Merge tag 'loongarch-5.20' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson

Pull LoongArch updates from Huacai Chen:

 - Optimise getcpu() with vDSO

 - PCI enablement on top of pci & irqchip changes

 - Stack unwinder and stack trace support

 - Some bug fixes and build error fixes

 - Update the default config file

* tag 'loongarch-5.20' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson:
  docs/zh_CN/LoongArch: Add I14 description
  docs/LoongArch: Add I14 description
  LoongArch: Update Loongson-3 default config file
  LoongArch: Add USER_STACKTRACE support
  LoongArch: Add STACKTRACE support
  LoongArch: Add prologue unwinder support
  LoongArch: Add guess unwinder support
  LoongArch: Add vDSO syscall __vdso_getcpu()
  LoongArch: Add PCI controller support
  LoongArch: Parse MADT to get multi-processor information
  LoongArch: Jump to the link address before enable PG
  LoongArch: Requires __force attributes for any casts
  LoongArch: Fix unsigned comparison with less than zero
  LoongArch: Adjust arch/loongarch/Kconfig
  LoongArch: cpuinfo: Fix a warning for CONFIG_CPUMASK_OFFSTACK

36 files changed, 1086 insertions, 60 deletions

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index ae15610a9427..4abc9a28aba4 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -2,7 +2,9 @@
 config LOONGARCH
 	bool
 	default y
+	select ACPI
 	select ACPI_GENERIC_GSI if ACPI
+	select ACPI_MCFG if ACPI
 	select ACPI_SYSTEM_POWER_STATES_SUPPORT	if ACPI
 	select ARCH_BINFMT_ELF_STATE
 	select ARCH_ENABLE_MEMORY_HOTPLUG
@@ -40,6 +42,7 @@ config LOONGARCH
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ARCH_SPARSEMEM_ENABLE
+	select ARCH_STACKWALK
 	select ARCH_SUPPORTS_ACPI
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_HUGETLBFS
@@ -51,6 +54,7 @@ config LOONGARCH
 	select ARCH_WANTS_NO_INSTR
 	select BUILDTIME_TABLE_SORT
 	select COMMON_CLK
+	select EFI
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_CPU_AUTOPROBE
@@ -86,6 +90,7 @@ config LOONGARCH
 	select HAVE_IRQ_TIME_ACCOUNTING
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI
+	select HAVE_PCI
 	select HAVE_PERF_EVENTS
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RSEQ
@@ -95,20 +100,27 @@ config LOONGARCH
 	select HAVE_VIRT_CPU_ACCOUNTING_GEN if !SMP
 	select IRQ_FORCED_THREADING
 	select IRQ_LOONGARCH_CPU
+	select MMU_GATHER_MERGE_VMAS if MMU
 	select MODULES_USE_ELF_RELA if MODULES
 	select NEED_PER_CPU_EMBED_FIRST_CHUNK
 	select NEED_PER_CPU_PAGE_FIRST_CHUNK
 	select OF
 	select OF_EARLY_FLATTREE
+	select PCI
+	select PCI_DOMAINS_GENERIC
+	select PCI_ECAM if ACPI
+	select PCI_LOONGSON
+	select PCI_MSI_ARCH_FALLBACKS
 	select PERF_USE_VMALLOC
 	select RTC_LIB
+	select SMP
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
 	select SWIOTLB
 	select TRACE_IRQFLAGS_SUPPORT
 	select USE_PERCPU_NUMA_NODE_ID
+	select USER_STACKTRACE_SUPPORT
 	select ZONE_DMA32
-	select MMU_GATHER_MERGE_VMAS if MMU
 
 config 32BIT
 	bool
@@ -141,6 +153,10 @@ config LOCKDEP_SUPPORT
 	bool
 	default y
 
+config STACKTRACE_SUPPORT
+	bool
+	default y
+
 # MACH_LOONGSON32 and MACH_LOONGSON64 are delibrately carried over from the
 # MIPS Loongson code, to preserve Loongson-specific code paths in drivers that
 # are shared between architectures, and specifically expecting the symbols.
diff --git a/arch/loongarch/Kconfig.debug b/arch/loongarch/Kconfig.debug
index e69de29bb2d1..8d36aab53008 100644
--- a/arch/loongarch/Kconfig.debug
+++ b/arch/loongarch/Kconfig.debug
@@ -0,0 +1,29 @@
+choice
+	prompt "Choose kernel unwinder"
+	default UNWINDER_PROLOGUE if KALLSYMS
+	help
+	  This determines which method will be used for unwinding kernel stack
+	  traces for panics, oopses, bugs, warnings, perf, /proc/<pid>/stack,
+	  lockdep, and more.
+
+config UNWINDER_GUESS
+	bool "Guess unwinder"
+	help
+	  This option enables the "guess" unwinder for unwinding kernel stack
+	  traces.  It scans the stack and reports every kernel text address it
+	  finds.  Some of the addresses it reports may be incorrect.
+
+	  While this option often produces false positives, it can still be
+	  useful in many cases.
+
+config UNWINDER_PROLOGUE
+	bool "Prologue unwinder"
+	depends on KALLSYMS
+	help
+	  This option enables the "prologue" unwinder for unwinding kernel stack
+	  traces.  It unwind the stack frame based on prologue code analyze.  Symbol
+	  information is needed, at least the address and length of each function.
+	  Some of the addresses it reports may be incorrect (but better than the
+	  Guess unwinder).
+
+endchoice
diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile
index fbe4277e6404..ec3de6191276 100644
--- a/arch/loongarch/Makefile
+++ b/arch/loongarch/Makefile
@@ -47,6 +47,8 @@ cflags-y += $(call cc-option, -mno-check-zero-division)
 load-y		= 0x9000000000200000
 bootvars-y	= VMLINUX_LOAD_ADDRESS=$(load-y)
 
+drivers-$(CONFIG_PCI)		+= arch/loongarch/pci/
+
 KBUILD_AFLAGS	+= $(cflags-y)
 KBUILD_CFLAGS	+= $(cflags-y)
 KBUILD_CPPFLAGS += -DVMLINUX_LOAD_ADDRESS=$(load-y)
diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig
index eb9149786b6b..3712552e18d3 100644
--- a/arch/loongarch/configs/loongson3_defconfig
+++ b/arch/loongarch/configs/loongson3_defconfig
@@ -278,6 +278,8 @@ CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_BPF=m
 CONFIG_OPENVSWITCH=m
+CONFIG_VSOCKETS=m
+CONFIG_VIRTIO_VSOCKETS=m
 CONFIG_NETLINK_DIAG=y
 CONFIG_CGROUP_NET_PRIO=y
 CONFIG_BT=m
@@ -289,6 +291,7 @@ CONFIG_MAC80211=m
 CONFIG_RFKILL=m
 CONFIG_RFKILL_INPUT=y
 CONFIG_NET_9P=y
+CONFIG_NET_9P_VIRTIO=y
 CONFIG_CEPH_LIB=m
 CONFIG_PCIEPORTBUS=y
 CONFIG_HOTPLUG_PCI_PCIE=y
@@ -308,6 +311,8 @@ CONFIG_RAPIDIO_MPORT_CDEV=m
 CONFIG_UEVENT_HELPER=y
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_FW_LOADER_COMPRESS=y
+CONFIG_FW_LOADER_COMPRESS_ZSTD=y
 CONFIG_MTD=m
 CONFIG_MTD_BLOCK=m
 CONFIG_MTD_CFI=m
@@ -328,8 +333,19 @@ CONFIG_BLK_DEV_CRYPTOLOOP=y
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=8192
+CONFIG_VIRTIO_BLK=y
 CONFIG_BLK_DEV_RBD=m
 CONFIG_BLK_DEV_NVME=y
+CONFIG_NVME_MULTIPATH=y
+CONFIG_NVME_RDMA=m
+CONFIG_NVME_FC=m
+CONFIG_NVME_TCP=m
+CONFIG_NVME_TARGET=m
+CONFIG_NVME_TARGET_PASSTHRU=y
+CONFIG_NVME_TARGET_LOOP=m
+CONFIG_NVME_TARGET_RDMA=m
+CONFIG_NVME_TARGET_FC=m
+CONFIG_NVME_TARGET_TCP=m
 CONFIG_EEPROM_AT24=m
 CONFIG_BLK_DEV_SD=y
 CONFIG_BLK_DEV_SR=y
@@ -359,6 +375,7 @@ CONFIG_SCSI_QLA_FC=m
 CONFIG_TCM_QLA2XXX=m
 CONFIG_SCSI_QLA_ISCSI=m
 CONFIG_SCSI_LPFC=m
+CONFIG_SCSI_VIRTIO=m
 CONFIG_ATA=y
 CONFIG_SATA_AHCI=y
 CONFIG_SATA_AHCI_PLATFORM=y
@@ -403,6 +420,7 @@ CONFIG_VXLAN=y
 CONFIG_RIONET=m
 CONFIG_TUN=m
 CONFIG_VETH=m
+CONFIG_VIRTIO_NET=m
 # CONFIG_NET_VENDOR_3COM is not set
 # CONFIG_NET_VENDOR_ADAPTEC is not set
 # CONFIG_NET_VENDOR_AGERE is not set
@@ -527,10 +545,12 @@ CONFIG_SERIAL_8250_SHARE_IRQ=y
 CONFIG_SERIAL_8250_RSA=y
 CONFIG_SERIAL_NONSTANDARD=y
 CONFIG_PRINTER=m
+CONFIG_VIRTIO_CONSOLE=y
 CONFIG_IPMI_HANDLER=m
 CONFIG_IPMI_DEVICE_INTERFACE=m
 CONFIG_IPMI_SI=m
 CONFIG_HW_RANDOM=y
+CONFIG_HW_RANDOM_VIRTIO=m
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_PIIX4=y
 CONFIG_I2C_GPIO=y
@@ -568,6 +588,8 @@ CONFIG_DRM_AMDGPU_SI=y
 CONFIG_DRM_AMDGPU_CIK=y
 CONFIG_DRM_AMDGPU_USERPTR=y
 CONFIG_DRM_AST=y
+CONFIG_DRM_QXL=m
+CONFIG_DRM_VIRTIO_GPU=m
 CONFIG_FB=y
 CONFIG_FB_EFI=y
 CONFIG_FB_RADEON=y
@@ -637,7 +659,16 @@ CONFIG_UIO=m
 CONFIG_UIO_PDRV_GENIRQ=m
 CONFIG_UIO_DMEM_GENIRQ=m
 CONFIG_UIO_PCI_GENERIC=m
-# CONFIG_VIRTIO_MENU is not set
+CONFIG_VFIO=m
+CONFIG_VFIO_PCI=m
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_BALLOON=m
+CONFIG_VIRTIO_INPUT=m
+CONFIG_VIRTIO_MMIO=m
+CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
+CONFIG_VHOST_NET=m
+CONFIG_VHOST_SCSI=m
+CONFIG_VHOST_VSOCK=m
 CONFIG_COMEDI=m
 CONFIG_COMEDI_PCI_DRIVERS=m
 CONFIG_COMEDI_8255_PCI=m
@@ -762,6 +793,7 @@ CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
+CONFIG_CRYPTO_DEV_VIRTIO=m
 CONFIG_PRINTK_TIME=y
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_MAGIC_SYSRQ=y
diff --git a/arch/loongarch/include/asm/bootinfo.h b/arch/loongarch/include/asm/bootinfo.h
index 9b8d49d9e61b..e02ac4af7f6e 100644
--- a/arch/loongarch/include/asm/bootinfo.h
+++ b/arch/loongarch/include/asm/bootinfo.h
@@ -28,10 +28,10 @@ struct loongson_board_info {
 struct loongson_system_configuration {
 	int nr_cpus;
 	int nr_nodes;
-	int nr_io_pics;
 	int boot_cpu_id;
 	int cores_per_node;
 	int cores_per_package;
+	unsigned long cores_io_master;
 	const char *cpuname;
 };
 
diff --git a/arch/loongarch/include/asm/dma.h b/arch/loongarch/include/asm/dma.h
new file mode 100644
index 000000000000..1a8866319fe2
--- /dev/null
+++ b/arch/loongarch/include/asm/dma.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+#ifndef __ASM_DMA_H
+#define __ASM_DMA_H
+
+#define MAX_DMA_ADDRESS	PAGE_OFFSET
+#define MAX_DMA32_PFN	(1UL << (32 - PAGE_SHIFT))
+
+#endif
diff --git a/arch/loongarch/include/asm/inst.h b/arch/loongarch/include/asm/inst.h
index 575d1bb66ffb..7b07cbb3188c 100644
--- a/arch/loongarch/include/asm/inst.h
+++ b/arch/loongarch/include/asm/inst.h
@@ -23,12 +23,33 @@ enum reg1i20_op {
 	lu32id_op	= 0x0b,
 };
 
+enum reg1i21_op {
+	beqz_op		= 0x10,
+	bnez_op		= 0x11,
+};
+
 enum reg2i12_op {
+	addiw_op	= 0x0a,
+	addid_op	= 0x0b,
 	lu52id_op	= 0x0c,
+	ldb_op		= 0xa0,
+	ldh_op		= 0xa1,
+	ldw_op		= 0xa2,
+	ldd_op		= 0xa3,
+	stb_op		= 0xa4,
+	sth_op		= 0xa5,
+	stw_op		= 0xa6,
+	std_op		= 0xa7,
 };
 
 enum reg2i16_op {
 	jirl_op		= 0x13,
+	beq_op		= 0x16,
+	bne_op		= 0x17,
+	blt_op		= 0x18,
+	bge_op		= 0x19,
+	bltu_op		= 0x1a,
+	bgeu_op		= 0x1b,
 };
 
 struct reg0i26_format {
@@ -110,6 +131,37 @@ enum loongarch_gpr {
 	LOONGARCH_GPR_MAX
 };
 
+#define is_imm12_negative(val)	is_imm_negative(val, 12)
+
+static inline bool is_imm_negative(unsigned long val, unsigned int bit)
+{
+	return val & (1UL << (bit - 1));
+}
+
+static inline bool is_branch_ins(union loongarch_instruction *ip)
+{
+	return ip->reg1i21_format.opcode >= beqz_op &&
+		ip->reg1i21_format.opcode <= bgeu_op;
+}
+
+static inline bool is_ra_save_ins(union loongarch_instruction *ip)
+{
+	/* st.d $ra, $sp, offset */
+	return ip->reg2i12_format.opcode == std_op &&
+		ip->reg2i12_format.rj == LOONGARCH_GPR_SP &&
+		ip->reg2i12_format.rd == LOONGARCH_GPR_RA &&
+		!is_imm12_negative(ip->reg2i12_format.immediate);
+}
+
+static inline bool is_stack_alloc_ins(union loongarch_instruction *ip)
+{
+	/* addi.d $sp, $sp, -imm */
+	return ip->reg2i12_format.opcode == addid_op &&
+		ip->reg2i12_format.rj == LOONGARCH_GPR_SP &&
+		ip->reg2i12_format.rd == LOONGARCH_GPR_SP &&
+		is_imm12_negative(ip->reg2i12_format.immediate);
+}
+
 u32 larch_insn_gen_lu32id(enum loongarch_gpr rd, int imm);
 u32 larch_insn_gen_lu52id(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm);
 u32 larch_insn_gen_jirl(enum loongarch_gpr rd, enum loongarch_gpr rj, unsigned long pc, unsigned long dest);
diff --git a/arch/loongarch/include/asm/irq.h b/arch/loongarch/include/asm/irq.h
index 149b2123e7f4..4b130199ceae 100644
--- a/arch/loongarch/include/asm/irq.h
+++ b/arch/loongarch/include/asm/irq.h
@@ -82,8 +82,6 @@ extern struct acpi_vector_group msi_group[MAX_IO_PICS];
 #define GSI_MAX_PCH_IRQ		(LOONGSON_PCH_IRQ_BASE + 256 - 1)
 
 extern int find_pch_pic(u32 gsi);
-extern int eiointc_get_node(int id);
-
 struct acpi_madt_lio_pic;
 struct acpi_madt_eio_pic;
 struct acpi_madt_ht_pic;
@@ -100,16 +98,8 @@ struct irq_domain *htvec_acpi_init(struct irq_domain *parent,
 					struct acpi_madt_ht_pic *acpi_htvec);
 int pch_lpc_acpi_init(struct irq_domain *parent,
 					struct acpi_madt_lpc_pic *acpi_pchlpc);
-#if IS_ENABLED(CONFIG_LOONGSON_PCH_MSI)
 int pch_msi_acpi_init(struct irq_domain *parent,
 					struct acpi_madt_msi_pic *acpi_pchmsi);
-#else
-static inline int pch_msi_acpi_init(struct irq_domain *parent,
-					struct acpi_madt_msi_pic *acpi_pchmsi)
-{
-	return 0;
-}
-#endif
 int pch_pic_acpi_init(struct irq_domain *parent,
 					struct acpi_madt_bio_pic *acpi_pchpic);
 int find_pch_pic(u32 gsi);
diff --git a/arch/loongarch/include/asm/page.h b/arch/loongarch/include/asm/page.h
index dc47fc724fa1..a37324ac460b 100644
--- a/arch/loongarch/include/asm/page.h
+++ b/arch/loongarch/include/asm/page.h
@@ -33,8 +33,6 @@
 #include <linux/kernel.h>
 #include <linux/pfn.h>
 
-#define MAX_DMA32_PFN  (1UL << (32 - PAGE_SHIFT))
-
 /*
  * It's normally defined only for FLATMEM config but it's
  * used in our early mem init code for all memory models.
diff --git a/arch/loongarch/include/asm/pci.h b/arch/loongarch/include/asm/pci.h
new file mode 100644
index 000000000000..846909d7e831
--- /dev/null
+++ b/arch/loongarch/include/asm/pci.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+#ifndef _ASM_PCI_H
+#define _ASM_PCI_H
+
+#include <linux/ioport.h>
+#include <linux/list.h>
+#include <linux/types.h>
+#include <asm/io.h>
+
+#define PCIBIOS_MIN_IO		0x4000
+#define PCIBIOS_MIN_MEM		0x20000000
+#define PCIBIOS_MIN_CARDBUS_IO	0x4000
+
+#define HAVE_PCI_MMAP
+#define pcibios_assign_all_busses()     0
+
+extern phys_addr_t mcfg_addr_init(int node);
+
+/* generic pci stuff */
+#include <asm-generic/pci.h>
+
+#endif /* _ASM_PCI_H */
diff --git a/arch/loongarch/include/asm/processor.h b/arch/loongarch/include/asm/processor.h
index 57ec45aa078e..1c4b4308378d 100644
--- a/arch/loongarch/include/asm/processor.h
+++ b/arch/loongarch/include/asm/processor.h
@@ -101,6 +101,10 @@ struct thread_struct {
 	unsigned long reg23, reg24, reg25, reg26; /* s0-s3 */
 	unsigned long reg27, reg28, reg29, reg30, reg31; /* s4-s8 */
 
+	/* __schedule() return address / call frame address */
+	unsigned long sched_ra;
+	unsigned long sched_cfa;
+
 	/* CSR registers */
 	unsigned long csr_prmd;
 	unsigned long csr_crmd;
@@ -129,6 +133,9 @@ struct thread_struct {
 	struct loongarch_fpu fpu FPU_ALIGN;
 };
 
+#define thread_saved_ra(tsk)	(tsk->thread.sched_ra)
+#define thread_saved_fp(tsk)	(tsk->thread.sched_cfa)
+
 #define INIT_THREAD  {						\
 	/*							\
 	 * Main processor registers				\
@@ -145,6 +152,8 @@ struct thread_struct {
 	.reg29			= 0,				\
 	.reg30			= 0,				\
 	.reg31			= 0,				\
+	.sched_ra		= 0,				\
+	.sched_cfa		= 0,				\
 	.csr_crmd		= 0,				\
 	.csr_prmd		= 0,				\
 	.csr_euen		= 0,				\
diff --git a/arch/loongarch/include/asm/stacktrace.h b/arch/loongarch/include/asm/stacktrace.h
index 6b5c2a7aa706..f23adb15f418 100644
--- a/arch/loongarch/include/asm/stacktrace.h
+++ b/arch/loongarch/include/asm/stacktrace.h
@@ -10,6 +10,26 @@
 #include <asm/loongarch.h>
 #include <linux/stringify.h>
 
+enum stack_type {
+	STACK_TYPE_UNKNOWN,
+	STACK_TYPE_IRQ,
+	STACK_TYPE_TASK,
+};
+
+struct stack_info {
+	enum stack_type type;
+	unsigned long begin, end, next_sp;
+};
+
+struct stack_frame {
+	unsigned long	fp;
+	unsigned long	ra;
+};
+
+bool in_irq_stack(unsigned long stack, struct stack_info *info);
+bool in_task_stack(unsigned long stack, struct task_struct *task, struct stack_info *info);
+int get_stack_info(unsigned long stack, struct task_struct *task, struct stack_info *info);
+
 #define STR_LONG_L    __stringify(LONG_L)
 #define STR_LONG_S    __stringify(LONG_S)
 #define STR_LONGSIZE  __stringify(LONGSIZE)
diff --git a/arch/loongarch/include/asm/switch_to.h b/arch/loongarch/include/asm/switch_to.h
index 2a8d04375574..43a5ab162d38 100644
--- a/arch/loongarch/include/asm/switch_to.h
+++ b/arch/loongarch/include/asm/switch_to.h
@@ -15,12 +15,15 @@ struct task_struct;
  * @prev:	The task previously executed.
  * @next:	The task to begin executing.
  * @next_ti:	task_thread_info(next).
+ * @sched_ra:	__schedule return address.
+ * @sched_cfa:	__schedule call frame address.
  *
  * This function is used whilst scheduling to save the context of prev & load
  * the context of next. Returns prev.
  */
 extern asmlinkage struct task_struct *__switch_to(struct task_struct *prev,
-			struct task_struct *next, struct thread_info *next_ti);
+			struct task_struct *next, struct thread_info *next_ti,
+			void *sched_ra, void *sched_cfa);
 
 /*
  * For newly created kernel threads switch_to() will return to
@@ -28,10 +31,11 @@ extern asmlinkage struct task_struct *__switch_to(struct task_struct *prev,
  * That is, everything following __switch_to() will be skipped for new threads.
  * So everything that matters to new threads should be placed before __switch_to().
  */
-#define switch_to(prev, next, last)					\
-do {									\
-	lose_fpu_inatomic(1, prev);					\
-	(last) = __switch_to(prev, next, task_thread_info(next));	\
+#define switch_to(prev, next, last)						\
+do {										\
+	lose_fpu_inatomic(1, prev);						\
+	(last) = __switch_to(prev, next, task_thread_info(next),		\
+		 __builtin_return_address(0), __builtin_frame_address(0));	\
 } while (0)
 
 #endif /* _ASM_SWITCH_TO_H */
diff --git a/arch/loongarch/include/asm/uaccess.h b/arch/loongarch/include/asm/uaccess.h
index 2b44edc604a2..a8ae2af4025a 100644
--- a/arch/loongarch/include/asm/uaccess.h
+++ b/arch/loongarch/include/asm/uaccess.h
@@ -229,13 +229,13 @@ extern unsigned long __copy_user(void *to, const void *from, __kernel_size_t n);
 static inline unsigned long __must_check
 raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	return __copy_user(to, from, n);
+	return __copy_user(to, (__force const void *)from, n);
 }
 
 static inline unsigned long __must_check
 raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	return __copy_user(to, from, n);
+	return __copy_user((__force void *)to, from, n);
 }
 
 #define INLINE_COPY_FROM_USER
diff --git a/arch/loongarch/include/asm/unwind.h b/arch/loongarch/include/asm/unwind.h
new file mode 100644
index 000000000000..6af4718bdf01
--- /dev/null
+++ b/arch/loongarch/include/asm/unwind.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Most of this ideas comes from x86.
+ *
+ * Copyright (C) 2022 Loongson Technology Corporation Limited
+ */
+#ifndef _ASM_UNWIND_H
+#define _ASM_UNWIND_H
+
+#include <linux/sched.h>
+
+#include <asm/stacktrace.h>
+
+enum unwinder_type {
+	UNWINDER_GUESS,
+	UNWINDER_PROLOGUE,
+};
+
+struct unwind_state {
+	char type; /* UNWINDER_XXX */
+	struct stack_info stack_info;
+	struct task_struct *task;
+	bool first, error;
+	unsigned long sp, pc, ra;
+};
+
+void unwind_start(struct unwind_state *state,
+		  struct task_struct *task, struct pt_regs *regs);
+bool unwind_next_frame(struct unwind_state *state);
+unsigned long unwind_get_return_address(struct unwind_state *state);
+
+static inline bool unwind_done(struct unwind_state *state)
+{
+	return state->stack_info.type == STACK_TYPE_UNKNOWN;
+}
+
+static inline bool unwind_error(struct unwind_state *state)
+{
+	return state->error;
+}
+
+#endif /* _ASM_UNWIND_H */
diff --git a/arch/loongarch/include/asm/vdso.h b/arch/loongarch/include/asm/vdso.h
index 8f8a0f9a4953..d3ba35eb23e7 100644
--- a/arch/loongarch/include/asm/vdso.h
+++ b/arch/loongarch/include/asm/vdso.h
@@ -7,6 +7,7 @@
 #ifndef __ASM_VDSO_H
 #define __ASM_VDSO_H
 
+#include <linux/mm.h>
 #include <linux/mm_types.h>
 #include <vdso/datapage.h>
 
diff --git a/arch/loongarch/include/asm/vdso/vdso.h b/arch/loongarch/include/asm/vdso/vdso.h
index 5a01643a65b3..3b55d32a0619 100644
--- a/arch/loongarch/include/asm/vdso/vdso.h
+++ b/arch/loongarch/include/asm/vdso/vdso.h
@@ -8,6 +8,18 @@
 
 #include <asm/asm.h>
 #include <asm/page.h>
+#include <asm/vdso.h>
+
+struct vdso_pcpu_data {
+	u32 node;
+} ____cacheline_aligned_in_smp;
+
+struct loongarch_vdso_data {
+	struct vdso_pcpu_data pdata[NR_CPUS];
+	struct vdso_data data[CS_BASES]; /* Arch-independent data */
+};
+
+#define VDSO_DATA_SIZE PAGE_ALIGN(sizeof(struct loongarch_vdso_data))
 
 static inline unsigned long get_vdso_base(void)
 {
@@ -24,7 +36,8 @@ static inline unsigned long get_vdso_base(void)
 
 static inline const struct vdso_data *get_vdso_data(void)
 {
-	return (const struct vdso_data *)(get_vdso_base() - PAGE_SIZE);
+	return (const struct vdso_data *)(get_vdso_base()
+			- VDSO_DATA_SIZE + SMP_CACHE_BYTES * NR_CPUS);
 }
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index 940de9173542..e5be17009fe8 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -15,6 +15,7 @@ obj-$(CONFIG_EFI) 		+= efi.o
 obj-$(CONFIG_CPU_HAS_FPU)	+= fpu.o
 
 obj-$(CONFIG_MODULES)		+= module.o module-sections.o
+obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 
 obj-$(CONFIG_PROC_FS)		+= proc.o
 
@@ -22,4 +23,7 @@ obj-$(CONFIG_SMP)		+= smp.o
 
 obj-$(CONFIG_NUMA)		+= numa.o
 
+obj-$(CONFIG_UNWINDER_GUESS)	+= unwind_guess.o
+obj-$(CONFIG_UNWINDER_PROLOGUE) += unwind_prologue.o
+
 CPPFLAGS_vmlinux.lds		:= $(KBUILD_CFLAGS)
diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
index 03aa14581d0a..f1c928648a4a 100644
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@@ -104,6 +104,39 @@ static int set_processor_mask(u32 id, u32 flags)
 }
 #endif
 
+static int __init
+acpi_parse_processor(union acpi_subtable_headers *header, const unsigned long end)
+{
+	struct acpi_madt_core_pic *processor = NULL;
+
+	processor = (struct acpi_madt_core_pic *)header;
+	if (BAD_MADT_ENTRY(processor, end))
+		return -EINVAL;
+
+	acpi_table_print_madt_entry(&header->common);
+#ifdef CONFIG_SMP
+	set_processor_mask(processor->core_id, processor->flags);
+#endif
+
+	return 0;
+}
+
+static int __init
+acpi_parse_eio_master(union acpi_subtable_headers *header, const unsigned long end)
+{
+	static int core = 0;
+	struct acpi_madt_eio_pic *eiointc = NULL;
+
+	eiointc = (struct acpi_madt_eio_pic *)header;
+	if (BAD_MADT_ENTRY(eiointc, end))
+		return -EINVAL;
+
+	core = eiointc->node * CORES_PER_EIO_NODE;
+	set_bit(core, &(loongson_sysconf.cores_io_master));
+
+	return 0;
+}
+
 static void __init acpi_process_madt(void)
 {
 #ifdef CONFIG_SMP
@@ -114,6 +147,11 @@ static void __init acpi_process_madt(void)
 		__cpu_logical_map[i] = -1;
 	}
 #endif
+	acpi_table_parse_madt(ACPI_MADT_TYPE_CORE_PIC,
+			acpi_parse_processor, MAX_CORE_PIC);
+
+	acpi_table_parse_madt(ACPI_MADT_TYPE_EIO_PIC,
+			acpi_parse_eio_master, MAX_IO_PICS);
 
 	loongson_sysconf.nr_cpus = num_processors;
 }
diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c
index d256b81c397a..bdd88eda9513 100644
--- a/arch/loongarch/kernel/asm-offsets.c
+++ b/arch/loongarch/kernel/asm-offsets.c
@@ -103,6 +103,8 @@ void output_thread_defines(void)
 	OFFSET(THREAD_REG29, task_struct, thread.reg29);
 	OFFSET(THREAD_REG30, task_struct, thread.reg30);
 	OFFSET(THREAD_REG31, task_struct, thread.reg31);
+	OFFSET(THREAD_SCHED_RA, task_struct, thread.sched_ra);
+	OFFSET(THREAD_SCHED_CFA, task_struct, thread.sched_cfa);
 	OFFSET(THREAD_CSRCRMD, task_struct,
 	       thread.csr_crmd);
 	OFFSET(THREAD_CSRPRMD, task_struct,
diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S
index 7062cdf0e33e..c60eb66793e3 100644
--- a/arch/loongarch/kernel/head.S
+++ b/