Merge tag 'loongarch-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson

Pull LoongArch updates from Huacai Chen:

 - Use EXPLICIT_RELOCS (ABIv2.0)

 - Use generic BUG() handler

 - Refactor TLB/Cache operations

 - Add qspinlock support

 - Add perf events support

 - Add kexec/kdump support

 - Add BPF JIT support

 - Add ACPI-based laptop driver

 - Update the default config file

* tag 'loongarch-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson: (25 commits)
  LoongArch: Update Loongson-3 default config file
  LoongArch: Add ACPI-based generic laptop driver
  LoongArch: Add BPF JIT support
  LoongArch: Add some instruction opcodes and formats
  LoongArch: Move {signed,unsigned}_imm_check() to inst.h
  LoongArch: Add kdump support
  LoongArch: Add kexec support
  LoongArch: Use generic BUG() handler
  LoongArch: Add SysRq-x (TLB Dump) support
  LoongArch: Add perf events support
  LoongArch: Add qspinlock support
  LoongArch: Use TLB for ioremap()
  LoongArch: Support access filter to /dev/mem interface
  LoongArch: Refactor cache probe and flush methods
  LoongArch: mm: Refactor TLB exception handlers
  LoongArch: Support R_LARCH_GOT_PC_{LO12,HI20} in modules
  LoongArch: Support PC-relative relocations in modules
  LoongArch: Define ELF relocation types added in ABIv2.0
  LoongArch: Adjust symbol addressing for AS_HAS_EXPLICIT_RELOCS
  LoongArch: Add Kconfig option AS_HAS_EXPLICIT_RELOCS
  ...

18 files changed, 1754 insertions, 111 deletions

diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index 6c33b5c45573..42be564278fa 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -23,7 +23,14 @@ obj-$(CONFIG_SMP)		+= smp.o
 
 obj-$(CONFIG_NUMA)		+= numa.o
 
+obj-$(CONFIG_MAGIC_SYSRQ)	+= sysrq.o
+
+obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
+obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
+
 obj-$(CONFIG_UNWINDER_GUESS)	+= unwind_guess.o
 obj-$(CONFIG_UNWINDER_PROLOGUE) += unwind_prologue.o
 
+obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_regs.o
+
 CPPFLAGS_vmlinux.lds		:= $(KBUILD_CFLAGS)
diff --git a/arch/loongarch/kernel/cacheinfo.c b/arch/loongarch/kernel/cacheinfo.c
index 4662b06269f4..c7988f757281 100644
--- a/arch/loongarch/kernel/cacheinfo.c
+++ b/arch/loongarch/kernel/cacheinfo.c
@@ -5,73 +5,34 @@
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
 #include <linux/cacheinfo.h>
+#include <linux/topology.h>
 #include <asm/bootinfo.h>
 #include <asm/cpu-info.h>
 
-/* Populates leaf and increments to next leaf */
-#define populate_cache(cache, leaf, c_level, c_type)		\
-do {								\
-	leaf->type = c_type;					\
-	leaf->level = c_level;					\
-	leaf->coherency_line_size = c->cache.linesz;		\
-	leaf->number_of_sets = c->cache.sets;			\
-	leaf->ways_of_associativity = c->cache.ways;		\
-	leaf->size = c->cache.linesz * c->cache.sets *		\
-		c->cache.ways;					\
-	if (leaf->level > 2)					\
-		leaf->size *= nodes_per_package;		\
-	leaf++;							\
-} while (0)
-
 int init_cache_level(unsigned int cpu)
 {
-	struct cpuinfo_loongarch *c = &current_cpu_data;
+	int cache_present = current_cpu_data.cache_leaves_present;
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
-	int levels = 0, leaves = 0;
-
-	/*
-	 * If Dcache is not set, we assume the cache structures
-	 * are not properly initialized.
-	 */
-	if (c->dcache.waysize)
-		levels += 1;
-	else
-		return -ENOENT;
-
-
-	leaves += (c->icache.waysize) ? 2 : 1;
-
-	if (c->vcache.waysize) {
-		levels++;
-		leaves++;
-	}
 
-	if (c->scache.waysize) {
-		levels++;
-		leaves++;
-	}
+	this_cpu_ci->num_levels =
+		current_cpu_data.cache_leaves[cache_present - 1].level;
+	this_cpu_ci->num_leaves = cache_present;
 
-	if (c->tcache.waysize) {
-		levels++;
-		leaves++;
-	}
-
-	this_cpu_ci->num_levels = levels;
-	this_cpu_ci->num_leaves = leaves;
 	return 0;
 }
 
 static inline bool cache_leaves_are_shared(struct cacheinfo *this_leaf,
 					   struct cacheinfo *sib_leaf)
 {
-	return !((this_leaf->level == 1) || (this_leaf->level == 2));
+	return (!(*(unsigned char *)(this_leaf->priv) & CACHE_PRIVATE)
+		&& !(*(unsigned char *)(sib_leaf->priv) & CACHE_PRIVATE));
 }
 
 static void cache_cpumap_setup(unsigned int cpu)
 {
-	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
-	struct cacheinfo *this_leaf, *sib_leaf;
 	unsigned int index;
+	struct cacheinfo *this_leaf, *sib_leaf;
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
 
 	for (index = 0; index < this_cpu_ci->num_leaves; index++) {
 		unsigned int i;
@@ -85,8 +46,10 @@ static void cache_cpumap_setup(unsigned int cpu)
 		for_each_online_cpu(i) {
 			struct cpu_cacheinfo *sib_cpu_ci = get_cpu_cacheinfo(i);
 
-			if (i == cpu || !sib_cpu_ci->info_list)
-				continue;/* skip if itself or no cacheinfo */
+			if (i == cpu || !sib_cpu_ci->info_list ||
+				(cpu_to_node(i) != cpu_to_node(cpu)))
+				continue;
+
 			sib_leaf = sib_cpu_ci->info_list + index;
 			if (cache_leaves_are_shared(this_leaf, sib_leaf)) {
 				cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map);
@@ -98,31 +61,24 @@ static void cache_cpumap_setup(unsigned int cpu)
 
 int populate_cache_leaves(unsigned int cpu)
 {
-	int level = 1, nodes_per_package = 1;
-	struct cpuinfo_loongarch *c = &current_cpu_data;
+	int i, cache_present = current_cpu_data.cache_leaves_present;
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
 	struct cacheinfo *this_leaf = this_cpu_ci->info_list;
-
-	if (loongson_sysconf.nr_nodes > 1)
-		nodes_per_package = loongson_sysconf.cores_per_package
-					/ loongson_sysconf.cores_per_node;
-
-	if (c->icache.waysize) {
-		populate_cache(dcache, this_leaf, level, CACHE_TYPE_DATA);
-		populate_cache(icache, this_leaf, level++, CACHE_TYPE_INST);
-	} else {
-		populate_cache(dcache, this_leaf, level++, CACHE_TYPE_UNIFIED);
+	struct cache_desc *cd, *cdesc = current_cpu_data.cache_leaves;
+
+	for (i = 0; i < cache_present; i++) {
+		cd = cdesc + i;
+
+		this_leaf->type = cd->type;
+		this_leaf->level = cd->level;
+		this_leaf->coherency_line_size = cd->linesz;
+		this_leaf->number_of_sets = cd->sets;
+		this_leaf->ways_of_associativity = cd->ways;
+		this_leaf->size = cd->linesz * cd->sets * cd->ways;
+		this_leaf->priv = &cd->flags;
+		this_leaf++;
 	}
 
-	if (c->vcache.waysize)
-		populate_cache(vcache, this_leaf, level++, CACHE_TYPE_UNIFIED);
-
-	if (c->scache.waysize)
-		populate_cache(scache, this_leaf, level++, CACHE_TYPE_UNIFIED);
-
-	if (c->tcache.waysize)
-		populate_cache(tcache, this_leaf, level++, CACHE_TYPE_UNIFIED);
-
 	cache_cpumap_setup(cpu);
 	this_cpu_ci->cpu_map_populated = true;
 
diff --git a/arch/loongarch/kernel/cpu-probe.c b/arch/loongarch/kernel/cpu-probe.c
index 529ab8f44ec6..255a09876ef2 100644
--- a/arch/loongarch/kernel/cpu-probe.c
+++ b/arch/loongarch/kernel/cpu-probe.c
@@ -187,7 +187,9 @@ static inline void cpu_probe_loongson(struct cpuinfo_loongarch *c, unsigned int
 	uint64_t *vendor = (void *)(&cpu_full_name[VENDOR_OFFSET]);
 	uint64_t *cpuname = (void *)(&cpu_full_name[CPUNAME_OFFSET]);
 
-	__cpu_full_name[cpu] = cpu_full_name;
+	if (!__cpu_full_name[cpu])
+		__cpu_full_name[cpu] = cpu_full_name;
+
 	*vendor = iocsr_read64(LOONGARCH_IOCSR_VENDOR);
 	*cpuname = iocsr_read64(LOONGARCH_IOCSR_CPUNAME);
 
diff --git a/arch/loongarch/kernel/crash_dump.c b/arch/loongarch/kernel/crash_dump.c
new file mode 100644
index 000000000000..e559307c1092
--- /dev/null
+++ b/arch/loongarch/kernel/crash_dump.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/crash_dump.h>
+#include <linux/io.h>
+#include <linux/uio.h>
+
+ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn,
+			 size_t csize, unsigned long offset)
+{
+	void *vaddr;
+
+	if (!csize)
+		return 0;
+
+	vaddr = memremap(__pfn_to_phys(pfn), PAGE_SIZE, MEMREMAP_WB);
+	if (!vaddr)
+		return -ENOMEM;
+
+	csize = copy_to_iter(vaddr + offset, csize, iter);
+
+	memunmap(vaddr);
+
+	return csize;
+}
diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S
index 7e57ae8741b1..97425779ce9f 100644
--- a/arch/loongarch/kernel/head.S
+++ b/arch/loongarch/kernel/head.S
@@ -8,6 +8,7 @@
 #include <asm/addrspace.h>
 #include <asm/asm.h>
 #include <asm/asmmacro.h>
+#include <asm/bug.h>
 #include <asm/regdef.h>
 #include <asm/loongarch.h>
 #include <asm/stackframe.h>
@@ -20,7 +21,11 @@
 
 _head:
 	.word	MZ_MAGIC		/* "MZ", MS-DOS header */
-	.org	0x3c			/* 0x04 ~ 0x3b reserved */
+	.org	0x8
+	.dword	kernel_entry		/* Kernel entry point */
+	.dword	_end - _text		/* Kernel image effective size */
+	.quad	0			/* Kernel image load offset from start of RAM */
+	.org	0x3c			/* 0x20 ~ 0x3b reserved */
 	.long	pe_header - _head	/* Offset to the PE header */
 
 pe_header:
@@ -57,19 +62,19 @@ SYM_CODE_START(kernel_entry)			# kernel entry point
 	li.w		t0, 0x00		# FPE=0, SXE=0, ASXE=0, BTE=0
 	csrwr		t0, LOONGARCH_CSR_EUEN
 
-	la		t0, __bss_start		# clear .bss
+	la.pcrel	t0, __bss_start		# clear .bss
 	st.d		zero, t0, 0
-	la		t1, __bss_stop - LONGSIZE
+	la.pcrel	t1, __bss_stop - LONGSIZE
 1:
 	addi.d		t0, t0, LONGSIZE
 	st.d		zero, t0, 0
 	bne		t0, t1, 1b
 
-	la		t0, fw_arg0
+	la.pcrel	t0, fw_arg0
 	st.d		a0, t0, 0		# firmware arguments
-	la		t0, fw_arg1
+	la.pcrel	t0, fw_arg1
 	st.d		a1, t0, 0
-	la		t0, fw_arg2
+	la.pcrel	t0, fw_arg2
 	st.d		a2, t0, 0
 
 	/* KSave3 used for percpu base, initialized as 0 */
@@ -77,7 +82,7 @@ SYM_CODE_START(kernel_entry)			# kernel entry point
 	/* GPR21 used for percpu base (runtime), initialized as 0 */
 	move		u0, zero
 
-	la		tp, init_thread_union
+	la.pcrel	tp, init_thread_union
 	/* Set the SP after an empty pt_regs.  */
 	PTR_LI		sp, (_THREAD_SIZE - 32 - PT_SIZE)
 	PTR_ADD		sp, sp, tp
@@ -85,6 +90,7 @@ SYM_CODE_START(kernel_entry)			# kernel entry point
 	PTR_ADDI	sp, sp, -4 * SZREG	# init stack pointer
 
 	bl		start_kernel
+	ASM_BUG()
 
 SYM_CODE_END(kernel_entry)
 
@@ -116,6 +122,8 @@ SYM_CODE_START(smpboot_entry)
 	ld.d		tp, t0, CPU_BOOT_TINFO
 
 	bl		start_secondary
+	ASM_BUG()
+
 SYM_CODE_END(smpboot_entry)
 
 #endif /* CONFIG_SMP */
diff --git a/arch/loongarch/kernel/machine_kexec.c b/arch/loongarch/kernel/machine_kexec.c
new file mode 100644
index 000000000000..2dcb9e003657
--- /dev/null
+++ b/arch/loongarch/kernel/machine_kexec.c
@@ -0,0 +1,304 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * machine_kexec.c for kexec
+ *
+ * Copyright (C) 2022 Loongson Technology Corporation Limited
+ */
+#include <linux/compiler.h>
+#include <linux/cpu.h>
+#include <linux/kexec.h>
+#include <linux/crash_dump.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/libfdt.h>
+#include <linux/mm.h>
+#include <linux/of_fdt.h>
+#include <linux/reboot.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+
+#include <asm/bootinfo.h>
+#include <asm/cacheflush.h>
+#include <asm/page.h>
+
+/* 0x100000 ~ 0x200000 is safe */
+#define KEXEC_CONTROL_CODE	TO_CACHE(0x100000UL)
+#define KEXEC_CMDLINE_ADDR	TO_CACHE(0x108000UL)
+
+static unsigned long reboot_code_buffer;
+static cpumask_t cpus_in_crash = CPU_MASK_NONE;
+
+#ifdef CONFIG_SMP
+static void (*relocated_kexec_smp_wait)(void *);
+atomic_t kexec_ready_to_reboot = ATOMIC_INIT(0);
+#endif
+
+static unsigned long efi_boot;
+static unsigned long cmdline_ptr;
+static unsigned long systable_ptr;
+static unsigned long start_addr;
+static unsigned long first_ind_entry;
+
+static void kexec_image_info(const struct kimage *kimage)
+{
+	unsigned long i;
+
+	pr_debug("kexec kimage info:\n");
+	pr_debug("\ttype:        %d\n", kimage->type);
+	pr_debug("\tstart:       %lx\n", kimage->start);
+	pr_debug("\thead:        %lx\n", kimage->head);
+	pr_debug("\tnr_segments: %lu\n", kimage->nr_segments);
+
+	for (i = 0; i < kimage->nr_segments; i++) {
+		pr_debug("\t    segment[%lu]: %016lx - %016lx", i,
+			kimage->segment[i].mem,
+			kimage->segment[i].mem + kimage->segment[i].memsz);
+		pr_debug("\t\t0x%lx bytes, %lu pages\n",
+			(unsigned long)kimage->segment[i].memsz,
+			(unsigned long)kimage->segment[i].memsz /  PAGE_SIZE);
+	}
+}
+
+int machine_kexec_prepare(struct kimage *kimage)
+{
+	int i;
+	char *bootloader = "kexec";
+	void *cmdline_ptr = (void *)KEXEC_CMDLINE_ADDR;
+
+	kexec_image_info(kimage);
+
+	kimage->arch.efi_boot = fw_arg0;
+	kimage->arch.systable_ptr = fw_arg2;
+
+	/* Find the command line */
+	for (i = 0; i < kimage->nr_segments; i++) {
+		if (!strncmp(bootloader, (char __user *)kimage->segment[i].buf, strlen(bootloader))) {
+			if (!copy_from_user(cmdline_ptr, kimage->segment[i].buf, COMMAND_LINE_SIZE))
+				kimage->arch.cmdline_ptr = (unsigned long)cmdline_ptr;
+			break;
+		}
+	}
+
+	if (!kimage->arch.cmdline_ptr) {
+		pr_err("Command line not included in the provided image\n");
+		return -EINVAL;
+	}
+
+	/* kexec/kdump need a safe page to save reboot_code_buffer */
+	kimage->control_code_page = virt_to_page((void *)KEXEC_CONTROL_CODE);
+
+	reboot_code_buffer = (unsigned long)page_address(kimage->control_code_page);
+	memcpy((void *)reboot_code_buffer, relocate_new_kernel, relocate_new_kernel_size);
+
+#ifdef CONFIG_SMP
+	/* All secondary cpus now may jump to kexec_smp_wait cycle */
+	relocated_kexec_smp_wait = reboot_code_buffer + (void *)(kexec_smp_wait - relocate_new_kernel);
+#endif
+
+	return 0;
+}
+
+void machine_kexec_cleanup(struct kimage *kimage)
+{
+}
+
+void kexec_reboot(void)
+{
+	do_kexec_t do_kexec = NULL;
+
+	/*
+	 * We know we were online, and there will be no incoming IPIs at
+	 * this point. Mark online again before rebooting so that the crash
+	 * analysis tool will see us correctly.
+	 */
+	set_cpu_online(smp_processor_id(), true);
+
+	/* Ensure remote CPUs observe that we're online before rebooting. */
+	smp_mb__after_atomic();
+
+	/*
+	 * Make sure we get correct instructions written by the
+	 * machine_kexec_prepare() CPU.
+	 */
+	__asm__ __volatile__ ("\tibar 0\n"::);
+
+#ifdef CONFIG_SMP
+	/* All secondary cpus go to kexec_smp_wait */
+	if (smp_processor_id() > 0) {
+		relocated_kexec_smp_wait(NULL);
+		unreachable();
+	}
+#endif
+
+	do_kexec = (void *)reboot_code_buffer;
+	do_kexec(efi_boot, cmdline_ptr, systable_ptr, start_addr, first_ind_entry);
+
+	unreachable();
+}
+
+
+#ifdef CONFIG_SMP
+static void kexec_shutdown_secondary(void *regs)
+{
+	int cpu = smp_processor_id();
+
+	if (!cpu_online(cpu))
+		return;
+
+	/* We won't be sent IPIs any more. */
+	set_cpu_online(cpu, false);
+
+	local_irq_disable();
+	while (!atomic_read(&kexec_ready_to_reboot))
+		cpu_relax();
+
+	kexec_reboot();
+}
+
+static void crash_shutdown_secondary(void *passed_regs)
+{
+	int cpu = smp_processor_id();
+	struct pt_regs *regs = passed_regs;
+
+	/*
+	 * If we are passed registers, use those. Otherwise get the
+	 * regs from the last interrupt, which should be correct, as
+	 * we are in an interrupt. But if the regs are not there,
+	 * pull them from the top of the stack. They are probably
+	 * wrong, but we need something to keep from crashing again.
+	 */
+	if (!regs)
+		regs = get_irq_regs();
+	if (!regs)
+		regs = task_pt_regs(current);
+
+	if (!cpu_online(cpu))
+		return;
+
+	/* We won't be sent IPIs any more. */
+	set_cpu_online(cpu, false);
+
+	local_irq_disable();
+	if (!cpumask_test_cpu(cpu, &cpus_in_crash))
+		crash_save_cpu(regs, cpu);
+	cpumask_set_cpu(cpu, &cpus_in_crash);
+
+	while (!atomic_read(&kexec_ready_to_reboot))
+		cpu_relax();
+
+	kexec_reboot();
+}
+
+void crash_smp_send_stop(void)
+{
+	unsigned int ncpus;
+	unsigned long timeout;
+	static int cpus_stopped;
+
+	/*
+	 * This function can be called twice in panic path, but obviously
+	 * we should execute this only once.
+	 */
+	if (cpus_stopped)
+		return;
+
+	cpus_stopped = 1;
+
+	 /* Excluding the panic cpu */
+	ncpus = num_online_cpus() - 1;
+
+	smp_call_function(crash_shutdown_secondary, NULL, 0);
+	smp_wmb();
+
+	/*
+	 * The crash CPU sends an IPI and wait for other CPUs to
+	 * respond. Delay of at least 10 seconds.
+	 */
+	timeout = MSEC_PER_SEC * 10;
+	pr_emerg("Sending IPI to other cpus...\n");
+	while ((cpumask_weight(&cpus_in_crash) < ncpus) && timeout--) {
+		mdelay(1);
+		cpu_relax();
+	}
+}
+#endif /* defined(CONFIG_SMP) */
+
+void machine_shutdown(void)
+{
+	int cpu;
+
+	/* All CPUs go to reboot_code_buffer */
+	for_each_possible_cpu(cpu)
+		if (!cpu_online(cpu))
+			cpu_device_up(get_cpu_device(cpu));
+
+#ifdef CONFIG_SMP
+	smp_call_function(kexec_shutdown_secondary, NULL, 0);
+#endif
+}
+
+void machine_crash_shutdown(struct pt_regs *regs)
+{
+	int crashing_cpu;
+
+	local_irq_disable();
+
+	crashing_cpu = smp_processor_id();
+	crash_save_cpu(regs, crashing_cpu);
+
+#ifdef CONFIG_SMP
+	crash_smp_send_stop();
+#endif
+	cpumask_set_cpu(crashing_cpu, &cpus_in_crash);
+
+	pr_info("Starting crashdump kernel...\n");
+}
+
+void machine_kexec(struct kimage *image)
+{
+	unsigned long entry, *ptr;
+	struct kimage_arch *internal = &image->arch;
+
+	efi_boot = internal->efi_boot;
+	cmdline_ptr = internal->cmdline_ptr;
+	systable_ptr = internal->systable_ptr;
+
+	start_addr = (unsigned long)phys_to_virt(image->start);
+
+	first_ind_entry = (image->type == KEXEC_TYPE_DEFAULT) ?
+		(unsigned long)phys_to_virt(image->head & PAGE_MASK) : 0;
+
+	/*
+	 * The generic kexec code builds a page list with physical
+	 * addresses. they are directly accessible through XKPRANGE
+	 * hence the phys_to_virt() call.
+	 */
+	for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE);
+	     ptr = (entry & IND_INDIRECTION) ?
+	       phys_to_virt(entry & PAGE_MASK) : ptr + 1) {
+		if (*ptr & IND_SOURCE || *ptr & IND_INDIRECTION ||
+		    *ptr & IND_DESTINATION)
+			*ptr = (unsigned long) phys_to_virt(*ptr);
+	}
+
+	/* Mark offline before disabling local irq. */
+	set_cpu_online(smp_processor_id(), false);
+
+	/* We do not want to be bothered. */
+	local_irq_disable();
+
+	pr_notice("EFI boot flag 0x%lx\n", efi_boot);
+	pr_notice("Command line at 0x%lx\n", cmdline_ptr);
+	pr_notice("System table at 0x%lx\n", systable_ptr);
+	pr_notice("We will call new kernel at 0x%lx\n", start_addr);
+	pr_notice("Bye ...\n");
+
+	/* Make reboot code buffer available to the boot CPU. */
+	flush_cache_all();
+
+#ifdef CONFIG_SMP
+	atomic_set(&kexec_ready_to_reboot, 1);
+#endif
+
+	kexec_reboot();
+}
diff --git a/arch/loongarch/kernel/mem.c b/arch/loongarch/kernel/mem.c
index 7423361b0ebc..4a4107a6a965 100644
--- a/arch/loongarch/kernel/mem.c
+++ b/arch/loongarch/kernel/mem.c
@@ -58,7 +58,4 @@ void __init memblock_init(void)
 	/* Reserve the kernel text/data/bss */
 	memblock_reserve(__pa_symbol(&_text),
 			 __pa_symbol(&_end) - __pa_symbol(&_text));
-
-	/* Reserve the initrd */
-	reserve_initrd_mem();
 }
diff --git a/arch/loongarch/kernel/module-sections.c b/arch/loongarch/kernel/module-sections.c
index 6d498288977d..d296a70b758f 100644
--- a/arch/loongarch/kernel/module-sections.c
+++ b/arch/loongarch/kernel/module-sections.c
@@ -7,7 +7,33 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 
-Elf_Addr module_emit_plt_entry(struct module *mod, unsigned long val)
+Elf_Addr module_emit_got_entry(struct module *mod, Elf_Addr val)
+{
+	struct mod_section *got_sec = &mod->arch.got;
+	int i = got_sec->num_entries;
+	struct got_entry *got = get_got_entry(val, got_sec);
+
+	if (got)
+		return (Elf_Addr)got;
+
+	/* There is no GOT entry for val yet, create a new one. */
+	got = (struct got_entry *)got_sec->shdr->sh_addr;
+	got[i] = emit_got_entry(val);
+
+	got_sec->num_entries++;
+	if (got_sec->num_entries > got_sec->max_entries) {
+		/*
+		 * This may happen when the module contains a GOT_HI20 without
+		 * a paired GOT_LO12. Such a module is broken, reject it.
+		 */
+		pr_err("%s: module contains bad GOT relocation\n", mod->name);
+		return 0;
+	}
+
+	return (Elf_Addr)&got[i];
+}
+
+Elf_Addr module_emit_plt_entry(struct module *mod, Elf_Addr val)
 {
 	int nr;
 	struct mod_section *plt_sec = &mod->arch.plt;
@@ -50,15 +76,25 @@ static bool duplicate_rela(const Elf_Rela *rela, int idx)
 	return false;
 }
 
-static void count_max_entries(Elf_Rela *relas, int num, unsigned int *plts)
+static void count_max_entries(Elf_Rela *relas, int num,
+			      unsigned int *plts, unsigned int *gots)
 {
 	unsigned int i, type;
 
 	for (i = 0; i < num; i++) {
 		type = ELF_R_TYPE(relas[i].r_info);
-		if (type == R_LARCH_SOP_PUSH_PLT_PCREL) {
+		switch (type) {
+		case R_LARCH_SOP_PUSH_PLT_PCREL:
+		case R_LARCH_B26:
 			if (!duplicate_rela(relas, i))
 				(*plts)++;
+			break;
+		case R_LARCH_GOT_PC_HI20:
+			if (!duplicate_rela(relas, i))
+				(*gots)++;
+			break;
+		default:
+			break; /* Do nothing. */
 		}
 	}
 }
@@ -66,18 +102,24 @@ static void count_max_entries(Elf_Rela *relas, int num, unsigned int *plts)
 int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 			      char *secstrings, struct module *mod)
 {
-	unsigned int i, num_plts = 0;
+	unsigned int i, num_plts = 0, num_gots = 0;
 
 	/*
 	 * Find the empty .plt sections.
 	 */
 	for (i = 0; i < ehdr->e_shnum; i++) {
-		if (!strcmp(secstrings + sechdrs[i].sh_name, ".plt"))
+		if (!strcmp(secstrings + sechdrs[i].sh_name, ".got"))
+			mod->arch.got.shdr = sechdrs + i;
+		else if (!strcmp(secstrings + sechdrs[i].sh_name, ".plt"))
 			mod->arch.plt.shdr = sechdrs + i;
 		else if (!strcmp(secstrings + sechdrs[i].sh_name, ".plt.idx"))
 			mod->arch.plt_idx.shdr = sechdrs + i;
 	}
 
+	if (!mod->arch.got.shdr) {
+		pr_err("%s: module GOT section(s) missing\n", mod->name);
+		return -ENOEXEC;
+	}
 	if (!mod->arch.plt.shdr) {
 		pr_err("%s: module PLT section(s) missing\n", mod->name);
 		return -ENOEXEC;
@@ -100,9 +142,16 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 		if (!(dst_sec->sh_flags & SHF_EXECINSTR))
 			continue;
 
-		count_max_entries(relas, num_rela, &num_plts);
+		count_max_entries(relas, num_rela, &num_plts, &num_gots);
 	}
 
+	mod->arch.got.shdr->sh_type = SHT_NOBITS;
+	mod->arch.got.shdr->sh_flags = SHF_ALLOC;
+	mod->arch.got.shdr->sh_addralign = L1_CACHE_BYTES;
+	mod->arch.got.shdr->sh_size = (num_gots + 1) * sizeof(struct got_entry);
+	mod->arch.got.num_entries = 0;
+	mod->arch.got.max_entries = num_gots;
+
 	mod->arch.plt.shdr->sh_type = SHT_NOBITS;
 	mod->arch.plt.shdr->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
 	mod->arch.plt.shdr->sh_addralign = L1_CACHE_BYTES;
diff --git a/arch/loongarch/kernel/module.c b/arch/loongarch/kernel/module.c
index 638427ff0d51..097595b2fc14 100644
--- a/arch/loongarch/kernel/module.c
+++ b/arch/loongarch/kernel/module.c
@@ -18,16 +18,6 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
 
-static inline bool signed_imm_check(long val, unsigned int bit)
-{
-	return -(1L << (bit - 1)) <= val && val < (1L << (bit - 1));
-}
-
-static inline bool unsigned_imm_check(unsigned long val, unsigned int bit)
-{
-	return val < (1UL << bit);
-}
-
 static int rela_stack_push(s64 stack_value, s64 *rela_stack, size_t *rela_stack_top)
 {
 	if (*rela_stack_top >= RELA_STACK_DEPTH)
@@ -281,6 +271,96 @@ static int apply_r_larch_add_sub(struct module *mod, u32 *location, Elf_Addr v,
 	}
 }
 
+static int apply_r_larch_b26(struct module *mod, u32 *location, Elf_Addr v,
+			s64 *rela_stack, size_t *rela_stack_top, unsigned int type)
+{
+	ptrdiff_t offset = (void *)v - (void *)location;
+	union loongarch_instruction *insn = (union loongarch_instruction *)location;
+
+	if (offset >= SZ_128M)
+		v = module_emit_plt_entry(mod, v);
+
+	if (offset < -SZ_128M)
+		v = module_emit_plt_entry(mod, v);
+
+	offset = (void *)v - (void *)location;
+
+	if (offset & 3) {
+		pr_err("module %s: jump offset = 0x%llx unaligned! dangerous R_LARCH_B26 (%u) relocation\n",
+				mod->name, (long long)offset, type);
+		return -ENOEXEC;
+	}
+
+	if (!signed_imm_check(offset, 28)) {
+		pr_err("module %s: jump offset = 0x%llx overflow! dangerous R_LARCH_B26 (%u) relocation\n",
+				mod->name, (long long)offset, type);
+		return -ENOEXEC;
+	}
+
+	offset >>= 2;
+	insn->reg0i26_format.immediate_l = offset & 0xffff;
+	insn->reg0i26_format.immediate_h = (offset >> 16) & 0x3ff;
+
+	return 0;
+}
+
+static int apply_r_larch_pcala(struct module *mod, u32 *location, Elf_Addr v,
+			s64 *rela_stack, size_t *rela_stack_top, unsigned int type)
+{
+	union loongarch_instruction *insn = (union loongarch_instruction *)location;
+	/* Use s32 for a sign-extension deliberately. */
+	s32 offset_hi20 = (void *)((v + 0x800) & ~0xfff) -
+			  (void *)((Elf_Addr)location & ~0xfff);
+	Elf_Addr anchor = (((Elf_Addr)location) & ~0xfff) + offset_hi20;
+	ptrdiff_t offset_rem = (void *)v - (void *)anchor;
+
+	switch (type) {
+	case R_LARCH_PCALA_LO12:
+		insn->reg2i12_format.immediate = v & 0xfff;
+		break;
+	case R_LARCH_PCALA_HI20:
+		v = offset_hi20 >> 12;
+		insn->reg1i20_format.immediate = v & 0xfffff;
+		break;
+	case R_LARCH_PCALA64_LO20:
+		v = offset_rem >> 32;
+		insn->reg1i20_format.immediate = v & 0xfffff;
+		break;
+	case R_LARCH_PCALA64_HI12:
+		v = offset_rem >> 52;
+		insn->reg2i12_format.immediate = v & 0xfff;
+		break;
+	default:
+		pr_err("%s: Unsupport relocation type %u\n", mod->name, type);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int apply_r_larch_got_pc(struct module *mod, u32 *location, Elf_Addr v,
+			s64 *rela_stack, size_t *rela_stack_top, unsigned int type)
+{
+	Elf_Addr got = module_emit_got_entry(mod, v);
+
+	if (!got)
+		return -EINVAL;
+
+	switch (type) {
+	case R_LARCH_GOT_PC_LO12:
+		type = R_LARCH_PCALA_LO12;
+		break;
+	case R_LARCH_GOT_PC_HI20:
+		type = R_LARCH_PCALA_HI20;
+		break;
+	default:
+		pr_err("%s: Unsupport relocation type %u\n", mod->name, type);
+		return -EINVAL;
+	}
+
+	return apply_r_larch_pcala(mod, location, got, rela_stack, rela_stack_top, type);
+}
+
 /*
  * reloc_handlers_rela() - Apply a particular relocation to a module
  * @mod: the module to apply the reloc to
@@ -296,7 +376,7 @@ typedef int (*reloc_rela_handler)(struct module *mod, u32 *location, Elf_Addr v,
 
 /* The handlers for known reloc types */
 static reloc_rela_handler reloc_rela_handlers[] = {
-	[R_LARCH_NONE ... R_LARCH_SUB64]		     = apply_r_larch_error,
+	[R_LARCH_NONE ... R_LARCH_RELAX]		     = apply_r_larch_error,
 
 	[R_LARCH_NONE]					     = apply_r_larch_none,
 	[R_LARCH_32]					     = apply_r_larch_32,
@@ -310,6 +390,9 @@ static reloc_rela_handler reloc_rela_handlers[] = {
 	[R_LARCH_SOP_SUB ... R_LARCH_SOP_IF_ELSE] 	     = apply_r_larch_sop,
 	[R_LARCH_SOP_POP_32_S_10_5 ... R_LARCH_SOP_POP_32_U] = apply_r_larch_sop_imm_field,
 	[R_LARCH_ADD32 ... R_LARCH_SUB64]		     = apply_r_larch_add_sub,
+	[R_LARCH_B26]					     = apply_r_larch_b26,
+	[R_LARCH_PCALA_HI20...R_LARCH_PCALA64_HI12]	     = apply_r_larch_pcala,
+	[R_LARCH_GOT_PC_HI20...R_LARCH_GOT_PC_LO12]	     = apply_r_larch_got_pc,
 };
 
 int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
diff --git a/arch/loongarch/kernel/perf_event.c b/arch/loongarch/kernel/perf_event.c
new file mode 100644
index 000000000000..707bd32e5c4f
--- /dev/null
+++ b/arch/loongarch/kernel/perf_event.c
@@ -0,0 +1,887 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Linux performance counter support for LoongArch.
+ *
+ * Copyright (C) 2022 Loongson Technology Corporation Limited
+ *
+ * Derived from MIPS:
+ * Copyright (C) 2010 MIPS Technologies, Inc.
+ * Copyright (C) 2011 Cavium Networks, Inc.
+ * Author: Deng-Cheng Zhu
+ */
+
+#include <linux/cpumask.h>
+#include <linux/interrupt.h>
+#include <linux/smp.h>
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/uaccess.h>
+#include <linux/sched/task_stack.h>
+
+#include <asm/irq.h>
+#include <asm/irq_regs.h>
+#include <asm/stacktrace.h>
+#include <asm/unwind.h>
+
+/*
+ * Get the return address for a single stackframe and return a pointer to the
+ * next frame tail.
+ */
+static unsigned long
+user_backtrace(struct perf_callchain_entry_ctx *entry, unsigned long fp)
+{
+	unsigned long err;
+	unsigned long __user *user_frame_tail;
+	struct stack_frame buftail;
+
+	user_frame_tail = (unsigned long __user *)(fp - sizeof(struct stack_frame));
+
+	/* Also check accessibility of one struct frame_tail beyond */
+	if (!access_ok(user_frame_tail, sizeof(buftail)))
+		return 0;
+
+	pagefault_disable();
+	err = __copy_from_user_inatomic(&buftail, user_frame_tail, sizeof(buftail));
+	pagefault_enable();
+
+	if (err || (unsigned long)user_frame_tail >= buftail.fp)
+		return 0;
+
+	perf_callchain_store(entry, buftail.ra);
+
+	return buftail.fp;
+}
+
+void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
+			 struct pt_regs *regs)
+{
+	unsigned long fp;
+
+	if (perf_guest_state()) {
+		/* We don't support guest os callchain now */
+		return;
+	}
+
+	perf_callchain_store(entry, regs->csr_era);
+
+	fp = regs->regs[22];
+
+	while (entry->nr < entry->max_stack && fp && !((unsigned long)fp & 0xf))
+		fp = user_backtrace(entry, fp);
+}
+
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
+			   struct pt_regs *regs)
+{
+	struct unwind_state state;
+	unsigned long addr;
+
+	for (unwind_start(&state, current, regs);
+	      !unwind_done(&state); unwind_next_frame(&state)) {
+		addr = unwind_get_return_address(&state);
+		if (!addr || perf_callchain_store(entry, addr))
+			return;
+	}
+}
+
+#define LOONGARCH_MAX_HWEVENTS 32
+
+struct cpu_hw_events {
+	/* Array of events on this cpu. */
+	struct perf_event	*events[LOONGARCH_MAX_HWEVENTS];
+
+	/*
+	 * Set the bit (indexed by the counter number) when the counter
+	 * is used for an event.
+	 */
+	unsigned long		used_mask[BITS_TO_LONGS(LOONGARCH_MAX_HWEVENTS)];
+
+	/*
+	 * Software copy of the control register for each performance counter.
+	 */
+	unsigned int		saved_ctrl[LOONGARCH_MAX_HWEVENTS];
+};
+static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
+	.saved_ctrl = {0},
+};
+
+/* The description of LoongArch performance events. */
+struct loongarch_perf_event {
+	unsigned int event_id;
+};
+
+static struct loongarch_perf_event raw_event;
+static DEFINE_MUTEX(raw_event_mutex);
+
+#define C(x) PERF_COUNT_HW_CACHE_##x
+#define HW_OP_UNSUPPORTED		0xffffffff
+#define CACHE_OP_UNSUPPORTED		0xffffffff
+
+#define PERF_MAP_ALL_UNSUPPORTED					\
+	[0 ... PERF_COUNT_HW_MAX - 1] = {HW_OP_UNSUPPORTED}
+
+#define PERF_CACHE_MAP_ALL_UNSUPPORTED					\
+[0 ... C(MAX) - 1] = {							\
+	[0 ... C(OP_MAX) - 1] = {					\
+		[0 ... C(RESULT_MAX) - 1] = {CACHE_OP_UNSUPPORTED},	\
+	},								\
+}
+
+struct loongarch_pmu {
+	u64		max_period;
+	u64		valid_count;
+	u64		overflow;
+	const char	*name;
+	unsigned int	num_counters;
+	u64		(*read_counter)(unsigned int idx);
+	void		(*write_counter)(unsigned int idx, u64 val);
+	const struct loongarch_perf_event *(*map_raw_event)(u64 config);
+	const struct loongarch_perf_event (*general_event_map)[PERF_COUNT_HW_MAX];
+	const struct loongarch_perf_event (*cache_event_map)
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX];
+};
+
+static struct loongarch_pmu loongarch_pmu;
+
+#define M_PERFCTL_EVENT(event)	(event & CSR_PERFCTRL_EVENT)
+
+#define M_PERFCTL_COUNT_EVENT_WHENEVER	(CSR_PERFCTRL_PLV0 |	\
+					CSR_PERFCTRL_PLV1 |	\
+					CSR_PERFCTRL_PLV2 |	\
+					CSR_PERFCTRL_PLV3 |	\
+					CSR_PERFCTRL_IE)
+
+#define M_PERFCTL_CONFIG_MASK		0x1f0000
+
+static void pause_local_counters(void);
+static void resume_local_counters(void);
+
+static u64 loongarch_pmu_read_counter(unsigned int idx)
+{
+	u64 val = -1;
+
+	switch (idx) {
+	case 0:
+		val = read_csr_perfcntr0();
+		break;
+	case 1:
+		val = read_csr_perfcntr1();
+		break;
+	case 2:
+		val = read_csr_perfcntr2();
+		break;
+	case 3:
+		val = read_csr_perfcntr3();
+		break;
+	default:
+		WARN_ONCE(1, "Invalid performance counter number (%d)\n", idx);
+		return 0;
+	}
+
+	return val;
+}
+
+static void loongarch_pmu_write_counter(unsigned int idx, u64 val)
+{
+	switch (idx) {
+	case 0:
+		write_csr_perfcntr0(val);
+		return;
+	case 1:
+		write_csr_perfcntr1(val);
+		return;
+	case 2:
+		write_csr_perfcntr2(val);
+		return;
+	case 3:
+		write_csr_perfcntr3(val);
+		return;
+	default:
+		WARN_ONCE(1, "Invalid performance counter number (%d)\n", idx);
+		return;
+	}
+}
+
+static unsigned int loongarch_pmu_read_control(unsigned int idx)
+{
+	unsigned int val = -1;
+
+	switch (idx) {
+	case 0:
+		val = read_csr_perfctrl0();
+		break;
+	case 1:
+		val = read_csr_perfctrl1();
+		break;
+	case 2:
+		val = read_csr_perfctrl2();
+		break;
+	case 3:
+		val = read_csr_perfctrl3();
+		break;
+	default:
+		WARN_ONCE(1, "Invalid performance counter number (%d)\n", idx);
+		return 0;
+	}
+
+	return val;
+}
+
+static void loongarch_pmu_write_control(unsigned int idx, unsigned int val)
+{
+	switch (idx) {
+	case 0:
+		write_csr_perfctrl0(val);
+		return;
+	case 1:
+		write_csr_perfctrl1(val);
+		return;
+	case 2:
+		write_csr_perfctrl2(val);
+		return;
+	case 3:
+		write_csr_perfctrl3(val);
+		return;
+	default:
+		WARN_ONCE(1, "Invalid performance counter number (%d)\n", idx);
+		return;
+	}
+}
+
+static int loongarch_pmu_alloc_counter(struct cpu_hw_events *cpuc, struct hw_perf_event *hwc)
+{
+	int i;
+
+	for (i = 0; i < loongarch_pmu.num_counters; i++) {
+		if (!test_and_set_bit(i, cpuc->used_mask))
+			return i;
+	}
+
+	return -EAGAIN;
+}
+
+static void loongarch_pmu_enable_event(struct hw_perf_event *evt, int idx)
+{
+	unsigned int cpu;
+	struct perf_event *event = container_of(evt, struct perf_event, hw);
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	WARN_ON(idx < 0 || idx >= loongarch_pmu.num_counters);
+
+	/* Make sure interrupt enabled. */
+	cpuc->saved_ctrl[idx] = M_PERFCTL_EVENT(evt->event_base & 0xff) |
+		(evt->config_base & M_PERFCTL_CONFIG_MASK) | CSR_PERFCTRL_IE;
+
+	cpu = (event->cpu >= 0) ? event->cpu : smp_processor_id();
+
+	/*
+	 * We do not actually let the counter run. Leave it until start().
+	 */
+	pr_debug("Enabling perf counter for CPU%d\n", cpu);
+}
+
+static void loongarch_pmu_disable_event(int idx)
+{
+	unsigned long flags;
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	WARN_ON(idx < 0 || idx >= loongarch_pmu.num_counters);
+
+	local_irq_save(flags);
+	cpuc->saved_ctrl[idx] = loongarch_pmu_read_control(idx) &
+		~M_PERFCTL_COUNT_EVENT_WHENEVER;
+	loongarch_pmu_write_control(idx, cpuc->saved_ctrl[idx]);
+	local_irq_restore(flags);
+}
+
+static int loongarch_pmu_event_set_period(struct perf_event *event,
+				    struct hw_perf_event *hwc,
+				    int idx)
+{
+	int ret = 0;
+	u64 left = local64_read(&hwc->period_left);
+	u64 period = hwc->sample_period;
+
+	if (unlikely((left + period) & (1ULL << 63))) {
+		/* left underflowed by more than period. */
+		left = period;
+		local64_set(&hwc->period_left, left);
+		hwc->last_period = period;
+		ret = 1;
+	} else	if (unlikely((left + period) <= period)) {
+		/* left underflowed by less than period. */
+		left += period;
+		local64_set(&hwc->period_left, left);
+		hwc->last_period = period;
+		ret = 1;
+	}
+
+	if (left > loongarch_pmu.max_period) {
+		left = loongarch_pmu.max_period;
+		local64_set(&hwc->period_left, left);
+	}
+
+	local64_set(&hwc->prev_count, loongarch_pmu.overflow - left);
+
+	loongarch_pmu.write_counter(idx, loongarch_pmu.overflow - left);
+
+	perf_event_update_userpage(event);
+
+	return ret;
+}
+
+static void loongarch_pmu_event_update(struct perf_event *event,
+				 struct hw_perf_event *hwc,
+				 int idx)
+{
+	u64 delta;
+	u64 prev_raw_count, new_raw_count;
+
+again:
+	prev_raw_count = local64_read(&hwc->prev_count);
+	new_raw_count = loongarch_pmu.read_counter(idx);
+
+	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
+				new_raw_count) != prev_raw_count)
+		goto again;
+
+	delta = new_raw_count - prev_raw_count;
+
+	local64_add(delta, &event->count);
+	local64_sub(delta, &hwc->period_left);
+}
+
+static void loongarch_pmu_start(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
+
+	hwc->state = 0;
+
+	/* Set the period for the event. */
+	loongarch_pmu_event_set_period(event, hwc, hwc->idx);
+
+	/* Enable the event. */
+	loongarch_pmu_enable_event(hwc, hwc->idx);
+}
+
+static void loongarch_pmu_stop(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (!(hwc->state & PERF_HES_STOPPED)) {
+		/* We are working on a local event. */
+		loongarch_pmu_disable_event(hwc->idx);
+		barrier();
+		loongarch_pmu_event_update(event, hwc, hwc->idx);
+		hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	}
+}
+
+static int loongarch_pmu_add(struct perf_event *event, int flags)
+{
+	int idx, err = 0;
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+
+	perf_pmu_disable(event->pmu);
+
+	/* To look for a free counter for this event. */
+	idx = loongarch_pmu_alloc_counter(cpuc, hwc);
+	if (idx < 0) {
+		err = idx;
+		goto out;
+	}
+
+	/*
+	 * If there is an event in the counter we are going to use then
+	 * make sure it is disabled.
+	 */
+	event->hw.idx = idx;
+	loongarch_pmu_disable_event(idx);
+	cpuc->events[idx] = event;
+
+	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	if (flags & PERF_EF_START)
+		loongarch_pmu_start(event, PERF_EF_RELOAD);
+
+	/* Propagate our changes to the userspace mapping. */
+	perf_event_update_userpage(event);
+
+out:
+	perf_pmu_enable(event->pmu);
+	return err;
+}
+
+static void loongarch_pmu_del(struct perf_event *event, int flags)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	WARN_ON(idx < 0 || idx >= loongarch_pmu.num_counters);
+
+	loongarch_pmu_stop(event, PERF_EF_UPDATE);
+	cpuc->events[idx] = NULL;
+	clear_bit(idx, cpuc->used_mask);
+
+	perf_event_update_userpage(event);
+}
+
+static void loongarch_pmu_read(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	/* Don't read disabled counters! */
+	if (hwc->idx < 0)
+		return;
+
+	loongarch_pmu_event_update(event, hwc, hwc->idx);
+}
+
+static void loongarch_pmu_enable(struct pmu *pmu)
+{
+	resume_local_counters();
+}
+
+static void loongarch_pmu_disable(struct pmu *pmu)
+{
+	pause_local_counters();
+}
+
+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, EXCCODE_PMC - EXCCODE_INT_START);
+
+	return -EINVAL;
+}
+
+static void reset_counters(void *arg);
+static int __hw_perf_event_init(struct perf_event *event);
+
+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);
+		mutex_unlock(&pmu_reserve_mutex);
+	}
+}
+
+static void handle_associated_event(struct cpu_hw_events *cpuc, int idx,
+			struct perf_sample_data *data, struct pt_regs *regs)
+{
+	struct perf_event *event = cpuc->events[idx];
+	struct hw_perf_event *hwc = &event->hw;
+
+	loongarch_pmu_event_update(event, hwc, idx);
+	data->period = event->hw.last_period;
+	if (!loongarch_pmu_event_set_period(event, hwc, idx))
+		return;
+
+	if (perf_event_overflow(event, data, regs))
+		loongarch_pmu_disable_event(idx);
+}
+
+static irqreturn_t pmu_handle_irq(int irq, void *dev)
+{
+	int n;
+	int handled = IRQ_NONE;
+	uint64_t counter;
+	struct pt_regs *regs;
+	struct perf_sample_data data;
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	/*
+	 * First we pause the local counters, so that when we are locked
+	 * here, the counters are all paused. When it gets locked due to
+	 * perf_disable(), the timer interrupt handler will be delayed.
+	 *
+	 * See also loongarch_pmu_start().
+	 */
+	pause_local_counters();
+
+	regs = get_irq_regs();
+
+	perf_sample_data_init(&data, 0, 0);
+
+	for (n = 0; n < loongarch_pmu.num_counters; n++) {
+		if (test_bit(n, cpuc->used_mask)) {
+			counter = loongarch_pmu.read_counter(n);
+			if (counter & loongarch_pmu.overflow) {
+				handle_associated_event(cpuc, n, &data, regs);
+				handled = IRQ_HANDLED;
+			}
+		}
+	}
+
+	resume_local_counters();
+
+	/*
+	 * Do all the work for the pending perf events. We can do this
+	 * in here because the performance counter interrupt is a regular
+	 * interrupt, not NMI.
+	 */
+	if (handled == IRQ_HANDLED)
+		irq_work_run();
+
+	return handled;
+}
+
+static int loongarch_pmu_event_init(struct perf_event *event)
+{
+	int r, irq;
+	unsigned long flags;
+
+	/* does not support taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
+	switch (event->attr.type) {
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+		break;
+
+	default:
+		/* Init it to avoid false validate_group */
+		event->hw.event_base = 0xffffffff;
+		return -ENOENT;
+	}
+
+	if (event->cpu >= 0 && !cpu_online(event->cpu))
+		return -ENODEV;
+
+	irq = get_pmc_irq();
+	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);
+		if (atomic_read(&active_events) == 0) {
+			r = request_irq(irq, pmu_handle_irq, flags, "Perf_PMU", &loongarch_pmu);
+			if (r < 0) {
+				mutex_unlock(&pmu_reserve_mutex);
+				pr_warn("PMU IRQ request failed\n");
+				return -ENODEV;
+			}
+		}
+		atomic_inc(&active_events);
+		mutex_unlock(&pmu_reserve_mutex);
+	}
+
+	return __hw_perf_event_init(event);
+}
+
+static struct pmu pmu = {
+	.pmu_enable	= loongarch_pmu_enable,
+	.pmu_disable	= loongarch_pmu_disable,
+	.event_init	= loongarch_pmu_event_init,
+	.add		= loongarch_pmu_add,
+	.del		= loongarch_pmu_del,
+	.start		= loongarch_pmu_start,
+	.stop		= loongarch_pmu_stop,
+	.read		= loongarch_pmu_read,
+};
+
+static unsigned int loongarch_pmu_perf_event_encode(const struct loongarch_perf_event *pev)
+{
+	return (pev->event_id & 0xff);
+}
+
+static const struct loongarch_perf_event *loongarch_pmu_map_general_event(int idx)
+{
+	const struct loongarch_perf_event *pev;
+
+	pev = &(*loongarch_pmu.general_event_map)[idx];
+
+	if (pev->event_id == HW_OP_UNSUPPORTED)
+		return ERR_PTR(-ENOENT);
+
+	return pev;
+}
+
+static const struct loongarch_perf_event *loongarch_pmu_map_cache_event(u64 config)
+{
+	unsigned int cache_type, cache_op, cache_result;
+	const struct loongarch_perf_event *pev;
+
+	cache_type = (config >> 0) & 0xff;
+	if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
+		return ERR_PTR(-EINVAL);
+
+	cache_op = (config >> 8) & 0xff;
+	if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX)
+		return ERR_PTR(-EINVAL);
+
+	cache_result = (config >> 16) & 0xff;
+	if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
+		return ERR_PTR(-EINVAL);
+
+	pev = &((*loongarch_pmu.cache_event_map)
+					[cache_type]
+					[cache_op]
+					[cache_result]);
+
+	if (pev->event_id == CACHE_OP_UNSUPPORTED)
+		return ERR_PTR(-ENOENT);
+
+	return pev;
+}
+
+static int validate_group(struct perf_event *event)
+{
+	struct cpu_hw_events fake_cpuc;
+	struct perf_event *sibling, *leader = event->group_leader;
+
+	memset(&fake_cpuc, 0, sizeof(fake_cpuc));
+
+	if (loongarch_pmu_alloc_counter(&fake_cpuc, &leader->hw) < 0)
+		return -EINVAL;
+
+	for_each_sibling_event(sibling, leader) {
+		if (loongarch_pmu_alloc_counter(&fake_cpuc, &sibling->hw) < 0)
+			return -EINVAL;
+	}
+
+	if (loongarch_pmu_alloc_counter(&fake_cpuc, &event->hw) < 0)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void reset_counters(void *arg)
+{
+	int n;
+	int counters = loongarch_pmu.num_counters;
+
+	for (n = 0; n < counters; n++) {
+		loongarch_pmu_write_control(n, 0);
+		loongarch_pmu.write_counter(n, 0);
+	}
+}
+
+static const struct loongarch_perf_event loongson_event_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
+	[PERF_COUNT_HW_CPU_CYCLES] = { 0x00 },
+	[PERF_COUNT_HW_INSTRUCTIONS] = { 0x01 },
+	[PERF_COUNT_HW_CACHE_REFERENCES] = { 0x08 },
+	[PERF_COUNT_HW_CACHE_MISSES] = { 0x09 },
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = { 0x02 },
+	[PERF_COUNT_HW_BRANCH_MISSES] = { 0x03 },
+};
+
+static const struct loongarch_perf_event loongson_cache_map
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+PERF_CACHE_MAP_ALL_UNSUPPORTED,
+[C(L1D)] = {
+	/*
+	 * Like some other architectures (e.g. ARM), the performance
+	 * counters don't differentiate between read and write
+	 * accesses/misses, so this isn't strictly correct, but it's the
+	 * best we can do. Writes and reads get combined.
+	 */
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)]	= { 0x8 },
+		[C(RESULT_MISS)]	= { 0x9 },
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)]	= { 0x8 },
+		[C(RESULT_MISS)]	= { 0x9 },
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)]	= { 0xaa },
+		[C(RESULT_MISS)]	= { 0xa9 },
+	},
+},
+[C(L1I)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)]	= { 0x6 },
+		[C(RESULT_MISS)]	= { 0x7 },
+	},
+},
+[C(LL)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)]	= { 0xc },
+		[C(RESULT_MISS)]	= { 0xd },
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)]	= { 0xc },
+		[C(RESULT_MISS)]	= { 0xd },
+	},
+},
+[C(ITLB)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_MISS)]    = { 0x3b },
+	},
+},
+[C(DTLB)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)]	= { 0x4 },
+		[C(RESULT_MISS)]	= { 0x3c },
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)]	= { 0x4 },
+		[C(RESULT_MISS)]	= { 0x3c },
+	},
+},
+[C(BPU)] = {
+	/* Using the same code for *HW_BRANCH* */
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)]  = { 0x02 },
+		[C(RESULT_MISS)]    = { 0x03 },
+	},
+},
+};
+
+static int __hw_perf_event_init(struct perf_event *event)
+{
+	int err;
+	struct hw_perf_event *hwc = &event->hw;
+	struct perf_event_attr *attr = &event->attr;
+	const struct loongarch_perf_event *pev;
+
+	/* Returning LoongArch event descriptor for generic perf event. */
+	if (PERF_TYPE_HARDWARE == event->attr.type) {
+		if (event->attr.config >= PERF_COUNT_HW_MAX)
+			return -EINVAL;
+		pev = loongarch_pmu_map_general_event(event->attr.config);
+	} else if (PERF_TYPE_HW_CACHE == event->attr.type) {
+		pev = loongarch_pmu_map_cache_event(event->attr.config);
+	} else if (PERF_TYPE_RAW == event->attr.type) {
+		/* We are working on the global raw event. */
+		mutex_lock(&raw_event_mutex);
+		pev = loongarch_pmu.map_raw_event(event->attr.config);
+	} else {
+		/* The event type is not (yet) supported. */
+		return -EOPNOTSUPP;
+	}
+
+	if (IS_ERR(pev)) {
+		if (PERF_TYPE_RAW == event->attr.type)
+			mutex_unlock(&raw_event_mutex);
+		return PTR_ERR(pev);
+	}
+
+	/*
+	 * We allow max flexibility on how each individual counter shared
+	 * by the single CPU operates (the mode exclusion and the range).
+	 */
+	hwc->config_base = CSR_PERFCTRL_IE;
+
+	hwc->event_base = loongarch_pmu_perf_event_encode(pev);
+	if (PERF_TYPE_RAW == event->attr.type)
+		mutex_unlock(&raw_event_mutex);
+
+	if (!attr->exclude_user) {
+		hwc->config_base |= CSR_PERFCTRL_PLV3;
+		hwc->config_base |= CSR_PERFCTRL_PLV2;
+	}
+	if (!attr->exclude_kernel) {
+		hwc->config_base |= CSR_PERFCTRL_PLV0;
+	}
+	if (!attr->exclude_hv) {
+		hwc->config_base |= CSR_PERFCTRL_PLV1;
+	}
+
+	hwc->config_base &= M_PERFCTL_CONFIG_MASK;
+	/*
+	 * The event can belong to another cpu. We do not assign a local
+	 * counter for it for now.
+	 */
+	hwc->idx = -1;
+	hwc->config = 0;
+
+	if (!hwc->sample_period) {
+		hwc->sample_period  = loongarch_pmu.max_period;
+		hwc->last_period    = hwc->sample_period;
+		local64_set(&hwc->period_left, hwc->sample_period);
+	}
+
+	err = 0;
+	if (event->group_leader != event)
+		err = validate_group(event);
+
+	event->destroy = hw_perf_event_destroy;
+
+	if (err)
+		event->destroy(event);
+
+	return err;
+}
+
+static void pause_local_counters(void)
+{
+	unsigned long flags;
+	int ctr = loongarch_pmu.num_counters;
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	local_irq_save(flags);
+	do {
+		ctr--;
+		cpuc->saved_ctrl[ctr] = loongarch_pmu_read_control(ctr);
+		loongarch_pmu_write_control(ctr, cpuc->saved_ctrl[ctr] &
+					 ~M_PERFCTL_COUNT_EVENT_WHENEVER);
+	} while (ctr > 0);
+	local_irq_restore(flags);
+}
+
+static void resume_local_counters(void)
+{
+	int ctr = loongarch_pmu.num_counters;
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	do {
+		ctr--;
+		loongarch_pmu_write_control(ctr, cpuc->saved_ctrl[ctr]);
+	} while (ctr > 0);
+}
+
+static const struct loongarch_perf_event *loongarch_pmu_map_raw_event(u64 config)
+{
+	raw_event.event_id = config & 0xff;
+
+	return &raw_event;
+}
+
+static int __init init_hw_perf_events(void)
+{
+	int counters;
+
+	if (!cpu_has_pmp)
+		return -ENODEV;
+
+	pr_info("Performance counters: ");
+	counters = ((read_cpucfg(LOONGARCH_CPUCFG6) & CPUCFG6_PMNUM) >> 4) + 1;
+
+	loongarch_pmu.num_counters = counters;
+	loongarch_pmu.max_period = (1ULL << 63) - 1;
+	loongarch_pmu.valid_count = (1ULL << 63) - 1;
+	loongarch_pmu.overflow = 1ULL << 63;
+	loongarch_pmu.name = "loongarch/loongson64";
+	loongarch_pmu.read_counter = loongarch_pmu_read_counter;
+	loongarch_pmu.write_counter = loongarch_pmu_write_counter;
+	loongarch_pmu.map_raw_event = loongarch_pmu_map_raw_event;
+	loongarch_pmu.general_event_map = &loongson_event_map;
+	loongarch_pmu.cache_event_map = &loongson_cache_map;
+
+	on_each_cpu(reset_counters, NULL, 1);
+
+	pr_cont("%s PMU enabled, %d %d-bit counters available to each CPU.\n",
+			loongarch_pmu.name, counters, 64);
+
+	perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
+
+	return 0;
+}
+early_initcall(init_hw_perf_events);
diff --git a/arch/loongarch/kernel/perf_regs.c b/arch/loongarch/kernel/perf_regs.c
new file mode 100644
index 000000000000..263ac4ab5af6
--- /dev/null
+++ b/arch/loongarch/kernel/perf_regs.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022 Loongson Technology Corporation Limited
+ *
+ * Derived from MIPS:
+ * Copyright (C) 2013 Cavium, Inc.
+ */
+
+#include <linux/perf_event.h>
+
+#include <asm/ptrace.h>
+
+#ifdef CONFIG_32BIT
+u64 perf_reg_abi(struct task_struct *tsk)
+{
+	return PERF_SAMPLE_REGS_ABI_32;
+}
+#else /* Must be CONFIG_64BIT */
+u64 perf_reg_abi(struct task_struct *tsk)
+{
+	if (test_tsk_thread_flag(tsk, TIF_32BIT_REGS))
+		return PERF_SAMPLE_REGS_ABI_32;
+	else
+		return PERF_SAMPLE_REGS_ABI_64;
+}
+#endif /* CONFIG_32BIT */
+
+int perf_reg_validate(u64 mask)
+{
+	if (!mask)
+		return -EINVAL;
+	if (mask & ~((1ull << PERF_REG_LOONGARCH_MAX) - 1))
+		return -EINVAL;
+	return 0;
+}
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+	if (WARN_ON_ONCE((u32)idx >= PERF_REG_LOONGARCH_MAX))
+		return 0;
+
+	if ((u32)idx == PERF_REG_LOONGARCH_PC)
+		return regs->csr_era;
+
+	return regs->regs[idx];
+}
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
diff --git a/arch/loongarch/kernel/relocate_kernel.S b/arch/loongarch/kernel/relocate_kernel.S
new file mode 100644
index 000000000000..d13252553a7c
--- /dev/null
+++ b/arch/loongarch/kernel/relocate_kernel.S
@@ -0,0 +1,112 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * relocate_kernel.S for kexec
+ *
+ * Copyright (C) 2022 Loongson Technology Corporation Limited
+ */
+
+#include <linux/kexec.h>
+
+#include <asm/asm.h>
+#include <asm/asmmacro.h>
+#include <asm/regdef.h>
+#include <asm/loongarch.h>
+#include <asm/stackframe.h>
+#include <asm/addrspace.h>
+
+SYM_CODE_START(relocate_new_kernel)
+	/*
+	 * a0: EFI boot flag for the new kernel
+	 * a1: Command line pointer for the new kernel
+	 * a2: System table pointer for the new kernel
+	 * a3: Start address to jump to after relocation
+	 * a4: Pointer to the current indirection page entry
+	 */
+	move		s0, a4
+
+	/*
+	 * In case of a kdump/crash kernel, the indirection page is not
+	 * populated as the kernel is directly copied to a reserved location
+	 */
+	beqz		s0, done
+
+process_entry:
+	PTR_L		s1, s0, 0
+	PTR_ADDI	s0, s0, SZREG
+
+	/* destination page */
+	andi		s2, s1, IND_DESTINATION
+	beqz		s2, 1f
+	li.w		t0, ~0x1
+	and		s3, s1, t0	/* store destination addr in s3 */
+	b		process_entry
+
+1:
+	/* indirection page, update s0	*/
+	andi		s2, s1, IND_INDIRECTION
+	beqz		s2, 1f
+	li.w		t0, ~0x2
+	and		s0, s1, t0
+	b		process_entry
+
+1:
+	/* done page */
+	andi		s2, s1, IND_DONE
+	beqz		s2, 1f
+	b		done
+
+1:
+	/* source page */
+	andi		s2, s1, IND_SOURCE
+	beqz		s2, process_entry
+	li.w		t0, ~0x8
+	and		s1, s1, t0
+	li.w		s5, (1 << _PAGE_SHIFT) / SZREG
+
+copy_word:
+	/* copy page word by word */
+	REG_L		s4, s1, 0
+	REG_S		s4, s3, 0
+	PTR_ADDI	s3, s3, SZREG
+	PTR_ADDI	s1, s1, SZREG
+	LONG_ADDI	s5, s5, -1
+	beqz		s5, process_entry
+	b		copy_word
+	b		process_entry
+
+done:
+	ibar		0
+	dbar		0
+
+	/*
+	 * Jump to the new kernel,
+	 * make sure the values of a0, a1, a2 and a3 are not changed.
+	 */
+	jr		a3
+SYM_CODE_END(relocate_new_kernel)
+
+#ifdef CONFIG_SMP
+/*
+ * Other CPUs should wait until code is relocated and
+ * then start at the entry point from LOONGARCH_IOCSR_MBUF0.
+ */
+SYM_CODE_START(kexec_smp_wait)
+1:	li.w		t0, 0x100			/* wait for init loop */
+2:	addi.w		t0, t0, -1			/* limit mailbox access */
+	bnez		t0, 2b
+	li.w		t1, LOONGARCH_IOCSR_MBUF0
+	iocsrrd.w	s0, t1				/* check PC as an indicator */
+	beqz		s0, 1b
+	iocsrrd.d	s0, t1				/* get PC via mailbox */
+
+	li.d		t0, CACHE_BASE
+	or		s0, s0, t0			/* s0 = TO_CACHE(s0) */
+	jr		s0				/* jump to initial PC */
+SYM_CODE_END(kexec_smp_wait)
+#endif
+
+relocate_new_kernel_end:
+
+SYM_DATA_START(relocate_new_kernel_size)
+	PTR		relocate_new_kernel_end - relocate_new_kernel
+SYM_DATA_END(relocate_new_kernel_size)
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index 5b49c78c23f4..1eb63fa9bc81 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -19,6 +19,8 @@
 #include <linux/memblock.h>
 #include <linux/initrd.h>
 #include <linux/ioport.h>
+#include <linux/kexec.h>
+#include <linux/crash_dump.h>
 #include <linux/root_dev.h>
 #include <linux/console.h>
 #include <linux/pfn.h>
@@ -185,8 +187,70 @@ static int __init early_parse_mem(char *p)
 }
 early_param("mem", early_parse_mem);
 
+static void __init arch_reserve_vmcore(void)
+{
+#ifdef CONFIG_PROC_VMCORE
+	u64 i;
+	phys_addr_t start, end;
+
+	if (!is_kdump_kernel())
+		return;
+
+	if (!elfcorehdr_size) {
+		for_each_mem_range(i, &start, &end) {
+			if (elfcorehdr_addr >= start && elfcorehdr_addr < end) {
+				/*
+				 * Reserve from the elf core header to the end of
+				 * the memory segment, that should all be kdump
+				 * reserved memory.
+				 */
+				elfcorehdr_size = end - elfcorehdr_addr;
+				break;
+			}
+		}
+	}
+
+	if (memblock_is_region_reserved(elfcorehdr_addr, elfcorehdr_size)) {
+		pr_warn("elfcorehdr is overlapped\n");
+		return;
+	}
+
+	memblock_reserve(elfcorehdr_addr, elfcorehdr_size);
+
+	pr_info("Reserving %llu KiB of memory at 0x%llx for elfcorehdr\n",
+		elfcorehdr_size >> 10, elfcorehdr_addr);
+#endif
+}
+
+static void __init arch_parse_crashkernel(void)
+{
+#ifdef CONFIG_KEXEC
+	int ret;
+	unsigned long long start;
+	unsigned long long total_mem;
+	unsigned long long crash_base, crash_size;
+
+	total_mem = memblock_phys_mem_size();
+	ret = parse_crashkernel(boot_command_line, total_mem, &crash_size, &crash_base);
+	if (ret < 0 || crash_size <= 0)
+		return;
+
+	start = memblock_phys_alloc_range(crash_size, 1, crash_base, crash_base + crash_size);
+	if (start != crash_base) {
+		pr_warn("Invalid memory region reserved for crash kernel\n");
+		return;
+	}
+
+	crashk_res.start = crash_base;
+	crashk_res.end	 = crash_base + crash_size - 1;
+#endif
+}
+
 void __init platform_init(void)
 {
+	arch_reserve_vmcore();
+	arch_parse_crashkernel();
+
 #ifdef CONFIG_ACPI_TABLE_UPGRADE
 	acpi_table_upgrade();
 #endif
@@ -289,6 +353,15 @@ static void __init resource_init(void)
 		request_resource(res, &data_resource);
 		request_resource(res, &bss_resource);
 	}
+
+#ifdef CONFIG_KEXEC
+	if (crashk_res.start < crashk_res.end) {
+		insert_resource(&iomem_resource, &crashk_res);
+		pr_info("Reserving %ldMB of memory at %ldMB for crashkernel\n",
+			(unsigned long)((crashk_res.end - crashk_res.start + 1) >> 20),
+			(unsigned long)(crashk_res.start  >> 20));
+	}
+#endif
 }
 
 static int __init reserve_memblock_reserved_regions(void)
@@ -348,10 +421,11 @@ void __init setup_arch(char **cmdline_p)
 	init_environ();
 	efi_init();
 	memblock_init();
+	pagetable_init();
 	parse_early_param();
+	reserve_initrd_mem();
 
 	platform_init();
-	pagetable_init();
 	arch_mem_init(cmdline_p);
 
 	resource_init();
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index b5fab308dcf2..781a4d4bdddc 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -240,11 +240,6 @@ void loongson3_smp_finish(void)
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-static bool io_master(int cpu)
-{
-	return test_bit(cpu, &loongson_sysconf.cores_io_master);
-}
-
 int loongson3_cpu_disable(void)
 {
 	unsigned long flags;
diff --git a/arch/loongarch/kernel/sysrq.c b/arch/loongarch/kernel/sysrq.c
new file mode 100644
index 000000000000..366baef72d29
--- /dev/null
+++ b/arch/loongarch/kernel/sysrq.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * LoongArch specific sysrq operations.
+ *
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/spinlock.h>
+#include <linux/sysrq.h>
+#include <linux/workqueue.h>
+
+#include <asm/cpu-features.h>
+#include <asm/tlb.h>
+
+/*
+ * Dump TLB entries on all CPUs.
+ */
+
+static DEFINE_SPINLOCK(show_lock);
+
+static void sysrq_tlbdump_single(void *dummy)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&show_lock, flags);
+
+	pr_info("CPU%d:\n", smp_processor_id());
+	dump_tlb_regs();
+	pr_info("\n");
+	dump_tlb_all();
+	pr_info("\n");
+
+	spin_unlock_irqrestore(&show_lock, flags);
+}
+
+#ifdef CONFIG_SMP
+static void sysrq_tlbdump_othercpus(struct work_struct *dummy)
+{
+	smp_call_function(sysrq_tlbdump_single, NULL, 0);
+}
+
+static DECLARE_WORK(sysrq_tlbdump, sysrq_tlbdump_othercpus);
+#endif
+
+static void sysrq_handle_tlbdump(int key)
+{
+	sysrq_tlbdump_single(NULL);
+#ifdef CONFIG_SMP
+	schedule_work(&sysrq_tlbdump);
+#endif
+}
+
+static struct sysrq_key_op sysrq_tlbdump_op = {
+	.handler        = sysrq_handle_tlbdump,
+	.help_msg       = "show-tlbs(x)",
+	.action_msg     = "Show TLB entries",
+	.enable_mask	= SYSRQ_ENABLE_DUMP,
+};
+
+static int __init loongarch_sysrq_init(void)
+{
+	return register_sysrq_key('x', &sysrq_tlbdump_op);
+}
+arch_initcall(loongarch_sysrq_init);
diff --git a/arch/loongarch/kernel/topology.c b/arch/loongarch/kernel/topology.c
index ab1a75c0b5a6..caa7cd859078 100644
--- a/arch/loongarch/kernel/topology.c
+++ b/arch/loongarch/kernel/topology.c
@@ -5,6 +5,7 @@
 #include <linux/node.h>
 #include <linux/nodemask.h>
 #include <linux/percpu.h>
+#include <asm/bootinfo.h>
 
 static DEFINE_PER_CPU(struct cpu, cpu_devices);
 
@@ -40,7 +41,7 @@ static int __init topology_init(void)
 	for_each_present_cpu(i) {
 		struct cpu *c = &per_cpu(cpu_devices, i);
 
-		c->hotpluggable = !!i;
+		c->hotpluggable = !io_master(i);
 		ret = register_cpu(c, i);
 		if (ret < 0)
 			pr_warn("topology_init: register_cpu %d failed (%d)\n", i, ret);
diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c
index 5010e95cef84..1a4dce84ebc6 100644
--- a/arch/loongarch/kernel/traps.c
+++ b/arch/loongarch/kernel/traps.c
@@ -10,6 +10,7 @@
 #include <linux/entry-common.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/kexec.h>
 #include <linux/module.h>
 #include <linux/extable.h>
 #include <linux/mm.h>
@@ -246,6 +247,9 @@ void __noreturn die(const char *str, struct pt_regs *regs)
 
 	oops_exit();
 
+	if (regs && kexec_should_crash(current))
+		crash_kexec(regs);
+
 	if (in_interrupt())
 		panic("Fatal exception in interrupt");
 
@@ -374,6 +378,29 @@ asmlinkage void noinstr do_ale(struct pt_regs *regs)
 	irqentry_exit(regs, state);
 }
 
+#ifdef CONFIG_GENERIC_BUG
+int is_valid_bugaddr(unsigned long addr)
+{
+	return 1;
+}
+#endif /* CONFIG_GENERIC_BUG */
+
+static void bug_handler(struct pt_regs *regs)
+{
+	switch (report_bug(regs->csr_era, regs)) {
+	case BUG_TRAP_TYPE_BUG:
+	case BUG_TRAP_TYPE_NONE:
+		die_if_kernel("Oops - BUG", regs);
+		force_sig(SIGTRAP);
+		break;
+
+	case BUG_TRAP_TYPE_WARN:
+		/* Skip the BUG instruction and continue */
+		regs->csr_era += LOONGARCH_INSN_SIZE;
+		break;
+	}
+}
+
 asmlinkage void noinstr do_bp(struct pt_regs *regs)
 {
 	bool user = user_mode(regs);
@@ -427,8 +454,7 @@ asmlinkage void noinstr do_bp(struct pt_regs *regs)
 
 	switch (bcode) {
 	case BRK_BUG:
-		die_if_kernel("Kernel bug detected", regs);
-		force_sig(SIGTRAP);
+		bug_handler(regs);
 		break;
 	case BRK_DIVZERO:
 		die_if_kernel("Break instruction in kernel code", regs);
@@ -620,9 +646,6 @@ asmlinkage void noinstr do_vint(struct pt_regs *regs, unsigned long sp)
 	irqentry_exit(regs, state);
 }
 
-extern void tlb_init(int cpu);
-extern void cache_error_setup(void);
-
 unsigned long eentry;
 unsigned long tlbrentry;
 
diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S
index e5890bec2bf6..b3309a5e695b 100644
--- a/arch/loongarch/kernel/vmlinux.lds.S
+++ b/arch/loongarch/kernel/vmlinux.lds.S
@@ -55,6 +55,10 @@ SECTIONS
 
 	EXCEPTION_TABLE(16)
 
+	.got : ALIGN(16) { *(.got) }
+	.plt : ALIGN(16) { *(.plt) }
+	.got.plt : ALIGN(16) { *(.got.plt) }
+
 	. = ALIGN(PECOFF_SEGMENT_ALIGN);
 	__init_begin = .;
 	__inittext_begin = .;