dm bio prison v2: new interface for the bio prison

The deferred set is gone and all methods have _v2 appended to the end of
their names to allow for continued use of the original bio prison in DM
thin-provisioning.

Signed-off-by: Joe Thornber <ejt@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

drivers/md/Makefile

@@ -11,6 +11,7 @@ dm-snapshot-y	+= dm-snap.o dm-exception-store.o dm-snap-transient.o \
 dm-mirror-y	+= dm-raid1.o
 dm-log-userspace-y \
 		+= dm-log-userspace-base.o dm-log-userspace-transfer.o
+dm-bio-prison-y += dm-bio-prison-v1.o dm-bio-prison-v2.o
 dm-thin-pool-y	+= dm-thin.o dm-thin-metadata.o
 dm-cache-y	+= dm-cache-target.o dm-cache-metadata.o dm-cache-policy.o
 dm-cache-smq-y   += dm-cache-policy-smq.o

drivers/md/dm-bio-prison-v1.c

@@ -5,7 +5,8 @@
  */
 
 #include "dm.h"
-#include "dm-bio-prison.h"
+#include "dm-bio-prison-v1.h"
+#include "dm-bio-prison-v2.h"
 
 #include <linux/spinlock.h>
 #include <linux/mempool.h>
@@ -398,7 +399,7 @@ EXPORT_SYMBOL_GPL(dm_deferred_set_add_work);
 
 /*----------------------------------------------------------------*/
 
-static int __init dm_bio_prison_init(void)
+static int __init dm_bio_prison_init_v1(void)
 {
 	_cell_cache = KMEM_CACHE(dm_bio_prison_cell, 0);
 	if (!_cell_cache)
@@ -407,12 +408,51 @@ static int __init dm_bio_prison_init(void)
 	return 0;
 }
 
-static void __exit dm_bio_prison_exit(void)
+static void dm_bio_prison_exit_v1(void)
 {
 	kmem_cache_destroy(_cell_cache);
 	_cell_cache = NULL;
 }
 
+static int (*_inits[])(void) __initdata = {
+	dm_bio_prison_init_v1,
+	dm_bio_prison_init_v2,
+};
+
+static void (*_exits[])(void) = {
+	dm_bio_prison_exit_v1,
+	dm_bio_prison_exit_v2,
+};
+
+static int __init dm_bio_prison_init(void)
+{
+	const int count = ARRAY_SIZE(_inits);
+
+	int r, i;
+
+	for (i = 0; i < count; i++) {
+		r = _inits[i]();
+		if (r)
+			goto bad;
+	}
+
+	return 0;
+
+      bad:
+	while (i--)
+		_exits[i]();
+
+	return r;
+}
+
+static void __exit dm_bio_prison_exit(void)
+{
+	int i = ARRAY_SIZE(_exits);
+
+	while (i--)
+		_exits[i]();
+}
+
 /*
  * module hooks
  */

drivers/md/dm-bio-prison-v1.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2011-2012 Red Hat, Inc.
+ * Copyright (C) 2011-2017 Red Hat, Inc.
  *
  * This file is released under the GPL.
  */

drivers/md/dm-bio-prison-v2.c

@@ -0,0 +1,369 @@
+/*
+ * Copyright (C) 2012-2017 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#include "dm.h"
+#include "dm-bio-prison-v2.h"
+
+#include <linux/spinlock.h>
+#include <linux/mempool.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/rwsem.h>
+
+/*----------------------------------------------------------------*/
+
+#define MIN_CELLS 1024
+
+struct dm_bio_prison_v2 {
+	struct workqueue_struct *wq;
+
+	spinlock_t lock;
+	mempool_t *cell_pool;
+	struct rb_root cells;
+};
+
+static struct kmem_cache *_cell_cache;
+
+/*----------------------------------------------------------------*/
+
+/*
+ * @nr_cells should be the number of cells you want in use _concurrently_.
+ * Don't confuse it with the number of distinct keys.
+ */
+struct dm_bio_prison_v2 *dm_bio_prison_create_v2(struct workqueue_struct *wq)
+{
+	struct dm_bio_prison_v2 *prison = kmalloc(sizeof(*prison), GFP_KERNEL);
+
+	if (!prison)
+		return NULL;
+
+	prison->wq = wq;
+	spin_lock_init(&prison->lock);
+
+	prison->cell_pool = mempool_create_slab_pool(MIN_CELLS, _cell_cache);
+	if (!prison->cell_pool) {
+		kfree(prison);
+		return NULL;
+	}
+
+	prison->cells = RB_ROOT;
+
+	return prison;
+}
+EXPORT_SYMBOL_GPL(dm_bio_prison_create_v2);
+
+void dm_bio_prison_destroy_v2(struct dm_bio_prison_v2 *prison)
+{
+	mempool_destroy(prison->cell_pool);
+	kfree(prison);
+}
+EXPORT_SYMBOL_GPL(dm_bio_prison_destroy_v2);
+
+struct dm_bio_prison_cell_v2 *dm_bio_prison_alloc_cell_v2(struct dm_bio_prison_v2 *prison, gfp_t gfp)
+{
+	return mempool_alloc(prison->cell_pool, gfp);
+}
+EXPORT_SYMBOL_GPL(dm_bio_prison_alloc_cell_v2);
+
+void dm_bio_prison_free_cell_v2(struct dm_bio_prison_v2 *prison,
+				struct dm_bio_prison_cell_v2 *cell)
+{
+	mempool_free(cell, prison->cell_pool);
+}
+EXPORT_SYMBOL_GPL(dm_bio_prison_free_cell_v2);
+
+static void __setup_new_cell(struct dm_cell_key_v2 *key,
+			     struct dm_bio_prison_cell_v2 *cell)
+{
+	memset(cell, 0, sizeof(*cell));
+	memcpy(&cell->key, key, sizeof(cell->key));
+	bio_list_init(&cell->bios);
+}
+
+static int cmp_keys(struct dm_cell_key_v2 *lhs,
+		    struct dm_cell_key_v2 *rhs)
+{
+	if (lhs->virtual < rhs->virtual)
+		return -1;
+
+	if (lhs->virtual > rhs->virtual)
+		return 1;
+
+	if (lhs->dev < rhs->dev)
+		return -1;
+
+	if (lhs->dev > rhs->dev)
+		return 1;
+
+	if (lhs->block_end <= rhs->block_begin)
+		return -1;
+
+	if (lhs->block_begin >= rhs->block_end)
+		return 1;
+
+	return 0;
+}
+
+/*
+ * Returns true if node found, otherwise it inserts a new one.
+ */
+static bool __find_or_insert(struct dm_bio_prison_v2 *prison,
+			     struct dm_cell_key_v2 *key,
+			     struct dm_bio_prison_cell_v2 *cell_prealloc,
+			     struct dm_bio_prison_cell_v2 **result)
+{
+	int r;
+	struct rb_node **new = &prison->cells.rb_node, *parent = NULL;
+
+	while (*new) {
+		struct dm_bio_prison_cell_v2 *cell =
+			container_of(*new, struct dm_bio_prison_cell_v2, node);
+
+		r = cmp_keys(key, &cell->key);
+
+		parent = *new;
+		if (r < 0)
+			new = &((*new)->rb_left);
+
+		else if (r > 0)
+			new = &((*new)->rb_right);
+
+		else {
+			*result = cell;
+			return true;
+		}
+	}
+
+	__setup_new_cell(key, cell_prealloc);
+	*result = cell_prealloc;
+	rb_link_node(&cell_prealloc->node, parent, new);
+	rb_insert_color(&cell_prealloc->node, &prison->cells);
+
+	return false;
+}
+
+static bool __get(struct dm_bio_prison_v2 *prison,
+		  struct dm_cell_key_v2 *key,
+		  unsigned lock_level,
+		  struct bio *inmate,
+		  struct dm_bio_prison_cell_v2 *cell_prealloc,
+		  struct dm_bio_prison_cell_v2 **cell)
+{
+	if (__find_or_insert(prison, key, cell_prealloc, cell)) {
+		if ((*cell)->exclusive_lock) {
+			if (lock_level <= (*cell)->exclusive_level) {
+				bio_list_add(&(*cell)->bios, inmate);
+				return false;
+			}
+		}
+
+		(*cell)->shared_count++;
+
+	} else
+		(*cell)->shared_count = 1;
+
+	return true;
+}
+
+bool dm_cell_get_v2(struct dm_bio_prison_v2 *prison,
+		    struct dm_cell_key_v2 *key,
+		    unsigned lock_level,
+		    struct bio *inmate,
+		    struct dm_bio_prison_cell_v2 *cell_prealloc,
+		    struct dm_bio_prison_cell_v2 **cell_result)
+{
+	int r;
+	unsigned long flags;
+
+	spin_lock_irqsave(&prison->lock, flags);
+	r = __get(prison, key, lock_level, inmate, cell_prealloc, cell_result);
+	spin_unlock_irqrestore(&prison->lock, flags);
+
+	return r;
+}
+EXPORT_SYMBOL_GPL(dm_cell_get_v2);
+
+static bool __put(struct dm_bio_prison_v2 *prison,
+		  struct dm_bio_prison_cell_v2 *cell)
+{
+	BUG_ON(!cell->shared_count);
+	cell->shared_count--;
+
+	// FIXME: shared locks granted above the lock level could starve this
+	if (!cell->shared_count) {
+		if (cell->exclusive_lock){
+			if (cell->quiesce_continuation) {
+				queue_work(prison->wq, cell->quiesce_continuation);
+				cell->quiesce_continuation = NULL;
+			}
+		} else {
+			rb_erase(&cell->node, &prison->cells);
+			return true;
+		}
+	}
+
+	return false;
+}
+
+bool dm_cell_put_v2(struct dm_bio_prison_v2 *prison,
+		    struct dm_bio_prison_cell_v2 *cell)
+{
+	bool r;
+	unsigned long flags;
+
+	spin_lock_irqsave(&prison->lock, flags);
+	r = __put(prison, cell);
+	spin_unlock_irqrestore(&prison->lock, flags);
+
+	return r;
+}
+EXPORT_SYMBOL_GPL(dm_cell_put_v2);
+
+static int __lock(struct dm_bio_prison_v2 *prison,
+		  struct dm_cell_key_v2 *key,
+		  unsigned lock_level,
+		  struct dm_bio_prison_cell_v2 *cell_prealloc,
+		  struct dm_bio_prison_cell_v2 **cell_result)
+{
+	struct dm_bio_prison_cell_v2 *cell;
+
+	if (__find_or_insert(prison, key, cell_prealloc, &cell)) {
+		if (cell->exclusive_lock)
+			return -EBUSY;
+
+		cell->exclusive_lock = true;
+		cell->exclusive_level = lock_level;
+		*cell_result = cell;
+
+		// FIXME: we don't yet know what level these shared locks
+		// were taken at, so have to quiesce them all.
+		return cell->shared_count > 0;
+
+	} else {
+		cell = cell_prealloc;
+		cell->shared_count = 0;
+		cell->exclusive_lock = true;
+		cell->exclusive_level = lock_level;
+		*cell_result = cell;
+	}
+
+	return 0;
+}
+
+int dm_cell_lock_v2(struct dm_bio_prison_v2 *prison,
+		    struct dm_cell_key_v2 *key,
+		    unsigned lock_level,
+		    struct dm_bio_prison_cell_v2 *cell_prealloc,
+		    struct dm_bio_prison_cell_v2 **cell_result)
+{
+	int r;
+	unsigned long flags;
+
+	spin_lock_irqsave(&prison->lock, flags);
+	r = __lock(prison, key, lock_level, cell_prealloc, cell_result);
+	spin_unlock_irqrestore(&prison->lock, flags);
+
+	return r;
+}
+EXPORT_SYMBOL_GPL(dm_cell_lock_v2);
+
+static void __quiesce(struct dm_bio_prison_v2 *prison,
+		      struct dm_bio_prison_cell_v2 *cell,
+		      struct work_struct *continuation)
+{
+	if (!cell->shared_count)
+		queue_work(prison->wq, continuation);
+	else
+		cell->quiesce_continuation = continuation;
+}
+
+void dm_cell_quiesce_v2(struct dm_bio_prison_v2 *prison,
+			struct dm_bio_prison_cell_v2 *cell,
+			struct work_struct *continuation)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&prison->lock, flags);
+	__quiesce(prison, cell, continuation);
+	spin_unlock_irqrestore(&prison->lock, flags);
+}
+EXPORT_SYMBOL_GPL(dm_cell_quiesce_v2);
+
+static int __promote(struct dm_bio_prison_v2 *prison,
+		     struct dm_bio_prison_cell_v2 *cell,
+		     unsigned new_lock_level)
+{
+	if (!cell->exclusive_lock)
+		return -EINVAL;
+
+	cell->exclusive_level = new_lock_level;
+	return cell->shared_count > 0;
+}
+
+int dm_cell_lock_promote_v2(struct dm_bio_prison_v2 *prison,
+			    struct dm_bio_prison_cell_v2 *cell,
+			    unsigned new_lock_level)
+{
+	int r;
+	unsigned long flags;
+
+	spin_lock_irqsave(&prison->lock, flags);
+	r = __promote(prison, cell, new_lock_level);
+	spin_unlock_irqrestore(&prison->lock, flags);
+
+	return r;
+}
+EXPORT_SYMBOL_GPL(dm_cell_lock_promote_v2);
+
+static bool __unlock(struct dm_bio_prison_v2 *prison,
+		     struct dm_bio_prison_cell_v2 *cell,
+		     struct bio_list *bios)
+{
+	BUG_ON(!cell->exclusive_lock);
+
+	bio_list_merge(bios, &cell->bios);
+	bio_list_init(&cell->bios);
+
+	if (cell->shared_count) {
+		cell->exclusive_lock = 0;
+		return false;
+	}
+
+	rb_erase(&cell->node, &prison->cells);
+	return true;
+}
+
+bool dm_cell_unlock_v2(struct dm_bio_prison_v2 *prison,
+		       struct dm_bio_prison_cell_v2 *cell,
+		       struct bio_list *bios)
+{
+	bool r;
+	unsigned long flags;
+
+	spin_lock_irqsave(&prison->lock, flags);
+	r = __unlock(prison, cell, bios);
+	spin_unlock_irqrestore(&prison->lock, flags);
+
+	return r;
+}
+EXPORT_SYMBOL_GPL(dm_cell_unlock_v2);
+
+/*----------------------------------------------------------------*/
+
+int __init dm_bio_prison_init_v2(void)
+{
+	_cell_cache = KMEM_CACHE(dm_bio_prison_cell_v2, 0);
+	if (!_cell_cache)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void dm_bio_prison_exit_v2(void)
+{
+	kmem_cache_destroy(_cell_cache);
+	_cell_cache = NULL;
+}

drivers/md/dm-bio-prison-v2.h

@@ -0,0 +1,152 @@
+/*
+ * Copyright (C) 2011-2017 Red Hat, Inc.
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef DM_BIO_PRISON_V2_H
+#define DM_BIO_PRISON_V2_H
+
+#include "persistent-data/dm-block-manager.h" /* FIXME: for dm_block_t */
+#include "dm-thin-metadata.h" /* FIXME: for dm_thin_id */
+
+#include <linux/bio.h>
+#include <linux/rbtree.h>
+#include <linux/workqueue.h>
+
+/*----------------------------------------------------------------*/
+
+int dm_bio_prison_init_v2(void);
+void dm_bio_prison_exit_v2(void);
+
+/*
+ * Sometimes we can't deal with a bio straight away.  We put them in prison
+ * where they can't cause any mischief.  Bios are put in a cell identified
+ * by a key, multiple bios can be in the same cell.  When the cell is
+ * subsequently unlocked the bios become available.
+ */
+struct dm_bio_prison_v2;
+
+/*
+ * Keys define a range of blocks within either a virtual or physical
+ * device.
+ */
+struct dm_cell_key_v2 {
+	int virtual;
+	dm_thin_id dev;
+	dm_block_t block_begin, block_end;
+};
+
+/*
+ * Treat this as opaque, only in header so callers can manage allocation
+ * themselves.
+ */
+struct dm_bio_prison_cell_v2 {
+	// FIXME: pack these
+	bool exclusive_lock;
+	unsigned exclusive_level;
+	unsigned shared_count;
+	struct work_struct *quiesce_continuation;
+
+	struct rb_node node;
+	struct dm_cell_key_v2 key;
+	struct bio_list bios;
+};
+
+struct dm_bio_prison_v2 *dm_bio_prison_create_v2(struct workqueue_struct *wq);
+void dm_bio_prison_destroy_v2(struct dm_bio_prison_v2 *prison);
+
+/*
+ * These two functions just wrap a mempool.  This is a transitory step:
+ * Eventually all bio prison clients should manage their own cell memory.
+ *
+ * Like mempool_alloc(), dm_bio_prison_alloc_cell_v2() can only fail if called
+ * in interrupt context or passed GFP_NOWAIT.
+ */
+struct dm_bio_prison_cell_v2 *dm_bio_prison_alloc_cell_v2(struct dm_bio_prison_v2 *prison,
+						    gfp_t gfp);
+void dm_bio_prison_free_cell_v2(struct dm_bio_prison_v2 *prison,
+				struct dm_bio_prison_cell_v2 *cell);
+
+/*
+ * Shared locks have a bio associated with them.
+ *
+ * If the lock is granted the caller can continue to use the bio, and must
+ * call dm_cell_put_v2() to drop the reference count when finished using it.
+ *
+ * If the lock cannot be granted then the bio will be tracked within the
+ * cell, and later given to the holder of the exclusive lock.
+ *
+ * See dm_cell_lock_v2() for discussion of the lock_level parameter.
+ *
+ * Compare *cell_result with cell_prealloc to see if the prealloc was used.
+ * If cell_prealloc was used then inmate wasn't added to it.
+ *
+ * Returns true if the lock is granted.
+ */
+bool dm_cell_get_v2(struct dm_bio_prison_v2 *prison,
+		    struct dm_cell_key_v2 *key,
+		    unsigned lock_level,
+		    struct bio *inmate,
+		    struct dm_bio_prison_cell_v2 *cell_prealloc,
+		    struct dm_bio_prison_cell_v2 **cell_result);
+
+/*
+ * Decrement the shared reference count for the lock.  Returns true if
+ * returning ownership of the cell (ie. you should free it).
+ */
+bool dm_cell_put_v2(struct dm_bio_prison_v2 *prison,
+		    struct dm_bio_prison_cell_v2 *cell);
+
+/*
+ * Locks a cell.  No associated bio.  Exclusive locks get priority.  These
+ * locks constrain whether the io locks are granted according to level.
+ *
+ * Shared locks will still be granted if the lock_level is > (not = to) the
+ * exclusive lock level.
+ *
+ * If an _exclusive_ lock is already held then -EBUSY is returned.
+ *
+ * Return values:
+ *  < 0 - error
+ *  0   - locked; no quiescing needed
+ *  1   - locked; quiescing needed
+ */
+int dm_cell_lock_v2(struct dm_bio_prison_v2 *prison,
+		    struct dm_cell_key_v2 *key,
+		    unsigned lock_level,
+		    struct dm_bio_prison_cell_v2 *cell_prealloc,
+		    struct dm_bio_prison_cell_v2 **cell_result);
+
+void dm_cell_quiesce_v2(struct dm_bio_prison_v2 *prison,
+			struct dm_bio_prison_cell_v2 *cell,
+			struct work_struct *continuation);
+
+/*
+ * Promotes an _exclusive_ lock to a higher lock level.
+ *
+ * Return values:
+ *  < 0 - error
+ *  0   - promoted; no quiescing needed
+ *  1   - promoted; quiescing needed
+ */
+int dm_cell_lock_promote_v2(struct dm_bio_prison_v2 *prison,
+			    struct dm_bio_prison_cell_v2 *cell,
+			    unsigned new_lock_level);
+
+/*
+ * Adds any held bios to the bio list.
+ *
+ * There may be shared locks still held at this point even if you quiesced
+ * (ie. different lock levels).
+ *
+ * Returns true if returning ownership of the cell (ie. you should free
+ * it).
+ */
+bool dm_cell_unlock_v2(struct dm_bio_prison_v2 *prison,
+		       struct dm_bio_prison_cell_v2 *cell,
+		       struct bio_list *bios);
+
+/*----------------------------------------------------------------*/
+
+#endif

drivers/md/dm-cache-target.c

@@ -5,7 +5,7 @@
  */
 
 #include "dm.h"
-#include "dm-bio-prison.h"
+#include "dm-bio-prison-v1.h"
 #include "dm-bio-record.h"
 #include "dm-cache-metadata.h"
 

drivers/md/dm-thin.c

@@ -5,7 +5,7 @@
  */
 
 #include "dm-thin-metadata.h"
-#include "dm-bio-prison.h"
+#include "dm-bio-prison-v1.h"
 #include "dm.h"
 
 #include <linux/device-mapper.h>