* Parth Shah <pa...@linux.ibm.com> [2021-07-28 23:26:05]:
> From: "Gautham R. Shenoy" <e...@linux.vnet.ibm.com>
>
> Currently the cacheinfo code on powerpc indexes the "cache" objects
> (modelling the L1/L2/L3 caches) where the key is device-tree node
> corresponding to that cache. On some of the POWER server platforms
> thread-groups within the core share different sets of caches (Eg: On
> SMT8 POWER9 systems, threads 0,2,4,6 of a core share L1 cache and
> threads 1,3,5,7 of the same core share another L1 cache). On such
> platforms, there is a single device-tree node corresponding to that
> cache and the cache-configuration within the threads of the core is
> indicated via "ibm,thread-groups" device-tree property.
>
> Since the current code is not aware of the "ibm,thread-groups"
> property, on the aforementoined systems, cacheinfo code still treats
> all the threads in the core to be sharing the cache because of the
> single device-tree node (In the earlier example, the cacheinfo code
> would says CPUs 0-7 share L1 cache).
>
> In this patch, we make the powerpc cacheinfo code aware of the
> "ibm,thread-groups" property. We indexe the "cache" objects by the
> key-pair (device-tree node, thread-group id). For any CPUX, for a
> given level of cache, the thread-group id is defined to be the first
> CPU in the "ibm,thread-groups" cache-group containing CPUX. For levels
> of cache which are not represented in "ibm,thread-groups" property,
> the thread-group id is -1.
>
> Signed-off-by: Gautham R. Shenoy <e...@linux.vnet.ibm.com>
> [parth: Remove "static" keyword for the definition of
> "thread_group_l1_cache_map"
> and "thread_group_l2_cache_map" to get rid of the compile error.]
> Signed-off-by: Parth Shah <pa...@linux.ibm.com>
Looks good to me.
Reviewed-by: Srikar Dronamraju <sri...@linux.vnet.ibm.com>
> ---
> arch/powerpc/include/asm/smp.h | 3 ++
> arch/powerpc/kernel/cacheinfo.c | 80 ++++++++++++++++++++++++---------
> arch/powerpc/kernel/smp.c | 4 +-
> 3 files changed, 63 insertions(+), 24 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
> index 03b3d010cbab..1259040cc3a4 100644
> --- a/arch/powerpc/include/asm/smp.h
> +++ b/arch/powerpc/include/asm/smp.h
> @@ -33,6 +33,9 @@ extern bool coregroup_enabled;
> extern int cpu_to_chip_id(int cpu);
> extern int *chip_id_lookup_table;
>
> +DECLARE_PER_CPU(cpumask_var_t, thread_group_l1_cache_map);
> +DECLARE_PER_CPU(cpumask_var_t, thread_group_l2_cache_map);
> +
> #ifdef CONFIG_SMP
>
> struct smp_ops_t {
> diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
> index 6f903e9aa20b..5a6925d87424 100644
> --- a/arch/powerpc/kernel/cacheinfo.c
> +++ b/arch/powerpc/kernel/cacheinfo.c
> @@ -120,6 +120,7 @@ struct cache {
> struct cpumask shared_cpu_map; /* online CPUs using this cache */
> int type; /* split cache disambiguation */
> int level; /* level not explicit in device tree */
> + int group_id; /* id of the group of threads that share
> this cache */
> struct list_head list; /* global list of cache objects */
> struct cache *next_local; /* next cache of >= level */
> };
> @@ -142,22 +143,24 @@ static const char *cache_type_string(const struct cache
> *cache)
> }
>
> static void cache_init(struct cache *cache, int type, int level,
> - struct device_node *ofnode)
> + struct device_node *ofnode, int group_id)
> {
> cache->type = type;
> cache->level = level;
> cache->ofnode = of_node_get(ofnode);
> + cache->group_id = group_id;
> INIT_LIST_HEAD(&cache->list);
> list_add(&cache->list, &cache_list);
> }
>
> -static struct cache *new_cache(int type, int level, struct device_node
> *ofnode)
> +static struct cache *new_cache(int type, int level,
> + struct device_node *ofnode, int group_id)
> {
> struct cache *cache;
>
> cache = kzalloc(sizeof(*cache), GFP_KERNEL);
> if (cache)
> - cache_init(cache, type, level, ofnode);
> + cache_init(cache, type, level, ofnode, group_id);
>
> return cache;
> }
> @@ -309,20 +312,24 @@ static struct cache *cache_find_first_sibling(struct
> cache *cache)
> return cache;
>
> list_for_each_entry(iter, &cache_list, list)
> - if (iter->ofnode == cache->ofnode && iter->next_local == cache)
> + if (iter->ofnode == cache->ofnode &&
> + iter->group_id == cache->group_id &&
> + iter->next_local == cache)
> return iter;
>
> return cache;
> }
>
> -/* return the first cache on a local list matching node */
> -static struct cache *cache_lookup_by_node(const struct device_node *node)
> +/* return the first cache on a local list matching node and thread-group id
> */
> +static struct cache *cache_lookup_by_node_group(const struct device_node
> *node,
> + int group_id)
> {
> struct cache *cache = NULL;
> struct cache *iter;
>
> list_for_each_entry(iter, &cache_list, list) {
> - if (iter->ofnode != node)
> + if (iter->ofnode != node ||
> + iter->group_id != group_id)
> continue;
> cache = cache_find_first_sibling(iter);
> break;
> @@ -352,14 +359,15 @@ static int cache_is_unified_d(const struct device_node
> *np)
> CACHE_TYPE_UNIFIED_D : CACHE_TYPE_UNIFIED;
> }
>
> -static struct cache *cache_do_one_devnode_unified(struct device_node *node,
> int level)
> +static struct cache *cache_do_one_devnode_unified(struct device_node *node,
> int group_id,
> + int level)
> {
> pr_debug("creating L%d ucache for %pOFP\n", level, node);
>
> - return new_cache(cache_is_unified_d(node), level, node);
> + return new_cache(cache_is_unified_d(node), level, node, group_id);
> }
>
> -static struct cache *cache_do_one_devnode_split(struct device_node *node,
> +static struct cache *cache_do_one_devnode_split(struct device_node *node,
> int group_id,
> int level)
> {
> struct cache *dcache, *icache;
> @@ -367,8 +375,8 @@ static struct cache *cache_do_one_devnode_split(struct
> device_node *node,
> pr_debug("creating L%d dcache and icache for %pOFP\n", level,
> node);
>
> - dcache = new_cache(CACHE_TYPE_DATA, level, node);
> - icache = new_cache(CACHE_TYPE_INSTRUCTION, level, node);
> + dcache = new_cache(CACHE_TYPE_DATA, level, node, group_id);
> + icache = new_cache(CACHE_TYPE_INSTRUCTION, level, node, group_id);
>
> if (!dcache || !icache)
> goto err;
> @@ -382,31 +390,32 @@ static struct cache *cache_do_one_devnode_split(struct
> device_node *node,
> return NULL;
> }
>
> -static struct cache *cache_do_one_devnode(struct device_node *node, int
> level)
> +static struct cache *cache_do_one_devnode(struct device_node *node, int
> group_id, int level)
> {
> struct cache *cache;
>
> if (cache_node_is_unified(node))
> - cache = cache_do_one_devnode_unified(node, level);
> + cache = cache_do_one_devnode_unified(node, group_id, level);
> else
> - cache = cache_do_one_devnode_split(node, level);
> + cache = cache_do_one_devnode_split(node, group_id, level);
>
> return cache;
> }
>
> static struct cache *cache_lookup_or_instantiate(struct device_node *node,
> + int group_id,
> int level)
> {
> struct cache *cache;
>
> - cache = cache_lookup_by_node(node);
> + cache = cache_lookup_by_node_group(node, group_id);
>
> WARN_ONCE(cache && cache->level != level,
> "cache level mismatch on lookup (got %d, expected %d)\n",
> cache->level, level);
>
> if (!cache)
> - cache = cache_do_one_devnode(node, level);
> + cache = cache_do_one_devnode(node, group_id, level);
>
> return cache;
> }
> @@ -443,7 +452,27 @@ static void do_subsidiary_caches_debugcheck(struct cache
> *cache)
> of_node_get_device_type(cache->ofnode));
> }
>
> -static void do_subsidiary_caches(struct cache *cache)
> +/*
> + * If sub-groups of threads in a core containing @cpu_id share the
> + * L@level-cache (information obtained via "ibm,thread-groups"
> + * device-tree property), then we identify the group by the first
> + * thread-sibling in the group. We define this to be the group-id.
> + *
> + * In the absence of any thread-group information for L@level-cache,
> + * this function returns -1.
> + */
> +static int get_group_id(unsigned int cpu_id, int level)
> +{
> + if (has_big_cores && level == 1)
> + return cpumask_first(per_cpu(thread_group_l1_cache_map,
> + cpu_id));
> + else if (thread_group_shares_l2 && level == 2)
> + return cpumask_first(per_cpu(thread_group_l2_cache_map,
> + cpu_id));
> + return -1;
> +}
> +
> +static void do_subsidiary_caches(struct cache *cache, unsigned int cpu_id)
> {
> struct device_node *subcache_node;
> int level = cache->level;
> @@ -452,9 +481,11 @@ static void do_subsidiary_caches(struct cache *cache)
>
> while ((subcache_node = of_find_next_cache_node(cache->ofnode))) {
> struct cache *subcache;
> + int group_id;
>
> level++;
> - subcache = cache_lookup_or_instantiate(subcache_node, level);
> + group_id = get_group_id(cpu_id, level);
> + subcache = cache_lookup_or_instantiate(subcache_node, group_id,
> level);
> of_node_put(subcache_node);
> if (!subcache)
> break;
> @@ -468,6 +499,7 @@ static struct cache *cache_chain_instantiate(unsigned int
> cpu_id)
> {
> struct device_node *cpu_node;
> struct cache *cpu_cache = NULL;
> + int group_id;
>
> pr_debug("creating cache object(s) for CPU %i\n", cpu_id);
>
> @@ -476,11 +508,13 @@ static struct cache *cache_chain_instantiate(unsigned
> int cpu_id)
> if (!cpu_node)
> goto out;
>
> - cpu_cache = cache_lookup_or_instantiate(cpu_node, 1);
> + group_id = get_group_id(cpu_id, 1);
> +
> + cpu_cache = cache_lookup_or_instantiate(cpu_node, group_id, 1);
> if (!cpu_cache)
> goto out;
>
> - do_subsidiary_caches(cpu_cache);
> + do_subsidiary_caches(cpu_cache, cpu_id);
>
> cache_cpu_set(cpu_cache, cpu_id);
> out:
> @@ -848,13 +882,15 @@ static struct cache *cache_lookup_by_cpu(unsigned int
> cpu_id)
> {
> struct device_node *cpu_node;
> struct cache *cache;
> + int group_id;
>
> cpu_node = of_get_cpu_node(cpu_id, NULL);
> WARN_ONCE(!cpu_node, "no OF node found for CPU %i\n", cpu_id);
> if (!cpu_node)
> return NULL;
>
> - cache = cache_lookup_by_node(cpu_node);
> + group_id = get_group_id(cpu_id, 1);
> + cache = cache_lookup_by_node_group(cpu_node, group_id);
> of_node_put(cpu_node);
>
> return cache;
> diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
> index 447b78a87c8f..a7fcac44a8e2 100644
> --- a/arch/powerpc/kernel/smp.c
> +++ b/arch/powerpc/kernel/smp.c
> @@ -122,14 +122,14 @@ static struct thread_groups_list tgl[NR_CPUS]
> __initdata;
> * On big-cores system, thread_group_l1_cache_map for each CPU corresponds to
> * the set its siblings that share the L1-cache.
> */
> -static DEFINE_PER_CPU(cpumask_var_t, thread_group_l1_cache_map);
> +DEFINE_PER_CPU(cpumask_var_t, thread_group_l1_cache_map);
>
> /*
> * On some big-cores system, thread_group_l2_cache_map for each CPU
> * corresponds to the set its siblings within the core that share the
> * L2-cache.
> */
> -static DEFINE_PER_CPU(cpumask_var_t, thread_group_l2_cache_map);
> +DEFINE_PER_CPU(cpumask_var_t, thread_group_l2_cache_map);
>
> /* SMP operations for this machine */
> struct smp_ops_t *smp_ops;
> --
> 2.26.3
>
--
Thanks and Regards
Srikar Dronamraju
