[PATCH 04/10] block: avoid unpinning/freeing the bio_vec incase of cloned bio

[Christoph Hellwig]

On Wed, May 01, 2024 at 06:32:45PM +0530, Kanchan Joshi wrote:
> Can you please tell what function(s) in bio data path that need this 
> conversion?
> To me data path handling seems similar. Each cloned bio will lead to 
> some amount of data transfer to pinned user-memory. The same is 
> happening for meta transfer here.

Well, everywhere.  e.g. for direct I/O everything is just driven from
the fs/direct-io.c and and fs/iomap/direct-io.c code without any
knowledge in the underlying driver if data has been pinned (no bounce
buffering in this case).  Or for passthrough I/O none of the underlying
logic knows about the pinning or bounce buffering, everything is handled
in block/blk-map.c.