Re: [PATCH v7 05/24] x86/resctrl: Track the closid with the rmid

[Moger, Babu]

Hi James,

On 10/25/23 13:03, James Morse wrote:
> x86's RMID are independent of the CLOSID. An RMID can be allocated,
> used and freed without considering the CLOSID.
> 
> MPAM's equivalent feature is PMG, which is not an independent number,
> it extends the CLOSID/PARTID space. For MPAM, only PMG-bits worth of
> 'RMID' can be allocated for a single CLOSID.
> i.e. if there is 1 bit of PMG space, then each CLOSID can have two
> monitor groups.
> 
> To allow resctrl to disambiguate RMID values for different CLOSID,
> everything in resctrl that keeps an RMID value needs to know the CLOSID
> too. This will always be ignored on x86.
> 
> Tested-by: Shaopeng Tan <tan.shaopeng@xxxxxxxxxxx>
> Tested-by: Peter Newman <peternewman@xxxxxxxxxx>
> Reviewed-by: Shaopeng Tan <tan.shaopeng@xxxxxxxxxxx>
> Reviewed-by: Xin Hao <xhao@xxxxxxxxxxxxxxxxx>
> Signed-off-by: James Morse <james.morse@xxxxxxx>
> 
> ---
> Is there a better term for 'the unique identifier for a monitor group'.
> Using RMID for that here may be confusing...
> 
> Changes since v1:
>  * Added comment in struct rmid_entry
> 
> Changes since v2:
>  * Moved X86_RESCTRL_BAD_CLOSID from a subsequent patch
> 
> Chances since v3:
>  * Renamed X86_RESCTRL_BAD_CLOSID to EMPTY
>  * Clarified a few comments and kernel-doc
> 
> Changes since v5:
>  * Use entry->closid from the iterator, instead of the parent control group.
>  * Move the reserved defines into this patch to reduce the churn.
>  * Added some kernel doc.
>  * Renamed some arch closid parameters as 'unused'.
> 
> Changes since v6:
>  * Changes to comments.
> ---
>  arch/x86/include/asm/resctrl.h            |  7 +++
>  arch/x86/kernel/cpu/resctrl/internal.h    |  2 +-
>  arch/x86/kernel/cpu/resctrl/monitor.c     | 74 ++++++++++++++---------
>  arch/x86/kernel/cpu/resctrl/pseudo_lock.c |  4 +-
>  arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 12 ++--
>  include/linux/resctrl.h                   | 16 ++++-
>  6 files changed, 77 insertions(+), 38 deletions(-)
> 
> diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
> index 255a78d9d906..cc6e1bce7b1a 100644
> --- a/arch/x86/include/asm/resctrl.h
> +++ b/arch/x86/include/asm/resctrl.h
> @@ -7,6 +7,13 @@
>  #include <linux/sched.h>
>  #include <linux/jump_label.h>
>  
> +/*
> + * This value can never be a valid CLOSID, and is used when mapping a
> + * (closid, rmid) pair to an index and back. On x86 only the RMID is
> + * needed. The index is a software defined value.
> + */
> +#define X86_RESCTRL_EMPTY_CLOSID         ((u32)~0)
> +
>  /**
>   * struct resctrl_pqr_state - State cache for the PQR MSR
>   * @cur_rmid:		The cached Resource Monitoring ID
> diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
> index f68c6aecfa66..c836e3294e12 100644
> --- a/arch/x86/kernel/cpu/resctrl/internal.h
> +++ b/arch/x86/kernel/cpu/resctrl/internal.h
> @@ -544,7 +544,7 @@ struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
>  int closids_supported(void);
>  void closid_free(int closid);
>  int alloc_rmid(void);
> -void free_rmid(u32 rmid);
> +void free_rmid(u32 closid, u32 rmid);
>  int rdt_get_mon_l3_config(struct rdt_resource *r);
>  void __exit rdt_put_mon_l3_config(struct rdt_resource *r);
>  bool __init rdt_cpu_has(int flag);
> diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
> index 5d9864919f1c..2a0233cd0bc9 100644
> --- a/arch/x86/kernel/cpu/resctrl/monitor.c
> +++ b/arch/x86/kernel/cpu/resctrl/monitor.c
> @@ -24,7 +24,20 @@
>  
>  #include "internal.h"
>  
> +/**
> + * struct rmid_entry - dirty tracking for all RMID.
> + * @closid:	The CLOSID for this entry.
> + * @rmid:	The RMID for this entry.
> + * @busy:	The number of domains with cached data using this RMID.
> + * @list:	Member of the rmid_free_lru list when busy == 0.
> + *
> + * Depending on the architecture the correct monitor is accessed using
> + * both @closid and @rmid, or @rmid only.
> + *
> + * Take the rdtgroup_mutex when accessing.
> + */
>  struct rmid_entry {
> +	u32				closid;
>  	u32				rmid;
>  	int				busy;
>  	struct list_head		list;
> @@ -136,7 +149,7 @@ static inline u64 get_corrected_mbm_count(u32 rmid, unsigned long val)
>  	return val;
>  }
>  
> -static inline struct rmid_entry *__rmid_entry(u32 rmid)
> +static inline struct rmid_entry *__rmid_entry(u32 closid, u32 rmid)
>  {
>  	struct rmid_entry *entry;
>  
> @@ -190,7 +203,8 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
>  }
>  
>  void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
> -			     u32 rmid, enum resctrl_event_id eventid)
> +			     u32 unused, u32 rmid,
> +			     enum resctrl_event_id eventid)
>  {
>  	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
>  	struct arch_mbm_state *am;
> @@ -230,7 +244,8 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
>  }
>  
>  int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
> -			   u32 rmid, enum resctrl_event_id eventid, u64 *val)
> +			   u32 unused, u32 rmid, enum resctrl_event_id eventid,
> +			   u64 *val)
>  {
>  	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
>  	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
> @@ -285,9 +300,9 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
>  		if (nrmid >= r->num_rmid)
>  			break;
>  
> -		entry = __rmid_entry(nrmid);
> +		entry = __rmid_entry(X86_RESCTRL_EMPTY_CLOSID, nrmid);// temporary

What is temporary means here? Can you please elaborate(or remove)?

Thanks
Babu Moger