From: Dan Smith <danms@xxxxxxxxxx> Subject: Re: [PATCH 1/2] Add userspace device-mapper target Date: Thu, 08 Feb 2007 08:33:48 -0800 > FT> - enable an user-space to pass the kernel data to write > > FT> If you add u64 (user's address) to struct > FT> dmu_msg_map_response, the kernel can map user's pages and add them > FT> to a bio. the write is done in a zero-copy manner. A user-space > FT> process can simply mmap a file and pass the address of the > FT> metadata (for CoW) to the > FT> kernel. 2.6.20/drivers/scsi/scsi_tgt_lib.c does the same thing. > > So we would need a pointer, an offset in the file, and then a length > or size, correct? We need a pointer and length (or size) but not an offset. This enables an user-space to pass the kernel data to write. The data doesn't need to be in a file. The user space can pass any kind of a memory address. > In looking at bio_map_user(), and scsi_map_user_pages(), I'm not sure > where the bio->bi_sector gets set to control where the metadata would > be written. I assume that we could just set it on the result of > bio_map_user(), but I wonder if I'm missing something. You need to set bio->bi_sector. bio_map_user() just grabs user's pages and put them into a bio. Users of blk_rq_map_user (like SG_IO) doesn't need bio->bi_sector. Sorry, I should have mentioned blk_rq_map_user instead of bio_map_user. > If (from userspace), I mmap the cow file, and make the metadata change > in the mmap'd space, isn't there a chance that the metadata change > could be written to disk before the dmu response goes back to the > kernel? The danger here is that the metadata gets written before the > data block gets flushed to disk. What am I missing? Oh, yeah. That was a bad example. > If you don't mmap the file, but rather just prepare a block of data > with the metadata to be written, then it wouldn't be a problem. > However, you would then have a problem if the metadata format you were > using wasn't page or sector aligned. Yeah, as you said, you can just allocate buffer and use it. If buffer is properly aligned, we can do zero-copy. But if not, the kernel allocates pages and copies user's pages (bio_copy_user). Sorry, again. I should have mentioned blk_rq_map_user instead of bio_map_user. -- dm-devel mailing list dm-devel@xxxxxxxxxx https://www.redhat.com/mailman/listinfo/dm-devel
