15 files changed, 90 insertions, 168 deletions

diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
index 382a09a7152c..1120ac2824f6 100644
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@@ -249,18 +249,6 @@ static __init int setup_node(int pxm)
 	return acpi_map_pxm_to_node(pxm);
 }
 
-/*
- * Callback for SLIT parsing.  pxm_to_node() returns NUMA_NO_NODE for
- * I/O localities since SRAT does not list them.  I/O localities are
- * not supported at this point.
- */
-unsigned int numa_distance_cnt;
-
-static inline unsigned int get_numa_distances_cnt(struct acpi_table_slit *slit)
-{
-	return slit->locality_count;
-}
-
 void __init numa_set_distance(int from, int to, int distance)
 {
 	if ((u8)distance != distance || (from == to && distance != LOCAL_DISTANCE)) {
diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c
index 8be1c38ad8eb..db1e4bb26b6a 100644
--- a/arch/loongarch/kernel/asm-offsets.c
+++ b/arch/loongarch/kernel/asm-offsets.c
@@ -296,6 +296,7 @@ static void __used output_kvm_defines(void)
 	OFFSET(KVM_ARCH_HSP, kvm_vcpu_arch, host_sp);
 	OFFSET(KVM_ARCH_HTP, kvm_vcpu_arch, host_tp);
 	OFFSET(KVM_ARCH_HPGD, kvm_vcpu_arch, host_pgd);
+	OFFSET(KVM_ARCH_KVMPGD, kvm_vcpu_arch, kvm_pgd);
 	OFFSET(KVM_ARCH_HANDLE_EXIT, kvm_vcpu_arch, handle_exit);
 	OFFSET(KVM_ARCH_HEENTRY, kvm_vcpu_arch, host_eentry);
 	OFFSET(KVM_ARCH_GEENTRY, kvm_vcpu_arch, guest_eentry);
@@ -315,6 +316,6 @@ static void __used output_vdso_defines(void)
 {
 	COMMENT("LoongArch vDSO offsets.");
 
-	DEFINE(__VVAR_PAGES, VVAR_NR_PAGES);
+	DEFINE(__VDSO_PAGES, VDSO_NR_PAGES);
 	BLANK();
 }
diff --git a/arch/loongarch/kernel/env.c b/arch/loongarch/kernel/env.c
index 2f1f5b08638f..27144de5c5fe 100644
--- a/arch/loongarch/kernel/env.c
+++ b/arch/loongarch/kernel/env.c
@@ -68,6 +68,8 @@ static int __init fdt_cpu_clk_init(void)
 		return -ENODEV;
 
 	clk = of_clk_get(np, 0);
+	of_node_put(np);
+
 	if (IS_ERR(clk))
 		return -ENODEV;
 
diff --git a/arch/loongarch/kernel/ftrace_dyn.c b/arch/loongarch/kernel/ftrace_dyn.c
index 25c9a4cfd5fa..d5d81d74034c 100644
--- a/arch/loongarch/kernel/ftrace_dyn.c
+++ b/arch/loongarch/kernel/ftrace_dyn.c
@@ -85,14 +85,13 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec, struct module *mod
 	 * dealing with an out-of-range condition, we can assume it
 	 * is due to a module being loaded far away from the kernel.
 	 *
-	 * NOTE: __module_text_address() must be called with preemption
-	 * disabled, but we can rely on ftrace_lock to ensure that 'mod'
+	 * NOTE: __module_text_address() must be called within a RCU read
+	 * section, but we can rely on ftrace_lock to ensure that 'mod'
 	 * retains its validity throughout the remainder of this code.
 	 */
 	if (!mod) {
-		preempt_disable();
-		mod = __module_text_address(pc);
-		preempt_enable();
+		scoped_guard(rcu)
+			mod = __module_text_address(pc);
 	}
 
 	if (WARN_ON(!mod))
diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S
index 86d5d90ebefe..4f0912141781 100644
--- a/arch/loongarch/kernel/genex.S
+++ b/arch/loongarch/kernel/genex.S
@@ -18,16 +18,19 @@
 
 	.align	5
 SYM_FUNC_START(__arch_cpu_idle)
-	/* start of rollback region */
-	LONG_L	t0, tp, TI_FLAGS
-	nop
-	andi	t0, t0, _TIF_NEED_RESCHED
-	bnez	t0, 1f
-	nop
-	nop
-	nop
+	/* start of idle interrupt region */
+	ori	t0, zero, CSR_CRMD_IE
+	/* idle instruction needs irq enabled */
+	csrxchg	t0, t0, LOONGARCH_CSR_CRMD
+	/*
+	 * If an interrupt lands here; between enabling interrupts above and
+	 * going idle on the next instruction, we must *NOT* go idle since the
+	 * interrupt could have set TIF_NEED_RESCHED or caused an timer to need
+	 * reprogramming. Fall through -- see handle_vint() below -- and have
+	 * the idle loop take care of things.
+	 */
 	idle	0
-	/* end of rollback region */
+	/* end of idle interrupt region */
 1:	jr	ra
 SYM_FUNC_END(__arch_cpu_idle)
 
@@ -35,11 +38,10 @@ SYM_CODE_START(handle_vint)
 	UNWIND_HINT_UNDEFINED
 	BACKUP_T0T1
 	SAVE_ALL
-	la_abs	t1, __arch_cpu_idle
+	la_abs	t1, 1b
 	LONG_L	t0, sp, PT_ERA
-	/* 32 byte rollback region */
-	ori	t0, t0, 0x1f
-	xori	t0, t0, 0x1f
+	/* 3 instructions idle interrupt region */
+	ori	t0, t0, 0b1100
 	bne	t0, t1, 1f
 	LONG_S	t0, sp, PT_ERA
 1:	move	a0, sp
diff --git a/arch/loongarch/kernel/idle.c b/arch/loongarch/kernel/idle.c
index 0b5dd2faeb90..54b247d8cdb6 100644
--- a/arch/loongarch/kernel/idle.c
+++ b/arch/loongarch/kernel/idle.c
@@ -11,7 +11,6 @@
 
 void __cpuidle arch_cpu_idle(void)
 {
-	raw_local_irq_enable();
-	__arch_cpu_idle(); /* idle instruction needs irq enabled */
+	__arch_cpu_idle();
 	raw_local_irq_disable();
 }
diff --git a/arch/loongarch/kernel/kgdb.c b/arch/loongarch/kernel/kgdb.c
index 445c452d72a7..7be5b4c0c900 100644
--- a/arch/loongarch/kernel/kgdb.c
+++ b/arch/loongarch/kernel/kgdb.c
@@ -8,6 +8,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/kdebug.h>
 #include <linux/kgdb.h>
+#include <linux/objtool.h>
 #include <linux/processor.h>
 #include <linux/ptrace.h>
 #include <linux/sched.h>
@@ -224,13 +225,13 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
 	regs->csr_era = pc;
 }
 
-void arch_kgdb_breakpoint(void)
+noinline void arch_kgdb_breakpoint(void)
 {
 	__asm__ __volatile__ (			\
 		".globl kgdb_breakinst\n\t"	\
-		"nop\n"				\
 		"kgdb_breakinst:\tbreak 2\n\t"); /* BRK_KDB = 2 */
 }
+STACK_FRAME_NON_STANDARD(arch_kgdb_breakpoint);
 
 /*
  * Calls linux_debug_hook before the kernel dies. If KGDB is enabled,
diff --git a/arch/loongarch/kernel/machine_kexec.c b/arch/loongarch/kernel/machine_kexec.c
index 8ae641dc53bb..f9381800e291 100644
--- a/arch/loongarch/kernel/machine_kexec.c
+++ b/arch/loongarch/kernel/machine_kexec.c
@@ -126,14 +126,14 @@ void kexec_reboot(void)
 	/* All secondary cpus go to kexec_smp_wait */
 	if (smp_processor_id() > 0) {
 		relocated_kexec_smp_wait(NULL);
-		unreachable();
+		BUG();
 	}
 #endif
 
 	do_kexec = (void *)reboot_code_buffer;
 	do_kexec(efi_boot, cmdline_ptr, systable_ptr, start_addr, first_ind_entry);
 
-	unreachable();
+	BUG();
 }
 
 
diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c
index 84fe7f854820..30a72fd528c0 100644
--- a/arch/loongarch/kernel/numa.c
+++ b/arch/loongarch/kernel/numa.c
@@ -387,12 +387,6 @@ void __init paging_init(void)
 	free_area_init(zones_size);
 }
 
-void __init mem_init(void)
-{
-	high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
-	memblock_free_all();
-}
-
 int pcibus_to_node(struct pci_bus *bus)
 {
 	return dev_to_node(&bus->dev);
diff --git a/arch/loongarch/kernel/proc.c b/arch/loongarch/kernel/proc.c
index 6ce46d92f1f1..cea30768ae92 100644
--- a/arch/loongarch/kernel/proc.c
+++ b/arch/loongarch/kernel/proc.c
@@ -13,28 +13,12 @@
 #include <asm/processor.h>
 #include <asm/time.h>
 
-/*
- * No lock; only written during early bootup by CPU 0.
- */
-static RAW_NOTIFIER_HEAD(proc_cpuinfo_chain);
-
-int __ref register_proc_cpuinfo_notifier(struct notifier_block *nb)
-{
-	return raw_notifier_chain_register(&proc_cpuinfo_chain, nb);
-}
-
-int proc_cpuinfo_notifier_call_chain(unsigned long val, void *v)
-{
-	return raw_notifier_call_chain(&proc_cpuinfo_chain, val, v);
-}
-
 static int show_cpuinfo(struct seq_file *m, void *v)
 {
 	unsigned long n = (unsigned long) v - 1;
 	unsigned int isa = cpu_data[n].isa_level;
 	unsigned int version = cpu_data[n].processor_id & 0xff;
 	unsigned int fp_version = cpu_data[n].fpu_vers;
-	struct proc_cpuinfo_notifier_args proc_cpuinfo_notifier_args;
 
 #ifdef CONFIG_SMP
 	if (!cpu_online(n))
@@ -91,20 +75,13 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	if (cpu_has_lbt_mips)	seq_printf(m, " lbt_mips");
 	seq_printf(m, "\n");
 
-	seq_printf(m, "Hardware Watchpoint\t: %s",
-		      cpu_has_watch ? "yes, " : "no\n");
+	seq_printf(m, "Hardware Watchpoint\t: %s", str_yes_no(cpu_has_watch));
 	if (cpu_has_watch) {
-		seq_printf(m, "iwatch count: %d, dwatch count: %d\n",
+		seq_printf(m, ", iwatch count: %d, dwatch count: %d",
 		      cpu_data[n].watch_ireg_count, cpu_data[n].watch_dreg_count);
 	}
 
-	proc_cpuinfo_notifier_args.m = m;
-	proc_cpuinfo_notifier_args.n = n;
-
-	raw_notifier_call_chain(&proc_cpuinfo_chain, 0,
-				&proc_cpuinfo_notifier_args);
-
-	seq_printf(m, "\n");
+	seq_printf(m, "\n\n");
 
 	return 0;
 }
diff --git a/arch/loongarch/kernel/reset.c b/arch/loongarch/kernel/reset.c
index 1ef8c6383535..de8fa5a8a825 100644
--- a/arch/loongarch/kernel/reset.c
+++ b/arch/loongarch/kernel/reset.c
@@ -33,7 +33,7 @@ void machine_halt(void)
 	console_flush_on_panic(CONSOLE_FLUSH_PENDING);
 
 	while (true) {
-		__arch_cpu_idle();
+		__asm__ __volatile__("idle 0" : : : "memory");
 	}
 }
 
@@ -53,7 +53,7 @@ void machine_power_off(void)
 #endif
 
 	while (true) {
-		__arch_cpu_idle();
+		__asm__ __volatile__("idle 0" : : : "memory");
 	}
 }
 
@@ -74,6 +74,6 @@ void machine_restart(char *command)
 		acpi_reboot();
 
 	while (true) {
-		__arch_cpu_idle();
+		__asm__ __volatile__("idle 0" : : : "memory");
 	}
 }
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index edcfdfcad7d2..b99fbb388fe0 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -259,18 +259,17 @@ static void __init arch_reserve_crashkernel(void)
 	int ret;
 	unsigned long long low_size = 0;
 	unsigned long long crash_base, crash_size;
-	char *cmdline = boot_command_line;
 	bool high = false;
 
 	if (!IS_ENABLED(CONFIG_CRASH_RESERVE))
 		return;
 
-	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
+	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
 				&crash_size, &crash_base, &low_size, &high);
 	if (ret)
 		return;
 
-	reserve_crashkernel_generic(cmdline, crash_size, crash_base, low_size, high);
+	reserve_crashkernel_generic(crash_size, crash_base, low_size, high);
 }
 
 static void __init fdt_setup(void)
@@ -387,6 +386,9 @@ static void __init check_kernel_sections_mem(void)
  */
 static void __init arch_mem_init(char **cmdline_p)
 {
+	/* Recalculate max_low_pfn for "mem=xxx" */
+	max_pfn = max_low_pfn = PHYS_PFN(memblock_end_of_DRAM());
+
 	if (usermem)
 		pr_info("User-defined physical RAM map overwrite\n");
 
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index fbf747447f13..4b24589c0b56 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -19,6 +19,7 @@
 #include <linux/smp.h>
 #include <linux/threads.h>
 #include <linux/export.h>
+#include <linux/suspend.h>
 #include <linux/syscore_ops.h>
 #include <linux/time.h>
 #include <linux/tracepoint.h>
@@ -423,7 +424,7 @@ void loongson_cpu_die(unsigned int cpu)
 	mb();
 }
 
-void __noreturn arch_cpu_idle_dead(void)
+static void __noreturn idle_play_dead(void)
 {
 	register uint64_t addr;
 	register void (*init_fn)(void);
@@ -447,6 +448,50 @@ void __noreturn arch_cpu_idle_dead(void)
 	BUG();
 }
 
+#ifdef CONFIG_HIBERNATION
+static void __noreturn poll_play_dead(void)
+{
+	register uint64_t addr;
+	register void (*init_fn)(void);
+
+	idle_task_exit();
+	__this_cpu_write(cpu_state, CPU_DEAD);
+
+	__smp_mb();
+	do {
+		__asm__ __volatile__("nop\n\t");
+		addr = iocsr_read64(LOONGARCH_IOCSR_MBUF0);
+	} while (addr == 0);
+
+	init_fn = (void *)TO_CACHE(addr);
+	iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_CLEAR);
+
+	init_fn();
+	BUG();
+}
+#endif
+
+static void (*play_dead)(void) = idle_play_dead;
+
+void __noreturn arch_cpu_idle_dead(void)
+{
+	play_dead();
+	BUG(); /* play_dead() doesn't return */
+}
+
+#ifdef CONFIG_HIBERNATION
+int hibernate_resume_nonboot_cpu_disable(void)
+{
+	int ret;
+
+	play_dead = poll_play_dead;
+	ret = suspend_disable_secondary_cpus();
+	play_dead = idle_play_dead;
+
+	return ret;
+}
+#endif
+
 #endif
 
 /*
diff --git a/arch/loongarch/kernel/unwind_orc.c b/arch/loongarch/kernel/unwind_orc.c
index b25722876331..d623935a7547 100644
--- a/arch/loongarch/kernel/unwind_orc.c
+++ b/arch/loongarch/kernel/unwind_orc.c
@@ -399,7 +399,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		return false;
 
 	/* Don't let modules unload while we're reading their ORC data. */
-	preempt_disable();
+	guard(rcu)();
 
 	if (is_entry_func(state->pc))
 		goto end;
@@ -514,14 +514,12 @@ bool unwind_next_frame(struct unwind_state *state)
 	if (!__kernel_text_address(state->pc))
 		goto err;
 
-	preempt_enable();
 	return true;
 
 err:
 	state->error = true;
 
 end:
-	preempt_enable();
 	state->stack_info.type = STACK_TYPE_UNKNOWN;
 	return false;
 }
diff --git a/arch/loongarch/kernel/vdso.c b/arch/loongarch/kernel/vdso.c
index 05e5fbac102a..10cf1608c7b3 100644
--- a/arch/loongarch/kernel/vdso.c
+++ b/arch/loongarch/kernel/vdso.c
@@ -14,7 +14,7 @@
 #include <linux/random.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/time_namespace.h>
+#include <linux/vdso_datastore.h>
 
 #include <asm/page.h>
 #include <asm/vdso.h>
@@ -25,18 +25,6 @@
 
 extern char vdso_start[], vdso_end[];
 
-/* Kernel-provided data used by the VDSO. */
-static union vdso_data_store generic_vdso_data __page_aligned_data;
-
-static union {
-	u8 page[LOONGARCH_VDSO_DATA_SIZE];
-	struct loongarch_vdso_data vdata;
-} loongarch_vdso_data __page_aligned_data;
-
-struct vdso_data *vdso_data = generic_vdso_data.data;
-struct vdso_pcpu_data *vdso_pdata = loongarch_vdso_data.vdata.pdata;
-struct vdso_rng_data *vdso_rng_data = &loongarch_vdso_data.vdata.rng_data;
-
 static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma)
 {
 	current->mm->context.vdso = (void *)(new_vma->vm_start);
@@ -44,53 +32,12 @@ static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struc
 	return 0;
 }
 
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
-			     struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	unsigned long pfn;
-	struct page *timens_page = find_timens_vvar_page(vma);
-
-	switch (vmf->pgoff) {
-	case VVAR_GENERIC_PAGE_OFFSET:
-		if (!timens_page)
-			pfn = sym_to_pfn(vdso_data);
-		else
-			pfn = page_to_pfn(timens_page);
-		break;
-#ifdef CONFIG_TIME_NS
-	case VVAR_TIMENS_PAGE_OFFSET:
-		/*
-		 * If a task belongs to a time namespace then a namespace specific
-		 * VVAR is mapped with the VVAR_GENERIC_PAGE_OFFSET and the real
-		 * VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET offset.
-		 * See also the comment near timens_setup_vdso_data().
-		 */
-		if (!timens_page)
-			return VM_FAULT_SIGBUS;
-		else
-			pfn = sym_to_pfn(vdso_data);
-		break;
-#endif /* CONFIG_TIME_NS */
-	case VVAR_LOONGARCH_PAGES_START ... VVAR_LOONGARCH_PAGES_END:
-		pfn = sym_to_pfn(&loongarch_vdso_data) + vmf->pgoff - VVAR_LOONGARCH_PAGES_START;
-		break;
-	default:
-		return VM_FAULT_SIGBUS;
-	}
-
-	return vmf_insert_pfn(vma, vmf->address, pfn);
-}
-
 struct loongarch_vdso_info vdso_info = {
 	.vdso = vdso_start,
 	.code_mapping = {
 		.name = "[vdso]",
 		.mremap = vdso_mremap,
 	},
-	.data_mapping = {
-		.name = "[vvar]",
-		.fault = vvar_fault,
-	},
 	.offset_sigreturn = vdso_offset_sigreturn,
 };
 
@@ -101,7 +48,7 @@ static int __init init_vdso(void)
 	BUG_ON(!PAGE_ALIGNED(vdso_info.vdso));
 
 	for_each_possible_cpu(cpu)
-		vdso_pdata[cpu].node = cpu_to_node(cpu);
+		vdso_k_arch_data->pdata[cpu].node = cpu_to_node(cpu);
 
 	vdso_info.size = PAGE_ALIGN(vdso_end - vdso_start);
 	vdso_info.code_mapping.pages =
@@ -115,37 +62,6 @@ static int __init init_vdso(void)
 }
 subsys_initcall(init_vdso);
 
-#ifdef CONFIG_TIME_NS
-struct vdso_data *arch_get_vdso_data(void *vvar_page)
-{
-	return (struct vdso_data *)(vvar_page);
-}
-
-/*
- * The vvar mapping contains data for a specific time namespace, so when a
- * task changes namespace we must unmap its vvar data for the old namespace.
- * Subsequent faults will map in data for the new namespace.
- *
- * For more details see timens_setup_vdso_data().
- */
-int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
-{
-	struct mm_struct *mm = task->mm;
-	struct vm_area_struct *vma;
-
-	VMA_ITERATOR(vmi, mm, 0);
-
-	mmap_read_lock(mm);
-	for_each_vma(vmi, vma) {
-		if (vma_is_special_mapping(vma, &vdso_info.data_mapping))
-			zap_vma_pages(vma);
-	}
-	mmap_read_unlock(mm);
-
-	return 0;
-}
-#endif
-
 static unsigned long vdso_base(void)
 {
 	unsigned long base = STACK_TOP;
@@ -181,9 +97,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 		goto out;
 	}
 
-	vma = _install_special_mapping(mm, data_addr, VVAR_SIZE,
-				       VM_READ | VM_MAYREAD | VM_PFNMAP,
-				       &info->data_mapping);
+	vma = vdso_install_vvar_mapping(mm, data_addr);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto out;