Merge tag 'loongarch-fixes-7.1-1' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson

Pull LoongArch fixes from Huacai Chen:
 "Fix some build and runtime issues after 32BIT Kconfig option enabled,
  improve the platform-specific PCI controller compatibility, drop
  custom __arch_vdso_hres_capable(), and fix a lot of KVM bugs"

* tag 'loongarch-fixes-7.1-1' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson:
  LoongArch: KVM: Move unconditional delay into timer clear scenery
  LoongArch: KVM: Fix HW timer interrupt lost when inject interrupt by software
  LoongArch: KVM: Move AVEC interrupt injection into switch loop
  LoongArch: KVM: Use kvm_set_pte() in kvm_flush_pte()
  LoongArch: KVM: Fix missing EMULATE_FAIL in kvm_emu_mmio_read()
  LoongArch: KVM: Cap KVM_CAP_NR_VCPUS by KVM_CAP_MAX_VCPUS
  LoongArch: KVM: Fix "unreliable stack" for kvm_exc_entry
  LoongArch: KVM: Compile switch.S directly into the kernel
  LoongArch: vDSO: Drop custom __arch_vdso_hres_capable()
  LoongArch: Fix potential ADE in loongson_gpu_fixup_dma_hang()
  LoongArch: Use per-root-bridge PCIH flag to skip mem resource fixup
  LoongArch: Fix SYM_SIGFUNC_START definition for 32BIT
  LoongArch: Specify -m32/-m64 explicitly for 32BIT/64BIT
  LoongArch: Make CONFIG_64BIT as the default option

18 files changed, 90 insertions, 65 deletions

diff --git a/arch/loongarch/Kbuild b/arch/loongarch/Kbuild
index beb8499dd8ed..1c7a0dbe5e72 100644
--- a/arch/loongarch/Kbuild
+++ b/arch/loongarch/Kbuild
@@ -3,7 +3,7 @@ obj-y += mm/
 obj-y += net/
 obj-y += vdso/
 
-obj-$(CONFIG_KVM) += kvm/
+obj-$(subst m,y,$(CONFIG_KVM)) += kvm/
 
 # for cleaning
 subdir- += boot
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 3b042dbb2c41..606597da46b8 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -220,6 +220,7 @@ menu "Kernel type and options"
 
 choice
 	prompt "Kernel type"
+	default 64BIT # Keep existing behavior
 
 config 32BIT
 	bool "32-bit kernel"
diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile
index 47516aeea9d2..54fcfa1eac1f 100644
--- a/arch/loongarch/Makefile
+++ b/arch/loongarch/Makefile
@@ -55,9 +55,11 @@ endif
 ifdef CONFIG_32BIT
 tool-archpref		= $(32bit-tool-archpref)
 UTS_MACHINE		:= loongarch32
+cflags-y		+= $(call cc-option,-m32)
 else
 tool-archpref		= $(64bit-tool-archpref)
 UTS_MACHINE		:= loongarch64
+cflags-y		+= $(call cc-option,-m64)
 endif
 
 ifneq ($(SUBARCH),$(ARCH))
diff --git a/arch/loongarch/include/asm/asm-prototypes.h b/arch/loongarch/include/asm/asm-prototypes.h
index 704066b4f736..de0c17f3f49c 100644
--- a/arch/loongarch/include/asm/asm-prototypes.h
+++ b/arch/loongarch/include/asm/asm-prototypes.h
@@ -20,3 +20,23 @@ asmlinkage void noinstr __no_stack_protector ret_from_kernel_thread(struct task_
 								    struct pt_regs *regs,
 								    int (*fn)(void *),
 								    void *fn_arg);
+
+struct kvm_run;
+struct kvm_vcpu;
+struct loongarch_fpu;
+
+void kvm_exc_entry(void);
+int  kvm_enter_guest(struct kvm_run *run, struct kvm_vcpu *vcpu);
+
+void kvm_save_fpu(struct loongarch_fpu *fpu);
+void kvm_restore_fpu(struct loongarch_fpu *fpu);
+
+#ifdef CONFIG_CPU_HAS_LSX
+void kvm_save_lsx(struct loongarch_fpu *fpu);
+void kvm_restore_lsx(struct loongarch_fpu *fpu);
+#endif
+
+#ifdef CONFIG_CPU_HAS_LASX
+void kvm_save_lasx(struct loongarch_fpu *fpu);
+void kvm_restore_lasx(struct loongarch_fpu *fpu);
+#endif
diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h
index 130cedbb6b39..776bc487a705 100644
--- a/arch/loongarch/include/asm/kvm_host.h
+++ b/arch/loongarch/include/asm/kvm_host.h
@@ -87,7 +87,6 @@ struct kvm_context {
 struct kvm_world_switch {
 	int (*exc_entry)(void);
 	int (*enter_guest)(struct kvm_run *run, struct kvm_vcpu *vcpu);
-	unsigned long page_order;
 };
 
 #define MAX_PGTABLE_LEVELS	4
@@ -359,8 +358,6 @@ void kvm_exc_entry(void);
 int  kvm_enter_guest(struct kvm_run *run, struct kvm_vcpu *vcpu);
 
 extern unsigned long vpid_mask;
-extern const unsigned long kvm_exception_size;
-extern const unsigned long kvm_enter_guest_size;
 extern struct kvm_world_switch *kvm_loongarch_ops;
 
 #define SW_GCSR		(1 << 0)
diff --git a/arch/loongarch/include/asm/linkage.h b/arch/loongarch/include/asm/linkage.h
index a1bd6a3ee03a..ae937d1708b2 100644
--- a/arch/loongarch/include/asm/linkage.h
+++ b/arch/loongarch/include/asm/linkage.h
@@ -69,7 +69,7 @@
 		  9,  10, 11, 12, 13, 14, 15, 16,	\
 		  17, 18, 19, 20, 21, 22, 23, 24,	\
 		  25, 26, 27, 28, 29, 30, 31;		\
-	.cfi_offset \num, SC_REGS + \num * SZREG;	\
+	.cfi_offset \num, SC_REGS + \num * 8;		\
 	.endr;						\
 							\
 	nop;						\
diff --git a/arch/loongarch/include/asm/vdso/gettimeofday.h b/arch/loongarch/include/asm/vdso/gettimeofday.h
index bae76767c693..18ba403e1ed9 100644
--- a/arch/loongarch/include/asm/vdso/gettimeofday.h
+++ b/arch/loongarch/include/asm/vdso/gettimeofday.h
@@ -85,12 +85,6 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
 	return count;
 }
 
-static inline bool loongarch_vdso_hres_capable(void)
-{
-	return true;
-}
-#define __arch_vdso_hres_capable loongarch_vdso_hres_capable
-
 #endif /* CONFIG_GENERIC_GETTIMEOFDAY */
 
 #endif /* !__ASSEMBLER__ */
diff --git a/arch/loongarch/kvm/Makefile b/arch/loongarch/kvm/Makefile
index ae469edec99c..a4d044da3aa7 100644
--- a/arch/loongarch/kvm/Makefile
+++ b/arch/loongarch/kvm/Makefile
@@ -7,11 +7,12 @@ include $(srctree)/virt/kvm/Makefile.kvm
 
 obj-$(CONFIG_KVM) += kvm.o
 
+obj-y += switch.o
+
 kvm-y += exit.o
 kvm-y += interrupt.o
 kvm-y += main.o
 kvm-y += mmu.o
-kvm-y += switch.o
 kvm-y += timer.o
 kvm-y += tlb.o
 kvm-y += vcpu.o
diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c
index da0ad89f2eb7..3b95cd0f989b 100644
--- a/arch/loongarch/kvm/exit.c
+++ b/arch/loongarch/kvm/exit.c
@@ -390,6 +390,7 @@ int kvm_emu_mmio_read(struct kvm_vcpu *vcpu, larch_inst inst)
 			run->mmio.len = 8;
 			break;
 		default:
+			ret = EMULATE_FAIL;
 			break;
 		}
 		break;
diff --git a/arch/loongarch/kvm/interrupt.c b/arch/loongarch/kvm/interrupt.c
index 32930959f7c2..a18c60dffbba 100644
--- a/arch/loongarch/kvm/interrupt.c
+++ b/arch/loongarch/kvm/interrupt.c
@@ -28,23 +28,29 @@ static unsigned int priority_to_irq[EXCCODE_INT_NUM] = {
 static int kvm_irq_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
 {
 	unsigned int irq = 0;
+	unsigned long old, new;
 
 	clear_bit(priority, &vcpu->arch.irq_pending);
 	if (priority < EXCCODE_INT_NUM)
 		irq = priority_to_irq[priority];
 
-	if (kvm_guest_has_msgint(&vcpu->arch) && (priority == INT_AVEC)) {
-		dmsintc_inject_irq(vcpu);
-		set_gcsr_estat(irq);
-		return 1;
-	}
-
 	switch (priority) {
+	case INT_AVEC:
+		if (!kvm_guest_has_msgint(&vcpu->arch))
+			break;
+		dmsintc_inject_irq(vcpu);
+		fallthrough;
 	case INT_TI:
 	case INT_IPI:
 	case INT_SWI0:
 	case INT_SWI1:
+		old = kvm_read_hw_gcsr(LOONGARCH_CSR_TVAL);
 		set_gcsr_estat(irq);
+		new = kvm_read_hw_gcsr(LOONGARCH_CSR_TVAL);
+
+		/* Inject TI if TVAL inverted */
+		if (new > old)
+			set_gcsr_estat(CPU_TIMER);
 		break;
 
 	case INT_HWI0 ... INT_HWI7:
@@ -61,22 +67,28 @@ static int kvm_irq_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
 static int kvm_irq_clear(struct kvm_vcpu *vcpu, unsigned int priority)
 {
 	unsigned int irq = 0;
+	unsigned long old, new;
 
 	clear_bit(priority, &vcpu->arch.irq_clear);
 	if (priority < EXCCODE_INT_NUM)
 		irq = priority_to_irq[priority];
 
-	if (kvm_guest_has_msgint(&vcpu->arch) && (priority == INT_AVEC)) {
-		clear_gcsr_estat(irq);
-		return 1;
-	}
-
 	switch (priority) {
+	case INT_AVEC:
+		if (!kvm_guest_has_msgint(&vcpu->arch))
+			break;
+		fallthrough;
 	case INT_TI:
 	case INT_IPI:
 	case INT_SWI0:
 	case INT_SWI1:
+		old = kvm_read_hw_gcsr(LOONGARCH_CSR_TVAL);
 		clear_gcsr_estat(irq);
+		new = kvm_read_hw_gcsr(LOONGARCH_CSR_TVAL);
+
+		/* Inject TI if TVAL inverted */
+		if (new > old)
+			set_gcsr_estat(CPU_TIMER);
 		break;
 
 	case INT_HWI0 ... INT_HWI7:
diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c
index 76ebff2faedd..f105a86143f5 100644
--- a/arch/loongarch/kvm/main.c
+++ b/arch/loongarch/kvm/main.c
@@ -348,8 +348,7 @@ void kvm_arch_disable_virtualization_cpu(void)
 
 static int kvm_loongarch_env_init(void)
 {
-	int cpu, order, ret;
-	void *addr;
+	int cpu, ret;
 	struct kvm_context *context;
 
 	vmcs = alloc_percpu(struct kvm_context);
@@ -365,30 +364,8 @@ static int kvm_loongarch_env_init(void)
 		return -ENOMEM;
 	}
 
-	/*
-	 * PGD register is shared between root kernel and kvm hypervisor.
-	 * So world switch entry should be in DMW area rather than TLB area
-	 * to avoid page fault reenter.
-	 *
-	 * In future if hardware pagetable walking is supported, we won't
-	 * need to copy world switch code to DMW area.
-	 */
-	order = get_order(kvm_exception_size + kvm_enter_guest_size);
-	addr = (void *)__get_free_pages(GFP_KERNEL, order);
-	if (!addr) {
-		free_percpu(vmcs);
-		vmcs = NULL;
-		kfree(kvm_loongarch_ops);
-		kvm_loongarch_ops = NULL;
-		return -ENOMEM;
-	}
-
-	memcpy(addr, kvm_exc_entry, kvm_exception_size);
-	memcpy(addr + kvm_exception_size, kvm_enter_guest, kvm_enter_guest_size);
-	flush_icache_range((unsigned long)addr, (unsigned long)addr + kvm_exception_size + kvm_enter_guest_size);
-	kvm_loongarch_ops->exc_entry = addr;
-	kvm_loongarch_ops->enter_guest = addr + kvm_exception_size;
-	kvm_loongarch_ops->page_order = order;
+	kvm_loongarch_ops->exc_entry = (void *)kvm_exc_entry;
+	kvm_loongarch_ops->enter_guest = (void *)kvm_enter_guest;
 
 	vpid_mask = read_csr_gstat();
 	vpid_mask = (vpid_mask & CSR_GSTAT_GIDBIT) >> CSR_GSTAT_GIDBIT_SHIFT;
@@ -428,16 +405,10 @@ static int kvm_loongarch_env_init(void)
 
 static void kvm_loongarch_env_exit(void)
 {
-	unsigned long addr;
-
 	if (vmcs)
 		free_percpu(vmcs);
 
 	if (kvm_loongarch_ops) {
-		if (kvm_loongarch_ops->exc_entry) {
-			addr = (unsigned long)kvm_loongarch_ops->exc_entry;
-			free_pages(addr, kvm_loongarch_ops->page_order);
-		}
 		kfree(kvm_loongarch_ops);
 	}
 
diff --git a/arch/loongarch/kvm/mmu.c b/arch/loongarch/kvm/mmu.c
index a7fa458e3360..e104897aa532 100644
--- a/arch/loongarch/kvm/mmu.c
+++ b/arch/loongarch/kvm/mmu.c
@@ -95,7 +95,7 @@ static int kvm_flush_pte(kvm_pte_t *pte, phys_addr_t addr, kvm_ptw_ctx *ctx)
 	else
 		kvm->stat.pages--;
 
-	*pte = ctx->invalid_entry;
+	kvm_set_pte(pte, ctx->invalid_entry);
 
 	return 1;
 }
diff --git a/arch/loongarch/kvm/switch.S b/arch/loongarch/kvm/switch.S
index f1768b7a6194..936e4ae3e408 100644
--- a/arch/loongarch/kvm/switch.S
+++ b/arch/loongarch/kvm/switch.S
@@ -4,9 +4,11 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/kvm_types.h>
 #include <asm/asm.h>
 #include <asm/asmmacro.h>
 #include <asm/loongarch.h>
+#include <asm/page.h>
 #include <asm/regdef.h>
 #include <asm/unwind_hints.h>
 
@@ -100,11 +102,16 @@
 	 *  -        is still in guest mode, such as pgd table/vmid registers etc,
 	 *  -        will fix with hw page walk enabled in future
 	 * load kvm_vcpu from reserved CSR KVM_VCPU_KS, and save a2 to KVM_TEMP_KS
+	 *
+	 * PGD register is shared between root kernel and kvm hypervisor.
+	 * So world switch entry should be in DMW area rather than TLB area
+	 * to avoid page fault re-enter.
 	 */
 	.text
+	.p2align PAGE_SHIFT
 	.cfi_sections	.debug_frame
 SYM_CODE_START(kvm_exc_entry)
-	UNWIND_HINT_UNDEFINED
+	UNWIND_HINT_END_OF_STACK
 	csrwr	a2,   KVM_TEMP_KS
 	csrrd	a2,   KVM_VCPU_KS
 	addi.d	a2,   a2, KVM_VCPU_ARCH
@@ -190,8 +197,8 @@ ret_to_host:
 	kvm_restore_host_gpr    a2
 	jr      ra
 
-SYM_INNER_LABEL(kvm_exc_entry_end, SYM_L_LOCAL)
 SYM_CODE_END(kvm_exc_entry)
+EXPORT_SYMBOL_FOR_KVM(kvm_exc_entry)
 
 /*
  * int kvm_enter_guest(struct kvm_run *run, struct kvm_vcpu *vcpu)
@@ -215,8 +222,8 @@ SYM_FUNC_START(kvm_enter_guest)
 	/* Save kvm_vcpu to kscratch */
 	csrwr	a1, KVM_VCPU_KS
 	kvm_switch_to_guest
-SYM_INNER_LABEL(kvm_enter_guest_end, SYM_L_LOCAL)
 SYM_FUNC_END(kvm_enter_guest)
+EXPORT_SYMBOL_FOR_KVM(kvm_enter_guest)
 
 SYM_FUNC_START(kvm_save_fpu)
 	fpu_save_csr	a0 t1
@@ -224,6 +231,7 @@ SYM_FUNC_START(kvm_save_fpu)
 	fpu_save_cc	a0 t1 t2
 	jr              ra
 SYM_FUNC_END(kvm_save_fpu)
+EXPORT_SYMBOL_FOR_KVM(kvm_save_fpu)
 
 SYM_FUNC_START(kvm_restore_fpu)
 	fpu_restore_double a0 t1
@@ -231,6 +239,7 @@ SYM_FUNC_START(kvm_restore_fpu)
 	fpu_restore_cc	   a0 t1 t2
 	jr                 ra
 SYM_FUNC_END(kvm_restore_fpu)
+EXPORT_SYMBOL_FOR_KVM(kvm_restore_fpu)
 
 #ifdef CONFIG_CPU_HAS_LSX
 SYM_FUNC_START(kvm_save_lsx)
@@ -239,6 +248,7 @@ SYM_FUNC_START(kvm_save_lsx)
 	lsx_save_data   a0 t1
 	jr              ra
 SYM_FUNC_END(kvm_save_lsx)
+EXPORT_SYMBOL_FOR_KVM(kvm_save_lsx)
 
 SYM_FUNC_START(kvm_restore_lsx)
 	lsx_restore_data a0 t1
@@ -246,6 +256,7 @@ SYM_FUNC_START(kvm_restore_lsx)
 	fpu_restore_csr  a0 t1 t2
 	jr               ra
 SYM_FUNC_END(kvm_restore_lsx)
+EXPORT_SYMBOL_FOR_KVM(kvm_restore_lsx)
 #endif
 
 #ifdef CONFIG_CPU_HAS_LASX
@@ -255,6 +266,7 @@ SYM_FUNC_START(kvm_save_lasx)
 	lasx_save_data  a0 t1
 	jr              ra
 SYM_FUNC_END(kvm_save_lasx)
+EXPORT_SYMBOL_FOR_KVM(kvm_save_lasx)
 
 SYM_FUNC_START(kvm_restore_lasx)
 	lasx_restore_data a0 t1
@@ -262,10 +274,8 @@ SYM_FUNC_START(kvm_restore_lasx)
 	fpu_restore_csr   a0 t1 t2
 	jr                ra
 SYM_FUNC_END(kvm_restore_lasx)
+EXPORT_SYMBOL_FOR_KVM(kvm_restore_lasx)
 #endif
-	.section ".rodata"
-SYM_DATA(kvm_exception_size, .quad kvm_exc_entry_end - kvm_exc_entry)
-SYM_DATA(kvm_enter_guest_size, .quad kvm_enter_guest_end - kvm_enter_guest)
 
 #ifdef CONFIG_CPU_HAS_LBT
 STACK_FRAME_NON_STANDARD kvm_restore_fpu
diff --git a/arch/loongarch/kvm/timer.c b/arch/loongarch/kvm/timer.c
index 29c2aaba63c3..8356fce0043f 100644
--- a/arch/loongarch/kvm/timer.c
+++ b/arch/loongarch/kvm/timer.c
@@ -96,15 +96,21 @@ void kvm_restore_timer(struct kvm_vcpu *vcpu)
 		 * and set CSR TVAL with -1
 		 */
 		write_gcsr_timertick(0);
-		__delay(2); /* Wait cycles until timer interrupt injected */
 
 		/*
 		 * Writing CSR_TINTCLR_TI to LOONGARCH_CSR_TINTCLR will clear
 		 * timer interrupt, and CSR TVAL keeps unchanged with -1, it
 		 * avoids spurious timer interrupt
 		 */
-		if (!(estat & CPU_TIMER))
+		if (!(estat & CPU_TIMER)) {
+			__delay(2); /* Wait cycles until timer interrupt injected */
+
+			/* Write TVAL with max value if no TI shot */
+			estat = kvm_read_hw_gcsr(LOONGARCH_CSR_ESTAT);
+			if (!(estat & CPU_TIMER))
+				write_gcsr_timertick(CSR_TCFG_VAL);
 			gcsr_write(CSR_TINTCLR_TI, LOONGARCH_CSR_TINTCLR);
+		}
 		return;
 	}
 
diff --git a/arch/loongarch/kvm/vm.c b/arch/loongarch/kvm/vm.c
index 8cc5ee1c53ef..1317c718f896 100644
--- a/arch/loongarch/kvm/vm.c
+++ b/arch/loongarch/kvm/vm.c
@@ -125,7 +125,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
-		r = num_online_cpus();
+		r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
 		break;
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
diff --git a/arch/loongarch/pci/acpi.c b/arch/loongarch/pci/acpi.c
index 0dde3ddcd544..b02698a338ee 100644
--- a/arch/loongarch/pci/acpi.c
+++ b/arch/loongarch/pci/acpi.c
@@ -61,11 +61,16 @@ static void acpi_release_root_info(struct acpi_pci_root_info *ci)
 static int acpi_prepare_root_resources(struct acpi_pci_root_info *ci)
 {
 	int status;
+	unsigned long long pci_h = 0;
 	struct resource_entry *entry, *tmp;
 	struct acpi_device *device = ci->bridge;
 
 	status = acpi_pci_probe_root_resources(ci);
 	if (status > 0) {
+		acpi_evaluate_integer(device->handle, "PCIH", NULL, &pci_h);
+		if (pci_h)
+			return status;
+
 		resource_list_for_each_entry_safe(entry, tmp, &ci->resources) {
 			if (entry->res->flags & IORESOURCE_MEM) {
 				entry->offset = ci->root->mcfg_addr & GENMASK_ULL(63, 40);
diff --git a/arch/loongarch/pci/pci.c b/arch/loongarch/pci/pci.c
index d233ea2218fe..f33c7ea1443d 100644
--- a/arch/loongarch/pci/pci.c
+++ b/arch/loongarch/pci/pci.c
@@ -132,6 +132,9 @@ static void loongson_gpu_fixup_dma_hang(struct pci_dev *pdev, bool on)
 		crtc_reg = regbase;
 		crtc_offset = 0x400;
 		break;
+	default:
+		iounmap(regbase);
+		return;
 	}
 
 	for (i = 0; i < CRTC_NUM_MAX; i++, crtc_reg += crtc_offset) {
diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile
index 42aa96249828..9c9181bb4071 100644
--- a/arch/loongarch/vdso/Makefile
+++ b/arch/loongarch/vdso/Makefile
@@ -12,6 +12,8 @@ obj-vdso-$(CONFIG_GENERIC_GETTIMEOFDAY) += vgettimeofday.o
 ccflags-vdso := \
 	$(filter -I%,$(KBUILD_CFLAGS)) \
 	$(filter -E%,$(KBUILD_CFLAGS)) \
+	$(filter -m32,$(KBUILD_CFLAGS)) \
+	$(filter -m64,$(KBUILD_CFLAGS)) \
 	$(filter -march=%,$(KBUILD_CFLAGS)) \
 	$(filter -m%-float,$(KBUILD_CFLAGS)) \
 	$(CLANG_FLAGS) \