linux/arch/riscv/kernel/smp.c
Guo Ren 9b932aadfc
riscv: kexec: Fixup crash_smp_send_stop without multi cores
Current crash_smp_send_stop is the same as the generic one in
kernel/panic and misses crash_save_cpu in percpu. This patch is inspired
by 78fd584cde ("arm64: kdump: implement machine_crash_shutdown()")
and adds the same mechanism for riscv.

Before this patch, test result:
crash> help -r
CPU 0: [OFFLINE]

CPU 1:
epc : ffffffff80009ff0 ra : ffffffff800b789a sp : ff2000001098bb40
 gp : ffffffff815fca60 tp : ff60000004680000 t0 : 6666666666663c5b
 t1 : 0000000000000000 t2 : 666666666666663c s0 : ff2000001098bc90
 s1 : ffffffff81600798 a0 : ff2000001098bb48 a1 : 0000000000000000
 a2 : 0000000000000000 a3 : 0000000000000001 a4 : 0000000000000000
 a5 : ff60000004690800 a6 : 0000000000000000 a7 : 0000000000000000
 s2 : ff2000001098bb48 s3 : ffffffff81093ec8 s4 : ffffffff816004ac
 s5 : 0000000000000000 s6 : 0000000000000007 s7 : ffffffff80e7f720
 s8 : 00fffffffffff3f0 s9 : 0000000000000007 s10: 00aaaaaaaab98700
 s11: 0000000000000001 t3 : ffffffff819a8097 t4 : ffffffff819a8097
 t5 : ffffffff819a8098 t6 : ff2000001098b9a8

CPU 2: [OFFLINE]

CPU 3: [OFFLINE]

After this patch, test result:
crash> help -r
CPU 0:
epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ffffffff81403eb0
 gp : ffffffff815fcb48 tp : ffffffff81413400 t0 : 0000000000000000
 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ffffffff81403ec0
 s1 : 0000000000000000 a0 : 0000000000000000 a1 : 0000000000000000
 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000
 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000
 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18
 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000
 s8 : 0000000000000000 s9 : 0000000080039eac s10: 0000000000000000
 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000
 t5 : 0000000000000000 t6 : 0000000000000000

CPU 1:
epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ff2000000068bf30
 gp : ffffffff815fcb48 tp : ff6000000240d400 t0 : 0000000000000000
 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ff2000000068bf40
 s1 : 0000000000000001 a0 : 0000000000000000 a1 : 0000000000000000
 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000
 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000
 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18
 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000
 s8 : 0000000000000000 s9 : 0000000080039ea8 s10: 0000000000000000
 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000
 t5 : 0000000000000000 t6 : 0000000000000000

CPU 2:
epc : ffffffff80003f34 ra : ffffffff808caa7c sp : ff20000000693f30
 gp : ffffffff815fcb48 tp : ff6000000240e900 t0 : 0000000000000000
 t1 : 0000000000000000 t2 : 0000000000000000 s0 : ff20000000693f40
 s1 : 0000000000000002 a0 : 0000000000000000 a1 : 0000000000000000
 a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000
 a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000
 s2 : ffffffff816001c8 s3 : ffffffff81600370 s4 : ffffffff80c32e18
 s5 : ffffffff819d3018 s6 : ffffffff810e2110 s7 : 0000000000000000
 s8 : 0000000000000000 s9 : 0000000080039eb0 s10: 0000000000000000
 s11: 0000000000000000 t3 : 0000000000000000 t4 : 0000000000000000
 t5 : 0000000000000000 t6 : 0000000000000000

CPU 3:
epc : ffffffff8000a1e4 ra : ffffffff800b7bba sp : ff200000109bbb40
 gp : ffffffff815fcb48 tp : ff6000000373aa00 t0 : 6666666666663c5b
 t1 : 0000000000000000 t2 : 666666666666663c s0 : ff200000109bbc90
 s1 : ffffffff816007a0 a0 : ff200000109bbb48 a1 : 0000000000000000
 a2 : 0000000000000000 a3 : 0000000000000001 a4 : 0000000000000000
 a5 : ff60000002c61c00 a6 : 0000000000000000 a7 : 0000000000000000
 s2 : ff200000109bbb48 s3 : ffffffff810941a8 s4 : ffffffff816004b4
 s5 : 0000000000000000 s6 : 0000000000000007 s7 : ffffffff80e7f7a0
 s8 : 00fffffffffff3f0 s9 : 0000000000000007 s10: 00aaaaaaaab98700
 s11: 0000000000000001 t3 : ffffffff819a8097 t4 : ffffffff819a8097
 t5 : ffffffff819a8098 t6 : ff200000109bb9a8

Fixes: ad943893d5 ("RISC-V: Fixup schedule out issue in machine_crash_shutdown()")
Reviewed-by: Xianting Tian <xianting.tian@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@kernel.org>
Cc: Nick Kossifidis <mick@ics.forth.gr>
Link: https://lore.kernel.org/r/20221020141603.2856206-3-guoren@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
2022-11-29 21:50:59 -08:00

336 lines
7.1 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* SMP initialisation and IPI support
* Based on arch/arm64/kernel/smp.c
*
* Copyright (C) 2012 ARM Ltd.
* Copyright (C) 2015 Regents of the University of California
* Copyright (C) 2017 SiFive
*/
#include <linux/cpu.h>
#include <linux/clockchips.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/kexec.h>
#include <linux/profile.h>
#include <linux/smp.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/delay.h>
#include <linux/irq_work.h>
#include <asm/sbi.h>
#include <asm/tlbflush.h>
#include <asm/cacheflush.h>
#include <asm/cpu_ops.h>
enum ipi_message_type {
IPI_RESCHEDULE,
IPI_CALL_FUNC,
IPI_CPU_STOP,
IPI_CPU_CRASH_STOP,
IPI_IRQ_WORK,
IPI_TIMER,
IPI_MAX
};
unsigned long __cpuid_to_hartid_map[NR_CPUS] __ro_after_init = {
[0 ... NR_CPUS-1] = INVALID_HARTID
};
void __init smp_setup_processor_id(void)
{
cpuid_to_hartid_map(0) = boot_cpu_hartid;
}
/* A collection of single bit ipi messages. */
static struct {
unsigned long stats[IPI_MAX] ____cacheline_aligned;
unsigned long bits ____cacheline_aligned;
} ipi_data[NR_CPUS] __cacheline_aligned;
int riscv_hartid_to_cpuid(unsigned long hartid)
{
int i;
for (i = 0; i < NR_CPUS; i++)
if (cpuid_to_hartid_map(i) == hartid)
return i;
pr_err("Couldn't find cpu id for hartid [%lu]\n", hartid);
return -ENOENT;
}
bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
{
return phys_id == cpuid_to_hartid_map(cpu);
}
static void ipi_stop(void)
{
set_cpu_online(smp_processor_id(), false);
while (1)
wait_for_interrupt();
}
#ifdef CONFIG_KEXEC_CORE
static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0);
static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
{
crash_save_cpu(regs, cpu);
atomic_dec(&waiting_for_crash_ipi);
local_irq_disable();
#ifdef CONFIG_HOTPLUG_CPU
if (cpu_has_hotplug(cpu))
cpu_ops[cpu]->cpu_stop();
#endif
for(;;)
wait_for_interrupt();
}
#else
static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
{
unreachable();
}
#endif
static const struct riscv_ipi_ops *ipi_ops __ro_after_init;
void riscv_set_ipi_ops(const struct riscv_ipi_ops *ops)
{
ipi_ops = ops;
}
EXPORT_SYMBOL_GPL(riscv_set_ipi_ops);
void riscv_clear_ipi(void)
{
if (ipi_ops && ipi_ops->ipi_clear)
ipi_ops->ipi_clear();
csr_clear(CSR_IP, IE_SIE);
}
EXPORT_SYMBOL_GPL(riscv_clear_ipi);
static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op)
{
int cpu;
smp_mb__before_atomic();
for_each_cpu(cpu, mask)
set_bit(op, &ipi_data[cpu].bits);
smp_mb__after_atomic();
if (ipi_ops && ipi_ops->ipi_inject)
ipi_ops->ipi_inject(mask);
else
pr_warn("SMP: IPI inject method not available\n");
}
static void send_ipi_single(int cpu, enum ipi_message_type op)
{
smp_mb__before_atomic();
set_bit(op, &ipi_data[cpu].bits);
smp_mb__after_atomic();
if (ipi_ops && ipi_ops->ipi_inject)
ipi_ops->ipi_inject(cpumask_of(cpu));
else
pr_warn("SMP: IPI inject method not available\n");
}
#ifdef CONFIG_IRQ_WORK
void arch_irq_work_raise(void)
{
send_ipi_single(smp_processor_id(), IPI_IRQ_WORK);
}
#endif
void handle_IPI(struct pt_regs *regs)
{
unsigned int cpu = smp_processor_id();
unsigned long *pending_ipis = &ipi_data[cpu].bits;
unsigned long *stats = ipi_data[cpu].stats;
riscv_clear_ipi();
while (true) {
unsigned long ops;
/* Order bit clearing and data access. */
mb();
ops = xchg(pending_ipis, 0);
if (ops == 0)
return;
if (ops & (1 << IPI_RESCHEDULE)) {
stats[IPI_RESCHEDULE]++;
scheduler_ipi();
}
if (ops & (1 << IPI_CALL_FUNC)) {
stats[IPI_CALL_FUNC]++;
generic_smp_call_function_interrupt();
}
if (ops & (1 << IPI_CPU_STOP)) {
stats[IPI_CPU_STOP]++;
ipi_stop();
}
if (ops & (1 << IPI_CPU_CRASH_STOP)) {
ipi_cpu_crash_stop(cpu, get_irq_regs());
}
if (ops & (1 << IPI_IRQ_WORK)) {
stats[IPI_IRQ_WORK]++;
irq_work_run();
}
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
if (ops & (1 << IPI_TIMER)) {
stats[IPI_TIMER]++;
tick_receive_broadcast();
}
#endif
BUG_ON((ops >> IPI_MAX) != 0);
/* Order data access and bit testing. */
mb();
}
}
static const char * const ipi_names[] = {
[IPI_RESCHEDULE] = "Rescheduling interrupts",
[IPI_CALL_FUNC] = "Function call interrupts",
[IPI_CPU_STOP] = "CPU stop interrupts",
[IPI_CPU_CRASH_STOP] = "CPU stop (for crash dump) interrupts",
[IPI_IRQ_WORK] = "IRQ work interrupts",
[IPI_TIMER] = "Timer broadcast interrupts",
};
void show_ipi_stats(struct seq_file *p, int prec)
{
unsigned int cpu, i;
for (i = 0; i < IPI_MAX; i++) {
seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i,
prec >= 4 ? " " : "");
for_each_online_cpu(cpu)
seq_printf(p, "%10lu ", ipi_data[cpu].stats[i]);
seq_printf(p, " %s\n", ipi_names[i]);
}
}
void arch_send_call_function_ipi_mask(struct cpumask *mask)
{
send_ipi_mask(mask, IPI_CALL_FUNC);
}
void arch_send_call_function_single_ipi(int cpu)
{
send_ipi_single(cpu, IPI_CALL_FUNC);
}
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
void tick_broadcast(const struct cpumask *mask)
{
send_ipi_mask(mask, IPI_TIMER);
}
#endif
void smp_send_stop(void)
{
unsigned long timeout;
if (num_online_cpus() > 1) {
cpumask_t mask;
cpumask_copy(&mask, cpu_online_mask);
cpumask_clear_cpu(smp_processor_id(), &mask);
if (system_state <= SYSTEM_RUNNING)
pr_crit("SMP: stopping secondary CPUs\n");
send_ipi_mask(&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_warn("SMP: failed to stop secondary CPUs %*pbl\n",
cpumask_pr_args(cpu_online_mask));
}
#ifdef CONFIG_KEXEC_CORE
/*
* The number of CPUs online, not counting this CPU (which may not be
* fully online and so not counted in num_online_cpus()).
*/
static inline unsigned int num_other_online_cpus(void)
{
unsigned int this_cpu_online = cpu_online(smp_processor_id());
return num_online_cpus() - this_cpu_online;
}
void crash_smp_send_stop(void)
{
static int cpus_stopped;
cpumask_t mask;
unsigned long timeout;
/*
* This function can be called twice in panic path, but obviously
* we execute this only once.
*/
if (cpus_stopped)
return;
cpus_stopped = 1;
/*
* If this cpu is the only one alive at this point in time, online or
* not, there are no stop messages to be sent around, so just back out.
*/
if (num_other_online_cpus() == 0)
return;
cpumask_copy(&mask, cpu_online_mask);
cpumask_clear_cpu(smp_processor_id(), &mask);
atomic_set(&waiting_for_crash_ipi, num_other_online_cpus());
pr_crit("SMP: stopping secondary CPUs\n");
send_ipi_mask(&mask, IPI_CPU_CRASH_STOP);
/* Wait up to one second for other CPUs to stop */
timeout = USEC_PER_SEC;
while ((atomic_read(&waiting_for_crash_ipi) > 0) && timeout--)
udelay(1);
if (atomic_read(&waiting_for_crash_ipi) > 0)
pr_warn("SMP: failed to stop secondary CPUs %*pbl\n",
cpumask_pr_args(&mask));
}
bool smp_crash_stop_failed(void)
{
return (atomic_read(&waiting_for_crash_ipi) > 0);
}
#endif
void smp_send_reschedule(int cpu)
{
send_ipi_single(cpu, IPI_RESCHEDULE);
}
EXPORT_SYMBOL_GPL(smp_send_reschedule);