Merge tag 'v3.10.30' into linux-linaro-lskHEADlinux-linaro-lsk-v3.10linux-linaro-lsk

This is the 3.10.30 stable release

11 files changed, 147 insertions, 30 deletions

diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 3bfc8f1da9f..29cff90096a 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -176,8 +176,12 @@ config MD_FAULTY
 
 source "drivers/md/bcache/Kconfig"
 
+config BLK_DEV_DM_BUILTIN
+	boolean
+
 config BLK_DEV_DM
 	tristate "Device mapper support"
+	select BLK_DEV_DM_BUILTIN
 	---help---
 	  Device-mapper is a low level volume manager.  It works by allowing
 	  people to specify mappings for ranges of logical sectors.  Various
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 1439fd4ad9b..3591a729238 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -32,6 +32,7 @@ obj-$(CONFIG_MD_FAULTY)		+= faulty.o
 obj-$(CONFIG_BCACHE)		+= bcache/
 obj-$(CONFIG_BLK_DEV_MD)	+= md-mod.o
 obj-$(CONFIG_BLK_DEV_DM)	+= dm-mod.o
+obj-$(CONFIG_BLK_DEV_DM_BUILTIN) += dm-builtin.o
 obj-$(CONFIG_DM_BUFIO)		+= dm-bufio.o
 obj-$(CONFIG_DM_BIO_PRISON)	+= dm-bio-prison.o
 obj-$(CONFIG_DM_CRYPT)		+= dm-crypt.o
diff --git a/drivers/md/dm-builtin.c b/drivers/md/dm-builtin.c
new file mode 100644
index 00000000000..6c9049c51b2
--- /dev/null
+++ b/drivers/md/dm-builtin.c
@@ -0,0 +1,48 @@
+#include "dm.h"
+
+/*
+ * The kobject release method must not be placed in the module itself,
+ * otherwise we are subject to module unload races.
+ *
+ * The release method is called when the last reference to the kobject is
+ * dropped. It may be called by any other kernel code that drops the last
+ * reference.
+ *
+ * The release method suffers from module unload race. We may prevent the
+ * module from being unloaded at the start of the release method (using
+ * increased module reference count or synchronizing against the release
+ * method), however there is no way to prevent the module from being
+ * unloaded at the end of the release method.
+ *
+ * If this code were placed in the dm module, the following race may
+ * happen:
+ *  1. Some other process takes a reference to dm kobject
+ *  2. The user issues ioctl function to unload the dm device
+ *  3. dm_sysfs_exit calls kobject_put, however the object is not released
+ *     because of the other reference taken at step 1
+ *  4. dm_sysfs_exit waits on the completion
+ *  5. The other process that took the reference in step 1 drops it,
+ *     dm_kobject_release is called from this process
+ *  6. dm_kobject_release calls complete()
+ *  7. a reschedule happens before dm_kobject_release returns
+ *  8. dm_sysfs_exit continues, the dm device is unloaded, module reference
+ *     count is decremented
+ *  9. The user unloads the dm module
+ * 10. The other process that was rescheduled in step 7 continues to run,
+ *     it is now executing code in unloaded module, so it crashes
+ *
+ * Note that if the process that takes the foreign reference to dm kobject
+ * has a low priority and the system is sufficiently loaded with
+ * higher-priority processes that prevent the low-priority process from
+ * being scheduled long enough, this bug may really happen.
+ *
+ * In order to fix this module unload race, we place the release method
+ * into a helper code that is compiled directly into the kernel.
+ */
+
+void dm_kobject_release(struct kobject *kobj)
+{
+	complete(dm_get_completion_from_kobject(kobj));
+}
+
+EXPORT_SYMBOL(dm_kobject_release);
diff --git a/drivers/md/dm-sysfs.c b/drivers/md/dm-sysfs.c
index 84d2b91e4ef..c62c5ab6aed 100644
--- a/drivers/md/dm-sysfs.c
+++ b/drivers/md/dm-sysfs.c
@@ -86,6 +86,7 @@ static const struct sysfs_ops dm_sysfs_ops = {
 static struct kobj_type dm_ktype = {
 	.sysfs_ops	= &dm_sysfs_ops,
 	.default_attrs	= dm_attrs,
+	.release	= dm_kobject_release,
 };
 
 /*
@@ -104,5 +105,7 @@ int dm_sysfs_init(struct mapped_device *md)
  */
 void dm_sysfs_exit(struct mapped_device *md)
 {
-	kobject_put(dm_kobject(md));
+	struct kobject *kobj = dm_kobject(md);
+	kobject_put(kobj);
+	wait_for_completion(dm_get_completion_from_kobject(kobj));
 }
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 60bce435f4f..33ac3be2e83 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -1349,6 +1349,12 @@ dm_thin_id dm_thin_dev_id(struct dm_thin_device *td)
 	return td->id;
 }
 
+/*
+ * Check whether @time (of block creation) is older than @td's last snapshot.
+ * If so then the associated block is shared with the last snapshot device.
+ * Any block on a device created *after* the device last got snapshotted is
+ * necessarily not shared.
+ */
 static bool __snapshotted_since(struct dm_thin_device *td, uint32_t time)
 {
 	return td->snapshotted_time > time;
@@ -1458,6 +1464,20 @@ int dm_thin_remove_block(struct dm_thin_device *td, dm_block_t block)
 	return r;
 }
 
+int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *result)
+{
+	int r;
+	uint32_t ref_count;
+
+	down_read(&pmd->root_lock);
+	r = dm_sm_get_count(pmd->data_sm, b, &ref_count);
+	if (!r)
+		*result = (ref_count != 0);
+	up_read(&pmd->root_lock);
+
+	return r;
+}
+
 bool dm_thin_changed_this_transaction(struct dm_thin_device *td)
 {
 	int r;
diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h
index 845ebbe589a..125c0944401 100644
--- a/drivers/md/dm-thin-metadata.h
+++ b/drivers/md/dm-thin-metadata.h
@@ -181,6 +181,8 @@ int dm_pool_get_data_block_size(struct dm_pool_metadata *pmd, sector_t *result);
 
 int dm_pool_get_data_dev_size(struct dm_pool_metadata *pmd, dm_block_t *result);
 
+int dm_pool_block_is_used(struct dm_pool_metadata *pmd, dm_block_t b, bool *result);
+
 /*
  * Returns -ENOSPC if the new size is too small and already allocated
  * blocks would be lost.
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index e36f81e282e..73c76c565a4 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -512,6 +512,7 @@ struct dm_thin_new_mapping {
 	unsigned quiesced:1;
 	unsigned prepared:1;
 	unsigned pass_discard:1;
+	unsigned definitely_not_shared:1;
 
 	struct thin_c *tc;
 	dm_block_t virt_block;
@@ -683,7 +684,15 @@ static void process_prepared_discard_passdown(struct dm_thin_new_mapping *m)
 	cell_defer_no_holder(tc, m->cell2);
 
 	if (m->pass_discard)
-		remap_and_issue(tc, m->bio, m->data_block);
+		if (m->definitely_not_shared)
+			remap_and_issue(tc, m->bio, m->data_block);
+		else {
+			bool used = false;
+			if (dm_pool_block_is_used(tc->pool->pmd, m->data_block, &used) || used)
+				bio_endio(m->bio, 0);
+			else
+				remap_and_issue(tc, m->bio, m->data_block);
+		}
 	else
 		bio_endio(m->bio, 0);
 
@@ -751,13 +760,17 @@ static int ensure_next_mapping(struct pool *pool)
 
 static struct dm_thin_new_mapping *get_next_mapping(struct pool *pool)
 {
-	struct dm_thin_new_mapping *r = pool->next_mapping;
+	struct dm_thin_new_mapping *m = pool->next_mapping;
 
 	BUG_ON(!pool->next_mapping);
 
+	memset(m, 0, sizeof(struct dm_thin_new_mapping));
+	INIT_LIST_HEAD(&m->list);
+	m->bio = NULL;
+
 	pool->next_mapping = NULL;
 
-	return r;
+	return m;
 }
 
 static void schedule_copy(struct thin_c *tc, dm_block_t virt_block,
@@ -769,15 +782,10 @@ static void schedule_copy(struct thin_c *tc, dm_block_t virt_block,
 	struct pool *pool = tc->pool;
 	struct dm_thin_new_mapping *m = get_next_mapping(pool);
 
-	INIT_LIST_HEAD(&m->list);
-	m->quiesced = 0;
-	m->prepared = 0;
 	m->tc = tc;
 	m->virt_block = virt_block;
 	m->data_block = data_dest;
 	m->cell = cell;
-	m->err = 0;
-	m->bio = NULL;
 
 	if (!dm_deferred_set_add_work(pool->shared_read_ds, &m->list))
 		m->quiesced = 1;
@@ -840,15 +848,12 @@ static void schedule_zero(struct thin_c *tc, dm_block_t virt_block,
 	struct pool *pool = tc->pool;
 	struct dm_thin_new_mapping *m = get_next_mapping(pool);
 
-	INIT_LIST_HEAD(&m->list);
 	m->quiesced = 1;
 	m->prepared = 0;
 	m->tc = tc;
 	m->virt_block = virt_block;
 	m->data_block = data_block;
 	m->cell = cell;
-	m->err = 0;
-	m->bio = NULL;
 
 	/*
 	 * If the whole block of data is being overwritten or we are not
@@ -1032,12 +1037,12 @@ static void process_discard(struct thin_c *tc, struct bio *bio)
 			 */
 			m = get_next_mapping(pool);
 			m->tc = tc;
-			m->pass_discard = (!lookup_result.shared) && pool->pf.discard_passdown;
+			m->pass_discard = pool->pf.discard_passdown;
+			m->definitely_not_shared = !lookup_result.shared;
 			m->virt_block = block;
 			m->data_block = lookup_result.block;
 			m->cell = cell;
 			m->cell2 = cell2;
-			m->err = 0;
 			m->bio = bio;
 
 			if (!dm_deferred_set_add_work(pool->all_io_ds, &m->list)) {
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 1c13071a81b..204a59fd872 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -184,8 +184,8 @@ struct mapped_device {
 	/* forced geometry settings */
 	struct hd_geometry geometry;
 
-	/* sysfs handle */
-	struct kobject kobj;
+	/* kobject and completion */
+	struct dm_kobject_holder kobj_holder;
 
 	/* zero-length flush that will be cloned and submitted to targets */
 	struct bio flush_bio;
@@ -1904,6 +1904,7 @@ static struct mapped_device *alloc_dev(int minor)
 	init_waitqueue_head(&md->wait);
 	INIT_WORK(&md->work, dm_wq_work);
 	init_waitqueue_head(&md->eventq);
+	init_completion(&md->kobj_holder.completion);
 
 	md->disk->major = _major;
 	md->disk->first_minor = minor;
@@ -2735,20 +2736,14 @@ struct gendisk *dm_disk(struct mapped_device *md)
 
 struct kobject *dm_kobject(struct mapped_device *md)
 {
-	return &md->kobj;
+	return &md->kobj_holder.kobj;
 }
 
-/*
- * struct mapped_device should not be exported outside of dm.c
- * so use this check to verify that kobj is part of md structure
- */
 struct mapped_device *dm_get_from_kobject(struct kobject *kobj)
 {
 	struct mapped_device *md;
 
-	md = container_of(kobj, struct mapped_device, kobj);
-	if (&md->kobj != kobj)
-		return NULL;
+	md = container_of(kobj, struct mapped_device, kobj_holder.kobj);
 
 	if (test_bit(DMF_FREEING, &md->flags) ||
 	    dm_deleting_md(md))
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 45b97da1bd0..9b3222f4483 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -15,6 +15,8 @@
 #include <linux/list.h>
 #include <linux/blkdev.h>
 #include <linux/hdreg.h>
+#include <linux/completion.h>
+#include <linux/kobject.h>
 
 /*
  * Suspend feature flags
@@ -125,12 +127,27 @@ void dm_interface_exit(void);
 /*
  * sysfs interface
  */
+struct dm_kobject_holder {
+	struct kobject kobj;
+	struct completion completion;
+};
+
+static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj)
+{
+	return &container_of(kobj, struct dm_kobject_holder, kobj)->completion;
+}
+
 int dm_sysfs_init(struct mapped_device *md);
 void dm_sysfs_exit(struct mapped_device *md);
 struct kobject *dm_kobject(struct mapped_device *md);
 struct mapped_device *dm_get_from_kobject(struct kobject *kobj);
 
 /*
+ * The kobject helper
+ */
+void dm_kobject_release(struct kobject *kobj);
+
+/*
  * Targets for linear and striped mappings
  */
 int dm_linear_init(void);
diff --git a/drivers/md/persistent-data/dm-space-map-common.c b/drivers/md/persistent-data/dm-space-map-common.c
index 3e7a88d99eb..0d240373ffa 100644
--- a/drivers/md/persistent-data/dm-space-map-common.c
+++ b/drivers/md/persistent-data/dm-space-map-common.c
@@ -245,6 +245,10 @@ int sm_ll_extend(struct ll_disk *ll, dm_block_t extra_blocks)
 		return -EINVAL;
 	}
 
+	/*
+	 * We need to set this before the dm_tm_new_block() call below.
+	 */
+	ll->nr_blocks = nr_blocks;
 	for (i = old_blocks; i < blocks; i++) {
 		struct dm_block *b;
 		struct disk_index_entry idx;
@@ -252,6 +256,7 @@ int sm_ll_extend(struct ll_disk *ll, dm_block_t extra_blocks)
 		r = dm_tm_new_block(ll->tm, &dm_sm_bitmap_validator, &b);
 		if (r < 0)
 			return r;
+
 		idx.blocknr = cpu_to_le64(dm_block_location(b));
 
 		r = dm_tm_unlock(ll->tm, b);
@@ -266,7 +271,6 @@ int sm_ll_extend(struct ll_disk *ll, dm_block_t extra_blocks)
 			return r;
 	}
 
-	ll->nr_blocks = nr_blocks;
 	return 0;
 }
 
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
index 58fc1eef749..afb419e514b 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.c
+++ b/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -608,20 +608,38 @@ static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks)
 	 * Flick into a mode where all blocks get allocated in the new area.
 	 */
 	smm->begin = old_len;
-	memcpy(&smm->sm, &bootstrap_ops, sizeof(smm->sm));
+	memcpy(sm, &bootstrap_ops, sizeof(*sm));
 
 	/*
 	 * Extend.
 	 */
 	r = sm_ll_extend(&smm->ll, extra_blocks);
+	if (r)
+		goto out;
 
 	/*
-	 * Switch back to normal behaviour.
+	 * We repeatedly increment then commit until the commit doesn't
+	 * allocate any new blocks.
 	 */
-	memcpy(&smm->sm, &ops, sizeof(smm->sm));
-	for (i = old_len; !r && i < smm->begin; i++)
-		r = sm_ll_inc(&smm->ll, i, &ev);
+	do {
+		for (i = old_len; !r && i < smm->begin; i++) {
+			r = sm_ll_inc(&smm->ll, i, &ev);
+			if (r)
+				goto out;
+		}
+		old_len = smm->begin;
+
+		r = sm_ll_commit(&smm->ll);
+		if (r)
+			goto out;
+
+	} while (old_len != smm->begin);
 
+out:
+	/*
+	 * Switch back to normal behaviour.
+	 */
+	memcpy(sm, &ops, sizeof(*sm));
 	return r;
 }