->private_data;
-	int size = 0;
+	if (size < 0)
+		return -EINVAL;
 
-	size += sprintf(&buf[size], "Flag in port struct : [ %08lX ]\n",
+	size += sprintf(&buf[size], "Flag-port : [ %08lX ]\n",
 							dd->port->flags);
-	size += sprintf(&buf[size], "Flag in dd struct   : [ %08lX ]\n",
+	size += sprintf(&buf[size], "Flag-dd   : [ %08lX ]\n",
 							dd->dd_flag);
 
-	return size;
+	*offset = size <= len ? size : len;
+	size = copy_to_user(ubuf, buf, *offset);
+	if (size)
+		return -EFAULT;
+
+	return *offset;
 }
 
-static DEVICE_ATTR(registers, S_IRUGO, mtip_hw_show_registers, NULL);
-static DEVICE_ATTR(status, S_IRUGO, mtip_hw_show_status, NULL);
-static DEVICE_ATTR(flags, S_IRUGO, mtip_hw_show_flags, NULL);
+static const struct file_operations mtip_regs_fops = {
+	.owner  = THIS_MODULE,
+	.open   = simple_open,
+	.read   = mtip_hw_read_registers,
+	.llseek = no_llseek,
+};
+
+static const struct file_operations mtip_flags_fops = {
+	.owner  = THIS_MODULE,
+	.open   = simple_open,
+	.read   = mtip_hw_read_flags,
+	.llseek = no_llseek,
+};
 
 /*
  * Create the sysfs related attributes.
@@ -2671,15 +2705,9 @@ static int mtip_hw_sysfs_init(struct driver_data *dd, struct kobject *kobj)
 	if (!kobj || !dd)
 		return -EINVAL;
 
-	if (sysfs_create_file(kobj, &dev_attr_registers.attr))
-		dev_warn(&dd->pdev->dev,
-			"Error creating 'registers' sysfs entry\n");
 	if (sysfs_create_file(kobj, &dev_attr_status.attr))
 		dev_warn(&dd->pdev->dev,
 			"Error creating 'status' sysfs entry\n");
-	if (sysfs_create_file(kobj, &dev_attr_flags.attr))
-		dev_warn(&dd->pdev->dev,
-			"Error creating 'flags' sysfs entry\n");
 	return 0;
 }
 
@@ -2698,13 +2726,39 @@ static int mtip_hw_sysfs_exit(struct driver_data *dd, struct kobject *kobj)
 	if (!kobj || !dd)
 		return -EINVAL;
 
-	sysfs_remove_file(kobj, &dev_attr_registers.attr);
 	sysfs_remove_file(kobj, &dev_attr_status.attr);
-	sysfs_remove_file(kobj, &dev_attr_flags.attr);
 
 	return 0;
 }
 
+static int mtip_hw_debugfs_init(struct driver_data *dd)
+{
+	if (!dfs_parent)
+		return -1;
+
+	dd->dfs_node = debugfs_create_dir(dd->disk->disk_name, dfs_parent);
+	if (IS_ERR_OR_NULL(dd->dfs_node)) {
+		dev_warn(&dd->pdev->dev,
+			"Error creating node %s under debugfs\n",
+						dd->disk->disk_name);
+		dd->dfs_node = NULL;
+		return -1;
+	}
+
+	debugfs_create_file("flags", S_IRUGO, dd->dfs_node, dd,
+							&mtip_flags_fops);
+	debugfs_create_file("registers", S_IRUGO, dd->dfs_node, dd,
+							&mtip_regs_fops);
+
+	return 0;
+}
+
+static void mtip_hw_debugfs_exit(struct driver_data *dd)
+{
+	debugfs_remove_recursive(dd->dfs_node);
+}
+
+
 /*
  * Perform any init/resume time hardware setup
  *
@@ -3730,6 +3784,7 @@ skip_create_disk:
 		mtip_hw_sysfs_init(dd, kobj);
 		kobject_put(kobj);
 	}
+	mtip_hw_debugfs_init(dd);
 
 	if (dd->mtip_svc_handler) {
 		set_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag);
@@ -3755,6 +3810,8 @@ start_service_thread:
 	return rv;
 
 kthread_run_error:
+	mtip_hw_debugfs_exit(dd);
+
 	/* Delete our gendisk. This also removes the device from /dev */
 	del_gendisk(dd->disk);
 
@@ -3805,6 +3862,7 @@ static int mtip_block_remove(struct driver_data *dd)
 			kobject_put(kobj);
 		}
 	}
+	mtip_hw_debugfs_exit(dd);
 
 	/*
 	 * Delete our gendisk structure. This also removes the device
@@ -4152,10 +4210,20 @@ static int __init mtip_init(void)
 	}
 	mtip_major = error;
 
+	if (!dfs_parent) {
+		dfs_parent = debugfs_create_dir("rssd", NULL);
+		if (IS_ERR_OR_NULL(dfs_parent)) {
+			printk(KERN_WARNING "Error creating debugfs parent\n");
+			dfs_parent = NULL;
+		}
+	}
+
 	/* Register our PCI operations. */
 	error = pci_register_driver(&mtip_pci_driver);
-	if (error)
+	if (error) {
+		debugfs_remove(dfs_parent);
 		unregister_blkdev(mtip_major, MTIP_DRV_NAME);
+	}
 
 	return error;
 }
@@ -4172,6 +4240,8 @@ static int __init mtip_init(void)
  */
 static void __exit mtip_exit(void)
 {
+	debugfs_remove_recursive(dfs_parent);
+
 	/* Release the allocated major block device number. */
 	unregister_blkdev(mtip_major, MTIP_DRV_NAME);
 

drivers/block/mtip32xx/mtip32xx.h

@@ -26,7 +26,6 @@
 #include <linux/ata.h>
 #include <linux/interrupt.h>
 #include <linux/genhd.h>
-#include <linux/version.h>
 
 /* Offset of Subsystem Device ID in pci confoguration space */
 #define PCI_SUBSYSTEM_DEVICEID	0x2E
@@ -111,6 +110,8 @@
  #define dbg_printk(format, arg...)
 #endif
 
+#define MTIP_DFS_MAX_BUF_SIZE 1024
+
 #define __force_bit2int (unsigned int __force)
 
 enum {
@@ -447,6 +448,8 @@ struct driver_data {
 	unsigned long dd_flag; /* NOTE: use atomic bit operations on this */
 
 	struct task_struct *mtip_svc_handler; /* task_struct of svc thd */
+
+	struct dentry *dfs_node;
 };
 
 #endif

drivers/block/umem.c

@@ -513,6 +513,44 @@ static void process_page(unsigned long data)
 	}
 }
 
+struct mm_plug_cb {
+	struct blk_plug_cb cb;
+	struct cardinfo *card;
+};
+
+static void mm_unplug(struct blk_plug_cb *cb)
+{
+	struct mm_plug_cb *mmcb = container_of(cb, struct mm_plug_cb, cb);
+
+	spin_lock_irq(&mmcb->card->lock);
+	activate(mmcb->card);
+	spin_unlock_irq(&mmcb->card->lock);
+	kfree(mmcb);
+}
+
+static int mm_check_plugged(struct cardinfo *card)
+{
+	struct blk_plug *plug = current->plug;
+	struct mm_plug_cb *mmcb;
+
+	if (!plug)
+		return 0;
+
+	list_for_each_entry(mmcb, &plug->cb_list, cb.list) {
+		if (mmcb->cb.callback == mm_unplug && mmcb->card == card)
+			return 1;
+	}
+	/* Not currently on the callback list */
+	mmcb = kmalloc(sizeof(*mmcb), GFP_ATOMIC);
+	if (!mmcb)
+		return 0;
+
+	mmcb->card = card;
+	mmcb->cb.callback = mm_unplug;
+	list_add(&mmcb->cb.list, &plug->cb_list);
+	return 1;
+}
+
 static void mm_make_request(struct request_queue *q, struct bio *bio)
 {
 	struct cardinfo *card = q->queuedata;
@@ -523,6 +561,8 @@ static void mm_make_request(struct request_queue *q, struct bio *bio)
 	*card->biotail = bio;
 	bio->bi_next = NULL;
 	card->biotail = &bio->bi_next;
+	if (bio->bi_rw & REQ_SYNC || !mm_check_plugged(card))
+		activate(card);
 	spin_unlock_irq(&card->lock);
 
 	return;

drivers/block/xen-blkback/common.h

@@ -257,6 +257,7 @@ static inline void blkif_get_x86_32_req(struct blkif_request *dst,
 		break;
 	case BLKIF_OP_DISCARD:
 		dst->u.discard.flag = src->u.discard.flag;
+		dst->u.discard.id = src->u.discard.id;
 		dst->u.discard.sector_number = src->u.discard.sector_number;
 		dst->u.discard.nr_sectors = src->u.discard.nr_sectors;
 		break;
@@ -287,6 +288,7 @@ static inline void blkif_get_x86_64_req(struct blkif_request *dst,
 		break;
 	case BLKIF_OP_DISCARD:
 		dst->u.discard.flag = src->u.discard.flag;
+		dst->u.discard.id = src->u.discard.id;
 		dst->u.discard.sector_number = src->u.discard.sector_number;
 		dst->u.discard.nr_sectors = src->u.discard.nr_sectors;
 		break;

drivers/block/xen-blkfront.c

@@ -141,14 +141,36 @@ static int get_id_from_freelist(struct blkfront_info *info)
 	return free;
 }
 
-static void add_id_to_freelist(struct blkfront_info *info,
+static int add_id_to_freelist(struct blkfront_info *info,
 			       unsigned long id)
 {
+	if (info->shadow[id].req.u.rw.id != id)
+		return -EINVAL;
+	if (info->shadow[id].request == NULL)
+		return -EINVAL;
 	info->shadow[id].req.u.rw.id  = info->shadow_free;
 	info->shadow[id].request = NULL;
 	info->shadow_free = id;
+	return 0;
 }
 
+static const char *op_name(int op)
+{
+	static const char *const names[] = {
+		[BLKIF_OP_READ] = "read",
+		[BLKIF_OP_WRITE] = "write",
+		[BLKIF_OP_WRITE_BARRIER] = "barrier",
+		[BLKIF_OP_FLUSH_DISKCACHE] = "flush",
+		[BLKIF_OP_DISCARD] = "discard" };
+
+	if (op < 0 || op >= ARRAY_SIZE(names))
+		return "unknown";
+
+	if (!names[op])
+		return "reserved";
+
+	return names[op];
+}
 static int xlbd_reserve_minors(unsigned int minor, unsigned int nr)
 {
 	unsigned int end = minor + nr;
@@ -746,20 +768,36 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 
 		bret = RING_GET_RESPONSE(&info->ring, i);
 		id   = bret->id;
+		/*
+		 * The backend has messed up and given us an id that we would
+		 * never have given to it (we stamp it up to BLK_RING_SIZE -
+		 * look in get_id_from_freelist.
+		 */
+		if (id >= BLK_RING_SIZE) {
+			WARN(1, "%s: response to %s has incorrect id (%ld)\n",
+			     info->gd->disk_name, op_name(bret->operation), id);
+			/* We can't safely get the 'struct request' as
+			 * the id is busted. */
+			continue;
+		}
 		req  = info->shadow[id].request;
 
 		if (bret->operation != BLKIF_OP_DISCARD)
 			blkif_completion(&info->shadow[id]);
 
-		add_id_to_freelist(info, id);
+		if (add_id_to_freelist(info, id)) {
+			WARN(1, "%s: response to %s (id %ld) couldn't be recycled!\n",
+			     info->gd->disk_name, op_name(bret->operation), id);
+			continue;
+		}
 
 		error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
 		switch (bret->operation) {
 		case BLKIF_OP_DISCARD:
 			if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
 				struct request_queue *rq = info->rq;
-				printk(KERN_WARNING "blkfront: %s: discard op failed\n",
-					   info->gd->disk_name);
+				printk(KERN_WARNING "blkfront: %s: %s op failed\n",
+					   info->gd->disk_name, op_name(bret->operation));
 				error = -EOPNOTSUPP;
 				info->feature_discard = 0;
 				info->feature_secdiscard = 0;
@@ -771,18 +809,14 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 		case BLKIF_OP_FLUSH_DISKCACHE:
 		case BLKIF_OP_WRITE_BARRIER:
 			if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
-				printk(KERN_WARNING "blkfront: %s: write %s op failed\n",
-				       info->flush_op == BLKIF_OP_WRITE_BARRIER ?
-				       "barrier" :  "flush disk cache",
-				       info->gd->disk_name);
+				printk(KERN_WARNING "blkfront: %s: %s op failed\n",
+				       info->gd->disk_name, op_name(bret->operation));
 				error = -EOPNOTSUPP;
 			}
 			if (unlikely(bret->status == BLKIF_RSP_ERROR &&
 				     info->shadow[id].req.u.rw.nr_segments == 0)) {
-				printk(KERN_WARNING "blkfront: %s: empty write %s op failed\n",
-				       info->flush_op == BLKIF_OP_WRITE_BARRIER ?
-				       "barrier" :  "flush disk cache",
-				       info->gd->disk_name);
+				printk(KERN_WARNING "blkfront: %s: empty %s op failed\n",
+				       info->gd->disk_name, op_name(bret->operation));
 				error = -EOPNOTSUPP;
 			}
 			if (unlikely(error)) {

fs/splice.c

@@ -273,13 +273,16 @@ void spd_release_page(struct splice_pipe_desc *spd, unsigned int i)
  * Check if we need to grow the arrays holding pages and partial page
  * descriptions.
  */
-int splice_grow_spd(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd)
+int splice_grow_spd(const struct pipe_inode_info *pipe, struct splice_pipe_desc *spd)
 {
-	if (pipe->buffers <= PIPE_DEF_BUFFERS)
+	unsigned int buffers = ACCESS_ONCE(pipe->buffers);
+
+	spd->nr_pages_max = buffers;
+	if (buffers <= PIPE_DEF_BUFFERS)
 		return 0;
 
-	spd->pages = kmalloc(pipe->buffers * sizeof(struct page *), GFP_KERNEL);
-	spd->partial = kmalloc(pipe->buffers * sizeof(struct partial_page), GFP_KERNEL);
+	spd->pages = kmalloc(buffers * sizeof(struct page *), GFP_KERNEL);
+	spd->partial = kmalloc(buffers * sizeof(struct partial_page), GFP_KERNEL);
 
 	if (spd->pages && spd->partial)
 		return 0;
@@ -289,10 +292,9 @@ int splice_grow_spd(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd)
 	return -ENOMEM;
 }
 
-void splice_shrink_spd(struct pipe_inode_info *pipe,
-		       struct splice_pipe_desc *spd)
+void splice_shrink_spd(struct splice_pipe_desc *spd)
 {
-	if (pipe->buffers <= PIPE_DEF_BUFFERS)
+	if (spd->nr_pages_max <= PIPE_DEF_BUFFERS)
 		return;
 
 	kfree(spd->pages);
@@ -315,6 +317,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
 	struct splice_pipe_desc spd = {
 		.pages = pages,
 		.partial = partial,
+		.nr_pages_max = PIPE_DEF_BUFFERS,
 		.flags = flags,
 		.ops = &page_cache_pipe_buf_ops,
 		.spd_release = spd_release_page,
@@ -326,7 +329,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos,
 	index = *ppos >> PAGE_CACHE_SHIFT;
 	loff = *ppos & ~PAGE_CACHE_MASK;
 	req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	nr_pages = min(req_pages, pipe->buffers);
+	nr_pages = min(req_pages, spd.nr_pages_max);
 
 	/*
 	 * Lookup the (hopefully) full range of pages we need.
@@ -497,7 +500,7 @@ fill_it:
 	if (spd.nr_pages)
 		error = splice_to_pipe(pipe, &spd);
 
-	splice_shrink_spd(pipe, &spd);
+	splice_shrink_spd(&spd);
 	return error;
 }
 
@@ -598,6 +601,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
 	struct splice_pipe_desc spd = {
 		.pages = pages,
 		.partial = partial,
+		.nr_pages_max = PIPE_DEF_BUFFERS,
 		.flags = flags,
 		.ops = &default_pipe_buf_ops,
 		.spd_release = spd_release_page,
@@ -608,8 +612,8 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
 
 	res = -ENOMEM;
 	vec = __vec;
-	if (pipe->buffers > PIPE_DEF_BUFFERS) {
-		vec = kmalloc(pipe->buffers * sizeof(struct iovec), GFP_KERNEL);
+	if (spd.nr_pages_max > PIPE_DEF_BUFFERS) {
+		vec = kmalloc(spd.nr_pages_max * sizeof(struct iovec), GFP_KERNEL);
 		if (!vec)
 			goto shrink_ret;
 	}
@@ -617,7 +621,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
 	offset = *ppos & ~PAGE_CACHE_MASK;
 	nr_pages = (len + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 
-	for (i = 0; i < nr_pages && i < pipe->buffers && len; i++) {
+	for (i = 0; i < nr_pages && i < spd.nr_pages_max && len; i++) {
 		struct page *page;
 
 		page = alloc_page(GFP_USER);
@@ -665,7 +669,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
 shrink_ret:
 	if (vec != __vec)
 		kfree(vec);
-	splice_shrink_spd(pipe, &spd);
+	splice_shrink_spd(&spd);
 	return res;
 
 err:
@@ -1614,6 +1618,7 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov,
 	struct splice_pipe_desc spd = {
 		.pages = pages,
 		.partial = partial,
+		.nr_pages_max = PIPE_DEF_BUFFERS,
 		.flags = flags,
 		.ops = &user_page_pipe_buf_ops,
 		.spd_release = spd_release_page,
@@ -1629,13 +1634,13 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov,
 
 	spd.nr_pages = get_iovec_page_array(iov, nr_segs, spd.pages,
 					    spd.partial, false,
-					    pipe->buffers);
+					    spd.nr_pages_max);
 	if (spd.nr_pages <= 0)
 		ret = spd.nr_pages;
 	else
 		ret = splice_to_pipe(pipe, &spd);
 
-	splice_shrink_spd(pipe, &spd);
+	splice_shrink_spd(&spd);
 	return ret;
 }
 

include/linux/blkdev.h

@@ -827,7 +827,6 @@ extern bool __blk_end_request_err(struct request *rq, int error);
 extern void blk_complete_request(struct request *);
 extern void __blk_complete_request(struct request *);
 extern void blk_abort_request(struct request *);
-extern void blk_abort_queue(struct request_queue *);
 extern void blk_unprep_request(struct request *);
 
 /*

include/linux/splice.h

@@ -51,7 +51,8 @@ struct partial_page {
 struct splice_pipe_desc {
 	struct page **pages;		/* page map */
 	struct partial_page *partial;	/* pages[] may not be contig */
-	int nr_pages;			/* number of pages in map */
+	int nr_pages;			/* number of populated pages in map */
+	unsigned int nr_pages_max;	/* pages[] & partial[] arrays size */
 	unsigned int flags;		/* splice flags */
 	const struct pipe_buf_operations *ops;/* ops associated with output pipe */
 	void (*spd_release)(struct splice_pipe_desc *, unsigned int);
@@ -85,9 +86,8 @@ extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *,
 /*
  * for dynamic pipe sizing
  */
-extern int splice_grow_spd(struct pipe_inode_info *, struct splice_pipe_desc *);
-extern void splice_shrink_spd(struct pipe_inode_info *,
-				struct splice_pipe_desc *);
+extern int splice_grow_spd(const struct pipe_inode_info *, struct splice_pipe_desc *);
+extern void splice_shrink_spd(struct splice_pipe_desc *);
 extern void spd_release_page(struct splice_pipe_desc *, unsigned int);
 
 extern const struct pipe_buf_operations page_cache_pipe_buf_ops;

kernel/relay.c

@@ -1235,6 +1235,7 @@ static ssize_t subbuf_splice_actor(struct file *in,
 	struct splice_pipe_desc spd = {
 		.pages = pages,
 		.nr_pages = 0,
+		.nr_pages_max = PIPE_DEF_BUFFERS,
 		.partial = partial,
 		.flags = flags,
 		.ops = &relay_pipe_buf_ops,
@@ -1302,8 +1303,8 @@ static ssize_t subbuf_splice_actor(struct file *in,
                 ret += padding;
 
 out:
-	splice_shrink_spd(pipe, &spd);
-        return ret;
+	splice_shrink_spd(&spd);
+	return ret;
 }
 
 static ssize_t relay_file_splice_read(struct file *in,

kernel/trace/trace.c

@@ -3609,6 +3609,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 		.pages		= pages_def,
 		.partial	= partial_def,
 		.nr_pages	= 0, /* This gets updated below. */
+		.nr_pages_max	= PIPE_DEF_BUFFERS,
 		.flags		= flags,
 		.ops		= &tracing_pipe_buf_ops,
 		.spd_release	= tracing_spd_release_pipe,
@@ -3680,7 +3681,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 
 	ret = splice_to_pipe(pipe, &spd);
 out:
-	splice_shrink_spd(pipe, &spd);
+	splice_shrink_spd(&spd);
 	return ret;
 
 out_err:
@@ -4231,6 +4232,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 	struct splice_pipe_desc spd = {
 		.pages		= pages_def,
 		.partial	= partial_def,
+		.nr_pages_max	= PIPE_DEF_BUFFERS,
 		.flags		= flags,
 		.ops		= &buffer_pipe_buf_ops,
 		.spd_release	= buffer_spd_release,
@@ -4318,7 +4320,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 	}
 
 	ret = splice_to_pipe(pipe, &spd);
-	splice_shrink_spd(pipe, &spd);
+	splice_shrink_spd(&spd);
 out:
 	return ret;
 }

mm/shmem.c

@@ -1594,6 +1594,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
 	struct splice_pipe_desc spd = {
 		.pages = pages,
 		.partial = partial,
+		.nr_pages_max = PIPE_DEF_BUFFERS,
 		.flags = flags,
 		.ops = &page_cache_pipe_buf_ops,
 		.spd_release = spd_release_page,
@@ -1682,7 +1683,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
 	if (spd.nr_pages)
 		error = splice_to_pipe(pipe, &spd);
 
-	splice_shrink_spd(pipe, &spd);
+	splice_shrink_spd(&spd);
 
 	if (error > 0) {
 		*ppos += error;

net/core/skbuff.c

@@ -1755,6 +1755,7 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset,
 	struct splice_pipe_desc spd = {
 		.pages = pages,
 		.partial = partial,
+		.nr_pages_max = MAX_SKB_FRAGS,
 		.flags = flags,
 		.ops = &sock_pipe_buf_ops,
 		.spd_release = sock_spd_release,