Merge tag 'loongarch-fixes-6.14-2' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson

Pull LoongArch fixes from Huacai Chen:
 "Fix bugs in kernel build, hibernation, memory management and KVM"

* tag 'loongarch-fixes-6.14-2' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson:
  LoongArch: KVM: Fix GPA size issue about VM
  LoongArch: KVM: Reload guest CSR registers after sleep
  LoongArch: KVM: Add interrupt checking for AVEC
  LoongArch: Set hugetlb mmap base address aligned with pmd size
  LoongArch: Set max_pfn with the PFN of the last page
  LoongArch: Use polling play_dead() when resuming from hibernation
  LoongArch: Eliminate superfluous get_numa_distances_cnt()
  LoongArch: Convert unreachable() to BUG()

Author: torvalds

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)) {

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();
 }
 
 

arch/loongarch/kernel/setup.c

@@ -387,6 +387,9 @@ 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");
 

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
 
 /*

arch/loongarch/kvm/exit.c

@@ -669,6 +669,12 @@ static int kvm_handle_rdwr_fault(struct kvm_vcpu *vcpu, bool write)
 	struct kvm_run *run = vcpu->run;
 	unsigned long badv = vcpu->arch.badv;
 
+	/* Inject ADE exception if exceed max GPA size */
+	if (unlikely(badv >= vcpu->kvm->arch.gpa_size)) {
+		kvm_queue_exception(vcpu, EXCCODE_ADE, EXSUBCODE_ADEM);
+		return RESUME_GUEST;
+	}
+
 	ret = kvm_handle_mm_fault(vcpu, badv, write);
 	if (ret) {
 		/* Treat as MMIO */

arch/loongarch/kvm/main.c

@@ -317,6 +317,13 @@ int kvm_arch_enable_virtualization_cpu(void)
 	kvm_debug("GCFG:%lx GSTAT:%lx GINTC:%lx GTLBC:%lx",
 		  read_csr_gcfg(), read_csr_gstat(), read_csr_gintc(), read_csr_gtlbc());
 
+	/*
+	 * HW Guest CSR registers are lost after CPU suspend and resume.
+	 * Clear last_vcpu so that Guest CSR registers forced to reload
+	 * from vCPU SW state.
+	 */
+	this_cpu_ptr(vmcs)->last_vcpu = NULL;
+
 	return 0;
 }
 

arch/loongarch/kvm/vcpu.c

@@ -311,7 +311,7 @@ static int kvm_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	int ret = RESUME_GUEST;
 	unsigned long estat = vcpu->arch.host_estat;
-	u32 intr = estat & 0x1fff; /* Ignore NMI */
+	u32 intr = estat & CSR_ESTAT_IS;
 	u32 ecode = (estat & CSR_ESTAT_EXC) >> CSR_ESTAT_EXC_SHIFT;
 
 	vcpu->mode = OUTSIDE_GUEST_MODE;

arch/loongarch/kvm/vm.c

@@ -48,7 +48,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (kvm_pvtime_supported())
 		kvm->arch.pv_features |= BIT(KVM_FEATURE_STEAL_TIME);
 
-	kvm->arch.gpa_size = BIT(cpu_vabits - 1);
+	/*
+	 * cpu_vabits means user address space only (a half of total).
+	 * GPA size of VM is the same with the size of user address space.
+	 */
+	kvm->arch.gpa_size = BIT(cpu_vabits);
 	kvm->arch.root_level = CONFIG_PGTABLE_LEVELS - 1;
 	kvm->arch.invalid_ptes[0] = 0;
 	kvm->arch.invalid_ptes[1] = (unsigned long)invalid_pte_table;

arch/loongarch/mm/mmap.c

@@ -3,6 +3,7 @@
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
 #include <linux/export.h>
+#include <linux/hugetlb.h>
 #include <linux/io.h>
 #include <linux/kfence.h>
 #include <linux/memblock.h>
@@ -63,8 +64,11 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp,
 	}
 
 	info.length = len;
-	info.align_mask = do_color_align ? (PAGE_MASK & SHM_ALIGN_MASK) : 0;
 	info.align_offset = pgoff << PAGE_SHIFT;
+	if (filp && is_file_hugepages(filp))
+		info.align_mask = huge_page_mask_align(filp);
+	else
+		info.align_mask = do_color_align ? (PAGE_MASK & SHM_ALIGN_MASK) : 0;
 
 	if (dir == DOWN) {
 		info.flags = VM_UNMAPPED_AREA_TOPDOWN;