[v2] x86/resctrl: Fix WARN in get_domain_from_cpu()

Message ID ZdZPht8hY4J9uIOz@agluck-desk3
State New
Headers
Series [v2] x86/resctrl: Fix WARN in get_domain_from_cpu() |

Commit Message

Luck, Tony Feb. 21, 2024, 7:31 p.m. UTC
  reset_all_ctrls() and resctrl_arch_update_domains() use on_each_cpu_mask()
to call rdt_ctrl_update() on potentially one CPU from each domain.

But this means rdt_ctrl_update() needs to figure out which domain to
apply changes to. Doing so requires a search of all domains in a resource,
which can only be done safely if cpus_lock is held. Both callers do hold
this lock, but there isn't a way for a function called on another CPU
via IPI to verify this.

Fix by adding the target domain to the msr_param structure and passing an
array with CDP_NUM_TYPES entries. Then calling for each domain separately
using smp_call_function_single()

Change the low level cat_wrmsr(), mba_wrmsr_intel(), and mba_wrmsr_amd()
functions to just take a msr_param structure since it contains the
rdt_resource and rdt_domain information.

Signed-off-by: Tony Luck <tony.luck@intel.com>

---

Changes since v1:

* Avoid double IPI to the same core when CDP is enabled.
* Don't pass the resource and domain to functions that can
  get these from the msr_param structure.
* Clean up some fir tree issues in functions that I changed.


 arch/x86/kernel/cpu/resctrl/internal.h    |  4 +-
 arch/x86/kernel/cpu/resctrl/core.c        | 56 +++++++++------------
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 59 +++++++----------------
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 23 ++++-----
 4 files changed, 50 insertions(+), 92 deletions(-)
  

Comments

Reinette Chatre Feb. 21, 2024, 10:59 p.m. UTC | #1
Hi Tony,

On 2/21/2024 11:31 AM, Tony Luck wrote:
> reset_all_ctrls() and resctrl_arch_update_domains() use on_each_cpu_mask()
> to call rdt_ctrl_update() on potentially one CPU from each domain.
> 
> But this means rdt_ctrl_update() needs to figure out which domain to
> apply changes to. Doing so requires a search of all domains in a resource,
> which can only be done safely if cpus_lock is held. Both callers do hold
> this lock, but there isn't a way for a function called on another CPU
> via IPI to verify this.
> 
> Fix by adding the target domain to the msr_param structure and passing an
> array with CDP_NUM_TYPES entries. Then calling for each domain separately
> using smp_call_function_single()

This work contains no changes to get_domain_from_cpu(). I expect the WARN
within it to be removed as intended with [1] and then this work can build
on that without urgency. As I understand, to support the stated goal of this
work, I expect get_domain_from_cpu() in the end to not have any WARN or
IS_ENABLED checks, but just a lockdep_assert_cpus_held(). 

Do you have different expectations?

> Change the low level cat_wrmsr(), mba_wrmsr_intel(), and mba_wrmsr_amd()
> functions to just take a msr_param structure since it contains the
> rdt_resource and rdt_domain information.

Could moving the rdt_domain into msr_param be done in a separate patch?

..

> diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
> index 7997b47743a2..09f6e624f1bb 100644
> --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
> +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
> @@ -272,22 +272,6 @@ static u32 get_config_index(u32 closid, enum resctrl_conf_type type)
>  	}
>  }
>  
> -static bool apply_config(struct rdt_hw_domain *hw_dom,
> -			 struct resctrl_staged_config *cfg, u32 idx,
> -			 cpumask_var_t cpu_mask)
> -{
> -	struct rdt_domain *dom = &hw_dom->d_resctrl;
> -
> -	if (cfg->new_ctrl != hw_dom->ctrl_val[idx]) {
> -		cpumask_set_cpu(cpumask_any(&dom->cpu_mask), cpu_mask);
> -		hw_dom->ctrl_val[idx] = cfg->new_ctrl;
> -
> -		return true;
> -	}
> -
> -	return false;
> -}
> -
>  int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
>  			    u32 closid, enum resctrl_conf_type t, u32 cfg_val)
>  {
> @@ -304,59 +288,50 @@ int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
>  	msr_param.res = r;
>  	msr_param.low = idx;
>  	msr_param.high = idx + 1;
> -	hw_res->msr_update(d, &msr_param, r);
> +	hw_res->msr_update(&msr_param);
>  

Is this missing setting the domain in msr_param?

>  	return 0;
>  }
>  
>  int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
>  {
> +	struct msr_param msr_param[CDP_NUM_TYPES];
>  	struct resctrl_staged_config *cfg;
>  	struct rdt_hw_domain *hw_dom;
> -	struct msr_param msr_param;
>  	enum resctrl_conf_type t;
> -	cpumask_var_t cpu_mask;
>  	struct rdt_domain *d;
> +	bool need_update;
> +	int cpu;
>  	u32 idx;
>  
>  	/* Walking r->domains, ensure it can't race with cpuhp */
>  	lockdep_assert_cpus_held();
>  
> -	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
> -		return -ENOMEM;
> -
> -	msr_param.res = NULL;
> +	memset(msr_param, 0, sizeof(msr_param));
>  	list_for_each_entry(d, &r->domains, list) {
>  		hw_dom = resctrl_to_arch_dom(d);
> +		need_update = false;
>  		for (t = 0; t < CDP_NUM_TYPES; t++) {
>  			cfg = &hw_dom->d_resctrl.staged_config[t];
>  			if (!cfg->have_new_ctrl)
>  				continue;
>  
>  			idx = get_config_index(closid, t);
> -			if (!apply_config(hw_dom, cfg, idx, cpu_mask))
> +			if (cfg->new_ctrl == hw_dom->ctrl_val[idx])
>  				continue;
> -
> -			if (!msr_param.res) {
> -				msr_param.low = idx;
> -				msr_param.high = msr_param.low + 1;
> -				msr_param.res = r;
> -			} else {
> -				msr_param.low = min(msr_param.low, idx);
> -				msr_param.high = max(msr_param.high, idx + 1);
> -			}
> +			hw_dom->ctrl_val[idx] = cfg->new_ctrl;
> +			cpu = cpumask_any(&d->cpu_mask);
> +
> +			msr_param[t].low = idx;
> +			msr_param[t].high = msr_param[t].low + 1;
> +			msr_param[t].res = r;
> +			msr_param[t].dom = d;
> +			need_update = true;
>  		}
> +		if (need_update)
> +			smp_call_function_single(cpu, rdt_ctrl_update, &msr_param, 1);

It is not clear to me why it is needed to pass this additional data. Why not
just use the original mechanism of letting the low and high of msr_param span the
multiple indices that need updating? There can still be a "need_update" but it
can be set when msr_param gets its first data. Any other index needing updating
can just update low/high and a single msr_param can be used.

Reinette

[1] https://lore.kernel.org/lkml/20240221122306.633273-1-james.morse@arm.com/
  
Luck, Tony Feb. 21, 2024, 11:56 p.m. UTC | #2
On Wed, Feb 21, 2024 at 02:59:43PM -0800, Reinette Chatre wrote:
> Hi Tony,
> 
> On 2/21/2024 11:31 AM, Tony Luck wrote:
> > reset_all_ctrls() and resctrl_arch_update_domains() use on_each_cpu_mask()
> > to call rdt_ctrl_update() on potentially one CPU from each domain.
> > 
> > But this means rdt_ctrl_update() needs to figure out which domain to
> > apply changes to. Doing so requires a search of all domains in a resource,
> > which can only be done safely if cpus_lock is held. Both callers do hold
> > this lock, but there isn't a way for a function called on another CPU
> > via IPI to verify this.
> > 
> > Fix by adding the target domain to the msr_param structure and passing an
> > array with CDP_NUM_TYPES entries. Then calling for each domain separately
> > using smp_call_function_single()
> 
> This work contains no changes to get_domain_from_cpu(). I expect the WARN
> within it to be removed as intended with [1] and then this work can build
> on that without urgency. As I understand, to support the stated goal of this
> work, I expect get_domain_from_cpu() in the end to not have any WARN or
> IS_ENABLED checks, but just a lockdep_assert_cpus_held(). 
> 
> Do you have different expectations?

Same expectations. Boris should apply the simple fix (delete the WARN
that is giving a false positive) for this current cycle.

If there is support for my patch (with changes/fixes you point out
below), then it could be added in the future and get_domain_from_cpu()
can use lockdep_assert_cpus_held().

> > Change the low level cat_wrmsr(), mba_wrmsr_intel(), and mba_wrmsr_amd()
> > functions to just take a msr_param structure since it contains the
> > rdt_resource and rdt_domain information.
> 
> Could moving the rdt_domain into msr_param be done in a separate patch?

I can break it into more pieces if there is enthusiam to apply it.

> ...
> 
> > diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
> > index 7997b47743a2..09f6e624f1bb 100644
> > --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
> > +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
> > @@ -272,22 +272,6 @@ static u32 get_config_index(u32 closid, enum resctrl_conf_type type)
> >  	}
> >  }
> >  
> > -static bool apply_config(struct rdt_hw_domain *hw_dom,
> > -			 struct resctrl_staged_config *cfg, u32 idx,
> > -			 cpumask_var_t cpu_mask)
> > -{
> > -	struct rdt_domain *dom = &hw_dom->d_resctrl;
> > -
> > -	if (cfg->new_ctrl != hw_dom->ctrl_val[idx]) {
> > -		cpumask_set_cpu(cpumask_any(&dom->cpu_mask), cpu_mask);
> > -		hw_dom->ctrl_val[idx] = cfg->new_ctrl;
> > -
> > -		return true;
> > -	}
> > -
> > -	return false;
> > -}
> > -
> >  int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
> >  			    u32 closid, enum resctrl_conf_type t, u32 cfg_val)
> >  {
> > @@ -304,59 +288,50 @@ int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
> >  	msr_param.res = r;
> >  	msr_param.low = idx;
> >  	msr_param.high = idx + 1;
> > -	hw_res->msr_update(d, &msr_param, r);
> > +	hw_res->msr_update(&msr_param);
> >  
> 
> Is this missing setting the domain in msr_param?

Indeed yes.

> >  	return 0;
> >  }
> >  
> >  int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
> >  {
> > +	struct msr_param msr_param[CDP_NUM_TYPES];
> >  	struct resctrl_staged_config *cfg;
> >  	struct rdt_hw_domain *hw_dom;
> > -	struct msr_param msr_param;
> >  	enum resctrl_conf_type t;
> > -	cpumask_var_t cpu_mask;
> >  	struct rdt_domain *d;
> > +	bool need_update;
> > +	int cpu;
> >  	u32 idx;
> >  
> >  	/* Walking r->domains, ensure it can't race with cpuhp */
> >  	lockdep_assert_cpus_held();
> >  
> > -	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
> > -		return -ENOMEM;
> > -
> > -	msr_param.res = NULL;
> > +	memset(msr_param, 0, sizeof(msr_param));
> >  	list_for_each_entry(d, &r->domains, list) {
> >  		hw_dom = resctrl_to_arch_dom(d);
> > +		need_update = false;
> >  		for (t = 0; t < CDP_NUM_TYPES; t++) {
> >  			cfg = &hw_dom->d_resctrl.staged_config[t];
> >  			if (!cfg->have_new_ctrl)
> >  				continue;
> >  
> >  			idx = get_config_index(closid, t);
> > -			if (!apply_config(hw_dom, cfg, idx, cpu_mask))
> > +			if (cfg->new_ctrl == hw_dom->ctrl_val[idx])
> >  				continue;
> > -
> > -			if (!msr_param.res) {
> > -				msr_param.low = idx;
> > -				msr_param.high = msr_param.low + 1;
> > -				msr_param.res = r;
> > -			} else {
> > -				msr_param.low = min(msr_param.low, idx);
> > -				msr_param.high = max(msr_param.high, idx + 1);
> > -			}
> > +			hw_dom->ctrl_val[idx] = cfg->new_ctrl;
> > +			cpu = cpumask_any(&d->cpu_mask);
> > +
> > +			msr_param[t].low = idx;
> > +			msr_param[t].high = msr_param[t].low + 1;
> > +			msr_param[t].res = r;
> > +			msr_param[t].dom = d;
> > +			need_update = true;
> >  		}
> > +		if (need_update)
> > +			smp_call_function_single(cpu, rdt_ctrl_update, &msr_param, 1);
> 
> It is not clear to me why it is needed to pass this additional data. Why not
> just use the original mechanism of letting the low and high of msr_param span the
> multiple indices that need updating? There can still be a "need_update" but it
> can be set when msr_param gets its first data. Any other index needing updating
> can just update low/high and a single msr_param can be used.

For some reason this morning I thought that the domain needed to be
different. It isn't, so keeping the code that just adjusts the range
of MSRs will work just fine.

The "need_update" variable isn't required. I will move the
	msr_param.res = NULL;
inside the for each domain loop, and can use non-NULL value to
decide whether to IPI a CPU.

-Tony
  
Reinette Chatre Feb. 22, 2024, 11:18 p.m. UTC | #3
Hi Tony,

Is sending new versions of patch series in response to the previous
versions a new custom? I am finding the SNC thread [1] to have become
a maze and now this thread is headed in the same direction. My understanding
of custom (supported by [2]) is to send new versions as a new thread. 
This thread even complicates it more by mixing versions of different
features in the same email thread.

Reinette

[1] https://lore.kernel.org/lkml/20230713163207.219710-1-tony.luck@intel.com/
[2] https://www.kernel.org/doc/html/latest/process/submitting-patches.html#explicit-in-reply-to-headers
  
Luck, Tony Feb. 22, 2024, 11:26 p.m. UTC | #4
> Is sending new versions of patch series in response to the previous
> versions a new custom? I am finding the SNC thread [1] to have become
> a maze and now this thread is headed in the same direction. My understanding
> of custom (supported by [2]) is to send new versions as a new thread. 
> This thread even complicates it more by mixing versions of different
> features in the same email thread.

Reinette,

Not new for me. I've always (tried) to link everything together.

But thanks for this link:

[2] https://www.kernel.org/doc/html/latest/process/submitting-patches.html#explicit-in-reply-to-headers

I see that this isn't desired. I'll switch over to adding a Link: URL in the cover
letter going forward.[1]

-Tony

[1] I'm going to need a v4 if only to s/Simply/Simplify/ in the subject of part 2 :-(
  

Patch

diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index c99f26ebe7a6..2f21358b9621 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -383,6 +383,7 @@  static inline struct rdt_hw_domain *resctrl_to_arch_dom(struct rdt_domain *r)
  */
 struct msr_param {
 	struct rdt_resource	*res;
+	struct rdt_domain	*dom;
 	u32			low;
 	u32			high;
 };
@@ -442,8 +443,7 @@  struct rdt_hw_resource {
 	struct rdt_resource	r_resctrl;
 	u32			num_closid;
 	unsigned int		msr_base;
-	void (*msr_update)	(struct rdt_domain *d, struct msr_param *m,
-				 struct rdt_resource *r);
+	void			(*msr_update)(struct msr_param *m);
 	unsigned int		mon_scale;
 	unsigned int		mbm_width;
 	unsigned int		mbm_cfg_mask;
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 8a4ef4f5bddc..643bf64bf1be 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -56,14 +56,9 @@  int max_name_width, max_data_width;
  */
 bool rdt_alloc_capable;
 
-static void
-mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m,
-		struct rdt_resource *r);
-static void
-cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);
-static void
-mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m,
-	      struct rdt_resource *r);
+static void mba_wrmsr_intel(struct msr_param *m);
+static void cat_wrmsr(struct msr_param *m);
+static void mba_wrmsr_amd(struct msr_param *m);
 
 #define domain_init(id) LIST_HEAD_INIT(rdt_resources_all[id].r_resctrl.domains)
 
@@ -309,12 +304,11 @@  static void rdt_get_cdp_l2_config(void)
 	rdt_get_cdp_config(RDT_RESOURCE_L2);
 }
 
-static void
-mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+static void mba_wrmsr_amd(struct msr_param *m)
 {
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
+	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom);
 	unsigned int i;
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 
 	for (i = m->low; i < m->high; i++)
 		wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
@@ -334,25 +328,22 @@  static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
 	return r->default_ctrl;
 }
 
-static void
-mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m,
-		struct rdt_resource *r)
+static void mba_wrmsr_intel(struct msr_param *m)
 {
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
+	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom);
 	unsigned int i;
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 
 	/*  Write the delay values for mba. */
 	for (i = m->low; i < m->high; i++)
-		wrmsrl(hw_res->msr_base + i, delay_bw_map(hw_dom->ctrl_val[i], r));
+		wrmsrl(hw_res->msr_base + i, delay_bw_map(hw_dom->ctrl_val[i], m->res));
 }
 
-static void
-cat_wrmsr(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
+static void cat_wrmsr(struct msr_param *m)
 {
+	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
+	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(m->dom);
 	unsigned int i;
-	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
 
 	for (i = m->low; i < m->high; i++)
 		wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
@@ -387,19 +378,14 @@  u32 resctrl_arch_get_num_closid(struct rdt_resource *r)
 
 void rdt_ctrl_update(void *arg)
 {
+	struct rdt_hw_resource *hw_res;
 	struct msr_param *m = arg;
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(m->res);
-	struct rdt_resource *r = m->res;
-	int cpu = smp_processor_id();
-	struct rdt_domain *d;
+	int t;
 
-	d = get_domain_from_cpu(cpu, r);
-	if (d) {
-		hw_res->msr_update(d, m, r);
-		return;
-	}
-	pr_warn_once("cpu %d not found in any domain for resource %s\n",
-		     cpu, r->name);
+	hw_res = resctrl_to_arch_res(m->res);
+	for (t = 0; t < CDP_NUM_TYPES; t++)
+		if (m[t].dom)
+			hw_res->msr_update(m + t);
 }
 
 /*
@@ -472,9 +458,11 @@  static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
 	hw_dom->ctrl_val = dc;
 	setup_default_ctrlval(r, dc);
 
+	m.res = r;
+	m.dom = d;
 	m.low = 0;
 	m.high = hw_res->num_closid;
-	hw_res->msr_update(d, &m, r);
+	hw_res->msr_update(&m);
 	return 0;
 }
 
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 7997b47743a2..09f6e624f1bb 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -272,22 +272,6 @@  static u32 get_config_index(u32 closid, enum resctrl_conf_type type)
 	}
 }
 
-static bool apply_config(struct rdt_hw_domain *hw_dom,
-			 struct resctrl_staged_config *cfg, u32 idx,
-			 cpumask_var_t cpu_mask)
-{
-	struct rdt_domain *dom = &hw_dom->d_resctrl;
-
-	if (cfg->new_ctrl != hw_dom->ctrl_val[idx]) {
-		cpumask_set_cpu(cpumask_any(&dom->cpu_mask), cpu_mask);
-		hw_dom->ctrl_val[idx] = cfg->new_ctrl;
-
-		return true;
-	}
-
-	return false;
-}
-
 int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
 			    u32 closid, enum resctrl_conf_type t, u32 cfg_val)
 {
@@ -304,59 +288,50 @@  int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
 	msr_param.res = r;
 	msr_param.low = idx;
 	msr_param.high = idx + 1;
-	hw_res->msr_update(d, &msr_param, r);
+	hw_res->msr_update(&msr_param);
 
 	return 0;
 }
 
 int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
 {
+	struct msr_param msr_param[CDP_NUM_TYPES];
 	struct resctrl_staged_config *cfg;
 	struct rdt_hw_domain *hw_dom;
-	struct msr_param msr_param;
 	enum resctrl_conf_type t;
-	cpumask_var_t cpu_mask;
 	struct rdt_domain *d;
+	bool need_update;
+	int cpu;
 	u32 idx;
 
 	/* Walking r->domains, ensure it can't race with cpuhp */
 	lockdep_assert_cpus_held();
 
-	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
-		return -ENOMEM;
-
-	msr_param.res = NULL;
+	memset(msr_param, 0, sizeof(msr_param));
 	list_for_each_entry(d, &r->domains, list) {
 		hw_dom = resctrl_to_arch_dom(d);
+		need_update = false;
 		for (t = 0; t < CDP_NUM_TYPES; t++) {
 			cfg = &hw_dom->d_resctrl.staged_config[t];
 			if (!cfg->have_new_ctrl)
 				continue;
 
 			idx = get_config_index(closid, t);
-			if (!apply_config(hw_dom, cfg, idx, cpu_mask))
+			if (cfg->new_ctrl == hw_dom->ctrl_val[idx])
 				continue;
-
-			if (!msr_param.res) {
-				msr_param.low = idx;
-				msr_param.high = msr_param.low + 1;
-				msr_param.res = r;
-			} else {
-				msr_param.low = min(msr_param.low, idx);
-				msr_param.high = max(msr_param.high, idx + 1);
-			}
+			hw_dom->ctrl_val[idx] = cfg->new_ctrl;
+			cpu = cpumask_any(&d->cpu_mask);
+
+			msr_param[t].low = idx;
+			msr_param[t].high = msr_param[t].low + 1;
+			msr_param[t].res = r;
+			msr_param[t].dom = d;
+			need_update = true;
 		}
+		if (need_update)
+			smp_call_function_single(cpu, rdt_ctrl_update, &msr_param, 1);
 	}
 
-	if (cpumask_empty(cpu_mask))
-		goto done;
-
-	/* Update resource control msr on all the CPUs. */
-	on_each_cpu_mask(cpu_mask, rdt_ctrl_update, &msr_param, 1);
-
-done:
-	free_cpumask_var(cpu_mask);
-
 	return 0;
 }
 
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 011e17efb1a6..5d9ff8883c60 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2811,21 +2811,19 @@  static int rdt_init_fs_context(struct fs_context *fc)
 static int reset_all_ctrls(struct rdt_resource *r)
 {
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
+	struct msr_param msr_param[CDP_NUM_TYPES];
 	struct rdt_hw_domain *hw_dom;
-	struct msr_param msr_param;
-	cpumask_var_t cpu_mask;
 	struct rdt_domain *d;
+	int cpu;
 	int i;
 
 	/* Walking r->domains, ensure it can't race with cpuhp */
 	lockdep_assert_cpus_held();
 
-	if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
-		return -ENOMEM;
-
-	msr_param.res = r;
-	msr_param.low = 0;
-	msr_param.high = hw_res->num_closid;
+	memset(msr_param, 0, sizeof(msr_param));
+	msr_param[0].res = r;
+	msr_param[0].low = 0;
+	msr_param[0].high = hw_res->num_closid;
 
 	/*
 	 * Disable resource control for this resource by setting all
@@ -2834,17 +2832,14 @@  static int reset_all_ctrls(struct rdt_resource *r)
 	 */
 	list_for_each_entry(d, &r->domains, list) {
 		hw_dom = resctrl_to_arch_dom(d);
-		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
+		cpu = cpumask_any(&d->cpu_mask);
 
 		for (i = 0; i < hw_res->num_closid; i++)
 			hw_dom->ctrl_val[i] = r->default_ctrl;
+		msr_param[0].dom = d;
+		smp_call_function_single(cpu, rdt_ctrl_update, &msr_param, 1);
 	}
 
-	/* Update CBM on all the CPUs in cpu_mask */
-	on_each_cpu_mask(cpu_mask, rdt_ctrl_update, &msr_param, 1);
-
-	free_cpumask_var(cpu_mask);
-
 	return 0;
 }