On Fri, 11 Jul 2025 18:36:19 +0000
James Morse <james.morse@arm.com> wrote:
> The MPAM table identifies caches by id. The MPAM driver also wants to know
> the cache level to determine if the platform is of the shape that can be
> managed via resctrl. Cacheinfo has this information, but only for CPUs that
> are online.
>
> Waiting for all CPUs to come online is a problem for platforms where
> CPUs are brought online late by user-space.
>
> Add a helper that walks every possible cache, until it finds the one
> identified by cache-id, then return the level.
>
> acpi_count_levels() expects its levels parameter to be initialised to
> zero as it passes it to acpi_find_cache_level() as starting_level.
> The existing callers do this. Document it.
>
> Signed-off-by: James Morse <james.morse@arm.com>
> Reviewed-by: Sudeep Holla <sudeep.holla@arm.com>
A few suggestions inline. Mostly driven by the number of missing table
puts I've seen in ACPI code. You don't have any missing here but with a
bit of restructuring you can make that easy to see.
> ---
> drivers/acpi/pptt.c | 73 ++++++++++++++++++++++++++++++++++++++++++++
> include/linux/acpi.h | 5 +++
> 2 files changed, 78 insertions(+)
>
> diff --git a/drivers/acpi/pptt.c b/drivers/acpi/pptt.c
> index 13ca2eee3b98..f53748a5df19 100644
> --- a/drivers/acpi/pptt.c
> +++ b/drivers/acpi/pptt.c
> @@ -912,3 +912,76 @@ int find_acpi_cpu_topology_hetero_id(unsigned int cpu)
> return find_acpi_cpu_topology_tag(cpu, PPTT_ABORT_PACKAGE,
> ACPI_PPTT_ACPI_IDENTICAL);
> }
> +
> +/**
> + * find_acpi_cache_level_from_id() - Get the level of the specified cache
> + * @cache_id: The id field of the unified cache
> + *
> + * Determine the level relative to any CPU for the unified cache identified by
> + * cache_id. This allows the property to be found even if the CPUs are offline.
> + *
> + * The returned level can be used to group unified caches that are peers.
> + *
> + * The PPTT table must be rev 3 or later,
> + *
> + * If one CPUs L2 is shared with another as L3, this function will return
> + * an unpredictable value.
> + *
> + * Return: -ENOENT if the PPTT doesn't exist, or the cache cannot be found.
> + * Otherwise returns a value which represents the level of the specified cache.
> + */
> +int find_acpi_cache_level_from_id(u32 cache_id)
> +{
> + u32 acpi_cpu_id;
> + acpi_status status;
> + int level, cpu, num_levels;
> + struct acpi_pptt_cache *cache;
> + struct acpi_table_header *table;
> + struct acpi_pptt_cache_v1 *cache_v1;
> + struct acpi_pptt_processor *cpu_node;
> +
> + status = acpi_get_table(ACPI_SIG_PPTT, 0, &table);
> + if (ACPI_FAILURE(status)) {
> + acpi_pptt_warn_missing();
> + return -ENOENT;
> + }
> +
> + if (table->revision < 3) {
Maybe a unified exit path given all paths need to do
acpi_put_table() and return either error or level.
Or maybe it's time for some cleanup.h magic for acpi tables. I've
been thinking about it for a while and mostly stuck on the name ;)
(simpler suggestion follows)
static struct acpi_table_header *acpi_get_table_ret(char *signature, u32 instance)
{
struct acpi_table_header *table;
int status = acpi_get_table(signature, instance, &table);
if (ACPI_FAILURE(status))
return ERR_PTR(-ENOENT);
return table;
}
DEFINE_FREE(acpi_table, struct acpi_table_header *, if (!IS_ERR(_T)) acpi_put_table(_T))
Finally in here and loads of other places we avoid chance of missing an acpi_put_table
and generally simplify the code a little.
int find_acpi_cache_level_from_id(u32 cache_id)
{
u32 acpi_cpu_id;
acpi_status status;
int level, cpu, num_levels;
struct acpi_pptt_cache *cache;
struct acpi_pptt_cache_v1 *cache_v1;
struct acpi_pptt_processor *cpu_node;
struct acpi_table_header *table __free(acpi_table) =
acpi_get_table_ret(ACPI_SIG_PPTT, 0);
if (IS_ERR(table)
return PTR_ERR(table);
if (table->revision < 3)
return -ENOENT;
/*
* If we found the cache first, we'd still need to walk from each CPU
* to find the level...
*/
for_each_possible_cpu(cpu) {
acpi_cpu_id = get_acpi_id_for_cpu(cpu);
cpu_node = acpi_find_processor_node(table, acpi_cpu_id);
if (!cpu_node)
return -ENOENT;
acpi_count_levels(table, cpu_node, &num_levels, NULL);
/* Start at 1 for L1 */
for (level = 1; level <= num_levels; level++) {
cache = acpi_find_cache_node(table, acpi_cpu_id,
ACPI_PPTT_CACHE_TYPE_UNIFIED,
level, &cpu_node);
if (!cache)
continue;
cache_v1 = ACPI_ADD_PTR(struct acpi_pptt_cache_v1,
cache,
sizeof(struct acpi_pptt_cache));
if (cache->flags & ACPI_PPTT_CACHE_ID_VALID &&
cache_v1->cache_id == cache_id) {
acpi_put_table(table);
return level;
}
}
}
return -ENOENT;
}
A less 'fun' alternative is pull some code out as a helper to make put the get and put
near each other with no conditionals to confuse things.
static int __find_acpi_cache_level_from_id(u32 cache_id, struct acpi_table_header *head);
{
u32 acpi_cpu_id;
int level, cpu, num_levels;
struct acpi_pptt_cache *cache;
struct acpi_pptt_cache_v1 *cache_v1;
struct acpi_pptt_processor *cpu_node;
if (table->revision < 3)
return -ENOENT;
/*
* If we found the cache first, we'd still need to walk from each CPU
* to find the level...
*/
for_each_possible_cpu(cpu) {
acpi_cpu_id = get_acpi_id_for_cpu(cpu);
cpu_node = acpi_find_processor_node(table, acpi_cpu_id);
if (!cpu_node)
return -ENOENT;
acpi_count_levels(table, cpu_node, &num_levels, NULL);
/* Start at 1 for L1 */
for (level = 1; level <= num_levels; level++) {
cache = acpi_find_cache_node(table, acpi_cpu_id,
ACPI_PPTT_CACHE_TYPE_UNIFIED,
level, &cpu_node);
if (!cache)
continue;
cache_v1 = ACPI_ADD_PTR(struct acpi_pptt_cache_v1,
cache,
sizeof(struct acpi_pptt_cache));
if (cache->flags & ACPI_PPTT_CACHE_ID_VALID &&
cache_v1->cache_id == cache_id)
return level;
}
}
return -ENOENT;
}
int find_acpi_cache_level_from_id(u32 cache_id)
{
int ret;
acpi_status status;
struct acpi_table_header *table;
status = acpi_get_table(ACPI_SIG_PPTT, 0, &table);
if (ACPI_FAILURE(status)) {
acpi_pptt_warn_missing();
return -ENOENT;
}
ret = __find_acpi_cache_level_from_id(cache_id, table)
acpi_put_table(table);
return ret;
}
> + acpi_put_table(table);
> + return -ENOENT;
> + }
> +
> + /*
> + * If we found the cache first, we'd still need to walk from each CPU
> + * to find the level...
> + */
> + for_each_possible_cpu(cpu) {
> + acpi_cpu_id = get_acpi_id_for_cpu(cpu);
> + cpu_node = acpi_find_processor_node(table, acpi_cpu_id);
> + if (!cpu_node)
> + break;
> + acpi_count_levels(table, cpu_node, &num_levels, NULL);
> +
> + /* Start at 1 for L1 */
> + for (level = 1; level <= num_levels; level++) {
> + cache = acpi_find_cache_node(table, acpi_cpu_id,
> + ACPI_PPTT_CACHE_TYPE_UNIFIED,
> + level, &cpu_node);
> + if (!cache)
> + continue;
> +
> + cache_v1 = ACPI_ADD_PTR(struct acpi_pptt_cache_v1,
> + cache,
> + sizeof(struct acpi_pptt_cache));
> +
> + if (cache->flags & ACPI_PPTT_CACHE_ID_VALID &&
> + cache_v1->cache_id == cache_id) {
> + acpi_put_table(table);
> + return level;
> + }
> + }
> + }
> +
> + acpi_put_table(table);
> + return -ENOENT;
> +}
> diff --git a/include/linux/acpi.h b/include/linux/acpi.h
> index 8c3165c2b083..82947f6d2a43 100644
> --- a/include/linux/acpi.h
> +++ b/include/linux/acpi.h
> @@ -1542,6 +1542,7 @@ int find_acpi_cpu_topology_cluster(unsigned int cpu);
> int find_acpi_cpu_topology_package(unsigned int cpu);
> int find_acpi_cpu_topology_hetero_id(unsigned int cpu);
> int acpi_pptt_get_cpus_from_container(u32 acpi_cpu_id, cpumask_t *cpus);
> +int find_acpi_cache_level_from_id(u32 cache_id);
> #else
> static inline int acpi_pptt_cpu_is_thread(unsigned int cpu)
> {
> @@ -1568,6 +1569,10 @@ static inline int acpi_pptt_get_cpus_from_container(u32 acpi_cpu_id,
> {
> return -EINVAL;
> }
> +static inline int find_acpi_cache_level_from_id(u32 cache_id)
> +{
> + return -EINVAL;
> +}
> #endif
>
> void acpi_arch_init(void);