Re: [PATCH v7 11/24] x86/resctrl: Move CLOSID/RMID matching and setting to use helpers

[Moger, Babu]

Hi James,

On 10/25/23 13:03, James Morse wrote:
> When switching tasks, the CLOSID and RMID that the new task should
> use are stored in struct task_struct. For x86 the CLOSID known by resctrl,
> the value in task_struct, and the value written to the CPU register are
> all the same thing.
> 
> MPAM's CPU interface has two different PARTID's one for data accesses
> the other for instruction fetch. Storing resctrl's CLOSID value in
> struct task_struct implies the arch code knows whether resctrl is using
> CDP.
> 
> Move the matching and setting of the struct task_struct properties
> to use helpers. This allows arm64 to store the hardware format of
> the register, instead of having to convert it each time.
> 
> __rdtgroup_move_task()s use of READ_ONCE()/WRITE_ONCE() ensures torn
> values aren't seen as another CPU may schedule the task being moved
> while the value is being changed. MPAM has an additional corner-case
> here as the PMG bits extend the PARTID space. If the scheduler sees a
> new-CLOSID but old-RMID, the task will dirty an RMID that the limbo code
> is not watching causing an inaccurate count. x86's RMID are independent
> values, so the limbo code will still be watching the old-RMID in this
> circumstance.
> To avoid this, arm64 needs both the CLOSID/RMID WRITE_ONCE()d together.
> Both values must be provided together.
> 
> Because MPAM's RMID values are not unique, the CLOSID must be provided
> when matching the RMID.
> 
> Tested-by: Shaopeng Tan <tan.shaopeng@xxxxxxxxxxx>
> Tested-by: Peter Newman <peternewman@xxxxxxxxxx>
> Reviewed-by: Shaopeng Tan <tan.shaopeng@xxxxxxxxxxx>
> Reviewed-by: Reinette Chatre <reinette.chatre@xxxxxxxxx>
> Signed-off-by: James Morse <james.morse@xxxxxxx>

Reviewed-by: Babu Moger <babu.moger@xxxxxxx>

> ---
> Changes since v2:
>  * __rdtgroup_move_task() changed to set CLOSID from different CLOSID place
>    depending on group type
> 
> No changes since v6
> ---
>  arch/x86/include/asm/resctrl.h         | 18 ++++++++
>  arch/x86/kernel/cpu/resctrl/rdtgroup.c | 62 ++++++++++++++++----------
>  2 files changed, 56 insertions(+), 24 deletions(-)
> 
> diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
> index db4c84dde2d5..1d274dbabc44 100644
> --- a/arch/x86/include/asm/resctrl.h
> +++ b/arch/x86/include/asm/resctrl.h
> @@ -95,6 +95,24 @@ static inline unsigned int resctrl_arch_round_mon_val(unsigned int val)
>  	return val * scale;
>  }
>  
> +static inline void resctrl_arch_set_closid_rmid(struct task_struct *tsk,
> +						u32 closid, u32 rmid)
> +{
> +	WRITE_ONCE(tsk->closid, closid);
> +	WRITE_ONCE(tsk->rmid, rmid);
> +}
> +
> +static inline bool resctrl_arch_match_closid(struct task_struct *tsk, u32 closid)
> +{
> +	return READ_ONCE(tsk->closid) == closid;
> +}
> +
> +static inline bool resctrl_arch_match_rmid(struct task_struct *tsk, u32 ignored,
> +					   u32 rmid)
> +{
> +	return READ_ONCE(tsk->rmid) == rmid;
> +}
> +
>  static inline void resctrl_sched_in(struct task_struct *tsk)
>  {
>  	if (static_branch_likely(&rdt_enable_key))
> diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> index 0b9bd5f0f60d..fe6dfea471f2 100644
> --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
> @@ -102,7 +102,7 @@ void rdt_staged_configs_clear(void)
>   *
>   * Using a global CLOSID across all resources has some advantages and
>   * some drawbacks:
> - * + We can simply set "current->closid" to assign a task to a resource
> + * + We can simply set current's closid to assign a task to a resource
>   *   group.
>   * + Context switch code can avoid extra memory references deciding which
>   *   CLOSID to load into the PQR_ASSOC MSR
> @@ -574,14 +574,26 @@ static void update_task_closid_rmid(struct task_struct *t)
>  		_update_task_closid_rmid(t);
>  }
>  
> +static bool task_in_rdtgroup(struct task_struct *tsk, struct rdtgroup *rdtgrp)
> +{
> +	u32 closid, rmid = rdtgrp->mon.rmid;
> +
> +	if (rdtgrp->type == RDTCTRL_GROUP)
> +		closid = rdtgrp->closid;
> +	else if (rdtgrp->type == RDTMON_GROUP)
> +		closid = rdtgrp->mon.parent->closid;
> +	else
> +		return false;
> +
> +	return resctrl_arch_match_closid(tsk, closid) &&
> +	       resctrl_arch_match_rmid(tsk, closid, rmid);
> +}
> +
>  static int __rdtgroup_move_task(struct task_struct *tsk,
>  				struct rdtgroup *rdtgrp)
>  {
>  	/* If the task is already in rdtgrp, no need to move the task. */
> -	if ((rdtgrp->type == RDTCTRL_GROUP && tsk->closid == rdtgrp->closid &&
> -	     tsk->rmid == rdtgrp->mon.rmid) ||
> -	    (rdtgrp->type == RDTMON_GROUP && tsk->rmid == rdtgrp->mon.rmid &&
> -	     tsk->closid == rdtgrp->mon.parent->closid))
> +	if (task_in_rdtgroup(tsk, rdtgrp))
>  		return 0;
>  
>  	/*
> @@ -592,19 +604,19 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
>  	 * For monitor groups, can move the tasks only from
>  	 * their parent CTRL group.
>  	 */
> -
> -	if (rdtgrp->type == RDTCTRL_GROUP) {
> -		WRITE_ONCE(tsk->closid, rdtgrp->closid);
> -		WRITE_ONCE(tsk->rmid, rdtgrp->mon.rmid);
> -	} else if (rdtgrp->type == RDTMON_GROUP) {
> -		if (rdtgrp->mon.parent->closid == tsk->closid) {
> -			WRITE_ONCE(tsk->rmid, rdtgrp->mon.rmid);
> -		} else {
> -			rdt_last_cmd_puts("Can't move task to different control group\n");
> -			return -EINVAL;
> -		}
> +	if (rdtgrp->type == RDTMON_GROUP &&
> +	    !resctrl_arch_match_closid(tsk, rdtgrp->mon.parent->closid)) {
> +		rdt_last_cmd_puts("Can't move task to different control group\n");
> +		return -EINVAL;
>  	}
>  
> +	if (rdtgrp->type == RDTMON_GROUP)
> +		resctrl_arch_set_closid_rmid(tsk, rdtgrp->mon.parent->closid,
> +					     rdtgrp->mon.rmid);
> +	else
> +		resctrl_arch_set_closid_rmid(tsk, rdtgrp->closid,
> +					     rdtgrp->mon.rmid);
> +
>  	/*
>  	 * Ensure the task's closid and rmid are written before determining if
>  	 * the task is current that will decide if it will be interrupted.
> @@ -626,14 +638,15 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
>  
>  static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
>  {
> -	return (rdt_alloc_capable &&
> -	       (r->type == RDTCTRL_GROUP) && (t->closid == r->closid));
> +	return (rdt_alloc_capable && (r->type == RDTCTRL_GROUP) &&
> +		resctrl_arch_match_closid(t, r->closid));
>  }
>  
>  static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r)
>  {
> -	return (rdt_mon_capable &&
> -	       (r->type == RDTMON_GROUP) && (t->rmid == r->mon.rmid));
> +	return (rdt_mon_capable && (r->type == RDTMON_GROUP) &&
> +		resctrl_arch_match_rmid(t, r->mon.parent->closid,
> +					r->mon.rmid));
>  }
>  
>  /**
> @@ -884,7 +897,7 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns,
>  		    rdtg->mode != RDT_MODE_EXCLUSIVE)
>  			continue;
>  
> -		if (rdtg->closid != tsk->closid)
> +		if (!resctrl_arch_match_closid(tsk, rdtg->closid))
>  			continue;
>  
>  		seq_printf(s, "res:%s%s\n", (rdtg == &rdtgroup_default) ? "/" : "",
> @@ -892,7 +905,8 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns,
>  		seq_puts(s, "mon:");
>  		list_for_each_entry(crg, &rdtg->mon.crdtgrp_list,
>  				    mon.crdtgrp_list) {
> -			if (tsk->rmid != crg->mon.rmid)
> +			if (!resctrl_arch_match_rmid(tsk, crg->mon.parent->closid,
> +						     crg->mon.rmid))
>  				continue;
>  			seq_printf(s, "%s", crg->kn->name);
>  			break;
> @@ -2825,8 +2839,8 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
>  	for_each_process_thread(p, t) {
>  		if (!from || is_closid_match(t, from) ||
>  		    is_rmid_match(t, from)) {
> -			WRITE_ONCE(t->closid, to->closid);
> -			WRITE_ONCE(t->rmid, to->mon.rmid);
> +			resctrl_arch_set_closid_rmid(t, to->closid,
> +						     to->mon.rmid);
>  
>  			/*
>  			 * Order the closid/rmid stores above before the loads

-- 
Thanks
Babu Moger