Re: [RFC PATCH 0/1] dm-crypt excessive overhead
Ignat Korchagin <[email protected]>
| Newsgroups | gmane.linux.kernel.device-mapper.dm-crypt,gmane.linux.kernel,gmane.linux.kernel.device-mapper.devel |
|---|---|
| Message-ID | <CALrw=nHZK7JhUO+-vAeMxCZqTBGBkWckBeg56pFuc1bo6yep6A@mail.gmail.com> |
Yes, it should. I got one when I was testing the first iteration (without the tasklet) of the patch on an NVME? disk. On Sat, Jun 20, 2020 at 8:36 PM Mikulas Patocka <[email protected]> wrote: > > > > On Sat, 20 Jun 2020, Herbert Xu wrote: > > > On Fri, Jun 19, 2020 at 02:39:39PM -0400, Mikulas Patocka wrote: > > > > > > I'm looking at this and I'd like to know why does the crypto API fail in > > > hard-irq context and why does it work in tasklet context. What's the exact > > > reason behind this? > > > > You're not supposed to do any real work in IRQ handlers. All > > the substantial work should be postponed to softirq context. > > I see. > > BTW - should it also warn if it is running in a process context with > interrupts disabled? > > Mikulas > > > Why do you need to do work in hard IRQ context? > > > > Cheers, > > -- > > Email: Herbert Xu <[email protected]> > > Home Page: http://gondor.apana.org.au/~herbert/ > > PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt > > > _______________________________________________ dm-crypt mailing list [email protected] https://www.saout.de/mailman/listinfo/dm-crypt