Re: [PATCH v5 4/4] mm: Defer ZONE_DEVICE page initialization to the point where we init pgmap

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

To: Dan Williams <dan.j.williams@xxxxxxxxx>
Subject: Re: [PATCH v5 4/4] mm: Defer ZONE_DEVICE page initialization to the point where we init pgmap
From: Michal Hocko <mhocko@xxxxxxxxxx>
Date: Thu, 27 Sep 2018 13:20:41 +0200
Cc: alexander.h.duyck@xxxxxxxxxxxxxxx, Linux MM <linux-mm@xxxxxxxxx>, Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>, Linux Kernel Mailing List <linux-kernel@xxxxxxxxxxxxxxx>, linux-nvdimm <linux-nvdimm@xxxxxxxxxxxx>, Pasha Tatashin <pavel.tatashin@xxxxxxxxxxxxx>, Dave Jiang <dave.jiang@xxxxxxxxx>, Dave Hansen <dave.hansen@xxxxxxxxx>, Jérôme Glisse <jglisse@xxxxxxxxxx>, rppt@xxxxxxxxxxxxxxxxxx, Logan Gunthorpe <logang@xxxxxxxxxxxx>, Ingo Molnar <mingo@xxxxxxxxxx>, "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
In-reply-to: <CAPcyv4iVnodai0bB74yeSCD2H+hoLsZYUk4sR9jV0pPAE+Zorw@mail.gmail.com>
References: <20180925200551.3576.18755.stgit@localhost.localdomain> <20180925202053.3576.66039.stgit@localhost.localdomain> <20180926075540.GD6278@dhcp22.suse.cz> <6f87a5d7-05e2-00f4-8568-bb3521869cea@linux.intel.com> <CAPcyv4iVnodai0bB74yeSCD2H+hoLsZYUk4sR9jV0pPAE+Zorw@mail.gmail.com>
User-agent: Mutt/1.10.1 (2018-07-13)

On Wed 26-09-18 11:52:56, Dan Williams wrote:
[...]
> Could we push the hotplug lock deeper to the places that actually need
> it? What I found with my initial investigation is that we don't even
> need the hotplug lock for the vmemmap initialization with this patch
> [1].

Yes, the scope of the hotplug lock should be evaluated and _documented_.
Then we can build on top.
-- 
Michal Hocko
SUSE Labs

References:
- [PATCH v5 0/4] Address issues slowing persistent memory initialization
  - From: Alexander Duyck
- [PATCH v5 4/4] mm: Defer ZONE_DEVICE page initialization to the point where we init pgmap
  - From: Alexander Duyck
- Re: [PATCH v5 4/4] mm: Defer ZONE_DEVICE page initialization to the point where we init pgmap
  - From: Michal Hocko
- Re: [PATCH v5 4/4] mm: Defer ZONE_DEVICE page initialization to the point where we init pgmap
  - From: Alexander Duyck
- Re: [PATCH v5 4/4] mm: Defer ZONE_DEVICE page initialization to the point where we init pgmap
  - From: Dan Williams

Prev by Date: Re: [PATCH v5 07/11] filesystem-dax: Introduce dax_lock_mapping_entry()
Next by Date: Re: [PATCH v3 3/4] devres: provide devm_kstrdup_const()
Previous by thread: Re: [PATCH v5 4/4] mm: Defer ZONE_DEVICE page initialization to the point where we init pgmap
Next by thread: Re: [PATCH v5 4/4] mm: Defer ZONE_DEVICE page initialization to the point where we init pgmap
Index(es):
- Date
- Thread

[Index of Archives] [Linux ARM Kernel] [Linux ARM] [Linux Omap] [Fedora ARM] [IETF Annouce] [Bugtraq] [Linux OMAP] [Linux MIPS] [eCos] [Asterisk Internet PBX] [Linux API]