Re: [PATCH v14 05/32] x86,fs/resctrl: Prepare for more monitor events

[Reinette Chatre]

Hi Babu/Tony,

On 6/13/25 2:04 PM, Babu Moger wrote:
> From: Tony Luck <tony.luck@xxxxxxxxx>

...

> @@ -400,25 +400,27 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_ctrl_domain *
>   */
>  static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_mon_domain *hw_dom)
>  {
> -	size_t tsize;
> -
> -	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) {
> -		tsize = sizeof(*hw_dom->arch_mbm_total);
> -		hw_dom->arch_mbm_total = kcalloc(num_rmid, tsize, GFP_KERNEL);
> -		if (!hw_dom->arch_mbm_total)
> -			return -ENOMEM;
> -	}
> -	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) {
> -		tsize = sizeof(*hw_dom->arch_mbm_local);
> -		hw_dom->arch_mbm_local = kcalloc(num_rmid, tsize, GFP_KERNEL);
> -		if (!hw_dom->arch_mbm_local) {
> -			kfree(hw_dom->arch_mbm_total);
> -			hw_dom->arch_mbm_total = NULL;
> -			return -ENOMEM;
> -		}
> +	size_t tsize = sizeof(*hw_dom->arch_mbm_states[0]);
> +	enum resctrl_event_id eventid;
> +	int idx;
> +
> +	for_each_mbm_event_id(eventid) {
> +		if (!resctrl_is_mon_event_enabled(eventid))
> +			continue;
> +		idx = MBM_STATE_IDX(eventid);
> +		hw_dom->arch_mbm_states[idx] = kcalloc(num_rmid, tsize, GFP_KERNEL);
> +		if (!hw_dom->arch_mbm_states[idx])
> +			goto cleanup;
>  	}
>  
>  	return 0;
> +cleanup:
> +	while (--idx >= 0) {

(please see note about this pattern below)

> +		kfree(hw_dom->arch_mbm_states[idx]);
> +		hw_dom->arch_mbm_states[idx] = NULL;
> +	}
> +
> +	return -ENOMEM;
>  }
>  
>  static int get_domain_id_from_scope(int cpu, enum resctrl_scope scope)
> diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
> index 5e3c41b36437..44ef0d94131e 100644
> --- a/arch/x86/kernel/cpu/resctrl/internal.h
> +++ b/arch/x86/kernel/cpu/resctrl/internal.h
> @@ -54,15 +54,16 @@ struct rdt_hw_ctrl_domain {
>   * struct rdt_hw_mon_domain - Arch private attributes of a set of CPUs that share
>   *			      a resource for a monitor function
>   * @d_resctrl:	Properties exposed to the resctrl file system
> - * @arch_mbm_total:	arch private state for MBM total bandwidth
> - * @arch_mbm_local:	arch private state for MBM local bandwidth
> + * @arch_mbm_states:	arch private state for each MBM event

Duplicate @arch_mbm_states

> + * @arch_mbm_states:	Per-event pointer to the MBM event's saved state.
> + *			An MBM event's state is an array of struct arch_mbm_state
> + *			indexed by RMID on x86 or combined CLOSID, RMID on Arm.

The "or combined CLOSID, RMID on Arm" can be dropped from the x86 arch specific
docs.

>   *
>   * Members of this structure are accessed via helpers that provide abstraction.
>   */
>  struct rdt_hw_mon_domain {
>  	struct rdt_mon_domain		d_resctrl;
> -	struct arch_mbm_state		*arch_mbm_total;
> -	struct arch_mbm_state		*arch_mbm_local;
> +	struct arch_mbm_state		*arch_mbm_states[QOS_NUM_L3_MBM_EVENTS];
>  };
>  
>  static inline struct rdt_hw_ctrl_domain *resctrl_to_arch_ctrl_dom(struct rdt_ctrl_domain *r)
> diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
> index 07f8ab097cbe..0add57b29a4d 100644
> --- a/arch/x86/kernel/cpu/resctrl/monitor.c
> +++ b/arch/x86/kernel/cpu/resctrl/monitor.c
> @@ -161,18 +161,14 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_mon_domain *hw_do
>  						 u32 rmid,
>  						 enum resctrl_event_id eventid)
>  {
> -	switch (eventid) {
> -	case QOS_L3_OCCUP_EVENT_ID:
> -		return NULL;
> -	case QOS_L3_MBM_TOTAL_EVENT_ID:
> -		return &hw_dom->arch_mbm_total[rmid];
> -	case QOS_L3_MBM_LOCAL_EVENT_ID:
> -		return &hw_dom->arch_mbm_local[rmid];
> -	default:
> -		/* Never expect to get here */
> -		WARN_ON_ONCE(1);
> +	struct arch_mbm_state *state;
> +
> +	if (!resctrl_is_mbm_event(eventid))
>  		return NULL;
> -	}
> +
> +	state = hw_dom->arch_mbm_states[MBM_STATE_IDX(eventid)];
> +
> +	return state ? &state[rmid] : NULL;
>  }
>  
>  void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
> @@ -201,14 +197,16 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
>  void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d)
>  {
>  	struct rdt_hw_mon_domain *hw_dom = resctrl_to_arch_mon_dom(d);
> -
> -	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID))
> -		memset(hw_dom->arch_mbm_total, 0,
> -		       sizeof(*hw_dom->arch_mbm_total) * r->num_rmid);
> -
> -	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID))
> -		memset(hw_dom->arch_mbm_local, 0,
> -		       sizeof(*hw_dom->arch_mbm_local) * r->num_rmid);
> +	enum resctrl_event_id eventid;
> +	int idx;
> +
> +	for_each_mbm_event_id(eventid) {
> +		if (!resctrl_is_mon_event_enabled(eventid))
> +			continue;
> +		idx = MBM_STATE_IDX(eventid);
> +		memset(hw_dom->arch_mbm_states[idx], 0,
> +		       sizeof(struct arch_mbm_state) * r->num_rmid);

sizeof(struct arch_mbm_state) -> sizeof(*hw_dom->arch_mbm_states[0])?

> +	}
>  }
>  
>  static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)


...

>  void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d)
> @@ -4085,32 +4081,34 @@ void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d
>  static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain *d)
>  {
>  	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
> -	size_t tsize;
> +	size_t tsize = sizeof(*d->mbm_states[0]);
> +	enum resctrl_event_id eventid;
> +	int idx;
>  
>  	if (resctrl_is_mon_event_enabled(QOS_L3_OCCUP_EVENT_ID)) {
>  		d->rmid_busy_llc = bitmap_zalloc(idx_limit, GFP_KERNEL);
>  		if (!d->rmid_busy_llc)
>  			return -ENOMEM;
>  	}
> -	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) {
> -		tsize = sizeof(*d->mbm_total);
> -		d->mbm_total = kcalloc(idx_limit, tsize, GFP_KERNEL);
> -		if (!d->mbm_total) {
> -			bitmap_free(d->rmid_busy_llc);
> -			return -ENOMEM;
> -		}
> -	}
> -	if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) {
> -		tsize = sizeof(*d->mbm_local);
> -		d->mbm_local = kcalloc(idx_limit, tsize, GFP_KERNEL);
> -		if (!d->mbm_local) {
> -			bitmap_free(d->rmid_busy_llc);
> -			kfree(d->mbm_total);
> -			return -ENOMEM;
> -		}
> +
> +	for_each_mbm_event_id(eventid) {
> +		if (!resctrl_is_mon_event_enabled(eventid))
> +			continue;
> +		idx = MBM_STATE_IDX(eventid);
> +		d->mbm_states[idx] = kcalloc(idx_limit, tsize, GFP_KERNEL);
> +		if (!d->mbm_states[idx])
> +			goto cleanup;
>  	}

Looks like this cleanup pattern is a landmine that this
series stepped on in patch #13. Any code added here that fails
and then run the "cleanup" code will either end up with a memory
leak or accessing an uninitialized variable. 
>  
>  	return 0;
> +cleanup:
> +	bitmap_free(d->rmid_busy_llc);
> +	while (--idx >= 0) {
> +		kfree(d->mbm_states[idx]);
> +		d->mbm_states[idx] = NULL;
> +	}

This pattern should be made safer by not relying on idx, or
ensure here that idx is initialized correctly.

> +
> +	return -ENOMEM;
>  }
>  

Reinette