From 41bd26d67c41e325c6b9e56aadfe9dad8af9a565 Mon Sep 17 00:00:00 2001 From: "holt@sgi.com" Date: Thu, 3 Apr 2008 15:17:12 -0500 Subject: [PATCH 1/2] [IA64] Correct pernodesize calculation. A simple fix. The existing pernodesize reservation is not taking into account a second array of pg_data_t structures. This is normally not important because the PAGE_ALIGN macro reserves adequate space. I made the compute_pernodesize steps in the same order as the fill_pernode steps to make the correlation more clear. Signed-off-by: Robin Holt Signed-off-by: Tony Luck --- arch/ia64/mm/discontig.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index ee5e68b2af94..06c540a29467 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -124,6 +124,7 @@ static unsigned long __meminit compute_pernodesize(int node) pernodesize += node * L1_CACHE_BYTES; pernodesize += L1_CACHE_ALIGN(sizeof(pg_data_t)); pernodesize += L1_CACHE_ALIGN(sizeof(struct ia64_node_data)); + pernodesize += L1_CACHE_ALIGN(sizeof(pg_data_t)); pernodesize = PAGE_ALIGN(pernodesize); return pernodesize; } From 2c6e6db41f01b6b4eb98809350827c9678996698 Mon Sep 17 00:00:00 2001 From: "holt@sgi.com" Date: Thu, 3 Apr 2008 15:17:13 -0500 Subject: [PATCH 2/2] [IA64] Minimize per_cpu reservations. This attached patch significantly shrinks boot memory allocation on ia64. It does this by not allocating per_cpu areas for cpus that can never exist. In the case where acpi does not have any numa node description of the cpus, I defaulted to assigning the first 32 round-robin on the known nodes.. For the !CONFIG_ACPI I used for_each_possible_cpu(). Signed-off-by: Robin Holt Signed-off-by: Tony Luck --- arch/ia64/kernel/acpi.c | 4 +++- arch/ia64/kernel/numa.c | 2 +- arch/ia64/kernel/setup.c | 2 ++ arch/ia64/mm/discontig.c | 12 ++++-------- arch/ia64/mm/numa.c | 4 +++- include/asm-ia64/acpi.h | 33 +++++++++++++++++++++++++++++++++ include/asm-ia64/numa.h | 2 ++ 7 files changed, 48 insertions(+), 11 deletions(-) diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index 78f28d825f30..c7467f863c7a 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -423,6 +423,7 @@ static u32 __devinitdata pxm_flag[PXM_FLAG_LEN]; #define pxm_bit_set(bit) (set_bit(bit,(void *)pxm_flag)) #define pxm_bit_test(bit) (test_bit(bit,(void *)pxm_flag)) static struct acpi_table_slit __initdata *slit_table; +cpumask_t early_cpu_possible_map = CPU_MASK_NONE; static int get_processor_proximity_domain(struct acpi_srat_cpu_affinity *pa) { @@ -482,6 +483,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) (pa->apic_id << 8) | (pa->local_sapic_eid); /* nid should be overridden as logical node id later */ node_cpuid[srat_num_cpus].nid = pxm; + cpu_set(srat_num_cpus, early_cpu_possible_map); srat_num_cpus++; } @@ -559,7 +561,7 @@ void __init acpi_numa_arch_fixup(void) } /* set logical node id in cpu structure */ - for (i = 0; i < srat_num_cpus; i++) + for_each_possible_early_cpu(i) node_cpuid[i].nid = pxm_to_node(node_cpuid[i].nid); printk(KERN_INFO "Number of logical nodes in system = %d\n", diff --git a/arch/ia64/kernel/numa.c b/arch/ia64/kernel/numa.c index a78b45f5fe2f..c93420c97409 100644 --- a/arch/ia64/kernel/numa.c +++ b/arch/ia64/kernel/numa.c @@ -73,7 +73,7 @@ void __init build_cpu_to_node_map(void) for(node=0; node < MAX_NUMNODES; node++) cpus_clear(node_to_cpu_mask[node]); - for(cpu = 0; cpu < NR_CPUS; ++cpu) { + for_each_possible_early_cpu(cpu) { node = -1; for (i = 0; i < NR_CPUS; ++i) if (cpu_physical_id(cpu) == node_cpuid[i].phys_id) { diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 4aa9eaea76c3..6206541f9e87 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -493,6 +493,8 @@ setup_arch (char **cmdline_p) acpi_table_init(); # ifdef CONFIG_ACPI_NUMA acpi_numa_init(); + per_cpu_scan_finalize((cpus_weight(early_cpu_possible_map) == 0 ? + 32 : cpus_weight(early_cpu_possible_map)), additional_cpus); # endif #else # ifdef CONFIG_SMP diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index 06c540a29467..6136a4c6df11 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -104,7 +104,7 @@ static int __meminit early_nr_cpus_node(int node) { int cpu, n = 0; - for (cpu = 0; cpu < NR_CPUS; cpu++) + for_each_possible_early_cpu(cpu) if (node == node_cpuid[cpu].nid) n++; @@ -143,7 +143,7 @@ static void *per_cpu_node_setup(void *cpu_data, int node) #ifdef CONFIG_SMP int cpu; - for (cpu = 0; cpu < NR_CPUS; cpu++) { + for_each_possible_early_cpu(cpu) { if (node == node_cpuid[cpu].nid) { memcpy(__va(cpu_data), __phys_per_cpu_start, __per_cpu_end - __per_cpu_start); @@ -346,7 +346,7 @@ static void __init initialize_pernode_data(void) #ifdef CONFIG_SMP /* Set the node_data pointer for each per-cpu struct */ - for (cpu = 0; cpu < NR_CPUS; cpu++) { + for_each_possible_early_cpu(cpu) { node = node_cpuid[cpu].nid; per_cpu(cpu_info, cpu).node_data = mem_data[node].node_data; } @@ -494,13 +494,9 @@ void __cpuinit *per_cpu_init(void) int cpu; static int first_time = 1; - - if (smp_processor_id() != 0) - return __per_cpu_start + __per_cpu_offset[smp_processor_id()]; - if (first_time) { first_time = 0; - for (cpu = 0; cpu < NR_CPUS; cpu++) + for_each_possible_early_cpu(cpu) per_cpu(local_per_cpu_offset, cpu) = __per_cpu_offset[cpu]; } diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c index 7807fc5c0422..b73bf1838e57 100644 --- a/arch/ia64/mm/numa.c +++ b/arch/ia64/mm/numa.c @@ -27,7 +27,9 @@ */ int num_node_memblks; struct node_memblk_s node_memblk[NR_NODE_MEMBLKS]; -struct node_cpuid_s node_cpuid[NR_CPUS]; +struct node_cpuid_s node_cpuid[NR_CPUS] = + { [0 ... NR_CPUS-1] = { .phys_id = 0, .nid = NUMA_NO_NODE } }; + /* * This is a matrix with "distances" between nodes, they should be * proportional to the memory access latency ratios. diff --git a/include/asm-ia64/acpi.h b/include/asm-ia64/acpi.h index cd1cc39b5599..fcfad326f4c7 100644 --- a/include/asm-ia64/acpi.h +++ b/include/asm-ia64/acpi.h @@ -35,6 +35,7 @@ #include #include #include +#include #define COMPILER_DEPENDENT_INT64 long #define COMPILER_DEPENDENT_UINT64 unsigned long @@ -115,7 +116,11 @@ extern unsigned int is_cpu_cpei_target(unsigned int cpu); extern void set_cpei_target_cpu(unsigned int cpu); extern unsigned int get_cpei_target_cpu(void); extern void prefill_possible_map(void); +#ifdef CONFIG_ACPI_HOTPLUG_CPU extern int additional_cpus; +#else +#define additional_cpus 0 +#endif #ifdef CONFIG_ACPI_NUMA #if MAX_NUMNODES > 256 @@ -129,6 +134,34 @@ extern int __initdata nid_to_pxm_map[MAX_NUMNODES]; #define acpi_unlazy_tlb(x) +#ifdef CONFIG_ACPI_NUMA +extern cpumask_t early_cpu_possible_map; +#define for_each_possible_early_cpu(cpu) \ + for_each_cpu_mask((cpu), early_cpu_possible_map) + +static inline void per_cpu_scan_finalize(int min_cpus, int reserve_cpus) +{ + int low_cpu, high_cpu; + int cpu; + int next_nid = 0; + + low_cpu = cpus_weight(early_cpu_possible_map); + + high_cpu = max(low_cpu, min_cpus); + high_cpu = min(high_cpu + reserve_cpus, NR_CPUS); + + for (cpu = low_cpu; cpu < high_cpu; cpu++) { + cpu_set(cpu, early_cpu_possible_map); + if (node_cpuid[cpu].nid == NUMA_NO_NODE) { + node_cpuid[cpu].nid = next_nid; + next_nid++; + if (next_nid >= num_online_nodes()) + next_nid = 0; + } + } +} +#endif /* CONFIG_ACPI_NUMA */ + #endif /*__KERNEL__*/ #endif /*_ASM_ACPI_H*/ diff --git a/include/asm-ia64/numa.h b/include/asm-ia64/numa.h index 6a8a27cfae3e..3499ff57bf42 100644 --- a/include/asm-ia64/numa.h +++ b/include/asm-ia64/numa.h @@ -22,6 +22,8 @@ #include +#define NUMA_NO_NODE -1 + extern u16 cpu_to_node_map[NR_CPUS] __cacheline_aligned; extern cpumask_t node_to_cpu_mask[MAX_NUMNODES] __cacheline_aligned; extern pg_data_t *pgdat_list[MAX_NUMNODES];