Ilya, > sd_config_write_same() ignores ->max_ws_blocks == 0 and resets it to I'm not so keen on that description. sd is the entity that owns max_ws_blocks so it certainly doesn't ignore it. The default is for max_ws_blocks to be set because we have no generic, non-destructive way of finding out whether a WRITE SAME command is going to work or not. If a WRITE SAME subsequently fails, we'll disable the feature by clearing max_write_same_sectors in the queue limits. > permit trying WRITE SAME on older SCSI devices, unless ->no_write_same > is set. Because REQ_OP_WRITE_ZEROES is implemented in terms of WRITE > SAME, blkdev_issue_zeroout() may fail with -EREMOTEIO: Other than that patch looks good. Reviewed-by: Martin K. Petersen <martin.petersen@xxxxxxxxxx> -- Martin K. Petersen Oracle Linux Engineering
