Re: [PATCH v8 2/2] memory tier: create CPUless memory tiers after obtaining HMAT info

[Huang, Ying]

"Ho-Ren (Jack) Chuang" <horenchuang@bytedance.com> writes:

> The current implementation treats emulated memory devices, such as
> CXL1.1 type3 memory, as normal DRAM when they are emulated as normal memory
> (E820_TYPE_RAM). However, these emulated devices have different
> characteristics than traditional DRAM, making it important to
> distinguish them. Thus, we modify the tiered memory initialization process
> to introduce a delay specifically for CPUless NUMA nodes. This delay
> ensures that the memory tier initialization for these nodes is deferred
> until HMAT information is obtained during the boot process. Finally,
> demotion tables are recalculated at the end.
>
> * late_initcall(memory_tier_late_init);
> Some device drivers may have initialized memory tiers between
> `memory_tier_init()` and `memory_tier_late_init()`, potentially bringing
> online memory nodes and configuring memory tiers. They should be excluded
> in the late init.
>
> * Handle cases where there is no HMAT when creating memory tiers
> There is a scenario where a CPUless node does not provide HMAT information.
> If no HMAT is specified, it falls back to using the default DRAM tier.
>
> * Introduce another new lock `default_dram_perf_lock` for adist calculation
> In the current implementation, iterating through CPUlist nodes requires
> holding the `memory_tier_lock`. However, `mt_calc_adistance()` will end up
> trying to acquire the same lock, leading to a potential deadlock.
> Therefore, we propose introducing a standalone `default_dram_perf_lock` to
> protect `default_dram_perf_*`. This approach not only avoids deadlock
> but also prevents holding a large lock simultaneously.
>
> * Upgrade `set_node_memory_tier` to support additional cases, including
>   default DRAM, late CPUless, and hot-plugged initializations.
> To cover hot-plugged memory nodes, `mt_calc_adistance()` and
> `mt_find_alloc_memory_type()` are moved into `set_node_memory_tier()` to
> handle cases where memtype is not initialized and where HMAT information is
> available.
>
> * Introduce `default_memory_types` for those memory types that are not
>   initialized by device drivers.
> Because late initialized memory and default DRAM memory need to be managed,
> a default memory type is created for storing all memory types that are
> not initialized by device drivers and as a fallback.
>
> Signed-off-by: Ho-Ren (Jack) Chuang <horenchuang@bytedance.com>
> Signed-off-by: Hao Xiang <hao.xiang@bytedance.com>
> Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
> ---
>  mm/memory-tiers.c | 94 +++++++++++++++++++++++++++++++++++++++--------
>  1 file changed, 78 insertions(+), 16 deletions(-)
>
> diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
> index 974af10cfdd8..e24fc3bebae4 100644
> --- a/mm/memory-tiers.c
> +++ b/mm/memory-tiers.c
> @@ -36,6 +36,11 @@ struct node_memory_type_map {
>  
>  static DEFINE_MUTEX(memory_tier_lock);
>  static LIST_HEAD(memory_tiers);
> +/*
> + * The list is used to store all memory types that are not created
> + * by a device driver.
> + */
> +static LIST_HEAD(default_memory_types);
>  static struct node_memory_type_map node_memory_types[MAX_NUMNODES];
>  struct memory_dev_type *default_dram_type;
>  
> @@ -108,6 +113,8 @@ static struct demotion_nodes *node_demotion __read_mostly;
>  
>  static BLOCKING_NOTIFIER_HEAD(mt_adistance_algorithms);
>  
> +/* The lock is used to protect `default_dram_perf*` info and nid. */
> +static DEFINE_MUTEX(default_dram_perf_lock);
>  static bool default_dram_perf_error;
>  static struct access_coordinate default_dram_perf;
>  static int default_dram_perf_ref_nid = NUMA_NO_NODE;
> @@ -505,7 +512,8 @@ static inline void __init_node_memory_type(int node, 
> struct memory_dev_type *mem
>  static struct memory_tier *set_node_memory_tier(int node)
>  {
>       struct memory_tier *memtier;
> -     struct memory_dev_type *memtype;
> +     struct memory_dev_type *mtype = default_dram_type;
> +     int adist = MEMTIER_ADISTANCE_DRAM;
>       pg_data_t *pgdat = NODE_DATA(node);
>  
>  
> @@ -514,11 +522,20 @@ static struct memory_tier *set_node_memory_tier(int 
> node)
>       if (!node_state(node, N_MEMORY))
>               return ERR_PTR(-EINVAL);
>  
> -     __init_node_memory_type(node, default_dram_type);
> +     mt_calc_adistance(node, &adist);
> +     if (node_memory_types[node].memtype == NULL) {
> +             mtype = mt_find_alloc_memory_type(adist, &default_memory_types);
> +             if (IS_ERR(mtype)) {
> +                     mtype = default_dram_type;
> +                     pr_info("Failed to allocate a memory type. Fall 
> back.\n");
> +             }
> +     }
> +
> +     __init_node_memory_type(node, mtype);
>  
> -     memtype = node_memory_types[node].memtype;
> -     node_set(node, memtype->nodes);
> -     memtier = find_create_memory_tier(memtype);
> +     mtype = node_memory_types[node].memtype;
> +     node_set(node, mtype->nodes);
> +     memtier = find_create_memory_tier(mtype);
>       if (!IS_ERR(memtier))
>               rcu_assign_pointer(pgdat->memtier, memtier);
>       return memtier;
> @@ -655,6 +672,34 @@ void mt_put_memory_types(struct list_head *memory_types)
>  }
>  EXPORT_SYMBOL_GPL(mt_put_memory_types);
>  
> +/*
> + * This is invoked via `late_initcall()` to initialize memory tiers for
> + * CPU-less memory nodes after driver initialization, which is
> + * expected to provide `adistance` algorithms.
> + */
> +static int __init memory_tier_late_init(void)
> +{
> +     int nid;
> +
> +     mutex_lock(&memory_tier_lock);
> +     for_each_node_state(nid, N_MEMORY)
> +             if (!node_state(nid, N_CPU) &&

It appears that you didn't notice my comments about this...

87v857kujp.fsf@yhuang6-desk2.ccr.corp.intel.com/">https://lore.kernel.org/linux-mm/87v857kujp.fsf@yhuang6-desk2.ccr.corp.intel.com/

> +                     node_memory_types[nid].memtype == NULL)
> +                     /*
> +                      * Some device drivers may have initialized memory tiers
> +                      * between `memory_tier_init()` and 
> `memory_tier_late_init()`,
> +                      * potentially bringing online memory nodes and
> +                      * configuring memory tiers. Exclude them here.
> +                      */
> +                     set_node_memory_tier(nid);
> +
> +     establish_demotion_targets();
> +     mutex_unlock(&memory_tier_lock);
> +
> +     return 0;
> +}
> +late_initcall(memory_tier_late_init);
> +
>  static void dump_hmem_attrs(struct access_coordinate *coord, const char 
> *prefix)
>  {
>       pr_info(
> @@ -668,7 +713,7 @@ int mt_set_default_dram_perf(int nid, struct 
> access_coordinate *perf,
>  {
>       int rc = 0;
>  
> -     mutex_lock(&memory_tier_lock);
> +     mutex_lock(&default_dram_perf_lock);
>       if (default_dram_perf_error) {
>               rc = -EIO;
>               goto out;
> @@ -716,23 +761,30 @@ int mt_set_default_dram_perf(int nid, struct 
> access_coordinate *perf,
>       }
>  
>  out:
> -     mutex_unlock(&memory_tier_lock);
> +     mutex_unlock(&default_dram_perf_lock);
>       return rc;
>  }
>  
>  int mt_perf_to_adistance(struct access_coordinate *perf, int *adist)
>  {
> -     if (default_dram_perf_error)
> -             return -EIO;
> +     int rc = 0;
>  
> -     if (default_dram_perf_ref_nid == NUMA_NO_NODE)
> -             return -ENOENT;
> +     mutex_lock(&default_dram_perf_lock);
> +     if (default_dram_perf_error) {
> +             rc = -EIO;
> +             goto out;
> +     }
>  
>       if (perf->read_latency + perf->write_latency == 0 ||
> -         perf->read_bandwidth + perf->write_bandwidth == 0)
> -             return -EINVAL;
> +         perf->read_bandwidth + perf->write_bandwidth == 0) {
> +             rc = -EINVAL;
> +             goto out;
> +     }
>  
> -     mutex_lock(&memory_tier_lock);
> +     if (default_dram_perf_ref_nid == NUMA_NO_NODE) {
> +             rc = -ENOENT;
> +             goto out;
> +     }
>       /*
>        * The abstract distance of a memory node is in direct proportion to
>        * its memory latency (read + write) and inversely proportional to its
> @@ -745,8 +797,9 @@ int mt_perf_to_adistance(struct access_coordinate *perf, 
> int *adist)
>               (default_dram_perf.read_latency + 
> default_dram_perf.write_latency) *
>               (default_dram_perf.read_bandwidth + 
> default_dram_perf.write_bandwidth) /
>               (perf->read_bandwidth + perf->write_bandwidth);
> -     mutex_unlock(&memory_tier_lock);
>  
> +out:
> +     mutex_unlock(&default_dram_perf_lock);
>       return 0;
>  }
>  EXPORT_SYMBOL_GPL(mt_perf_to_adistance);
> @@ -858,7 +911,8 @@ static int __init memory_tier_init(void)
>        * For now we can have 4 faster memory tiers with smaller adistance
>        * than default DRAM tier.
>        */
> -     default_dram_type = alloc_memory_type(MEMTIER_ADISTANCE_DRAM);
> +     default_dram_type = mt_find_alloc_memory_type(MEMTIER_ADISTANCE_DRAM,
> +                                                                     
> &default_memory_types);
>       if (IS_ERR(default_dram_type))
>               panic("%s() failed to allocate default DRAM tier\n", __func__);
>  
> @@ -868,6 +922,14 @@ static int __init memory_tier_init(void)
>        * types assigned.
>        */
>       for_each_node_state(node, N_MEMORY) {
> +             if (!node_state(node, N_CPU))
> +                     /*
> +                      * Defer memory tier initialization on CPUless numa 
> nodes.
> +                      * These will be initialized after firmware and devices 
> are
> +                      * initialized.
> +                      */
> +                     continue;
> +
>               memtier = set_node_memory_tier(node);
>               if (IS_ERR(memtier))
>                       /*

--
Best Regards,
Huang, Ying