Re: [PATCH v5 06/24] x86/resctrl: Track the number of dirty RMID a CLOSID has

[Fenghua Yu]

Hi, James,

On 7/28/23 09:42, James Morse wrote:
> MPAM's PMG bits extend its PARTID space, meaning the same PMG value can be
> used for different control groups.
>
> This means once a CLOSID is allocated, all its monitoring ids may still be
> dirty, and held in limbo.
>
> Keep track of the number of RMID held in limbo each CLOSID has. This will
> allow a future helper to find the 'cleanest' CLOSID when allocating.
>
> The array is only needed when CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID is
> defined. This will never be the case on x86.
>
> Signed-off-by: James Morse <james.morse@xxxxxxx>
> ---
> Changes since v4:
>   * Moved closid_num_dirty_rmid[] update under entry->busy check
>   * Take the mutex in dom_data_init() as the caller doesn't.
> ---
>   arch/x86/kernel/cpu/resctrl/monitor.c | 49 +++++++++++++++++++++++----
>   1 file changed, 42 insertions(+), 7 deletions(-)
>
> diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
> index de91ca781d9f..44addc0126fc 100644
> --- a/arch/x86/kernel/cpu/resctrl/monitor.c
> +++ b/arch/x86/kernel/cpu/resctrl/monitor.c
> @@ -43,6 +43,13 @@ struct rmid_entry {
>    */
>   static LIST_HEAD(rmid_free_lru);
>   

Better to add:

#if CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID
> +/**
> + * @closid_num_dirty_rmid    The number of dirty RMID each CLOSID has.
> + * Only allocated when CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID is defined.
> + * Indexed by CLOSID. Protected by rdtgroup_mutex.
> + */
> +static int *closid_num_dirty_rmid;
#endif

Then the global variable won't exist on x86 to avoid confusion and space.

Some code related to the CONFIG also needs to be changed accordingly.

> +
>   /**
>    * @rmid_limbo_count     count of currently unused but (potentially)
>    *     dirty RMIDs.
> @@ -285,6 +292,17 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
>   	return 0;
>   }
>   
> +static void limbo_release_entry(struct rmid_entry *entry)
> +{
> +	lockdep_assert_held(&rdtgroup_mutex);
> +
> +	rmid_limbo_count--;
> +	list_add_tail(&entry->list, &rmid_free_lru);
> +
> +	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
> +		closid_num_dirty_rmid[entry->closid]--;


Maybe define some helpers (along with other similar ones) in resctrl.h 
like this:

#ifdef CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID
static inline void closid_num_dirty_rmid_dec(struct rmid_entry *entry)
{
		closid_num_dirty_rmid[entry->closid]--;
}
...
#else
static inline void closid_num_dirty_rmid_dec(struct rmid_entry *unused)
{
}
...
#endif

Then directly call the helper here:

+		closid_num_dirty_rmid_dec(entry);

On x86 this is noop without occupy any space and cleaner code.

> +}
> +
>   /*
>    * Check the RMIDs that are marked as busy for this domain. If the
>    * reported LLC occupancy is below the threshold clear the busy bit and
> @@ -321,10 +339,8 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
>   
>   		if (force_free || !rmid_dirty) {
>   			clear_bit(idx, d->rmid_busy_llc);
> -			if (!--entry->busy) {
> -				rmid_limbo_count--;
> -				list_add_tail(&entry->list, &rmid_free_lru);
> -			}
> +			if (!--entry->busy)
> +				limbo_release_entry(entry);
>   		}
>   		cur_idx = idx + 1;
>   	}
> @@ -391,6 +407,8 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
>   	u64 val = 0;
>   	u32 idx;
>   
> +	lockdep_assert_held(&rdtgroup_mutex);
> +
>   	idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid);
>   
>   	entry->busy = 0;
> @@ -416,9 +434,11 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
>   	}
>   	put_cpu();
>   
> -	if (entry->busy)
> +	if (entry->busy) {
>   		rmid_limbo_count++;
> -	else
> +		if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
> +			closid_num_dirty_rmid[entry->closid]++;

Ditto.

> +	} else
>   		list_add_tail(&entry->list, &rmid_free_lru);
>   }
>   
> @@ -782,13 +802,28 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
>   static int dom_data_init(struct rdt_resource *r)
>   {
>   	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
> +	u32 num_closid = resctrl_arch_get_num_closid(r);
>   	struct rmid_entry *entry = NULL;
>   	u32 idx;
>   	int i;
>   
> +	if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
> +		int *tmp;
> +
> +		tmp = kcalloc(num_closid, sizeof(int), GFP_KERNEL);
> +		if (!tmp)
> +			return -ENOMEM;
> +
> +		mutex_lock(&rdtgroup_mutex);

data_init() is called in __init. No need to lock here, right?

> +		closid_num_dirty_rmid = tmp;
> +		mutex_unlock(&rdtgroup_mutex);
> +	}
> +

This code is also can be defined as a helper in resctrl.h.

>   	rmid_ptrs = kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL);
> -	if (!rmid_ptrs)
> +	if (!rmid_ptrs) {
> +		kfree(closid_num_dirty_rmid);
>   		return -ENOMEM;
> +	}
>   
>   	for (i = 0; i < idx_limit; i++) {
>   		entry = &rmid_ptrs[i];

Thanks.

-Fenghua