[PATCH v2 3/3] LoongArch: SMP: Implement parallel CPU bring up
From: Jiaxun Yang
Date: Mon Jul 15 2024 - 09:36:20 EST
Implement parallel CPU bring up for LoongArch to reduce
boot time consumption on bring up CPUs.
On my Loongson-3A5000 ~120ms boot time improvement is observed.
tp, sp register values are passed by MBUF now to avoid racing
cpuboot_data global struct.
cpu_running completion is handled by HOTPLUG_CORE_SYNC_FULL.
Signed-off-by: Jiaxun Yang <jiaxun.yang@xxxxxxxxxxx>
---
arch/loongarch/Kconfig | 1 +
arch/loongarch/include/asm/smp.h | 6 ------
arch/loongarch/kernel/asm-offsets.c | 10 ----------
arch/loongarch/kernel/head.S | 7 ++++---
arch/loongarch/kernel/smp.c | 35 +++++++----------------------------
5 files changed, 12 insertions(+), 47 deletions(-)
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index ddc042895d01..656435c1dbd5 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -162,6 +162,7 @@ config LOONGARCH
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_TIF_NOHZ
select HAVE_VIRT_CPU_ACCOUNTING_GEN if !SMP
+ select HOTPLUG_PARALLEL if SMP
select IRQ_FORCED_THREADING
select IRQ_LOONGARCH_CPU
select LOCK_MM_AND_FIND_VMA
diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h
index 50db503f44e3..f6953cb16492 100644
--- a/arch/loongarch/include/asm/smp.h
+++ b/arch/loongarch/include/asm/smp.h
@@ -75,12 +75,6 @@ extern int __cpu_logical_map[NR_CPUS];
#define SMP_CALL_FUNCTION BIT(ACTION_CALL_FUNCTION)
#define SMP_IRQ_WORK BIT(ACTION_IRQ_WORK)
-struct secondary_data {
- unsigned long stack;
- unsigned long thread_info;
-};
-extern struct secondary_data cpuboot_data;
-
extern asmlinkage void smpboot_entry(void);
extern asmlinkage void start_secondary(void);
diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c
index bee9f7a3108f..598498f47a4c 100644
--- a/arch/loongarch/kernel/asm-offsets.c
+++ b/arch/loongarch/kernel/asm-offsets.c
@@ -257,16 +257,6 @@ static void __used output_signal_defines(void)
BLANK();
}
-#ifdef CONFIG_SMP
-static void __used output_smpboot_defines(void)
-{
- COMMENT("Linux smp cpu boot offsets.");
- OFFSET(CPU_BOOT_STACK, secondary_data, stack);
- OFFSET(CPU_BOOT_TINFO, secondary_data, thread_info);
- BLANK();
-}
-#endif
-
#ifdef CONFIG_HIBERNATION
static void __used output_pbe_defines(void)
{
diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S
index fdb831dc64df..8dd8fb450f46 100644
--- a/arch/loongarch/kernel/head.S
+++ b/arch/loongarch/kernel/head.S
@@ -136,9 +136,10 @@ SYM_CODE_START(smpboot_entry)
li.w t0, 0x00 # FPE=0, SXE=0, ASXE=0, BTE=0
csrwr t0, LOONGARCH_CSR_EUEN
- la.pcrel t0, cpuboot_data
- ld.d sp, t0, CPU_BOOT_STACK
- ld.d tp, t0, CPU_BOOT_TINFO
+ li.w t0, LOONGARCH_IOCSR_MBUF1
+ iocsrrd.d sp, t0
+ li.w t0, LOONGARCH_IOCSR_MBUF2
+ iocsrrd.d tp, t0
bl start_secondary
ASM_BUG()
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index ca405ab86aae..ca6a95a0280d 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -48,10 +48,6 @@ EXPORT_SYMBOL(cpu_sibling_map);
/* Representing the core map of multi-core chips of each logical CPU */
cpumask_t cpu_core_map[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(cpu_core_map);
-
-static DECLARE_COMPLETION(cpu_starting);
-static DECLARE_COMPLETION(cpu_running);
-
/*
* A logcal cpu mask containing only one VPE per core to
* reduce the number of IPIs on large MT systems.
@@ -65,7 +61,6 @@ static cpumask_t cpu_sibling_setup_map;
/* representing cpus for which core maps can be computed */
static cpumask_t cpu_core_setup_map;
-struct secondary_data cpuboot_data;
static DEFINE_PER_CPU(int, cpu_state);
static const char *ipi_types[NR_IPI] __tracepoint_string = {
@@ -340,14 +335,16 @@ void __init loongson_prepare_cpus(unsigned int max_cpus)
*/
void loongson_boot_secondary(int cpu, struct task_struct *idle)
{
- unsigned long entry;
+ unsigned long entry, stack, thread_info;
pr_info("Booting CPU#%d...\n", cpu);
entry = __pa_symbol((unsigned long)&smpboot_entry);
- cpuboot_data.stack = (unsigned long)__KSTK_TOS(idle);
- cpuboot_data.thread_info = (unsigned long)task_thread_info(idle);
+ stack = (unsigned long)__KSTK_TOS(idle);
+ thread_info = (unsigned long)task_thread_info(idle);
+ csr_mail_send(thread_info, cpu_logical_map(cpu), 2);
+ csr_mail_send(stack, cpu_logical_map(cpu), 1);
csr_mail_send(entry, cpu_logical_map(cpu), 0);
loongson_send_ipi_single(cpu, ACTION_BOOT_CPU);
@@ -525,20 +522,10 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
#endif
}
-int __cpu_up(unsigned int cpu, struct task_struct *tidle)
+int arch_cpuhp_kick_ap_alive(unsigned int cpu, struct task_struct *tidle)
{
loongson_boot_secondary(cpu, tidle);
- /* Wait for CPU to start and be ready to sync counters */
- if (!wait_for_completion_timeout(&cpu_starting,
- msecs_to_jiffies(5000))) {
- pr_crit("CPU%u: failed to start\n", cpu);
- return -EIO;
- }
-
- /* Wait for CPU to finish startup & mark itself online before return */
- wait_for_completion(&cpu_running);
-
return 0;
}
@@ -561,22 +548,14 @@ asmlinkage void start_secondary(void)
set_cpu_sibling_map(cpu);
set_cpu_core_map(cpu);
+ cpuhp_ap_sync_alive();
notify_cpu_starting(cpu);
- /* Notify boot CPU that we're starting */
- complete(&cpu_starting);
-
/* The CPU is running, now mark it online */
set_cpu_online(cpu, true);
calculate_cpu_foreign_map();
- /*
- * Notify boot CPU that we're up & online and it can safely return
- * from __cpu_up()
- */
- complete(&cpu_running);
-
/*
* irq will be enabled in loongson_smp_finish(), enabling it too
* early is dangerous.
--
2.45.2