Commit 0cc3cd21 authored by Thomas Gleixner's avatar Thomas Gleixner

cpu/hotplug: Boot HT siblings at least once

Due to the way Machine Check Exceptions work on X86 hyperthreads it's
required to boot up _all_ logical cores at least once in order to set the
CR4.MCE bit.

So instead of ignoring the sibling threads right away, let them boot up
once so they can configure themselves. After they came out of the initial
boot stage check whether its a "secondary" sibling and cancel the operation
which puts the CPU back into offline state.
Reported-by: default avatarDave Hansen <dave.hansen@intel.com>
Signed-off-by: default avatarThomas Gleixner <tglx@linutronix.de>
Tested-by: default avatarTony Luck <tony.luck@intel.com>
parent 506a66f3
...@@ -60,6 +60,7 @@ struct cpuhp_cpu_state { ...@@ -60,6 +60,7 @@ struct cpuhp_cpu_state {
bool rollback; bool rollback;
bool single; bool single;
bool bringup; bool bringup;
bool booted_once;
struct hlist_node *node; struct hlist_node *node;
struct hlist_node *last; struct hlist_node *last;
enum cpuhp_state cb_state; enum cpuhp_state cb_state;
...@@ -342,6 +343,40 @@ void cpu_hotplug_enable(void) ...@@ -342,6 +343,40 @@ void cpu_hotplug_enable(void)
EXPORT_SYMBOL_GPL(cpu_hotplug_enable); EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
#endif /* CONFIG_HOTPLUG_CPU */ #endif /* CONFIG_HOTPLUG_CPU */
#ifdef CONFIG_HOTPLUG_SMT
enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
static int __init smt_cmdline_disable(char *str)
{
cpu_smt_control = CPU_SMT_DISABLED;
if (str && !strcmp(str, "force")) {
pr_info("SMT: Force disabled\n");
cpu_smt_control = CPU_SMT_FORCE_DISABLED;
}
return 0;
}
early_param("nosmt", smt_cmdline_disable);
static inline bool cpu_smt_allowed(unsigned int cpu)
{
if (cpu_smt_control == CPU_SMT_ENABLED)
return true;
if (topology_is_primary_thread(cpu))
return true;
/*
* On x86 it's required to boot all logical CPUs at least once so
* that the init code can get a chance to set CR4.MCE on each
* CPU. Otherwise, a broadacasted MCE observing CR4.MCE=0b on any
* core will shutdown the machine.
*/
return !per_cpu(cpuhp_state, cpu).booted_once;
}
#else
static inline bool cpu_smt_allowed(unsigned int cpu) { return true; }
#endif
static inline enum cpuhp_state static inline enum cpuhp_state
cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target) cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target)
{ {
...@@ -422,6 +457,16 @@ static int bringup_wait_for_ap(unsigned int cpu) ...@@ -422,6 +457,16 @@ static int bringup_wait_for_ap(unsigned int cpu)
stop_machine_unpark(cpu); stop_machine_unpark(cpu);
kthread_unpark(st->thread); kthread_unpark(st->thread);
/*
* SMT soft disabling on X86 requires to bring the CPU out of the
* BIOS 'wait for SIPI' state in order to set the CR4.MCE bit. The
* CPU marked itself as booted_once in cpu_notify_starting() so the
* cpu_smt_allowed() check will now return false if this is not the
* primary sibling.
*/
if (!cpu_smt_allowed(cpu))
return -ECANCELED;
if (st->target <= CPUHP_AP_ONLINE_IDLE) if (st->target <= CPUHP_AP_ONLINE_IDLE)
return 0; return 0;
...@@ -933,29 +978,6 @@ EXPORT_SYMBOL(cpu_down); ...@@ -933,29 +978,6 @@ EXPORT_SYMBOL(cpu_down);
#define takedown_cpu NULL #define takedown_cpu NULL
#endif /*CONFIG_HOTPLUG_CPU*/ #endif /*CONFIG_HOTPLUG_CPU*/
#ifdef CONFIG_HOTPLUG_SMT
enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
static int __init smt_cmdline_disable(char *str)
{
cpu_smt_control = CPU_SMT_DISABLED;
if (str && !strcmp(str, "force")) {
pr_info("SMT: Force disabled\n");
cpu_smt_control = CPU_SMT_FORCE_DISABLED;
}
return 0;
}
early_param("nosmt", smt_cmdline_disable);
static inline bool cpu_smt_allowed(unsigned int cpu)
{
return cpu_smt_control == CPU_SMT_ENABLED ||
topology_is_primary_thread(cpu);
}
#else
static inline bool cpu_smt_allowed(unsigned int cpu) { return true; }
#endif
/** /**
* notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU * notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU
* @cpu: cpu that just started * @cpu: cpu that just started
...@@ -970,6 +992,7 @@ void notify_cpu_starting(unsigned int cpu) ...@@ -970,6 +992,7 @@ void notify_cpu_starting(unsigned int cpu)
int ret; int ret;
rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */
st->booted_once = true;
while (st->state < target) { while (st->state < target) {
st->state++; st->state++;
ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
...@@ -2180,5 +2203,6 @@ void __init boot_cpu_init(void) ...@@ -2180,5 +2203,6 @@ void __init boot_cpu_init(void)
*/ */
void __init boot_cpu_state_init(void) void __init boot_cpu_state_init(void)
{ {
per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE; this_cpu_write(cpuhp_state.booted_once, true);
this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
} }
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment