dax: add .recovery_write dax_operation

Introduce dax_recovery_write() operation. The function is used to
recover a dax range that contains poison. Typical use case is when
a user process receives a SIGBUS with si_code BUS_MCEERR_AR
indicating poison(s) in a dax range, in response, the user process
issues a pwrite() to the page-aligned dax range, thus clears the
poison and puts valid data in the range.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jane Chu <jane.chu@oracle.com>
Link: https://lore.kernel.org/r/20220422224508.440670-6-jane.chu@oracle.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
This commit is contained in:
Jane Chu 2022-04-22 16:45:06 -06:00 committed by Dan Williams
parent e511c4a3d2
commit 047218ec90
9 changed files with 100 additions and 1 deletions

View File

@ -195,6 +195,15 @@ 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 *iter)
{
if (!dax_dev->ops->recovery_write)
return 0;
return dax_dev->ops->recovery_write(dax_dev, pgoff, addr, bytes, iter);
}
EXPORT_SYMBOL_GPL(dax_recovery_write);
#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)

View File

@ -188,9 +188,18 @@ 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);
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 +217,7 @@ 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)

View File

@ -905,9 +905,18 @@ 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);
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 = {
@ -925,6 +934,7 @@ 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)

View File

@ -331,9 +331,18 @@ 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);
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
/*
@ -470,6 +479,7 @@ 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)

View File

@ -1147,6 +1147,25 @@ 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;
int srcu_idx;
long ret = 0;
ti = dm_dax_get_live_target(md, sector, &srcu_idx);
if (!ti || !ti->type->dax_recovery_write)
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
@ -3147,6 +3166,7 @@ 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,
};
/*

View File

@ -287,9 +287,16 @@ static long pmem_dax_direct_access(struct dax_device *dax_dev,
return __pmem_direct_access(pmem, pgoff, nr_pages, mode, 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,

View File

@ -1240,6 +1240,7 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
const size_t size = ALIGN(length + offset, PAGE_SIZE);
pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
ssize_t map_len;
bool recovery = false;
void *kaddr;
if (fatal_signal_pending(current)) {
@ -1249,6 +1250,13 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
map_len = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size),
DAX_ACCESS, &kaddr, NULL);
if (map_len == -EIO && iov_iter_rw(iter) == WRITE) {
map_len = dax_direct_access(dax_dev, pgoff,
PHYS_PFN(size), DAX_RECOVERY_WRITE,
&kaddr, NULL);
if (map_len > 0)
recovery = true;
}
if (map_len < 0) {
ret = map_len;
break;
@ -1260,7 +1268,10 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
if (map_len > end - pos)
map_len = end - pos;
if (iov_iter_rw(iter) == WRITE)
if (recovery)
xfer = dax_recovery_write(dax_dev, pgoff, kaddr,
map_len, iter);
else if (iov_iter_rw(iter) == WRITE)
xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr,
map_len, iter);
else

View File

@ -35,6 +35,12 @@ 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: recover a poisoned range by DAX device driver
* capable of clearing poison.
*/
size_t (*recovery_write)(struct dax_device *dax_dev, pgoff_t pgoff,
void *addr, size_t bytes, struct iov_iter *iter);
};
#if IS_ENABLED(CONFIG_DAX)
@ -45,6 +51,8 @@ void dax_write_cache(struct dax_device *dax_dev, bool wc);
bool dax_write_cache_enabled(struct dax_device *dax_dev);
bool dax_synchronous(struct dax_device *dax_dev);
void set_dax_synchronous(struct dax_device *dax_dev);
size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
void *addr, size_t bytes, struct iov_iter *i);
/*
* Check if given mapping is supported by the file / underlying device.
*/
@ -92,6 +100,11 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
{
return !(vma->vm_flags & VM_SYNC);
}
static inline 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
void set_dax_nocache(struct dax_device *dax_dev);

View File

@ -152,6 +152,14 @@ 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
* 0 : recovery write failed
*/
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 {
@ -201,6 +209,7 @@ 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;