linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Davidlohr Bueso <dave@stgolabs.net>
To: Gregory Price <gregory.price@memverge.com>
Cc: Dan Williams <dan.j.williams@intel.com>,
	linux-cxl@vger.kernel.org, David Hildenbrand <david@redhat.com>,
	Kees Cook <keescook@chromium.org>,
	stable@vger.kernel.org, Dave Hansen <dave.hansen@linux.intel.com>,
	Michal Hocko <mhocko@suse.com>,
	linux-mm@kvack.org, linux-acpi@vger.kernel.org
Subject: Re: [PATCH 00/18] CXL RAM and the 'Soft Reserved' => 'System RAM' default
Date: Mon, 6 Feb 2023 08:40:56 -0800	[thread overview]
Message-ID: <20230206164056.a4ifv3k4juadlazl@offworld> (raw)
In-Reply-To: <Y+CRyz0eFKfERZLD@memverge.com>

On Mon, 06 Feb 2023, Gregory Price wrote:

>On Sun, Feb 05, 2023 at 05:02:29PM -0800, Dan Williams wrote:
>> Summary:
>> --------
>>
>> CXL RAM support allows for the dynamic provisioning of new CXL RAM
>> regions, and more routinely, assembling a region from an existing
>> configuration established by platform-firmware. The latter is motivated
>> by CXL memory RAS (Reliability, Availability and Serviceability)
>> support, that requires associating device events with System Physical
>> Address ranges and vice versa.
>>
>> The 'Soft Reserved' policy rework arranges for performance
>> differentiated memory like CXL attached DRAM, or high-bandwidth memory,
>> to be designated for 'System RAM' by default, rather than the device-dax
>> dedicated access mode. That current device-dax default is confusing and
>> surprising for the Pareto of users that do not expect memory to be
>> quarantined for dedicated access by default. Most users expect all
>> 'System RAM'-capable memory to show up in FREE(1).
>
>Leverage the same QEMU branch, machine, and configuration as my prior
>tests, i'm now experiencing a kernel panic on boot.  Will debug a bit
>in the morning, but here is the stack trace i'm seeing
>
>Saw this in both 1 and 2 root port configurations

I also see it in "regular" pmem setups, and narrowed it down to this
change in the last patch:

-module_init(cxl_acpi_init);
+/* load before dax_hmem sees 'Soft Reserved' CXL ranges */
+subsys_initcall(cxl_acpi_init);


  reply	other threads:[~2023-02-06 17:08 UTC|newest]

Thread overview: 111+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-02-06  1:02 Dan Williams
2023-02-06  1:02 ` [PATCH 01/18] cxl/Documentation: Update references to attributes added in v6.0 Dan Williams
2023-02-06 15:17   ` Jonathan Cameron
2023-02-06 16:37   ` Gregory Price
2023-02-06 17:27   ` [PATCH 1/18] " Davidlohr Bueso
2023-02-06 19:15   ` [PATCH 01/18] " Ira Weiny
2023-02-06 21:04   ` Dave Jiang
2023-02-09  0:20   ` Verma, Vishal L
2023-02-06  1:02 ` [PATCH 02/18] cxl/region: Add a mode attribute for regions Dan Williams
2023-02-06 15:46   ` Jonathan Cameron
2023-02-06 17:47     ` Dan Williams
2023-02-06 16:39   ` Gregory Price
2023-02-06 19:16   ` Ira Weiny
2023-02-06 21:05   ` Dave Jiang
2023-02-09  0:22   ` Verma, Vishal L
2023-02-06  1:02 ` [PATCH 03/18] cxl/region: Support empty uuids for non-pmem regions Dan Williams
2023-02-06 15:54   ` Jonathan Cameron
2023-02-06 18:07     ` Dan Williams
2023-02-06 19:22   ` Ira Weiny
2023-02-06 19:35     ` Dan Williams
2023-02-09  0:24   ` Verma, Vishal L
2023-02-06  1:02 ` [PATCH 04/18] cxl/region: Validate region mode vs decoder mode Dan Williams
2023-02-06 16:02   ` Jonathan Cameron
2023-02-06 18:14     ` Dan Williams
2023-02-06 16:44   ` Gregory Price
2023-02-06 21:51     ` Dan Williams
2023-02-06 19:55       ` Gregory Price
2023-02-06 19:23   ` Ira Weiny
2023-02-06 22:16   ` Dave Jiang
2023-02-09  0:25   ` Verma, Vishal L
2023-02-06  1:02 ` [PATCH 05/18] cxl/region: Add volatile region creation support Dan Williams
2023-02-06 16:18   ` Jonathan Cameron
2023-02-06 18:19     ` Dan Williams
2023-02-06 16:55   ` Gregory Price
2023-02-06 21:57     ` Dan Williams
2023-02-06 19:56       ` Gregory Price
2023-02-06 19:25   ` Ira Weiny
2023-02-06 22:31   ` Dave Jiang
2023-02-06 22:37     ` Dan Williams
2023-02-09  1:02   ` Verma, Vishal L
2023-02-06  1:03 ` [PATCH 06/18] cxl/region: Refactor attach_target() for autodiscovery Dan Williams
2023-02-06 17:06   ` Jonathan Cameron
2023-02-06 18:48     ` Dan Williams
2023-02-06 19:26   ` Ira Weiny
2023-02-06 22:41   ` Dave Jiang
2023-02-09  1:09   ` Verma, Vishal L
2023-02-06  1:03 ` [PATCH 07/18] cxl/region: Move region-position validation to a helper Dan Williams
2023-02-06 17:44   ` Ira Weiny
2023-02-06 19:15     ` Dan Williams
2023-02-08 12:30   ` Jonathan Cameron
2023-02-09  4:09     ` Dan Williams
2023-02-09  4:26     ` Dan Williams
2023-02-09 11:07       ` Jonathan Cameron
2023-02-09 20:52         ` Dan Williams
2023-02-09 19:45   ` Verma, Vishal L
2023-02-06  1:03 ` [PATCH 08/18] kernel/range: Uplevel the cxl subsystem's range_contains() helper Dan Williams
2023-02-06 17:02   ` Gregory Price
2023-02-06 22:01     ` Dan Williams
2023-02-06 19:28   ` Ira Weiny
2023-02-06 23:41   ` Dave Jiang
2023-02-08 12:32   ` Jonathan Cameron
2023-02-09 19:47   ` Verma, Vishal L
2023-02-06  1:03 ` [PATCH 09/18] cxl/region: Enable CONFIG_CXL_REGION to be toggled Dan Williams
2023-02-06 17:03   ` Gregory Price
2023-02-06 23:57   ` Dave Jiang
2023-02-08 12:36   ` Jonathan Cameron
2023-02-09 20:17   ` Verma, Vishal L
2023-02-06  1:03 ` [PATCH 10/18] cxl/region: Fix passthrough-decoder detection Dan Williams
2023-02-06  5:38   ` Greg KH
2023-02-06 17:22     ` Dan Williams
2023-02-07  0:00   ` Dave Jiang
2023-02-08 12:44   ` Jonathan Cameron
2023-02-09 20:28   ` Verma, Vishal L
2023-02-06  1:03 ` [PATCH 11/18] cxl/region: Add region autodiscovery Dan Williams
2023-02-06 19:02   ` Ira Weiny
2023-02-07 23:54   ` Dave Jiang
2023-02-08 17:07   ` Jonathan Cameron
2023-02-09  4:07     ` Dan Williams
2023-02-06  1:03 ` [PATCH 12/18] tools/testing/cxl: Define a fixed volatile configuration to parse Dan Williams
2023-02-08 17:31   ` Jonathan Cameron
2023-02-09 20:50     ` Dan Williams
2023-02-06  1:03 ` [PATCH 13/18] dax/hmem: Move HMAT and Soft reservation probe initcall level Dan Williams
2023-02-06  1:03 ` [PATCH 14/18] dax/hmem: Drop unnecessary dax_hmem_remove() Dan Williams
2023-02-06 17:15   ` Gregory Price
2023-02-08 17:33   ` Jonathan Cameron
2023-02-06  1:03 ` [PATCH 15/18] dax/hmem: Convey the dax range via memregion_info() Dan Williams
2023-02-08 17:35   ` Jonathan Cameron
2023-02-06  1:03 ` [PATCH 16/18] dax/hmem: Move hmem device registration to dax_hmem.ko Dan Williams
2023-02-06  1:04 ` [PATCH 17/18] dax: Assign RAM regions to memory-hotplug by default Dan Williams
2023-02-06 17:26   ` Gregory Price
2023-02-06 22:15     ` Dan Williams
2023-02-06 19:05       ` Gregory Price
2023-02-06 23:20         ` Dan Williams
2023-02-06  1:04 ` [PATCH 18/18] cxl/dax: Create dax devices for CXL RAM regions Dan Williams
2023-02-06  5:36 ` [PATCH 00/18] CXL RAM and the 'Soft Reserved' => 'System RAM' default Gregory Price
2023-02-06 16:40   ` Davidlohr Bueso [this message]
2023-02-06 18:23     ` Dan Williams
2023-02-06 17:29   ` Dan Williams
2023-02-06 17:18     ` Davidlohr Bueso
     [not found] ` <CGME20230208173730uscas1p2af3a9eeb8946dfa607b190c079a49653@uscas1p2.samsung.com>
2023-02-08 17:37   ` Fan Ni
2023-02-09  4:56     ` Dan Williams
2023-02-13 12:13 ` David Hildenbrand
2023-02-14 18:45   ` Dan Williams
2023-02-14 18:27 ` Gregory Price
2023-02-14 18:39   ` Dan Williams
2023-02-14 19:01     ` Gregory Price
2023-02-14 21:18       ` Jonathan Cameron
2023-02-14 21:51         ` Gregory Price
2023-02-14 21:54           ` Gregory Price
2023-02-15 10:03             ` Jonathan Cameron
2023-02-18  9:47               ` Gregory Price

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=20230206164056.a4ifv3k4juadlazl@offworld \
    --to=dave@stgolabs.net \
    --cc=dan.j.williams@intel.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=david@redhat.com \
    --cc=gregory.price@memverge.com \
    --cc=keescook@chromium.org \
    --cc=linux-acpi@vger.kernel.org \
    --cc=linux-cxl@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@suse.com \
    --cc=stable@vger.kernel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox