On 13/03/2025 07:49, Christoph Hellwig wrote:
On Thu, Mar 13, 2025 at 07:41:11AM +0000, John Garry wrote:
So how about this (I would re-add the write through comment):
This looks roughly sane. You'd probably want to turn the
iomap_dio_bio_opflags removal into a prep path, though.
Sure
- blk_opf_t opflags = REQ_SYNC | REQ_IDLE;
This good lost and should move to the bio_opf declaration now.
ok
+ (bdev_fua(iomap->bdev) || !bdev_write_cache(iomap->bdev))) {
+ bio_opf |= REQ_FUA; //reads as well?
REQ_FUA is not defined for reads in Linux Some of the storage standards
define it for reads, but the semantics are pretty nonsensical.
ok, so I will need to check for writes when setting that (as it was
previously)
