From: Muralidhara M K <muralidhara.mk@amd.com>
To: <ilpo.jarvinen@linux.intel.com>
Cc: <platform-driver-x86@vger.kernel.org>,
<linux-kernel@vger.kernel.org>, <muthusamy.ramalingam@amd.com>,
Muralidhara M K <muralidhara.mk@amd.com>
Subject: [PATCH 7/7] Documentation/arch/x86/amd_hsmp: Document the SMN and MSR IOCTLs
Date: Wed, 29 Jul 2026 22:10:34 +0530 [thread overview]
Message-ID: <20260729164034.1331375-8-muralidhara.mk@amd.com> (raw)
In-Reply-To: <20260729164034.1331375-1-muralidhara.mk@amd.com>
Describe HSMP_IOCTL_SMN_CMD and HSMP_IOCTL_MSR_CMD: the payload structs,
the CAP_SYS_RAWIO and open-mode requirements, and the rule that both are
read-only, so a request with @write set is refused with -EPERM even for a
fully privileged caller on an O_RDWR handle.
Also note that reading the protocol_version attribute can fail on the
Fam1Ah client platforms, because some client SMU builds reject the
interface-version query, which is why the telemetry ioctl rather than
that attribute is the way to reach the client telemetry layout.
Signed-off-by: Muralidhara M K <muralidhara.mk@amd.com>
---
Documentation/arch/x86/amd_hsmp.rst | 44 +++++++++++++++++++++++++++++
1 file changed, 44 insertions(+)
diff --git a/Documentation/arch/x86/amd_hsmp.rst b/Documentation/arch/x86/amd_hsmp.rst
index 8a9d6fe7d4cf..0f03201a9f68 100644
--- a/Documentation/arch/x86/amd_hsmp.rst
+++ b/Documentation/arch/x86/amd_hsmp.rst
@@ -229,6 +229,50 @@ The following IOCTLs are defined:
``sizeof(struct hsmp_metric_table)``. Later version metrics table
layout is documented in the Public PPR.
+ On the Fam1Ah client platforms reading ``protocol_version`` can fail,
+ because some client SMU builds reject the interface-version query.
+ Those parts have their own telemetry layout and this ioctl is the way
+ to read it.
+
+``ioctl(file, HSMP_IOCTL_SMN_CMD, struct hsmp_smn_message *smn)``
+ Read a 32-bit SMN register on the socket given by ``sock_ind``. This
+ reaches registers outside the HSMP message ABI, so it requires
+ ``CAP_SYS_RAWIO`` as well as a handle opened for reading, the latter
+ because the value read is written back into the request struct.
+
+ The ioctl is read-only. ``write`` must be zero, and a request that
+ sets it is rejected with ``-EPERM`` even with ``CAP_SYS_RAWIO`` and an
+ ``O_RDWR`` handle; the field exists only so that write support could be
+ added later without changing the layout. ``reserved`` must be zero.
+ Argument::
+
+ struct hsmp_smn_message {
+ __u32 smn_address; /* SMN address to read */
+ __u32 value; /* Value read, filled in by the kernel */
+ __u16 sock_ind; /* Socket index */
+ __u8 write; /* Must be zero */
+ __u8 reserved; /* Reserved, must be zero */
+ };
+
+``ioctl(file, HSMP_IOCTL_MSR_CMD, struct hsmp_msr_message *msr)``
+ Read a 64-bit MSR on the logical CPU given by ``core_id``, or on
+ whichever CPU the ioctl runs on when ``core_id`` is
+ ``HSMP_MSR_ANY_CPU`` (``(__u32)-1``). Any other ``core_id`` must refer
+ to an online CPU, otherwise the call fails with ``-EINVAL``. Requires
+ ``CAP_SYS_RAWIO`` and a handle opened for reading.
+
+ Read-only on the same terms as ``HSMP_IOCTL_SMN_CMD``: a non-zero
+ ``write`` is rejected with ``-EPERM``, and every byte of ``reserved``
+ must be zero. Argument::
+
+ struct hsmp_msr_message {
+ __u32 msr_address; /* MSR index to read */
+ __u32 core_id; /* Logical CPU, or HSMP_MSR_ANY_CPU */
+ __u64 value; /* Value read, filled in by the kernel */
+ __u8 write; /* Must be zero */
+ __u8 reserved[3]; /* Reserved, must be zero */
+ };
+
The ioctl would return a non-zero on failure; you can read errno to see
what happened. The transaction returns 0 on success.
--
2.34.1
next prev parent reply other threads:[~2026-07-29 16:41 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-07-29 16:40 [PATCH 0/7] platform/x86/amd/hsmp: Family 1Ah client support Muralidhara M K
2026-07-29 16:40 ` [PATCH 1/7] platform/x86/amd/hsmp: Add HSMP client support for Family 1Ah Muralidhara M K
2026-07-29 21:27 ` Mario Limonciello
2026-07-30 9:37 ` M K, Muralidhara
2026-07-30 16:43 ` Armin Wolf
2026-07-31 4:27 ` M K, Muralidhara
2026-07-31 7:00 ` Shyam Sundar S K
2026-07-31 10:29 ` Armin Wolf
2026-10-11 10:04 ` Shyam Sundar S K
2026-07-29 16:40 ` [PATCH 2/7] platform/x86/amd/hsmp: Route metric table through the client messages Muralidhara M K
2026-07-29 21:29 ` Mario Limonciello
2026-07-30 9:42 ` M K, Muralidhara
2026-07-29 16:40 ` [PATCH 3/7] platform/x86/amd/hsmp: Add ACPI client support via the SMNR method Muralidhara M K
2026-07-29 21:30 ` Mario Limonciello
2026-07-30 9:44 ` M K, Muralidhara
2026-07-29 16:40 ` [PATCH 4/7] platform/x86/amd/hsmp: Leave the hwmon power sensors off on client platforms Muralidhara M K
2026-07-29 21:35 ` Mario Limonciello
2026-07-30 10:01 ` M K, Muralidhara
2026-07-29 16:40 ` [PATCH 5/7] platform/x86/amd/hsmp: Add SMN read IOCTL support Muralidhara M K
2026-07-29 16:40 ` [PATCH 6/7] platform/x86/amd/hsmp: Add MSR " Muralidhara M K
2026-07-29 16:40 ` Muralidhara M K [this message]
2026-07-29 21:41 ` [PATCH 7/7] Documentation/arch/x86/amd_hsmp: Document the SMN and MSR IOCTLs Mario Limonciello
2026-07-30 10:05 ` M K, Muralidhara
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=20260729164034.1331375-8-muralidhara.mk@amd.com \
--to=muralidhara.mk@amd.com \
--cc=ilpo.jarvinen@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=muthusamy.ramalingam@amd.com \
--cc=platform-driver-x86@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
all inboxes | Powered by JetHome®