From: Ben Cheatham <benjamin.cheatham@amd.com>
To: Alison Schofield <alison.schofield@intel.com>
Cc: linux-cxl@vger.kernel.org, vishal.l.verma@intel.com,
ira.weiny@intel.com, dan.j.williams@intel.com,
jonathan.cameron@huawei.com, bwidawsk@kernel.org
Subject: Re: [PATCH] cxl: identify CXL3.0 cache/mem register capability IDs
Date: Thu, 20 Oct 2022 14:27:11 -0500 [thread overview]
Message-ID: <9de53e60-5eab-37ee-97e5-658884de8e92@amd.com> (raw)
In-Reply-To: <Y1GZgjGg50/+bz6f@aschofie-mobl2>
On 10/20/22 1:54 PM, Alison Schofield wrote:
> On Thu, Oct 20, 2022 at 12:52:39PM -0500, Ben Cheatham wrote:
>> Add code to identify the non extended cache mem CXL register capabilities
>> based on capability ID.
>>
>> As of now, nothing is done with this information except logging that the
>> capabilities were found. In the case of the NULL capability this is
>> probably all that should be done since the spec specifies software should
>> skip this capability. The other capabilities are added so that if any
>> additional setup/info is required, like for the HDM decoder capability, the
>> stub is already there.
> Hi Ben,
>
> What is the user visible impact of making this change.
> Perhaps it would be better reviewed alongside it's use case.
>
> Alison
Hi Alison,
As this patch is written it's mainly for debugging/logging, but there is
some work going on inside AMD that could use the RAS ID case for getting
info about/initializing RAS capabilities. Originally the patch was just
for logging skipped NULL capabilities, but I figured I may as well add
cases for the other capability IDs in case someone wanted to use them.
That being said, I would be fine submitting this code inside another
patch where it's being used at a later date. Thanks for the comments.
Ben
>> Signed-off-by: Ben Cheatham <Benjamin.Cheatham@amd.com>
>> ---
>> drivers/cxl/core/regs.c | 42 ++++++++++++++++++++++++++++++++++++++---
>> drivers/cxl/cxl.h | 13 ++++++++++++-
>> 2 files changed, 51 insertions(+), 4 deletions(-)
>>
>> diff --git a/drivers/cxl/core/regs.c b/drivers/cxl/core/regs.c
>> index 39a129c57d40..616d926de1e6 100644
>> --- a/drivers/cxl/core/regs.c
>> +++ b/drivers/cxl/core/regs.c
>> @@ -27,8 +27,8 @@
>> * @base: Mapping containing the HDM Decoder Capability Header
>> * @map: Map object describing the register block information found
>> *
>> - * See CXL 2.0 8.2.4 Component Register Layout and Definition
>> - * See CXL 2.0 8.2.5.5 CXL Device Register Interface
>> + * See CXL 3.0 8.2.3 Component Register Layout and Definition
>> + * See CXL 3.0 8.2.8 CXL Device Register Interface
>> *
>> * Probe for component register information and return it in map object.
>> */
>> @@ -42,7 +42,7 @@ void cxl_probe_component_regs(struct device *dev, void
>> __iomem *base,
>>
>> /*
>> * CXL.cache and CXL.mem registers are at offset 0x1000 as defined in
>> - * CXL 2.0 8.2.4 Table 141.
>> + * CXL 3.0 8.2.3 Table 8-21.
>> */
>> base += CXL_CM_OFFSET;
>>
>> @@ -71,6 +71,26 @@ void cxl_probe_component_regs(struct device *dev, void
>> __iomem *base,
>> register_block = base + offset;
>>
>> switch (cap_id) {
>> + case CXL_CM_CAP_CAP_ID_NULL:
>> + dev_dbg(dev, "found NULL capability (0x%x)\n",
>> + offset);
>> + break;
>> + case CXL_CM_CAP_CAP_ID_CXL:
>> + dev_dbg(dev, "found CXL capability (0x%x)\n",
>> + offset);
>> + break;
>> + case CXL_CM_CAP_CAP_ID_RAS:
>> + dev_dbg(dev, "found RAS capability (0x%x)\n",
>> + offset);
>> + break;
>> + case CXL_CM_CAP_CAP_ID_SECURITY:
>> + dev_dbg(dev, "found Security capability (0x%x)\n",
>> + offset);
>> + break;
>> + case CXL_CM_CAP_CAP_ID_LINK:
>> + dev_dbg(dev, "found Link capability (0x%x)\n",
>> + offset);
>> + break;
>> case CXL_CM_CAP_CAP_ID_HDM:
>> dev_dbg(dev, "found HDM decoder capability (0x%x)\n",
>> offset);
>> @@ -84,6 +104,22 @@ void cxl_probe_component_regs(struct device *dev, void
>> __iomem *base,
>> map->hdm_decoder.offset = CXL_CM_OFFSET + offset;
>> map->hdm_decoder.size = length;
>> break;
>> + case CXL_CM_CAP_CAP_ID_EXT_SEC:
>> + dev_dbg(dev, "found Extended Security capability (0x%x)\n",
>> + offset);
>> + break;
>> + case CXL_CM_CAP_CAP_ID_IDE:
>> + dev_dbg(dev, "found IDE capability (0x%x)\n",
>> + offset);
>> + break;
>> + case CXL_CM_CAP_CAP_ID_SNOOP:
>> + dev_dbg(dev, "found Snoop Filter capability (0x%x)\n",
>> + offset);
>> + break;
>> + case CXL_CM_CAP_CAP_ID_TIMEOUT:
>> + dev_dbg(dev, "found Timeout and Isolation capability (0x%x)\n",
>> + offset);
>> + break;
>> default:
>> dev_dbg(dev, "Unknown CM cap ID: %d (0x%x)\n", cap_id,
>> offset);
>> diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
>> index f680450f0b16..762e5243162a 100644
>> --- a/drivers/cxl/cxl.h
>> +++ b/drivers/cxl/cxl.h
>> @@ -33,9 +33,20 @@
>> #define CXL_CM_CAP_HDR_ARRAY_SIZE_MASK GENMASK(31, 24)
>> #define CXL_CM_CAP_PTR_MASK GENMASK(31, 20)
>>
>> -#define CXL_CM_CAP_CAP_ID_HDM 0x5
>> #define CXL_CM_CAP_CAP_HDM_VERSION 1
>>
>> +/* CXL 3.0 8.2.4 Table 8-22 CXL_Capability_ID Assignment*/
>> +#define CXL_CM_CAP_CAP_ID_NULL 0x0
>> +#define CXL_CM_CAP_CAP_ID_CXL 0x1
>> +#define CXL_CM_CAP_CAP_ID_RAS 0x2
>> +#define CXL_CM_CAP_CAP_ID_SECURITY 0x3
>> +#define CXL_CM_CAP_CAP_ID_LINK 0x4
>> +#define CXL_CM_CAP_CAP_ID_HDM 0x5
>> +#define CXL_CM_CAP_CAP_ID_EXT_SEC 0x6
>> +#define CXL_CM_CAP_CAP_ID_IDE 0x7
>> +#define CXL_CM_CAP_CAP_ID_SNOOP 0x8
>> +#define CXL_CM_CAP_CAP_ID_TIMEOUT 0x9
>> +
>> /* HDM decoders CXL 2.0 8.2.5.12 CXL HDM Decoder Capability Structure */
>> #define CXL_HDM_DECODER_CAP_OFFSET 0x0
>> #define CXL_HDM_DECODER_COUNT_MASK GENMASK(3, 0)
>> --
>> 2.34.1
prev parent reply other threads:[~2022-10-20 19:27 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-10-20 17:52 [PATCH] cxl: identify CXL3.0 cache/mem register capability IDs Ben Cheatham
2022-10-20 18:54 ` Alison Schofield
2022-10-20 19:27 ` Ben Cheatham [this message]
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=9de53e60-5eab-37ee-97e5-658884de8e92@amd.com \
--to=benjamin.cheatham@amd.com \
--cc=alison.schofield@intel.com \
--cc=bwidawsk@kernel.org \
--cc=dan.j.williams@intel.com \
--cc=ira.weiny@intel.com \
--cc=jonathan.cameron@huawei.com \
--cc=linux-cxl@vger.kernel.org \
--cc=vishal.l.verma@intel.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