dm: add ->copy_from_iter() dax operation support

Allow device-mapper to route copy_from_iter 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 copy_from_iter implementations.

Reviewed-by: Toshi Kani <toshi.kani@hpe.com>
Reviewed-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 6ed32aac8bbeec9f139d0ba622d4b5fb6d1aca4b..dd299e55f65d125a78c23b212aa17968750f4046 100644 (file)
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -18,6 +18,7 @@
 #include <linux/cdev.h>
 #include <linux/hash.h>
 #include <linux/slab.h>
+#include <linux/uio.h>
 #include <linux/dax.h>
 #include <linux/fs.h>
 
@@ -172,6 +173,18 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
 }
 EXPORT_SYMBOL_GPL(dax_direct_access);
 
+size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
+               size_t bytes, struct iov_iter *i)
+{
+       if (!dax_alive(dax_dev))
+               return 0;
+
+       if (!dax_dev->ops->copy_from_iter)
+               return copy_from_iter(addr, bytes, i);
+       return dax_dev->ops->copy_from_iter(dax_dev, pgoff, addr, bytes, i);
+}
+EXPORT_SYMBOL_GPL(dax_copy_from_iter);
+
 bool dax_alive(struct dax_device *dax_dev)
 {
        lockdep_assert_held(&dax_srcu);

diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 7d42a9d9f406b713448e75822669cd4e23b1b966..0841ec1bfbad19716dbfabdd69c302362627bf40 100644 (file)
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -159,6 +159,20 @@ static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
        return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
 }
 
+static size_t linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff,
+               void *addr, size_t bytes, struct iov_iter *i)
+{
+       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(bytes, PAGE_SIZE), &pgoff))
+               return 0;
+       return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i);
+}
+
 static struct target_type linear_target = {
        .name   = "linear",
        .version = {1, 3, 0},
@@ -171,6 +185,7 @@ static struct target_type linear_target = {
        .prepare_ioctl = linear_prepare_ioctl,
        .iterate_devices = linear_iterate_devices,
        .direct_access = linear_dax_direct_access,
+       .dax_copy_from_iter = linear_dax_copy_from_iter,
 };
 
 int __init dm_linear_init(void)

diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 75152482f3ad068b71e17001129903c091a5628d..1ef914f9ca72cf9df7ab6efe47c19cf0712f3f25 100644 (file)
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -332,6 +332,25 @@ static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
        return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
 }
 
+static size_t stripe_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff,
+               void *addr, size_t bytes, struct iov_iter *i)
+{
+       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(bytes, PAGE_SIZE), &pgoff))
+               return 0;
+       return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i);
+}
+
 /*
  * Stripe status:
  *
@@ -451,6 +470,7 @@ static struct target_type stripe_target = {
        .iterate_devices = stripe_iterate_devices,
        .io_hints = stripe_io_hints,
        .direct_access = stripe_dax_direct_access,
+       .dax_copy_from_iter = stripe_dax_copy_from_iter,
 };
 
 int __init dm_stripe_init(void)

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 37ccd73c79ecf2eeb4f33b5bc597f88ca5750d4b..7faaceb528197f6e8e2b1373ca7b94b47053b526 100644 (file)
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -19,6 +19,7 @@
 #include <linux/dax.h>
 #include <linux/slab.h>
 #include <linux/idr.h>
+#include <linux/uio.h>
 #include <linux/hdreg.h>
 #include <linux/delay.h>
 #include <linux/wait.h>
@@ -969,6 +970,30 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
        return ret;
 }
 
+static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
+               void *addr, size_t bytes, struct iov_iter *i)
+{
+       struct mapped_device *md = dax_get_private(dax_dev);
+       sector_t sector = pgoff * PAGE_SECTORS;
+       struct dm_target *ti;
+       long ret = 0;
+       int srcu_idx;
+
+       ti = dm_dax_get_live_target(md, sector, &srcu_idx);
+
+       if (!ti)
+               goto out;
+       if (!ti->type->dax_copy_from_iter) {
+               ret = copy_from_iter(addr, bytes, i);
+               goto out;
+       }
+       ret = ti->type->dax_copy_from_iter(ti, pgoff, addr, bytes, i);
+ out:
+       dm_put_live_table(md, srcu_idx);
+
+       return ret;
+}
+
 /*
  * A target may call dm_accept_partial_bio only from the map routine.  It is
  * allowed for all bio types except REQ_PREFLUSH.
@@ -2859,6 +2884,7 @@ 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,
 };
 
 /*

diff --git a/include/linux/dax.h b/include/linux/dax.h
index bbe79ed90e2b15f8caf2748625fae44b33b5f928..28e398f8c59e3ab429e05514f5f20655514500d5 100644 (file)
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -78,6 +78,8 @@ void kill_dax(struct dax_device *dax_dev);
 void *dax_get_private(struct dax_device *dax_dev);
 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);
 
 /*
  * We use lowest available bit in exceptional entry for locking, one bit for

diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index f4c639c0c362fd4c5106c5a6d2d6ceae1f3c795a..11c8a0a92f9c6e25813692e909a6d557ac3864bc 100644 (file)
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -132,6 +132,8 @@ typedef int (*dm_busy_fn) (struct dm_target *ti);
  */
 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);
 #define PAGE_SECTORS (PAGE_SIZE / 512)
 
 void dm_error(const char *message);
@@ -181,6 +183,7 @@ struct target_type {
        dm_iterate_devices_fn iterate_devices;
        dm_io_hints_fn io_hints;
        dm_dax_direct_access_fn direct_access;
+       dm_dax_copy_from_iter_fn dax_copy_from_iter;
 
        /* For internal device-mapper use. */
        struct list_head list;