All of lore.kernel.org
 help / color / mirror / Atom feed
From: Gregory Price <gregory.price@memverge.com>
To: Dan Williams <dan.j.williams@intel.com>
Cc: linux-cxl@vger.kernel.org, dave.hansen@linux.intel.com,
	linux-mm@kvack.org, linux-acpi@vger.kernel.org
Subject: Re: [PATCH 04/18] cxl/region: Validate region mode vs decoder mode
Date: Mon, 6 Feb 2023 11:44:19 -0500	[thread overview]
Message-ID: <Y+EuYzk2Ro7WBEhz@memverge.com> (raw)
In-Reply-To: <167564537131.847146.9020072654741860107.stgit@dwillia2-xfh.jf.intel.com>

On Sun, Feb 05, 2023 at 05:02:51PM -0800, Dan Williams wrote:
> In preparation for a new region mode, do not, for example, allow
> 'ram' decoders to be assigned to 'pmem' regions and vice versa.
> 
> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
> ---
>  drivers/cxl/core/region.c |    6 ++++++
>  1 file changed, 6 insertions(+)
> 
> diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
> index c9e7f05caa0f..53d6dbe4de6d 100644
> --- a/drivers/cxl/core/region.c
> +++ b/drivers/cxl/core/region.c
> @@ -1217,6 +1217,12 @@ static int cxl_region_attach(struct cxl_region *cxlr,
>  	struct cxl_dport *dport;
>  	int i, rc = -ENXIO;
>  
> +	if (cxled->mode != cxlr->mode) {
> +		dev_dbg(&cxlr->dev, "%s region mode: %d mismatch: %d\n",
> +			dev_name(&cxled->cxld.dev), cxlr->mode, cxled->mode);
> +		return -EINVAL;
> +	}
> +
>  	if (cxled->mode == CXL_DECODER_DEAD) {
>  		dev_dbg(&cxlr->dev, "%s dead\n", dev_name(&cxled->cxld.dev));
>  		return -ENODEV;
> 


Maybe a stupid question.  It will be entirely possible to "convert" pmem
to "ram" (i.e. just online it as system memory).

Are type-3 devices with pmem expected to carry 2 decoders (one ram, 1
pmem), such that you can create a ram region from pmem, or is it expected
that the pmem decoder will be used for pmem, even if it gets onlined
as volatile?

Just asking because depending on how that flushes out, you might
expected a "ram region" to get assigned to a "pmem decoder", unless
you're expecting all pmem-carrying-devices to create 2 decoders per pmem
region depending on how the end user intends to use it.

~Gregory

  parent reply	other threads:[~2023-02-06 20:43 UTC|newest]

Thread overview: 112+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-02-06  1:02 [PATCH 00/18] CXL RAM and the 'Soft Reserved' => 'System RAM' default 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 [this message]
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
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
2023-02-15 10:03               ` Jonathan Cameron via
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=Y+EuYzk2Ro7WBEhz@memverge.com \
    --to=gregory.price@memverge.com \
    --cc=dan.j.williams@intel.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=linux-acpi@vger.kernel.org \
    --cc=linux-cxl@vger.kernel.org \
    --cc=linux-mm@kvack.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.