WSL2-Linux-Kernel/arch/x86/kernel/apic/x2apic_cluster.c

296 строки
7.4 KiB
C
Исходник Обычный вид История

#include <linux/threads.h>
#include <linux/cpumask.h>
#include <linux/string.h>
#include <linux/kernel.h>
#include <linux/ctype.h>
#include <linux/dmar.h>
#include <linux/cpu.h>
#include <asm/smp.h>
#include <asm/x2apic.h>
static DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid);
static DEFINE_PER_CPU(cpumask_var_t, cpus_in_cluster);
static DEFINE_PER_CPU(cpumask_var_t, ipi_mask);
static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
{
return x2apic_enabled();
}
static inline u32 x2apic_cluster(int cpu)
{
return per_cpu(x86_cpu_to_logical_apicid, cpu) >> 16;
}
static void x2apic_send_IPI(int cpu, int vector)
{
u32 dest = per_cpu(x86_cpu_to_logical_apicid, cpu);
x2apic_wrmsr_fence();
__x2apic_send_IPI_dest(dest, vector, APIC_DEST_LOGICAL);
}
static void
__x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
{
struct cpumask *cpus_in_cluster_ptr;
struct cpumask *ipi_mask_ptr;
unsigned int cpu, this_cpu;
unsigned long flags;
u32 dest;
x2apic_wrmsr_fence();
local_irq_save(flags);
this_cpu = smp_processor_id();
/*
* We are to modify mask, so we need an own copy
* and be sure it's manipulated with irq off.
*/
ipi_mask_ptr = this_cpu_cpumask_var_ptr(ipi_mask);
cpumask_copy(ipi_mask_ptr, mask);
/*
* The idea is to send one IPI per cluster.
*/
for_each_cpu(cpu, ipi_mask_ptr) {
unsigned long i;
cpus_in_cluster_ptr = per_cpu(cpus_in_cluster, cpu);
dest = 0;
/* Collect cpus in cluster. */
for_each_cpu_and(i, ipi_mask_ptr, cpus_in_cluster_ptr) {
if (apic_dest == APIC_DEST_ALLINC || i != this_cpu)
dest |= per_cpu(x86_cpu_to_logical_apicid, i);
}
if (!dest)
continue;
__x2apic_send_IPI_dest(dest, vector, apic->dest_logical);
/*
* Cluster sibling cpus should be discared now so
* we would not send IPI them second time.
*/
cpumask_andnot(ipi_mask_ptr, ipi_mask_ptr, cpus_in_cluster_ptr);
}
local_irq_restore(flags);
}
static void x2apic_send_IPI_mask(const struct cpumask *mask, int vector)
{
__x2apic_send_IPI_mask(mask, vector, APIC_DEST_ALLINC);
}
static void
x2apic_send_IPI_mask_allbutself(const struct cpumask *mask, int vector)
{
__x2apic_send_IPI_mask(mask, vector, APIC_DEST_ALLBUT);
}
static void x2apic_send_IPI_allbutself(int vector)
{
__x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLBUT);
}
static void x2apic_send_IPI_all(int vector)
{
__x2apic_send_IPI_mask(cpu_online_mask, vector, APIC_DEST_ALLINC);
}
x86/apic: Make cpu_mask_to_apicid() operations return error code Current cpu_mask_to_apicid() and cpu_mask_to_apicid_and() implementations have few shortcomings: 1. A value returned by cpu_mask_to_apicid() is written to hardware registers unconditionally. Should BAD_APICID get ever returned it will be written to a hardware too. But the value of BAD_APICID is not universal across all hardware in all modes and might cause unexpected results, i.e. interrupts might get routed to CPUs that are not configured to receive it. 2. Because the value of BAD_APICID is not universal it is counter- intuitive to return it for a hardware where it does not make sense (i.e. x2apic). 3. cpu_mask_to_apicid_and() operation is thought as an complement to cpu_mask_to_apicid() that only applies a AND mask on top of a cpumask being passed. Yet, as consequence of 18374d8 commit the two operations are inconsistent in that of: cpu_mask_to_apicid() should not get a offline CPU with the cpumask cpu_mask_to_apicid_and() should not fail and return BAD_APICID These limitations are impossible to realize just from looking at the operations prototypes. Most of these shortcomings are resolved by returning a error code instead of BAD_APICID. As the result, faults are reported back early rather than possibilities to cause a unexpected behaviour exist (in case of [1]). The only exception is setup_timer_IRQ0_pin() routine. Although obviously controversial to this fix, its existing behaviour is preserved to not break the fragile check_timer() and would better addressed in a separate fix. Signed-off-by: Alexander Gordeev <agordeev@redhat.com> Acked-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Yinghai Lu <yinghai@kernel.org> Link: http://lkml.kernel.org/r/20120607131559.GF4759@dhcp-26-207.brq.redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-07 17:15:59 +04:00
static int
x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
x86/apic: Make cpu_mask_to_apicid() operations return error code Current cpu_mask_to_apicid() and cpu_mask_to_apicid_and() implementations have few shortcomings: 1. A value returned by cpu_mask_to_apicid() is written to hardware registers unconditionally. Should BAD_APICID get ever returned it will be written to a hardware too. But the value of BAD_APICID is not universal across all hardware in all modes and might cause unexpected results, i.e. interrupts might get routed to CPUs that are not configured to receive it. 2. Because the value of BAD_APICID is not universal it is counter- intuitive to return it for a hardware where it does not make sense (i.e. x2apic). 3. cpu_mask_to_apicid_and() operation is thought as an complement to cpu_mask_to_apicid() that only applies a AND mask on top of a cpumask being passed. Yet, as consequence of 18374d8 commit the two operations are inconsistent in that of: cpu_mask_to_apicid() should not get a offline CPU with the cpumask cpu_mask_to_apicid_and() should not fail and return BAD_APICID These limitations are impossible to realize just from looking at the operations prototypes. Most of these shortcomings are resolved by returning a error code instead of BAD_APICID. As the result, faults are reported back early rather than possibilities to cause a unexpected behaviour exist (in case of [1]). The only exception is setup_timer_IRQ0_pin() routine. Although obviously controversial to this fix, its existing behaviour is preserved to not break the fragile check_timer() and would better addressed in a separate fix. Signed-off-by: Alexander Gordeev <agordeev@redhat.com> Acked-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Yinghai Lu <yinghai@kernel.org> Link: http://lkml.kernel.org/r/20120607131559.GF4759@dhcp-26-207.brq.redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-07 17:15:59 +04:00
const struct cpumask *andmask,
unsigned int *apicid)
{
u32 dest = 0;
u16 cluster;
int i;
for_each_cpu_and(i, cpumask, andmask) {
if (!cpumask_test_cpu(i, cpu_online_mask))
continue;
dest = per_cpu(x86_cpu_to_logical_apicid, i);
cluster = x2apic_cluster(i);
break;
}
if (!dest)
x86/apic: Make cpu_mask_to_apicid() operations return error code Current cpu_mask_to_apicid() and cpu_mask_to_apicid_and() implementations have few shortcomings: 1. A value returned by cpu_mask_to_apicid() is written to hardware registers unconditionally. Should BAD_APICID get ever returned it will be written to a hardware too. But the value of BAD_APICID is not universal across all hardware in all modes and might cause unexpected results, i.e. interrupts might get routed to CPUs that are not configured to receive it. 2. Because the value of BAD_APICID is not universal it is counter- intuitive to return it for a hardware where it does not make sense (i.e. x2apic). 3. cpu_mask_to_apicid_and() operation is thought as an complement to cpu_mask_to_apicid() that only applies a AND mask on top of a cpumask being passed. Yet, as consequence of 18374d8 commit the two operations are inconsistent in that of: cpu_mask_to_apicid() should not get a offline CPU with the cpumask cpu_mask_to_apicid_and() should not fail and return BAD_APICID These limitations are impossible to realize just from looking at the operations prototypes. Most of these shortcomings are resolved by returning a error code instead of BAD_APICID. As the result, faults are reported back early rather than possibilities to cause a unexpected behaviour exist (in case of [1]). The only exception is setup_timer_IRQ0_pin() routine. Although obviously controversial to this fix, its existing behaviour is preserved to not break the fragile check_timer() and would better addressed in a separate fix. Signed-off-by: Alexander Gordeev <agordeev@redhat.com> Acked-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Yinghai Lu <yinghai@kernel.org> Link: http://lkml.kernel.org/r/20120607131559.GF4759@dhcp-26-207.brq.redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-07 17:15:59 +04:00
return -EINVAL;
for_each_cpu_and(i, cpumask, andmask) {
if (!cpumask_test_cpu(i, cpu_online_mask))
continue;
if (cluster != x2apic_cluster(i))
continue;
dest |= per_cpu(x86_cpu_to_logical_apicid, i);
}
x86/apic: Make cpu_mask_to_apicid() operations return error code Current cpu_mask_to_apicid() and cpu_mask_to_apicid_and() implementations have few shortcomings: 1. A value returned by cpu_mask_to_apicid() is written to hardware registers unconditionally. Should BAD_APICID get ever returned it will be written to a hardware too. But the value of BAD_APICID is not universal across all hardware in all modes and might cause unexpected results, i.e. interrupts might get routed to CPUs that are not configured to receive it. 2. Because the value of BAD_APICID is not universal it is counter- intuitive to return it for a hardware where it does not make sense (i.e. x2apic). 3. cpu_mask_to_apicid_and() operation is thought as an complement to cpu_mask_to_apicid() that only applies a AND mask on top of a cpumask being passed. Yet, as consequence of 18374d8 commit the two operations are inconsistent in that of: cpu_mask_to_apicid() should not get a offline CPU with the cpumask cpu_mask_to_apicid_and() should not fail and return BAD_APICID These limitations are impossible to realize just from looking at the operations prototypes. Most of these shortcomings are resolved by returning a error code instead of BAD_APICID. As the result, faults are reported back early rather than possibilities to cause a unexpected behaviour exist (in case of [1]). The only exception is setup_timer_IRQ0_pin() routine. Although obviously controversial to this fix, its existing behaviour is preserved to not break the fragile check_timer() and would better addressed in a separate fix. Signed-off-by: Alexander Gordeev <agordeev@redhat.com> Acked-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Yinghai Lu <yinghai@kernel.org> Link: http://lkml.kernel.org/r/20120607131559.GF4759@dhcp-26-207.brq.redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-06-07 17:15:59 +04:00
*apicid = dest;
return 0;
}
static void init_x2apic_ldr(void)
{
unsigned int this_cpu = smp_processor_id();
unsigned int cpu;
per_cpu(x86_cpu_to_logical_apicid, this_cpu) = apic_read(APIC_LDR);
cpumask_set_cpu(this_cpu, per_cpu(cpus_in_cluster, this_cpu));
for_each_online_cpu(cpu) {
if (x2apic_cluster(this_cpu) != x2apic_cluster(cpu))
continue;
cpumask_set_cpu(this_cpu, per_cpu(cpus_in_cluster, cpu));
cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, this_cpu));
}
}
/*
* At CPU state changes, update the x2apic cluster sibling info.
*/
x86: delete __cpuinit usage from all x86 files The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. Note that some harmless section mismatch warnings may result, since notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c) are flagged as __cpuinit -- so if we remove the __cpuinit from arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. This removes all the arch/x86 uses of the __cpuinit macros from all C files. x86 only had the one __CPUINIT used in assembly files, and it wasn't paired off with a .previous or a __FINIT, so we can delete it directly w/o any corresponding additional change there. [1] https://lkml.org/lkml/2013/5/20/589 Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: x86@kernel.org Acked-by: Ingo Molnar <mingo@kernel.org> Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: H. Peter Anvin <hpa@linux.intel.com> Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2013-06-19 02:23:59 +04:00
static int
update_clusterinfo(struct notifier_block *nfb, unsigned long action, void *hcpu)
{
unsigned int this_cpu = (unsigned long)hcpu;
unsigned int cpu;
int err = 0;
switch (action) {
case CPU_UP_PREPARE:
if (!zalloc_cpumask_var(&per_cpu(cpus_in_cluster, this_cpu),
GFP_KERNEL)) {
err = -ENOMEM;
} else if (!zalloc_cpumask_var(&per_cpu(ipi_mask, this_cpu),
GFP_KERNEL)) {
free_cpumask_var(per_cpu(cpus_in_cluster, this_cpu));
err = -ENOMEM;
}
break;
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
case CPU_DEAD:
for_each_online_cpu(cpu) {
if (x2apic_cluster(this_cpu) != x2apic_cluster(cpu))
continue;
cpumask_clear_cpu(this_cpu, per_cpu(cpus_in_cluster, cpu));
cpumask_clear_cpu(cpu, per_cpu(cpus_in_cluster, this_cpu));
}
free_cpumask_var(per_cpu(cpus_in_cluster, this_cpu));
free_cpumask_var(per_cpu(ipi_mask, this_cpu));
break;
}
return notifier_from_errno(err);
}
static struct notifier_block x2apic_cpu_notifier = {
.notifier_call = update_clusterinfo,
};
static int x2apic_init_cpu_notifier(void)
{
int cpu = smp_processor_id();
zalloc_cpumask_var(&per_cpu(cpus_in_cluster, cpu), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(ipi_mask, cpu), GFP_KERNEL);
BUG_ON(!per_cpu(cpus_in_cluster, cpu) || !per_cpu(ipi_mask, cpu));
cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, cpu));
register_hotcpu_notifier(&x2apic_cpu_notifier);
return 1;
}
static int x2apic_cluster_probe(void)
{
if (x2apic_mode)
return x2apic_init_cpu_notifier();
else
return 0;
}
static const struct cpumask *x2apic_cluster_target_cpus(void)
{
return cpu_all_mask;
}
/*
* Each x2apic cluster is an allocation domain.
*/
static void cluster_vector_allocation_domain(int cpu, struct cpumask *retmask,
const struct cpumask *mask)
{
/*
* To minimize vector pressure, default case of boot, device bringup
* etc will use a single cpu for the interrupt destination.
*
* On explicit migration requests coming from irqbalance etc,
* interrupts will be routed to the x2apic cluster (cluster-id
* derived from the first cpu in the mask) members specified
* in the mask.
*/
if (mask == x2apic_cluster_target_cpus())
cpumask_copy(retmask, cpumask_of(cpu));
else
cpumask_and(retmask, mask, per_cpu(cpus_in_cluster, cpu));
}
static struct apic apic_x2apic_cluster = {
.name = "cluster x2apic",
.probe = x2apic_cluster_probe,
.acpi_madt_oem_check = x2apic_acpi_madt_oem_check,
.apic_id_valid = x2apic_apic_id_valid,
.apic_id_registered = x2apic_apic_id_registered,
.irq_delivery_mode = dest_LowestPrio,
.irq_dest_mode = 1, /* logical */
.target_cpus = x2apic_cluster_target_cpus,
.disable_esr = 0,
.dest_logical = APIC_DEST_LOGICAL,
.check_apicid_used = NULL,
.vector_allocation_domain = cluster_vector_allocation_domain,
.init_apic_ldr = init_x2apic_ldr,
.ioapic_phys_id_map = NULL,
.setup_apic_routing = NULL,
.cpu_present_to_apicid = default_cpu_present_to_apicid,
.apicid_to_cpu_present = NULL,
.check_phys_apicid_present = default_check_phys_apicid_present,
.phys_pkg_id = x2apic_phys_pkg_id,
.get_apic_id = x2apic_get_apic_id,
.set_apic_id = x2apic_set_apic_id,
.apic_id_mask = 0xFFFFFFFFu,
.cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and,
.send_IPI = x2apic_send_IPI,
.send_IPI_mask = x2apic_send_IPI_mask,
.send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself,
.send_IPI_allbutself = x2apic_send_IPI_allbutself,
.send_IPI_all = x2apic_send_IPI_all,
.send_IPI_self = x2apic_send_IPI_self,
.inquire_remote_apic = NULL,
.read = native_apic_msr_read,
.write = native_apic_msr_write,
.eoi_write = native_apic_msr_eoi_write,
.icr_read = native_x2apic_icr_read,
.icr_write = native_x2apic_icr_write,
.wait_icr_idle = native_x2apic_wait_icr_idle,
.safe_wait_icr_idle = native_safe_x2apic_wait_icr_idle,
};
apic_driver(apic_x2apic_cluster);