[PATCH] dm: enable opt-out of device-mapper dax support
by Dan Williams
Now that dax is no longer a default property of a block-device, i.e.
->direct_access() is not a block-device operation, we optionally enable
device-mapper dax support with a new CONFIG_DM_DAX option.
All the dax operations helpers are moved to a new file,
drivers/md/dm-dax.c, that is optionally compiled when CONFIG_DM_DAX=y.
Otherwise, we stub out all the operations with NULL function pointers
and nop wrappers for the core dax routines.
Cc: Alasdair Kergon <agk(a)redhat.com>
Cc: Mike Snitzer <snitzer(a)redhat.com>
Reported-by: Bart Van Assche <Bart.VanAssche(a)wdc.com>
Signed-off-by: Dan Williams <dan.j.williams(a)intel.com>
---
drivers/md/Kconfig | 14 +++
drivers/md/Makefile | 1
drivers/md/dm-dax.c | 227 ++++++++++++++++++++++++++++++++++++++++++++++++
drivers/md/dm-dax.h | 73 +++++++++++++++
drivers/md/dm-linear.c | 56 ------------
drivers/md/dm-snap.c | 9 --
drivers/md/dm-stripe.c | 89 -------------------
drivers/md/dm-target.c | 7 -
drivers/md/dm.c | 105 ++--------------------
drivers/md/dm.h | 34 +++++++
10 files changed, 363 insertions(+), 252 deletions(-)
create mode 100644 drivers/md/dm-dax.c
create mode 100644 drivers/md/dm-dax.h
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 4a249ee86364..bf27b435f7cd 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -200,7 +200,6 @@ config BLK_DEV_DM_BUILTIN
config BLK_DEV_DM
tristate "Device mapper support"
select BLK_DEV_DM_BUILTIN
- select DAX
---help---
Device-mapper is a low level volume manager. It works by allowing
people to specify mappings for ranges of logical sectors. Various
@@ -214,6 +213,19 @@ config BLK_DEV_DM
If unsure, say N.
+config DM_DAX
+ bool "Direct access (DAX) support"
+ depends on BLK_DEV_DM
+ default BLK_DEV_PMEM
+ select DAX
+ ---help---
+ Enable DAX support for the device-mapper linear and stripe
+ targets for use with DAX capable block devices like /dev/pmemN.
+ If you have a DAX capable block device and have enabled
+ filesystem DAX support (CONFIG_FS_DAX), then say Y.
+
+ If unsure, say N.
+
config DM_MQ_DEFAULT
bool "request-based DM: use blk-mq I/O path by default"
depends on BLK_DEV_DM
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 786ec9e86d65..4a2fd958a3d9 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -5,6 +5,7 @@
dm-mod-y += dm.o dm-table.o dm-target.o dm-linear.o dm-stripe.o \
dm-ioctl.o dm-io.o dm-kcopyd.o dm-sysfs.o dm-stats.o \
dm-rq.o
+dm-mod-$(CONFIG_DM_DAX) += dm-dax.o
dm-multipath-y += dm-path-selector.o dm-mpath.o
dm-snapshot-y += dm-snap.o dm-exception-store.o dm-snap-transient.o \
dm-snap-persistent.o
diff --git a/drivers/md/dm-dax.c b/drivers/md/dm-dax.c
new file mode 100644
index 000000000000..d48386fe2578
--- /dev/null
+++ b/drivers/md/dm-dax.c
@@ -0,0 +1,227 @@
+/*
+ * Copyright(c) 2017 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include <linux/device-mapper.h>
+#include <linux/dax.h>
+#include <linux/uio.h>
+
+#include "dm.h"
+
+extern sector_t linear_map_sector(struct dm_target *ti, sector_t bi_sector);
+extern sector_t max_io_len(sector_t sector, struct dm_target *ti);
+
+long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
+ long nr_pages, void **kaddr, pfn_t *pfn)
+{
+ long ret;
+ 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);
+ ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages * PAGE_SIZE, &pgoff);
+ if (ret)
+ return ret;
+ return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
+}
+
+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);
+}
+
+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);
+}
+
+long origin_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
+ long nr_pages, void **kaddr, pfn_t *pfn)
+{
+#define DM_MSG_PREFIX "snapshots"
+ DMWARN("device does not support dax.");
+ return -EIO;
+}
+EXPORT_SYMBOL_GPL(origin_dax_direct_access);
+
+extern void stripe_map_sector(struct stripe_c *sc, sector_t sector,
+ uint32_t *stripe, sector_t *result);
+long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
+ long nr_pages, void **kaddr, pfn_t *pfn)
+{
+ 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;
+ long ret;
+
+ 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;
+
+ ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages * PAGE_SIZE, &pgoff);
+ if (ret)
+ return ret;
+ return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
+}
+
+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);
+}
+
+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);
+}
+
+long io_err_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
+ long nr_pages, void **kaddr, pfn_t *pfn)
+{
+ return -EIO;
+}
+
+static struct dm_target *dm_dax_get_live_target(struct mapped_device *md,
+ sector_t sector, int *srcu_idx)
+{
+ struct dm_table *map;
+ struct dm_target *ti;
+
+ map = dm_get_live_table(md, srcu_idx);
+ if (!map)
+ return NULL;
+
+ ti = dm_table_find_target(map, sector);
+ if (!dm_target_is_valid(ti))
+ return NULL;
+
+ return ti;
+}
+
+long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
+ long nr_pages, void **kaddr, pfn_t *pfn)
+{
+ struct mapped_device *md = dax_get_private(dax_dev);
+ sector_t sector = pgoff * PAGE_SECTORS;
+ struct dm_target *ti;
+ long len, ret = -EIO;
+ int srcu_idx;
+
+ ti = dm_dax_get_live_target(md, sector, &srcu_idx);
+
+ if (!ti)
+ goto out;
+ if (!ti->type->direct_access)
+ goto out;
+ len = max_io_len(sector, ti) / PAGE_SECTORS;
+ if (len < 1)
+ goto out;
+ nr_pages = min(len, nr_pages);
+ if (ti->type->direct_access)
+ ret = ti->type->direct_access(ti, pgoff, nr_pages, kaddr, pfn);
+
+ out:
+ dm_put_live_table(md, srcu_idx);
+
+ return ret;
+}
+
+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;
+}
+
+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);
+}
diff --git a/drivers/md/dm-dax.h b/drivers/md/dm-dax.h
new file mode 100644
index 000000000000..02cd4589d05a
--- /dev/null
+++ b/drivers/md/dm-dax.h
@@ -0,0 +1,73 @@
+#ifndef __DM_DAX_H__
+#define __DM_DAX_H__
+#include <linux/dax.h>
+#if IS_ENABLED(CONFIG_DM_DAX)
+/* dax helpers to allow compiling out dax support */
+long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
+ long nr_pages, void **kaddr, pfn_t *pfn);
+size_t linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff,
+ void *addr, size_t bytes, struct iov_iter *i);
+void linear_dax_flush(struct dm_target *ti, pgoff_t pgoff, void *addr,
+ size_t size);
+long origin_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
+ long nr_pages, void **kaddr, pfn_t *pfn);
+long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
+ long nr_pages, void **kaddr, pfn_t *pfn);
+size_t stripe_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff,
+ void *addr, size_t bytes, struct iov_iter *i);
+void stripe_dax_flush(struct dm_target *ti, pgoff_t pgoff, void *addr,
+ size_t size);
+long io_err_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
+ long nr_pages, void **kaddr, pfn_t *pfn);
+static inline struct dax_device *dm_dax_get_by_host(const char *host)
+{
+ return dax_get_by_host(host);
+}
+static inline void dm_put_dax(struct dax_device *dax_dev)
+{
+ put_dax(dax_dev);
+}
+static inline struct dax_device *dm_alloc_dax(void *p, const char *host,
+ const struct dax_operations *ops)
+{
+ return alloc_dax(p, host, ops);
+}
+static inline void dm_kill_dax(struct dax_device *dax_dev)
+{
+ kill_dax(dax_dev);
+}
+long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
+ long nr_pages, void **kaddr, pfn_t *pfn);
+size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
+ void *addr, size_t bytes, struct iov_iter *i);
+void dm_dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
+ size_t size);
+#else
+#define linear_dax_direct_access NULL
+#define linear_dax_copy_from_iter NULL
+#define linear_dax_flush NULL
+#define origin_dax_direct_access NULL
+#define stripe_dax_direct_access NULL
+#define stripe_dax_copy_from_iter NULL
+#define stripe_dax_flush NULL
+#define io_err_dax_direct_access NULL
+static inline struct dax_device *dm_dax_get_by_host(const char *host)
+{
+ return NULL;
+}
+static inline void dm_put_dax(struct dax_device *dax_dev)
+{
+}
+static inline struct dax_device *dm_alloc_dax(void *private, const char *__host,
+ const struct dax_operations *ops)
+{
+ return NULL;
+}
+static inline void dm_kill_dax(struct dax_device *dax_dev)
+{
+}
+#define dm_dax_direct_access NULL
+#define dm_dax_copy_from_iter NULL
+#define dm_dax_flush NULL
+#endif
+#endif /* __DM_DAX_H__ */
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 41971a090e34..184ae6e76ac4 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -5,25 +5,17 @@
*/
#include "dm.h"
+#include "dm-dax.h"
#include <linux/module.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
-#include <linux/dax.h>
#include <linux/slab.h>
#include <linux/device-mapper.h>
#define DM_MSG_PREFIX "linear"
/*
- * Linear: maps a linear range of a device.
- */
-struct linear_c {
- struct dm_dev *dev;
- sector_t start;
-};
-
-/*
* Construct a linear mapping: <dev_path> <offset>
*/
static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
@@ -77,7 +69,7 @@ static void linear_dtr(struct dm_target *ti)
kfree(lc);
}
-static sector_t linear_map_sector(struct dm_target *ti, sector_t bi_sector)
+sector_t linear_map_sector(struct dm_target *ti, sector_t bi_sector)
{
struct linear_c *lc = ti->private;
@@ -154,50 +146,6 @@ static int linear_iterate_devices(struct dm_target *ti,
return fn(ti, lc->dev, lc->start, ti->len, data);
}
-static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
- long nr_pages, void **kaddr, pfn_t *pfn)
-{
- long ret;
- 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);
- ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages * PAGE_SIZE, &pgoff);
- if (ret)
- return ret;
- 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 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, 4, 0},
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 1ba41048b438..fa31d9f5642d 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -21,7 +21,7 @@
#include <linux/dm-kcopyd.h>
#include "dm.h"
-
+#include "dm-dax.h"
#include "dm-exception-store.h"
#define DM_MSG_PREFIX "snapshots"
@@ -2303,13 +2303,6 @@ static int origin_map(struct dm_target *ti, struct bio *bio)
return do_origin(o->dev, bio);
}
-static long origin_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
- long nr_pages, void **kaddr, pfn_t *pfn)
-{
- DMWARN("device does not support dax.");
- return -EIO;
-}
-
/*
* Set the target "max_io_len" field to the minimum of all the snapshots'
* chunk sizes.
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index a0375530b07f..a4720abac523 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -5,45 +5,19 @@
*/
#include "dm.h"
+#include "dm-dax.h"
#include <linux/device-mapper.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
-#include <linux/dax.h>
#include <linux/slab.h>
#include <linux/log2.h>
#define DM_MSG_PREFIX "striped"
#define DM_IO_ERROR_THRESHOLD 15
-struct stripe {
- struct dm_dev *dev;
- sector_t physical_start;
-
- atomic_t error_count;
-};
-
-struct stripe_c {
- uint32_t stripes;
- int stripes_shift;
-
- /* The size of this target / num. stripes */
- sector_t stripe_width;
-
- uint32_t chunk_size;
- int chunk_size_shift;
-
- /* Needed for handling events */
- struct dm_target *ti;
-
- /* Work struct used for triggering events*/
- struct work_struct trigger_event;
-
- struct stripe stripe[0];
-};
-
/*
* An event is triggered whenever a drive
* drops out of a stripe volume.
@@ -212,7 +186,7 @@ static void stripe_dtr(struct dm_target *ti)
kfree(sc);
}
-static void stripe_map_sector(struct stripe_c *sc, sector_t sector,
+void stripe_map_sector(struct stripe_c *sc, sector_t sector,
uint32_t *stripe, sector_t *result)
{
sector_t chunk = dm_target_offset(sc->ti, sector);
@@ -311,65 +285,6 @@ static int stripe_map(struct dm_target *ti, struct bio *bio)
return DM_MAPIO_REMAPPED;
}
-static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
- long nr_pages, void **kaddr, pfn_t *pfn)
-{
- 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;
- long ret;
-
- 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;
-
- ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages * PAGE_SIZE, &pgoff);
- if (ret)
- return ret;
- 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);
-}
-
-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:
*
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index c0d7e60820c4..3d4130e2e1e9 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -5,6 +5,7 @@
*/
#include "dm-core.h"
+#include "dm-dax.h"
#include <linux/module.h>
#include <linux/init.h>
@@ -142,12 +143,6 @@ static void io_err_release_clone_rq(struct request *clone)
{
}
-static long io_err_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
- long nr_pages, void **kaddr, pfn_t *pfn)
-{
- return -EIO;
-}
-
static struct target_type error_target = {
.name = "error",
.version = {1, 5, 0},
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 2edbcc2d7d3f..73aca9ce5581 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -8,6 +8,7 @@
#include "dm-core.h"
#include "dm-rq.h"
#include "dm-uevent.h"
+#include "dm-dax.h"
#include <linux/init.h>
#include <linux/module.h>
@@ -16,7 +17,6 @@
#include <linux/blkpg.h>
#include <linux/bio.h>
#include <linux/mempool.h>
-#include <linux/dax.h>
#include <linux/slab.h>
#include <linux/idr.h>
#include <linux/uio.h>
@@ -634,7 +634,7 @@ static int open_table_device(struct table_device *td, dev_t dev,
}
td->dm_dev.bdev = bdev;
- td->dm_dev.dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
+ td->dm_dev.dax_dev = dm_dax_get_by_host(bdev->bd_disk->disk_name);
return 0;
}
@@ -648,7 +648,7 @@ static void close_table_device(struct table_device *td, struct mapped_device *md
bd_unlink_disk_holder(td->dm_dev.bdev, dm_disk(md));
blkdev_put(td->dm_dev.bdev, td->dm_dev.mode | FMODE_EXCL);
- put_dax(td->dm_dev.dax_dev);
+ dm_put_dax(td->dm_dev.dax_dev);
td->dm_dev.bdev = NULL;
td->dm_dev.dax_dev = NULL;
}
@@ -890,7 +890,7 @@ static sector_t max_io_len_target_boundary(sector_t sector, struct dm_target *ti
return ti->len - target_offset;
}
-static sector_t max_io_len(sector_t sector, struct dm_target *ti)
+sector_t max_io_len(sector_t sector, struct dm_target *ti)
{
sector_t len = max_io_len_target_boundary(sector, ti);
sector_t offset, max_len;
@@ -928,93 +928,6 @@ int dm_set_target_max_io_len(struct dm_target *ti, sector_t len)
}
EXPORT_SYMBOL_GPL(dm_set_target_max_io_len);
-static struct dm_target *dm_dax_get_live_target(struct mapped_device *md,
- sector_t sector, int *srcu_idx)
-{
- struct dm_table *map;
- struct dm_target *ti;
-
- map = dm_get_live_table(md, srcu_idx);
- if (!map)
- return NULL;
-
- ti = dm_table_find_target(map, sector);
- if (!dm_target_is_valid(ti))
- return NULL;
-
- return ti;
-}
-
-static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
- long nr_pages, void **kaddr, pfn_t *pfn)
-{
- struct mapped_device *md = dax_get_private(dax_dev);
- sector_t sector = pgoff * PAGE_SECTORS;
- struct dm_target *ti;
- long len, ret = -EIO;
- int srcu_idx;
-
- ti = dm_dax_get_live_target(md, sector, &srcu_idx);
-
- if (!ti)
- goto out;
- if (!ti->type->direct_access)
- goto out;
- len = max_io_len(sector, ti) / PAGE_SECTORS;
- if (len < 1)
- goto out;
- nr_pages = min(len, nr_pages);
- if (ti->type->direct_access)
- ret = ti->type->direct_access(ti, pgoff, nr_pages, kaddr, pfn);
-
- out:
- dm_put_live_table(md, srcu_idx);
-
- 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;
-}
-
-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.
@@ -1681,8 +1594,8 @@ static void cleanup_mapped_device(struct mapped_device *md)
bioset_free(md->bs);
if (md->dax_dev) {
- kill_dax(md->dax_dev);
- put_dax(md->dax_dev);
+ dm_kill_dax(md->dax_dev);
+ dm_put_dax(md->dax_dev);
md->dax_dev = NULL;
}
@@ -1779,8 +1692,8 @@ static struct mapped_device *alloc_dev(int minor)
md->disk->private_data = md;
sprintf(md->disk->disk_name, "dm-%d", minor);
- dax_dev = alloc_dax(md, md->disk->disk_name, &dm_dax_ops);
- if (!dax_dev)
+ dax_dev = dm_alloc_dax(md, md->disk->disk_name, &dm_dax_ops);
+ if (!dax_dev && IS_ENABLED(CONFIG_DM_DAX))
goto bad;
md->dax_dev = dax_dev;
@@ -2999,7 +2912,7 @@ static const struct block_device_operations dm_blk_dops = {
.owner = THIS_MODULE
};
-static const struct dax_operations dm_dax_ops = {
+static const __maybe_unused struct dax_operations dm_dax_ops = {
.direct_access = dm_dax_direct_access,
.copy_from_iter = dm_dax_copy_from_iter,
.flush = dm_dax_flush,
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 38c84c0a35d4..2c9d94ec2391 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -174,6 +174,40 @@ int dm_stripe_init(void);
void dm_stripe_exit(void);
/*
+ * Linear: maps a linear range of a device.
+ */
+struct linear_c {
+ struct dm_dev *dev;
+ sector_t start;
+};
+
+struct stripe {
+ struct dm_dev *dev;
+ sector_t physical_start;
+
+ atomic_t error_count;
+};
+
+struct stripe_c {
+ uint32_t stripes;
+ int stripes_shift;
+
+ /* The size of this target / num. stripes */
+ sector_t stripe_width;
+
+ uint32_t chunk_size;
+ int chunk_size_shift;
+
+ /* Needed for handling events */
+ struct dm_target *ti;
+
+ /* Work struct used for triggering events*/
+ struct work_struct trigger_event;
+
+ struct stripe stripe[0];
+};
+
+/*
* mapped_device operations
*/
void dm_destroy(struct mapped_device *md);
3 years, 5 months
We could not deliver your parcel, #5628471
by eimearon＠box845.bluehost.com
Dear Customer,
Your parcel was successfully delivered August 01 to UPS Station, but our courier cound not contact you.
You can download the shipment label attached!
Most sincerely,
Lonnie Whitney,
UPS Chief Operation Agent.
3 years, 5 months
[PATCH] nvdimm: avoid bogus -Wmaybe-uninitialized warning
by Arnd Bergmann
Removing the btt_rw_page/pmem_rw_page functions had a surprising
side-effect of introducing a false-positive warning in another
function, due to changed inlining decisions in gcc:
In file included from drivers/nvdimm/pmem.c:36:0:
drivers/nvdimm/pmem.c: In function 'pmem_make_request':
drivers/nvdimm/nd.h:407:2: error: 'start' may be used uninitialized in this function [-Werror=maybe-uninitialized]
drivers/nvdimm/pmem.c:174:16: note: 'start' was declared here
In file included from drivers/nvdimm/btt.c:27:0:
drivers/nvdimm/btt.c: In function 'btt_make_request':
drivers/nvdimm/nd.h:407:2: error: 'start' may be used uninitialized in this function [-Werror=maybe-uninitialized]
drivers/nvdimm/btt.c:1202:16: note: 'start' was declared here
The problem is that gcc fails to track the value of the 'do_acct'
variable here and has to read it back from stack, but it does
remember that 'start' may be uninitialized sometimes.
This shuts up the warning by making nd_iostat_start() always
initialize the 'start' variable. In those cases that gcc successfully
tracks the state of the variable, this will have no effect.
Fixes: 503a5e89b1de ("drivers/nvdimm/btt.c: remove btt_rw_page()")
Fixes: 58100d6e735e ("drivers/nvdimm/pmem.c: remove pmem_rw_page()")
Signed-off-by: Arnd Bergmann <arnd(a)arndb.de>
---
drivers/nvdimm/nd.h | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index e1b5715bd91f..64f79a156456 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -392,8 +392,10 @@ static inline bool nd_iostat_start(struct bio *bio, unsigned long *start)
{
struct gendisk *disk = bio->bi_bdev->bd_disk;
- if (!blk_queue_io_stat(disk->queue))
+ if (!blk_queue_io_stat(disk->queue)) {
+ *start = 0;
return false;
+ }
*start = jiffies;
generic_start_io_acct(bio_data_dir(bio),
--
2.9.0
3 years, 5 months
[PATCH v4 0/6] BTT error clearing rework
by Vishal Verma
Changes in v4:
- move the deadlock fix to before enabling the BTT error clear paths (Dan)
- No need for an error lock per freelist entry, just have one per arena (Dan)
Changes in v3:
- Change the dynamically allocated (during IO) zerobuf to the kernel's
ZERO_PAGE for error clearing (patch 5) (Dan).
- Move the NOIO fixes a level down into nvdimm_clear_poison since both
btt and pmem poison clearing goes through that (Dan).
Changes in v2:
- Drop the ACPI allocation change patch. Instead use
memalloc_noio_{save,restore} to set the GFP_NOIO flag around anything
that can be expected to call into ACPI for clearing errors. (Rafael, Dan).
Clearing errors or badblocks during a BTT write requires sending an ACPI
DSM, which means potentially sleeping. Since a BTT IO happens in atomic
context (preemption disabled, spinlocks may be held), we cannot perform
error clearing in the course of an IO. Due to this error clearing for
BTT IOs has hitherto been disabled.
This series fixes these problems by moving the error clearing out of
the atomic sections in the BTT.
Also fix a potential deadlock that can occur while clearing errors
from either BTT or pmem due to memory allocations in the IO path.
Vishal Verma (6):
btt: fix a missed NVDIMM_IO_ATOMIC case in the write path
btt: refactor map entry operations with macros
btt: ensure that flags were also unchanged during a map_read
btt: cache sector_size in arena_info
libnvdimm: fix potential deadlock while clearing errors
libnvdimm, btt: rework error clearing
drivers/nvdimm/btt.c | 116 +++++++++++++++++++++++++++++++++++++++++--------
drivers/nvdimm/btt.h | 11 +++++
drivers/nvdimm/bus.c | 6 +++
drivers/nvdimm/claim.c | 9 +---
4 files changed, 117 insertions(+), 25 deletions(-)
--
2.9.3
3 years, 5 months
