[PATCH 03/23] resctrl: Expose MBA resource_schemata mode sysfs

Ben Horgan ben.horgan at arm.com
Mon Jul 20 08:02:24 PDT 2026


Hi Fenghua,

On 7/17/26 09:54, Ben Horgan wrote:
> Hi Fenghua,
> 
> On 7/16/26 22:02, Fenghua Yu wrote:
>> Node-scoped MBA on MPAM needs a way to distinguish native memory-side
>> controls from legacy L3-shaped MB emulation. Track the selected emulate
>> mode on rdt_resource and expose it as
>> info/<resource>/resource_schemata/mode ("native" or "legacy") when the
>> architecture enables emulation.
> 
> This doesn't sound right.
> 
> If the MPAM mbwu counters are counting traffic on the egress of the L3 they should be described in
> the acpi tables as such, if they are not then they shouldn't. If they are the MB resource can then
> be scoped to the L3.
> 
> If the MPAM mbwu counters are at the memory bandwidth controller then they should be described in
> the acpi tables as such. Currently there is no support for such counters except when there is a
> single L3 and a single NUMA node and so a single link between the caches and the memory. Counting at
> either end of the link, egress of the L3 or entry to the memory gives the same counts and so the
> driver performs some unfortunate gymnastics to use L3 scope in this case. Do you see a reason not to
> do this? If we change the scope to be NUMA node in these platforms all I see changing is the domain
> id for the sole MB domain.
> 
> As such, can't we just add support for a NUMA scope memory bandwidth allocation resource, MB_NODE,
> without having a legacy/native switch?

There is some further discussion here on when emulation is required in resctrl. [1] No firm
conclusion as of yet.

[1] https://lore.kernel.org/lkml/8fd6caed-820f-457a-a1ef-a0a006fa52aa@intel.com/

Thanks,

Ben

> 
> Thanks,
> 
> Ben
> 
>>
>> The mode file is only created when rdt_resource::mode is non-zero
>> (RESCTRL_CTRL_LEGACY or RESCTRL_CTRL_NATIVE). It defaults to
>> RESCTRL_CTRL_MODE_NONE, so resources whose architecture does not support
>> control emulation get no mode file and are unaffected. Architecture
>> backends that support emulation set the initial mode when they create
>> their controls; on MPAM this is wired up together with the node-scoped
>> MB_NODE control in a later patch, so this commit only adds the (dormant)
>> generic mechanism.
>>
>> The mode file is added read-only here: switching the mode at runtime
>> requires rebuilding the resource_schemata layout to match the new mode,
>> so the writable interface is added together with that rebuild logic in a
>> later patch. Keeping the file read-only until then avoids exposing a
>> writable-but-no-op interface.
>>
>> Store rdt_resource_final in the resource_schemata directory priv so the
>> mode file can resolve the backing resource without dereferencing NULL.
>>
>> Signed-off-by: Fenghua Yu <fenghuay at nvidia.com>
>> ---
>>  fs/resctrl/rdtgroup.c   | 77 ++++++++++++++++++++++++++++++++++++++++-
>>  include/linux/resctrl.h | 17 +++++++++
>>  2 files changed, 93 insertions(+), 1 deletion(-)
>>
>> diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
>> index 2abb7fda6091..6b1f24c6a1f2 100644
>> --- a/fs/resctrl/rdtgroup.c
>> +++ b/fs/resctrl/rdtgroup.c
>> @@ -2696,6 +2696,74 @@ static unsigned long fflags_from_resource(struct rdt_resource *r)
>>  	return WARN_ON_ONCE(1);
>>  }
>>  
>> +static int resctrl_ctrl_mb_mode_show(struct kernfs_open_file *of,
>> +				     struct seq_file *seq, void *v)
>> +{
>> +	struct rdt_resource_final *f = rdt_kn_parent_priv(of->kn);
>> +	struct rdt_resource *r = f->res;
>> +
>> +	guard(mutex)(&rdtgroup_mutex);
>> +
>> +	switch (r->mode) {
>> +	case RESCTRL_CTRL_LEGACY:
>> +		seq_puts(seq, "[legacy] native\n");
>> +		break;
>> +	case RESCTRL_CTRL_NATIVE:
>> +		seq_puts(seq, "legacy [native]\n");
>> +		break;
>> +	default:
>> +		WARN_ONCE(1, "%s: unexpected MB control mode %d\n",
>> +			  f->name, r->mode);
>> +		seq_puts(seq, "legacy native\n");
>> +		break;
>> +	}
>> +
>> +	return 0;
>> +}
>> +
>> +static struct rftype resctrl_ctrl_mb_files[] = {
>> +	{
>> +		.name		= "mode",
>> +		.mode		= 0444,
>> +		.kf_ops		= &rdtgroup_kf_single_ops,
>> +		.seq_show	= resctrl_ctrl_mb_mode_show,
>> +		/*
>> +		 * Directory-level file, not per-control: fflags is only a
>> +		 * presence flag here, not the BIT(ctrl->type) type filter used
>> +		 * by resctrl_add_ctrl_files().
>> +		 */
>> +		.fflags		= 1,
>> +	}
>> +};
>> +
>> +static int resctrl_ctrl_add_files(struct kernfs_node *kn)
>> +{
>> +	struct rftype *rfts, *rft;
>> +	int ret, len;
>> +
>> +	rfts = resctrl_ctrl_mb_files;
>> +	len = ARRAY_SIZE(resctrl_ctrl_mb_files);
>> +
>> +	lockdep_assert_held(&rdtgroup_mutex);
>> +
>> +	for (rft = rfts; rft < rfts + len; rft++) {
>> +		if (rft->fflags) {
>> +			ret = rdtgroup_add_file(kn, rft);
>> +			if (ret)
>> +				goto error;
>> +		}
>> +	}
>> +
>> +	return 0;
>> +error:
>> +	pr_warn("Failed to add %s, err=%d\n", rft->name, ret);
>> +	while (--rft >= rfts) {
>> +		if (rft->fflags)
>> +			kernfs_remove_by_name(kn, rft->name);
>> +	}
>> +	return ret;
>> +}
>> +
>>  /*
>>   * No need to cleanup on exit - caller calls the recursive kernfs_remove()
>>   * on failure.
>> @@ -2704,11 +2772,12 @@ static int resctrl_mkdir_schemata_dir(struct kernfs_node *kn,
>>  				      struct rdt_resource_final *f)
>>  {
>>  	struct kernfs_node *kn_subdir, *kn_ctrl;
>> +	struct rdt_resource *r = f->res;
>>  	struct resctrl_ctrl *ctrl;
>>  	char ctrl_full_name[20];
>>  	int ret;
>>  
>> -	kn_subdir = kernfs_create_dir(kn, "resource_schemata", kn->mode, NULL);
>> +	kn_subdir = kernfs_create_dir(kn, "resource_schemata", kn->mode, f);
>>  	if (IS_ERR(kn_subdir))
>>  		return PTR_ERR(kn_subdir);
>>  
>> @@ -2716,6 +2785,12 @@ static int resctrl_mkdir_schemata_dir(struct kernfs_node *kn,
>>  	if (ret)
>>  		return ret;
>>  
>> +	if (r->mode) {
>> +		ret = resctrl_ctrl_add_files(kn_subdir);
>> +		if (ret)
>> +			return ret;
>> +	}
>> +
>>  	for_each_resource_ctrl(ctrl, f->res) {
>>  		ret = snprintf(ctrl_full_name, sizeof(ctrl_full_name), "%s%s%s",
>>  			       f->name, resctrl_ctrl_is_default(ctrl) ? "" : "_",
>> diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
>> index 72fb7256270e..4fc41e269d0b 100644
>> --- a/include/linux/resctrl.h
>> +++ b/include/linux/resctrl.h
>> @@ -257,6 +257,16 @@ enum resctrl_ctrl_unit {
>>  	RESCTRL_CTRL_UNIT_GBPS,
>>  };
>>  
>> +enum resctrl_ctrl_mode {
>> +	/*
>> +	 * Default (zero) value: the resource does not support control
>> +	 * emulation, so no resource_schemata/mode file is created for it.
>> +	 */
>> +	RESCTRL_CTRL_MODE_NONE = 0,
>> +	RESCTRL_CTRL_LEGACY,
>> +	RESCTRL_CTRL_NATIVE,
>> +};
>> +
>>  /**
>>   * struct resctrl_membw - Memory bandwidth allocation related data
>>   * @min_bw:		Minimum memory bandwidth percentage user can request
>> @@ -399,6 +409,12 @@ struct resctrl_ctrl {
>>   *			different memory bandwidths
>>   * @cache_io_alloc_capable:True if portion of the cache can be configured
>>   *			   for I/O traffic.
>> + * @mode:		Control emulation mode for this resource.
>> + *			RESCTRL_CTRL_MODE_NONE if the resource does not support
>> + *			emulation. "legacy": keep the legacy MB control,
>> + *			emulating it with a native control when it has no MBW
>> + *			hardware of its own. "native": expose native controls
>> + *			directly with no emulation.
>>   * @controls:		List of controls of an alloc_capable resource
>>   */
>>  struct rdt_resource {
>> @@ -413,6 +429,7 @@ struct rdt_resource {
>>  	bool				bw_delay_linear;
>>  	enum membw_throttle_mode	bw_throttle_mode;
>>  	bool				cache_io_alloc_capable;
>> +	enum resctrl_ctrl_mode		mode;
>>  	struct list_head		controls;
>>  };
>>  
> 
> 




More information about the linux-arm-kernel mailing list