8 files changed, 87 insertions, 121 deletions

diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index 811e11c82f32..0809cda93cc0 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -2954,7 +2954,7 @@ DAC960_DetectController(struct pci_dev *PCI_Device,
 	case DAC960_PD_Controller:
 	  if (!request_region(Controller->IO_Address, 0x80,
 			      Controller->FullModelName)) {
-		DAC960_Error("IO port 0x%d busy for Controller at\n",
+		DAC960_Error("IO port 0x%lx busy for Controller at\n",
 			     Controller, Controller->IO_Address);
 		goto Failure;
 	  }
@@ -2990,7 +2990,7 @@ DAC960_DetectController(struct pci_dev *PCI_Device,
 	case DAC960_P_Controller:
 	  if (!request_region(Controller->IO_Address, 0x80,
 			      Controller->FullModelName)){
-		DAC960_Error("IO port 0x%d busy for Controller at\n",
+		DAC960_Error("IO port 0x%lx busy for Controller at\n",
 		   	     Controller, Controller->IO_Address);
 		goto Failure;
 	  }
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index ab19adb07a12..3c606c09fd5a 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -853,45 +853,6 @@ rqbiocnt(struct request *r)
 	return n;
 }
 
-/* This can be removed if we are certain that no users of the block
- * layer will ever use zero-count pages in bios.  Otherwise we have to
- * protect against the put_page sometimes done by the network layer.
- *
- * See http://oss.sgi.com/archives/xfs/2007-01/msg00594.html for
- * discussion.
- *
- * We cannot use get_page in the workaround, because it insists on a
- * positive page count as a precondition.  So we use _refcount directly.
- */
-static void
-bio_pageinc(struct bio *bio)
-{
-	struct bio_vec bv;
-	struct page *page;
-	struct bvec_iter iter;
-
-	bio_for_each_segment(bv, bio, iter) {
-		/* Non-zero page count for non-head members of
-		 * compound pages is no longer allowed by the kernel.
-		 */
-		page = compound_head(bv.bv_page);
-		page_ref_inc(page);
-	}
-}
-
-static void
-bio_pagedec(struct bio *bio)
-{
-	struct page *page;
-	struct bio_vec bv;
-	struct bvec_iter iter;
-
-	bio_for_each_segment(bv, bio, iter) {
-		page = compound_head(bv.bv_page);
-		page_ref_dec(page);
-	}
-}
-
 static void
 bufinit(struct buf *buf, struct request *rq, struct bio *bio)
 {
@@ -899,7 +860,6 @@ bufinit(struct buf *buf, struct request *rq, struct bio *bio)
 	buf->rq = rq;
 	buf->bio = bio;
 	buf->iter = bio->bi_iter;
-	bio_pageinc(bio);
 }
 
 static struct buf *
@@ -1127,7 +1087,6 @@ aoe_end_buf(struct aoedev *d, struct buf *buf)
 	if (buf == d->ip.buf)
 		d->ip.buf = NULL;
 	rq = buf->rq;
-	bio_pagedec(buf->bio);
 	mempool_free(buf, d->bufpool);
 	n = (unsigned long) rq->special;
 	rq->special = (void *) --n;
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 100be556e613..83482721bc01 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -1871,7 +1871,7 @@ int drbd_send(struct drbd_connection *connection, struct socket *sock,
 		drbd_update_congested(connection);
 	}
 	do {
-		rv = kernel_sendmsg(sock, &msg, &iov, 1, size);
+		rv = kernel_sendmsg(sock, &msg, &iov, 1, iov.iov_len);
 		if (rv == -EAGAIN) {
 			if (we_should_drop_the_connection(connection, sock))
 				break;
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index abb71628ab61..7b274ff4632c 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -415,15 +415,15 @@ struct rbd_device {
 };
 
 /*
- * Flag bits for rbd_dev->flags.  If atomicity is required,
- * rbd_dev->lock is used to protect access.
- *
- * Currently, only the "removing" flag (which is coupled with the
- * "open_count" field) requires atomic access.
+ * Flag bits for rbd_dev->flags:
+ * - REMOVING (which is coupled with rbd_dev->open_count) is protected
+ *   by rbd_dev->lock
+ * - BLACKLISTED is protected by rbd_dev->lock_rwsem
  */
 enum rbd_dev_flags {
 	RBD_DEV_FLAG_EXISTS,	/* mapped snapshot has not been deleted */
 	RBD_DEV_FLAG_REMOVING,	/* this mapping is being removed */
+	RBD_DEV_FLAG_BLACKLISTED, /* our ceph_client is blacklisted */
 };
 
 static DEFINE_MUTEX(client_mutex);	/* Serialize client creation */
@@ -3926,6 +3926,7 @@ static void rbd_reregister_watch(struct work_struct *work)
 	struct rbd_device *rbd_dev = container_of(to_delayed_work(work),
 					    struct rbd_device, watch_dwork);
 	bool was_lock_owner = false;
+	bool need_to_wake = false;
 	int ret;
 
 	dout("%s rbd_dev %p\n", __func__, rbd_dev);
@@ -3935,19 +3936,27 @@ static void rbd_reregister_watch(struct work_struct *work)
 		was_lock_owner = rbd_release_lock(rbd_dev);
 
 	mutex_lock(&rbd_dev->watch_mutex);
-	if (rbd_dev->watch_state != RBD_WATCH_STATE_ERROR)
-		goto fail_unlock;
+	if (rbd_dev->watch_state != RBD_WATCH_STATE_ERROR) {
+		mutex_unlock(&rbd_dev->watch_mutex);
+		goto out;
+	}
 
 	ret = __rbd_register_watch(rbd_dev);
 	if (ret) {
 		rbd_warn(rbd_dev, "failed to reregister watch: %d", ret);
-		if (ret != -EBLACKLISTED)
+		if (ret == -EBLACKLISTED || ret == -ENOENT) {
+			set_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags);
+			need_to_wake = true;
+		} else {
 			queue_delayed_work(rbd_dev->task_wq,
 					   &rbd_dev->watch_dwork,
 					   RBD_RETRY_DELAY);
-		goto fail_unlock;
+		}
+		mutex_unlock(&rbd_dev->watch_mutex);
+		goto out;
 	}
 
+	need_to_wake = true;
 	rbd_dev->watch_state = RBD_WATCH_STATE_REGISTERED;
 	rbd_dev->watch_cookie = rbd_dev->watch_handle->linger_id;
 	mutex_unlock(&rbd_dev->watch_mutex);
@@ -3963,13 +3972,10 @@ static void rbd_reregister_watch(struct work_struct *work)
 				 ret);
 	}
 
+out:
 	up_write(&rbd_dev->lock_rwsem);
-	wake_requests(rbd_dev, true);
-	return;
-
-fail_unlock:
-	mutex_unlock(&rbd_dev->watch_mutex);
-	up_write(&rbd_dev->lock_rwsem);
+	if (need_to_wake)
+		wake_requests(rbd_dev, true);
 }
 
 /*
@@ -4074,7 +4080,9 @@ static void rbd_wait_state_locked(struct rbd_device *rbd_dev)
 		up_read(&rbd_dev->lock_rwsem);
 		schedule();
 		down_read(&rbd_dev->lock_rwsem);
-	} while (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED);
+	} while (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED &&
+		 !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags));
+
 	finish_wait(&rbd_dev->lock_waitq, &wait);
 }
 
@@ -4166,8 +4174,16 @@ static void rbd_queue_workfn(struct work_struct *work)
 
 	if (must_be_locked) {
 		down_read(&rbd_dev->lock_rwsem);
-		if (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED)
+		if (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED &&
+		    !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags))
 			rbd_wait_state_locked(rbd_dev);
+
+		WARN_ON((rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED) ^
+			!test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags));
+		if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
+			result = -EBLACKLISTED;
+			goto err_unlock;
+		}
 	}
 
 	img_request = rbd_img_request_create(rbd_dev, offset, length, op_type,
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 2dc5c96c186a..5545a679abd8 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -376,7 +376,7 @@ static void virtblk_config_changed(struct virtio_device *vdev)
 
 static int init_vq(struct virtio_blk *vblk)
 {
-	int err = 0;
+	int err;
 	int i;
 	vq_callback_t **callbacks;
 	const char **names;
@@ -390,13 +390,13 @@ static int init_vq(struct virtio_blk *vblk)
 	if (err)
 		num_vqs = 1;
 
-	vblk->vqs = kmalloc(sizeof(*vblk->vqs) * num_vqs, GFP_KERNEL);
+	vblk->vqs = kmalloc_array(num_vqs, sizeof(*vblk->vqs), GFP_KERNEL);
 	if (!vblk->vqs)
 		return -ENOMEM;
 
-	names = kmalloc(sizeof(*names) * num_vqs, GFP_KERNEL);
-	callbacks = kmalloc(sizeof(*callbacks) * num_vqs, GFP_KERNEL);
-	vqs = kmalloc(sizeof(*vqs) * num_vqs, GFP_KERNEL);
+	names = kmalloc_array(num_vqs, sizeof(*names), GFP_KERNEL);
+	callbacks = kmalloc_array(num_vqs, sizeof(*callbacks), GFP_KERNEL);
+	vqs = kmalloc_array(num_vqs, sizeof(*vqs), GFP_KERNEL);
 	if (!names || !callbacks || !vqs) {
 		err = -ENOMEM;
 		goto out;
diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
index 4b5cd3a7b2b6..12046f4f00e4 100644
--- a/drivers/block/zram/zcomp.c
+++ b/drivers/block/zram/zcomp.c
@@ -160,82 +160,56 @@ int zcomp_decompress(struct zcomp_strm *zstrm,
 			dst, &dst_len);
 }
 
-static int __zcomp_cpu_notifier(struct zcomp *comp,
-		unsigned long action, unsigned long cpu)
+int zcomp_cpu_up_prepare(unsigned int cpu, struct hlist_node *node)
 {
+	struct zcomp *comp = hlist_entry(node, struct zcomp, node);
 	struct zcomp_strm *zstrm;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-		if (WARN_ON(*per_cpu_ptr(comp->stream, cpu)))
-			break;
-		zstrm = zcomp_strm_alloc(comp);
-		if (IS_ERR_OR_NULL(zstrm)) {
-			pr_err("Can't allocate a compression stream\n");
-			return NOTIFY_BAD;
-		}
-		*per_cpu_ptr(comp->stream, cpu) = zstrm;
-		break;
-	case CPU_DEAD:
-	case CPU_UP_CANCELED:
-		zstrm = *per_cpu_ptr(comp->stream, cpu);
-		if (!IS_ERR_OR_NULL(zstrm))
-			zcomp_strm_free(zstrm);
-		*per_cpu_ptr(comp->stream, cpu) = NULL;
-		break;
-	default:
-		break;
+	if (WARN_ON(*per_cpu_ptr(comp->stream, cpu)))
+		return 0;
+
+	zstrm = zcomp_strm_alloc(comp);
+	if (IS_ERR_OR_NULL(zstrm)) {
+		pr_err("Can't allocate a compression stream\n");
+		return -ENOMEM;
 	}
-	return NOTIFY_OK;
+	*per_cpu_ptr(comp->stream, cpu) = zstrm;
+	return 0;
 }
 
-static int zcomp_cpu_notifier(struct notifier_block *nb,
-		unsigned long action, void *pcpu)
+int zcomp_cpu_dead(unsigned int cpu, struct hlist_node *node)
 {
-	unsigned long cpu = (unsigned long)pcpu;
-	struct zcomp *comp = container_of(nb, typeof(*comp), notifier);
+	struct zcomp *comp = hlist_entry(node, struct zcomp, node);
+	struct zcomp_strm *zstrm;
 
-	return __zcomp_cpu_notifier(comp, action, cpu);
+	zstrm = *per_cpu_ptr(comp->stream, cpu);
+	if (!IS_ERR_OR_NULL(zstrm))
+		zcomp_strm_free(zstrm);
+	*per_cpu_ptr(comp->stream, cpu) = NULL;
+	return 0;
 }
 
 static int zcomp_init(struct zcomp *comp)
 {
-	unsigned long cpu;
 	int ret;
 
-	comp->notifier.notifier_call = zcomp_cpu_notifier;
-
 	comp->stream = alloc_percpu(struct zcomp_strm *);
 	if (!comp->stream)
 		return -ENOMEM;
 
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu) {
-		ret = __zcomp_cpu_notifier(comp, CPU_UP_PREPARE, cpu);
-		if (ret == NOTIFY_BAD)
-			goto cleanup;
-	}
-	__register_cpu_notifier(&comp->notifier);
-	cpu_notifier_register_done();
+	ret = cpuhp_state_add_instance(CPUHP_ZCOMP_PREPARE, &comp->node);
+	if (ret < 0)
+		goto cleanup;
 	return 0;
 
 cleanup:
-	for_each_online_cpu(cpu)
-		__zcomp_cpu_notifier(comp, CPU_UP_CANCELED, cpu);
-	cpu_notifier_register_done();
-	return -ENOMEM;
+	free_percpu(comp->stream);
+	return ret;
 }
 
 void zcomp_destroy(struct zcomp *comp)
 {
-	unsigned long cpu;
-
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		__zcomp_cpu_notifier(comp, CPU_UP_CANCELED, cpu);
-	__unregister_cpu_notifier(&comp->notifier);
-	cpu_notifier_register_done();
-
+	cpuhp_state_remove_instance(CPUHP_ZCOMP_PREPARE, &comp->node);
 	free_percpu(comp->stream);
 	kfree(comp);
 }
diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h
index 478cac2ed465..41c1002a7d7d 100644
--- a/drivers/block/zram/zcomp.h
+++ b/drivers/block/zram/zcomp.h
@@ -19,11 +19,12 @@ struct zcomp_strm {
 /* dynamic per-device compression frontend */
 struct zcomp {
 	struct zcomp_strm * __percpu *stream;
-	struct notifier_block notifier;
-
 	const char *name;
+	struct hlist_node node;
 };
 
+int zcomp_cpu_up_prepare(unsigned int cpu, struct hlist_node *node);
+int zcomp_cpu_dead(unsigned int cpu, struct hlist_node *node);
 ssize_t zcomp_available_show(const char *comp, char *buf);
 bool zcomp_available_algorithm(const char *comp);
 
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 04365b17ee67..15f58ab44d0b 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -30,6 +30,7 @@
 #include <linux/err.h>
 #include <linux/idr.h>
 #include <linux/sysfs.h>
+#include <linux/cpuhotplug.h>
 
 #include "zram_drv.h"
 
@@ -1403,7 +1404,8 @@ static ssize_t hot_remove_store(struct class *class,
 	zram = idr_find(&zram_index_idr, dev_id);
 	if (zram) {
 		ret = zram_remove(zram);
-		idr_remove(&zram_index_idr, dev_id);
+		if (!ret)
+			idr_remove(&zram_index_idr, dev_id);
 	} else {
 		ret = -ENODEV;
 	}
@@ -1412,8 +1414,14 @@ static ssize_t hot_remove_store(struct class *class,
 	return ret ? ret : count;
 }
 
+/*
+ * NOTE: hot_add attribute is not the usual read-only sysfs attribute. In a
+ * sense that reading from this file does alter the state of your system -- it
+ * creates a new un-initialized zram device and returns back this device's
+ * device_id (or an error code if it fails to create a new device).
+ */
 static struct class_attribute zram_control_class_attrs[] = {
-	__ATTR_RO(hot_add),
+	__ATTR(hot_add, 0400, hot_add_show, NULL),
 	__ATTR_WO(hot_remove),
 	__ATTR_NULL,
 };
@@ -1436,15 +1444,22 @@ static void destroy_devices(void)
 	idr_for_each(&zram_index_idr, &zram_remove_cb, NULL);
 	idr_destroy(&zram_index_idr);
 	unregister_blkdev(zram_major, "zram");
+	cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE);
 }
 
 static int __init zram_init(void)
 {
 	int ret;
 
+	ret = cpuhp_setup_state_multi(CPUHP_ZCOMP_PREPARE, "block/zram:prepare",
+				      zcomp_cpu_up_prepare, zcomp_cpu_dead);
+	if (ret < 0)
+		return ret;
+
 	ret = class_register(&zram_control_class);
 	if (ret) {
 		pr_err("Unable to register zram-control class\n");
+		cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE);
 		return ret;
 	}
 
@@ -1452,6 +1467,7 @@ static int __init zram_init(void)
 	if (zram_major <= 0) {
 		pr_err("Unable to get major number\n");
 		class_unregister(&zram_control_class);
+		cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE);
 		return -EBUSY;
 	}