diff options
Diffstat (limited to 'arch/powerpc/mm')
| -rw-r--r-- | arch/powerpc/mm/mem.c | 2 | ||||
| -rw-r--r-- | arch/powerpc/mm/numa.c | 96 | ||||
| -rw-r--r-- | arch/powerpc/mm/pgtable.c | 1 | ||||
| -rw-r--r-- | arch/powerpc/mm/pgtable_64.c | 1 | ||||
| -rw-r--r-- | arch/powerpc/mm/tlb_hash64.c | 1 |
5 files changed, 92 insertions, 9 deletions
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 94448cd4b444..b1c5734bc2ce 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -513,7 +513,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, * System memory should not be in /proc/iomem but various tools expect it * (eg kdump). */ -static int add_system_ram_resources(void) +static int __init add_system_ram_resources(void) { struct memblock_region *reg; diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 078d3e00a616..4f50c6a9e68f 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -31,6 +31,8 @@ #include <asm/sparsemem.h> #include <asm/prom.h> #include <asm/smp.h> +#include <asm/cputhreads.h> +#include <asm/topology.h> #include <asm/firmware.h> #include <asm/paca.h> #include <asm/hvcall.h> @@ -152,9 +154,22 @@ static void __init get_node_active_region(unsigned long pfn, } } -static void map_cpu_to_node(int cpu, int node) +static void reset_numa_cpu_lookup_table(void) +{ + unsigned int cpu; + + for_each_possible_cpu(cpu) + numa_cpu_lookup_table[cpu] = -1; +} + +static void update_numa_cpu_lookup_table(unsigned int cpu, int node) { numa_cpu_lookup_table[cpu] = node; +} + +static void map_cpu_to_node(int cpu, int node) +{ + update_numa_cpu_lookup_table(cpu, node); dbg("adding cpu %d to node %d\n", cpu, node); @@ -522,11 +537,24 @@ static int of_drconf_to_nid_single(struct of_drconf_cell *drmem, */ static int numa_setup_cpu(unsigned long lcpu) { - int nid = 0; - struct device_node *cpu = of_get_cpu_node(lcpu, NULL); + int nid; + struct device_node *cpu; + + /* + * If a valid cpu-to-node mapping is already available, use it + * directly instead of querying the firmware, since it represents + * the most recent mapping notified to us by the platform (eg: VPHN). + */ + if ((nid = numa_cpu_lookup_table[lcpu]) >= 0) { + map_cpu_to_node(lcpu, nid); + return nid; + } + + cpu = of_get_cpu_node(lcpu, NULL); if (!cpu) { WARN_ON(1); + nid = 0; goto out; } @@ -542,16 +570,38 @@ out: return nid; } +static void verify_cpu_node_mapping(int cpu, int node) +{ + int base, sibling, i; + + /* Verify that all the threads in the core belong to the same node */ + base = cpu_first_thread_sibling(cpu); + + for (i = 0; i < threads_per_core; i++) { + sibling = base + i; + + if (sibling == cpu || cpu_is_offline(sibling)) + continue; + + if (cpu_to_node(sibling) != node) { + WARN(1, "CPU thread siblings %d and %d don't belong" + " to the same node!\n", cpu, sibling); + break; + } + } +} + static int cpu_numa_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned long lcpu = (unsigned long)hcpu; - int ret = NOTIFY_DONE; + int ret = NOTIFY_DONE, nid; switch (action) { case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: - numa_setup_cpu(lcpu); + nid = numa_setup_cpu(lcpu); + verify_cpu_node_mapping((int)lcpu, nid); ret = NOTIFY_OK; break; #ifdef CONFIG_HOTPLUG_CPU @@ -1067,6 +1117,7 @@ void __init do_init_bootmem(void) */ setup_node_to_cpumask_map(); + reset_numa_cpu_lookup_table(); register_cpu_notifier(&ppc64_numa_nb); cpu_numa_callback(&ppc64_numa_nb, CPU_UP_PREPARE, (void *)(unsigned long)boot_cpuid); @@ -1445,6 +1496,33 @@ static int update_cpu_topology(void *data) return 0; } +static int update_lookup_table(void *data) +{ + struct topology_update_data *update; + + if (!data) + return -EINVAL; + + /* + * Upon topology update, the numa-cpu lookup table needs to be updated + * for all threads in the core, including offline CPUs, to ensure that + * future hotplug operations respect the cpu-to-node associativity + * properly. + */ + for (update = data; update; update = update->next) { + int nid, base, j; + + nid = update->new_nid; + base = cpu_first_thread_sibling(update->cpu); + + for (j = 0; j < threads_per_core; j++) { + update_numa_cpu_lookup_table(base + j, nid); + } + } + + return 0; +} + /* * Update the node maps and sysfs entries for each cpu whose home node * has changed. Returns 1 when the topology has changed, and 0 otherwise. @@ -1513,6 +1591,14 @@ int arch_update_cpu_topology(void) stop_machine(update_cpu_topology, &updates[0], &updated_cpus); + /* + * Update the numa-cpu lookup table with the new mappings, even for + * offline CPUs. It is best to perform this update from the stop- + * machine context. + */ + stop_machine(update_lookup_table, &updates[0], + cpumask_of(raw_smp_processor_id())); + for (ud = &updates[0]; ud; ud = ud->next) { unregister_cpu_under_node(ud->cpu, ud->old_nid); register_cpu_under_node(ud->cpu, ud->new_nid); diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index ad90429bbd8b..c695943a513c 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -24,7 +24,6 @@ #include <linux/kernel.h> #include <linux/gfp.h> #include <linux/mm.h> -#include <linux/init.h> #include <linux/percpu.h> #include <linux/hardirq.h> #include <linux/hugetlb.h> diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 755138218e04..65b7b65e8708 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -33,7 +33,6 @@ #include <linux/swap.h> #include <linux/stddef.h> #include <linux/vmalloc.h> -#include <linux/init.h> #include <linux/bootmem.h> #include <linux/memblock.h> #include <linux/slab.h> diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c index 36e44b4260eb..c99f6510a0b2 100644 --- a/arch/powerpc/mm/tlb_hash64.c +++ b/arch/powerpc/mm/tlb_hash64.c @@ -23,7 +23,6 @@ #include <linux/kernel.h> #include <linux/mm.h> -#include <linux/init.h> #include <linux/percpu.h> #include <linux/hardirq.h> #include <asm/pgalloc.h> |