linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: Michael Bringmann <mwb@linux.vnet.ibm.com>
To: linuxppc-dev@lists.ozlabs.org, mwb@linux.vnet.ibm.com
Cc: Juliet Kim <minkim@us.ibm.com>,
	Thomas Falcon <tlfalcon@linux.vnet.ibm.com>,
	Tyrel Datwyler <tyreld@linux.vnet.ibm.com>,
	Nathan Fontenot <nfont@linux.vnet.ibm.com>
Subject: [PATCH v06 0/5] powerpc/migration: Affinity fix for memory
Date: Mon, 15 Oct 2018 14:45:29 -0500	[thread overview]
Message-ID: <20181015194522.5562.61687.stgit@ltcalpine2-lp9.aus.stglabs.ibm.com> (raw)

The migration of LPARs across Power systems affects many attributes
including that of the associativity of memory blocks.  The patches
in this set execute when a system is coming up fresh upon a migration
target.  They are intended to,

* Recognize changes to the associativity of memory recorded in
  internal data structures when compared to the latest copies in
  the device tree (e.g. ibm,dynamic-memory, ibm,dynamic-memory-v2).
* Recognize changes to the associativity mapping (e.g. ibm,
  associativity-lookup-arrays), locate all assigned memory blocks
  corresponding to each changed row, and readd all such blocks.
* Generate calls to other code layers to reset the data structures
  related to associativity of memory.
* Re-register the 'changed' entities into the target system.
  Re-registration of memory blocks mostly entails acting as if they
  have been newly hot-added into the target system.

This code builds upon features introduced in a previous patch set
that updates CPUs for affinity changes that may occur during LPM.

Signed-off-by: Michael Bringmann <mwb@linux.vnet.ibm.com>

Michael Bringmann (5):
  powerpc/drmem: Export 'dynamic-memory' loader
  powerpc/drmem: Add internal_flags feature
  migration/memory: Add hotplug flags READD_MULTIPLE
  migration/memory: Evaluate LMB assoc changes
  migration/memory: Support 'ibm,dynamic-memory-v2'
---
Changes in v06:
  -- Rebase to powerpc next branch to account for recent code changes.
  -- Fix prototype problem when CONFIG_MEMORY_HOTPLUG not defined.
Changes in v05:
  -- Add walk_drmem_lmbs_pairs to replace macro for_each_pair_lmb
  -- Use walk_drmem_lmbs_pairs and callback instead of local loop
  -- Provide dlpar_memory_readd_helper routine to compress some common code
  -- Move common structure from numa.c + hotplug-memory.c to header file.
  -- Clarify some comments.
Changes in v04:
  -- Move dlpar_memory_readd_multiple() to patch with new ACTION
     constant.
  -- Move init of 'lmb->internal_flags' in init_drmem_v2_lmbs to
     patch with other references to flag.
  -- Correct spacing in one of the patches
Changes in v03:
  -- Change operation to tag changed LMBs in DRMEM array instead of
     queuing a potentially huge number of structures.
  -- Added another hotplug queue event for CPU/memory operations
  -- Added internal_flags feature to DRMEM
  -- Improve the patch description language for the patch set.
  -- Revise patch set to queue worker for memory association
     updates directly to pseries worker queue.


                 reply	other threads:[~2018-10-15 19:47 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

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=20181015194522.5562.61687.stgit@ltcalpine2-lp9.aus.stglabs.ibm.com \
    --to=mwb@linux.vnet.ibm.com \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=minkim@us.ibm.com \
    --cc=nfont@linux.vnet.ibm.com \
    --cc=tlfalcon@linux.vnet.ibm.com \
    --cc=tyreld@linux.vnet.ibm.com \
    /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).