From: Babu Moger <babu.moger@amd.com>
To: tony.luck@intel.com, reinette.chatre@intel.com,
ben.horgan@arm.com, Dave.Martin@arm.com, james.morse@arm.com,
bp@alien8.de
Cc: corbet@lwn.net, skhan@linuxfoundation.org, rdunlap@infradead.org,
x86@kernel.org, fustini@kernel.org, tglx@kernel.org,
mingo@redhat.com, dave.hansen@linux.intel.com, hpa@zytor.com,
fenghuay@nvidia.com, rppt@kernel.org, arnd@arndb.de,
kmehltretter@gmail.com, dapeng1.mi@linux.intel.com,
elver@google.com, enelsonmoore@gmail.com, jlayton@kernel.org,
seanjc@google.com, ewanhai-oc@zhaoxin.com,
binbin.wu@linux.intel.com, nikunj@amd.com, ashish.kalra@amd.com,
peterz@infradead.org, superm1@kernel.org,
thomas.lendacky@amd.com, prathyushi.nangia@amd.com,
kim.phillips@amd.com, ricardo.neri-calderon@linux.intel.com,
darwi@linutronix.de, linux-doc@vger.kernel.org,
linux-kernel@vger.kernel.org,
linux-arm-kernel@lists.infradead.org
Subject: Re: [PATCH v7 15/19] fs/resctrl: Extend info/kernel_mode to configure the kernel mode
Date: Mon, 16 Nov 2026 14:09:48 -0600 [thread overview]
Message-ID: <3d008992-dab9-4353-a25e-0007926e19a4@amd.com> (raw)
In-Reply-To: <f2ad1989facce953f3ffe1b8687ae4fcf8629a26.1794437052.git.babu.moger@amd.com>
On 11/11/26 16:44, Babu Moger wrote:
> Kernel mode support allows the CPU's CLOSID and/or RMID associations to
> change during the transition from user mode to kernel mode. The resctrl
> file info/kernel_mode lists the current kernel mode configuration.
>
> Extend info/kernel_mode with write support so user space can configure the
> active kernel mode. Validate kernel mode configuration before activation.
> Restrict backing groups to shareable mode so the kernel can use the group's
> CLOSID and/or RMID, which are shared with the group's tasks.
>
> Document the interface in Documentation/filesystems/resctrl.rst.
>
> Signed-off-by: Babu Moger <babu.moger@amd.com>
> ---
> v7: Refactored rdtgroup_kmode_global_activate and rdtgroup_kmode_global_deactivate().
> Removed resctrl_kmode_switch().
> Refactored resctrl_kmode_parse_group().
> Handled the "group=" as the last parameter.
>
> v6: Use flattened resctrl_kmode and global_enable_per_cpu. Omitted
> parameters keep the values shown by reading the file. Drop the
> ctrl=inherit;mon=inherit no-op. Parse options with strsep(), as the
> other resctrl writers do, and split validation out of the write path.
> https://lore.kernel.org/lkml/3bc39dd7-b7b0-4203-a493-0bd872fdc644@intel.com/
>
> v5: Adapt to the resctrl_kcfg caps and active split. Accept
> assign_global_enable_per_cpu:ctrl=;mon=;group=<ctrl>/<mon>/ writes.
> Treat both ctrl=inherit and mon=inherit as a no-op. Use group=// for
> the default control group. Show associated kmode files through
> resctrl_hidden_files_set_visible().
> Added kmode check in rdtgroup_locksetup_enter(), rdtgroup_mode_write()
> and rdtgroup_rename().
> Simplify kernel-doc for write and activate helpers.
>
> v4: Validate input before tearing down the active association so failures
> retain the previous association. Allow assign_mon on CTRL_MON and MON
> groups; require a control group when control assignment is inherit.
>
> v3: New patch to make info/kernel_mode writable.
> ---
> Documentation/filesystems/resctrl.rst | 40 ++++
> fs/resctrl/rdtgroup.c | 274 +++++++++++++++++++++++++-
> 2 files changed, 313 insertions(+), 1 deletion(-)
>
> diff --git a/Documentation/filesystems/resctrl.rst b/Documentation/filesystems/resctrl.rst
> index e57361dd342e..1a1877222624 100644
> --- a/Documentation/filesystems/resctrl.rst
> +++ b/Documentation/filesystems/resctrl.rst
> @@ -608,6 +608,46 @@ The top level of the "info" directory contains the following file(s):
> [inherit_user]
> global_enable_per_cpu:ctrl=assign;mon=assign;group=//
>
> + Writes use the same line format as reads, without square brackets and
> + with a trailing newline. Errors are reported in "info/last_cmd_status".
> +
> + "inherit_user":
> + Written without parameters.
> +
> + "global_enable_per_cpu":
> + "ctrl=", "mon=", and "group=" are optional.
> +
> + An omitted "ctrl=", "mon=" and "group=" keeps the default values.
> +
> + If "mon=inherit", or monitoring is unsupported, "group=" must
> + reference a CTRL_MON group.
> +
> + The "ctrl=inherit" together with "mon=inherit" is rejected.
> +
> + A MON group requires "mon=assign".
> +
> + "group=" must be the last parameter. The group must be in shareable mode.
> +
> + Selecting a new kernel mode, parameter, or group replaces the active
> + mode and updates "kmode_cpus" to include all online CPUs.
> +
> + Empty values are rejected.
> +
> + Example::
> +
> + # mkdir ctrl1
> + # echo "global_enable_per_cpu:ctrl=assign;mon=assign;group=ctrl1//" \
> + > info/kernel_mode
> +
> + # cat info/kernel_mode
> + inherit_user
> + [global_enable_per_cpu:ctrl=assign;mon=assign;group=ctrl1//]
> +
> + # echo "inherit_user" > info/kernel_mode
> + # cat info/kernel_mode
> + [inherit_user]
> + global_enable_per_cpu:ctrl=assign;mon=assign;group=//
> +
> Resource alloc and monitor groups
> =================================
>
> diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
> index 97d99406de00..872755532fb4 100644
> --- a/fs/resctrl/rdtgroup.c
> +++ b/fs/resctrl/rdtgroup.c
> @@ -1201,6 +1201,277 @@ static void rdtgroup_kmode_global_deactivate(struct rdtgroup *rdtgrp)
> resctrl_kmode.mon = KMODE_ASSIGN;
> }
>
> +/* Program @rdtgrp on every online CPU and show its kmode_cpus files. */
> +static void rdtgroup_kmode_global_activate(struct rdtgroup *rdtgrp,
> + enum resctrl_kernel_mode mode,
> + enum kmode_state ctrl,
> + enum kmode_state mon)
> +{
> + resctrl_kmode.active = mode;
> + resctrl_kmode.ctrl = ctrl;
> + resctrl_kmode.mon = mon;
> + resctrl_kmode.rdtgrp = rdtgrp;
> +
> + cpumask_copy(&rdtgrp->kmode_cpu_mask, cpu_online_mask);
> + resctrl_configure_kmode_global(&rdtgrp->kmode_cpu_mask, rdtgrp, true);
> +}
> +
> +static int resctrl_kmode_parse_state(char *val, enum kmode_state *state)
> +{
> + if (!strcmp(val, "assign")) {
> + *state = KMODE_ASSIGN;
> + return 0;
> + }
> + if (!strcmp(val, "inherit")) {
> + *state = KMODE_INHERIT;
> + return 0;
> + }
> + return -EINVAL;
> +}
> +
> +/*
> + * group is "<CTRL_MON>/" or "<CTRL_MON>/<MON>/". The MON component is
> + * optional: mon=inherit and systems without monitoring do not require it.
> + * An empty name selects the default CTRL_MON group. Names are not trimmed;
> + * "/" cannot appear in a resource group name.
> + */
> +static int resctrl_kmode_parse_group(char *group, struct rdtgroup **rdtgrp)
> +{
> + struct rdtgroup *rdtg, *parent = &rdtgroup_default;
> + char *mon = NULL, *slash;
> + size_t len;
> +
> + len = strlen(group);
> + if (!len || group[len - 1] != '/') {
> + rdt_last_cmd_puts("Group must be <CTRL_MON>/ or <CTRL_MON>/<MON>/\n");
> + return -EINVAL;
> + }
> + group[len - 1] = '\0';
> +
> + slash = strchr(group, '/');
> + if (slash) {
> + *slash = '\0';
> + mon = slash + 1;
> + if (strchr(mon, '/')) {
> + rdt_last_cmd_puts("Group must be <CTRL_MON>/ or <CTRL_MON>/<MON>/\n");
> + return -EINVAL;
> + }
> + }
> +
> + if (group[0] != '\0') {
> + parent = NULL;
> + list_for_each_entry(rdtg, &rdt_all_groups, rdtgroup_list) {
> + if (!strcmp(rdt_kn_name(rdtg->kn), group)) {
> + parent = rdtg;
> + break;
> + }
> + }
> + }
> + if (!parent)
> + goto not_found;
> +
> + if (!mon || mon[0] == '\0') {
> + *rdtgrp = parent;
> + return 0;
> + }
> +
> + list_for_each_entry(rdtg, &parent->mon.crdtgrp_list, mon.crdtgrp_list) {
> + if (!strcmp(rdt_kn_name(rdtg->kn), mon)) {
> + *rdtgrp = rdtg;
> + return 0;
> + }
> + }
> +
> +not_found:
> + rdt_last_cmd_puts("Group not found\n");
> + return -EINVAL;
> +}
> +
> +static int resctrl_kmode_parse_parameters(char *params, enum kmode_state *ctrl,
> + enum kmode_state *mon,
> + struct rdtgroup **rdtgrp)
> +{
> + char *key, *tok;
> +
> + while ((tok = strsep(¶ms, ";"))) {
> + key = strsep(&tok, "=");
> + if (!tok) {
> + if (strim(key)[0] == '\0')
> + continue;
> + rdt_last_cmd_puts("Missing '=' in kernel mode parameter\n");
> + return -EINVAL;
> + }
> + key = strim(key);
> + if (key[0] == '\0') {
> + rdt_last_cmd_puts("Empty kernel mode parameters\n");
> + return -EINVAL;
> + }
> +
> + /*
> + * group= is the last parameter and may contain ';'.
> + * Restore it if stripped.
> + */
> + if (!strcmp(key, "group") && params)
> + params[-1] = ';';
> +
> + tok = strim(tok);
> + if (tok[0] == '\0') {
> + rdt_last_cmd_puts("Empty kernel mode parameters\n");
> + return -EINVAL;
> + }
> +
> + if (!strcmp(key, "group"))
> + return resctrl_kmode_parse_group(tok, rdtgrp);
Sashiko reported:
https://sashiko.dev/#/patchset/cover.1794437052.git.babu.moger%40amd.com?part=15
=====================================================================================
commit c63c65a55b0de1c92fbdb68970fd3628b6b0e821
Author: Babu Moger <babu.moger@amd.com>
fs/resctrl: Extend info/kernel_mode to configure the kernel mode
This commit adds write support to info/kernel_mode so user space can
configure and validate the active kernel mode and its backing resource
group.
> diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
> index 6f51db3cb283f..fd551dd527b9c 100644
> --- a/fs/resctrl/rdtgroup.c
> +++ b/fs/resctrl/rdtgroup.c
> @@ -1201,6 +1201,277 @@ static void
rdtgroup_kmode_global_deactivate(struct rdtgroup *rdtgrp)
[ ... ]
> +/*
> + * group is "<CTRL_MON>/" or "<CTRL_MON>/<MON>/". The MON component is
> + * optional: mon=inherit and systems without monitoring do not
require it.
> + * An empty name selects the default CTRL_MON group. Names are not
trimmed;
> + * "/" cannot appear in a resource group name.
> + */
> +static int resctrl_kmode_parse_group(char *group, struct rdtgroup
**rdtgrp)
[ ... ]
> +static int resctrl_kmode_parse_parameters(char *params, enum
kmode_state *ctrl,
> + enum kmode_state *mon,
> + struct rdtgroup **rdtgrp)
> +{
> + char *key, *tok;
> +
> + while ((tok = strsep(¶ms, ";"))) {
> + key = strsep(&tok, "=");
> + if (!tok) {
> + if (strim(key)[0] == '\0')
> + continue;
> + rdt_last_cmd_puts("Missing '=' in kernel mode parameter\n");
> + return -EINVAL;
> + }
> + key = strim(key);
> + if (key[0] == '\0') {
> + rdt_last_cmd_puts("Empty kernel mode parameters\n");
> + return -EINVAL;
> + }
> +
> + /*
> + * group= is the last parameter and may contain ';'.
> + * Restore it if stripped.
> + */
> + if (!strcmp(key, "group") && params)
> + params[-1] = ';';
> +
> + tok = strim(tok);
> + if (tok[0] == '\0') {
> + rdt_last_cmd_puts("Empty kernel mode parameters\n");
> + return -EINVAL;
> + }
> +
> + if (!strcmp(key, "group"))
> + return resctrl_kmode_parse_group(tok, rdtgrp);
Does calling strim(tok) before the "group" check strip leading
whitespace from the CTRL_MON group name? The comment on
resctrl_kmode_parse_group() notes that group names are not trimmed, and
trimming tok here causes lookup of a CTRL_MON group whose name begins
with whitespace to fail with -EINVAL ("Group not found").
========================================================================
Interesting.. reesctrl allows trailing/leading white spaces in the group
names.
So, we cannot run "strim(tok)" for the group names.
Will move the strim(tok) after the group check is done.
Thanks
Babu
next prev parent reply other threads:[~2026-11-16 20:10 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-11 22:43 [PATCH v7 00/19] x86,fs/resctrl: Add kernel-mode (e.g., PLZA) support to the resctrl subsystem Babu Moger
2026-11-11 22:43 ` [PATCH v7 01/19] x86/cpufeatures: Support Privilege Level Zero Association (PLZA) Babu Moger
2026-11-11 22:43 ` [PATCH v7 02/19] x86/resctrl: Add PLZA support to command-line options Babu Moger
2026-11-11 22:43 ` [PATCH v7 03/19] x86/resctrl: Add PLZA MSR definition and field layout Babu Moger
2026-11-11 22:43 ` [PATCH v7 04/19] fs/resctrl: Introduce kernel mode enum Babu Moger
2026-11-16 20:07 ` Babu Moger
2026-11-11 22:43 ` [PATCH v7 05/19] arm,x86,fs/resctrl: Introduce arch hook to program global per-CPU kernel mode Babu Moger
2026-11-11 22:43 ` [PATCH v7 06/19] fs/resctrl: Introduce data structures for kernel mode configuration Babu Moger
2026-11-11 22:44 ` [PATCH v7 07/19] fs/resctrl: Introduce resctrl_set_kmode_support() to register supported modes Babu Moger
2026-11-11 22:44 ` [PATCH v7 08/19] x86/resctrl: Register RESCTRL_GLOBAL_ENABLE_PER_CPU when PLZA is available Babu Moger
2026-11-11 22:44 ` [PATCH v7 09/19] fs/resctrl: Rearrange top-level files in info directory Babu Moger
2026-11-11 22:44 ` [PATCH v7 10/19] fs/resctrl: Add interface to display kernel mode status Babu Moger
2026-11-11 22:44 ` [PATCH v7 11/19] fs/resctrl: Add support for hidden resource group files Babu Moger
2026-11-11 22:44 ` [PATCH v7 12/19] fs/resctrl: Introduce kmode_cpus/kmode_cpus_list per rdtgroup Babu Moger
2026-11-11 22:44 ` [PATCH v7 13/19] x86,fs/resctrl: Add CPU hotplug support for kernel mode Babu Moger
2026-11-16 20:08 ` Babu Moger
2026-11-11 22:44 ` [PATCH v7 14/19] fs/resctrl: Deactivate kernel mode when the group is removed Babu Moger
2026-11-11 22:44 ` [PATCH v7 15/19] fs/resctrl: Extend info/kernel_mode to configure the kernel mode Babu Moger
2026-11-16 20:09 ` Babu Moger [this message]
2026-11-11 22:44 ` [PATCH v7 16/19] fs/resctrl: Reject mode changes for groups backing " Babu Moger
2026-11-11 22:44 ` [PATCH v7 17/19] fs/resctrl: Control visibility of global per-CPU kernel mode group files Babu Moger
2026-11-16 20:10 ` Babu Moger
2026-11-11 22:44 ` [PATCH v7 18/19] fs/resctrl: Allow userspace to write kmode_cpus/kmode_cpus_list Babu Moger
2026-11-11 22:44 ` [PATCH v7 19/19] fs/resctrl: Add kernel mode documentation and examples Babu Moger
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=3d008992-dab9-4353-a25e-0007926e19a4@amd.com \
--to=babu.moger@amd.com \
--cc=Dave.Martin@arm.com \
--cc=arnd@arndb.de \
--cc=ashish.kalra@amd.com \
--cc=ben.horgan@arm.com \
--cc=binbin.wu@linux.intel.com \
--cc=bp@alien8.de \
--cc=corbet@lwn.net \
--cc=dapeng1.mi@linux.intel.com \
--cc=darwi@linutronix.de \
--cc=dave.hansen@linux.intel.com \
--cc=elver@google.com \
--cc=enelsonmoore@gmail.com \
--cc=ewanhai-oc@zhaoxin.com \
--cc=fenghuay@nvidia.com \
--cc=fustini@kernel.org \
--cc=hpa@zytor.com \
--cc=james.morse@arm.com \
--cc=jlayton@kernel.org \
--cc=kim.phillips@amd.com \
--cc=kmehltretter@gmail.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=nikunj@amd.com \
--cc=peterz@infradead.org \
--cc=prathyushi.nangia@amd.com \
--cc=rdunlap@infradead.org \
--cc=reinette.chatre@intel.com \
--cc=ricardo.neri-calderon@linux.intel.com \
--cc=rppt@kernel.org \
--cc=seanjc@google.com \
--cc=skhan@linuxfoundation.org \
--cc=superm1@kernel.org \
--cc=tglx@kernel.org \
--cc=thomas.lendacky@amd.com \
--cc=tony.luck@intel.com \
--cc=x86@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®