From: Srikar Dronamraju srikar@linux.vnet.ibm.com
[ Upstream commit c47f892d7aa62765bf0689073f75990b4517a4cf ]
Daniel reported that with Commit 4ca234a9cbd7 ("powerpc/smp: Stop updating cpu_core_mask") QEMU was unable to set single NUMA node SMP topologies such as: -smp 8,maxcpus=8,cores=2,threads=2,sockets=2 i.e he expected 2 sockets in one NUMA node.
The above commit helped to reduce boot time on Large Systems for example 4096 vCPU single socket QEMU instance. PAPR is silent on having more than one socket within a NUMA node.
cpu_core_mask and cpu_cpu_mask for any CPU would be same unless the number of sockets is different from the number of NUMA nodes.
One option is to reintroduce cpu_core_mask but use a slightly different method to arrive at the cpu_core_mask. Previously each CPU's chip-id would be compared with all other CPU's chip-id to verify if both the CPUs were related at the chip level. Now if a CPU 'A' is found related / (unrelated) to another CPU 'B', all the thread siblings of 'A' and thread siblings of 'B' are automatically marked as related / (unrelated).
Also if a platform doesn't support ibm,chip-id property, i.e its cpu_to_chip_id returns -1, cpu_core_map holds a copy of cpu_cpu_mask().
Fixes: 4ca234a9cbd7 ("powerpc/smp: Stop updating cpu_core_mask") Reported-by: Daniel Henrique Barboza danielhb413@gmail.com 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/20210415120934.232271-2-srikar@linux.vnet.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/include/asm/smp.h | 5 +++++ arch/powerpc/kernel/smp.c | 39 ++++++++++++++++++++++++++++------ 2 files changed, 37 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index c4e2d53acd2b..15144aac2f70 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -121,6 +121,11 @@ static inline struct cpumask *cpu_sibling_mask(int cpu) return per_cpu(cpu_sibling_map, cpu); }
+static inline struct cpumask *cpu_core_mask(int cpu) +{ + return per_cpu(cpu_core_map, cpu); +} + static inline struct cpumask *cpu_l2_cache_mask(int cpu) { return per_cpu(cpu_l2_cache_map, cpu); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 9e2246e80efd..d1bc51a128b2 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1056,17 +1056,12 @@ void __init smp_prepare_cpus(unsigned int max_cpus) local_memory_node(numa_cpu_lookup_table[cpu])); } #endif - /* - * cpu_core_map is now more updated and exists only since - * its been exported for long. It only will have a snapshot - * of cpu_cpu_mask. - */ - cpumask_copy(per_cpu(cpu_core_map, cpu), cpu_cpu_mask(cpu)); }
/* Init the cpumasks so the boot CPU is related to itself */ cpumask_set_cpu(boot_cpuid, cpu_sibling_mask(boot_cpuid)); cpumask_set_cpu(boot_cpuid, cpu_l2_cache_mask(boot_cpuid)); + cpumask_set_cpu(boot_cpuid, cpu_core_mask(boot_cpuid));
if (has_coregroup_support()) cpumask_set_cpu(boot_cpuid, cpu_coregroup_mask(boot_cpuid)); @@ -1407,6 +1402,9 @@ static void remove_cpu_from_masks(int cpu) set_cpus_unrelated(cpu, i, cpu_smallcore_mask); }
+ for_each_cpu(i, cpu_core_mask(cpu)) + set_cpus_unrelated(cpu, i, cpu_core_mask); + if (has_coregroup_support()) { for_each_cpu(i, cpu_coregroup_mask(cpu)) set_cpus_unrelated(cpu, i, cpu_coregroup_mask); @@ -1467,8 +1465,11 @@ static void update_coregroup_mask(int cpu, cpumask_var_t *mask)
static void add_cpu_to_masks(int cpu) { + struct cpumask *(*submask_fn)(int) = cpu_sibling_mask; int first_thread = cpu_first_thread_sibling(cpu); + int chip_id = cpu_to_chip_id(cpu); cpumask_var_t mask; + bool ret; int i;
/* @@ -1484,12 +1485,36 @@ static void add_cpu_to_masks(int cpu) add_cpu_to_smallcore_masks(cpu);
/* In CPU-hotplug path, hence use GFP_ATOMIC */ - alloc_cpumask_var_node(&mask, GFP_ATOMIC, cpu_to_node(cpu)); + ret = alloc_cpumask_var_node(&mask, GFP_ATOMIC, cpu_to_node(cpu)); update_mask_by_l2(cpu, &mask);
if (has_coregroup_support()) update_coregroup_mask(cpu, &mask);
+ if (chip_id == -1 || !ret) { + cpumask_copy(per_cpu(cpu_core_map, cpu), cpu_cpu_mask(cpu)); + goto out; + } + + if (shared_caches) + submask_fn = cpu_l2_cache_mask; + + /* Update core_mask with all the CPUs that are part of submask */ + or_cpumasks_related(cpu, cpu, submask_fn, cpu_core_mask); + + /* Skip all CPUs already part of current CPU core mask */ + cpumask_andnot(mask, cpu_online_mask, cpu_core_mask(cpu)); + + for_each_cpu(i, mask) { + if (chip_id == cpu_to_chip_id(i)) { + or_cpumasks_related(cpu, i, submask_fn, cpu_core_mask); + cpumask_andnot(mask, mask, submask_fn(i)); + } else { + cpumask_andnot(mask, mask, cpu_core_mask(i)); + } + } + +out: free_cpumask_var(mask); }