Re: [RFC PATCH v3 07/17] x86/resctrl: Add support to enable/disable ABMC feature

[Moger, Babu]

Hi Peter,

On 4/3/24 19:30, Peter Newman wrote:
> Hi Babu,
> 
> On Thu, Mar 28, 2024 at 6:07 PM Babu Moger <babu.moger@xxxxxxx> wrote:
>>  struct rdt_fs_context {
>>         struct kernfs_fs_context        kfc;
>>         bool                            enable_cdpl2;
>> @@ -433,6 +436,7 @@ struct rdt_parse_data {
>>   * @mbm_cfg_mask:      Bandwidth sources that can be tracked when Bandwidth
>>   *                     Monitoring Event Configuration (BMEC) is supported.
>>   * @cdp_enabled:       CDP state of this resource
>> + * @abmc_enabled:      ABMC feature is enabled
>>   *
>>   * Members of this structure are either private to the architecture
>>   * e.g. mbm_width, or accessed via helpers that provide abstraction. e.g.
>> @@ -448,6 +452,7 @@ struct rdt_hw_resource {
>>         unsigned int            mbm_width;
>>         unsigned int            mbm_cfg_mask;
>>         bool                    cdp_enabled;
>> +       bool                    abmc_enabled;
>>  };
>>
>>  static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r)
>> @@ -491,6 +496,13 @@ static inline bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l)
>>
>>  int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable);
>>
>> +static inline bool resctrl_arch_get_abmc_enabled(enum resctrl_res_level l)
>> +{
>> +       return rdt_resources_all[l].abmc_enabled;
>> +}
> 
> This inline definition will not work in either this file or
> fs/resctrl/internal.h, following James's change[1] moving the code.

Yea. I see..
> 
> resctrl_arch-definitions are either declared in linux/resctrl.h or
> defined inline in a file like asm/resctrl.h.

ok.
> 
> 
>> +
>> +int resctrl_arch_set_abmc_enabled(enum resctrl_res_level l, bool enable);
>> +
>>  /*
>>   * To return the common struct rdt_resource, which is contained in struct
>>   * rdt_hw_resource, walk the resctrl member of struct rdt_hw_resource.
>> diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
>> index 05f551bc316e..f49073c86884 100644
>> --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
>> +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
>> @@ -850,9 +850,15 @@ static int rdtgroup_mbm_assign_show(struct kernfs_open_file *of,
>>                                     struct seq_file *s, void *v)
>>  {
>>         struct rdt_resource *r = of->kn->parent->priv;
>> +       struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
>>
>> -       if (r->mbm_assign_capable)
>> +       if (r->mbm_assign_capable && hw_res->abmc_enabled) {
>> +               seq_puts(s, "[abmc]\n");
>> +               seq_puts(s, "legacy_mbm\n");
>> +       } else if (r->mbm_assign_capable) {
>>                 seq_puts(s, "abmc\n");
>> +               seq_puts(s, "[legacy_mbm]\n");
>> +       }
> 
> This looks like it would move to fs/resctrl/rdtgroup.c where it's not
> possible to dereference an rdt_hw_resource struct.
> 
> It might be helpful to try building your changes on top of James's
> change[1] to get an idea of how this would fit in post-refactoring.
> I'll stop pointing out inconsistencies with his portability scheme
> now.

Considering the complexity of James changes, I was hoping my series will
go first. It would be difficult for me to make changes based on transient
patch series. I would think it would be best to base the patches based on
tip/master.

> 
>>
>>         return 0;
>>  }
>> @@ -2433,6 +2439,74 @@ int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable)
>>         return 0;
>>  }
>>
>> +static void resctrl_abmc_msrwrite(void *arg)
>> +{
>> +       bool *enable = arg;
>> +       u64 msrval;
>> +
>> +       rdmsrl(MSR_IA32_L3_QOS_EXT_CFG, msrval);
>> +
>> +       if (*enable)
>> +               msrval |= ABMC_ENABLE;
>> +       else
>> +               msrval &= ~ABMC_ENABLE;
>> +
>> +       wrmsrl(MSR_IA32_L3_QOS_EXT_CFG, msrval);
>> +}
>> +
>> +static int resctrl_abmc_setup(enum resctrl_res_level l, bool enable)
>> +{
>> +       struct rdt_resource *r = &rdt_resources_all[l].r_resctrl;
>> +       struct rdt_domain *d;
>> +
>> +       /* Update QOS_CFG MSR on all the CPUs in cpu_mask */
>> +       list_for_each_entry(d, &r->domains, list) {
>> +               on_each_cpu_mask(&d->cpu_mask, resctrl_abmc_msrwrite, &enable, 1);
>> +               resctrl_arch_reset_rmid_all(r, d);
>> +       }
>> +
>> +       return 0;
>> +}
>> +
>> +static int resctrl_abmc_enable(enum resctrl_res_level l)
>> +{
>> +       struct rdt_hw_resource *hw_res = &rdt_resources_all[l];
>> +       int ret = 0;
>> +
>> +       if (!hw_res->abmc_enabled) {
>> +               ret = resctrl_abmc_setup(l, true);
>> +               if (!ret)
>> +                       hw_res->abmc_enabled = true;
> 
> Presumably this would be called holding the rdtgroup_mutex? Perhaps a
> lockdep assertion somewhere would be appropriate?

Yes. Sure. Will add it next revision.

> 
> Thanks!
> -Peter
> 
> [1] https://lore.kernel.org/lkml/20240321165106.31602-32-james.morse@xxxxxxx/

-- 
Thanks
Babu Moger