summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--arch/x86/Kconfig2
-rw-r--r--arch/x86/Kconfig.debug2
-rw-r--r--arch/x86/kernel/apic_32.c9
-rw-r--r--arch/x86/kernel/apic_64.c11
-rw-r--r--arch/x86/kernel/setup.c96
-rw-r--r--arch/x86/kernel/setup_32.c24
-rw-r--r--arch/x86/kernel/setup_64.c9
-rw-r--r--arch/x86/kernel/smpboot.c20
-rw-r--r--arch/x86/mm/numa_64.c43
-rw-r--r--arch/x86/mm/srat_64.c2
-rw-r--r--drivers/base/topology.c25
-rw-r--r--include/asm-x86/numa_64.h19
-rw-r--r--include/asm-x86/percpu.h46
-rw-r--r--include/asm-x86/smp.h15
-rw-r--r--include/asm-x86/topology.h143
15 files changed, 270 insertions, 196 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 2e325521e5e..4469a0db1ae 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -121,7 +121,7 @@ config ARCH_HAS_CACHE_LINE_SIZE
def_bool y
config HAVE_SETUP_PER_CPU_AREA
- def_bool X86_64 || (X86_SMP && !X86_VOYAGER)
+ def_bool X86_64_SMP || (X86_SMP && !X86_VOYAGER)
config HAVE_CPUMASK_OF_CPU_MAP
def_bool X86_64_SMP
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 18363374d51..24ca95a0ba5 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -60,7 +60,7 @@ config DEBUG_PAGEALLOC
config DEBUG_PER_CPU_MAPS
bool "Debug access to per_cpu maps"
depends on DEBUG_KERNEL
- depends on X86_64_SMP
+ depends on X86_SMP
default n
help
Say Y to verify that the per_cpu map being accessed has
diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c
index 4b99b1bdeb6..f17c1c1bc38 100644
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic_32.c
@@ -52,9 +52,6 @@
unsigned long mp_lapic_addr;
-DEFINE_PER_CPU(u16, x86_bios_cpu_apicid) = BAD_APICID;
-EXPORT_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
-
/*
* Knob to control our willingness to enable the local APIC.
*
@@ -1534,9 +1531,9 @@ void __cpuinit generic_processor_info(int apicid, int version)
}
#ifdef CONFIG_SMP
/* are we being called early in kernel startup? */
- if (x86_cpu_to_apicid_early_ptr) {
- u16 *cpu_to_apicid = x86_cpu_to_apicid_early_ptr;
- u16 *bios_cpu_apicid = x86_bios_cpu_apicid_early_ptr;
+ if (early_per_cpu_ptr(x86_cpu_to_apicid)) {
+ u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
+ u16 *bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
cpu_to_apicid[cpu] = apicid;
bios_cpu_apicid[cpu] = apicid;
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 0633cfd0dc2..4fd21f7d698 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -87,9 +87,6 @@ static unsigned long apic_phys;
unsigned long mp_lapic_addr;
-DEFINE_PER_CPU(u16, x86_bios_cpu_apicid) = BAD_APICID;
-EXPORT_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
-
unsigned int __cpuinitdata maxcpus = NR_CPUS;
/*
* Get the LAPIC version
@@ -1091,9 +1088,9 @@ void __cpuinit generic_processor_info(int apicid, int version)
cpu = 0;
}
/* are we being called early in kernel startup? */
- if (x86_cpu_to_apicid_early_ptr) {
- u16 *cpu_to_apicid = x86_cpu_to_apicid_early_ptr;
- u16 *bios_cpu_apicid = x86_bios_cpu_apicid_early_ptr;
+ if (early_per_cpu_ptr(x86_cpu_to_apicid)) {
+ u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
+ u16 *bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
cpu_to_apicid[cpu] = apicid;
bios_cpu_apicid[cpu] = apicid;
@@ -1269,7 +1266,7 @@ __cpuinit int apic_is_clustered_box(void)
if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && !is_vsmp_box())
return 0;
- bios_cpu_apicid = x86_bios_cpu_apicid_early_ptr;
+ bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
bitmap_zero(clustermap, NUM_APIC_CLUSTERS);
for (i = 0; i < NR_CPUS; i++) {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 6f80b852a19..03caa8e4351 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -19,13 +19,23 @@ unsigned disabled_cpus __cpuinitdata;
unsigned int boot_cpu_physical_apicid = -1U;
EXPORT_SYMBOL(boot_cpu_physical_apicid);
-DEFINE_PER_CPU(u16, x86_cpu_to_apicid) = BAD_APICID;
-EXPORT_PER_CPU_SYMBOL(x86_cpu_to_apicid);
-
/* Bitmask of physically existing CPUs */
physid_mask_t phys_cpu_present_map;
#endif
+/* map cpu index to physical APIC ID */
+DEFINE_EARLY_PER_CPU(u16, x86_cpu_to_apicid, BAD_APICID);
+DEFINE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid, BAD_APICID);
+EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
+EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
+
+#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+#define X86_64_NUMA 1
+
+DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
+EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);
+#endif
+
#if defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) && defined(CONFIG_X86_SMP)
/*
* Copy data used in early init routines from the initial arrays to the
@@ -37,20 +47,21 @@ static void __init setup_per_cpu_maps(void)
int cpu;
for_each_possible_cpu(cpu) {
- per_cpu(x86_cpu_to_apicid, cpu) = x86_cpu_to_apicid_init[cpu];
+ per_cpu(x86_cpu_to_apicid, cpu) =
+ early_per_cpu_map(x86_cpu_to_apicid, cpu);
per_cpu(x86_bios_cpu_apicid, cpu) =
- x86_bios_cpu_apicid_init[cpu];
-#ifdef CONFIG_NUMA
+ early_per_cpu_map(x86_bios_cpu_apicid, cpu);
+#ifdef X86_64_NUMA
per_cpu(x86_cpu_to_node_map, cpu) =
- x86_cpu_to_node_map_init[cpu];
+ early_per_cpu_map(x86_cpu_to_node_map, cpu);
#endif
}
/* indicate the early static arrays will soon be gone */
- x86_cpu_to_apicid_early_ptr = NULL;
- x86_bios_cpu_apicid_early_ptr = NULL;
-#ifdef CONFIG_NUMA
- x86_cpu_to_node_map_early_ptr = NULL;
+ early_per_cpu_ptr(x86_cpu_to_apicid) = NULL;
+ early_per_cpu_ptr(x86_bios_cpu_apicid) = NULL;
+#ifdef X86_64_NUMA
+ early_per_cpu_ptr(x86_cpu_to_node_map) = NULL;
#endif
}
@@ -109,7 +120,8 @@ void __init setup_per_cpu_areas(void)
if (!node_online(node) || !NODE_DATA(node)) {
ptr = alloc_bootmem_pages(size);
printk(KERN_INFO
- "cpu %d has no node or node-local memory\n", i);
+ "cpu %d has no node %d or node-local memory\n",
+ i, node);
}
else
ptr = alloc_bootmem_pages_node(NODE_DATA(node), size);
@@ -137,3 +149,63 @@ void __init setup_per_cpu_areas(void)
}
#endif
+
+#ifdef X86_64_NUMA
+void __cpuinit numa_set_node(int cpu, int node)
+{
+ int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);
+
+ if (cpu_to_node_map)
+ cpu_to_node_map[cpu] = node;
+
+ else if (per_cpu_offset(cpu))
+ per_cpu(x86_cpu_to_node_map, cpu) = node;
+
+ else
+ Dprintk(KERN_INFO "Setting node for non-present cpu %d\n", cpu);
+}
+
+void __cpuinit numa_clear_node(int cpu)
+{
+ numa_set_node(cpu, NUMA_NO_NODE);
+}
+
+void __cpuinit numa_add_cpu(int cpu)
+{
+ cpu_set(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+}
+
+void __cpuinit numa_remove_cpu(int cpu)
+{
+ cpu_clear(cpu, node_to_cpumask_map[cpu_to_node(cpu)]);
+}
+#endif /* CONFIG_NUMA */
+
+#if defined(CONFIG_DEBUG_PER_CPU_MAPS) && defined(CONFIG_X86_64)
+
+int cpu_to_node(int cpu)
+{
+ if (early_per_cpu_ptr(x86_cpu_to_node_map)) {
+ printk(KERN_WARNING
+ "cpu_to_node(%d): usage too early!\n", cpu);
+ dump_stack();
+ return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
+ }
+ return per_cpu(x86_cpu_to_node_map, cpu);
+}
+EXPORT_SYMBOL(cpu_to_node);
+
+int early_cpu_to_node(int cpu)
+{
+ if (early_per_cpu_ptr(x86_cpu_to_node_map))
+ return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
+
+ if (!per_cpu_offset(cpu)) {
+ printk(KERN_WARNING
+ "early_cpu_to_node(%d): no per_cpu area!\n", cpu);
+ dump_stack();
+ return NUMA_NO_NODE;
+ }
+ return per_cpu(x86_cpu_to_node_map, cpu);
+}
+#endif
diff --git a/arch/x86/kernel/setup_32.c b/arch/x86/kernel/setup_32.c
index 5a2f8e06388..ccd5f5cdbbe 100644
--- a/arch/x86/kernel/setup_32.c
+++ b/arch/x86/kernel/setup_32.c
@@ -737,18 +737,6 @@ char * __init __attribute__((weak)) memory_setup(void)
return machine_specific_memory_setup();
}
-#ifdef CONFIG_NUMA
-/*
- * In the golden day, when everything among i386 and x86_64 will be
- * integrated, this will not live here
- */
-void *x86_cpu_to_node_map_early_ptr;
-int x86_cpu_to_node_map_init[NR_CPUS] = {
- [0 ... NR_CPUS-1] = NUMA_NO_NODE
-};
-DEFINE_PER_CPU(int, x86_cpu_to_node_map) = NUMA_NO_NODE;
-#endif
-
/*
* Determine if we were loaded by an EFI loader. If so, then we have also been
* passed the efi memmap, systab, etc., so we should use these data structures
@@ -887,18 +875,6 @@ void __init setup_arch(char **cmdline_p)
io_delay_init();
-#ifdef CONFIG_X86_SMP
- /*
- * setup to use the early static init tables during kernel startup
- * X86_SMP will exclude sub-arches that don't deal well with it.
- */
- x86_cpu_to_apicid_early_ptr = (void *)x86_cpu_to_apicid_init;
- x86_bios_cpu_apicid_early_ptr = (void *)x86_bios_cpu_apicid_init;
-#ifdef CONFIG_NUMA
- x86_cpu_to_node_map_early_ptr = (void *)x86_cpu_to_node_map_init;
-#endif
-#endif
-
#ifdef CONFIG_X86_GENERICARCH
generic_apic_probe();
#endif
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index 6dff1286ad8..e8df64fad54 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -406,15 +406,6 @@ void __init setup_arch(char **cmdline_p)
kvmclock_init();
#endif
-#ifdef CONFIG_SMP
- /* setup to use the early static init tables during kernel startup */
- x86_cpu_to_apicid_early_ptr = (void *)x86_cpu_to_apicid_init;
- x86_bios_cpu_apicid_early_ptr = (void *)x86_bios_cpu_apicid_init;
-#ifdef CONFIG_NUMA
- x86_cpu_to_node_map_early_ptr = (void *)x86_cpu_to_node_map_init;
-#endif
-#endif
-
#ifdef CONFIG_ACPI
/*
* Initialize the ACPI boot-time table parser (gets the RSDP and SDT).
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 3e1cecedde4..036604d3dae 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -68,22 +68,6 @@
#include <mach_wakecpu.h>
#include <smpboot_hooks.h>
-/*
- * FIXME: For x86_64, those are defined in other files. But moving them here,
- * would make the setup areas dependent on smp, which is a loss. When we
- * integrate apic between arches, we can probably do a better job, but
- * right now, they'll stay here -- glommer
- */
-
-/* which logical CPU number maps to which CPU (physical APIC ID) */
-u16 x86_cpu_to_apicid_init[NR_CPUS] __initdata =
- { [0 ... NR_CPUS-1] = BAD_APICID };
-void *x86_cpu_to_apicid_early_ptr;
-
-u16 x86_bios_cpu_apicid_init[NR_CPUS] __initdata
- = { [0 ... NR_CPUS-1] = BAD_APICID };
-void *x86_bios_cpu_apicid_early_ptr;
-
#ifdef CONFIG_X86_32
u8 apicid_2_node[MAX_APICID];
static int low_mappings;
@@ -992,7 +976,7 @@ do_rest:
/* Try to put things back the way they were before ... */
unmap_cpu_to_logical_apicid(cpu);
#ifdef CONFIG_X86_64
- clear_node_cpumask(cpu); /* was set by numa_add_cpu */
+ numa_remove_cpu(cpu); /* was set by numa_add_cpu */
#endif
cpu_clear(cpu, cpu_callout_map); /* was set by do_boot_cpu() */
cpu_clear(cpu, cpu_initialized); /* was set by cpu_init() */
@@ -1373,7 +1357,7 @@ static void __ref remove_cpu_from_maps(int cpu)
cpu_clear(cpu, cpu_callin_map);
/* was set by cpu_init() */
clear_bit(cpu, (unsigned long *)&cpu_initialized);
- clear_node_cpumask(cpu);
+ numa_remove_cpu(cpu);
#endif
}
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index c5066d519e5..970f86775c4 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -31,16 +31,6 @@ bootmem_data_t plat_node_bdata[MAX_NUMNODES];
struct memnode memnode;
-#ifdef CONFIG_SMP
-int x86_cpu_to_node_map_init[NR_CPUS] = {
- [0 ... NR_CPUS-1] = NUMA_NO_NODE
-};
-void *x86_cpu_to_node_map_early_ptr;
-EXPORT_SYMBOL(x86_cpu_to_node_map_early_ptr);
-#endif
-DEFINE_PER_CPU(int, x86_cpu_to_node_map) = NUMA_NO_NODE;
-EXPORT_PER_CPU_SYMBOL(x86_cpu_to_node_map);
-
s16 apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
};
@@ -577,24 +567,6 @@ void __init numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn)
setup_node_bootmem(0, start_pfn << PAGE_SHIFT, end_pfn << PAGE_SHIFT);
}
-__cpuinit void numa_add_cpu(int cpu)
-{
- set_bit(cpu,
- (unsigned long *)&node_to_cpumask_map[early_cpu_to_node(cpu)]);
-}
-
-void __cpuinit numa_set_node(int cpu, int node)
-{
- int *cpu_to_node_map = x86_cpu_to_node_map_early_ptr;
-
- if(cpu_to_node_map)
- cpu_to_node_map[cpu] = node;
- else if(per_cpu_offset(cpu))
- per_cpu(x86_cpu_to_node_map, cpu) = node;
- else
- Dprintk(KERN_INFO "Setting node for non-present cpu %d\n", cpu);
-}
-
unsigned long __init numa_free_all_bootmem(void)
{
unsigned long pages = 0;
@@ -641,6 +613,7 @@ static __init int numa_setup(char *opt)
}
early_param("numa", numa_setup);
+#ifdef CONFIG_NUMA
/*
* Setup early cpu_to_node.
*
@@ -652,14 +625,19 @@ early_param("numa", numa_setup);
* is already initialized in a round robin manner at numa_init_array,
* prior to this call, and this initialization is good enough
* for the fake NUMA cases.
+ *
+ * Called before the per_cpu areas are setup.
*/
void __init init_cpu_to_node(void)
{
- int i;
+ int cpu;
+ u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
- for (i = 0; i < NR_CPUS; i++) {
+ BUG_ON(cpu_to_apicid == NULL);
+
+ for_each_possible_cpu(cpu) {
int node;
- u16 apicid = x86_cpu_to_apicid_init[i];
+ u16 apicid = cpu_to_apicid[cpu];
if (apicid == BAD_APICID)
continue;
@@ -668,8 +646,9 @@ void __init init_cpu_to_node(void)
continue;
if (!node_online(node))
continue;
- numa_set_node(i, node);
+ numa_set_node(cpu, node);
}
}
+#endif
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 99649dccad2..012220e31c9 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -376,7 +376,7 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
if (node == NUMA_NO_NODE)
continue;
if (!node_isset(node, node_possible_map))
- numa_set_node(i, NUMA_NO_NODE);
+ numa_clear_node(i);
}
numa_init_array();
return 0;
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index fdf4044d2e7..1efe162e16d 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -40,6 +40,7 @@ static ssize_t show_##name(struct sys_device *dev, char *buf) \
return sprintf(buf, "%d\n", topology_##name(cpu)); \
}
+#if defined(topology_thread_siblings) || defined(topology_core_siblings)
static ssize_t show_cpumap(int type, cpumask_t *mask, char *buf)
{
ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf;
@@ -54,21 +55,41 @@ static ssize_t show_cpumap(int type, cpumask_t *mask, char *buf)
}
return n;
}
+#endif
+#ifdef arch_provides_topology_pointers
#define define_siblings_show_map(name) \
-static inline ssize_t show_##name(struct sys_device *dev, char *buf) \
+static ssize_t show_##name(struct sys_device *dev, char *buf) \
{ \
unsigned int cpu = dev->id; \
return show_cpumap(0, &(topology_##name(cpu)), buf); \
}
#define define_siblings_show_list(name) \
-static inline ssize_t show_##name##_list(struct sys_device *dev, char *buf) \
+static ssize_t show_##name##_list(struct sys_device *dev, char *buf) \
{ \
unsigned int cpu = dev->id; \
return show_cpumap(1, &(topology_##name(cpu)), buf); \
}
+#else
+#define define_siblings_show_map(name) \
+static ssize_t show_##name(struct sys_device *dev, char *buf) \
+{ \
+ unsigned int cpu = dev->id; \
+ cpumask_t mask = topology_##name(cpu); \
+ return show_cpumap(0, &mask, buf); \
+}
+
+#define define_siblings_show_list(name) \
+static ssize_t show_##name##_list(struct sys_device *dev, char *buf) \
+{ \
+ unsigned int cpu = dev->id; \
+ cpumask_t mask = topology_##name(cpu); \
+ return show_cpumap(1, &mask, buf); \
+}
+#endif
+
#define define_siblings_show_func(name) \
define_siblings_show_map(name); define_siblings_show_list(name)
diff --git a/include/asm-x86/numa_64.h b/include/asm-x86/numa_64.h
index 22e87c9f6a8..b510daf4f4d 100644
--- a/include/asm-x86/numa_64.h
+++ b/include/asm-x86/numa_64.h
@@ -14,11 +14,9 @@ extern int compute_hash_shift(struct bootnode *nodes, int numblks,
#define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
-extern void numa_add_cpu(int cpu);
extern void numa_init_array(void);
extern int numa_off;
-extern void numa_set_node(int cpu, int node);
extern void srat_reserve_add_area(int nodeid);
extern int hotadd_percent;
@@ -31,15 +29,16 @@ extern void setup_node_bootmem(int nodeid, unsigned long start,
#ifdef CONFIG_NUMA
extern void __init init_cpu_to_node(void);
-
-static inline void clear_node_cpumask(int cpu)
-{
- clear_bit(cpu, (unsigned long *)&node_to_cpumask_map[cpu_to_node(cpu)]);
-}
-
+extern void __cpuinit numa_set_node(int cpu, int node);
+extern void __cpuinit numa_clear_node(int cpu);
+extern void __cpuinit numa_add_cpu(int cpu);
+extern void __cpuinit numa_remove_cpu(int cpu);
#else
-#define init_cpu_to_node() do {} while (0)
-#define clear_node_cpumask(cpu) do {} while (0)
+static inline void init_cpu_to_node(void) { }
+static inline void numa_set_node(int cpu, int node) { }
+static inline void numa_clear_node(int cpu) { }
+static inline void numa_add_cpu(int cpu, int node) { }
+static inline void numa_remove_cpu(int cpu) { }
#endif
#endif
diff --git a/include/asm-x86/percpu.h b/include/asm-x86/percpu.h
index 736fc3bb8e1..912a3a17b9d 100644
--- a/include/asm-x86/percpu.h
+++ b/include/asm-x86/percpu.h
@@ -143,4 +143,50 @@ do { \
#define x86_or_percpu(var, val) percpu_to_op("or", per_cpu__##var, val)
#endif /* !__ASSEMBLY__ */
#endif /* !CONFIG_X86_64 */
+
+#ifdef CONFIG_SMP
+
+/*
+ * Define the "EARLY_PER_CPU" macros. These are used for some per_cpu
+ * variables that are initialized and accessed before there are per_cpu
+ * areas allocated.
+ */
+
+#define DEFINE_EARLY_PER_CPU(_type, _name, _initvalue) \
+ DEFINE_PER_CPU(_type, _name) = _initvalue; \
+ __typeof__(_type) _name##_early_map[NR_CPUS] __initdata = \
+ { [0 ... NR_CPUS-1] = _initvalue }; \
+ __typeof__(_type) *_name##_early_ptr = _name##_early_map
+
+#define EXPORT_EARLY_PER_CPU_SYMBOL(_name) \
+ EXPORT_PER_CPU_SYMBOL(_name)
+
+#define DECLARE_EARLY_PER_CPU(_type, _name) \
+ DECLARE_PER_CPU(_type, _name); \
+ extern __typeof__(_type) *_name##_early_ptr; \
+ extern __typeof__(_type) _name##_early_map[]
+
+#define early_per_cpu_ptr(_name) (_name##_early_ptr)
+#define early_per_cpu_map(_name, _idx) (_name##_early_map[_idx])
+#define early_per_cpu(_name, _cpu) \
+ (early_per_cpu_ptr(_name) ? \
+ early_per_cpu_ptr(_name)[_cpu] : \
+ per_cpu(_name, _cpu))
+
+#else /* !CONFIG_SMP */
+#define DEFINE_EARLY_PER_CPU(_type, _name, _initvalue) \
+ DEFINE_PER_CPU(_type, _name) = _initvalue
+
+#define EXPORT_EARLY_PER_CPU_SYMBOL(_name) \
+ EXPORT_PER_CPU_SYMBOL(_name)
+
+#define DECLARE_EARLY_PER_CPU(_type, _name) \
+ DECLARE_PER_CPU(_type, _name)
+
+#define early_per_cpu(_name, _cpu) per_cpu(_name, _cpu)
+#define early_per_cpu_ptr(_name) NULL
+/* no early_per_cpu_map() */
+
+#endif /* !CONFIG_SMP */
+
#endif /* _ASM_X86_PERCPU_H_ */
diff --git a/include/asm-x86/smp.h b/include/asm-x86/smp.h
index 1ebaa5cd311..ec841639fb4 100644
--- a/include/asm-x86/smp.h
+++ b/include/asm-x86/smp.h
@@ -29,21 +29,12 @@ extern int smp_num_siblings;
extern unsigned int num_processors;
extern cpumask_t cpu_initialized;
-#ifdef CONFIG_SMP
-extern u16 x86_cpu_to_apicid_init[];
-extern u16 x86_bios_cpu_apicid_init[];
-extern void *x86_cpu_to_apicid_early_ptr;
-extern void *x86_bios_cpu_apicid_early_ptr;
-#else
-#define x86_cpu_to_apicid_early_ptr NULL
-#define x86_bios_cpu_apicid_early_ptr NULL
-#endif
-
DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
DECLARE_PER_CPU(cpumask_t, cpu_core_map);
DECLARE_PER_CPU(u16, cpu_llc_id);
-DECLARE_PER_CPU(u16, x86_cpu_to_apicid);
-DECLARE_PER_CPU(u16, x86_bios_cpu_apicid);
+
+DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
+DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
/* Static state in head.S used to set up a CPU */
extern struct {
diff --git a/include/asm-x86/topology.h b/include/asm-x86/topology.h
index dcf3f8131d6..dac09cb66dc 100644
--- a/include/asm-x86/topology.h
+++ b/include/asm-x86/topology.h
@@ -35,87 +35,67 @@
# endif
#endif
+/* Node not present */
+#define NUMA_NO_NODE (-1)
+
#ifdef CONFIG_NUMA
#include <linux/cpumask.h>
#include <asm/mpspec.h>
-/* Mappings between logical cpu number and node number */
#ifdef CONFIG_X86_32
-extern int cpu_to_node_map[];
-#else
-/* Returns the number of the current Node. */
-#define numa_node_id() (early_cpu_to_node(raw_smp_processor_id()))
-#endif
-
-DECLARE_PER_CPU(int, x86_cpu_to_node_map);
-
-#ifdef CONFIG_SMP
-extern int x86_cpu_to_node_map_init[];
-extern void *x86_cpu_to_node_map_early_ptr;
-#else
-#define x86_cpu_to_node_map_early_ptr NULL
-#endif
+/* Mappings between node number and cpus on that node. */
extern cpumask_t node_to_cpumask_map[];
-#define NUMA_NO_NODE (-1)
+/* Mappings between logical cpu number and node number */
+extern int cpu_to_node_map[];
/* Returns the number of the node containing CPU 'cpu' */
-#ifdef CONFIG_X86_32
-#define early_cpu_to_node(cpu) cpu_to_node(cpu)
static inline int cpu_to_node(int cpu)
{
return cpu_to_node_map[cpu];
}
+#define early_cpu_to_node(cpu) cpu_to_node(cpu)
#else /* CONFIG_X86_64 */
-#ifdef CONFIG_SMP
-static inline int early_cpu_to_node(int cpu)
-{
- int *cpu_to_node_map = x86_cpu_to_node_map_early_ptr;
-
- if (cpu_to_node_map)
- return cpu_to_node_map[cpu];
- else if (per_cpu_offset(cpu))
- return per_cpu(x86_cpu_to_node_map, cpu);
- else
- return NUMA_NO_NODE;
-}
-#else
-#define early_cpu_to_node(cpu) cpu_to_node(cpu)
-#endif
+/* Mappings between node number and cpus on that node. */
+extern cpumask_t node_to_cpumask_map[];
+
+/* Mappings between logical cpu number and node number */
+DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
+
+/* Returns the number of the current Node. */
+#define numa_node_id() (per_cpu(x86_cpu_to_node_map, raw_smp_processor_id()))
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+extern int cpu_to_node(int cpu);
+extern int early_cpu_to_node(int cpu);
+extern cpumask_t *_node_to_cpumask_ptr(int node);
+extern cpumask_t node_to_cpumask(int node);
+#else /* !CONFIG_DEBUG_PER_CPU_MAPS */
+
+/* Returns the number of the node containing CPU 'cpu' */
static inline int cpu_to_node(int cpu)
{
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
- if (x86_cpu_to_node_map_early_ptr) {
- printk("KERN_NOTICE cpu_to_node(%d): usage too early!\n",
- (int)cpu);
- dump_stack();
- return ((int *)x86_cpu_to_node_map_early_ptr)[cpu];
- }
-#endif
return per_cpu(x86_cpu_to_node_map, cpu);
}
-#ifdef CONFIG_NUMA
-
-/* Returns a pointer to the cpumask of CPUs on Node 'node'. */
-#define node_to_cpumask_ptr(v, node) \
- cpumask_t *v = &(node_to_cpumask_map[node])
-
-#define node_to_cpumask_ptr_next(v, node) \
- v = &(node_to_cpumask_map[node])
-#endif
+/* Same function but used if called before per_cpu areas are setup */
+static inline int early_cpu_to_node(int cpu)
+{
+ if (early_per_cpu_ptr(x86_cpu_to_node_map))
+ return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
-#endif /* CONFIG_X86_64 */
+ return per_cpu(x86_cpu_to_node_map, cpu);
+}
-/*
- * Returns the number of the node containing Node 'node'. This
- * architecture is flat, so it is a pretty simple function!
- */
-#define parent_node(node) (node)
+/* Returns a pointer to the cpumask of CPUs on Node 'node'. */
+static inline cpumask_t *_node_to_cpumask_ptr(int node)
+{
+ return &node_to_cpumask_map[node];
+}
/* Returns a bitmask of CPUs on Node 'node'. */
static inline cpumask_t node_to_cpumask(int node)
@@ -123,14 +103,29 @@ static inline cpumask_t node_to_cpumask(int node)
return node_to_cpumask_map[node];
}
+#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
+#endif /* CONFIG_X86_64 */
+
+/* Replace default node_to_cpumask_ptr with optimized version */
+#define node_to_cpumask_ptr(v, node) \
+ cpumask_t *v = _node_to_cpumask_ptr(node)
+
+#define node_to_cpumask_ptr_next(v, node) \
+ v = _node_to_cpumask_ptr(node)
+
/* Returns the number of the first CPU on Node 'node'. */
static inline int node_to_first_cpu(int node)
{
- cpumask_t mask = node_to_cpumask(node);
-
- return first_cpu(mask);
+ node_to_cpumask_ptr(mask, node);
+ return first_cpu(*mask);
}
+/*
+ * Returns the number of the node containing Node 'node'. This
+ * architecture is flat, so it is a pretty simple function!
+ */
+#define parent_node(node) (node)
+
#define pcibus_to_node(bus) __pcibus_to_node(bus)
#define pcibus_to_cpumask(bus) __pcibus_to_cpumask(bus)
@@ -180,8 +175,31 @@ extern int __node_distance(int, int);
#define node_distance(a, b) __node_distance(a, b)
#endif
-#else /* CONFIG_NUMA */
+#else /* !CONFIG_NUMA */
+
+#define numa_node_id() 0
+#define cpu_to_node(cpu) 0
+#define early_cpu_to_node(cpu) 0
+
+static inline cpumask_t *_node_to_cpumask_ptr(int node)
+{
+ return &cpu_online_map;
+}
+static inline cpumask_t node_to_cpumask(int node)
+{
+ return cpu_online_map;
+}
+static inline int node_to_first_cpu(int node)
+{
+ return first_cpu(cpu_online_map);
+}
+
+/* Replace default node_to_cpumask_ptr with optimized version */
+#define node_to_cpumask_ptr(v, node) \
+ cpumask_t *v = _node_to_cpumask_ptr(node)
+#define node_to_cpumask_ptr_next(v, node) \
+ v = _node_to_cpumask_ptr(node)
#endif
#include <asm-generic/topology.h>
@@ -193,6 +211,9 @@ extern cpumask_t cpu_coregroup_map(int cpu);
#define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id)
#define topology_core_siblings(cpu) (per_cpu(cpu_core_map, cpu))
#define topology_thread_siblings(cpu) (per_cpu(cpu_sibling_map, cpu))
+
+/* indicates that pointers to the topology cpumask_t maps are valid */
+#define arch_provides_topology_pointers yes
#endif
static inline void arch_fix_phys_package_id(int num, u32 slot)
@@ -220,4 +241,4 @@ static inline void set_mp_bus_to_node(int busnum, int node)
}
#endif
-#endif
+#endif /* _ASM_X86_TOPOLOGY_H */