14 files changed, 204 insertions, 84 deletions

diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index 3a7620b66b..c9bfeda89e 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -51,6 +51,7 @@ obj-$(CONFIG_MODULES)		+= module.o module-sections.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 
 obj-$(CONFIG_PROC_FS)		+= proc.o
+obj-$(CONFIG_PARAVIRT)		+= paravirt.o
 
 obj-$(CONFIG_SMP)		+= smp.o
 
diff --git a/arch/loongarch/kernel/dma.c b/arch/loongarch/kernel/dma.c
index 7a9c6a9dd2..429555fb4e 100644
--- a/arch/loongarch/kernel/dma.c
+++ b/arch/loongarch/kernel/dma.c
@@ -8,17 +8,12 @@
 void acpi_arch_dma_setup(struct device *dev)
 {
 	int ret;
-	u64 mask, end = 0;
+	u64 mask, end;
 	const struct bus_dma_region *map = NULL;
 
 	ret = acpi_dma_get_range(dev, &map);
 	if (!ret && map) {
-		const struct bus_dma_region *r = map;
-
-		for (end = 0; r->size; r++) {
-			if (r->dma_start + r->size - 1 > end)
-				end = r->dma_start + r->size - 1;
-		}
+		end = dma_range_map_max(map);
 
 		mask = DMA_BIT_MASK(ilog2(end) + 1);
 		dev->bus_dma_limit = end;
diff --git a/arch/loongarch/kernel/efi.c b/arch/loongarch/kernel/efi.c
index 000825406c..2bf86aeda8 100644
--- a/arch/loongarch/kernel/efi.c
+++ b/arch/loongarch/kernel/efi.c
@@ -66,6 +66,12 @@ void __init efi_runtime_init(void)
 	set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 }
 
+bool efi_poweroff_required(void)
+{
+	return efi_enabled(EFI_RUNTIME_SERVICES) &&
+		(acpi_gbl_reduced_hardware || acpi_no_s5);
+}
+
 unsigned long __initdata screen_info_table = EFI_INVALID_TABLE_ADDR;
 
 #if defined(CONFIG_SYSFB) || defined(CONFIG_EFI_EARLYCON)
diff --git a/arch/loongarch/kernel/hw_breakpoint.c b/arch/loongarch/kernel/hw_breakpoint.c
index 621ad7634d..a6e4b605bf 100644
--- a/arch/loongarch/kernel/hw_breakpoint.c
+++ b/arch/loongarch/kernel/hw_breakpoint.c
@@ -221,7 +221,7 @@ static int hw_breakpoint_control(struct perf_event *bp,
 		}
 		enable = csr_read64(LOONGARCH_CSR_CRMD);
 		csr_write64(CSR_CRMD_WE | enable, LOONGARCH_CSR_CRMD);
-		if (bp->hw.target)
+		if (bp->hw.target && test_tsk_thread_flag(bp->hw.target, TIF_LOAD_WATCH))
 			regs->csr_prmd |= CSR_PRMD_PWE;
 		break;
 	case HW_BREAKPOINT_UNINSTALL:
diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c
index 883e5066ae..f4991c0351 100644
--- a/arch/loongarch/kernel/irq.c
+++ b/arch/loongarch/kernel/irq.c
@@ -87,23 +87,9 @@ static void __init init_vec_parent_group(void)
 	acpi_table_parse(ACPI_SIG_MCFG, early_pci_mcfg_parse);
 }
 
-static int __init get_ipi_irq(void)
-{
-	struct irq_domain *d = irq_find_matching_fwnode(cpuintc_handle, DOMAIN_BUS_ANY);
-
-	if (d)
-		return irq_create_mapping(d, INT_IPI);
-
-	return -EINVAL;
-}
-
 void __init init_IRQ(void)
 {
 	int i;
-#ifdef CONFIG_SMP
-	int r, ipi_irq;
-	static int ipi_dummy_dev;
-#endif
 	unsigned int order = get_order(IRQ_STACK_SIZE);
 	struct page *page;
 
@@ -113,13 +99,7 @@ void __init init_IRQ(void)
 	init_vec_parent_group();
 	irqchip_init();
 #ifdef CONFIG_SMP
-	ipi_irq = get_ipi_irq();
-	if (ipi_irq < 0)
-		panic("IPI IRQ mapping failed\n");
-	irq_set_percpu_devid(ipi_irq);
-	r = request_percpu_irq(ipi_irq, loongson_ipi_interrupt, "IPI", &ipi_dummy_dev);
-	if (r < 0)
-		panic("IPI IRQ request failed\n");
+	mp_ops.init_ipi();
 #endif
 
 	for (i = 0; i < NR_IRQS; i++)
@@ -133,5 +113,5 @@ void __init init_IRQ(void)
 			per_cpu(irq_stack, i), per_cpu(irq_stack, i) + IRQ_STACK_SIZE);
 	}
 
-	set_csr_ecfg(ECFGF_IP0 | ECFGF_IP1 | ECFGF_IP2 | ECFGF_IPI | ECFGF_PMC);
+	set_csr_ecfg(ECFGF_SIP0 | ECFGF_IP0 | ECFGF_IP1 | ECFGF_IP2 | ECFGF_IPI | ECFGF_PMC);
 }
diff --git a/arch/loongarch/kernel/machine_kexec.c b/arch/loongarch/kernel/machine_kexec.c
index 2dcb9e0036..8ae641dc53 100644
--- a/arch/loongarch/kernel/machine_kexec.c
+++ b/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
 }
diff --git a/arch/loongarch/kernel/module.c b/arch/loongarch/kernel/module.c
index c7d0338d12..36d6d9eeb7 100644
--- a/arch/loongarch/kernel/module.c
+++ b/arch/loongarch/kernel/module.c
@@ -490,12 +490,6 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 	return 0;
 }
 
-void *module_alloc(unsigned long size)
-{
-	return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
-			GFP_KERNEL, PAGE_KERNEL, 0, NUMA_NO_NODE, __builtin_return_address(0));
-}
-
 static void module_init_ftrace_plt(const Elf_Ehdr *hdr,
 				   const Elf_Shdr *sechdrs, struct module *mod)
 {
diff --git a/arch/loongarch/kernel/paravirt.c b/arch/loongarch/kernel/paravirt.c
new file mode 100644
index 0000000000..1633ed4f69
--- /dev/null
+++ b/arch/loongarch/kernel/paravirt.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/jump_label.h>
+#include <linux/kvm_para.h>
+#include <linux/static_call.h>
+#include <asm/paravirt.h>
+
+struct static_key paravirt_steal_enabled;
+struct static_key paravirt_steal_rq_enabled;
+
+static u64 native_steal_clock(int cpu)
+{
+	return 0;
+}
+
+DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
+
+#ifdef CONFIG_SMP
+static void pv_send_ipi_single(int cpu, unsigned int action)
+{
+	int min, old;
+	irq_cpustat_t *info = &per_cpu(irq_stat, cpu);
+
+	old = atomic_fetch_or(BIT(action), &info->message);
+	if (old)
+		return;
+
+	min = cpu_logical_map(cpu);
+	kvm_hypercall3(KVM_HCALL_FUNC_IPI, 1, 0, min);
+}
+
+#define KVM_IPI_CLUSTER_SIZE	(2 * BITS_PER_LONG)
+
+static void pv_send_ipi_mask(const struct cpumask *mask, unsigned int action)
+{
+	int i, cpu, min = 0, max = 0, old;
+	__uint128_t bitmap = 0;
+	irq_cpustat_t *info;
+
+	if (cpumask_empty(mask))
+		return;
+
+	action = BIT(action);
+	for_each_cpu(i, mask) {
+		info = &per_cpu(irq_stat, i);
+		old = atomic_fetch_or(action, &info->message);
+		if (old)
+			continue;
+
+		cpu = cpu_logical_map(i);
+		if (!bitmap) {
+			min = max = cpu;
+		} else if (cpu < min && cpu > (max - KVM_IPI_CLUSTER_SIZE)) {
+			/* cpu < min, and bitmap still enough */
+			bitmap <<= min - cpu;
+			min = cpu;
+		} else if (cpu > min && cpu < (min + KVM_IPI_CLUSTER_SIZE)) {
+			/* cpu > min, and bitmap still enough */
+			max = cpu > max ? cpu : max;
+		} else {
+			/*
+			 * With cpu, bitmap will exceed KVM_IPI_CLUSTER_SIZE,
+			 * send IPI here directly and skip the remaining CPUs.
+			 */
+			kvm_hypercall3(KVM_HCALL_FUNC_IPI, (unsigned long)bitmap,
+				      (unsigned long)(bitmap >> BITS_PER_LONG), min);
+			min = max = cpu;
+			bitmap = 0;
+		}
+		__set_bit(cpu - min, (unsigned long *)&bitmap);
+	}
+
+	if (bitmap)
+		kvm_hypercall3(KVM_HCALL_FUNC_IPI, (unsigned long)bitmap,
+			      (unsigned long)(bitmap >> BITS_PER_LONG), min);
+}
+
+static irqreturn_t pv_ipi_interrupt(int irq, void *dev)
+{
+	u32 action;
+	irq_cpustat_t *info;
+
+	/* Clear SWI interrupt */
+	clear_csr_estat(1 << INT_SWI0);
+	info = this_cpu_ptr(&irq_stat);
+	action = atomic_xchg(&info->message, 0);
+
+	if (action & SMP_RESCHEDULE) {
+		scheduler_ipi();
+		info->ipi_irqs[IPI_RESCHEDULE]++;
+	}
+
+	if (action & SMP_CALL_FUNCTION) {
+		generic_smp_call_function_interrupt();
+		info->ipi_irqs[IPI_CALL_FUNCTION]++;
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void pv_init_ipi(void)
+{
+	int r, swi;
+
+	swi = get_percpu_irq(INT_SWI0);
+	if (swi < 0)
+		panic("SWI0 IRQ mapping failed\n");
+	irq_set_percpu_devid(swi);
+	r = request_percpu_irq(swi, pv_ipi_interrupt, "SWI0-IPI", &irq_stat);
+	if (r < 0)
+		panic("SWI0 IRQ request failed\n");
+}
+#endif
+
+static bool kvm_para_available(void)
+{
+	int config;
+	static int hypervisor_type;
+
+	if (!hypervisor_type) {
+		config = read_cpucfg(CPUCFG_KVM_SIG);
+		if (!memcmp(&config, KVM_SIGNATURE, 4))
+			hypervisor_type = HYPERVISOR_KVM;
+	}
+
+	return hypervisor_type == HYPERVISOR_KVM;
+}
+
+int __init pv_ipi_init(void)
+{
+	int feature;
+
+	if (!cpu_has_hypervisor)
+		return 0;
+	if (!kvm_para_available())
+		return 0;
+
+	feature = read_cpucfg(CPUCFG_KVM_FEATURE);
+	if (!(feature & KVM_FEATURE_IPI))
+		return 0;
+
+#ifdef CONFIG_SMP
+	mp_ops.init_ipi		= pv_init_ipi;
+	mp_ops.send_ipi_single	= pv_send_ipi_single;
+	mp_ops.send_ipi_mask	= pv_send_ipi_mask;
+#endif
+
+	return 0;
+}
diff --git a/arch/loongarch/kernel/perf_event.c b/arch/loongarch/kernel/perf_event.c
index cac7cba81b..f86a4b838d 100644
--- a/arch/loongarch/kernel/perf_event.c
+++ b/arch/loongarch/kernel/perf_event.c
@@ -456,16 +456,6 @@ static void loongarch_pmu_disable(struct pmu *pmu)
 static DEFINE_MUTEX(pmu_reserve_mutex);
 static atomic_t active_events = ATOMIC_INIT(0);
 
-static int get_pmc_irq(void)
-{
-	struct irq_domain *d = irq_find_matching_fwnode(cpuintc_handle, DOMAIN_BUS_ANY);
-
-	if (d)
-		return irq_create_mapping(d, INT_PCOV);
-
-	return -EINVAL;
-}
-
 static void reset_counters(void *arg);
 static int __hw_perf_event_init(struct perf_event *event);
 
@@ -473,7 +463,7 @@ static void hw_perf_event_destroy(struct perf_event *event)
 {
 	if (atomic_dec_and_mutex_lock(&active_events, &pmu_reserve_mutex)) {
 		on_each_cpu(reset_counters, NULL, 1);
-		free_irq(get_pmc_irq(), &loongarch_pmu);
+		free_irq(get_percpu_irq(INT_PCOV), &loongarch_pmu);
 		mutex_unlock(&pmu_reserve_mutex);
 	}
 }
@@ -562,7 +552,7 @@ static int loongarch_pmu_event_init(struct perf_event *event)
 	if (event->cpu >= 0 && !cpu_online(event->cpu))
 		return -ENODEV;
 
-	irq = get_pmc_irq();
+	irq = get_percpu_irq(INT_PCOV);
 	flags = IRQF_PERCPU | IRQF_NOBALANCING | IRQF_NO_THREAD | IRQF_NO_SUSPEND | IRQF_SHARED;
 	if (!atomic_inc_not_zero(&active_events)) {
 		mutex_lock(&pmu_reserve_mutex);
diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c
index 200109de19..19dc6eff45 100644
--- a/arch/loongarch/kernel/ptrace.c
+++ b/arch/loongarch/kernel/ptrace.c
@@ -589,6 +589,7 @@ static int ptrace_hbp_set_ctrl(unsigned int note_type,
 	struct perf_event *bp;
 	struct perf_event_attr attr;
 	struct arch_hw_breakpoint_ctrl ctrl;
+	struct thread_info *ti = task_thread_info(tsk);
 
 	bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx);
 	if (IS_ERR(bp))
@@ -613,8 +614,10 @@ static int ptrace_hbp_set_ctrl(unsigned int note_type,
 		if (err)
 			return err;
 		attr.disabled = 0;
+		set_ti_thread_flag(ti, TIF_LOAD_WATCH);
 	} else {
 		attr.disabled = 1;
+		clear_ti_thread_flag(ti, TIF_LOAD_WATCH);
 	}
 
 	return modify_user_hw_breakpoint(bp, &attr);
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index e8f7a54ff6..3d048f1be1 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -351,10 +351,8 @@ void __init platform_init(void)
 	arch_reserve_vmcore();
 	arch_reserve_crashkernel();
 
-#ifdef CONFIG_ACPI_TABLE_UPGRADE
-	acpi_table_upgrade();
-#endif
 #ifdef CONFIG_ACPI
+	acpi_table_upgrade();
 	acpi_gbl_use_default_register_widths = false;
 	acpi_boot_table_init();
 #endif
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index fd22a32755..1436d24659 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -29,6 +29,7 @@
 #include <asm/loongson.h>
 #include <asm/mmu_context.h>
 #include <asm/numa.h>
+#include <asm/paravirt.h>
 #include <asm/processor.h>
 #include <asm/setup.h>
 #include <asm/time.h>
@@ -66,11 +67,6 @@ static cpumask_t cpu_core_setup_map;
 struct secondary_data cpuboot_data;
 static DEFINE_PER_CPU(int, cpu_state);
 
-enum ipi_msg_type {
-	IPI_RESCHEDULE,
-	IPI_CALL_FUNCTION,
-};
-
 static const char *ipi_types[NR_IPI] __tracepoint_string = {
 	[IPI_RESCHEDULE] = "Rescheduling interrupts",
 	[IPI_CALL_FUNCTION] = "Function call interrupts",
@@ -190,24 +186,19 @@ static u32 ipi_read_clear(int cpu)
 
 static void ipi_write_action(int cpu, u32 action)
 {
-	unsigned int irq = 0;
-
-	while ((irq = ffs(action))) {
-		uint32_t val = IOCSR_IPI_SEND_BLOCKING;
+	uint32_t val;
 
-		val |= (irq - 1);
-		val |= (cpu << IOCSR_IPI_SEND_CPU_SHIFT);
-		iocsr_write32(val, LOONGARCH_IOCSR_IPI_SEND);
-		action &= ~BIT(irq - 1);
-	}
+	val = IOCSR_IPI_SEND_BLOCKING | action;
+	val |= (cpu << IOCSR_IPI_SEND_CPU_SHIFT);
+	iocsr_write32(val, LOONGARCH_IOCSR_IPI_SEND);
 }
 
-void loongson_send_ipi_single(int cpu, unsigned int action)
+static void loongson_send_ipi_single(int cpu, unsigned int action)
 {
 	ipi_write_action(cpu_logical_map(cpu), (u32)action);
 }
 
-void loongson_send_ipi_mask(const struct cpumask *mask, unsigned int action)
+static void loongson_send_ipi_mask(const struct cpumask *mask, unsigned int action)
 {
 	unsigned int i;
 
@@ -222,11 +213,11 @@ void loongson_send_ipi_mask(const struct cpumask *mask, unsigned int action)
  */
 void arch_smp_send_reschedule(int cpu)
 {
-	loongson_send_ipi_single(cpu, SMP_RESCHEDULE);
+	mp_ops.send_ipi_single(cpu, ACTION_RESCHEDULE);
 }
 EXPORT_SYMBOL_GPL(arch_smp_send_reschedule);
 
-irqreturn_t loongson_ipi_interrupt(int irq, void *dev)
+static irqreturn_t loongson_ipi_interrupt(int irq, void *dev)
 {
 	unsigned int action;
 	unsigned int cpu = smp_processor_id();
@@ -246,6 +237,26 @@ irqreturn_t loongson_ipi_interrupt(int irq, void *dev)
 	return IRQ_HANDLED;
 }
 
+static void loongson_init_ipi(void)
+{
+	int r, ipi_irq;
+
+	ipi_irq = get_percpu_irq(INT_IPI);
+	if (ipi_irq < 0)
+		panic("IPI IRQ mapping failed\n");
+
+	irq_set_percpu_devid(ipi_irq);
+	r = request_percpu_irq(ipi_irq, loongson_ipi_interrupt, "IPI", &irq_stat);
+	if (r < 0)
+		panic("IPI IRQ request failed\n");
+}
+
+struct smp_ops mp_ops = {
+	.init_ipi		= loongson_init_ipi,
+	.send_ipi_single	= loongson_send_ipi_single,
+	.send_ipi_mask		= loongson_send_ipi_mask,
+};
+
 static void __init fdt_smp_setup(void)
 {
 #ifdef CONFIG_OF
@@ -291,6 +302,7 @@ void __init loongson_smp_setup(void)
 	cpu_data[0].core = cpu_logical_map(0) % loongson_sysconf.cores_per_package;
 	cpu_data[0].package = cpu_logical_map(0) / loongson_sysconf.cores_per_package;
 
+	pv_ipi_init();
 	iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_EN);
 	pr_info("Detected %i available CPU(s)\n", loongson_sysconf.nr_cpus);
 }
@@ -325,7 +337,7 @@ void loongson_boot_secondary(int cpu, struct task_struct *idle)
 
 	csr_mail_send(entry, cpu_logical_map(cpu), 0);
 
-	loongson_send_ipi_single(cpu, SMP_BOOT_CPU);
+	loongson_send_ipi_single(cpu, ACTION_BOOT_CPU);
 }
 
 /*
@@ -335,7 +347,7 @@ void loongson_init_secondary(void)
 {
 	unsigned int cpu = smp_processor_id();
 	unsigned int imask = ECFGF_IP0 | ECFGF_IP1 | ECFGF_IP2 |
-			     ECFGF_IPI | ECFGF_PMC | ECFGF_TIMER;
+			     ECFGF_IPI | ECFGF_PMC | ECFGF_TIMER | ECFGF_SIP0;
 
 	change_csr_ecfg(ECFG0_IM, imask);
 
diff --git a/arch/loongarch/kernel/syscall.c b/arch/loongarch/kernel/syscall.c
index b4c5acd7aa..8801611143 100644
--- a/arch/loongarch/kernel/syscall.c
+++ b/arch/loongarch/kernel/syscall.c
@@ -22,7 +22,7 @@
 #define __SYSCALL(nr, call)	[nr] = (call),
 
 SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, unsigned long,
-		prot, unsigned long, flags, unsigned long, fd, off_t, offset)
+		prot, unsigned long, flags, unsigned long, fd, unsigned long, offset)
 {
 	if (offset & ~PAGE_MASK)
 		return -EINVAL;
diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c
index e7015f7b70..fd5354f9be 100644
--- a/arch/loongarch/kernel/time.c
+++ b/arch/loongarch/kernel/time.c
@@ -123,16 +123,6 @@ void sync_counter(void)
 	csr_write64(init_offset, LOONGARCH_CSR_CNTC);
 }
 
-static int get_timer_irq(void)
-{
-	struct irq_domain *d = irq_find_matching_fwnode(cpuintc_handle, DOMAIN_BUS_ANY);
-
-	if (d)
-		return irq_create_mapping(d, INT_TI);
-
-	return -EINVAL;
-}
-
 int constant_clockevent_init(void)
 {
 	unsigned int cpu = smp_processor_id();
@@ -142,7 +132,7 @@ int constant_clockevent_init(void)
 	static int irq = 0, timer_irq_installed = 0;
 
 	if (!timer_irq_installed) {
-		irq = get_timer_irq();
+		irq = get_percpu_irq(INT_TI);
 		if (irq < 0)
 			pr_err("Failed to map irq %d (timer)\n", irq);
 	}