Re: [PATCH v2 5/5] mm/memcg: Optimize user context object stock access

[Waiman Long <llong@redhat.com>]

On 4/12/21 7:10 PM, Shakeel Butt wrote:
> On Mon, Apr 12, 2021 at 3:55 PM Waiman Long <longman@redhat.com> wrote:
>> Most kmem_cache_alloc() calls are from user context. With instrumentation
>> enabled, the measured amount of kmem_cache_alloc() calls from non-task
>> context was about 0.01% of the total.
>>
>> The irq disable/enable sequence used in this case to access content
>> from object stock is slow.  To optimize for user context access, there
>> are now two object stocks for task context and interrupt context access
>> respectively.
>>
>> The task context object stock can be accessed after disabling preemption
>> which is cheap in non-preempt kernel. The interrupt context object stock
>> can only be accessed after disabling interrupt. User context code can
>> access interrupt object stock, but not vice versa.
>>
>> The mod_objcg_state() function is also modified to make sure that memcg
>> and lruvec stat updates are done with interrupted disabled.
>>
>> The downside of this change is that there are more data stored in local
>> object stocks and not reflected in the charge counter and the vmstat
>> arrays.  However, this is a small price to pay for better performance.
>>
>> Signed-off-by: Waiman Long <longman@redhat.com>
>> Acked-by: Roman Gushchin <guro@fb.com>
>> ---
>>   mm/memcontrol.c | 73 +++++++++++++++++++++++++++++++++++++++----------
>>   1 file changed, 59 insertions(+), 14 deletions(-)
>>
>> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
>> index 69f728383efe..29f2df76644a 100644
>> --- a/mm/memcontrol.c
>> +++ b/mm/memcontrol.c
>> @@ -2229,7 +2229,8 @@ struct obj_stock {
>>   struct memcg_stock_pcp {
>>          struct mem_cgroup *cached; /* this never be root cgroup */
>>          unsigned int nr_pages;
>> -       struct obj_stock obj;
>> +       struct obj_stock task_obj;
>> +       struct obj_stock irq_obj;
>>
>>          struct work_struct work;
>>          unsigned long flags;
>> @@ -2254,11 +2255,48 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
>>   }
>>   #endif
>>
>> +/*
>> + * Most kmem_cache_alloc() calls are from user context. The irq disable/enable
>> + * sequence used in this case to access content from object stock is slow.
>> + * To optimize for user context access, there are now two object stocks for
>> + * task context and interrupt context access respectively.
>> + *
>> + * The task context object stock can be accessed by disabling preemption only
>> + * which is cheap in non-preempt kernel. The interrupt context object stock
>> + * can only be accessed after disabling interrupt. User context code can
>> + * access interrupt object stock, but not vice versa.
>> + */
>>   static inline struct obj_stock *current_obj_stock(void)
>>   {
>>          struct memcg_stock_pcp *stock = this_cpu_ptr(&memcg_stock);
>>
>> -       return &stock->obj;
>> +       return in_task() ? &stock->task_obj : &stock->irq_obj;
>> +}
>> +
>> +#define get_obj_stock(flags)                           \
>> +({                                                     \
>> +       struct memcg_stock_pcp *stock;                  \
>> +       struct obj_stock *obj_stock;                    \
>> +                                                       \
>> +       if (in_task()) {                                \
>> +               preempt_disable();                      \
>> +               (flags) = -1L;                          \
>> +               stock = this_cpu_ptr(&memcg_stock);     \
> The above line was missing in the previous version.
>
>> +               obj_stock = &stock->task_obj;           \
>> +       } else {                                        \
>> +               local_irq_save(flags);                  \
>> +               stock = this_cpu_ptr(&memcg_stock);     \
>> +               obj_stock = &stock->irq_obj;            \
>> +       }                                               \
>> +       obj_stock;                                      \
>> +})
>> +
>> +static inline void put_obj_stock(unsigned long flags)
>> +{
>> +       if (flags == -1L)
>> +               preempt_enable();
>> +       else
>> +               local_irq_restore(flags);
>>   }
>>
>>   /**
>> @@ -2327,7 +2365,9 @@ static void drain_local_stock(struct work_struct *dummy)
>>          local_irq_save(flags);
>>
>>          stock = this_cpu_ptr(&memcg_stock);
>> -       drain_obj_stock(&stock->obj);
>> +       drain_obj_stock(&stock->irq_obj);
>> +       if (in_task())
>> +               drain_obj_stock(&stock->task_obj);
>>          drain_stock(stock);
>>          clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
>>
>> @@ -3183,7 +3223,7 @@ static inline void mod_objcg_state(struct obj_cgroup *objcg,
>>          memcg = obj_cgroup_memcg(objcg);
>>          if (pgdat)
>>                  lruvec = mem_cgroup_lruvec(memcg, pgdat);
>> -       __mod_memcg_lruvec_state(memcg, lruvec, idx, nr);
>> +       mod_memcg_lruvec_state(memcg, lruvec, idx, nr);
>>          rcu_read_unlock();
>>   }
>>
>> @@ -3193,7 +3233,7 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
>>          unsigned long flags;
>>          bool ret = false;
>>
>> -       local_irq_save(flags);
>> +       stock = get_obj_stock(flags);
>>
>>          stock = current_obj_stock();
> The above is redundant.

Right. I should check the patch carefully. Will remove it.

Thanks,
Longman