On Fri, Nov 5, 2021 at 6:17 PM Jane Chu <jane.chu@xxxxxxxxxx> 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>
[..]
> 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
Perhaps this should be called DAX_OP_FAILFAST?
> +#define DAX_OP_RECOVERY 1
> +
> 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,
Would be nice if that 'int' was an enum, but I'm not sure a new
parameter is needed at all, see below...
> + 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);
I'm not sure the flag is needed here as the "void *" could carry a
flag in the pointer to indicate that is a recovery kaddr.
> /* 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);
Same comment here.
> /* 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);
How about dax_direct_access() calling convention stays the same, but
the kaddr is optionally updated to carry a flag in the lower unused
bits. So:
void **kaddr = NULL; /* caller only cares about the pfn */
void *failfast = NULL;
void **kaddr = &failfast; /* caller wants -EIO not recovery */
void *recovery = (void *) DAX_OP_RECOVERY;
void **kaddr = &recovery; /* caller wants to carefully access page(s)
containing poison */
--
dm-devel mailing list
dm-devel@xxxxxxxxxx
https://listman.redhat.com/mailman/listinfo/dm-devel
