linux/arch/x86/kernel/smpboot.c

1438 lines
35 KiB
C
Raw Normal View History

/*
* x86 SMP booting functions
*
* (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
* whom a great many thanks are extended.
*
* Thanks to Intel for making available several different Pentium,
* Pentium Pro and Pentium-II/Xeon MP machines.
* Original development of Linux SMP code supported by Caldera.
*
* This code is released under the GNU General Public License version 2 or
* later.
*
* Fixes
* Felix Koop : NR_CPUS used properly
* Jose Renau : Handle single CPU case.
* Alan Cox : By repeated request 8) - Total BogoMIPS report.
* Greg Wright : Fix for kernel stacks panic.
* Erich Boleyn : MP v1.4 and additional changes.
* Matthias Sattler : Changes for 2.1 kernel map.
* Michel Lespinasse : Changes for 2.1 kernel map.
* Michael Chastain : Change trampoline.S to gnu as.
* Alan Cox : Dumb bug: 'B' step PPro's are fine
* Ingo Molnar : Added APIC timers, based on code
* from Jose Renau
* Ingo Molnar : various cleanups and rewrites
* Tigran Aivazian : fixed "0.00 in /proc/uptime on SMP" bug.
* Maciej W. Rozycki : Bits for genuine 82489DX APICs
* Andi Kleen : Changed for SMP boot into long mode.
* Martin J. Bligh : Added support for multi-quad systems
* Dave Jones : Report invalid combinations of Athlon CPUs.
* Rusty Russell : Hacked into shape for new "hotplug" boot process.
* Andi Kleen : Converted to new state machine.
* Ashok Raj : CPU hotplug support
* Glauber Costa : i386 and x86_64 integration
*/
#include <linux/init.h>
#include <linux/smp.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/percpu.h>
#include <linux/bootmem.h>
#include <linux/err.h>
#include <linux/nmi.h>
#include <linux/tboot.h>
#include <linux/stackprotector.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/gfp.h>
#include <asm/acpi.h>
#include <asm/desc.h>
#include <asm/nmi.h>
#include <asm/irq.h>
#include <asm/idle.h>
#include <asm/trampoline.h>
#include <asm/cpu.h>
#include <asm/numa.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/mtrr.h>
#include <asm/mwait.h>
#include <asm/apic.h>
#include <asm/io_apic.h>
x86: fix wakeup_cpu with numaq/es7000, v2 Impact: fix secondary-CPU wakeup/init path with numaq and es7000 While looking at wakeup_secondary_cpu for WAKE_SECONDARY_VIA_NMI: |#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) |{ | unsigned long send_status, accept_status = 0; | int maxlvt; |... | if (APIC_INTEGRATED(apic_version[phys_apicid])) { | maxlvt = lapic_get_maxlvt(); I noticed that there is no warning about undefined phys_apicid... because WAKE_SECONDARY_VIA_NMI and WAKE_SECONDARY_VIA_INIT can not be defined at the same time. So NUMAQ is using wrong wakeup_secondary_cpu. WAKE_SECONDARY_VIA_NMI, WAKE_SECONDARY_VIA_INIT and WAKE_SECONDARY_VIA_MIP are variants of a weird and fragile preprocessor-driven "HAL" mechanisms to specify the kind of secondary-CPU wakeup strategy a given x86 kernel will use. The vast majority of systems want to use INIT for secondary wakeup - NUMAQ uses an NMI, (old-style-) ES7000 uses 'MIP' (a firmware driven in-memory flag to let secondaries continue). So convert these mechanisms to x86_quirks and add a ->wakeup_secondary_cpu() method to specify the rare exception to the sane default. Extend genapic accordingly as well, for 32-bit. While looking further, I noticed that functions in wakecup.h for numaq and es7000 are different to the default in mach_wakecpu.h - but smpboot.c will only use default mach_wakecpu.h with smphook.h. So we need to add mach_wakecpu.h for mach_generic, to properly support numaq and es7000, and vectorize the following SMP init methods: int trampoline_phys_low; int trampoline_phys_high; void (*wait_for_init_deassert)(atomic_t *deassert); void (*smp_callin_clear_local_apic)(void); void (*store_NMI_vector)(unsigned short *high, unsigned short *low); void (*restore_NMI_vector)(unsigned short *high, unsigned short *low); void (*inquire_remote_apic)(int apicid); Signed-off-by: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-16 11:12:49 +00:00
#include <asm/setup.h>
#include <asm/uv/uv.h>
#include <linux/mc146818rtc.h>
#include <asm/smpboot_hooks.h>
#include <asm/i8259.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))
/*
* We need this for trampoline_base protection from concurrent accesses when
* off- and onlining cores wildly.
*/
static DEFINE_MUTEX(x86_cpu_hotplug_driver_mutex);
void cpu_hotplug_driver_lock(void)
{
mutex_lock(&x86_cpu_hotplug_driver_mutex);
}
void cpu_hotplug_driver_unlock(void)
{
mutex_unlock(&x86_cpu_hotplug_driver_mutex);
}
ssize_t arch_cpu_probe(const char *buf, size_t count) { return -1; }
ssize_t arch_cpu_release(const char *buf, size_t count) { return -1; }
#else
static 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;
/* representing HT siblings of each logical CPU */
DEFINE_PER_CPU(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_var_t, cpu_core_map);
EXPORT_PER_CPU_SYMBOL(cpu_core_map);
DEFINE_PER_CPU(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);
atomic_t init_deasserted;
/*
* Report back to the Boot Processor.
* Running on AP.
*/
static void __cpuinit smp_callin(void)
{
int cpuid, phys_id;
unsigned long timeout;
/*
* If waken up by an INIT in an 82489DX configuration
* 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.
*/
if (apic->wait_for_init_deassert)
apic->wait_for_init_deassert(&init_deasserted);
/*
* (This works even if the APIC is not enabled.)
*/
phys_id = read_apic_id();
cpuid = smp_processor_id();
if (cpumask_test_cpu(cpuid, cpu_callin_mask)) {
panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__,
phys_id, cpuid);
}
pr_debug("CPU#%d (phys ID: %d) waiting for CALLOUT\n", cpuid, phys_id);
/*
* STARTUP IPIs are fragile beasts as they might sometimes
* trigger some glue motherboard logic. Complete APIC bus
* silence for 1 second, this overestimates the time the
* boot CPU is spending to send the up to 2 STARTUP IPIs
* by a factor of two. This should be enough.
*/
/*
* Waiting 2s total for startup (udelay is not yet working)
*/
timeout = jiffies + 2*HZ;
while (time_before(jiffies, timeout)) {
/*
* Has the boot CPU finished it's STARTUP sequence?
*/
if (cpumask_test_cpu(cpuid, cpu_callout_mask))
break;
cpu_relax();
}
if (!time_before(jiffies, timeout)) {
panic("%s: CPU%d started up but did not get a callout!\n",
__func__, cpuid);
}
/*
* the boot CPU has finished the init stage and is spinning
* on callin_map until we finish. We are free to set up this
* CPU, first the APIC. (this is probably redundant on most
* boards)
*/
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();
/*
* Need to setup vector mappings before we enable interrupts.
*/
setup_vector_irq(smp_processor_id());
/*
* Get our bogomips.
*
* Need to enable IRQs because it can take longer and then
* the NMI watchdog might kill us.
*/
local_irq_enable();
calibrate_delay();
local_irq_disable();
pr_debug("Stack at about %p\n", &cpuid);
/*
* Save our processor parameters
*/
smp_store_cpu_info(cpuid);
/*
* This must be done before setting cpu_online_mask
* or calling notify_cpu_starting.
*/
set_cpu_sibling_map(raw_smp_processor_id());
wmb();
notify_cpu_starting(cpuid);
/*
* Allow the master to continue.
*/
cpumask_set_cpu(cpuid, cpu_callin_mask);
}
/*
* Activate a secondary processor.
*/
notrace static void __cpuinit 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.
*/
cpu_init();
preempt_disable();
smp_callin();
x86-32: Separate 1:1 pagetables from swapper_pg_dir This patch fixes machine crashes which occur when heavily exercising the CPU hotplug codepaths on a 32-bit kernel. These crashes are caused by AMD Erratum 383 and result in a fatal machine check exception. Here's the scenario: 1. On 32-bit, the swapper_pg_dir page table is used as the initial page table for booting a secondary CPU. 2. To make this work, swapper_pg_dir needs a direct mapping of physical memory in it (the low mappings). By adding those low, large page (2M) mappings (PAE kernel), we create the necessary conditions for Erratum 383 to occur. 3. Other CPUs which do not participate in the off- and onlining game may use swapper_pg_dir while the low mappings are present (when leave_mm is called). For all steps below, the CPU referred to is a CPU that is using swapper_pg_dir, and not the CPU which is being onlined. 4. The presence of the low mappings in swapper_pg_dir can result in TLB entries for addresses below __PAGE_OFFSET to be established speculatively. These TLB entries are marked global and large. 5. When the CPU with such TLB entry switches to another page table, this TLB entry remains because it is global. 6. The process then generates an access to an address covered by the above TLB entry but there is a permission mismatch - the TLB entry covers a large global page not accessible to userspace. 7. Due to this permission mismatch a new 4kb, user TLB entry gets established. Further, Erratum 383 provides for a small window of time where both TLB entries are present. This results in an uncorrectable machine check exception signalling a TLB multimatch which panics the machine. There are two ways to fix this issue: 1. Always do a global TLB flush when a new cr3 is loaded and the old page table was swapper_pg_dir. I consider this a hack hard to understand and with performance implications 2. Do not use swapper_pg_dir to boot secondary CPUs like 64-bit does. This patch implements solution 2. It introduces a trampoline_pg_dir which has the same layout as swapper_pg_dir with low_mappings. This page table is used as the initial page table of the booting CPU. Later in the bringup process, it switches to swapper_pg_dir and does a global TLB flush. This fixes the crashes in our test cases. -v2: switch to swapper_pg_dir right after entering start_secondary() so that we are able to access percpu data which might not be mapped in the trampoline page table. Signed-off-by: Joerg Roedel <joerg.roedel@amd.com> LKML-Reference: <20100816123833.GB28147@aftab> Signed-off-by: Borislav Petkov <borislav.petkov@amd.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-08-16 12:38:33 +00:00
#ifdef CONFIG_X86_32
/* switch away from the initial page table */
x86-32: Separate 1:1 pagetables from swapper_pg_dir This patch fixes machine crashes which occur when heavily exercising the CPU hotplug codepaths on a 32-bit kernel. These crashes are caused by AMD Erratum 383 and result in a fatal machine check exception. Here's the scenario: 1. On 32-bit, the swapper_pg_dir page table is used as the initial page table for booting a secondary CPU. 2. To make this work, swapper_pg_dir needs a direct mapping of physical memory in it (the low mappings). By adding those low, large page (2M) mappings (PAE kernel), we create the necessary conditions for Erratum 383 to occur. 3. Other CPUs which do not participate in the off- and onlining game may use swapper_pg_dir while the low mappings are present (when leave_mm is called). For all steps below, the CPU referred to is a CPU that is using swapper_pg_dir, and not the CPU which is being onlined. 4. The presence of the low mappings in swapper_pg_dir can result in TLB entries for addresses below __PAGE_OFFSET to be established speculatively. These TLB entries are marked global and large. 5. When the CPU with such TLB entry switches to another page table, this TLB entry remains because it is global. 6. The process then generates an access to an address covered by the above TLB entry but there is a permission mismatch - the TLB entry covers a large global page not accessible to userspace. 7. Due to this permission mismatch a new 4kb, user TLB entry gets established. Further, Erratum 383 provides for a small window of time where both TLB entries are present. This results in an uncorrectable machine check exception signalling a TLB multimatch which panics the machine. There are two ways to fix this issue: 1. Always do a global TLB flush when a new cr3 is loaded and the old page table was swapper_pg_dir. I consider this a hack hard to understand and with performance implications 2. Do not use swapper_pg_dir to boot secondary CPUs like 64-bit does. This patch implements solution 2. It introduces a trampoline_pg_dir which has the same layout as swapper_pg_dir with low_mappings. This page table is used as the initial page table of the booting CPU. Later in the bringup process, it switches to swapper_pg_dir and does a global TLB flush. This fixes the crashes in our test cases. -v2: switch to swapper_pg_dir right after entering start_secondary() so that we are able to access percpu data which might not be mapped in the trampoline page table. Signed-off-by: Joerg Roedel <joerg.roedel@amd.com> LKML-Reference: <20100816123833.GB28147@aftab> Signed-off-by: Borislav Petkov <borislav.petkov@amd.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-08-16 12:38:33 +00:00
load_cr3(swapper_pg_dir);
__flush_tlb_all();
#endif
/* otherwise gcc will move up smp_processor_id before the cpu_init */
barrier();
/*
* Check TSC synchronization with the BP:
*/
check_tsc_sync_target();
/*
* 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();
lock_vector_lock();
set_cpu_online(smp_processor_id(), true);
unlock_vector_lock();
ipi_call_unlock();
per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
x86_platform.nmi_init();
x86: cpu-hotplug: Prevent softirq wakeup on wrong CPU After a newly plugged CPU sets the cpu_online bit it enables interrupts and goes idle. The cpu which brought up the new cpu waits for the cpu_online bit and when it observes it, it sets the cpu_active bit for this cpu. The cpu_active bit is the relevant one for the scheduler to consider the cpu as a viable target. With forced threaded interrupt handlers which imply forced threaded softirqs we observed the following race: cpu 0 cpu 1 bringup(cpu1); set_cpu_online(smp_processor_id(), true); local_irq_enable(); while (!cpu_online(cpu1)); timer_interrupt() -> wake_up(softirq_thread_cpu1); -> enqueue_on(softirq_thread_cpu1, cpu0); ^^^^ cpu_notify(CPU_ONLINE, cpu1); -> sched_cpu_active(cpu1) -> set_cpu_active((cpu1, true); When an interrupt happens before the cpu_active bit is set by the cpu which brought up the newly onlined cpu, then the scheduler refuses to enqueue the woken thread which is bound to that newly onlined cpu on that newly onlined cpu due to the not yet set cpu_active bit and selects a fallback runqueue. Not really an expected and desirable behaviour. So far this has only been observed with forced hard/softirq threading, but in theory this could happen without forced threaded hard/softirqs as well. It's probably unobservable as it would take a massive interrupt storm on the newly onlined cpu which causes the softirq loop to wake up the softirq thread and an even longer delay of the cpu which waits for the cpu_online bit. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Peter Zijlstra <peterz@infradead.org> Cc: stable@kernel.org # 2.6.39
2010-07-20 12:34:50 +00:00
/*
* Wait until the cpu which brought this one up marked it
* online before enabling interrupts. If we don't do that then
* we can end up waking up the softirq thread before this cpu
* reached the active state, which makes the scheduler unhappy
* and schedule the softirq thread on the wrong cpu. This is
* only observable with forced threaded interrupts, but in
* theory it could also happen w/o them. It's just way harder
* to achieve.
*/
while (!cpumask_test_cpu(smp_processor_id(), cpu_active_mask))
cpu_relax();
/* enable local interrupts */
local_irq_enable();
/* to prevent fake stack check failure in clock setup */
boot_init_stack_canary();
x86_cpuinit.setup_percpu_clockev();
wmb();
cpu_idle();
}
/*
* The bootstrap kernel entry code has set these up. Save them for
* a given CPU
*/
void __cpuinit smp_store_cpu_info(int id)
{
struct cpuinfo_x86 *c = &cpu_data(id);
*c = boot_cpu_data;
c->cpu_index = id;
if (id != 0)
identify_secondary_cpu(c);
}
static void __cpuinit link_thread_siblings(int cpu1, int cpu2)
{
cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2));
cpumask_set_cpu(cpu2, cpu_sibling_mask(cpu1));
cpumask_set_cpu(cpu1, cpu_core_mask(cpu2));
cpumask_set_cpu(cpu2, cpu_core_mask(cpu1));
cpumask_set_cpu(cpu1, cpu_llc_shared_mask(cpu2));
cpumask_set_cpu(cpu2, cpu_llc_shared_mask(cpu1));
}
void __cpuinit set_cpu_sibling_map(int cpu)
{
int i;
struct cpuinfo_x86 *c = &cpu_data(cpu);
cpumask_set_cpu(cpu, cpu_sibling_setup_mask);
if (smp_num_siblings > 1) {
for_each_cpu(i, cpu_sibling_setup_mask) {
struct cpuinfo_x86 *o = &cpu_data(i);
if (cpu_has(c, X86_FEATURE_TOPOEXT)) {
if (c->phys_proc_id == o->phys_proc_id &&
per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i) &&
c->compute_unit_id == o->compute_unit_id)
link_thread_siblings(cpu, i);
} else if (c->phys_proc_id == o->phys_proc_id &&
c->cpu_core_id == o->cpu_core_id) {
link_thread_siblings(cpu, i);
}
}
} else {
cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
}
cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
if (__this_cpu_read(cpu_info.x86_max_cores) == 1) {
cpumask_copy(cpu_core_mask(cpu), cpu_sibling_mask(cpu));
c->booted_cores = 1;
return;
}
for_each_cpu(i, cpu_sibling_setup_mask) {
if (per_cpu(cpu_llc_id, cpu) != BAD_APICID &&
per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) {
cpumask_set_cpu(i, cpu_llc_shared_mask(cpu));
cpumask_set_cpu(cpu, cpu_llc_shared_mask(i));
}
if (c->phys_proc_id == cpu_data(i).phys_proc_id) {
cpumask_set_cpu(i, cpu_core_mask(cpu));
cpumask_set_cpu(cpu, cpu_core_mask(i));
/*
* Does this new cpu bringup a new core?
*/
if (cpumask_weight(cpu_sibling_mask(cpu)) == 1) {
/*
* for each core in package, increment
* the booted_cores for this new cpu
*/
if (cpumask_first(cpu_sibling_mask(i)) == i)
c->booted_cores++;
/*
* increment the core count for all
* the other cpus in this package
*/
if (i != cpu)
cpu_data(i).booted_cores++;
} else if (i != cpu && !c->booted_cores)
c->booted_cores = cpu_data(i).booted_cores;
}
}
}
/* maps the cpu to the sched domain representing multi-core */
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
*/
x86, sched: Workaround broken sched domain creation for AMD Magny-Cours Current sched domain creation code can't handle multi-node processors. When switching to power_savings scheduling errors show up and system might hang later on (due to broken sched domain hierarchy): # echo 0 >> /sys/devices/system/cpu/sched_mc_power_savings CPU0 attaching sched-domain: domain 0: span 0-5 level MC groups: 0 1 2 3 4 5 domain 1: span 0-23 level NODE groups: 0-5 6-11 18-23 12-17 ... # echo 1 >> /sys/devices/system/cpu/sched_mc_power_savings CPU0 attaching sched-domain: domain 0: span 0-11 level MC groups: 0 1 2 3 4 5 6 7 8 9 10 11 ERROR: parent span is not a superset of domain->span domain 1: span 0-5 level CPU ERROR: domain->groups does not contain CPU0 groups: 6-11 (__cpu_power = 12288) ERROR: groups don't span domain->span domain 2: span 0-23 level NODE groups: ERROR: domain->cpu_power not set ERROR: groups don't span domain->span ... Fixing all aspects of power-savings scheduling for Magny-Cours needs some larger changes in the sched domain creation code. As a short-term and temporary workaround avoid the problems by extending "the worst possible hack" ;-( and always use llc_shared_map on AMD Magny-Cours when MC domain span is calculated. With this I get: # echo 1 >> /sys/devices/system/cpu/sched_mc_power_savings CPU0 attaching sched-domain: domain 0: span 0-5 level MC groups: 0 1 2 3 4 5 domain 1: span 0-5 level CPU groups: 0-5 (__cpu_power = 6144) domain 2: span 0-23 level NODE groups: 0-5 (__cpu_power = 6144) 6-11 (__cpu_power = 6144) 18-23 (__cpu_power = 6144) 12-17 (__cpu_power = 6144) ... I.e. no errors during sched domain creation, no system hangs, and also mc_power_savings scheduling works to a certain extend. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-09-03 07:44:28 +00:00
if ((sched_mc_power_savings || sched_smt_power_savings) &&
!(cpu_has(c, X86_FEATURE_AMD_DCM)))
return cpu_core_mask(cpu);
else
return cpu_llc_shared_mask(cpu);
}
static void impress_friends(void)
{
int cpu;
unsigned long bogosum = 0;
/*
* Allow the user to impress friends.
*/
pr_debug("Before bogomips.\n");
for_each_possible_cpu(cpu)
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",
num_online_cpus(),
bogosum/(500000/HZ),
(bogosum/(5000/HZ))%100);
pr_debug("Before bogocount - setting activated=1.\n");
}
x86: fix wakeup_cpu with numaq/es7000, v2 Impact: fix secondary-CPU wakeup/init path with numaq and es7000 While looking at wakeup_secondary_cpu for WAKE_SECONDARY_VIA_NMI: |#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) |{ | unsigned long send_status, accept_status = 0; | int maxlvt; |... | if (APIC_INTEGRATED(apic_version[phys_apicid])) { | maxlvt = lapic_get_maxlvt(); I noticed that there is no warning about undefined phys_apicid... because WAKE_SECONDARY_VIA_NMI and WAKE_SECONDARY_VIA_INIT can not be defined at the same time. So NUMAQ is using wrong wakeup_secondary_cpu. WAKE_SECONDARY_VIA_NMI, WAKE_SECONDARY_VIA_INIT and WAKE_SECONDARY_VIA_MIP are variants of a weird and fragile preprocessor-driven "HAL" mechanisms to specify the kind of secondary-CPU wakeup strategy a given x86 kernel will use. The vast majority of systems want to use INIT for secondary wakeup - NUMAQ uses an NMI, (old-style-) ES7000 uses 'MIP' (a firmware driven in-memory flag to let secondaries continue). So convert these mechanisms to x86_quirks and add a ->wakeup_secondary_cpu() method to specify the rare exception to the sane default. Extend genapic accordingly as well, for 32-bit. While looking further, I noticed that functions in wakecup.h for numaq and es7000 are different to the default in mach_wakecpu.h - but smpboot.c will only use default mach_wakecpu.h with smphook.h. So we need to add mach_wakecpu.h for mach_generic, to properly support numaq and es7000, and vectorize the following SMP init methods: int trampoline_phys_low; int trampoline_phys_high; void (*wait_for_init_deassert)(atomic_t *deassert); void (*smp_callin_clear_local_apic)(void); void (*store_NMI_vector)(unsigned short *high, unsigned short *low); void (*restore_NMI_vector)(unsigned short *high, unsigned short *low); void (*inquire_remote_apic)(int apicid); Signed-off-by: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-16 11:12:49 +00:00
void __inquire_remote_apic(int apicid)
{
unsigned i, regs[] = { APIC_ID >> 4, APIC_LVR >> 4, APIC_SPIV >> 4 };
const char * const names[] = { "ID", "VERSION", "SPIV" };
int timeout;
u32 status;
printk(KERN_INFO "Inquiring remote APIC 0x%x...\n", apicid);
for (i = 0; i < ARRAY_SIZE(regs); i++) {
printk(KERN_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");
apic_icr_write(APIC_DM_REMRD | regs[i], apicid);
timeout = 0;
do {
udelay(100);
status = apic_read(APIC_ICR) & APIC_ICR_RR_MASK;
} while (status == APIC_ICR_RR_INPROG && timeout++ < 1000);
switch (status) {
case APIC_ICR_RR_VALID:
status = apic_read(APIC_RRR);
printk(KERN_CONT "%08x\n", status);
break;
default:
printk(KERN_CONT "failed\n");
}
}
}
/*
* 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.
*/
int __cpuinit
x86: fix wakeup_cpu with numaq/es7000, v2 Impact: fix secondary-CPU wakeup/init path with numaq and es7000 While looking at wakeup_secondary_cpu for WAKE_SECONDARY_VIA_NMI: |#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) |{ | unsigned long send_status, accept_status = 0; | int maxlvt; |... | if (APIC_INTEGRATED(apic_version[phys_apicid])) { | maxlvt = lapic_get_maxlvt(); I noticed that there is no warning about undefined phys_apicid... because WAKE_SECONDARY_VIA_NMI and WAKE_SECONDARY_VIA_INIT can not be defined at the same time. So NUMAQ is using wrong wakeup_secondary_cpu. WAKE_SECONDARY_VIA_NMI, WAKE_SECONDARY_VIA_INIT and WAKE_SECONDARY_VIA_MIP are variants of a weird and fragile preprocessor-driven "HAL" mechanisms to specify the kind of secondary-CPU wakeup strategy a given x86 kernel will use. The vast majority of systems want to use INIT for secondary wakeup - NUMAQ uses an NMI, (old-style-) ES7000 uses 'MIP' (a firmware driven in-memory flag to let secondaries continue). So convert these mechanisms to x86_quirks and add a ->wakeup_secondary_cpu() method to specify the rare exception to the sane default. Extend genapic accordingly as well, for 32-bit. While looking further, I noticed that functions in wakecup.h for numaq and es7000 are different to the default in mach_wakecpu.h - but smpboot.c will only use default mach_wakecpu.h with smphook.h. So we need to add mach_wakecpu.h for mach_generic, to properly support numaq and es7000, and vectorize the following SMP init methods: int trampoline_phys_low; int trampoline_phys_high; void (*wait_for_init_deassert)(atomic_t *deassert); void (*smp_callin_clear_local_apic)(void); void (*store_NMI_vector)(unsigned short *high, unsigned short *low); void (*restore_NMI_vector)(unsigned short *high, unsigned short *low); void (*inquire_remote_apic)(int apicid); Signed-off-by: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-16 11:12:49 +00:00
wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip)
{
unsigned long send_status, accept_status = 0;
int maxlvt;
/* Target chip */
/* Boot on the stack */
/* Kick the second */
apic_icr_write(APIC_DM_NMI | apic->dest_logical, logical_apicid);
pr_debug("Waiting for send to finish...\n");
send_status = safe_apic_wait_icr_idle();
/*
* Give the other CPU some time to accept the IPI.
*/
udelay(200);
x86: fix wakeup_cpu with numaq/es7000, v2 Impact: fix secondary-CPU wakeup/init path with numaq and es7000 While looking at wakeup_secondary_cpu for WAKE_SECONDARY_VIA_NMI: |#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) |{ | unsigned long send_status, accept_status = 0; | int maxlvt; |... | if (APIC_INTEGRATED(apic_version[phys_apicid])) { | maxlvt = lapic_get_maxlvt(); I noticed that there is no warning about undefined phys_apicid... because WAKE_SECONDARY_VIA_NMI and WAKE_SECONDARY_VIA_INIT can not be defined at the same time. So NUMAQ is using wrong wakeup_secondary_cpu. WAKE_SECONDARY_VIA_NMI, WAKE_SECONDARY_VIA_INIT and WAKE_SECONDARY_VIA_MIP are variants of a weird and fragile preprocessor-driven "HAL" mechanisms to specify the kind of secondary-CPU wakeup strategy a given x86 kernel will use. The vast majority of systems want to use INIT for secondary wakeup - NUMAQ uses an NMI, (old-style-) ES7000 uses 'MIP' (a firmware driven in-memory flag to let secondaries continue). So convert these mechanisms to x86_quirks and add a ->wakeup_secondary_cpu() method to specify the rare exception to the sane default. Extend genapic accordingly as well, for 32-bit. While looking further, I noticed that functions in wakecup.h for numaq and es7000 are different to the default in mach_wakecpu.h - but smpboot.c will only use default mach_wakecpu.h with smphook.h. So we need to add mach_wakecpu.h for mach_generic, to properly support numaq and es7000, and vectorize the following SMP init methods: int trampoline_phys_low; int trampoline_phys_high; void (*wait_for_init_deassert)(atomic_t *deassert); void (*smp_callin_clear_local_apic)(void); void (*store_NMI_vector)(unsigned short *high, unsigned short *low); void (*restore_NMI_vector)(unsigned short *high, unsigned short *low); void (*inquire_remote_apic)(int apicid); Signed-off-by: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-16 11:12:49 +00:00
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");
if (accept_status)
printk(KERN_ERR "APIC delivery error (%lx).\n", accept_status);
return (send_status | accept_status);
}
static int __cpuinit
x86: fix wakeup_cpu with numaq/es7000, v2 Impact: fix secondary-CPU wakeup/init path with numaq and es7000 While looking at wakeup_secondary_cpu for WAKE_SECONDARY_VIA_NMI: |#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) |{ | unsigned long send_status, accept_status = 0; | int maxlvt; |... | if (APIC_INTEGRATED(apic_version[phys_apicid])) { | maxlvt = lapic_get_maxlvt(); I noticed that there is no warning about undefined phys_apicid... because WAKE_SECONDARY_VIA_NMI and WAKE_SECONDARY_VIA_INIT can not be defined at the same time. So NUMAQ is using wrong wakeup_secondary_cpu. WAKE_SECONDARY_VIA_NMI, WAKE_SECONDARY_VIA_INIT and WAKE_SECONDARY_VIA_MIP are variants of a weird and fragile preprocessor-driven "HAL" mechanisms to specify the kind of secondary-CPU wakeup strategy a given x86 kernel will use. The vast majority of systems want to use INIT for secondary wakeup - NUMAQ uses an NMI, (old-style-) ES7000 uses 'MIP' (a firmware driven in-memory flag to let secondaries continue). So convert these mechanisms to x86_quirks and add a ->wakeup_secondary_cpu() method to specify the rare exception to the sane default. Extend genapic accordingly as well, for 32-bit. While looking further, I noticed that functions in wakecup.h for numaq and es7000 are different to the default in mach_wakecpu.h - but smpboot.c will only use default mach_wakecpu.h with smphook.h. So we need to add mach_wakecpu.h for mach_generic, to properly support numaq and es7000, and vectorize the following SMP init methods: int trampoline_phys_low; int trampoline_phys_high; void (*wait_for_init_deassert)(atomic_t *deassert); void (*smp_callin_clear_local_apic)(void); void (*store_NMI_vector)(unsigned short *high, unsigned short *low); void (*restore_NMI_vector)(unsigned short *high, unsigned short *low); void (*inquire_remote_apic)(int apicid); Signed-off-by: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-16 11:12:49 +00:00
wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
{
unsigned long send_status, accept_status = 0;
int maxlvt, num_starts, j;
x86: APIC: remove apic_write_around(); use alternatives Use alternatives to select the workaround for the 11AP Pentium erratum for the affected steppings on the fly rather than build time. Remove the X86_GOOD_APIC configuration option and replace all the calls to apic_write_around() with plain apic_write(), protecting accesses to the ESR as appropriate due to the 3AP Pentium erratum. Remove apic_read_around() and all its invocations altogether as not needed. Remove apic_write_atomic() and all its implementing backends. The use of ASM_OUTPUT2() is not strictly needed for input constraints, but I have used it for readability's sake. I had the feeling no one else was brave enough to do it, so I went ahead and here it is. Verified by checking the generated assembly and tested with both a 32-bit and a 64-bit configuration, also with the 11AP "feature" forced on and verified with gdb on /proc/kcore to work as expected (as an 11AP machines are quite hard to get hands on these days). Some script complained about the use of "volatile", but apic_write() needs it for the same reason and is effectively a replacement for writel(), so I have disregarded it. I am not sure what the policy wrt defconfig files is, they are generated and there is risk of a conflict resulting from an unrelated change, so I have left changes to them out. The option will get removed from them at the next run. Some testing with machines other than mine will be needed to avoid some stupid mistake, but despite its volume, the change is not really that intrusive, so I am fairly confident that because it works for me, it will everywhere. Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-16 18:15:30 +00:00
maxlvt = lapic_get_maxlvt();
/*
* Be paranoid about clearing APIC errors.
*/
if (APIC_INTEGRATED(apic_version[phys_apicid])) {
x86: APIC: remove apic_write_around(); use alternatives Use alternatives to select the workaround for the 11AP Pentium erratum for the affected steppings on the fly rather than build time. Remove the X86_GOOD_APIC configuration option and replace all the calls to apic_write_around() with plain apic_write(), protecting accesses to the ESR as appropriate due to the 3AP Pentium erratum. Remove apic_read_around() and all its invocations altogether as not needed. Remove apic_write_atomic() and all its implementing backends. The use of ASM_OUTPUT2() is not strictly needed for input constraints, but I have used it for readability's sake. I had the feeling no one else was brave enough to do it, so I went ahead and here it is. Verified by checking the generated assembly and tested with both a 32-bit and a 64-bit configuration, also with the 11AP "feature" forced on and verified with gdb on /proc/kcore to work as expected (as an 11AP machines are quite hard to get hands on these days). Some script complained about the use of "volatile", but apic_write() needs it for the same reason and is effectively a replacement for writel(), so I have disregarded it. I am not sure what the policy wrt defconfig files is, they are generated and there is risk of a conflict resulting from an unrelated change, so I have left changes to them out. The option will get removed from them at the next run. Some testing with machines other than mine will be needed to avoid some stupid mistake, but despite its volume, the change is not really that intrusive, so I am fairly confident that because it works for me, it will everywhere. Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-16 18:15:30 +00:00
if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
}
pr_debug("Asserting INIT.\n");
/*
* Turn INIT on target chip
*/
/*
* Send IPI
*/
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");
/* Target chip */
/* Send IPI */
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();
mb();
atomic_set(&init_deasserted, 1);
/*
* Should we send STARTUP IPIs ?
*
* Determine this based on the APIC version.
* If we don't have an integrated APIC, don't send the STARTUP IPIs.
*/
if (APIC_INTEGRATED(apic_version[phys_apicid]))
num_starts = 2;
else
num_starts = 0;
/*
* Paravirt / VMI wants a startup IPI hook here to set up the
* target processor state.
*/
startup_ipi_hook(phys_apicid, (unsigned long) start_secondary,
stack_start);
/*
* Run STARTUP IPI loop.
*/
pr_debug("#startup loops: %d.\n", num_starts);
for (j = 1; j <= num_starts; j++) {
pr_debug("Sending STARTUP #%d.\n", j);
x86: APIC: remove apic_write_around(); use alternatives Use alternatives to select the workaround for the 11AP Pentium erratum for the affected steppings on the fly rather than build time. Remove the X86_GOOD_APIC configuration option and replace all the calls to apic_write_around() with plain apic_write(), protecting accesses to the ESR as appropriate due to the 3AP Pentium erratum. Remove apic_read_around() and all its invocations altogether as not needed. Remove apic_write_atomic() and all its implementing backends. The use of ASM_OUTPUT2() is not strictly needed for input constraints, but I have used it for readability's sake. I had the feeling no one else was brave enough to do it, so I went ahead and here it is. Verified by checking the generated assembly and tested with both a 32-bit and a 64-bit configuration, also with the 11AP "feature" forced on and verified with gdb on /proc/kcore to work as expected (as an 11AP machines are quite hard to get hands on these days). Some script complained about the use of "volatile", but apic_write() needs it for the same reason and is effectively a replacement for writel(), so I have disregarded it. I am not sure what the policy wrt defconfig files is, they are generated and there is risk of a conflict resulting from an unrelated change, so I have left changes to them out. The option will get removed from them at the next run. Some testing with machines other than mine will be needed to avoid some stupid mistake, but despite its volume, the change is not really that intrusive, so I am fairly confident that because it works for me, it will everywhere. Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-16 18:15:30 +00:00
if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
pr_debug("After apic_write.\n");
/*
* STARTUP IPI
*/
/* Target chip */
/* Boot on the stack */
/* Kick the second */
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("Waiting for send to finish...\n");
send_status = safe_apic_wait_icr_idle();
/*
* Give the other CPU some time to accept the IPI.
*/
udelay(200);
x86: APIC: remove apic_write_around(); use alternatives Use alternatives to select the workaround for the 11AP Pentium erratum for the affected steppings on the fly rather than build time. Remove the X86_GOOD_APIC configuration option and replace all the calls to apic_write_around() with plain apic_write(), protecting accesses to the ESR as appropriate due to the 3AP Pentium erratum. Remove apic_read_around() and all its invocations altogether as not needed. Remove apic_write_atomic() and all its implementing backends. The use of ASM_OUTPUT2() is not strictly needed for input constraints, but I have used it for readability's sake. I had the feeling no one else was brave enough to do it, so I went ahead and here it is. Verified by checking the generated assembly and tested with both a 32-bit and a 64-bit configuration, also with the 11AP "feature" forced on and verified with gdb on /proc/kcore to work as expected (as an 11AP machines are quite hard to get hands on these days). Some script complained about the use of "volatile", but apic_write() needs it for the same reason and is effectively a replacement for writel(), so I have disregarded it. I am not sure what the policy wrt defconfig files is, they are generated and there is risk of a conflict resulting from an unrelated change, so I have left changes to them out. The option will get removed from them at the next run. Some testing with machines other than mine will be needed to avoid some stupid mistake, but despite its volume, the change is not really that intrusive, so I am fairly confident that because it works for me, it will everywhere. Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-16 18:15:30 +00:00
if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
apic_write(APIC_ESR, 0);
accept_status = (apic_read(APIC_ESR) & 0xEF);
if (send_status || accept_status)
break;
}
pr_debug("After Startup.\n");
if (send_status)
printk(KERN_ERR "APIC never delivered???\n");
if (accept_status)
printk(KERN_ERR "APIC delivery error (%lx).\n", accept_status);
return (send_status | accept_status);
}
struct create_idle {
struct work_struct work;
struct task_struct *idle;
struct completion done;
int cpu;
};
static void __cpuinit do_fork_idle(struct work_struct *work)
{
struct create_idle *c_idle =
container_of(work, struct create_idle, work);
c_idle->idle = fork_idle(c_idle->cpu);
complete(&c_idle->done);
}
x86: Limit the number of processor bootup messages When there are a large number of processors in a system, there is an excessive amount of messages sent to the system console. It's estimated that with 4096 processors in a system, and the console baudrate set to 56K, the startup messages will take about 84 minutes to clear the serial port. This set of patches limits the number of repetitious messages which contain no additional information. Much of this information is obtainable from the /proc and /sysfs. Some of the messages are also sent to the kernel log buffer as KERN_DEBUG messages so dmesg can be used to examine more closely any details specific to a problem. The new cpu bootup sequence for system_state == SYSTEM_BOOTING: Booting Node 0, Processors #1 #2 #3 #4 #5 #6 #7 Ok. Booting Node 1, Processors #8 #9 #10 #11 #12 #13 #14 #15 Ok. ... Booting Node 3, Processors #56 #57 #58 #59 #60 #61 #62 #63 Ok. Brought up 64 CPUs After the system is running, a single line boot message is displayed when CPU's are hotplugged on: Booting Node %d Processor %d APIC 0x%x Status of the following lines: CPU: Physical Processor ID: printed once (for boot cpu) CPU: Processor Core ID: printed once (for boot cpu) CPU: Hyper-Threading is disabled printed once (for boot cpu) CPU: Thermal monitoring enabled printed once (for boot cpu) CPU %d/0x%x -> Node %d: removed CPU %d is now offline: only if system_state == RUNNING Initializing CPU#%d: KERN_DEBUG Signed-off-by: Mike Travis <travis@sgi.com> LKML-Reference: <4B219E28.8080601@sgi.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-12-11 01:19:36 +00:00
/* reduce the number of lines printed when booting a large cpu count system */
static void __cpuinit announce_cpu(int cpu, int apicid)
{
static int current_node = -1;
int node = early_cpu_to_node(cpu);
x86: Limit the number of processor bootup messages When there are a large number of processors in a system, there is an excessive amount of messages sent to the system console. It's estimated that with 4096 processors in a system, and the console baudrate set to 56K, the startup messages will take about 84 minutes to clear the serial port. This set of patches limits the number of repetitious messages which contain no additional information. Much of this information is obtainable from the /proc and /sysfs. Some of the messages are also sent to the kernel log buffer as KERN_DEBUG messages so dmesg can be used to examine more closely any details specific to a problem. The new cpu bootup sequence for system_state == SYSTEM_BOOTING: Booting Node 0, Processors #1 #2 #3 #4 #5 #6 #7 Ok. Booting Node 1, Processors #8 #9 #10 #11 #12 #13 #14 #15 Ok. ... Booting Node 3, Processors #56 #57 #58 #59 #60 #61 #62 #63 Ok. Brought up 64 CPUs After the system is running, a single line boot message is displayed when CPU's are hotplugged on: Booting Node %d Processor %d APIC 0x%x Status of the following lines: CPU: Physical Processor ID: printed once (for boot cpu) CPU: Processor Core ID: printed once (for boot cpu) CPU: Hyper-Threading is disabled printed once (for boot cpu) CPU: Thermal monitoring enabled printed once (for boot cpu) CPU %d/0x%x -> Node %d: removed CPU %d is now offline: only if system_state == RUNNING Initializing CPU#%d: KERN_DEBUG Signed-off-by: Mike Travis <travis@sgi.com> LKML-Reference: <4B219E28.8080601@sgi.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-12-11 01:19:36 +00:00
if (system_state == SYSTEM_BOOTING) {
if (node != current_node) {
if (current_node > (-1))
pr_cont(" Ok.\n");
current_node = node;
pr_info("Booting Node %3d, Processors ", node);
}
pr_cont(" #%d%s", cpu, cpu == (nr_cpu_ids - 1) ? " Ok.\n" : "");
return;
} else
pr_info("Booting Node %d Processor %d APIC 0x%x\n",
node, cpu, apicid);
}
/*
* 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.
*/
static int __cpuinit do_boot_cpu(int apicid, int cpu)
{
unsigned long boot_error = 0;
unsigned long start_ip;
int timeout;
struct create_idle c_idle = {
.cpu = cpu,
.done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done),
};
INIT_WORK_ONSTACK(&c_idle.work, do_fork_idle);
alternatives_smp_switch(1);
c_idle.idle = get_idle_for_cpu(cpu);
/*
* 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;
}
schedule_work(&c_idle.work);
wait_for_completion(&c_idle.done);
if (IS_ERR(c_idle.idle)) {
printk("failed fork for CPU %d\n", cpu);
destroy_work_on_stack(&c_idle.work);
return PTR_ERR(c_idle.idle);
}
set_idle_for_cpu(cpu, c_idle.idle);
do_rest:
per_cpu(current_task, cpu) = c_idle.idle;
#ifdef CONFIG_X86_32
/* Stack for startup_32 can be just as for start_secondary onwards */
irq_ctx_init(cpu);
#else
clear_tsk_thread_flag(c_idle.idle, TIF_FORK);
initial_gs = per_cpu_offset(cpu);
per_cpu(kernel_stack, cpu) =
(unsigned long)task_stack_page(c_idle.idle) -
KERNEL_STACK_OFFSET + THREAD_SIZE;
#endif
early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
initial_code = (unsigned long)start_secondary;
stack_start = c_idle.idle->thread.sp;
/* start_ip had better be page-aligned! */
start_ip = trampoline_address();
x86: Limit the number of processor bootup messages When there are a large number of processors in a system, there is an excessive amount of messages sent to the system console. It's estimated that with 4096 processors in a system, and the console baudrate set to 56K, the startup messages will take about 84 minutes to clear the serial port. This set of patches limits the number of repetitious messages which contain no additional information. Much of this information is obtainable from the /proc and /sysfs. Some of the messages are also sent to the kernel log buffer as KERN_DEBUG messages so dmesg can be used to examine more closely any details specific to a problem. The new cpu bootup sequence for system_state == SYSTEM_BOOTING: Booting Node 0, Processors #1 #2 #3 #4 #5 #6 #7 Ok. Booting Node 1, Processors #8 #9 #10 #11 #12 #13 #14 #15 Ok. ... Booting Node 3, Processors #56 #57 #58 #59 #60 #61 #62 #63 Ok. Brought up 64 CPUs After the system is running, a single line boot message is displayed when CPU's are hotplugged on: Booting Node %d Processor %d APIC 0x%x Status of the following lines: CPU: Physical Processor ID: printed once (for boot cpu) CPU: Processor Core ID: printed once (for boot cpu) CPU: Hyper-Threading is disabled printed once (for boot cpu) CPU: Thermal monitoring enabled printed once (for boot cpu) CPU %d/0x%x -> Node %d: removed CPU %d is now offline: only if system_state == RUNNING Initializing CPU#%d: KERN_DEBUG Signed-off-by: Mike Travis <travis@sgi.com> LKML-Reference: <4B219E28.8080601@sgi.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-12-11 01:19:36 +00:00
/* So we see what's up */
announce_cpu(cpu, apicid);
/*
* This grunge runs the startup process for
* the targeted processor.
*/
printk(KERN_DEBUG "smpboot cpu %d: start_ip = %lx\n", cpu, start_ip);
atomic_set(&init_deasserted, 0);
if (get_uv_system_type() != UV_NON_UNIQUE_APIC) {
pr_debug("Setting warm reset code and vector.\n");
smpboot_setup_warm_reset_vector(start_ip);
/*
* Be paranoid about clearing APIC errors.
*/
if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
apic_write(APIC_ESR, 0);
apic_read(APIC_ESR);
}
}
/*
* Kick the secondary CPU. Use the method in the APIC driver
* if it's defined - or use an INIT boot APIC message otherwise:
*/
if (apic->wakeup_secondary_cpu)
boot_error = apic->wakeup_secondary_cpu(apicid, start_ip);
else
boot_error = wakeup_secondary_cpu_via_init(apicid, start_ip);
if (!boot_error) {
/*
* allow APs to start initializing.
*/
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 (cpumask_test_cpu(cpu, cpu_callin_mask))
break; /* It has booted */
udelay(100);
x86, mtrr: Use stop machine context to rendezvous all the cpu's Use the stop machine context rather than IPI's to rendezvous all the cpus for MTRR initialization that happens during cpu bringup or for MTRR modifications during runtime. This avoids deadlock scenario (reported by Prarit) like: cpu A holds a read_lock (tasklist_lock for example) with irqs enabled cpu B waits for the same lock with irqs disabled using write_lock_irq cpu C doing set_mtrr() (during AP bringup for example), which will try to rendezvous all the cpus using IPI's This will result in C and A come to the rendezvous point and waiting for B. B is stuck forever waiting for the lock and thus not reaching the rendezvous point. Using stop cpu (run in the process context of per cpu based keventd) to do this rendezvous, avoids this deadlock scenario. Also make sure all the cpu's are in the rendezvous handler before we proceed with the local_irq_save() on each cpu. This lock step disabling irqs on all the cpus will avoid other deadlock scenarios (for example involving with the blocking smp_call_function's etc). [ This problem is very old. Marking -stable only for 2.6.35 as the stop_one_cpu_nowait() API is present only in 2.6.35. Any older kernel interested in this fix need to do some more work in backporting this patch. ] Reported-by: Prarit Bhargava <prarit@redhat.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> LKML-Reference: <1280515602.2682.10.camel@sbsiddha-MOBL3.sc.intel.com> Acked-by: Prarit Bhargava <prarit@redhat.com> Cc: stable@kernel.org [2.6.35] Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2010-07-30 18:46:42 +00:00
/*
* 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();
}
x86: Limit the number of processor bootup messages When there are a large number of processors in a system, there is an excessive amount of messages sent to the system console. It's estimated that with 4096 processors in a system, and the console baudrate set to 56K, the startup messages will take about 84 minutes to clear the serial port. This set of patches limits the number of repetitious messages which contain no additional information. Much of this information is obtainable from the /proc and /sysfs. Some of the messages are also sent to the kernel log buffer as KERN_DEBUG messages so dmesg can be used to examine more closely any details specific to a problem. The new cpu bootup sequence for system_state == SYSTEM_BOOTING: Booting Node 0, Processors #1 #2 #3 #4 #5 #6 #7 Ok. Booting Node 1, Processors #8 #9 #10 #11 #12 #13 #14 #15 Ok. ... Booting Node 3, Processors #56 #57 #58 #59 #60 #61 #62 #63 Ok. Brought up 64 CPUs After the system is running, a single line boot message is displayed when CPU's are hotplugged on: Booting Node %d Processor %d APIC 0x%x Status of the following lines: CPU: Physical Processor ID: printed once (for boot cpu) CPU: Processor Core ID: printed once (for boot cpu) CPU: Hyper-Threading is disabled printed once (for boot cpu) CPU: Thermal monitoring enabled printed once (for boot cpu) CPU %d/0x%x -> Node %d: removed CPU %d is now offline: only if system_state == RUNNING Initializing CPU#%d: KERN_DEBUG Signed-off-by: Mike Travis <travis@sgi.com> LKML-Reference: <4B219E28.8080601@sgi.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-12-11 01:19:36 +00:00
if (cpumask_test_cpu(cpu, cpu_callin_mask))
pr_debug("CPU%d: has booted.\n", cpu);
else {
boot_error = 1;
if (*(volatile u32 *)TRAMPOLINE_SYM(trampoline_status)
== 0xA5A5A5A5)
/* trampoline started but...? */
x86: Limit the number of processor bootup messages When there are a large number of processors in a system, there is an excessive amount of messages sent to the system console. It's estimated that with 4096 processors in a system, and the console baudrate set to 56K, the startup messages will take about 84 minutes to clear the serial port. This set of patches limits the number of repetitious messages which contain no additional information. Much of this information is obtainable from the /proc and /sysfs. Some of the messages are also sent to the kernel log buffer as KERN_DEBUG messages so dmesg can be used to examine more closely any details specific to a problem. The new cpu bootup sequence for system_state == SYSTEM_BOOTING: Booting Node 0, Processors #1 #2 #3 #4 #5 #6 #7 Ok. Booting Node 1, Processors #8 #9 #10 #11 #12 #13 #14 #15 Ok. ... Booting Node 3, Processors #56 #57 #58 #59 #60 #61 #62 #63 Ok. Brought up 64 CPUs After the system is running, a single line boot message is displayed when CPU's are hotplugged on: Booting Node %d Processor %d APIC 0x%x Status of the following lines: CPU: Physical Processor ID: printed once (for boot cpu) CPU: Processor Core ID: printed once (for boot cpu) CPU: Hyper-Threading is disabled printed once (for boot cpu) CPU: Thermal monitoring enabled printed once (for boot cpu) CPU %d/0x%x -> Node %d: removed CPU %d is now offline: only if system_state == RUNNING Initializing CPU#%d: KERN_DEBUG Signed-off-by: Mike Travis <travis@sgi.com> LKML-Reference: <4B219E28.8080601@sgi.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-12-11 01:19:36 +00:00
pr_err("CPU%d: Stuck ??\n", cpu);
else
/* trampoline code not run */
x86: Limit the number of processor bootup messages When there are a large number of processors in a system, there is an excessive amount of messages sent to the system console. It's estimated that with 4096 processors in a system, and the console baudrate set to 56K, the startup messages will take about 84 minutes to clear the serial port. This set of patches limits the number of repetitious messages which contain no additional information. Much of this information is obtainable from the /proc and /sysfs. Some of the messages are also sent to the kernel log buffer as KERN_DEBUG messages so dmesg can be used to examine more closely any details specific to a problem. The new cpu bootup sequence for system_state == SYSTEM_BOOTING: Booting Node 0, Processors #1 #2 #3 #4 #5 #6 #7 Ok. Booting Node 1, Processors #8 #9 #10 #11 #12 #13 #14 #15 Ok. ... Booting Node 3, Processors #56 #57 #58 #59 #60 #61 #62 #63 Ok. Brought up 64 CPUs After the system is running, a single line boot message is displayed when CPU's are hotplugged on: Booting Node %d Processor %d APIC 0x%x Status of the following lines: CPU: Physical Processor ID: printed once (for boot cpu) CPU: Processor Core ID: printed once (for boot cpu) CPU: Hyper-Threading is disabled printed once (for boot cpu) CPU: Thermal monitoring enabled printed once (for boot cpu) CPU %d/0x%x -> Node %d: removed CPU %d is now offline: only if system_state == RUNNING Initializing CPU#%d: KERN_DEBUG Signed-off-by: Mike Travis <travis@sgi.com> LKML-Reference: <4B219E28.8080601@sgi.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-12-11 01:19:36 +00:00
pr_err("CPU%d: Not responding.\n", cpu);
if (apic->inquire_remote_apic)
apic->inquire_remote_apic(apicid);
}
}
if (boot_error) {
/* Try to put things back the way they were before ... */
x86: cleanup early per cpu variables/accesses v4 * Introduce a new PER_CPU macro called "EARLY_PER_CPU". This is used by some per_cpu variables that are initialized and accessed before there are per_cpu areas allocated. ["Early" in respect to per_cpu variables is "earlier than the per_cpu areas have been setup".] This patchset adds these new macros: DEFINE_EARLY_PER_CPU(_type, _name, _initvalue) EXPORT_EARLY_PER_CPU_SYMBOL(_name) DECLARE_EARLY_PER_CPU(_type, _name) early_per_cpu_ptr(_name) early_per_cpu_map(_name, _idx) early_per_cpu(_name, _cpu) The DEFINE macro defines the per_cpu variable as well as the early map and pointer. It also initializes the per_cpu variable and map elements to "_initvalue". The early_* macros provide access to the initial map (usually setup during system init) and the early pointer. This pointer is initialized to point to the early map but is then NULL'ed when the actual per_cpu areas are setup. After that the per_cpu variable is the correct access to the variable. The early_per_cpu() macro is not very efficient but does show how to access the variable if you have a function that can be called both "early" and "late". It tests the early ptr to be NULL, and if not then it's still valid. Otherwise, the per_cpu variable is used instead: #define early_per_cpu(_name, _cpu) \ (early_per_cpu_ptr(_name) ? \ early_per_cpu_ptr(_name)[_cpu] : \ per_cpu(_name, _cpu)) A better method is to actually check the pointer manually. In the case below, numa_set_node can be called both "early" and "late": 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 per_cpu(x86_cpu_to_node_map, cpu) = node; } * Add a flag "arch_provides_topology_pointers" that indicates pointers to topology cpumask_t maps are available. Otherwise, use the function returning the cpumask_t value. This is useful if cpumask_t set size is very large to avoid copying data on to/off of the stack. * The coverage of CONFIG_DEBUG_PER_CPU_MAPS has been increased while the non-debug case has been optimized a bit. * Remove an unreferenced compiler warning in drivers/base/topology.c * Clean up #ifdef in setup.c For inclusion into sched-devel/latest tree. Based on: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git + sched-devel/latest .../mingo/linux-2.6-sched-devel.git Signed-off-by: Mike Travis <travis@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 19:21:12 +00:00
numa_remove_cpu(cpu); /* was set by numa_add_cpu */
/* 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);
set_cpu_present(cpu, false);
per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID;
}
/* mark "stuck" area as not stuck */
*(volatile u32 *)TRAMPOLINE_SYM(trampoline_status) = 0;
if (get_uv_system_type() != UV_NON_UNIQUE_APIC) {
/*
* Cleanup possible dangling ends...
*/
smpboot_restore_warm_reset_vector();
}
destroy_work_on_stack(&c_idle.work);
return boot_error;
}
int __cpuinit native_cpu_up(unsigned int cpu)
{
int apicid = apic->cpu_present_to_apicid(cpu);
unsigned long flags;
int err;
WARN_ON(irqs_disabled());
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);
return -EINVAL;
}
/*
* Already booted CPU?
*/
if (cpumask_test_cpu(cpu, cpu_callin_mask)) {
pr_debug("do_boot_cpu %d Already started\n", cpu);
return -ENOSYS;
}
/*
* Save current MTRR state in case it was changed since early boot
* (e.g. by the ACPI SMI) to initialize new CPUs with MTRRs in sync:
*/
mtrr_save_state();
per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
err = do_boot_cpu(apicid, cpu);
x86: fix app crashes after SMP resume After resume on a 2cpu laptop, kernel builds collapse with a sed hang, sh or make segfault (often on 20295564), real-time signal to cc1 etc. Several hurdles to jump, but a manually-assisted bisect led to -rc1's d2bcbad5f3ad38a1c09861bca7e252dde7bb8259 x86: do not zap_low_mappings in __smp_prepare_cpus. Though the low mappings were removed at bootup, they were left behind (with Global flags helping to keep them in TLB) after resume or cpu online, causing the crashes seen. Reinstate zap_low_mappings (with local __flush_tlb_all) for each cpu_up on x86_32. This used to be serialized by smp_commenced_mask: that's now gone, but a low_mappings flag will do. No need for native_smp_cpus_done to repeat the zap: let mem_init zap BSP's low mappings just like on UP. (In passing, fix error code from native_cpu_up: do_boot_cpu returns a variety of diagnostic values, Dprintk what it says but convert to -EIO. And save_pg_dir separately before zap_low_mappings: doesn't matter now, but zapping twice in succession wiped out resume's swsusp_pg_dir.) That worked well on the duo and one quad, but wouldn't boot 3rd or 4th cpu on P4 Xeon, oopsing just after unlock_ipi_call_lock. The TLB flush IPI now being sent reveals a long-standing bug: the booting cpu has its APIC readied in smp_callin at the top of start_secondary, but isn't put into the cpu_online_map until just before that unlock_ipi_call_lock. So native_smp_call_function_mask to online cpus would send_IPI_allbutself, including the cpu just coming up, though it has been excluded from the count to wait for: by the time it handles the IPI, the call data on native_smp_call_function_mask's stack may well have been overwritten. So fall back to send_IPI_mask while cpu_online_map does not match cpu_callout_map: perhaps there's a better APICological fix to be made at the start_secondary end, but I wouldn't know that. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-05-13 13:26:57 +00:00
if (err) {
pr_debug("do_boot_cpu failed %d\n", err);
x86: fix app crashes after SMP resume After resume on a 2cpu laptop, kernel builds collapse with a sed hang, sh or make segfault (often on 20295564), real-time signal to cc1 etc. Several hurdles to jump, but a manually-assisted bisect led to -rc1's d2bcbad5f3ad38a1c09861bca7e252dde7bb8259 x86: do not zap_low_mappings in __smp_prepare_cpus. Though the low mappings were removed at bootup, they were left behind (with Global flags helping to keep them in TLB) after resume or cpu online, causing the crashes seen. Reinstate zap_low_mappings (with local __flush_tlb_all) for each cpu_up on x86_32. This used to be serialized by smp_commenced_mask: that's now gone, but a low_mappings flag will do. No need for native_smp_cpus_done to repeat the zap: let mem_init zap BSP's low mappings just like on UP. (In passing, fix error code from native_cpu_up: do_boot_cpu returns a variety of diagnostic values, Dprintk what it says but convert to -EIO. And save_pg_dir separately before zap_low_mappings: doesn't matter now, but zapping twice in succession wiped out resume's swsusp_pg_dir.) That worked well on the duo and one quad, but wouldn't boot 3rd or 4th cpu on P4 Xeon, oopsing just after unlock_ipi_call_lock. The TLB flush IPI now being sent reveals a long-standing bug: the booting cpu has its APIC readied in smp_callin at the top of start_secondary, but isn't put into the cpu_online_map until just before that unlock_ipi_call_lock. So native_smp_call_function_mask to online cpus would send_IPI_allbutself, including the cpu just coming up, though it has been excluded from the count to wait for: by the time it handles the IPI, the call data on native_smp_call_function_mask's stack may well have been overwritten. So fall back to send_IPI_mask while cpu_online_map does not match cpu_callout_map: perhaps there's a better APICological fix to be made at the start_secondary end, but I wouldn't know that. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-05-13 13:26:57 +00:00
return -EIO;
}
/*
* Check TSC synchronization with the AP (keep irqs disabled
* while doing so):
*/
local_irq_save(flags);
check_tsc_sync_source(cpu);
local_irq_restore(flags);
while (!cpu_online(cpu)) {
cpu_relax();
touch_nmi_watchdog();
}
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.
*
* RED-PEN audit/test this more. I bet there is more state messed up here.
*/
static __init void disable_smp(void)
{
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);
cpumask_set_cpu(0, cpu_sibling_mask(0));
cpumask_set_cpu(0, cpu_core_mask(0));
}
/*
* Various sanity checks.
*/
static int __init smp_sanity_check(unsigned max_cpus)
{
x86: support for new UV apic UV supports really big systems. So big, in fact, that the APICID register does not contain enough bits to contain an APICID that is unique across all cpus. The UV BIOS supports 3 APICID modes: - legacy mode. This mode uses the old APIC mode where APICID is in bits [31:24] of the APICID register. - x2apic mode. This mode is whitebox-compatible. APICIDs are unique across all cpus. Standard x2apic APIC operations (Intel-defined) can be used for IPIs. The node identifier fits within the Intel-defined portion of the APICID register. - x2apic-uv mode. In this mode, the APICIDs on each node have unique IDs, but IDs on different node are not unique. For example, if each mode has 32 cpus, the APICIDs on each node might be 0 - 31. Every node has the same set of IDs. The UV hub is used to route IPIs/interrupts to the correct node. Traditional APIC operations WILL NOT WORK. In x2apic-uv mode, the ACPI tables all contain a full unique ID (note: exact bit layout still changing but the following is close): nnnnnnnnnnlc0cch n = unique node number l = socket number on board c = core h = hyperthread Only the "lc0cch" bits are written to the APICID register. The remaining bits are supplied by having the get_apic_id() function "OR" the extra bits into the value read from the APICID register. (Hmmm.. why not keep the ENTIRE APICID register in per-cpu data....) The x2apic-uv mode is recognized by the MADT table containing: oem_id = "SGI" oem_table_id = "UV-X" Signed-off-by: Jack Steiner <steiner@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-03-28 19:12:16 +00:00
preempt_disable();
#if !defined(CONFIG_X86_BIGSMP) && defined(CONFIG_X86_32)
if (def_to_bigsmp && nr_cpu_ids > 8) {
unsigned int cpu;
unsigned nr;
printk(KERN_WARNING
"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());
physid_set(hard_smp_processor_id(), phys_cpu_present_map);
}
/*
* If we couldn't find an SMP configuration at boot time,
* get out of here now!
*/
if (!smp_found_config && !acpi_lapic) {
x86: support for new UV apic UV supports really big systems. So big, in fact, that the APICID register does not contain enough bits to contain an APICID that is unique across all cpus. The UV BIOS supports 3 APICID modes: - legacy mode. This mode uses the old APIC mode where APICID is in bits [31:24] of the APICID register. - x2apic mode. This mode is whitebox-compatible. APICIDs are unique across all cpus. Standard x2apic APIC operations (Intel-defined) can be used for IPIs. The node identifier fits within the Intel-defined portion of the APICID register. - x2apic-uv mode. In this mode, the APICIDs on each node have unique IDs, but IDs on different node are not unique. For example, if each mode has 32 cpus, the APICIDs on each node might be 0 - 31. Every node has the same set of IDs. The UV hub is used to route IPIs/interrupts to the correct node. Traditional APIC operations WILL NOT WORK. In x2apic-uv mode, the ACPI tables all contain a full unique ID (note: exact bit layout still changing but the following is close): nnnnnnnnnnlc0cch n = unique node number l = socket number on board c = core h = hyperthread Only the "lc0cch" bits are written to the APICID register. The remaining bits are supplied by having the get_apic_id() function "OR" the extra bits into the value read from the APICID register. (Hmmm.. why not keep the ENTIRE APICID register in per-cpu data....) The x2apic-uv mode is recognized by the MADT table containing: oem_id = "SGI" oem_table_id = "UV-X" Signed-off-by: Jack Steiner <steiner@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-03-28 19:12:16 +00:00
preempt_enable();
printk(KERN_NOTICE "SMP motherboard not detected.\n");
disable_smp();
if (APIC_init_uniprocessor())
printk(KERN_NOTICE "Local APIC not detected."
" Using dummy APIC emulation.\n");
return -1;
}
/*
* 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 (!apic->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);
physid_set(hard_smp_processor_id(), phys_cpu_present_map);
}
x86: support for new UV apic UV supports really big systems. So big, in fact, that the APICID register does not contain enough bits to contain an APICID that is unique across all cpus. The UV BIOS supports 3 APICID modes: - legacy mode. This mode uses the old APIC mode where APICID is in bits [31:24] of the APICID register. - x2apic mode. This mode is whitebox-compatible. APICIDs are unique across all cpus. Standard x2apic APIC operations (Intel-defined) can be used for IPIs. The node identifier fits within the Intel-defined portion of the APICID register. - x2apic-uv mode. In this mode, the APICIDs on each node have unique IDs, but IDs on different node are not unique. For example, if each mode has 32 cpus, the APICIDs on each node might be 0 - 31. Every node has the same set of IDs. The UV hub is used to route IPIs/interrupts to the correct node. Traditional APIC operations WILL NOT WORK. In x2apic-uv mode, the ACPI tables all contain a full unique ID (note: exact bit layout still changing but the following is close): nnnnnnnnnnlc0cch n = unique node number l = socket number on board c = core h = hyperthread Only the "lc0cch" bits are written to the APICID register. The remaining bits are supplied by having the get_apic_id() function "OR" the extra bits into the value read from the APICID register. (Hmmm.. why not keep the ENTIRE APICID register in per-cpu data....) The x2apic-uv mode is recognized by the MADT table containing: oem_id = "SGI" oem_table_id = "UV-X" Signed-off-by: Jack Steiner <steiner@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-03-28 19:12:16 +00:00
preempt_enable();
/*
* If we couldn't find a local APIC, then get out of here now!
*/
if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid]) &&
!cpu_has_apic) {
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;
}
verify_local_APIC();
/*
* If SMP should be disabled, then really disable it!
*/
if (!max_cpus) {
printk(KERN_INFO "SMP mode deactivated.\n");
smpboot_clear_io_apic();
connect_bsp_APIC();
setup_local_APIC();
bsp_end_local_APIC_setup();
return -1;
}
return 0;
}
static void __init smp_cpu_index_default(void)
{
int i;
struct cpuinfo_x86 *c;
for_each_possible_cpu(i) {
c = &cpu_data(i);
/* mark all to hotplug */
c->cpu_index = nr_cpu_ids;
}
}
/*
* Prepare for SMP bootup. The MP table or ACPI has been read
* earlier. Just do some sanity checking here and enable APIC mode.
*/
void __init native_smp_prepare_cpus(unsigned int max_cpus)
{
unsigned int i;
preempt_disable();
smp_cpu_index_default();
/*
* Setup boot CPU information
*/
smp_store_cpu_info(0); /* 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");
disable_smp();
goto out;
}
default_setup_apic_routing();
x86: support for new UV apic UV supports really big systems. So big, in fact, that the APICID register does not contain enough bits to contain an APICID that is unique across all cpus. The UV BIOS supports 3 APICID modes: - legacy mode. This mode uses the old APIC mode where APICID is in bits [31:24] of the APICID register. - x2apic mode. This mode is whitebox-compatible. APICIDs are unique across all cpus. Standard x2apic APIC operations (Intel-defined) can be used for IPIs. The node identifier fits within the Intel-defined portion of the APICID register. - x2apic-uv mode. In this mode, the APICIDs on each node have unique IDs, but IDs on different node are not unique. For example, if each mode has 32 cpus, the APICIDs on each node might be 0 - 31. Every node has the same set of IDs. The UV hub is used to route IPIs/interrupts to the correct node. Traditional APIC operations WILL NOT WORK. In x2apic-uv mode, the ACPI tables all contain a full unique ID (note: exact bit layout still changing but the following is close): nnnnnnnnnnlc0cch n = unique node number l = socket number on board c = core h = hyperthread Only the "lc0cch" bits are written to the APICID register. The remaining bits are supplied by having the get_apic_id() function "OR" the extra bits into the value read from the APICID register. (Hmmm.. why not keep the ENTIRE APICID register in per-cpu data....) The x2apic-uv mode is recognized by the MADT table containing: oem_id = "SGI" oem_table_id = "UV-X" Signed-off-by: Jack Steiner <steiner@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-03-28 19:12:16 +00:00
preempt_disable();
if (read_apic_id() != boot_cpu_physical_apicid) {
panic("Boot APIC ID in local APIC unexpected (%d vs %d)",
read_apic_id(), boot_cpu_physical_apicid);
/* Or can we switch back to PIC here? */
}
x86: support for new UV apic UV supports really big systems. So big, in fact, that the APICID register does not contain enough bits to contain an APICID that is unique across all cpus. The UV BIOS supports 3 APICID modes: - legacy mode. This mode uses the old APIC mode where APICID is in bits [31:24] of the APICID register. - x2apic mode. This mode is whitebox-compatible. APICIDs are unique across all cpus. Standard x2apic APIC operations (Intel-defined) can be used for IPIs. The node identifier fits within the Intel-defined portion of the APICID register. - x2apic-uv mode. In this mode, the APICIDs on each node have unique IDs, but IDs on different node are not unique. For example, if each mode has 32 cpus, the APICIDs on each node might be 0 - 31. Every node has the same set of IDs. The UV hub is used to route IPIs/interrupts to the correct node. Traditional APIC operations WILL NOT WORK. In x2apic-uv mode, the ACPI tables all contain a full unique ID (note: exact bit layout still changing but the following is close): nnnnnnnnnnlc0cch n = unique node number l = socket number on board c = core h = hyperthread Only the "lc0cch" bits are written to the APICID register. The remaining bits are supplied by having the get_apic_id() function "OR" the extra bits into the value read from the APICID register. (Hmmm.. why not keep the ENTIRE APICID register in per-cpu data....) The x2apic-uv mode is recognized by the MADT table containing: oem_id = "SGI" oem_table_id = "UV-X" Signed-off-by: Jack Steiner <steiner@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-03-28 19:12:16 +00:00
preempt_enable();
connect_bsp_APIC();
/*
* Switch from PIC to APIC mode.
*/
setup_local_APIC();
/*
* Enable IO APIC before setting up error vector
*/
if (!skip_ioapic_setup && nr_ioapics)
enable_IO_APIC();
bsp_end_local_APIC_setup();
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);
print_cpu_info(&cpu_data(0));
x86_init.timers.setup_percpu_clockev();
if (is_uv_system())
uv_system_init();
set_mtrr_aps_delayed_init();
out:
preempt_enable();
}
void arch_disable_nonboot_cpus_begin(void)
{
/*
* Avoid the smp alternatives switch during the disable_nonboot_cpus().
* In the suspend path, we will be back in the SMP mode shortly anyways.
*/
skip_smp_alternatives = true;
}
void arch_disable_nonboot_cpus_end(void)
{
skip_smp_alternatives = false;
}
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();
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");
impress_friends();
#ifdef CONFIG_X86_IO_APIC
setup_ioapic_dest();
#endif
mtrr_aps_init();
}
static int __initdata setup_possible_cpus = -1;
static int __init _setup_possible_cpus(char *str)
{
get_option(&str, &setup_possible_cpus);
return 0;
}
early_param("possible_cpus", _setup_possible_cpus);
/*
* 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_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 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, 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 (setup_max_cpus)
possible += disabled_cpus;
#else
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) {
printk(KERN_WARNING
"%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
if (possible > i) {
printk(KERN_WARNING
"%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",
possible, max_t(int, possible - num_processors, 0));
for (i = 0; i < possible; i++)
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)
{
set_cpu_online(cpu, false);
cpumask_clear_cpu(cpu, cpu_callout_mask);
cpumask_clear_cpu(cpu, cpu_callin_mask);
/* was set by cpu_init() */
cpumask_clear_cpu(cpu, cpu_initialized_mask);
x86: cleanup early per cpu variables/accesses v4 * Introduce a new PER_CPU macro called "EARLY_PER_CPU". This is used by some per_cpu variables that are initialized and accessed before there are per_cpu areas allocated. ["Early" in respect to per_cpu variables is "earlier than the per_cpu areas have been setup".] This patchset adds these new macros: DEFINE_EARLY_PER_CPU(_type, _name, _initvalue) EXPORT_EARLY_PER_CPU_SYMBOL(_name) DECLARE_EARLY_PER_CPU(_type, _name) early_per_cpu_ptr(_name) early_per_cpu_map(_name, _idx) early_per_cpu(_name, _cpu) The DEFINE macro defines the per_cpu variable as well as the early map and pointer. It also initializes the per_cpu variable and map elements to "_initvalue". The early_* macros provide access to the initial map (usually setup during system init) and the early pointer. This pointer is initialized to point to the early map but is then NULL'ed when the actual per_cpu areas are setup. After that the per_cpu variable is the correct access to the variable. The early_per_cpu() macro is not very efficient but does show how to access the variable if you have a function that can be called both "early" and "late". It tests the early ptr to be NULL, and if not then it's still valid. Otherwise, the per_cpu variable is used instead: #define early_per_cpu(_name, _cpu) \ (early_per_cpu_ptr(_name) ? \ early_per_cpu_ptr(_name)[_cpu] : \ per_cpu(_name, _cpu)) A better method is to actually check the pointer manually. In the case below, numa_set_node can be called both "early" and "late": 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 per_cpu(x86_cpu_to_node_map, cpu) = node; } * Add a flag "arch_provides_topology_pointers" that indicates pointers to topology cpumask_t maps are available. Otherwise, use the function returning the cpumask_t value. This is useful if cpumask_t set size is very large to avoid copying data on to/off of the stack. * The coverage of CONFIG_DEBUG_PER_CPU_MAPS has been increased while the non-debug case has been optimized a bit. * Remove an unreferenced compiler warning in drivers/base/topology.c * Clean up #ifdef in setup.c For inclusion into sched-devel/latest tree. Based on: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git + sched-devel/latest .../mingo/linux-2.6-sched-devel.git Signed-off-by: Mike Travis <travis@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-12 19:21:12 +00:00
numa_remove_cpu(cpu);
}
void cpu_disable_common(void)
{
int cpu = smp_processor_id();
remove_siblinginfo(cpu);
/* It's now safe to remove this processor from the online map */
lock_vector_lock();
remove_cpu_from_maps(cpu);
unlock_vector_lock();
fixup_irqs();
}
int native_cpu_disable(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;
clear_local_APIC();
cpu_disable_common();
return 0;
}
void native_cpu_die(unsigned int cpu)
{
/* We don't do anything here: idle task is faking death itself. */
unsigned int i;
for (i = 0; i < 10; i++) {
/* They ack this in play_dead by setting CPU_DEAD */
if (per_cpu(cpu_state, cpu) == CPU_DEAD) {
x86: Limit the number of processor bootup messages When there are a large number of processors in a system, there is an excessive amount of messages sent to the system console. It's estimated that with 4096 processors in a system, and the console baudrate set to 56K, the startup messages will take about 84 minutes to clear the serial port. This set of patches limits the number of repetitious messages which contain no additional information. Much of this information is obtainable from the /proc and /sysfs. Some of the messages are also sent to the kernel log buffer as KERN_DEBUG messages so dmesg can be used to examine more closely any details specific to a problem. The new cpu bootup sequence for system_state == SYSTEM_BOOTING: Booting Node 0, Processors #1 #2 #3 #4 #5 #6 #7 Ok. Booting Node 1, Processors #8 #9 #10 #11 #12 #13 #14 #15 Ok. ... Booting Node 3, Processors #56 #57 #58 #59 #60 #61 #62 #63 Ok. Brought up 64 CPUs After the system is running, a single line boot message is displayed when CPU's are hotplugged on: Booting Node %d Processor %d APIC 0x%x Status of the following lines: CPU: Physical Processor ID: printed once (for boot cpu) CPU: Processor Core ID: printed once (for boot cpu) CPU: Hyper-Threading is disabled printed once (for boot cpu) CPU: Thermal monitoring enabled printed once (for boot cpu) CPU %d/0x%x -> Node %d: removed CPU %d is now offline: only if system_state == RUNNING Initializing CPU#%d: KERN_DEBUG Signed-off-by: Mike Travis <travis@sgi.com> LKML-Reference: <4B219E28.8080601@sgi.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-12-11 01:19:36 +00:00
if (system_state == SYSTEM_RUNNING)
pr_info("CPU %u is now offline\n", cpu);
if (1 == num_online_cpus())
alternatives_smp_switch(0);
return;
}
msleep(100);
}
x86: Limit the number of processor bootup messages When there are a large number of processors in a system, there is an excessive amount of messages sent to the system console. It's estimated that with 4096 processors in a system, and the console baudrate set to 56K, the startup messages will take about 84 minutes to clear the serial port. This set of patches limits the number of repetitious messages which contain no additional information. Much of this information is obtainable from the /proc and /sysfs. Some of the messages are also sent to the kernel log buffer as KERN_DEBUG messages so dmesg can be used to examine more closely any details specific to a problem. The new cpu bootup sequence for system_state == SYSTEM_BOOTING: Booting Node 0, Processors #1 #2 #3 #4 #5 #6 #7 Ok. Booting Node 1, Processors #8 #9 #10 #11 #12 #13 #14 #15 Ok. ... Booting Node 3, Processors #56 #57 #58 #59 #60 #61 #62 #63 Ok. Brought up 64 CPUs After the system is running, a single line boot message is displayed when CPU's are hotplugged on: Booting Node %d Processor %d APIC 0x%x Status of the following lines: CPU: Physical Processor ID: printed once (for boot cpu) CPU: Processor Core ID: printed once (for boot cpu) CPU: Hyper-Threading is disabled printed once (for boot cpu) CPU: Thermal monitoring enabled printed once (for boot cpu) CPU %d/0x%x -> Node %d: removed CPU %d is now offline: only if system_state == RUNNING Initializing CPU#%d: KERN_DEBUG Signed-off-by: Mike Travis <travis@sgi.com> LKML-Reference: <4B219E28.8080601@sgi.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2009-12-11 01:19:36 +00:00
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();
}
/*
* 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;
int i;
void *mwait_ptr;
struct cpuinfo_x86 *c = __this_cpu_ptr(&cpu_info);
if (!(this_cpu_has(X86_FEATURE_MWAIT) && mwait_usable(c)))
return;
if (!this_cpu_has(X86_FEATURE_CLFLSH))
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.
*/
clflush(mwait_ptr);
__monitor(mwait_ptr, 0, 0);
mb();
__mwait(eax, 0);
}
}
static inline void hlt_play_dead(void)
{
if (__this_cpu_read(cpu_info.x86) >= 4)
wbinvd();
while (1) {
native_halt();
}
}
void native_play_dead(void)
{
play_dead_common();
tboot_shutdown(TB_SHUTDOWN_WFS);
mwait_play_dead(); /* Only returns on failure */
hlt_play_dead();
}
#else /* ... !CONFIG_HOTPLUG_CPU */
int native_cpu_disable(void)
{
return -ENOSYS;
}
void native_cpu_die(unsigned int cpu)
{
/* We said "no" in __cpu_disable */
BUG();
}
void native_play_dead(void)
{
BUG();
}
#endif