From: Dan Williams <dan.j.williams@intel.com>
To: Linda Knippers <linda.knippers@hpe.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
Christoph Hellwig <hch@lst.de>, david <david@fromorbit.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"linux-nvdimm@lists.01.org" <linux-nvdimm@lists.01.org>
Subject: Re: [PATCH 01/13] driver core, libnvdimm: disable manual unbind of dimms while region active
Date: Mon, 6 Jun 2016 12:31:28 -0700 [thread overview]
Message-ID: <CAPcyv4j2saB7=k=uw3Ze-cmsHW-PkHY=Xez4AomAxWUFR1-x2Q@mail.gmail.com> (raw)
In-Reply-To: <0d64fc79-fdfa-9d50-c8b8-fc7c3e79f1f4@hpe.com>
On Mon, Jun 6, 2016 at 12:25 PM, Linda Knippers <linda.knippers@hpe.com> wrote:
> On 6/4/2016 4:52 PM, Dan Williams wrote:
>> There are scenarios where we need a middle ground between disabling all
>> manual bind/unbind attempts (via driver->suppress_bind_attrs) and
>> allowing unbind at any userspace-determined time. Pinning modules takes
>> away one vector for unwanted out-of-sequence device_release_driver()
>> invocations, this new mechanism (via device->suppress_unbind_attr) takes
>> away another.
>>
>> The first user of this mechanism is the libnvdimm sub-system where
>> manual dimm disabling should be prevented while the dimm is active in
>> any region. Note that there is a 1:N dimm-to-region relationship which
>> is why this is implemented as a disable count rather than a flag. This
>> forces userspace to disable regions before dimms when manually shutting
>> down a bus topology.
>
> How is this related to deprecating pcommit?
We need guarantees that the flush hint mappings are valid for the
duration of a pmem namespace being enabled. I am going to move the
mapping of the flush hint region from per-dimm to per-region. However
since multiple regions may reference the same dimm the mapping needs
to be reference counted and shared across regions. This will be
similar to the arrangement we have for BLK-regions that share a
control region mapping.
_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm
WARNING: multiple messages have this Message-ID (diff)
From: Dan Williams <dan.j.williams@intel.com>
To: Linda Knippers <linda.knippers@hpe.com>
Cc: "linux-nvdimm@lists.01.org" <linux-nvdimm@ml01.01.org>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
david <david@fromorbit.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Christoph Hellwig <hch@lst.de>
Subject: Re: [PATCH 01/13] driver core, libnvdimm: disable manual unbind of dimms while region active
Date: Mon, 6 Jun 2016 12:31:28 -0700 [thread overview]
Message-ID: <CAPcyv4j2saB7=k=uw3Ze-cmsHW-PkHY=Xez4AomAxWUFR1-x2Q@mail.gmail.com> (raw)
In-Reply-To: <0d64fc79-fdfa-9d50-c8b8-fc7c3e79f1f4@hpe.com>
On Mon, Jun 6, 2016 at 12:25 PM, Linda Knippers <linda.knippers@hpe.com> wrote:
> On 6/4/2016 4:52 PM, Dan Williams wrote:
>> There are scenarios where we need a middle ground between disabling all
>> manual bind/unbind attempts (via driver->suppress_bind_attrs) and
>> allowing unbind at any userspace-determined time. Pinning modules takes
>> away one vector for unwanted out-of-sequence device_release_driver()
>> invocations, this new mechanism (via device->suppress_unbind_attr) takes
>> away another.
>>
>> The first user of this mechanism is the libnvdimm sub-system where
>> manual dimm disabling should be prevented while the dimm is active in
>> any region. Note that there is a 1:N dimm-to-region relationship which
>> is why this is implemented as a disable count rather than a flag. This
>> forces userspace to disable regions before dimms when manually shutting
>> down a bus topology.
>
> How is this related to deprecating pcommit?
We need guarantees that the flush hint mappings are valid for the
duration of a pmem namespace being enabled. I am going to move the
mapping of the flush hint region from per-dimm to per-region. However
since multiple regions may reference the same dimm the mapping needs
to be reference counted and shared across regions. This will be
similar to the arrangement we have for BLK-regions that share a
control region mapping.
next prev parent reply other threads:[~2016-06-06 19:31 UTC|newest]
Thread overview: 73+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-06-04 20:52 [PATCH 00/13] deprecate pcommit Dan Williams
2016-06-04 20:52 ` Dan Williams
2016-06-04 20:52 ` [PATCH 01/13] driver core, libnvdimm: disable manual unbind of dimms while region active Dan Williams
2016-06-04 20:52 ` Dan Williams
2016-06-04 21:10 ` Greg Kroah-Hartman
2016-06-04 21:10 ` Greg Kroah-Hartman
2016-06-04 21:39 ` Dan Williams
2016-06-04 21:39 ` Dan Williams
2016-06-04 21:45 ` Greg Kroah-Hartman
2016-06-04 21:45 ` Greg Kroah-Hartman
2016-06-04 21:48 ` Dan Williams
2016-06-04 21:48 ` Dan Williams
2016-06-04 21:50 ` kbuild test robot
2016-06-04 21:50 ` kbuild test robot
2016-06-06 19:25 ` Linda Knippers
2016-06-06 19:25 ` Linda Knippers
2016-06-06 19:31 ` Dan Williams [this message]
2016-06-06 19:31 ` Dan Williams
2016-06-06 19:36 ` Dan Williams
2016-06-06 19:36 ` Dan Williams
2016-06-06 19:36 ` Linda Knippers
2016-06-06 19:36 ` Linda Knippers
2016-06-06 19:46 ` Dan Williams
2016-06-06 19:46 ` Dan Williams
2016-06-06 20:20 ` Linda Knippers
2016-06-06 20:20 ` Linda Knippers
2016-06-06 20:36 ` Dan Williams
2016-06-06 20:36 ` Dan Williams
2016-06-06 21:15 ` Linda Knippers
2016-06-06 21:15 ` Linda Knippers
2016-06-04 20:52 ` [PATCH 02/13] nfit: always associate flush hints Dan Williams
2016-06-04 20:52 ` Dan Williams
2016-06-04 20:52 ` [PATCH 03/13] libnvdimm: introduce nvdimm_flush() Dan Williams
2016-06-04 20:52 ` Dan Williams
2016-06-06 17:45 ` Jeff Moyer
2016-06-04 20:52 ` [PATCH 04/13] libnvdimm, nfit: move flush hint mapping to dimm driver Dan Williams
2016-06-04 20:52 ` Dan Williams
2016-06-04 21:29 ` kbuild test robot
2016-06-04 21:29 ` kbuild test robot
2016-06-04 21:40 ` kbuild test robot
2016-06-04 21:40 ` kbuild test robot
2016-06-04 21:49 ` kbuild test robot
2016-06-04 21:49 ` kbuild test robot
2016-06-07 18:11 ` Kani, Toshimitsu
2016-06-07 18:11 ` Kani, Toshimitsu
2016-06-07 18:15 ` Dan Williams
2016-06-07 18:15 ` Dan Williams
2016-06-04 20:52 ` [PATCH 05/13] tools/testing/nvdimm: simulate multiple flush hints per-dimm Dan Williams
2016-06-04 20:52 ` Dan Williams
2016-06-04 20:53 ` [PATCH 06/13] libnvdimm: cycle flush hints per-cpu Dan Williams
2016-06-04 20:53 ` Dan Williams
2016-06-04 20:53 ` [PATCH 07/13] libnvdimm, pmem: use REQ_FUA, REQ_FLUSH for nvdimm_flush() Dan Williams
2016-06-04 20:53 ` Dan Williams
2016-06-04 20:53 ` [PATCH 08/13] fs/dax: remove wmb_pmem() Dan Williams
2016-06-04 20:53 ` Dan Williams
2016-06-04 20:53 ` [PATCH 09/13] libnvdimm, pmem: use nvdimm_flush() for namespace I/O writes Dan Williams
2016-06-04 20:53 ` Dan Williams
2016-06-04 20:53 ` [PATCH 10/13] pmem: kill wmb_pmem() Dan Williams
2016-06-04 20:53 ` Dan Williams
2016-06-04 20:53 ` [PATCH 11/13] Revert "KVM: x86: add pcommit support" Dan Williams
2016-06-04 20:53 ` Dan Williams
2016-06-06 15:14 ` Paolo Bonzini
2016-06-06 16:14 ` Dan Williams
2016-06-04 20:53 ` [PATCH 12/13] x86/insn: remove pcommit Dan Williams
2016-06-04 20:53 ` Dan Williams
2016-06-04 20:53 ` [PATCH 13/13] pmem: kill __pmem address space Dan Williams
2016-06-04 20:53 ` Dan Williams
2016-06-04 22:18 ` kbuild test robot
2016-06-04 22:18 ` kbuild test robot
2016-06-05 17:41 ` [PATCH 00/13] deprecate pcommit Andy Lutomirski
2016-06-05 17:41 ` Andy Lutomirski
2016-06-05 18:48 ` Rudoff, Andy
2016-06-05 18:48 ` Rudoff, Andy
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='CAPcyv4j2saB7=k=uw3Ze-cmsHW-PkHY=Xez4AomAxWUFR1-x2Q@mail.gmail.com' \
--to=dan.j.williams@intel.com \
--cc=david@fromorbit.com \
--cc=gregkh@linuxfoundation.org \
--cc=hch@lst.de \
--cc=linda.knippers@hpe.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvdimm@lists.01.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.