+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/crash_dump.h>
#include <linux/smp.h>
#include <linux/topology.h>
+#include <linux/pfn.h>
#include <asm/sections.h>
#include <asm/processor.h>
#include <asm/setup.h>
#include <asm/cpu.h>
#include <asm/stackprotector.h>
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
-# define DBG(x...) printk(KERN_DEBUG x)
-#else
-# define DBG(x...)
-#endif
-
DEFINE_PER_CPU(int, cpu_number);
EXPORT_PER_CPU_SYMBOL(cpu_number);
};
EXPORT_SYMBOL(__per_cpu_offset);
-static struct page **pcpu4k_pages __initdata;
-static int pcpu4k_nr_static_pages __initdata;
+/*
+ * On x86_64 symbols referenced from code should be reachable using
+ * 32bit relocations. Reserve space for static percpu variables in
+ * modules so that they are always served from the first chunk which
+ * is located at the percpu segment base. On x86_32, anything can
+ * address anywhere. No need to reserve space in the first chunk.
+ */
+#ifdef CONFIG_X86_64
+#define PERCPU_FIRST_CHUNK_RESERVE PERCPU_MODULE_RESERVE
+#else
+#define PERCPU_FIRST_CHUNK_RESERVE 0
+#endif
+
+#ifdef CONFIG_X86_32
+/**
+ * pcpu_need_numa - determine percpu allocation needs to consider NUMA
+ *
+ * If NUMA is not configured or there is only one NUMA node available,
+ * there is no reason to consider NUMA. This function determines
+ * whether percpu allocation should consider NUMA or not.
+ *
+ * RETURNS:
+ * true if NUMA should be considered; otherwise, false.
+ */
+static bool __init pcpu_need_numa(void)
+{
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+ pg_data_t *last = NULL;
+ unsigned int cpu;
+
+ for_each_possible_cpu(cpu) {
+ int node = early_cpu_to_node(cpu);
+
+ if (node_online(node) && NODE_DATA(node) &&
+ last && last != NODE_DATA(node))
+ return true;
+
+ last = NODE_DATA(node);
+ }
+#endif
+ return false;
+}
+#endif
-static struct page * __init pcpu4k_get_page(unsigned int cpu, int pageno)
+/**
+ * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu
+ * @cpu: cpu to allocate for
+ * @size: size allocation in bytes
+ * @align: alignment
+ *
+ * Allocate @size bytes aligned at @align for cpu @cpu. This wrapper
+ * does the right thing for NUMA regardless of the current
+ * configuration.
+ *
+ * RETURNS:
+ * Pointer to the allocated area on success, NULL on failure.
+ */
+static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size,
+ unsigned long align)
{
- if (pageno < pcpu4k_nr_static_pages)
- return pcpu4k_pages[cpu * pcpu4k_nr_static_pages + pageno];
- return NULL;
+ const unsigned long goal = __pa(MAX_DMA_ADDRESS);
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+ int node = early_cpu_to_node(cpu);
+ void *ptr;
+
+ if (!node_online(node) || !NODE_DATA(node)) {
+ ptr = __alloc_bootmem_nopanic(size, align, goal);
+ pr_info("cpu %d has no node %d or node-local memory\n",
+ cpu, node);
+ pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n",
+ cpu, size, __pa(ptr));
+ } else {
+ ptr = __alloc_bootmem_node_nopanic(NODE_DATA(node),
+ size, align, goal);
+ pr_debug("per cpu data for cpu%d %lu bytes on node%d at %016lx\n",
+ cpu, size, node, __pa(ptr));
+ }
+ return ptr;
+#else
+ return __alloc_bootmem_nopanic(size, align, goal);
+#endif
}
-static void __init pcpu4k_populate_pte(unsigned long addr)
+/*
+ * Helpers for first chunk memory allocation
+ */
+static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
+{
+ return pcpu_alloc_bootmem(cpu, size, align);
+}
+
+static void __init pcpu_fc_free(void *ptr, size_t size)
+{
+#ifdef CONFIG_NO_BOOTMEM
+ u64 start = __pa(ptr);
+ u64 end = start + size;
+ free_early_partial(start, end);
+#else
+ free_bootmem(__pa(ptr), size);
+#endif
+}
+
+static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
+{
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+ if (early_cpu_to_node(from) == early_cpu_to_node(to))
+ return LOCAL_DISTANCE;
+ else
+ return REMOTE_DISTANCE;
+#else
+ return LOCAL_DISTANCE;
+#endif
+}
+
+static void __init pcpup_populate_pte(unsigned long addr)
{
populate_extra_pte(addr);
}
#endif
}
-/*
- * Great future plan:
- * Declare PDA itself and support (irqstack,tss,pgd) as per cpu data.
- * Always point %gs to its beginning
- */
void __init setup_per_cpu_areas(void)
{
- ssize_t size = __per_cpu_end - __per_cpu_start;
- unsigned int nr_cpu_pages = DIV_ROUND_UP(size, PAGE_SIZE);
- static struct page **pages;
- size_t pages_size;
- unsigned int cpu, i, j;
+ unsigned int cpu;
unsigned long delta;
- size_t pcpu_unit_size;
+ int rc;
pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%d nr_node_ids:%d\n",
NR_CPUS, nr_cpumask_bits, nr_cpu_ids, nr_node_ids);
- pr_info("PERCPU: Allocating %zd bytes for static per cpu data\n", size);
-
- pages_size = nr_cpu_pages * num_possible_cpus() * sizeof(pages[0]);
- pages = alloc_bootmem(pages_size);
-
- j = 0;
- for_each_possible_cpu(cpu) {
- void *ptr;
- for (i = 0; i < nr_cpu_pages; i++) {
-#ifndef CONFIG_NEED_MULTIPLE_NODES
- ptr = alloc_bootmem_pages(PAGE_SIZE);
-#else
- int node = early_cpu_to_node(cpu);
-
- if (!node_online(node) || !NODE_DATA(node)) {
- ptr = alloc_bootmem_pages(PAGE_SIZE);
- pr_info("cpu %d has no node %d or node-local "
- "memory\n", cpu, node);
- pr_debug("per cpu data for cpu%d at %016lx\n",
- cpu, __pa(ptr));
- } else {
- ptr = alloc_bootmem_pages_node(NODE_DATA(node),
- PAGE_SIZE);
- pr_debug("per cpu data for cpu%d on node%d "
- "at %016lx\n", cpu, node, __pa(ptr));
- }
+ /*
+ * Allocate percpu area. Embedding allocator is our favorite;
+ * however, on NUMA configurations, it can result in very
+ * sparse unit mapping and vmalloc area isn't spacious enough
+ * on 32bit. Use page in that case.
+ */
+#ifdef CONFIG_X86_32
+ if (pcpu_chosen_fc == PCPU_FC_AUTO && pcpu_need_numa())
+ pcpu_chosen_fc = PCPU_FC_PAGE;
#endif
- memcpy(ptr, __per_cpu_load + i * PAGE_SIZE, PAGE_SIZE);
- pages[j++] = virt_to_page(ptr);
- }
- }
+ rc = -EINVAL;
+ if (pcpu_chosen_fc != PCPU_FC_PAGE) {
+ const size_t atom_size = cpu_has_pse ? PMD_SIZE : PAGE_SIZE;
+ const size_t dyn_size = PERCPU_MODULE_RESERVE +
+ PERCPU_DYNAMIC_RESERVE - PERCPU_FIRST_CHUNK_RESERVE;
- pcpu4k_pages = pages;
- pcpu4k_nr_static_pages = nr_cpu_pages;
- pcpu_unit_size = pcpu_setup_first_chunk(pcpu4k_get_page, size, 0, 0,
- NULL, pcpu4k_populate_pte);
-
- free_bootmem(__pa(pages), pages_size);
+ rc = pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
+ dyn_size, atom_size,
+ pcpu_cpu_distance,
+ pcpu_fc_alloc, pcpu_fc_free);
+ if (rc < 0)
+ pr_warning("%s allocator failed (%d), falling back to page size\n",
+ pcpu_fc_names[pcpu_chosen_fc], rc);
+ }
+ if (rc < 0)
+ rc = pcpu_page_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
+ pcpu_fc_alloc, pcpu_fc_free,
+ pcpup_populate_pte);
+ if (rc < 0)
+ panic("cannot initialize percpu area (err=%d)", rc);
+ /* alrighty, percpu areas up and running */
delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
for_each_possible_cpu(cpu) {
- per_cpu_offset(cpu) = delta + cpu * pcpu_unit_size;
+ per_cpu_offset(cpu) = delta + pcpu_unit_offsets[cpu];
per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
per_cpu(cpu_number, cpu) = cpu;
setup_percpu_segment(cpu);
#endif
#endif
/*
- * Up to this point, the boot CPU has been using .data.init
+ * Up to this point, the boot CPU has been using .init.data
* area. Reload any changed state for the boot CPU.
*/
if (cpu == boot_cpu_id)
switch_to_new_gdt(cpu);
-
- DBG("PERCPU: cpu %4d %p\n", cpu, ptr);
}
/* indicate the early static arrays will soon be gone */
early_per_cpu_ptr(x86_cpu_to_node_map) = NULL;
#endif
+#if defined(CONFIG_X86_64) && defined(CONFIG_NUMA)
+ /*
+ * make sure boot cpu numa_node is right, when boot cpu is on the
+ * node that doesn't have mem installed
+ */
+ set_cpu_numa_node(boot_cpu_id, early_cpu_to_node(boot_cpu_id));
+#endif
+
/* Setup node to cpumask map */
setup_node_to_cpumask_map();