linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: Frederic Barrat <fbarrat@linux.vnet.ibm.com>
To: alistair@popple.id.au, aneesh.kumar@linux.vnet.ibm.com,
	bsingharora@gmail.com, linuxppc-dev@lists.ozlabs.org,
	mpe@ellerman.id.au
Subject: [RFC 0/2] powerpc/mm: Mark memory contexts requiring global TLBIs
Date: Wed,  3 May 2017 16:29:04 +0200	[thread overview]
Message-ID: <20170503142906.29220-1-fbarrat@linux.vnet.ibm.com> (raw)

capi2 and opencapi require the TLB invalidations being sent for
addresses used on the cxl adapter or opencapi device to be global, as
there's a translation cache in the PSL (for capi2) or NPU (for
opencapi). The CAPP (for PSL) and NPU snoop the power bus.

This is not new: for the hash memory model, as soon as the cxl driver
is active, all local TLBIs become global. We need a similar mechanism
for the radix memory model. This patch tries to improve things a bit
by flagging the contexts requiring global TLBIs, therefore limiting
the "upgrade" and not affecting contexts not used by the card.

Alistair: for nvlink2, it is my understanding that all the required
invalidations are already in place through software mmio/ATSD, i.e. this
patch is not useful for you.

Submitting as an RFC, since I don't get to touch mmu.h everyday and
would like to probe people's reaction.



Frederic Barrat (2):
  powerpc/mm: Add marker for contexts requiring global TLB invalidations
  cxl: Mark context requiring global TLBIs

 arch/powerpc/include/asm/book3s/64/mmu.h |  9 +++++++++
 arch/powerpc/include/asm/tlb.h           | 10 ++++++++--
 arch/powerpc/mm/mmu_context_book3s64.c   |  1 +
 drivers/misc/cxl/api.c                   |  5 ++++-
 drivers/misc/cxl/file.c                  |  5 ++++-
 5 files changed, 26 insertions(+), 4 deletions(-)

-- 
2.11.0

             reply	other threads:[~2017-05-03 14:29 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-05-03 14:29 Frederic Barrat [this message]
2017-05-03 14:29 ` [RFC 1/2] powerpc/mm: Add marker for contexts requiring global TLB invalidations Frederic Barrat
2017-05-04  6:41   ` Aneesh Kumar K.V
2017-05-04 17:24     ` Frederic Barrat
2017-05-04  7:25   ` Balbir Singh
2017-05-04  9:24     ` Michael Ellerman
2017-05-04  9:42   ` Michael Ellerman
2017-05-07 11:15     ` Frederic Barrat
2017-05-03 14:29 ` [RFC 2/2] cxl: Mark context requiring global TLBIs Frederic Barrat
2017-05-04  7:39   ` Balbir Singh
2017-05-07 10:41     ` Frederic Barrat
2017-05-05  5:28 ` [RFC 0/2] powerpc/mm: Mark memory contexts " Alistair Popple

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20170503142906.29220-1-fbarrat@linux.vnet.ibm.com \
    --to=fbarrat@linux.vnet.ibm.com \
    --cc=alistair@popple.id.au \
    --cc=aneesh.kumar@linux.vnet.ibm.com \
    --cc=bsingharora@gmail.com \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=mpe@ellerman.id.au \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).