Herbert Xu [off-list ref] wrote:

quoted

I must be missing something, I think.  What's particularly optimal about the
code in hash_sendpage() but not hash_sendmsg()?  Is it that the former uses
finup/digest, but the latter ony does update+final?

A lot of hardware hashes can't perform partial updates, so they
will always fall back to software unless you use finup/digest.

Okay.  Btw, how much of a hard limit is ALG_MAX_PAGES?  Multipage folios can
exceed the current limit (16 pages, 64K) in size.  Is it just to prevent too
much memory being pinned at once?

David