dm: add ->flush() dax operation support

Allow device-mapper to route flush operations to the
per-target implementation. In order for the device stacking to work we
need a dax_dev and a pgoff relative to that device. This gives each
layer of the stack the information it needs to look up the operation
pointer for the next level.

This conceptually allows for an array of mixed device drivers with
varying flush implementations.
Reviewed-by: NToshi Kani <toshi.kani@hpe.com>
Reviewed-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>

drivers/dax/super.c

@@ -185,6 +185,17 @@ size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 }
 EXPORT_SYMBOL_GPL(dax_copy_from_iter);
 
+void dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
+		size_t size)
+{
+	if (!dax_alive(dax_dev))
+		return;
+
+	if (dax_dev->ops->flush)
+		dax_dev->ops->flush(dax_dev, pgoff, addr, size);
+}
+EXPORT_SYMBOL_GPL(dax_flush);
+
 bool dax_alive(struct dax_device *dax_dev)
 {
 	lockdep_assert_held(&dax_srcu);

drivers/md/dm-linear.c

@@ -173,6 +173,20 @@ static size_t linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff,
 	return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i);
 }
 
+static void linear_dax_flush(struct dm_target *ti, pgoff_t pgoff, void *addr,
+		size_t size)
+{
+	struct linear_c *lc = ti->private;
+	struct block_device *bdev = lc->dev->bdev;
+	struct dax_device *dax_dev = lc->dev->dax_dev;
+	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
+
+	dev_sector = linear_map_sector(ti, sector);
+	if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(size, PAGE_SIZE), &pgoff))
+		return;
+	dax_flush(dax_dev, pgoff, addr, size);
+}
+
 static struct target_type linear_target = {
 	.name   = "linear",
 	.version = {1, 3, 0},
@@ -186,6 +200,7 @@ static struct target_type linear_target = {
 	.iterate_devices = linear_iterate_devices,
 	.direct_access = linear_dax_direct_access,
 	.dax_copy_from_iter = linear_dax_copy_from_iter,
+	.dax_flush = linear_dax_flush,
 };
 
 int __init dm_linear_init(void)

drivers/md/dm-stripe.c

@@ -351,6 +351,25 @@ static size_t stripe_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff,
 	return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i);
 }
 
+static void stripe_dax_flush(struct dm_target *ti, pgoff_t pgoff, void *addr,
+		size_t size)
+{
+	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
+	struct stripe_c *sc = ti->private;
+	struct dax_device *dax_dev;
+	struct block_device *bdev;
+	uint32_t stripe;
+
+	stripe_map_sector(sc, sector, &stripe, &dev_sector);
+	dev_sector += sc->stripe[stripe].physical_start;
+	dax_dev = sc->stripe[stripe].dev->dax_dev;
+	bdev = sc->stripe[stripe].dev->bdev;
+
+	if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(size, PAGE_SIZE), &pgoff))
+		return;
+	dax_flush(dax_dev, pgoff, addr, size);
+}
+
 /*
  * Stripe status:
  *
@@ -471,6 +490,7 @@ static struct target_type stripe_target = {
 	.io_hints = stripe_io_hints,
 	.direct_access = stripe_dax_direct_access,
 	.dax_copy_from_iter = stripe_dax_copy_from_iter,
+	.dax_flush = stripe_dax_flush,
 };
 
 int __init dm_stripe_init(void)

drivers/md/dm.c

@@ -994,6 +994,24 @@ static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 	return ret;
 }
 
+static void dm_dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
+		size_t size)
+{
+	struct mapped_device *md = dax_get_private(dax_dev);
+	sector_t sector = pgoff * PAGE_SECTORS;
+	struct dm_target *ti;
+	int srcu_idx;
+
+	ti = dm_dax_get_live_target(md, sector, &srcu_idx);
+
+	if (!ti)
+		goto out;
+	if (ti->type->dax_flush)
+		ti->type->dax_flush(ti, pgoff, addr, size);
+ out:
+	dm_put_live_table(md, srcu_idx);
+}
+
 /*
  * A target may call dm_accept_partial_bio only from the map routine.  It is
  * allowed for all bio types except REQ_PREFLUSH.
@@ -2885,6 +2903,7 @@ static const struct block_device_operations dm_blk_dops = {
 static const struct dax_operations dm_dax_ops = {
 	.direct_access = dm_dax_direct_access,
 	.copy_from_iter = dm_dax_copy_from_iter,
+	.flush = dm_dax_flush,
 };
 
 /*

include/linux/dax.h

@@ -82,6 +82,8 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
 		void **kaddr, pfn_t *pfn);
 size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 		size_t bytes, struct iov_iter *i);
+void dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
+		size_t size);
 
 /*
  * We use lowest available bit in exceptional entry for locking, one bit for

include/linux/device-mapper.h

@@ -134,6 +134,8 @@ typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff,
 		long nr_pages, void **kaddr, pfn_t *pfn);
 typedef size_t (*dm_dax_copy_from_iter_fn)(struct dm_target *ti, pgoff_t pgoff,
 		void *addr, size_t bytes, struct iov_iter *i);
+typedef void (*dm_dax_flush_fn)(struct dm_target *ti, pgoff_t pgoff, void *addr,
+		size_t size);
 #define PAGE_SECTORS (PAGE_SIZE / 512)
 
 void dm_error(const char *message);
@@ -184,6 +186,7 @@ struct target_type {
 	dm_io_hints_fn io_hints;
 	dm_dax_direct_access_fn direct_access;
 	dm_dax_copy_from_iter_fn dax_copy_from_iter;
+	dm_dax_flush_fn dax_flush;
 
 	/* For internal device-mapper use. */
 	struct list_head list;