mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-14 13:26:44 +07:00
652af89979
The arm64 kernel has an internal holding pen, which is necessary for some systems where we can't bring CPUs online individually and must hold multiple CPUs in a safe area until the kernel is able to handle them. The current SMP infrastructure for arm64 is closely coupled to this holding pen, and alternative boot methods must launch CPUs into the pen, where they sit before they are launched into the kernel proper. With PSCI (and possibly other future boot methods), we can bring CPUs online individually, and need not perform the secondary_holding_pen dance. Instead, this patch factors the holding pen management code out to the spin-table boot method code, as it is the only boot method requiring the pen. A new entry point for secondaries, secondary_entry is added for other boot methods to use, which bypasses the holding pen and its associated overhead when bringing CPUs online. The smp.pen.text section is also removed, as the pen can live in head.text without problem. The cpu_operations structure is extended with two new functions, cpu_boot and cpu_postboot, for bringing a cpu into the kernel and performing any post-boot cleanup required by a bootmethod (e.g. resetting the secondary_holding_pen_release to INVALID_HWID). Documentation is added for cpu_operations. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
495 lines
11 KiB
C
495 lines
11 KiB
C
/*
|
|
* SMP initialisation and IPI support
|
|
* Based on arch/arm/kernel/smp.c
|
|
*
|
|
* Copyright (C) 2012 ARM Ltd.
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
* published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program. If not, see <http://www.gnu.org/licenses/>.
|
|
*/
|
|
|
|
#include <linux/delay.h>
|
|
#include <linux/init.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/cache.h>
|
|
#include <linux/profile.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/err.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/seq_file.h>
|
|
#include <linux/irq.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/clockchips.h>
|
|
#include <linux/completion.h>
|
|
#include <linux/of.h>
|
|
|
|
#include <asm/atomic.h>
|
|
#include <asm/cacheflush.h>
|
|
#include <asm/cputype.h>
|
|
#include <asm/cpu_ops.h>
|
|
#include <asm/mmu_context.h>
|
|
#include <asm/pgtable.h>
|
|
#include <asm/pgalloc.h>
|
|
#include <asm/processor.h>
|
|
#include <asm/smp_plat.h>
|
|
#include <asm/sections.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/ptrace.h>
|
|
|
|
/*
|
|
* as from 2.5, kernels no longer have an init_tasks structure
|
|
* so we need some other way of telling a new secondary core
|
|
* where to place its SVC stack
|
|
*/
|
|
struct secondary_data secondary_data;
|
|
|
|
enum ipi_msg_type {
|
|
IPI_RESCHEDULE,
|
|
IPI_CALL_FUNC,
|
|
IPI_CALL_FUNC_SINGLE,
|
|
IPI_CPU_STOP,
|
|
};
|
|
|
|
/*
|
|
* Boot a secondary CPU, and assign it the specified idle task.
|
|
* This also gives us the initial stack to use for this CPU.
|
|
*/
|
|
static int boot_secondary(unsigned int cpu, struct task_struct *idle)
|
|
{
|
|
if (cpu_ops[cpu]->cpu_boot)
|
|
return cpu_ops[cpu]->cpu_boot(cpu);
|
|
|
|
return -EOPNOTSUPP;
|
|
}
|
|
|
|
static DECLARE_COMPLETION(cpu_running);
|
|
|
|
int __cpu_up(unsigned int cpu, struct task_struct *idle)
|
|
{
|
|
int ret;
|
|
|
|
/*
|
|
* We need to tell the secondary core where to find its stack and the
|
|
* page tables.
|
|
*/
|
|
secondary_data.stack = task_stack_page(idle) + THREAD_START_SP;
|
|
__flush_dcache_area(&secondary_data, sizeof(secondary_data));
|
|
|
|
/*
|
|
* Now bring the CPU into our world.
|
|
*/
|
|
ret = boot_secondary(cpu, idle);
|
|
if (ret == 0) {
|
|
/*
|
|
* CPU was successfully started, wait for it to come online or
|
|
* time out.
|
|
*/
|
|
wait_for_completion_timeout(&cpu_running,
|
|
msecs_to_jiffies(1000));
|
|
|
|
if (!cpu_online(cpu)) {
|
|
pr_crit("CPU%u: failed to come online\n", cpu);
|
|
ret = -EIO;
|
|
}
|
|
} else {
|
|
pr_err("CPU%u: failed to boot: %d\n", cpu, ret);
|
|
}
|
|
|
|
secondary_data.stack = NULL;
|
|
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* This is the secondary CPU boot entry. We're using this CPUs
|
|
* idle thread stack, but a set of temporary page tables.
|
|
*/
|
|
asmlinkage void secondary_start_kernel(void)
|
|
{
|
|
struct mm_struct *mm = &init_mm;
|
|
unsigned int cpu = smp_processor_id();
|
|
|
|
printk("CPU%u: Booted secondary processor\n", cpu);
|
|
|
|
/*
|
|
* All kernel threads share the same mm context; grab a
|
|
* reference and switch to it.
|
|
*/
|
|
atomic_inc(&mm->mm_count);
|
|
current->active_mm = mm;
|
|
cpumask_set_cpu(cpu, mm_cpumask(mm));
|
|
|
|
/*
|
|
* TTBR0 is only used for the identity mapping at this stage. Make it
|
|
* point to zero page to avoid speculatively fetching new entries.
|
|
*/
|
|
cpu_set_reserved_ttbr0();
|
|
flush_tlb_all();
|
|
|
|
preempt_disable();
|
|
trace_hardirqs_off();
|
|
|
|
if (cpu_ops[cpu]->cpu_postboot)
|
|
cpu_ops[cpu]->cpu_postboot();
|
|
|
|
/*
|
|
* OK, now it's safe to let the boot CPU continue. Wait for
|
|
* the CPU migration code to notice that the CPU is online
|
|
* before we continue.
|
|
*/
|
|
set_cpu_online(cpu, true);
|
|
complete(&cpu_running);
|
|
|
|
/*
|
|
* Enable GIC and timers.
|
|
*/
|
|
notify_cpu_starting(cpu);
|
|
|
|
local_irq_enable();
|
|
local_fiq_enable();
|
|
|
|
/*
|
|
* OK, it's off to the idle thread for us
|
|
*/
|
|
cpu_startup_entry(CPUHP_ONLINE);
|
|
}
|
|
|
|
void __init smp_cpus_done(unsigned int max_cpus)
|
|
{
|
|
pr_info("SMP: Total of %d processors activated.\n", num_online_cpus());
|
|
}
|
|
|
|
void __init smp_prepare_boot_cpu(void)
|
|
{
|
|
}
|
|
|
|
static void (*smp_cross_call)(const struct cpumask *, unsigned int);
|
|
|
|
/*
|
|
* Enumerate the possible CPU set from the device tree and build the
|
|
* cpu logical map array containing MPIDR values related to logical
|
|
* cpus. Assumes that cpu_logical_map(0) has already been initialized.
|
|
*/
|
|
void __init smp_init_cpus(void)
|
|
{
|
|
const char *enable_method;
|
|
struct device_node *dn = NULL;
|
|
unsigned int i, cpu = 1;
|
|
bool bootcpu_valid = false;
|
|
|
|
while ((dn = of_find_node_by_type(dn, "cpu"))) {
|
|
const u32 *cell;
|
|
u64 hwid;
|
|
|
|
/*
|
|
* A cpu node with missing "reg" property is
|
|
* considered invalid to build a cpu_logical_map
|
|
* entry.
|
|
*/
|
|
cell = of_get_property(dn, "reg", NULL);
|
|
if (!cell) {
|
|
pr_err("%s: missing reg property\n", dn->full_name);
|
|
goto next;
|
|
}
|
|
hwid = of_read_number(cell, of_n_addr_cells(dn));
|
|
|
|
/*
|
|
* Non affinity bits must be set to 0 in the DT
|
|
*/
|
|
if (hwid & ~MPIDR_HWID_BITMASK) {
|
|
pr_err("%s: invalid reg property\n", dn->full_name);
|
|
goto next;
|
|
}
|
|
|
|
/*
|
|
* Duplicate MPIDRs are a recipe for disaster. Scan
|
|
* all initialized entries and check for
|
|
* duplicates. If any is found just ignore the cpu.
|
|
* cpu_logical_map was initialized to INVALID_HWID to
|
|
* avoid matching valid MPIDR values.
|
|
*/
|
|
for (i = 1; (i < cpu) && (i < NR_CPUS); i++) {
|
|
if (cpu_logical_map(i) == hwid) {
|
|
pr_err("%s: duplicate cpu reg properties in the DT\n",
|
|
dn->full_name);
|
|
goto next;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* The numbering scheme requires that the boot CPU
|
|
* must be assigned logical id 0. Record it so that
|
|
* the logical map built from DT is validated and can
|
|
* be used.
|
|
*/
|
|
if (hwid == cpu_logical_map(0)) {
|
|
if (bootcpu_valid) {
|
|
pr_err("%s: duplicate boot cpu reg property in DT\n",
|
|
dn->full_name);
|
|
goto next;
|
|
}
|
|
|
|
bootcpu_valid = true;
|
|
|
|
/*
|
|
* cpu_logical_map has already been
|
|
* initialized and the boot cpu doesn't need
|
|
* the enable-method so continue without
|
|
* incrementing cpu.
|
|
*/
|
|
continue;
|
|
}
|
|
|
|
if (cpu >= NR_CPUS)
|
|
goto next;
|
|
|
|
/*
|
|
* We currently support only the "spin-table" enable-method.
|
|
*/
|
|
enable_method = of_get_property(dn, "enable-method", NULL);
|
|
if (!enable_method) {
|
|
pr_err("%s: missing enable-method property\n",
|
|
dn->full_name);
|
|
goto next;
|
|
}
|
|
|
|
cpu_ops[cpu] = cpu_get_ops(enable_method);
|
|
|
|
if (!cpu_ops[cpu]) {
|
|
pr_err("%s: invalid enable-method property: %s\n",
|
|
dn->full_name, enable_method);
|
|
goto next;
|
|
}
|
|
|
|
if (cpu_ops[cpu]->cpu_init(dn, cpu))
|
|
goto next;
|
|
|
|
pr_debug("cpu logical map 0x%llx\n", hwid);
|
|
cpu_logical_map(cpu) = hwid;
|
|
next:
|
|
cpu++;
|
|
}
|
|
|
|
/* sanity check */
|
|
if (cpu > NR_CPUS)
|
|
pr_warning("no. of cores (%d) greater than configured maximum of %d - clipping\n",
|
|
cpu, NR_CPUS);
|
|
|
|
if (!bootcpu_valid) {
|
|
pr_err("DT missing boot CPU MPIDR, not enabling secondaries\n");
|
|
return;
|
|
}
|
|
|
|
/*
|
|
* All the cpus that made it to the cpu_logical_map have been
|
|
* validated so set them as possible cpus.
|
|
*/
|
|
for (i = 0; i < NR_CPUS; i++)
|
|
if (cpu_logical_map(i) != INVALID_HWID)
|
|
set_cpu_possible(i, true);
|
|
}
|
|
|
|
void __init smp_prepare_cpus(unsigned int max_cpus)
|
|
{
|
|
int err;
|
|
unsigned int cpu, ncores = num_possible_cpus();
|
|
|
|
/*
|
|
* are we trying to boot more cores than exist?
|
|
*/
|
|
if (max_cpus > ncores)
|
|
max_cpus = ncores;
|
|
|
|
/* Don't bother if we're effectively UP */
|
|
if (max_cpus <= 1)
|
|
return;
|
|
|
|
/*
|
|
* Initialise the present map (which describes the set of CPUs
|
|
* actually populated at the present time) and release the
|
|
* secondaries from the bootloader.
|
|
*
|
|
* Make sure we online at most (max_cpus - 1) additional CPUs.
|
|
*/
|
|
max_cpus--;
|
|
for_each_possible_cpu(cpu) {
|
|
if (max_cpus == 0)
|
|
break;
|
|
|
|
if (cpu == smp_processor_id())
|
|
continue;
|
|
|
|
if (!cpu_ops[cpu])
|
|
continue;
|
|
|
|
err = cpu_ops[cpu]->cpu_prepare(cpu);
|
|
if (err)
|
|
continue;
|
|
|
|
set_cpu_present(cpu, true);
|
|
max_cpus--;
|
|
}
|
|
}
|
|
|
|
|
|
void __init set_smp_cross_call(void (*fn)(const struct cpumask *, unsigned int))
|
|
{
|
|
smp_cross_call = fn;
|
|
}
|
|
|
|
void arch_send_call_function_ipi_mask(const struct cpumask *mask)
|
|
{
|
|
smp_cross_call(mask, IPI_CALL_FUNC);
|
|
}
|
|
|
|
void arch_send_call_function_single_ipi(int cpu)
|
|
{
|
|
smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
|
|
}
|
|
|
|
static const char *ipi_types[NR_IPI] = {
|
|
#define S(x,s) [x - IPI_RESCHEDULE] = s
|
|
S(IPI_RESCHEDULE, "Rescheduling interrupts"),
|
|
S(IPI_CALL_FUNC, "Function call interrupts"),
|
|
S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
|
|
S(IPI_CPU_STOP, "CPU stop interrupts"),
|
|
};
|
|
|
|
void show_ipi_list(struct seq_file *p, int prec)
|
|
{
|
|
unsigned int cpu, i;
|
|
|
|
for (i = 0; i < NR_IPI; i++) {
|
|
seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i + IPI_RESCHEDULE,
|
|
prec >= 4 ? " " : "");
|
|
for_each_present_cpu(cpu)
|
|
seq_printf(p, "%10u ",
|
|
__get_irq_stat(cpu, ipi_irqs[i]));
|
|
seq_printf(p, " %s\n", ipi_types[i]);
|
|
}
|
|
}
|
|
|
|
u64 smp_irq_stat_cpu(unsigned int cpu)
|
|
{
|
|
u64 sum = 0;
|
|
int i;
|
|
|
|
for (i = 0; i < NR_IPI; i++)
|
|
sum += __get_irq_stat(cpu, ipi_irqs[i]);
|
|
|
|
return sum;
|
|
}
|
|
|
|
static DEFINE_RAW_SPINLOCK(stop_lock);
|
|
|
|
/*
|
|
* ipi_cpu_stop - handle IPI from smp_send_stop()
|
|
*/
|
|
static void ipi_cpu_stop(unsigned int cpu)
|
|
{
|
|
if (system_state == SYSTEM_BOOTING ||
|
|
system_state == SYSTEM_RUNNING) {
|
|
raw_spin_lock(&stop_lock);
|
|
pr_crit("CPU%u: stopping\n", cpu);
|
|
dump_stack();
|
|
raw_spin_unlock(&stop_lock);
|
|
}
|
|
|
|
set_cpu_online(cpu, false);
|
|
|
|
local_fiq_disable();
|
|
local_irq_disable();
|
|
|
|
while (1)
|
|
cpu_relax();
|
|
}
|
|
|
|
/*
|
|
* Main handler for inter-processor interrupts
|
|
*/
|
|
void handle_IPI(int ipinr, struct pt_regs *regs)
|
|
{
|
|
unsigned int cpu = smp_processor_id();
|
|
struct pt_regs *old_regs = set_irq_regs(regs);
|
|
|
|
if (ipinr >= IPI_RESCHEDULE && ipinr < IPI_RESCHEDULE + NR_IPI)
|
|
__inc_irq_stat(cpu, ipi_irqs[ipinr - IPI_RESCHEDULE]);
|
|
|
|
switch (ipinr) {
|
|
case IPI_RESCHEDULE:
|
|
scheduler_ipi();
|
|
break;
|
|
|
|
case IPI_CALL_FUNC:
|
|
irq_enter();
|
|
generic_smp_call_function_interrupt();
|
|
irq_exit();
|
|
break;
|
|
|
|
case IPI_CALL_FUNC_SINGLE:
|
|
irq_enter();
|
|
generic_smp_call_function_single_interrupt();
|
|
irq_exit();
|
|
break;
|
|
|
|
case IPI_CPU_STOP:
|
|
irq_enter();
|
|
ipi_cpu_stop(cpu);
|
|
irq_exit();
|
|
break;
|
|
|
|
default:
|
|
pr_crit("CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr);
|
|
break;
|
|
}
|
|
set_irq_regs(old_regs);
|
|
}
|
|
|
|
void smp_send_reschedule(int cpu)
|
|
{
|
|
smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
|
|
}
|
|
|
|
void smp_send_stop(void)
|
|
{
|
|
unsigned long timeout;
|
|
|
|
if (num_online_cpus() > 1) {
|
|
cpumask_t mask;
|
|
|
|
cpumask_copy(&mask, cpu_online_mask);
|
|
cpu_clear(smp_processor_id(), mask);
|
|
|
|
smp_cross_call(&mask, IPI_CPU_STOP);
|
|
}
|
|
|
|
/* Wait up to one second for other CPUs to stop */
|
|
timeout = USEC_PER_SEC;
|
|
while (num_online_cpus() > 1 && timeout--)
|
|
udelay(1);
|
|
|
|
if (num_online_cpus() > 1)
|
|
pr_warning("SMP: failed to stop secondary CPUs\n");
|
|
}
|
|
|
|
/*
|
|
* not supported here
|
|
*/
|
|
int setup_profiling_timer(unsigned int multiplier)
|
|
{
|
|
return -EINVAL;
|
|
}
|