powerpc/smp: Cache CPU to chip lookup

On systems with large CPUs per node, even with the filtered matching of
related CPUs, there can be large number of calls to cpu_to_chip_id for
the same CPU. For example with 4096 vCPU, 1 node QEMU configuration,
with 4 threads per core, system could be see upto 1024 calls to
cpu_to_chip_id() for the same CPU. On a given system, cpu_to_chip_id()
for a given CPU would always return the same. Hence cache the result in
a lookup table for use in subsequent calls.

Since all CPUs sharing the same core will belong to the same chip, the
lookup_table has an entry for one CPU per core.  chip_id_lookup_table is
not being freed and would be used on subsequent CPU online post CPU
offline.

Reported-by: Daniel Henrique Barboza <danielhb413@gmail.com>
Suggested-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Tested-by: Daniel Henrique Barboza <danielhb413@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210415120934.232271-4-srikar@linux.vnet.ibm.com
This commit is contained in:
Srikar Dronamraju 2021-04-15 17:39:34 +05:30 коммит произвёл Michael Ellerman
Родитель 131c82b6a1
Коммит c1e53367da
3 изменённых файлов: 35 добавлений и 6 удалений

Просмотреть файл

@ -31,6 +31,7 @@ extern u32 *cpu_to_phys_id;
extern bool coregroup_enabled; extern bool coregroup_enabled;
extern int cpu_to_chip_id(int cpu); extern int cpu_to_chip_id(int cpu);
extern int *chip_id_lookup_table;
#ifdef CONFIG_SMP #ifdef CONFIG_SMP

Просмотреть файл

@ -65,6 +65,8 @@
#define DBG(fmt...) #define DBG(fmt...)
#endif #endif
int *chip_id_lookup_table;
#ifdef CONFIG_PPC64 #ifdef CONFIG_PPC64
int __initdata iommu_is_off; int __initdata iommu_is_off;
int __initdata iommu_force_on; int __initdata iommu_force_on;
@ -914,13 +916,22 @@ EXPORT_SYMBOL(of_get_ibm_chip_id);
int cpu_to_chip_id(int cpu) int cpu_to_chip_id(int cpu)
{ {
struct device_node *np; struct device_node *np;
int ret = -1, idx;
idx = cpu / threads_per_core;
if (chip_id_lookup_table && chip_id_lookup_table[idx] != -1)
return chip_id_lookup_table[idx];
np = of_get_cpu_node(cpu, NULL); np = of_get_cpu_node(cpu, NULL);
if (!np) if (np) {
return -1; ret = of_get_ibm_chip_id(np);
of_node_put(np); of_node_put(np);
return of_get_ibm_chip_id(np);
if (chip_id_lookup_table)
chip_id_lookup_table[idx] = ret;
}
return ret;
} }
EXPORT_SYMBOL(cpu_to_chip_id); EXPORT_SYMBOL(cpu_to_chip_id);

Просмотреть файл

@ -1073,6 +1073,20 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
cpu_smallcore_mask(boot_cpuid)); cpu_smallcore_mask(boot_cpuid));
} }
if (cpu_to_chip_id(boot_cpuid) != -1) {
int idx = num_possible_cpus() / threads_per_core;
/*
* All threads of a core will all belong to the same core,
* chip_id_lookup_table will have one entry per core.
* Assumption: if boot_cpuid doesn't have a chip-id, then no
* other CPUs, will also not have chip-id.
*/
chip_id_lookup_table = kcalloc(idx, sizeof(int), GFP_KERNEL);
if (chip_id_lookup_table)
memset(chip_id_lookup_table, -1, sizeof(int) * idx);
}
if (smp_ops && smp_ops->probe) if (smp_ops && smp_ops->probe)
smp_ops->probe(); smp_ops->probe();
} }
@ -1468,8 +1482,8 @@ static void add_cpu_to_masks(int cpu)
{ {
struct cpumask *(*submask_fn)(int) = cpu_sibling_mask; struct cpumask *(*submask_fn)(int) = cpu_sibling_mask;
int first_thread = cpu_first_thread_sibling(cpu); int first_thread = cpu_first_thread_sibling(cpu);
int chip_id = cpu_to_chip_id(cpu);
cpumask_var_t mask; cpumask_var_t mask;
int chip_id = -1;
bool ret; bool ret;
int i; int i;
@ -1492,7 +1506,10 @@ static void add_cpu_to_masks(int cpu)
if (has_coregroup_support()) if (has_coregroup_support())
update_coregroup_mask(cpu, &mask); update_coregroup_mask(cpu, &mask);
if (chip_id == -1 || !ret) { if (chip_id_lookup_table && ret)
chip_id = cpu_to_chip_id(cpu);
if (chip_id == -1) {
cpumask_copy(per_cpu(cpu_core_map, cpu), cpu_cpu_mask(cpu)); cpumask_copy(per_cpu(cpu_core_map, cpu), cpu_cpu_mask(cpu));
goto out; goto out;
} }