On Fri, Nov 05, 2021 at 07:16:37PM -0600, Jane Chu wrote:
> Introduce DAX_OP_NORMAL and DAX_OP_RECOVERY operation modes to
> {dax_direct_access, dax_copy_from_iter, dax_copy_to_iter}.
> DAX_OP_NORMAL is the default or the existing mode, and
> DAX_OP_RECOVERY is a new mode for data recovery purpose.
>
> When dax-FS suspects dax media error might be encountered
> on a read or write, it can enact the recovery mode read or write
> by setting DAX_OP_RECOVERY in the aforementioned APIs. A read
> in recovery mode attempts to fetch as much data as possible
> until the first poisoned page is encountered. A write in recovery
> mode attempts to clear poison(s) in a page-aligned range and
> then write the user provided data over.
>
> DAX_OP_NORMAL should be used for all non-recovery code path.
>
> Signed-off-by: Jane Chu <jane.chu@xxxxxxxxxx>
> ---
> drivers/dax/super.c | 15 +++++++++------
> drivers/md/dm-linear.c | 14 ++++++++------
> drivers/md/dm-log-writes.c | 19 +++++++++++--------
> drivers/md/dm-stripe.c | 14 ++++++++------
> drivers/md/dm-target.c | 2 +-
> drivers/md/dm-writecache.c | 8 +++++---
> drivers/md/dm.c | 14 ++++++++------
> drivers/nvdimm/pmem.c | 11 ++++++-----
> drivers/nvdimm/pmem.h | 2 +-
> drivers/s390/block/dcssblk.c | 13 ++++++++-----
> fs/dax.c | 14 ++++++++------
> fs/fuse/dax.c | 4 ++--
> fs/fuse/virtio_fs.c | 12 ++++++++----
> include/linux/dax.h | 18 +++++++++++-------
> include/linux/device-mapper.h | 5 +++--
> tools/testing/nvdimm/pmem-dax.c | 2 +-
> 16 files changed, 98 insertions(+), 69 deletions(-)
>
<snip>
> diff --git a/include/linux/dax.h b/include/linux/dax.h
> index 324363b798ec..931586df2905 100644
> --- a/include/linux/dax.h
> +++ b/include/linux/dax.h
> @@ -9,6 +9,10 @@
> /* Flag for synchronous flush */
> #define DAXDEV_F_SYNC (1UL << 0)
>
> +/* dax operation mode dynamically set by caller */
> +#define DAX_OP_NORMAL 0
> +#define DAX_OP_RECOVERY 1
Mostly looks ok to me, but since this is an operation mode, should this
be an enum instead of an int?
Granted I also think six arguments is a lot... though I don't really
see any better way to do this.
(Dunno, I spent all day running internal patches through the process
gauntlet so this is the remaining 2% of my brain speaking...)
--D
> +
> typedef unsigned long dax_entry_t;
>
> struct dax_device;
> @@ -22,8 +26,8 @@ struct dax_operations {
> * logical-page-offset into an absolute physical pfn. Return the
> * number of pages available for DAX at that pfn.
> */
> - long (*direct_access)(struct dax_device *, pgoff_t, long,
> - void **, pfn_t *);
> + long (*direct_access)(struct dax_device *, pgoff_t, long, int,
> + void **, pfn_t *);
> /*
> * Validate whether this device is usable as an fsdax backing
> * device.
> @@ -32,10 +36,10 @@ struct dax_operations {
> sector_t, sector_t);
> /* copy_from_iter: required operation for fs-dax direct-i/o */
> size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t,
> - struct iov_iter *);
> + struct iov_iter *, int);
> /* copy_to_iter: required operation for fs-dax direct-i/o */
> size_t (*copy_to_iter)(struct dax_device *, pgoff_t, void *, size_t,
> - struct iov_iter *);
> + struct iov_iter *, int);
> /* zero_page_range: required operation. Zero page range */
> int (*zero_page_range)(struct dax_device *, pgoff_t, size_t);
> };
> @@ -186,11 +190,11 @@ static inline void dax_read_unlock(int id)
> bool dax_alive(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);
> + int mode, 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);
> + size_t bytes, struct iov_iter *i, int mode);
> size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
> - size_t bytes, struct iov_iter *i);
> + size_t bytes, struct iov_iter *i, int mode);
> int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
> size_t nr_pages);
> void dax_flush(struct dax_device *dax_dev, void *addr, size_t size);
> diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
> index a7df155ea49b..6596a8e0ceed 100644
> --- a/include/linux/device-mapper.h
> +++ b/include/linux/device-mapper.h
> @@ -146,9 +146,10 @@ typedef int (*dm_busy_fn) (struct dm_target *ti);
> * >= 0 : the number of bytes accessible at the address
> */
> typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff,
> - long nr_pages, void **kaddr, pfn_t *pfn);
> + long nr_pages, int mode, void **kaddr, pfn_t *pfn);
> typedef size_t (*dm_dax_copy_iter_fn)(struct dm_target *ti, pgoff_t pgoff,
> - void *addr, size_t bytes, struct iov_iter *i);
> + void *addr, size_t bytes, struct iov_iter *i,
> + int mode);
> typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff,
> size_t nr_pages);
>
> diff --git a/tools/testing/nvdimm/pmem-dax.c b/tools/testing/nvdimm/pmem-dax.c
> index af19c85558e7..71c225630e7e 100644
> --- a/tools/testing/nvdimm/pmem-dax.c
> +++ b/tools/testing/nvdimm/pmem-dax.c
> @@ -8,7 +8,7 @@
> #include <nd.h>
>
> long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
> - long nr_pages, void **kaddr, pfn_t *pfn)
> + long nr_pages, int mode, void **kaddr, pfn_t *pfn)
> {
> resource_size_t offset = PFN_PHYS(pgoff) + pmem->data_offset;
>
> --
> 2.18.4
>
