Huang Ying <ying.hu...@intel.com> writes:
> Previously, in hmat_register_target_initiators(), the performance
> attributes are calculated and the corresponding sysfs links and files
> are created too. Which is called during memory onlining.
>
> But now, to calculate the abstract distance of a memory target before
> memory onlining, we need to calculate the performance attributes for
> a memory target without creating sysfs links and files.
>
> To do that, hmat_register_target_initiators() is refactored to make it
> possible to calculate performance attributes separately.
The refactor looks good and I have run the whole series on a system with
some hmat data so:
Reviewed-by: Alistair Popple <apop...@nvidia.com>
Tested-by: Alistair Popple <apop...@nvidia.com>
> Signed-off-by: "Huang, Ying" <ying.hu...@intel.com>
> Cc: Aneesh Kumar K.V <aneesh.ku...@linux.ibm.com>
> Cc: Wei Xu <weix...@google.com>
> Cc: Alistair Popple <apop...@nvidia.com>
> Cc: Dan Williams <dan.j.willi...@intel.com>
> Cc: Dave Hansen <dave.han...@intel.com>
> Cc: Davidlohr Bueso <d...@stgolabs.net>
> Cc: Johannes Weiner <han...@cmpxchg.org>
> Cc: Jonathan Cameron <jonathan.came...@huawei.com>
> Cc: Michal Hocko <mho...@kernel.org>
> Cc: Yang Shi <shy828...@gmail.com>
> Cc: Rafael J Wysocki <rafael.j.wyso...@intel.com>
> ---
> drivers/acpi/numa/hmat.c | 81 +++++++++++++++-------------------------
> 1 file changed, 30 insertions(+), 51 deletions(-)
>
> diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
> index bba268ecd802..2dee0098f1a9 100644
> --- a/drivers/acpi/numa/hmat.c
> +++ b/drivers/acpi/numa/hmat.c
> @@ -582,28 +582,25 @@ static int initiators_to_nodemask(unsigned long
> *p_nodes)
> return 0;
> }
>
> -static void hmat_register_target_initiators(struct memory_target *target)
> +static void hmat_update_target_attrs(struct memory_target *target,
> + unsigned long *p_nodes, int access)
> {
> - static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
> struct memory_initiator *initiator;
> - unsigned int mem_nid, cpu_nid;
> + unsigned int cpu_nid;
> struct memory_locality *loc = NULL;
> u32 best = 0;
> - bool access0done = false;
> int i;
>
> - mem_nid = pxm_to_node(target->memory_pxm);
> + bitmap_zero(p_nodes, MAX_NUMNODES);
> /*
> - * If the Address Range Structure provides a local processor pxm, link
> + * If the Address Range Structure provides a local processor pxm, set
> * only that one. Otherwise, find the best performance attributes and
> - * register all initiators that match.
> + * collect all initiators that match.
> */
> if (target->processor_pxm != PXM_INVAL) {
> cpu_nid = pxm_to_node(target->processor_pxm);
> - register_memory_node_under_compute_node(mem_nid, cpu_nid, 0);
> - access0done = true;
> - if (node_state(cpu_nid, N_CPU)) {
> - register_memory_node_under_compute_node(mem_nid,
> cpu_nid, 1);
> + if (access == 0 || node_state(cpu_nid, N_CPU)) {
> + set_bit(target->processor_pxm, p_nodes);
> return;
> }
> }
> @@ -617,47 +614,10 @@ static void hmat_register_target_initiators(struct
> memory_target *target)
> * We'll also use the sorting to prime the candidate nodes with known
> * initiators.
> */
> - bitmap_zero(p_nodes, MAX_NUMNODES);
> list_sort(NULL, &initiators, initiator_cmp);
> if (initiators_to_nodemask(p_nodes) < 0)
> return;
>
> - if (!access0done) {
> - for (i = WRITE_LATENCY; i <= READ_BANDWIDTH; i++) {
> - loc = localities_types[i];
> - if (!loc)
> - continue;
> -
> - best = 0;
> - list_for_each_entry(initiator, &initiators, node) {
> - u32 value;
> -
> - if (!test_bit(initiator->processor_pxm,
> p_nodes))
> - continue;
> -
> - value = hmat_initiator_perf(target, initiator,
> - loc->hmat_loc);
> - if (hmat_update_best(loc->hmat_loc->data_type,
> value, &best))
> - bitmap_clear(p_nodes, 0,
> initiator->processor_pxm);
> - if (value != best)
> - clear_bit(initiator->processor_pxm,
> p_nodes);
> - }
> - if (best)
> - hmat_update_target_access(target,
> loc->hmat_loc->data_type,
> - best, 0);
> - }
> -
> - for_each_set_bit(i, p_nodes, MAX_NUMNODES) {
> - cpu_nid = pxm_to_node(i);
> - register_memory_node_under_compute_node(mem_nid,
> cpu_nid, 0);
> - }
> - }
> -
> - /* Access 1 ignores Generic Initiators */
> - bitmap_zero(p_nodes, MAX_NUMNODES);
> - if (initiators_to_nodemask(p_nodes) < 0)
> - return;
> -
> for (i = WRITE_LATENCY; i <= READ_BANDWIDTH; i++) {
> loc = localities_types[i];
> if (!loc)
> @@ -667,7 +627,7 @@ static void hmat_register_target_initiators(struct
> memory_target *target)
> list_for_each_entry(initiator, &initiators, node) {
> u32 value;
>
> - if (!initiator->has_cpu) {
> + if (access == 1 && !initiator->has_cpu) {
> clear_bit(initiator->processor_pxm, p_nodes);
> continue;
> }
> @@ -681,14 +641,33 @@ static void hmat_register_target_initiators(struct
> memory_target *target)
> clear_bit(initiator->processor_pxm, p_nodes);
> }
> if (best)
> - hmat_update_target_access(target,
> loc->hmat_loc->data_type, best, 1);
> + hmat_update_target_access(target,
> loc->hmat_loc->data_type, best, access);
> }
> +}
> +
> +static void __hmat_register_target_initiators(struct memory_target *target,
> + unsigned long *p_nodes,
> + int access)
> +{
> + unsigned int mem_nid, cpu_nid;
> + int i;
> +
> + mem_nid = pxm_to_node(target->memory_pxm);
> + hmat_update_target_attrs(target, p_nodes, access);
> for_each_set_bit(i, p_nodes, MAX_NUMNODES) {
> cpu_nid = pxm_to_node(i);
> - register_memory_node_under_compute_node(mem_nid, cpu_nid, 1);
> + register_memory_node_under_compute_node(mem_nid, cpu_nid,
> access);
> }
> }
>
> +static void hmat_register_target_initiators(struct memory_target *target)
> +{
> + static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
> +
> + __hmat_register_target_initiators(target, p_nodes, 0);
> + __hmat_register_target_initiators(target, p_nodes, 1);
> +}
> +
> static void hmat_register_target_cache(struct memory_target *target)
> {
> unsigned mem_nid = pxm_to_node(target->memory_pxm);
