aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kernel/smpboot.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/smpboot.c')
-rw-r--r--arch/x86/kernel/smpboot.c1362
1 files changed, 735 insertions, 627 deletions
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 4b53a647bc0..5492798930e 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1,8 +1,8 @@
-/*
+ /*
* x86 SMP booting functions
*
- * (c) 1995 Alan Cox, Building #3 <alan@redhat.com>
- * (c) 1998, 1999, 2000 Ingo Molnar <mingo@redhat.com>
+ * (c) 1995 Alan Cox, Building #3 <alan@lxorguk.ukuu.org.uk>
+ * (c) 1998, 1999, 2000, 2009 Ingo Molnar <mingo@redhat.com>
* Copyright 2001 Andi Kleen, SuSE Labs.
*
* Much of the core SMP work is based on previous work by Thomas Radke, to
@@ -39,6 +39,8 @@
* Glauber Costa : i386 and x86_64 integration
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/init.h>
#include <linux/smp.h>
#include <linux/module.h>
@@ -47,154 +49,66 @@
#include <linux/bootmem.h>
#include <linux/err.h>
#include <linux/nmi.h>
+#include <linux/tboot.h>
+#include <linux/stackprotector.h>
+#include <linux/gfp.h>
+#include <linux/cpuidle.h>
#include <asm/acpi.h>
#include <asm/desc.h>
#include <asm/nmi.h>
#include <asm/irq.h>
-#include <asm/smp.h>
-#include <asm/trampoline.h>
+#include <asm/idle.h>
+#include <asm/realmode.h>
#include <asm/cpu.h>
#include <asm/numa.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/mtrr.h>
-#include <asm/vmi.h>
-#include <asm/genapic.h>
+#include <asm/mwait.h>
+#include <asm/apic.h>
+#include <asm/io_apic.h>
+#include <asm/i387.h>
+#include <asm/fpu-internal.h>
+#include <asm/setup.h>
+#include <asm/uv/uv.h>
#include <linux/mc146818rtc.h>
-
-#include <mach_apic.h>
-#include <mach_wakecpu.h>
-#include <smpboot_hooks.h>
-
-#ifdef CONFIG_X86_32
-u8 apicid_2_node[MAX_APICID];
-static int low_mappings;
-#endif
+#include <asm/smpboot_hooks.h>
+#include <asm/i8259.h>
+#include <asm/realmode.h>
+#include <asm/misc.h>
/* State of each CPU */
DEFINE_PER_CPU(int, cpu_state) = { 0 };
-/* Store all idle threads, this can be reused instead of creating
-* a new thread. Also avoids complicated thread destroy functionality
-* for idle threads.
-*/
-#ifdef CONFIG_HOTPLUG_CPU
-/*
- * Needed only for CONFIG_HOTPLUG_CPU because __cpuinitdata is
- * removed after init for !CONFIG_HOTPLUG_CPU.
- */
-static DEFINE_PER_CPU(struct task_struct *, idle_thread_array);
-#define get_idle_for_cpu(x) (per_cpu(idle_thread_array, x))
-#define set_idle_for_cpu(x, p) (per_cpu(idle_thread_array, x) = (p))
-#else
-struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;
-#define get_idle_for_cpu(x) (idle_thread_array[(x)])
-#define set_idle_for_cpu(x, p) (idle_thread_array[(x)] = (p))
-#endif
-
/* Number of siblings per CPU package */
int smp_num_siblings = 1;
EXPORT_SYMBOL(smp_num_siblings);
/* Last level cache ID of each logical CPU */
-DEFINE_PER_CPU(u16, cpu_llc_id) = BAD_APICID;
-
-/* bitmap of online cpus */
-cpumask_t cpu_online_map __read_mostly;
-EXPORT_SYMBOL(cpu_online_map);
-
-cpumask_t cpu_callin_map;
-cpumask_t cpu_callout_map;
-cpumask_t cpu_possible_map;
-EXPORT_SYMBOL(cpu_possible_map);
+DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID;
/* representing HT siblings of each logical CPU */
-DEFINE_PER_CPU(cpumask_t, cpu_sibling_map);
+DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
/* representing HT and core siblings of each logical CPU */
-DEFINE_PER_CPU(cpumask_t, cpu_core_map);
+DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
EXPORT_PER_CPU_SYMBOL(cpu_core_map);
+DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
+
/* Per CPU bogomips and other parameters */
DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
EXPORT_PER_CPU_SYMBOL(cpu_info);
-static atomic_t init_deasserted;
-
-static int boot_cpu_logical_apicid;
-
-/* representing cpus for which sibling maps can be computed */
-static cpumask_t cpu_sibling_setup_map;
-
-/* Set if we find a B stepping CPU */
-int __cpuinitdata smp_b_stepping;
-
-#if defined(CONFIG_NUMA) && defined(CONFIG_X86_32)
-
-/* which logical CPUs are on which nodes */
-cpumask_t node_to_cpumask_map[MAX_NUMNODES] __read_mostly =
- { [0 ... MAX_NUMNODES-1] = CPU_MASK_NONE };
-EXPORT_SYMBOL(node_to_cpumask_map);
-/* which node each logical CPU is on */
-int cpu_to_node_map[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = 0 };
-EXPORT_SYMBOL(cpu_to_node_map);
-
-/* set up a mapping between cpu and node. */
-static void map_cpu_to_node(int cpu, int node)
-{
- printk(KERN_INFO "Mapping cpu %d to node %d\n", cpu, node);
- cpu_set(cpu, node_to_cpumask_map[node]);
- cpu_to_node_map[cpu] = node;
-}
-
-/* undo a mapping between cpu and node. */
-static void unmap_cpu_to_node(int cpu)
-{
- int node;
-
- printk(KERN_INFO "Unmapping cpu %d from all nodes\n", cpu);
- for (node = 0; node < MAX_NUMNODES; node++)
- cpu_clear(cpu, node_to_cpumask_map[node]);
- cpu_to_node_map[cpu] = 0;
-}
-#else /* !(CONFIG_NUMA && CONFIG_X86_32) */
-#define map_cpu_to_node(cpu, node) ({})
-#define unmap_cpu_to_node(cpu) ({})
-#endif
-
-#ifdef CONFIG_X86_32
-u8 cpu_2_logical_apicid[NR_CPUS] __read_mostly =
- { [0 ... NR_CPUS-1] = BAD_APICID };
-
-static void map_cpu_to_logical_apicid(void)
-{
- int cpu = smp_processor_id();
- int apicid = logical_smp_processor_id();
- int node = apicid_to_node(apicid);
-
- if (!node_online(node))
- node = first_online_node;
-
- cpu_2_logical_apicid[cpu] = apicid;
- map_cpu_to_node(cpu, node);
-}
-
-void numa_remove_cpu(int cpu)
-{
- cpu_2_logical_apicid[cpu] = BAD_APICID;
- unmap_cpu_to_node(cpu);
-}
-#else
-#define map_cpu_to_logical_apicid() do {} while (0)
-#endif
+atomic_t init_deasserted;
/*
- * Report back to the Boot Processor.
- * Running on AP.
+ * Report back to the Boot Processor during boot time or to the caller processor
+ * during CPU online.
*/
-static void __cpuinit smp_callin(void)
+static void smp_callin(void)
{
int cpuid, phys_id;
unsigned long timeout;
@@ -204,15 +118,19 @@ static void __cpuinit smp_callin(void)
* we may get here before an INIT-deassert IPI reaches
* our local APIC. We have to wait for the IPI or we'll
* lock up on an APIC access.
+ *
+ * Since CPU0 is not wakened up by INIT, it doesn't wait for the IPI.
*/
- wait_for_init_deassert(&init_deasserted);
+ cpuid = smp_processor_id();
+ if (apic->wait_for_init_deassert && cpuid)
+ while (!atomic_read(&init_deasserted))
+ cpu_relax();
/*
* (This works even if the APIC is not enabled.)
*/
- phys_id = GET_APIC_ID(read_apic_id());
- cpuid = smp_processor_id();
- if (cpu_isset(cpuid, cpu_callin_map)) {
+ phys_id = read_apic_id();
+ if (cpumask_test_cpu(cpuid, cpu_callin_mask)) {
panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__,
phys_id, cpuid);
}
@@ -234,7 +152,7 @@ static void __cpuinit smp_callin(void)
/*
* Has the boot CPU finished it's STARTUP sequence?
*/
- if (cpu_isset(cpuid, cpu_callout_map))
+ if (cpumask_test_cpu(cpuid, cpu_callout_mask))
break;
cpu_relax();
}
@@ -251,51 +169,73 @@ static void __cpuinit smp_callin(void)
* boards)
*/
- pr_debug("CALLIN, before setup_local_APIC().\n");
- smp_callin_clear_local_apic();
+ pr_debug("CALLIN, before setup_local_APIC()\n");
+ if (apic->smp_callin_clear_local_apic)
+ apic->smp_callin_clear_local_apic();
setup_local_APIC();
end_local_APIC_setup();
- map_cpu_to_logical_apicid();
+
+ /*
+ * Need to setup vector mappings before we enable interrupts.
+ */
+ setup_vector_irq(smp_processor_id());
+
+ /*
+ * Save our processor parameters. Note: this information
+ * is needed for clock calibration.
+ */
+ smp_store_cpu_info(cpuid);
/*
* Get our bogomips.
- *
- * Need to enable IRQs because it can take longer and then
- * the NMI watchdog might kill us.
+ * Update loops_per_jiffy in cpu_data. Previous call to
+ * smp_store_cpu_info() stored a value that is close but not as
+ * accurate as the value just calculated.
*/
- local_irq_enable();
calibrate_delay();
- local_irq_disable();
+ cpu_data(cpuid).loops_per_jiffy = loops_per_jiffy;
pr_debug("Stack at about %p\n", &cpuid);
/*
- * Save our processor parameters
+ * This must be done before setting cpu_online_mask
+ * or calling notify_cpu_starting.
*/
- smp_store_cpu_info(cpuid);
+ set_cpu_sibling_map(raw_smp_processor_id());
+ wmb();
+
+ notify_cpu_starting(cpuid);
/*
* Allow the master to continue.
*/
- cpu_set(cpuid, cpu_callin_map);
+ cpumask_set_cpu(cpuid, cpu_callin_mask);
}
+static int cpu0_logical_apicid;
+static int enable_start_cpu0;
/*
* Activate a secondary processor.
*/
-static void __cpuinit start_secondary(void *unused)
+static void notrace start_secondary(void *unused)
{
/*
* Don't put *anything* before cpu_init(), SMP booting is too
* fragile that we want to limit the things done here to the
* most necessary things.
*/
-#ifdef CONFIG_VMI
- vmi_bringup();
-#endif
cpu_init();
+ x86_cpuinit.early_percpu_clock_init();
preempt_disable();
smp_callin();
+ enable_start_cpu0 = 0;
+
+#ifdef CONFIG_X86_32
+ /* switch away from the initial page table */
+ load_cr3(swapper_pg_dir);
+ __flush_tlb_all();
+#endif
+
/* otherwise gcc will move up smp_processor_id before the cpu_init */
barrier();
/*
@@ -303,182 +243,167 @@ static void __cpuinit start_secondary(void *unused)
*/
check_tsc_sync_target();
- if (nmi_watchdog == NMI_IO_APIC) {
- disable_8259A_irq(0);
- enable_NMI_through_LVT0();
- enable_8259A_irq(0);
- }
-
-#ifdef CONFIG_X86_32
- while (low_mappings)
- cpu_relax();
- __flush_tlb_all();
+ /*
+ * Enable the espfix hack for this CPU
+ */
+#ifdef CONFIG_X86_ESPFIX64
+ init_espfix_ap();
#endif
- /* This must be done before setting cpu_online_map */
- set_cpu_sibling_map(raw_smp_processor_id());
- wmb();
-
/*
- * We need to hold call_lock, so there is no inconsistency
- * between the time smp_call_function() determines number of
- * IPI recipients, and the time when the determination is made
- * for which cpus receive the IPI. Holding this
- * lock helps us to not include this cpu in a currently in progress
- * smp_call_function().
+ * We need to hold vector_lock so there the set of online cpus
+ * does not change while we are assigning vectors to cpus. Holding
+ * this lock ensures we don't half assign or remove an irq from a cpu.
*/
- ipi_call_lock_irq();
-#ifdef CONFIG_X86_IO_APIC
- setup_vector_irq(smp_processor_id());
-#endif
- cpu_set(smp_processor_id(), cpu_online_map);
- ipi_call_unlock_irq();
+ lock_vector_lock();
+ set_cpu_online(smp_processor_id(), true);
+ unlock_vector_lock();
per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
+ x86_platform.nmi_init();
+
+ /* enable local interrupts */
+ local_irq_enable();
+
+ /* to prevent fake stack check failure in clock setup */
+ boot_init_stack_canary();
- setup_secondary_clock();
+ x86_cpuinit.setup_percpu_clockev();
wmb();
- cpu_idle();
+ cpu_startup_entry(CPUHP_ONLINE);
}
-static void __cpuinit smp_apply_quirks(struct cpuinfo_x86 *c)
+void __init smp_store_boot_cpu_info(void)
{
- /*
- * Mask B, Pentium, but not Pentium MMX
- */
- if (c->x86_vendor == X86_VENDOR_INTEL &&
- c->x86 == 5 &&
- c->x86_mask >= 1 && c->x86_mask <= 4 &&
- c->x86_model <= 3)
- /*
- * Remember we have B step Pentia with bugs
- */
- smp_b_stepping = 1;
+ int id = 0; /* CPU 0 */
+ struct cpuinfo_x86 *c = &cpu_data(id);
+
+ *c = boot_cpu_data;
+ c->cpu_index = id;
+}
+
+/*
+ * The bootstrap kernel entry code has set these up. Save them for
+ * a given CPU
+ */
+void smp_store_cpu_info(int id)
+{
+ struct cpuinfo_x86 *c = &cpu_data(id);
+ *c = boot_cpu_data;
+ c->cpu_index = id;
/*
- * Certain Athlons might work (for various values of 'work') in SMP
- * but they are not certified as MP capable.
+ * During boot time, CPU0 has this setup already. Save the info when
+ * bringing up AP or offlined CPU0.
*/
- if ((c->x86_vendor == X86_VENDOR_AMD) && (c->x86 == 6)) {
+ identify_secondary_cpu(c);
+}
- if (num_possible_cpus() == 1)
- goto valid_k7;
+static bool
+topology_sane(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o, const char *name)
+{
+ int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
- /* Athlon 660/661 is valid. */
- if ((c->x86_model == 6) && ((c->x86_mask == 0) ||
- (c->x86_mask == 1)))
- goto valid_k7;
+ return !WARN_ONCE(cpu_to_node(cpu1) != cpu_to_node(cpu2),
+ "sched: CPU #%d's %s-sibling CPU #%d is not on the same node! "
+ "[node: %d != %d]. Ignoring dependency.\n",
+ cpu1, name, cpu2, cpu_to_node(cpu1), cpu_to_node(cpu2));
+}
- /* Duron 670 is valid */
- if ((c->x86_model == 7) && (c->x86_mask == 0))
- goto valid_k7;
+#define link_mask(_m, c1, c2) \
+do { \
+ cpumask_set_cpu((c1), cpu_##_m##_mask(c2)); \
+ cpumask_set_cpu((c2), cpu_##_m##_mask(c1)); \
+} while (0)
- /*
- * Athlon 662, Duron 671, and Athlon >model 7 have capability
- * bit. It's worth noting that the A5 stepping (662) of some
- * Athlon XP's have the MP bit set.
- * See http://www.heise.de/newsticker/data/jow-18.10.01-000 for
- * more.
- */
- if (((c->x86_model == 6) && (c->x86_mask >= 2)) ||
- ((c->x86_model == 7) && (c->x86_mask >= 1)) ||
- (c->x86_model > 7))
- if (cpu_has_mp)
- goto valid_k7;
-
- /* If we get here, not a certified SMP capable AMD system. */
- add_taint(TAINT_UNSAFE_SMP);
+static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+{
+ if (cpu_has_topoext) {
+ int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
+
+ if (c->phys_proc_id == o->phys_proc_id &&
+ per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) &&
+ c->compute_unit_id == o->compute_unit_id)
+ return topology_sane(c, o, "smt");
+
+ } else if (c->phys_proc_id == o->phys_proc_id &&
+ c->cpu_core_id == o->cpu_core_id) {
+ return topology_sane(c, o, "smt");
}
-valid_k7:
- ;
+ return false;
}
-static void __cpuinit smp_checks(void)
+static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
{
- if (smp_b_stepping)
- printk(KERN_WARNING "WARNING: SMP operation may be unreliable"
- "with B stepping processors.\n");
+ int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
- /*
- * Don't taint if we are running SMP kernel on a single non-MP
- * approved Athlon
- */
- if (tainted & TAINT_UNSAFE_SMP) {
- if (num_online_cpus())
- printk(KERN_INFO "WARNING: This combination of AMD"
- "processors is not suitable for SMP.\n");
- else
- tainted &= ~TAINT_UNSAFE_SMP;
- }
-}
+ if (per_cpu(cpu_llc_id, cpu1) != BAD_APICID &&
+ per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2))
+ return topology_sane(c, o, "llc");
-/*
- * The bootstrap kernel entry code has set these up. Save them for
- * a given CPU
- */
+ return false;
+}
-void __cpuinit smp_store_cpu_info(int id)
+static bool match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
{
- struct cpuinfo_x86 *c = &cpu_data(id);
+ if (c->phys_proc_id == o->phys_proc_id) {
+ if (cpu_has(c, X86_FEATURE_AMD_DCM))
+ return true;
- *c = boot_cpu_data;
- c->cpu_index = id;
- if (id != 0)
- identify_secondary_cpu(c);
- smp_apply_quirks(c);
+ return topology_sane(c, o, "mc");
+ }
+ return false;
}
-
-void __cpuinit set_cpu_sibling_map(int cpu)
+void set_cpu_sibling_map(int cpu)
{
- int i;
+ bool has_smt = smp_num_siblings > 1;
+ bool has_mp = has_smt || boot_cpu_data.x86_max_cores > 1;
struct cpuinfo_x86 *c = &cpu_data(cpu);
+ struct cpuinfo_x86 *o;
+ int i;
- cpu_set(cpu, cpu_sibling_setup_map);
-
- if (smp_num_siblings > 1) {
- for_each_cpu_mask(i, cpu_sibling_setup_map) {
- if (c->phys_proc_id == cpu_data(i).phys_proc_id &&
- c->cpu_core_id == cpu_data(i).cpu_core_id) {
- cpu_set(i, per_cpu(cpu_sibling_map, cpu));
- cpu_set(cpu, per_cpu(cpu_sibling_map, i));
- cpu_set(i, per_cpu(cpu_core_map, cpu));
- cpu_set(cpu, per_cpu(cpu_core_map, i));
- cpu_set(i, c->llc_shared_map);
- cpu_set(cpu, cpu_data(i).llc_shared_map);
- }
- }
- } else {
- cpu_set(cpu, per_cpu(cpu_sibling_map, cpu));
- }
-
- cpu_set(cpu, c->llc_shared_map);
+ cpumask_set_cpu(cpu, cpu_sibling_setup_mask);
- if (current_cpu_data.x86_max_cores == 1) {
- per_cpu(cpu_core_map, cpu) = per_cpu(cpu_sibling_map, cpu);
+ if (!has_mp) {
+ cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
+ cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
+ cpumask_set_cpu(cpu, cpu_core_mask(cpu));
c->booted_cores = 1;
return;
}
- for_each_cpu_mask(i, cpu_sibling_setup_map) {
- if (per_cpu(cpu_llc_id, cpu) != BAD_APICID &&
- per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) {
- cpu_set(i, c->llc_shared_map);
- cpu_set(cpu, cpu_data(i).llc_shared_map);
- }
- if (c->phys_proc_id == cpu_data(i).phys_proc_id) {
- cpu_set(i, per_cpu(cpu_core_map, cpu));
- cpu_set(cpu, per_cpu(cpu_core_map, i));
+ for_each_cpu(i, cpu_sibling_setup_mask) {
+ o = &cpu_data(i);
+
+ if ((i == cpu) || (has_smt && match_smt(c, o)))
+ link_mask(sibling, cpu, i);
+
+ if ((i == cpu) || (has_mp && match_llc(c, o)))
+ link_mask(llc_shared, cpu, i);
+
+ }
+
+ /*
+ * This needs a separate iteration over the cpus because we rely on all
+ * cpu_sibling_mask links to be set-up.
+ */
+ for_each_cpu(i, cpu_sibling_setup_mask) {
+ o = &cpu_data(i);
+
+ if ((i == cpu) || (has_mp && match_mc(c, o))) {
+ link_mask(core, cpu, i);
+
/*
* Does this new cpu bringup a new core?
*/
- if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1) {
+ if (cpumask_weight(cpu_sibling_mask(cpu)) == 1) {
/*
* for each core in package, increment
* the booted_cores for this new cpu
*/
- if (first_cpu(per_cpu(cpu_sibling_map, i)) == i)
+ if (cpumask_first(cpu_sibling_mask(i)) == i)
c->booted_cores++;
/*
* increment the core count for all
@@ -493,17 +418,9 @@ void __cpuinit set_cpu_sibling_map(int cpu)
}
/* maps the cpu to the sched domain representing multi-core */
-cpumask_t cpu_coregroup_map(int cpu)
+const struct cpumask *cpu_coregroup_mask(int cpu)
{
- struct cpuinfo_x86 *c = &cpu_data(cpu);
- /*
- * For perf, we return last level cache shared map.
- * And for power savings, we return cpu_core_map
- */
- if (sched_mc_power_savings || sched_smt_power_savings)
- return per_cpu(cpu_core_map, cpu);
- else
- return c->llc_shared_map;
+ return cpu_llc_shared_mask(cpu);
}
static void impress_friends(void)
@@ -513,41 +430,38 @@ static void impress_friends(void)
/*
* Allow the user to impress friends.
*/
- pr_debug("Before bogomips.\n");
+ pr_debug("Before bogomips\n");
for_each_possible_cpu(cpu)
- if (cpu_isset(cpu, cpu_callout_map))
+ if (cpumask_test_cpu(cpu, cpu_callout_mask))
bogosum += cpu_data(cpu).loops_per_jiffy;
- printk(KERN_INFO
- "Total of %d processors activated (%lu.%02lu BogoMIPS).\n",
+ pr_info("Total of %d processors activated (%lu.%02lu BogoMIPS)\n",
num_online_cpus(),
bogosum/(500000/HZ),
(bogosum/(5000/HZ))%100);
- pr_debug("Before bogocount - setting activated=1.\n");
+ pr_debug("Before bogocount - setting activated=1\n");
}
-static inline void __inquire_remote_apic(int apicid)
+void __inquire_remote_apic(int apicid)
{
unsigned i, regs[] = { APIC_ID >> 4, APIC_LVR >> 4, APIC_SPIV >> 4 };
- char *names[] = { "ID", "VERSION", "SPIV" };
+ const char * const names[] = { "ID", "VERSION", "SPIV" };
int timeout;
u32 status;
- printk(KERN_INFO "Inquiring remote APIC #%d...\n", apicid);
+ pr_info("Inquiring remote APIC 0x%x...\n", apicid);
for (i = 0; i < ARRAY_SIZE(regs); i++) {
- printk(KERN_INFO "... APIC #%d %s: ", apicid, names[i]);
+ pr_info("... APIC 0x%x %s: ", apicid, names[i]);
/*
* Wait for idle.
*/
status = safe_apic_wait_icr_idle();
if (status)
- printk(KERN_CONT
- "a previous APIC delivery may have failed\n");
+ pr_cont("a previous APIC delivery may have failed\n");
- apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(apicid));
- apic_write(APIC_ICR, APIC_DM_REMRD | regs[i]);
+ apic_icr_write(APIC_DM_REMRD | regs[i], apicid);
timeout = 0;
do {
@@ -558,32 +472,29 @@ static inline void __inquire_remote_apic(int apicid)
switch (status) {
case APIC_ICR_RR_VALID:
status = apic_read(APIC_RRR);
- printk(KERN_CONT "%08x\n", status);
+ pr_cont("%08x\n", status);
break;
default:
- printk(KERN_CONT "failed\n");
+ pr_cont("failed\n");
}
}
}
-#ifdef WAKE_SECONDARY_VIA_NMI
/*
* Poke the other CPU in the eye via NMI to wake it up. Remember that the normal
* INIT, INIT, STARTUP sequence will reset the chip hard for us, and this
* won't ... remember to clear down the APIC, etc later.
*/
-static int __devinit
-wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip)
+int
+wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip)
{
unsigned long send_status, accept_status = 0;
int maxlvt;
/* Target chip */
- apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(logical_apicid));
-
/* Boot on the stack */
/* Kick the second */
- apic_write(APIC_ICR, APIC_DM_NMI | APIC_DEST_LOGICAL);
+ apic_icr_write(APIC_DM_NMI | apic->dest_logical, apicid);
pr_debug("Waiting for send to finish...\n");
send_status = safe_apic_wait_icr_idle();
@@ -592,34 +503,28 @@ wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip)
* Give the other CPU some time to accept the IPI.
*/
udelay(200);
- maxlvt = lapic_get_maxlvt();
- if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
- apic_write(APIC_ESR, 0);
- accept_status = (apic_read(APIC_ESR) & 0xEF);
- pr_debug("NMI sent.\n");
+ if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
+ maxlvt = lapic_get_maxlvt();
+ if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
+ apic_write(APIC_ESR, 0);
+ accept_status = (apic_read(APIC_ESR) & 0xEF);
+ }
+ pr_debug("NMI sent\n");
if (send_status)
- printk(KERN_ERR "APIC never delivered???\n");
+ pr_err("APIC never delivered???\n");
if (accept_status)
- printk(KERN_ERR "APIC delivery error (%lx).\n", accept_status);
+ pr_err("APIC delivery error (%lx)\n", accept_status);
return (send_status | accept_status);
}
-#endif /* WAKE_SECONDARY_VIA_NMI */
-#ifdef WAKE_SECONDARY_VIA_INIT
-static int __devinit
-wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
+static int
+wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
{
unsigned long send_status, accept_status = 0;
int maxlvt, num_starts, j;
- if (get_uv_system_type() == UV_NON_UNIQUE_APIC) {
- send_status = uv_wakeup_secondary(phys_apicid, start_eip);
- atomic_set(&init_deasserted, 1);
- return send_status;
- }
-
maxlvt = lapic_get_maxlvt();
/*
@@ -631,31 +536,27 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
apic_read(APIC_ESR);
}
- pr_debug("Asserting INIT.\n");
+ pr_debug("Asserting INIT\n");
/*
* Turn INIT on target chip
*/
- apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
-
/*
* Send IPI
*/
- apic_write(APIC_ICR,
- APIC_INT_LEVELTRIG | APIC_INT_ASSERT | APIC_DM_INIT);
+ apic_icr_write(APIC_INT_LEVELTRIG | APIC_INT_ASSERT | APIC_DM_INIT,
+ phys_apicid);
pr_debug("Waiting for send to finish...\n");
send_status = safe_apic_wait_icr_idle();
mdelay(10);
- pr_debug("Deasserting INIT.\n");
+ pr_debug("Deasserting INIT\n");
/* Target chip */
- apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
-
/* Send IPI */
- apic_write(APIC_ICR, APIC_INT_LEVELTRIG | APIC_DM_INIT);
+ apic_icr_write(APIC_INT_LEVELTRIG | APIC_DM_INIT, phys_apicid);
pr_debug("Waiting for send to finish...\n");
send_status = safe_apic_wait_icr_idle();
@@ -679,37 +580,36 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
* target processor state.
*/
startup_ipi_hook(phys_apicid, (unsigned long) start_secondary,
- (unsigned long)stack_start.sp);
+ stack_start);
/*
* Run STARTUP IPI loop.
*/
- pr_debug("#startup loops: %d.\n", num_starts);
+ pr_debug("#startup loops: %d\n", num_starts);
for (j = 1; j <= num_starts; j++) {
- pr_debug("Sending STARTUP #%d.\n", j);
+ pr_debug("Sending STARTUP #%d\n", j);
if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
- pr_debug("After apic_write.\n");
+ pr_debug("After apic_write\n");
/*
* STARTUP IPI
*/
/* Target chip */
- apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid));
-
/* Boot on the stack */
/* Kick the second */
- apic_write(APIC_ICR, APIC_DM_STARTUP | (start_eip >> 12));
+ apic_icr_write(APIC_DM_STARTUP | (start_eip >> 12),
+ phys_apicid);
/*
* Give the other CPU some time to accept the IPI.
*/
udelay(300);
- pr_debug("Startup point 1.\n");
+ pr_debug("Startup point 1\n");
pr_debug("Waiting for send to finish...\n");
send_status = safe_apic_wait_icr_idle();
@@ -724,147 +624,165 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
if (send_status || accept_status)
break;
}
- pr_debug("After Startup.\n");
+ pr_debug("After Startup\n");
if (send_status)
- printk(KERN_ERR "APIC never delivered???\n");
+ pr_err("APIC never delivered???\n");
if (accept_status)
- printk(KERN_ERR "APIC delivery error (%lx).\n", accept_status);
+ pr_err("APIC delivery error (%lx)\n", accept_status);
return (send_status | accept_status);
}
-#endif /* WAKE_SECONDARY_VIA_INIT */
-struct create_idle {
- struct work_struct work;
- struct task_struct *idle;
- struct completion done;
- int cpu;
-};
+void smp_announce(void)
+{
+ int num_nodes = num_online_nodes();
+
+ printk(KERN_INFO "x86: Booted up %d node%s, %d CPUs\n",
+ num_nodes, (num_nodes > 1 ? "s" : ""), num_online_cpus());
+}
+
+/* reduce the number of lines printed when booting a large cpu count system */
+static void announce_cpu(int cpu, int apicid)
+{
+ static int current_node = -1;
+ int node = early_cpu_to_node(cpu);
+ static int width, node_width;
+
+ if (!width)
+ width = num_digits(num_possible_cpus()) + 1; /* + '#' sign */
+
+ if (!node_width)
+ node_width = num_digits(num_possible_nodes()) + 1; /* + '#' */
+
+ if (cpu == 1)
+ printk(KERN_INFO "x86: Booting SMP configuration:\n");
+
+ if (system_state == SYSTEM_BOOTING) {
+ if (node != current_node) {
+ if (current_node > (-1))
+ pr_cont("\n");
+ current_node = node;
+
+ printk(KERN_INFO ".... node %*s#%d, CPUs: ",
+ node_width - num_digits(node), " ", node);
+ }
+
+ /* Add padding for the BSP */
+ if (cpu == 1)
+ pr_cont("%*s", width + 1, " ");
+
+ pr_cont("%*s#%d", width - num_digits(cpu), " ", cpu);
+
+ } else
+ pr_info("Booting Node %d Processor %d APIC 0x%x\n",
+ node, cpu, apicid);
+}
-static void __cpuinit do_fork_idle(struct work_struct *work)
+static int wakeup_cpu0_nmi(unsigned int cmd, struct pt_regs *regs)
{
- struct create_idle *c_idle =
- container_of(work, struct create_idle, work);
+ int cpu;
+
+ cpu = smp_processor_id();
+ if (cpu == 0 && !cpu_online(cpu) && enable_start_cpu0)
+ return NMI_HANDLED;
- c_idle->idle = fork_idle(c_idle->cpu);
- complete(&c_idle->done);
+ return NMI_DONE;
}
-#ifdef CONFIG_X86_64
/*
- * Allocate node local memory for the AP pda.
+ * Wake up AP by INIT, INIT, STARTUP sequence.
+ *
+ * Instead of waiting for STARTUP after INITs, BSP will execute the BIOS
+ * boot-strap code which is not a desired behavior for waking up BSP. To
+ * void the boot-strap code, wake up CPU0 by NMI instead.
*
- * Must be called after the _cpu_pda pointer table is initialized.
+ * This works to wake up soft offlined CPU0 only. If CPU0 is hard offlined
+ * (i.e. physically hot removed and then hot added), NMI won't wake it up.
+ * We'll change this code in the future to wake up hard offlined CPU0 if
+ * real platform and request are available.
*/
-int __cpuinit get_local_pda(int cpu)
+static int
+wakeup_cpu_via_init_nmi(int cpu, unsigned long start_ip, int apicid,
+ int *cpu0_nmi_registered)
{
- struct x8664_pda *oldpda, *newpda;
- unsigned long size = sizeof(struct x8664_pda);
- int node = cpu_to_node(cpu);
+ int id;
+ int boot_error;
- if (cpu_pda(cpu) && !cpu_pda(cpu)->in_bootmem)
- return 0;
+ preempt_disable();
+
+ /*
+ * Wake up AP by INIT, INIT, STARTUP sequence.
+ */
+ if (cpu) {
+ boot_error = wakeup_secondary_cpu_via_init(apicid, start_ip);
+ goto out;
+ }
- oldpda = cpu_pda(cpu);
- newpda = kmalloc_node(size, GFP_ATOMIC, node);
- if (!newpda) {
- printk(KERN_ERR "Could not allocate node local PDA "
- "for CPU %d on node %d\n", cpu, node);
+ /*
+ * Wake up BSP by nmi.
+ *
+ * Register a NMI handler to help wake up CPU0.
+ */
+ boot_error = register_nmi_handler(NMI_LOCAL,
+ wakeup_cpu0_nmi, 0, "wake_cpu0");
- if (oldpda)
- return 0; /* have a usable pda */
+ if (!boot_error) {
+ enable_start_cpu0 = 1;
+ *cpu0_nmi_registered = 1;
+ if (apic->dest_logical == APIC_DEST_LOGICAL)
+ id = cpu0_logical_apicid;
else
- return -1;
+ id = apicid;
+ boot_error = wakeup_secondary_cpu_via_nmi(id, start_ip);
}
- if (oldpda) {
- memcpy(newpda, oldpda, size);
- if (!after_bootmem)
- free_bootmem((unsigned long)oldpda, size);
- }
+out:
+ preempt_enable();
- newpda->in_bootmem = 0;
- cpu_pda(cpu) = newpda;
- return 0;
+ return boot_error;
}
-#endif /* CONFIG_X86_64 */
-static int __cpuinit do_boot_cpu(int apicid, int cpu)
/*
* NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad
* (ie clustered apic addressing mode), this is a LOGICAL apic ID.
- * Returns zero if CPU booted OK, else error code from wakeup_secondary_cpu.
+ * Returns zero if CPU booted OK, else error code from
+ * ->wakeup_secondary_cpu.
*/
+static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
{
+ volatile u32 *trampoline_status =
+ (volatile u32 *) __va(real_mode_header->trampoline_status);
+ /* start_ip had better be page-aligned! */
+ unsigned long start_ip = real_mode_header->trampoline_start;
+
unsigned long boot_error = 0;
int timeout;
- unsigned long start_ip;
- unsigned short nmi_high = 0, nmi_low = 0;
- struct create_idle c_idle = {
- .cpu = cpu,
- .done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done),
- };
- INIT_WORK(&c_idle.work, do_fork_idle);
-
-#ifdef CONFIG_X86_64
- /* Allocate node local memory for AP pdas */
- if (cpu > 0) {
- boot_error = get_local_pda(cpu);
- if (boot_error)
- goto restore_state;
- /* if can't get pda memory, can't start cpu */
- }
-#endif
-
- alternatives_smp_switch(1);
-
- c_idle.idle = get_idle_for_cpu(cpu);
+ int cpu0_nmi_registered = 0;
- /*
- * We can't use kernel_thread since we must avoid to
- * reschedule the child.
- */
- if (c_idle.idle) {
- c_idle.idle->thread.sp = (unsigned long) (((struct pt_regs *)
- (THREAD_SIZE + task_stack_page(c_idle.idle))) - 1);
- init_idle(c_idle.idle, cpu);
- goto do_rest;
- }
+ /* Just in case we booted with a single CPU. */
+ alternatives_enable_smp();
- if (!keventd_up() || current_is_keventd())
- c_idle.work.func(&c_idle.work);
- else {
- schedule_work(&c_idle.work);
- wait_for_completion(&c_idle.done);
- }
+ idle->thread.sp = (unsigned long) (((struct pt_regs *)
+ (THREAD_SIZE + task_stack_page(idle))) - 1);
+ per_cpu(current_task, cpu) = idle;
- if (IS_ERR(c_idle.idle)) {
- printk("failed fork for CPU %d\n", cpu);
- return PTR_ERR(c_idle.idle);
- }
-
- set_idle_for_cpu(cpu, c_idle.idle);
-do_rest:
#ifdef CONFIG_X86_32
- per_cpu(current_task, cpu) = c_idle.idle;
- init_gdt(cpu);
/* Stack for startup_32 can be just as for start_secondary onwards */
irq_ctx_init(cpu);
#else
- cpu_pda(cpu)->pcurrent = c_idle.idle;
- clear_tsk_thread_flag(c_idle.idle, TIF_FORK);
+ clear_tsk_thread_flag(idle, TIF_FORK);
+ initial_gs = per_cpu_offset(cpu);
#endif
+ per_cpu(kernel_stack, cpu) =
+ (unsigned long)task_stack_page(idle) -
+ KERNEL_STACK_OFFSET + THREAD_SIZE;
early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
initial_code = (unsigned long)start_secondary;
- stack_start.sp = (void *) c_idle.idle->thread.sp;
+ stack_start = idle->thread.sp;
- /* start_ip had better be page-aligned! */
- start_ip = setup_trampoline();
-
- /* So we see what's up */
- printk(KERN_INFO "Booting processor %d/%d ip %lx\n",
- cpu, apicid, start_ip);
+ /* So we see what's up */
+ announce_cpu(cpu, apicid);
/*
* This grunge runs the startup process for
@@ -877,83 +795,101 @@ do_rest:
pr_debug("Setting warm reset code and vector.\n");
- store_NMI_vector(&nmi_high, &nmi_low);
-
smpboot_setup_warm_reset_vector(start_ip);
/*
* Be paranoid about clearing APIC errors.
- */
- apic_write(APIC_ESR, 0);
- apic_read(APIC_ESR);
+ */
+ if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
+ apic_write(APIC_ESR, 0);
+ apic_read(APIC_ESR);
+ }
}
/*
- * Starting actual IPI sequence...
+ * Wake up a CPU in difference cases:
+ * - Use the method in the APIC driver if it's defined
+ * Otherwise,
+ * - Use an INIT boot APIC message for APs or NMI for BSP.
*/
- boot_error = wakeup_secondary_cpu(apicid, start_ip);
+ if (apic->wakeup_secondary_cpu)
+ boot_error = apic->wakeup_secondary_cpu(apicid, start_ip);
+ else
+ boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid,
+ &cpu0_nmi_registered);
if (!boot_error) {
/*
* allow APs to start initializing.
*/
- pr_debug("Before Callout %d.\n", cpu);
- cpu_set(cpu, cpu_callout_map);
- pr_debug("After Callout %d.\n", cpu);
+ pr_debug("Before Callout %d\n", cpu);
+ cpumask_set_cpu(cpu, cpu_callout_mask);
+ pr_debug("After Callout %d\n", cpu);
/*
* Wait 5s total for a response
*/
for (timeout = 0; timeout < 50000; timeout++) {
- if (cpu_isset(cpu, cpu_callin_map))
+ if (cpumask_test_cpu(cpu, cpu_callin_mask))
break; /* It has booted */
udelay(100);
+ /*
+ * Allow other tasks to run while we wait for the
+ * AP to come online. This also gives a chance
+ * for the MTRR work(triggered by the AP coming online)
+ * to be completed in the stop machine context.
+ */
+ schedule();
}
- if (cpu_isset(cpu, cpu_callin_map)) {
- /* number CPUs logically, starting from 1 (BSP is 0) */
- pr_debug("OK.\n");
- printk(KERN_INFO "CPU%d: ", cpu);
- print_cpu_info(&cpu_data(cpu));
- pr_debug("CPU has booted.\n");
+ if (cpumask_test_cpu(cpu, cpu_callin_mask)) {
+ print_cpu_msr(&cpu_data(cpu));
+ pr_debug("CPU%d: has booted.\n", cpu);
} else {
boot_error = 1;
- if (*((volatile unsigned char *)trampoline_base)
- == 0xA5)
+ if (*trampoline_status == 0xA5A5A5A5)
/* trampoline started but...? */
- printk(KERN_ERR "Stuck ??\n");
+ pr_err("CPU%d: Stuck ??\n", cpu);
else
/* trampoline code not run */
- printk(KERN_ERR "Not responding.\n");
- if (get_uv_system_type() != UV_NON_UNIQUE_APIC)
- inquire_remote_apic(apicid);
+ pr_err("CPU%d: Not responding\n", cpu);
+ if (apic->inquire_remote_apic)
+ apic->inquire_remote_apic(apicid);
}
}
-#ifdef CONFIG_X86_64
-restore_state:
-#endif
+
if (boot_error) {
/* Try to put things back the way they were before ... */
numa_remove_cpu(cpu); /* was set by numa_add_cpu */
- cpu_clear(cpu, cpu_callout_map); /* was set by do_boot_cpu() */
- cpu_clear(cpu, cpu_initialized); /* was set by cpu_init() */
- cpu_clear(cpu, cpu_present_map);
- per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID;
+
+ /* was set by do_boot_cpu() */
+ cpumask_clear_cpu(cpu, cpu_callout_mask);
+
+ /* was set by cpu_init() */
+ cpumask_clear_cpu(cpu, cpu_initialized_mask);
}
/* mark "stuck" area as not stuck */
- *((volatile unsigned long *)trampoline_base) = 0;
+ *trampoline_status = 0;
+ if (get_uv_system_type() != UV_NON_UNIQUE_APIC) {
+ /*
+ * Cleanup possible dangling ends...
+ */
+ smpboot_restore_warm_reset_vector();
+ }
/*
- * Cleanup possible dangling ends...
+ * Clean up the nmi handler. Do this after the callin and callout sync
+ * to avoid impact of possible long unregister time.
*/
- smpboot_restore_warm_reset_vector();
+ if (cpu0_nmi_registered)
+ unregister_nmi_handler(NMI_LOCAL, "wake_cpu0");
return boot_error;
}
-int __cpuinit native_cpu_up(unsigned int cpu)
+int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
{
- int apicid = cpu_present_to_apicid(cpu);
+ int apicid = apic->cpu_present_to_apicid(cpu);
unsigned long flags;
int err;
@@ -961,16 +897,17 @@ int __cpuinit native_cpu_up(unsigned int cpu)
pr_debug("++++++++++++++++++++=_---CPU UP %u\n", cpu);
- if (apicid == BAD_APICID || apicid == boot_cpu_physical_apicid ||
- !physid_isset(apicid, phys_cpu_present_map)) {
- printk(KERN_ERR "%s: bad cpu %d\n", __func__, cpu);
+ if (apicid == BAD_APICID ||
+ !physid_isset(apicid, phys_cpu_present_map) ||
+ !apic->apic_id_valid(apicid)) {
+ pr_err("%s: bad cpu %d\n", __func__, cpu);
return -EINVAL;
}
/*
* Already booted CPU?
*/
- if (cpu_isset(cpu, cpu_callin_map)) {
+ if (cpumask_test_cpu(cpu, cpu_callin_mask)) {
pr_debug("do_boot_cpu %d Already started\n", cpu);
return -ENOSYS;
}
@@ -983,22 +920,12 @@ int __cpuinit native_cpu_up(unsigned int cpu)
per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
-#ifdef CONFIG_X86_32
- /* init low mem mapping */
- clone_pgd_range(swapper_pg_dir, swapper_pg_dir + KERNEL_PGD_BOUNDARY,
- min_t(unsigned long, KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
- flush_tlb_all();
- low_mappings = 1;
-
- err = do_boot_cpu(apicid, cpu);
+ /* the FPU context is blank, nobody can own it */
+ __cpu_disable_lazy_restore(cpu);
- zap_low_mappings();
- low_mappings = 0;
-#else
- err = do_boot_cpu(apicid, cpu);
-#endif
+ err = do_boot_cpu(apicid, cpu, tidle);
if (err) {
- pr_debug("do_boot_cpu failed %d\n", err);
+ pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu);
return -EIO;
}
@@ -1018,6 +945,14 @@ int __cpuinit native_cpu_up(unsigned int cpu)
return 0;
}
+/**
+ * arch_disable_smp_support() - disables SMP support for x86 at runtime
+ */
+void arch_disable_smp_support(void)
+{
+ disable_ioapic_support();
+}
+
/*
* Fall back to non SMP mode after errors.
*
@@ -1025,17 +960,16 @@ int __cpuinit native_cpu_up(unsigned int cpu)
*/
static __init void disable_smp(void)
{
- cpu_present_map = cpumask_of_cpu(0);
- cpu_possible_map = cpumask_of_cpu(0);
+ init_cpu_present(cpumask_of(0));
+ init_cpu_possible(cpumask_of(0));
smpboot_clear_io_apic_irqs();
if (smp_found_config)
physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
else
physid_set_mask_of_physid(0, &phys_cpu_present_map);
- map_cpu_to_logical_apicid();
- cpu_set(0, per_cpu(cpu_sibling_map, 0));
- cpu_set(0, per_cpu(cpu_core_map, 0));
+ cpumask_set_cpu(0, cpu_sibling_mask(0));
+ cpumask_set_cpu(0, cpu_core_mask(0));
}
/*
@@ -1044,9 +978,37 @@ static __init void disable_smp(void)
static int __init smp_sanity_check(unsigned max_cpus)
{
preempt_disable();
+
+#if !defined(CONFIG_X86_BIGSMP) && defined(CONFIG_X86_32)
+ if (def_to_bigsmp && nr_cpu_ids > 8) {
+ unsigned int cpu;
+ unsigned nr;
+
+ pr_warn("More than 8 CPUs detected - skipping them\n"
+ "Use CONFIG_X86_BIGSMP\n");
+
+ nr = 0;
+ for_each_present_cpu(cpu) {
+ if (nr >= 8)
+ set_cpu_present(cpu, false);
+ nr++;
+ }
+
+ nr = 0;
+ for_each_possible_cpu(cpu) {
+ if (nr >= 8)
+ set_cpu_possible(cpu, false);
+ nr++;
+ }
+
+ nr_cpu_ids = 8;
+ }
+#endif
+
if (!physid_isset(hard_smp_processor_id(), phys_cpu_present_map)) {
- printk(KERN_WARNING "weird, boot CPU (#%d) not listed"
- "by the BIOS.\n", hard_smp_processor_id());
+ pr_warn("weird, boot CPU (#%d) not listed by the BIOS\n",
+ hard_smp_processor_id());
+
physid_set(hard_smp_processor_id(), phys_cpu_present_map);
}
@@ -1056,11 +1018,10 @@ static int __init smp_sanity_check(unsigned max_cpus)
*/
if (!smp_found_config && !acpi_lapic) {
preempt_enable();
- printk(KERN_NOTICE "SMP motherboard not detected.\n");
+ pr_notice("SMP motherboard not detected\n");
disable_smp();
if (APIC_init_uniprocessor())
- printk(KERN_NOTICE "Local APIC not detected."
- " Using dummy APIC emulation.\n");
+ pr_notice("Local APIC not detected. Using dummy APIC emulation.\n");
return -1;
}
@@ -1068,10 +1029,9 @@ static int __init smp_sanity_check(unsigned max_cpus)
* Should not be necessary because the MP table should list the boot
* CPU too, but we do it for the sake of robustness anyway.
*/
- if (!check_phys_apicid_present(boot_cpu_physical_apicid)) {
- printk(KERN_NOTICE
- "weird, boot CPU (#%d) not listed by the BIOS.\n",
- boot_cpu_physical_apicid);
+ if (!apic->check_phys_apicid_present(boot_cpu_physical_apicid)) {
+ pr_notice("weird, boot CPU (#%d) not listed by the BIOS\n",
+ boot_cpu_physical_apicid);
physid_set(hard_smp_processor_id(), phys_cpu_present_map);
}
preempt_enable();
@@ -1081,11 +1041,13 @@ static int __init smp_sanity_check(unsigned max_cpus)
*/
if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid]) &&
!cpu_has_apic) {
- printk(KERN_ERR "BIOS bug, local APIC #%d not detected!...\n",
- boot_cpu_physical_apicid);
- printk(KERN_ERR "... forcing use of dummy APIC emulation."
- "(tell your hw vendor)\n");
+ if (!disable_apic) {
+ pr_err("BIOS bug, local APIC #%d not detected!...\n",
+ boot_cpu_physical_apicid);
+ pr_err("... forcing use of dummy APIC emulation (tell your hw vendor)\n");
+ }
smpboot_clear_io_apic();
+ disable_ioapic_support();
return -1;
}
@@ -1095,14 +1057,12 @@ static int __init smp_sanity_check(unsigned max_cpus)
* If SMP should be disabled, then really disable it!
*/
if (!max_cpus) {
- printk(KERN_INFO "SMP mode deactivated.\n");
+ pr_info("SMP mode deactivated\n");
smpboot_clear_io_apic();
- localise_nmi_watchdog();
-
connect_bsp_APIC();
setup_local_APIC();
- end_local_APIC_setup();
+ bsp_end_local_APIC_setup();
return -1;
}
@@ -1117,7 +1077,7 @@ static void __init smp_cpu_index_default(void)
for_each_possible_cpu(i) {
c = &cpu_data(i);
/* mark all to hotplug */
- c->cpu_index = NR_CPUS;
+ c->cpu_index = nr_cpu_ids;
}
}
@@ -1127,29 +1087,39 @@ static void __init smp_cpu_index_default(void)
*/
void __init native_smp_prepare_cpus(unsigned int max_cpus)
{
+ unsigned int i;
+
preempt_disable();
smp_cpu_index_default();
- current_cpu_data = boot_cpu_data;
- cpu_callin_map = cpumask_of_cpu(0);
- mb();
+
/*
* Setup boot CPU information
*/
- smp_store_cpu_info(0); /* Final full version of the data */
- boot_cpu_logical_apicid = logical_smp_processor_id();
+ smp_store_boot_cpu_info(); /* Final full version of the data */
+ cpumask_copy(cpu_callin_mask, cpumask_of(0));
+ mb();
+
current_thread_info()->cpu = 0; /* needed? */
+ for_each_possible_cpu(i) {
+ zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
+ zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
+ zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
+ }
set_cpu_sibling_map(0);
+
if (smp_sanity_check(max_cpus) < 0) {
- printk(KERN_INFO "SMP disabled\n");
+ pr_info("SMP disabled\n");
disable_smp();
goto out;
}
+ default_setup_apic_routing();
+
preempt_disable();
- if (GET_APIC_ID(read_apic_id()) != boot_cpu_physical_apicid) {
+ if (read_apic_id() != boot_cpu_physical_apicid) {
panic("Boot APIC ID in local APIC unexpected (%d vs %d)",
- GET_APIC_ID(read_apic_id()), boot_cpu_physical_apicid);
+ read_apic_id(), boot_cpu_physical_apicid);
/* Or can we switch back to PIC here? */
}
preempt_enable();
@@ -1161,187 +1131,212 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
*/
setup_local_APIC();
-#ifdef CONFIG_X86_64
+ if (x2apic_mode)
+ cpu0_logical_apicid = apic_read(APIC_LDR);
+ else
+ cpu0_logical_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
+
/*
* Enable IO APIC before setting up error vector
*/
if (!skip_ioapic_setup && nr_ioapics)
enable_IO_APIC();
-#endif
- end_local_APIC_setup();
- map_cpu_to_logical_apicid();
+ bsp_end_local_APIC_setup();
- setup_portio_remap();
+ if (apic->setup_portio_remap)
+ apic->setup_portio_remap();
smpboot_setup_io_apic();
/*
* Set up local APIC timer on boot CPU.
*/
- printk(KERN_INFO "CPU%d: ", 0);
+ pr_info("CPU%d: ", 0);
print_cpu_info(&cpu_data(0));
- setup_boot_clock();
+ x86_init.timers.setup_percpu_clockev();
+
+ if (is_uv_system())
+ uv_system_init();
+
+ set_mtrr_aps_delayed_init();
out:
preempt_enable();
}
+
+void arch_enable_nonboot_cpus_begin(void)
+{
+ set_mtrr_aps_delayed_init();
+}
+
+void arch_enable_nonboot_cpus_end(void)
+{
+ mtrr_aps_init();
+}
+
/*
* Early setup to make printk work.
*/
void __init native_smp_prepare_boot_cpu(void)
{
int me = smp_processor_id();
-#ifdef CONFIG_X86_32
- init_gdt(me);
-#endif
- switch_to_new_gdt();
- /* already set me in cpu_online_map in boot_cpu_init() */
- cpu_set(me, cpu_callout_map);
+ switch_to_new_gdt(me);
+ /* already set me in cpu_online_mask in boot_cpu_init() */
+ cpumask_set_cpu(me, cpu_callout_mask);
per_cpu(cpu_state, me) = CPU_ONLINE;
}
void __init native_smp_cpus_done(unsigned int max_cpus)
{
- pr_debug("Boot done.\n");
+ pr_debug("Boot done\n");
+ nmi_selftest();
impress_friends();
- smp_checks();
#ifdef CONFIG_X86_IO_APIC
setup_ioapic_dest();
#endif
- check_nmi_watchdog();
+ mtrr_aps_init();
}
-#ifdef CONFIG_HOTPLUG_CPU
-
-static void remove_siblinginfo(int cpu)
+static int __initdata setup_possible_cpus = -1;
+static int __init _setup_possible_cpus(char *str)
{
- int sibling;
- struct cpuinfo_x86 *c = &cpu_data(cpu);
-
- for_each_cpu_mask(sibling, per_cpu(cpu_core_map, cpu)) {
- cpu_clear(cpu, per_cpu(cpu_core_map, sibling));
- /*/
- * last thread sibling in this cpu core going down
- */
- if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1)
- cpu_data(sibling).booted_cores--;
- }
-
- for_each_cpu_mask(sibling, per_cpu(cpu_sibling_map, cpu))
- cpu_clear(cpu, per_cpu(cpu_sibling_map, sibling));
- cpus_clear(per_cpu(cpu_sibling_map, cpu));
- cpus_clear(per_cpu(cpu_core_map, cpu));
- c->phys_proc_id = 0;
- c->cpu_core_id = 0;
- cpu_clear(cpu, cpu_sibling_setup_map);
+ get_option(&str, &setup_possible_cpus);
+ return 0;
}
+early_param("possible_cpus", _setup_possible_cpus);
-static int additional_cpus __initdata = -1;
-
-static __init int setup_additional_cpus(char *s)
-{
- return s && get_option(&s, &additional_cpus) ? 0 : -EINVAL;
-}
-early_param("additional_cpus", setup_additional_cpus);
/*
- * cpu_possible_map should be static, it cannot change as cpu's
+ * cpu_possible_mask should be static, it cannot change as cpu's
* are onlined, or offlined. The reason is per-cpu data-structures
* are allocated by some modules at init time, and dont expect to
* do this dynamically on cpu arrival/departure.
- * cpu_present_map on the other hand can change dynamically.
+ * cpu_present_mask on the other hand can change dynamically.
* In case when cpu_hotplug is not compiled, then we resort to current
* behaviour, which is cpu_possible == cpu_present.
* - Ashok Raj
*
* Three ways to find out the number of additional hotplug CPUs:
* - If the BIOS specified disabled CPUs in ACPI/mptables use that.
- * - The user can overwrite it with additional_cpus=NUM
+ * - The user can overwrite it with possible_cpus=NUM
* - Otherwise don't reserve additional CPUs.
* We do this because additional CPUs waste a lot of memory.
* -AK
*/
__init void prefill_possible_map(void)
{
- int i;
- int possible;
+ int i, possible;
/* no processor from mptable or madt */
if (!num_processors)
num_processors = 1;
+ i = setup_max_cpus ?: 1;
+ if (setup_possible_cpus == -1) {
+ possible = num_processors;
#ifdef CONFIG_HOTPLUG_CPU
- if (additional_cpus == -1) {
- if (disabled_cpus > 0)
- additional_cpus = disabled_cpus;
- else
- additional_cpus = 0;
- }
+ if (setup_max_cpus)
+ possible += disabled_cpus;
#else
- additional_cpus = 0;
+ if (possible > i)
+ possible = i;
+#endif
+ } else
+ possible = setup_possible_cpus;
+
+ total_cpus = max_t(int, possible, num_processors + disabled_cpus);
+
+ /* nr_cpu_ids could be reduced via nr_cpus= */
+ if (possible > nr_cpu_ids) {
+ pr_warn("%d Processors exceeds NR_CPUS limit of %d\n",
+ possible, nr_cpu_ids);
+ possible = nr_cpu_ids;
+ }
+
+#ifdef CONFIG_HOTPLUG_CPU
+ if (!setup_max_cpus)
#endif
- possible = num_processors + additional_cpus;
- if (possible > NR_CPUS)
- possible = NR_CPUS;
+ if (possible > i) {
+ pr_warn("%d Processors exceeds max_cpus limit of %u\n",
+ possible, setup_max_cpus);
+ possible = i;
+ }
- printk(KERN_INFO "SMP: Allowing %d CPUs, %d hotplug CPUs\n",
+ pr_info("Allowing %d CPUs, %d hotplug CPUs\n",
possible, max_t(int, possible - num_processors, 0));
for (i = 0; i < possible; i++)
- cpu_set(i, cpu_possible_map);
+ set_cpu_possible(i, true);
+ for (; i < NR_CPUS; i++)
+ set_cpu_possible(i, false);
nr_cpu_ids = possible;
}
+#ifdef CONFIG_HOTPLUG_CPU
+
+static void remove_siblinginfo(int cpu)
+{
+ int sibling;
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+ for_each_cpu(sibling, cpu_core_mask(cpu)) {
+ cpumask_clear_cpu(cpu, cpu_core_mask(sibling));
+ /*/
+ * last thread sibling in this cpu core going down
+ */
+ if (cpumask_weight(cpu_sibling_mask(cpu)) == 1)
+ cpu_data(sibling).booted_cores--;
+ }
+
+ for_each_cpu(sibling, cpu_sibling_mask(cpu))
+ cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling));
+ cpumask_clear(cpu_sibling_mask(cpu));
+ cpumask_clear(cpu_core_mask(cpu));
+ c->phys_proc_id = 0;
+ c->cpu_core_id = 0;
+ cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);
+}
+
static void __ref remove_cpu_from_maps(int cpu)
{
- cpu_clear(cpu, cpu_online_map);
- cpu_clear(cpu, cpu_callout_map);
- cpu_clear(cpu, cpu_callin_map);
+ set_cpu_online(cpu, false);
+ cpumask_clear_cpu(cpu, cpu_callout_mask);
+ cpumask_clear_cpu(cpu, cpu_callin_mask);
/* was set by cpu_init() */
- cpu_clear(cpu, cpu_initialized);
+ cpumask_clear_cpu(cpu, cpu_initialized_mask);
numa_remove_cpu(cpu);
}
-int __cpu_disable(void)
+void cpu_disable_common(void)
{
int cpu = smp_processor_id();
- /*
- * Perhaps use cpufreq to drop frequency, but that could go
- * into generic code.
- *
- * We won't take down the boot processor on i386 due to some
- * interrupts only being able to be serviced by the BSP.
- * Especially so if we're not using an IOAPIC -zwane
- */
- if (cpu == 0)
- return -EBUSY;
-
- if (nmi_watchdog == NMI_LOCAL_APIC)
- stop_apic_nmi_watchdog(NULL);
- clear_local_APIC();
-
- /*
- * HACK:
- * Allow any queued timer interrupts to get serviced
- * This is only a temporary solution until we cleanup
- * fixup_irqs as we do for IA64.
- */
- local_irq_enable();
- mdelay(1);
-
- local_irq_disable();
remove_siblinginfo(cpu);
/* It's now safe to remove this processor from the online map */
+ lock_vector_lock();
remove_cpu_from_maps(cpu);
- fixup_irqs(cpu_online_map);
+ unlock_vector_lock();
+ fixup_irqs();
+}
+
+int native_cpu_disable(void)
+{
+ int ret;
+
+ ret = check_irq_vectors_for_cpu_disable();
+ if (ret)
+ return ret;
+
+ clear_local_APIC();
+
+ cpu_disable_common();
return 0;
}
-void __cpu_die(unsigned int cpu)
+void native_cpu_die(unsigned int cpu)
{
/* We don't do anything here: idle task is faking death itself. */
unsigned int i;
@@ -1349,38 +1344,151 @@ void __cpu_die(unsigned int cpu)
for (i = 0; i < 10; i++) {
/* They ack this in play_dead by setting CPU_DEAD */
if (per_cpu(cpu_state, cpu) == CPU_DEAD) {
- printk(KERN_INFO "CPU %d is now offline\n", cpu);
- if (1 == num_online_cpus())
- alternatives_smp_switch(0);
+ if (system_state == SYSTEM_RUNNING)
+ pr_info("CPU %u is now offline\n", cpu);
return;
}
msleep(100);
}
- printk(KERN_ERR "CPU %u didn't die...\n", cpu);
+ pr_err("CPU %u didn't die...\n", cpu);
+}
+
+void play_dead_common(void)
+{
+ idle_task_exit();
+ reset_lazy_tlbstate();
+ amd_e400_remove_cpu(raw_smp_processor_id());
+
+ mb();
+ /* Ack it */
+ __this_cpu_write(cpu_state, CPU_DEAD);
+
+ /*
+ * With physical CPU hotplug, we should halt the cpu
+ */
+ local_irq_disable();
+}
+
+static bool wakeup_cpu0(void)
+{
+ if (smp_processor_id() == 0 && enable_start_cpu0)
+ return true;
+
+ return false;
+}
+
+/*
+ * We need to flush the caches before going to sleep, lest we have
+ * dirty data in our caches when we come back up.
+ */
+static inline void mwait_play_dead(void)
+{
+ unsigned int eax, ebx, ecx, edx;
+ unsigned int highest_cstate = 0;
+ unsigned int highest_subcstate = 0;
+ void *mwait_ptr;
+ int i;
+
+ if (!this_cpu_has(X86_FEATURE_MWAIT))
+ return;
+ if (!this_cpu_has(X86_FEATURE_CLFLUSH))
+ return;
+ if (__this_cpu_read(cpu_info.cpuid_level) < CPUID_MWAIT_LEAF)
+ return;
+
+ eax = CPUID_MWAIT_LEAF;
+ ecx = 0;
+ native_cpuid(&eax, &ebx, &ecx, &edx);
+
+ /*
+ * eax will be 0 if EDX enumeration is not valid.
+ * Initialized below to cstate, sub_cstate value when EDX is valid.
+ */
+ if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) {
+ eax = 0;
+ } else {
+ edx >>= MWAIT_SUBSTATE_SIZE;
+ for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
+ if (edx & MWAIT_SUBSTATE_MASK) {
+ highest_cstate = i;
+ highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
+ }
+ }
+ eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
+ (highest_subcstate - 1);
+ }
+
+ /*
+ * This should be a memory location in a cache line which is
+ * unlikely to be touched by other processors. The actual
+ * content is immaterial as it is not actually modified in any way.
+ */
+ mwait_ptr = &current_thread_info()->flags;
+
+ wbinvd();
+
+ while (1) {
+ /*
+ * The CLFLUSH is a workaround for erratum AAI65 for
+ * the Xeon 7400 series. It's not clear it is actually
+ * needed, but it should be harmless in either case.
+ * The WBINVD is insufficient due to the spurious-wakeup
+ * case where we return around the loop.
+ */
+ mb();
+ clflush(mwait_ptr);
+ mb();
+ __monitor(mwait_ptr, 0, 0);
+ mb();
+ __mwait(eax, 0);
+ /*
+ * If NMI wants to wake up CPU0, start CPU0.
+ */
+ if (wakeup_cpu0())
+ start_cpu0();
+ }
+}
+
+static inline void hlt_play_dead(void)
+{
+ if (__this_cpu_read(cpu_info.x86) >= 4)
+ wbinvd();
+
+ while (1) {
+ native_halt();
+ /*
+ * If NMI wants to wake up CPU0, start CPU0.
+ */
+ if (wakeup_cpu0())
+ start_cpu0();
+ }
+}
+
+void native_play_dead(void)
+{
+ play_dead_common();
+ tboot_shutdown(TB_SHUTDOWN_WFS);
+
+ mwait_play_dead(); /* Only returns on failure */
+ if (cpuidle_play_dead())
+ hlt_play_dead();
}
+
#else /* ... !CONFIG_HOTPLUG_CPU */
-int __cpu_disable(void)
+int native_cpu_disable(void)
{
return -ENOSYS;
}
-void __cpu_die(unsigned int cpu)
+void native_cpu_die(unsigned int cpu)
{
/* We said "no" in __cpu_disable */
BUG();
}
-#endif
-/*
- * If the BIOS enumerates physical processors before logical,
- * maxcpus=N at enumeration-time can be used to disable HT.
- */
-static int __init parse_maxcpus(char *arg)
+void native_play_dead(void)
{
- extern unsigned int maxcpus;
-
- if (arg)
- maxcpus = simple_strtoul(arg, NULL, 0);
- return 0;
+ BUG();
}
-early_param("maxcpus", parse_maxcpus);
+
+#endif
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-12-06 04:00:04 +0000