@@ -195,6 +195,23 @@ int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
}
EXPORT_SYMBOL_GPL(dax_zero_page_range);
+size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
+ void *addr, size_t bytes, struct iov_iter *i)
+{
+ if (!dax_recovery_capable(dax_dev) || !dax_dev->ops->recovery_write)
+ return (size_t)-EOPNOTSUPP;
+ return dax_dev->ops->recovery_write(dax_dev, pgoff, addr, bytes, i);
+}
+EXPORT_SYMBOL_GPL(dax_recovery_write);
+
+bool dax_recovery_started(struct dax_device *dax_dev, void **kaddr)
+{
+ if (!kaddr || !dax_recovery_capable(dax_dev))
+ return false;
+ return test_bit(DAXDEV_RECOVERY, (unsigned long *)kaddr);
+}
+EXPORT_SYMBOL_GPL(dax_recovery_started);
+
#ifdef CONFIG_ARCH_HAS_PMEM_API
void arch_wb_cache_pmem(void *addr, size_t size);
void dax_flush(struct dax_device *dax_dev, void *addr, size_t size)
@@ -188,9 +188,20 @@ static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
return dax_zero_page_range(dax_dev, pgoff, nr_pages);
}
+static size_t linear_dax_recovery_write(struct dm_target *ti, pgoff_t pgoff,
+ void *addr, size_t bytes, struct iov_iter *i)
+{
+ struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff);
+
+ if (!dax_recovery_capable(dax_dev))
+ return (size_t) -EOPNOTSUPP;
+ return dax_recovery_write(dax_dev, pgoff, addr, bytes, i);
+};
+
#else
#define linear_dax_direct_access NULL
#define linear_dax_zero_page_range NULL
+#define linear_dax_recovery_write NULL
#endif
static struct target_type linear_target = {
@@ -208,6 +219,7 @@ static struct target_type linear_target = {
.iterate_devices = linear_iterate_devices,
.direct_access = linear_dax_direct_access,
.dax_zero_page_range = linear_dax_zero_page_range,
+ .dax_recovery_write = linear_dax_recovery_write,
};
int __init dm_linear_init(void)
@@ -927,9 +927,20 @@ static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
return dax_zero_page_range(dax_dev, pgoff, nr_pages << PAGE_SHIFT);
}
+static size_t log_writes_dax_recovery_write(struct dm_target *ti,
+ pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i)
+{
+ struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff);
+
+ if (!dax_recovery_capable(dax_dev))
+ return (size_t) -EOPNOTSUPP;
+ return dax_recovery_write(dax_dev, pgoff, addr, bytes, i);
+}
+
#else
#define log_writes_dax_direct_access NULL
#define log_writes_dax_zero_page_range NULL
+#define log_writes_dax_recovery_write NULL
#endif
static struct target_type log_writes_target = {
@@ -947,6 +958,7 @@ static struct target_type log_writes_target = {
.io_hints = log_writes_io_hints,
.direct_access = log_writes_dax_direct_access,
.dax_zero_page_range = log_writes_dax_zero_page_range,
+ .dax_recovery_write = log_writes_dax_recovery_write,
};
static int __init dm_log_writes_init(void)
@@ -332,9 +332,21 @@ static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
return dax_zero_page_range(dax_dev, pgoff, nr_pages);
}
+static size_t stripe_dax_recovery_write(struct dm_target *ti, pgoff_t pgoff,
+ void *addr, size_t bytes, struct iov_iter *i)
+{
+ struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff);
+
+ if (!dax_recovery_capable(dax_dev))
+ return (size_t) -EOPNOTSUPP;
+
+ return dax_recovery_write(dax_dev, pgoff, addr, bytes, i);
+}
+
#else
#define stripe_dax_direct_access NULL
#define stripe_dax_zero_page_range NULL
+#define stripe_dax_recovery_write NULL
#endif
/*
@@ -471,6 +483,7 @@ static struct target_type stripe_target = {
.io_hints = stripe_io_hints,
.direct_access = stripe_dax_direct_access,
.dax_zero_page_range = stripe_dax_zero_page_range,
+ .dax_recovery_write = stripe_dax_recovery_write,
};
int __init dm_stripe_init(void)
@@ -1054,6 +1054,32 @@ static int dm_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
return ret;
}
+static size_t dm_dax_recovery_write(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_recovery_write) {
+ ret = (size_t)-EOPNOTSUPP;
+ goto out;
+ }
+
+ ret = ti->type->dax_recovery_write(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, REQ_OP_ZONE_* zone management
@@ -2980,6 +3006,7 @@ static const struct block_device_operations dm_rq_blk_dops = {
static const struct dax_operations dm_dax_ops = {
.direct_access = dm_dax_direct_access,
.zero_page_range = dm_dax_zero_page_range,
+ .recovery_write = dm_dax_recovery_write,
};
/*
@@ -301,9 +301,16 @@ static long pmem_dax_direct_access(struct dax_device *dax_dev,
return __pmem_direct_access(pmem, pgoff, nr_pages, kaddr, pfn);
}
+static size_t pmem_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
+ void *addr, size_t bytes, struct iov_iter *i)
+{
+ return 0;
+}
+
static const struct dax_operations pmem_dax_ops = {
.direct_access = pmem_dax_direct_access,
.zero_page_range = pmem_dax_zero_page_range,
+ .recovery_write = pmem_recovery_write,
};
static ssize_t write_cache_show(struct device *dev,
@@ -30,6 +30,9 @@ struct dax_operations {
sector_t, sector_t);
/* zero_page_range: required operation. Zero page range */
int (*zero_page_range)(struct dax_device *, pgoff_t, size_t);
+ /* recovery_write: optional operation. */
+ size_t (*recovery_write)(struct dax_device *, pgoff_t, void *, size_t,
+ struct iov_iter *);
};
#if IS_ENABLED(CONFIG_DAX)
@@ -138,6 +141,9 @@ struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t st
dax_entry_t dax_lock_page(struct page *page);
void dax_unlock_page(struct page *page, dax_entry_t cookie);
int dax_prep_recovery(struct dax_device *dax_dev, void **kaddr);
+bool dax_recovery_started(struct dax_device *dax_dev, void **kaddr);
+size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
+ size_t bytes, struct iov_iter *i);
#else
static inline struct page *dax_layout_busy_page(struct address_space *mapping)
{
@@ -170,6 +176,18 @@ static inline int dax_prep_recovery(struct dax_device *dax_dev, void **kaddr)
{
return -EINVAL;
}
+
+static inline bool dax_recovery_started(struct dax_device *dax_dev,
+ void **kaddr)
+{
+ return false;
+}
+
+static size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
+ void *addr, size_t bytes, struct iov_iter *i)
+{
+ return 0;
+}
#endif
int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
@@ -150,6 +150,14 @@ typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff,
typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff,
size_t nr_pages);
+/*
+ * Returns:
+ * != 0 : number of bytes transferred, or size_t casted negative error code
+ * 0 : failure
+ */
+typedef size_t (*dm_dax_recovery_write_fn)(struct dm_target *ti, pgoff_t pgoff,
+ void *addr, size_t bytes, struct iov_iter *i);
+
void dm_error(const char *message);
struct dm_dev {
@@ -199,6 +207,7 @@ struct target_type {
dm_io_hints_fn io_hints;
dm_dax_direct_access_fn direct_access;
dm_dax_zero_page_range_fn dax_zero_page_range;
+ dm_dax_recovery_write_fn dax_recovery_write;
/* For internal device-mapper use. */
struct list_head list;
dax_recovery_write() dax op is only required for DAX device that export DAXDEV_RECOVERY indicating its capability to recover from poisons. DM may be nested, if part of the base dax devices forming a DM device support dax recovery, the DM device is marked with such capability. Signed-off-by: Jane Chu <jane.chu@oracle.com> --- drivers/dax/super.c | 17 +++++++++++++++++ drivers/md/dm-linear.c | 12 ++++++++++++ drivers/md/dm-log-writes.c | 12 ++++++++++++ drivers/md/dm-stripe.c | 13 +++++++++++++ drivers/md/dm.c | 27 +++++++++++++++++++++++++++ drivers/nvdimm/pmem.c | 7 +++++++ include/linux/dax.h | 18 ++++++++++++++++++ include/linux/device-mapper.h | 9 +++++++++ 8 files changed, 115 insertions(+)