LoongArch: Give a chance to build with !CONFIG_SMP

In the current code, SMP is selected in Kconfig for LoongArch, the users
can not unset it, this is reasonable for a multi-processor machine. But
as the help info of config SMP said, if you have a system with only one
CPU, say N. On a uni-processor machine, the kernel will run faster if you
say N here.

Loongson-2K0500 is a single-core CPU for applications like industrial
control, printing terminals, and BMC (Baseboard Management Controller),
there are many development boards, products and solutions on the market,
so it is better and necessary to give a chance to build with !CONFIG_SMP
for a uni-processor machine.

First of all, do not select SMP for config LOONGARCH in Kconfig to make
it possible to unset CONFIG_SMP. Then, do some changes to fix warnings
and errors if CONFIG_SMP is not set.

(1) Define get_ipi_irq() only if CONFIG_SMP is set to fix the warning:
arch/loongarch/kernel/irq.c:90:19: warning: 'get_ipi_irq' defined but not used [-Wunused-function]

(2) Add "#ifdef CONFIG_SMP" in asm/smp.h to fix the warning:
./arch/loongarch/include/asm/smp.h:49:9: warning: "raw_smp_processor_id" redefined
   49 | #define raw_smp_processor_id raw_smp_processor_id
      |         ^~~~~~~~~~~~~~~~~~~~
./include/linux/smp.h:198:9: note: this is the location of the previous definition
  198 | #define raw_smp_processor_id()                  0

(3) Define machine_shutdown() as empty under !CONFIG_SMP to fix the error:
arch/loongarch/kernel/machine_kexec.c: In function 'machine_shutdown':
arch/loongarch/kernel/machine_kexec.c:233:25: error: implicit declaration of function 'cpu_device_up'; did you mean 'put_device'? [-Wimplicit-function-declaration]

(4) Make config SCHED_SMT depends on SMP to fix many errors such as:
kernel/sched/core.c: In function 'sched_core_find':
kernel/sched/core.c:310:43: error: 'struct rq' has no member named 'cpu'

(5) Define cpu_logical_map(cpu) as 0 under !CONFIG_SMP in asm/smp.h,
then include asm/smp.h in asm/acpi.h (because acpi.h is included in
linux/irq.h indirectly) to fix many build errors under drivers/irqchip
such as:
drivers/irqchip/irq-loongson-eiointc.c: In function 'cpu_to_eio_node':
drivers/irqchip/irq-loongson-eiointc.c:59:16: error: implicit declaration of function 'cpu_logical_map' [-Wimplicit-function-declaration]

(6) Do not write per_cpu_offset(0) to PERCPU_BASE_KS when resume because
the per_cpu_offset(x) macro is defined as (__per_cpu_offset[x]) only
under CONFIG_SMP in include/asm-generic/percpu.h. Just save the value of
PERCPU_BASE_KS when suspend and restore it when resume to fix the error:
arch/loongarch/power/suspend.c: In function 'loongarch_common_resume':
arch/loongarch/power/suspend.c:47:21: error: implicit declaration of function 'per_cpu_offset' [-Wimplicit-function-declaration]

(7) Fix huge page handling under !CONFIG_SMP in tlbex.S.

When running the UnixBench tests with "-c 1" single-streamed pass, the
improvement of performance is about 9 percent with this patch.

By the way, it is helpful to debug and analysis the kernel issues of
multi-processor system under !CONFIG_SMP.
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>

arch/loongarch/Kconfig

@@ -178,7 +178,6 @@ config LOONGARCH
 	select PCI_QUIRKS
 	select PERF_USE_VMALLOC
 	select RTC_LIB
-	select SMP
 	select SPARSE_IRQ
 	select SYSCTL_ARCH_UNALIGN_ALLOW
 	select SYSCTL_ARCH_UNALIGN_NO_WARN
@@ -424,6 +423,7 @@ config EFI_STUB
 
 config SCHED_SMT
 	bool "SMT scheduler support"
+	depends on SMP
 	default y
 	help
 	  Improves scheduler's performance when there are multiple

arch/loongarch/include/asm/acpi.h

@@ -8,6 +8,7 @@
 #ifndef _ASM_LOONGARCH_ACPI_H
 #define _ASM_LOONGARCH_ACPI_H
 
+#include <asm/smp.h>
 #include <asm/suspend.h>
 
 #ifdef CONFIG_ACPI

arch/loongarch/include/asm/smp.h

@@ -6,6 +6,8 @@
 #ifndef __ASM_SMP_H
 #define __ASM_SMP_H
 
+#ifdef CONFIG_SMP
+
 #include <linux/atomic.h>
 #include <linux/bitops.h>
 #include <linux/linkage.h>
@@ -101,4 +103,8 @@ static inline void __cpu_die(unsigned int cpu)
 }
 #endif
 
+#else /* !CONFIG_SMP */
+#define cpu_logical_map(cpu)	0
+#endif /* CONFIG_SMP */
+
 #endif /* __ASM_SMP_H */

arch/loongarch/kernel/irq.c

@@ -87,6 +87,7 @@ static void __init init_vec_parent_group(void)
 	acpi_table_parse(ACPI_SIG_MCFG, early_pci_mcfg_parse);
 }
 
+#ifdef CONFIG_SMP
 static int __init get_ipi_irq(void)
 {
 	struct irq_domain *d = irq_find_matching_fwnode(cpuintc_handle, DOMAIN_BUS_ANY);
@@ -96,6 +97,7 @@ static int __init get_ipi_irq(void)
 
 	return -EINVAL;
 }
+#endif
 
 void __init init_IRQ(void)
 {

arch/loongarch/kernel/machine_kexec.c

@@ -225,6 +225,7 @@ void crash_smp_send_stop(void)
 
 void machine_shutdown(void)
 {
+#ifdef CONFIG_SMP
 	int cpu;
 
 	/* All CPUs go to reboot_code_buffer */
@@ -232,7 +233,6 @@ void machine_shutdown(void)
 		if (!cpu_online(cpu))
 			cpu_device_up(get_cpu_device(cpu));
 
-#ifdef CONFIG_SMP
 	smp_call_function(kexec_shutdown_secondary, NULL, 0);
 #endif
 }

arch/loongarch/mm/tlbex.S

@@ -125,6 +125,8 @@ vmalloc_load:
 tlb_huge_update_load:
 #ifdef CONFIG_SMP
 	ll.d		ra, t1, 0
+#else
+	rotri.d		ra, ra, 64 - (_PAGE_HUGE_SHIFT + 1)
 #endif
 	andi		t0, ra, _PAGE_PRESENT
 	beqz		t0, nopage_tlb_load
@@ -135,7 +137,6 @@ tlb_huge_update_load:
 	beqz		t0, tlb_huge_update_load
 	ori		t0, ra, _PAGE_VALID
 #else
-	rotri.d		ra, ra, 64 - (_PAGE_HUGE_SHIFT + 1)
 	ori		t0, ra, _PAGE_VALID
 	st.d		t0, t1, 0
 #endif
@@ -281,6 +282,8 @@ vmalloc_store:
 tlb_huge_update_store:
 #ifdef CONFIG_SMP
 	ll.d		ra, t1, 0
+#else
+	rotri.d		ra, ra, 64 - (_PAGE_HUGE_SHIFT + 1)
 #endif
 	andi		t0, ra, _PAGE_PRESENT | _PAGE_WRITE
 	xori		t0, t0, _PAGE_PRESENT | _PAGE_WRITE
@@ -292,7 +295,6 @@ tlb_huge_update_store:
 	beqz		t0, tlb_huge_update_store
 	ori		t0, ra, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
 #else
-	rotri.d		ra, ra, 64 - (_PAGE_HUGE_SHIFT + 1)
 	ori		t0, ra, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
 	st.d		t0, t1, 0
 #endif
@@ -438,6 +440,8 @@ vmalloc_modify:
 tlb_huge_update_modify:
 #ifdef CONFIG_SMP
 	ll.d		ra, t1, 0
+#else
+	rotri.d		ra, ra, 64 - (_PAGE_HUGE_SHIFT + 1)
 #endif
 	andi		t0, ra, _PAGE_WRITE
 	beqz		t0, nopage_tlb_modify
@@ -448,7 +452,6 @@ tlb_huge_update_modify:
 	beqz		t0, tlb_huge_update_modify
 	ori		t0, ra, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
 #else
-	rotri.d		ra, ra, 64 - (_PAGE_HUGE_SHIFT + 1)
 	ori		t0, ra, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
 	st.d		t0, t1, 0
 #endif

arch/loongarch/power/suspend.c

@@ -24,6 +24,7 @@ struct saved_registers {
 	u64 kpgd;
 	u32 pwctl0;
 	u32 pwctl1;
+	u64 pcpu_base;
 };
 static struct saved_registers saved_regs;
 
@@ -36,6 +37,7 @@ void loongarch_common_suspend(void)
 	saved_regs.pwctl1 = csr_read32(LOONGARCH_CSR_PWCTL1);
 	saved_regs.ecfg = csr_read32(LOONGARCH_CSR_ECFG);
 	saved_regs.euen = csr_read32(LOONGARCH_CSR_EUEN);
+	saved_regs.pcpu_base = csr_read64(PERCPU_BASE_KS);
 
 	loongarch_suspend_addr = loongson_sysconf.suspend_addr;
 }
@@ -44,7 +46,6 @@ void loongarch_common_resume(void)
 {
 	sync_counter();
 	local_flush_tlb_all();
-	csr_write64(per_cpu_offset(0), PERCPU_BASE_KS);
 	csr_write64(eentry, LOONGARCH_CSR_EENTRY);
 	csr_write64(eentry, LOONGARCH_CSR_MERRENTRY);
 	csr_write64(tlbrentry, LOONGARCH_CSR_TLBRENTRY);
@@ -55,6 +56,7 @@ void loongarch_common_resume(void)
 	csr_write32(saved_regs.pwctl1, LOONGARCH_CSR_PWCTL1);
 	csr_write32(saved_regs.ecfg, LOONGARCH_CSR_ECFG);
 	csr_write32(saved_regs.euen, LOONGARCH_CSR_EUEN);
+	csr_write64(saved_regs.pcpu_base, PERCPU_BASE_KS);
 }
 
 int loongarch_acpi_suspend(void)