diff --git a/arch/arm/include/asm/dma.h b/arch/arm/include/asm/dma.h
index a81dda65c576..45180a2cc47c 100644
--- a/arch/arm/include/asm/dma.h
+++ b/arch/arm/include/asm/dma.h
@@ -10,7 +10,7 @@
 #else
 #define MAX_DMA_ADDRESS	({ \
 	extern phys_addr_t arm_dma_zone_size; \
-	arm_dma_zone_size && arm_dma_zone_size < (0x10000000 - PAGE_OFFSET) ? \
+	arm_dma_zone_size && arm_dma_zone_size < (0x100000000ULL - PAGE_OFFSET) ? \
 		(PAGE_OFFSET + arm_dma_zone_size) : 0xffffffffUL; })
 #endif
 
diff --git a/arch/arm/lib/findbit.S b/arch/arm/lib/findbit.S
index b5e8b9ae4c7d..7fd3600db8ef 100644
--- a/arch/arm/lib/findbit.S
+++ b/arch/arm/lib/findbit.S
@@ -40,8 +40,8 @@ ENDPROC(_find_first_zero_bit_le)
  * Prototype: int find_next_zero_bit(void *addr, unsigned int maxbit, int offset)
  */
 ENTRY(_find_next_zero_bit_le)
-		teq	r1, #0
-		beq	3b
+		cmp	r2, r1
+		bhs	3b
 		ands	ip, r2, #7
 		beq	1b			@ If new byte, goto old routine
  ARM(		ldrb	r3, [r0, r2, lsr #3]	)
@@ -81,8 +81,8 @@ ENDPROC(_find_first_bit_le)
  * Prototype: int find_next_zero_bit(void *addr, unsigned int maxbit, int offset)
  */
 ENTRY(_find_next_bit_le)
-		teq	r1, #0
-		beq	3b
+		cmp	r2, r1
+		bhs	3b
 		ands	ip, r2, #7
 		beq	1b			@ If new byte, goto old routine
  ARM(		ldrb	r3, [r0, r2, lsr #3]	)
@@ -115,8 +115,8 @@ ENTRY(_find_first_zero_bit_be)
 ENDPROC(_find_first_zero_bit_be)
 
 ENTRY(_find_next_zero_bit_be)
-		teq	r1, #0
-		beq	3b
+		cmp	r2, r1
+		bhs	3b
 		ands	ip, r2, #7
 		beq	1b			@ If new byte, goto old routine
 		eor	r3, r2, #0x18		@ big endian byte ordering
@@ -149,8 +149,8 @@ ENTRY(_find_first_bit_be)
 ENDPROC(_find_first_bit_be)
 
 ENTRY(_find_next_bit_be)
-		teq	r1, #0
-		beq	3b
+		cmp	r2, r1
+		bhs	3b
 		ands	ip, r2, #7
 		beq	1b			@ If new byte, goto old routine
 		eor	r3, r2, #0x18		@ big endian byte ordering
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index b57daee98b89..62b5b07fa4e1 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -69,7 +69,6 @@ config LOONGARCH
 	select GENERIC_TIME_VSYSCALL
 	select GPIOLIB
 	select HAVE_ARCH_AUDITSYSCALL
-	select HAVE_ARCH_COMPILER_H
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
diff --git a/arch/loongarch/include/asm/asmmacro.h b/arch/loongarch/include/asm/asmmacro.h
index a1a04083bd67..be037a40580d 100644
--- a/arch/loongarch/include/asm/asmmacro.h
+++ b/arch/loongarch/include/asm/asmmacro.h
@@ -274,16 +274,4 @@
 	nor	\dst, \src, zero
 .endm
 
-.macro bgt r0 r1 label
-	blt	\r1, \r0, \label
-.endm
-
-.macro bltz r0 label
-	blt	\r0, zero, \label
-.endm
-
-.macro bgez r0 label
-	bge	\r0, zero, \label
-.endm
-
 #endif /* _ASM_ASMMACRO_H */
diff --git a/arch/loongarch/include/asm/atomic.h b/arch/loongarch/include/asm/atomic.h
index 979367ad4e2c..6b9aca9ab6e9 100644
--- a/arch/loongarch/include/asm/atomic.h
+++ b/arch/loongarch/include/asm/atomic.h
@@ -10,7 +10,6 @@
 #include <linux/types.h>
 #include <asm/barrier.h>
 #include <asm/cmpxchg.h>
-#include <asm/compiler.h>
 
 #if __SIZEOF_LONG__ == 4
 #define __LL		"ll.w	"
@@ -157,27 +156,25 @@ static inline int arch_atomic_sub_if_positive(int i, atomic_t *v)
 		__asm__ __volatile__(
 		"1:	ll.w	%1, %2		# atomic_sub_if_positive\n"
 		"	addi.w	%0, %1, %3				\n"
-		"	or	%1, %0, $zero				\n"
-		"	blt	%0, $zero, 2f				\n"
+		"	move	%1, %0					\n"
+		"	bltz	%0, 2f					\n"
 		"	sc.w	%1, %2					\n"
-		"	beq	$zero, %1, 1b				\n"
+		"	beqz	%1, 1b					\n"
 		"2:							\n"
 		__WEAK_LLSC_MB
-		: "=&r" (result), "=&r" (temp),
-		  "+" GCC_OFF_SMALL_ASM() (v->counter)
+		: "=&r" (result), "=&r" (temp), "+ZC" (v->counter)
 		: "I" (-i));
 	} else {
 		__asm__ __volatile__(
 		"1:	ll.w	%1, %2		# atomic_sub_if_positive\n"
 		"	sub.w	%0, %1, %3				\n"
-		"	or	%1, %0, $zero				\n"
-		"	blt	%0, $zero, 2f				\n"
+		"	move	%1, %0					\n"
+		"	bltz	%0, 2f					\n"
 		"	sc.w	%1, %2					\n"
-		"	beq	$zero, %1, 1b				\n"
+		"	beqz	%1, 1b					\n"
 		"2:							\n"
 		__WEAK_LLSC_MB
-		: "=&r" (result), "=&r" (temp),
-		  "+" GCC_OFF_SMALL_ASM() (v->counter)
+		: "=&r" (result), "=&r" (temp), "+ZC" (v->counter)
 		: "r" (i));
 	}
 
@@ -320,27 +317,25 @@ static inline long arch_atomic64_sub_if_positive(long i, atomic64_t *v)
 		__asm__ __volatile__(
 		"1:	ll.d	%1, %2	# atomic64_sub_if_positive	\n"
 		"	addi.d	%0, %1, %3				\n"
-		"	or	%1, %0, $zero				\n"
-		"	blt	%0, $zero, 2f				\n"
+		"	move	%1, %0					\n"
+		"	bltz	%0, 2f					\n"
 		"	sc.d	%1, %2					\n"
-		"	beq	%1, $zero, 1b				\n"
+		"	beqz	%1, 1b					\n"
 		"2:							\n"
 		__WEAK_LLSC_MB
-		: "=&r" (result), "=&r" (temp),
-		  "+" GCC_OFF_SMALL_ASM() (v->counter)
+		: "=&r" (result), "=&r" (temp), "+ZC" (v->counter)
 		: "I" (-i));
 	} else {
 		__asm__ __volatile__(
 		"1:	ll.d	%1, %2	# atomic64_sub_if_positive	\n"
 		"	sub.d	%0, %1, %3				\n"
-		"	or	%1, %0, $zero				\n"
-		"	blt	%0, $zero, 2f				\n"
+		"	move	%1, %0					\n"
+		"	bltz	%0, 2f					\n"
 		"	sc.d	%1, %2					\n"
-		"	beq	%1, $zero, 1b				\n"
+		"	beqz	%1, 1b					\n"
 		"2:							\n"
 		__WEAK_LLSC_MB
-		: "=&r" (result), "=&r" (temp),
-		  "+" GCC_OFF_SMALL_ASM() (v->counter)
+		: "=&r" (result), "=&r" (temp), "+ZC" (v->counter)
 		: "r" (i));
 	}
 
diff --git a/arch/loongarch/include/asm/barrier.h b/arch/loongarch/include/asm/barrier.h
index b6517eeeb141..cda977675854 100644
--- a/arch/loongarch/include/asm/barrier.h
+++ b/arch/loongarch/include/asm/barrier.h
@@ -48,9 +48,9 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
 	__asm__ __volatile__(
 		"sltu	%0, %1, %2\n\t"
 #if (__SIZEOF_LONG__ == 4)
-		"sub.w	%0, $r0, %0\n\t"
+		"sub.w	%0, $zero, %0\n\t"
 #elif (__SIZEOF_LONG__ == 8)
-		"sub.d	%0, $r0, %0\n\t"
+		"sub.d	%0, $zero, %0\n\t"
 #endif
 		: "=r" (mask)
 		: "r" (index), "r" (size)
diff --git a/arch/loongarch/include/asm/cmpxchg.h b/arch/loongarch/include/asm/cmpxchg.h
index 75b3a4478652..0a9b0fac1eee 100644
--- a/arch/loongarch/include/asm/cmpxchg.h
+++ b/arch/loongarch/include/asm/cmpxchg.h
@@ -55,9 +55,9 @@ static inline unsigned long __xchg(volatile void *ptr, unsigned long x,
 	__asm__ __volatile__(						\
 	"1:	" ld "	%0, %2		# __cmpxchg_asm \n"		\
 	"	bne	%0, %z3, 2f			\n"		\
-	"	or	$t0, %z4, $zero			\n"		\
+	"	move	$t0, %z4			\n"		\
 	"	" st "	$t0, %1				\n"		\
-	"	beq	$zero, $t0, 1b			\n"		\
+	"	beqz	$t0, 1b				\n"		\
 	"2:						\n"		\
 	__WEAK_LLSC_MB							\
 	: "=&r" (__ret), "=ZB"(*m)					\
diff --git a/arch/loongarch/include/asm/compiler.h b/arch/loongarch/include/asm/compiler.h
deleted file mode 100644
index 657cebe70ace..000000000000
--- a/arch/loongarch/include/asm/compiler.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
- */
-#ifndef _ASM_COMPILER_H
-#define _ASM_COMPILER_H
-
-#define GCC_OFF_SMALL_ASM() "ZC"
-
-#define LOONGARCH_ISA_LEVEL "loongarch"
-#define LOONGARCH_ISA_ARCH_LEVEL "arch=loongarch"
-#define LOONGARCH_ISA_LEVEL_RAW loongarch
-#define LOONGARCH_ISA_ARCH_LEVEL_RAW LOONGARCH_ISA_LEVEL_RAW
-
-#endif /* _ASM_COMPILER_H */
diff --git a/arch/loongarch/include/asm/elf.h b/arch/loongarch/include/asm/elf.h
index f3960b18a90e..5f3ff4781fda 100644
--- a/arch/loongarch/include/asm/elf.h
+++ b/arch/loongarch/include/asm/elf.h
@@ -288,8 +288,6 @@ struct arch_elf_state {
 	.interp_fp_abi = LOONGARCH_ABI_FP_ANY,	\
 }
 
-#define elf_read_implies_exec(ex, exec_stk) (exec_stk == EXSTACK_DEFAULT)
-
 extern int arch_elf_pt_proc(void *ehdr, void *phdr, struct file *elf,
 			    bool is_interp, struct arch_elf_state *state);
 
diff --git a/arch/loongarch/include/asm/futex.h b/arch/loongarch/include/asm/futex.h
index 9de8231694ec..feb6658c84ff 100644
--- a/arch/loongarch/include/asm/futex.h
+++ b/arch/loongarch/include/asm/futex.h
@@ -8,7 +8,6 @@
 #include <linux/futex.h>
 #include <linux/uaccess.h>
 #include <asm/barrier.h>
-#include <asm/compiler.h>
 #include <asm/errno.h>
 
 #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)		\
@@ -17,7 +16,7 @@
 	"1:	ll.w	%1, %4 # __futex_atomic_op\n"		\
 	"	" insn	"				\n"	\
 	"2:	sc.w	$t0, %2				\n"	\
-	"	beq	$t0, $zero, 1b			\n"	\
+	"	beqz	$t0, 1b				\n"	\
 	"3:						\n"	\
 	"	.section .fixup,\"ax\"			\n"	\
 	"4:	li.w	%0, %6				\n"	\
@@ -82,9 +81,9 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newv
 	"# futex_atomic_cmpxchg_inatomic			\n"
 	"1:	ll.w	%1, %3					\n"
 	"	bne	%1, %z4, 3f				\n"
-	"	or	$t0, %z5, $zero				\n"
+	"	move	$t0, %z5				\n"
 	"2:	sc.w	$t0, %2					\n"
-	"	beq	$zero, $t0, 1b				\n"
+	"	beqz	$t0, 1b					\n"
 	"3:							\n"
 	__WEAK_LLSC_MB
 	"	.section .fixup,\"ax\"				\n"
@@ -95,8 +94,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newv
 	"	"__UA_ADDR "\t1b, 4b				\n"
 	"	"__UA_ADDR "\t2b, 4b				\n"
 	"	.previous					\n"
-	: "+r" (ret), "=&r" (val), "=" GCC_OFF_SMALL_ASM() (*uaddr)
-	: GCC_OFF_SMALL_ASM() (*uaddr), "Jr" (oldval), "Jr" (newval),
+	: "+r" (ret), "=&r" (val), "=ZC" (*uaddr)
+	: "ZC" (*uaddr), "Jr" (oldval), "Jr" (newval),
 	  "i" (-EFAULT)
 	: "memory", "t0");
 
diff --git a/arch/loongarch/include/asm/irqflags.h b/arch/loongarch/include/asm/irqflags.h
index 52121cd791fe..319a8c616f1f 100644
--- a/arch/loongarch/include/asm/irqflags.h
+++ b/arch/loongarch/include/asm/irqflags.h
@@ -9,7 +9,6 @@
 
 #include <linux/compiler.h>
 #include <linux/stringify.h>
-#include <asm/compiler.h>
 #include <asm/loongarch.h>
 
 static inline void arch_local_irq_enable(void)
diff --git a/arch/loongarch/include/asm/local.h b/arch/loongarch/include/asm/local.h
index 2052a2267337..65fbbae9fc4d 100644
--- a/arch/loongarch/include/asm/local.h
+++ b/arch/loongarch/include/asm/local.h
@@ -9,7 +9,6 @@
 #include <linux/bitops.h>
 #include <linux/atomic.h>
 #include <asm/cmpxchg.h>
-#include <asm/compiler.h>
 
 typedef struct {
 	atomic_long_t a;
diff --git a/arch/loongarch/include/asm/loongson.h b/arch/loongarch/include/asm/loongson.h
index 6a8038725ba7..6e8f6972ceb6 100644
--- a/arch/loongarch/include/asm/loongson.h
+++ b/arch/loongarch/include/asm/loongson.h
@@ -39,18 +39,6 @@ extern const struct plat_smp_ops loongson3_smp_ops;
 
 #define MAX_PACKAGES 16
 
-/* Chip Config register of each physical cpu package */
-extern u64 loongson_chipcfg[MAX_PACKAGES];
-#define LOONGSON_CHIPCFG(id) (*(volatile u32 *)(loongson_chipcfg[id]))
-
-/* Chip Temperature register of each physical cpu package */
-extern u64 loongson_chiptemp[MAX_PACKAGES];
-#define LOONGSON_CHIPTEMP(id) (*(volatile u32 *)(loongson_chiptemp[id]))
-
-/* Freq Control register of each physical cpu package */
-extern u64 loongson_freqctrl[MAX_PACKAGES];
-#define LOONGSON_FREQCTRL(id) (*(volatile u32 *)(loongson_freqctrl[id]))
-
 #define xconf_readl(addr) readl(addr)
 #define xconf_readq(addr) readq(addr)
 
@@ -58,7 +46,7 @@ static inline void xconf_writel(u32 val, volatile void __iomem *addr)
 {
 	asm volatile (
 	"	st.w	%[v], %[hw], 0	\n"
-	"	ld.b	$r0, %[hw], 0	\n"
+	"	ld.b	$zero, %[hw], 0	\n"
 	:
 	: [hw] "r" (addr), [v] "r" (val)
 	);
@@ -68,7 +56,7 @@ static inline void xconf_writeq(u64 val64, volatile void __iomem *addr)
 {
 	asm volatile (
 	"	st.d	%[v], %[hw], 0	\n"
-	"	ld.b	$r0, %[hw], 0	\n"
+	"	ld.b	$zero, %[hw], 0	\n"
 	:
 	: [hw] "r" (addr),  [v] "r" (val64)
 	);
diff --git a/arch/loongarch/include/asm/stacktrace.h b/arch/loongarch/include/asm/stacktrace.h
index 26483e396ad1..6b5c2a7aa706 100644
--- a/arch/loongarch/include/asm/stacktrace.h
+++ b/arch/loongarch/include/asm/stacktrace.h
@@ -23,13 +23,13 @@
 static __always_inline void prepare_frametrace(struct pt_regs *regs)
 {
 	__asm__ __volatile__(
-		/* Save $r1 */
+		/* Save $ra */
 		STORE_ONE_REG(1)
-		/* Use $r1 to save PC */
-		"pcaddi	$r1, 0\n\t"
-		STR_LONG_S " $r1, %0\n\t"
-		/* Restore $r1 */
-		STR_LONG_L " $r1, %1, "STR_LONGSIZE"\n\t"
+		/* Use $ra to save PC */
+		"pcaddi	$ra, 0\n\t"
+		STR_LONG_S " $ra, %0\n\t"
+		/* Restore $ra */
+		STR_LONG_L " $ra, %1, "STR_LONGSIZE"\n\t"
 		STORE_ONE_REG(2)
 		STORE_ONE_REG(3)
 		STORE_ONE_REG(4)
diff --git a/arch/loongarch/include/asm/thread_info.h b/arch/loongarch/include/asm/thread_info.h
index 99beb11c2fa8..b7dd9f19a5a9 100644
--- a/arch/loongarch/include/asm/thread_info.h
+++ b/arch/loongarch/include/asm/thread_info.h
@@ -44,14 +44,14 @@ struct thread_info {
 }
 
 /* How to get the thread information struct from C. */
-register struct thread_info *__current_thread_info __asm__("$r2");
+register struct thread_info *__current_thread_info __asm__("$tp");
 
 static inline struct thread_info *current_thread_info(void)
 {
 	return __current_thread_info;
 }
 
-register unsigned long current_stack_pointer __asm__("$r3");
+register unsigned long current_stack_pointer __asm__("$sp");
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/loongarch/include/asm/uaccess.h b/arch/loongarch/include/asm/uaccess.h
index 217c6a3727b1..2b44edc604a2 100644
--- a/arch/loongarch/include/asm/uaccess.h
+++ b/arch/loongarch/include/asm/uaccess.h
@@ -162,7 +162,7 @@ do {									\
 	"2:							\n"	\
 	"	.section .fixup,\"ax\"				\n"	\
 	"3:	li.w	%0, %3					\n"	\
-	"	or	%1, $r0, $r0				\n"	\
+	"	move	%1, $zero				\n"	\
 	"	b	2b					\n"	\
 	"	.previous					\n"	\
 	"	.section __ex_table,\"a\"			\n"	\
diff --git a/arch/loongarch/kernel/cacheinfo.c b/arch/loongarch/kernel/cacheinfo.c
index b38f5489d094..4662b06269f4 100644
--- a/arch/loongarch/kernel/cacheinfo.c
+++ b/arch/loongarch/kernel/cacheinfo.c
@@ -4,8 +4,9 @@
  *
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
-#include <asm/cpu-info.h>
 #include <linux/cacheinfo.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)		\
@@ -17,6 +18,8 @@ do {								\
 	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)
 
@@ -95,11 +98,15 @@ static void cache_cpumap_setup(unsigned int cpu)
 
 int populate_cache_leaves(unsigned int cpu)
 {
-	int level = 1;
+	int level = 1, nodes_per_package = 1;
 	struct cpuinfo_loongarch *c = &current_cpu_data;
 	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);
diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S
index d5b3dbcf5425..d53b631c9022 100644
--- a/arch/loongarch/kernel/entry.S
+++ b/arch/loongarch/kernel/entry.S
@@ -27,7 +27,7 @@ SYM_FUNC_START(handle_syscall)
 
 	addi.d	sp, sp, -PT_SIZE
 	cfi_st	t2, PT_R3
-	cfi_rel_offset  sp, PT_R3
+	cfi_rel_offset	sp, PT_R3
 	st.d	zero, sp, PT_R0
 	csrrd	t2, LOONGARCH_CSR_PRMD
 	st.d	t2, sp, PT_PRMD
@@ -50,7 +50,7 @@ SYM_FUNC_START(handle_syscall)
 	cfi_st	a7, PT_R11
 	csrrd	ra, LOONGARCH_CSR_ERA
 	st.d	ra, sp, PT_ERA
-	cfi_rel_offset ra, PT_ERA
+	cfi_rel_offset	ra, PT_ERA
 
 	cfi_st	tp, PT_R2
 	cfi_st	u0, PT_R21
diff --git a/arch/loongarch/kernel/env.c b/arch/loongarch/kernel/env.c
index 467946ecf451..82b478a5c665 100644
--- a/arch/loongarch/kernel/env.c
+++ b/arch/loongarch/kernel/env.c
@@ -17,21 +17,6 @@ u64 efi_system_table;
 struct loongson_system_configuration loongson_sysconf;
 EXPORT_SYMBOL(loongson_sysconf);
 
-u64 loongson_chipcfg[MAX_PACKAGES];
-u64 loongson_chiptemp[MAX_PACKAGES];
-u64 loongson_freqctrl[MAX_PACKAGES];
-unsigned long long smp_group[MAX_PACKAGES];
-
-static void __init register_addrs_set(u64 *registers, const u64 addr, int num)
-{
-	u64 i;
-
-	for (i = 0; i < num; i++) {
-		*registers = (i << 44) | addr;
-		registers++;
-	}
-}
-
 void __init init_environ(void)
 {
 	int efi_boot = fw_arg0;
@@ -50,11 +35,6 @@ void __init init_environ(void)
 	efi_memmap_init_early(&data);
 	memblock_reserve(data.phys_map & PAGE_MASK,
 			 PAGE_ALIGN(data.size + (data.phys_map & ~PAGE_MASK)));
-
-	register_addrs_set(smp_group, TO_UNCACHE(0x1fe01000), 16);
-	register_addrs_set(loongson_chipcfg, TO_UNCACHE(0x1fe00180), 16);
-	register_addrs_set(loongson_chiptemp, TO_UNCACHE(0x1fe0019c), 16);
-	register_addrs_set(loongson_freqctrl, TO_UNCACHE(0x1fe001d0), 16);
 }
 
 static int __init init_cpu_fullname(void)
diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S
index a631a7137667..576b3370a296 100644
--- a/arch/loongarch/kernel/fpu.S
+++ b/arch/loongarch/kernel/fpu.S
@@ -27,78 +27,78 @@
 	.endm
 
 	.macro sc_save_fp base
-	EX	fst.d $f0,  \base, (0 * FPU_REG_WIDTH)
-	EX	fst.d $f1,  \base, (1 * FPU_REG_WIDTH)
-	EX	fst.d $f2,  \base, (2 * FPU_REG_WIDTH)
-	EX	fst.d $f3,  \base, (3 * FPU_REG_WIDTH)
-	EX	fst.d $f4,  \base, (4 * FPU_REG_WIDTH)
-	EX	fst.d $f5,  \base, (5 * FPU_REG_WIDTH)
-	EX	fst.d $f6,  \base, (6 * FPU_REG_WIDTH)
-	EX	fst.d $f7,  \base, (7 * FPU_REG_WIDTH)
-	EX	fst.d $f8,  \base, (8 * FPU_REG_WIDTH)
-	EX	fst.d $f9,  \base, (9 * FPU_REG_WIDTH)
-	EX	fst.d $f10, \base, (10 * FPU_REG_WIDTH)
-	EX	fst.d $f11, \base, (11 * FPU_REG_WIDTH)
-	EX	fst.d $f12, \base, (12 * FPU_REG_WIDTH)
-	EX	fst.d $f13, \base, (13 * FPU_REG_WIDTH)
-	EX	fst.d $f14, \base, (14 * FPU_REG_WIDTH)
-	EX	fst.d $f15, \base, (15 * FPU_REG_WIDTH)
-	EX	fst.d $f16, \base, (16 * FPU_REG_WIDTH)
-	EX	fst.d $f17, \base, (17 * FPU_REG_WIDTH)
-	EX	fst.d $f18, \base, (18 * FPU_REG_WIDTH)
-	EX	fst.d $f19, \base, (19 * FPU_REG_WIDTH)
-	EX	fst.d $f20, \base, (20 * FPU_REG_WIDTH)
-	EX	fst.d $f21, \base, (21 * FPU_REG_WIDTH)
-	EX	fst.d $f22, \base, (22 * FPU_REG_WIDTH)
-	EX	fst.d $f23, \base, (23 * FPU_REG_WIDTH)
-	EX	fst.d $f24, \base, (24 * FPU_REG_WIDTH)
-	EX	fst.d $f25, \base, (25 * FPU_REG_WIDTH)
-	EX	fst.d $f26, \base, (26 * FPU_REG_WIDTH)
-	EX	fst.d $f27, \base, (27 * FPU_REG_WIDTH)
-	EX	fst.d $f28, \base, (28 * FPU_REG_WIDTH)
-	EX	fst.d $f29, \base, (29 * FPU_REG_WIDTH)
-	EX	fst.d $f30, \base, (30 * FPU_REG_WIDTH)
-	EX	fst.d $f31, \base, (31 * FPU_REG_WIDTH)
+	EX	fst.d	$f0,  \base, (0 * FPU_REG_WIDTH)
+	EX	fst.d	$f1,  \base, (1 * FPU_REG_WIDTH)
+	EX	fst.d	$f2,  \base, (2 * FPU_REG_WIDTH)
+	EX	fst.d	$f3,  \base, (3 * FPU_REG_WIDTH)
+	EX	fst.d	$f4,  \base, (4 * FPU_REG_WIDTH)
+	EX	fst.d	$f5,  \base, (5 * FPU_REG_WIDTH)
+	EX	fst.d	$f6,  \base, (6 * FPU_REG_WIDTH)
+	EX	fst.d	$f7,  \base, (7 * FPU_REG_WIDTH)
+	EX	fst.d	$f8,  \base, (8 * FPU_REG_WIDTH)
+	EX	fst.d	$f9,  \base, (9 * FPU_REG_WIDTH)
+	EX	fst.d	$f10, \base, (10 * FPU_REG_WIDTH)
+	EX	fst.d	$f11, \base, (11 * FPU_REG_WIDTH)
+	EX	fst.d	$f12, \base, (12 * FPU_REG_WIDTH)
+	EX	fst.d	$f13, \base, (13 * FPU_REG_WIDTH)
+	EX	fst.d	$f14, \base, (14 * FPU_REG_WIDTH)
+	EX	fst.d	$f15, \base, (15 * FPU_REG_WIDTH)
+	EX	fst.d	$f16, \base, (16 * FPU_REG_WIDTH)
+	EX	fst.d	$f17, \base, (17 * FPU_REG_WIDTH)
+	EX	fst.d	$f18, \base, (18 * FPU_REG_WIDTH)
+	EX	fst.d	$f19, \base, (19 * FPU_REG_WIDTH)
+	EX	fst.d	$f20, \base, (20 * FPU_REG_WIDTH)
+	EX	fst.d	$f21, \base, (21 * FPU_REG_WIDTH)
+	EX	fst.d	$f22, \base, (22 * FPU_REG_WIDTH)
+	EX	fst.d	$f23, \base, (23 * FPU_REG_WIDTH)
+	EX	fst.d	$f24, \base, (24 * FPU_REG_WIDTH)
+	EX	fst.d	$f25, \base, (25 * FPU_REG_WIDTH)
+	EX	fst.d	$f26, \base, (26 * FPU_REG_WIDTH)
+	EX	fst.d	$f27, \base, (27 * FPU_REG_WIDTH)
+	EX	fst.d	$f28, \base, (28 * FPU_REG_WIDTH)
+	EX	fst.d	$f29, \base, (29 * FPU_REG_WIDTH)
+	EX	fst.d	$f30, \base, (30 * FPU_REG_WIDTH)
+	EX	fst.d	$f31, \base, (31 * FPU_REG_WIDTH)
 	.endm
 
 	.macro sc_restore_fp base
-	EX	fld.d $f0,  \base, (0 * FPU_REG_WIDTH)
-	EX	fld.d $f1,  \base, (1 * FPU_REG_WIDTH)
-	EX	fld.d $f2,  \base, (2 * FPU_REG_WIDTH)
-	EX	fld.d $f3,  \base, (3 * FPU_REG_WIDTH)
-	EX	fld.d $f4,  \base, (4 * FPU_REG_WIDTH)
-	EX	fld.d $f5,  \base, (5 * FPU_REG_WIDTH)
-	EX	fld.d $f6,  \base, (6 * FPU_REG_WIDTH)
-	EX	fld.d $f7,  \base, (7 * FPU_REG_WIDTH)
-	EX	fld.d $f8,  \base, (8 * FPU_REG_WIDTH)
-	EX	fld.d $f9,  \base, (9 * FPU_REG_WIDTH)
-	EX	fld.d $f10, \base, (10 * FPU_REG_WIDTH)
-	EX	fld.d $f11, \base, (11 * FPU_REG_WIDTH)
-	EX	fld.d $f12, \base, (12 * FPU_REG_WIDTH)
-	EX	fld.d $f13, \base, (13 * FPU_REG_WIDTH)
-	EX	fld.d $f14, \base, (14 * FPU_REG_WIDTH)
-	EX	fld.d $f15, \base, (15 * FPU_REG_WIDTH)
-	EX	fld.d $f16, \base, (16 * FPU_REG_WIDTH)
-	EX	fld.d $f17, \base, (17 * FPU_REG_WIDTH)
-	EX	fld.d $f18, \base, (18 * FPU_REG_WIDTH)
-	EX	fld.d $f19, \base, (19 * FPU_REG_WIDTH)
-	EX	fld.d $f20, \base, (20 * FPU_REG_WIDTH)
-	EX	fld.d $f21, \base, (21 * FPU_REG_WIDTH)
-	EX	fld.d $f22, \base, (22 * FPU_REG_WIDTH)
-	EX	fld.d $f23, \base, (23 * FPU_REG_WIDTH)
-	EX	fld.d $f24, \base, (24 * FPU_REG_WIDTH)
-	EX	fld.d $f25, \base, (25 * FPU_REG_WIDTH)
-	EX	fld.d $f26, \base, (26 * FPU_REG_WIDTH)
-	EX	fld.d $f27, \base, (27 * FPU_REG_WIDTH)
-	EX	fld.d $f28, \base, (28 * FPU_REG_WIDTH)
-	EX	fld.d $f29, \base, (29 * FPU_REG_WIDTH)
-	EX	fld.d $f30, \base, (30 * FPU_REG_WIDTH)
-	EX	fld.d $f31, \base, (31 * FPU_REG_WIDTH)
+	EX	fld.d	$f0,  \base, (0 * FPU_REG_WIDTH)
+	EX	fld.d	$f1,  \base, (1 * FPU_REG_WIDTH)
+	EX	fld.d	$f2,  \base, (2 * FPU_REG_WIDTH)
+	EX	fld.d	$f3,  \base, (3 * FPU_REG_WIDTH)
+	EX	fld.d	$f4,  \base, (4 * FPU_REG_WIDTH)
+	EX	fld.d	$f5,  \base, (5 * FPU_REG_WIDTH)
+	EX	fld.d	$f6,  \base, (6 * FPU_REG_WIDTH)
+	EX	fld.d	$f7,  \base, (7 * FPU_REG_WIDTH)
+	EX	fld.d	$f8,  \base, (8 * FPU_REG_WIDTH)
+	EX	fld.d	$f9,  \base, (9 * FPU_REG_WIDTH)
+	EX	fld.d	$f10, \base, (10 * FPU_REG_WIDTH)
+	EX	fld.d	$f11, \base, (11 * FPU_REG_WIDTH)
+	EX	fld.d	$f12, \base, (12 * FPU_REG_WIDTH)
+	EX	fld.d	$f13, \base, (13 * FPU_REG_WIDTH)
+	EX	fld.d	$f14, \base, (14 * FPU_REG_WIDTH)
+	EX	fld.d	$f15, \base, (15 * FPU_REG_WIDTH)
+	EX	fld.d	$f16, \base, (16 * FPU_REG_WIDTH)
+	EX	fld.d	$f17, \base, (17 * FPU_REG_WIDTH)
+	EX	fld.d	$f18, \base, (18 * FPU_REG_WIDTH)
+	EX	fld.d	$f19, \base, (19 * FPU_REG_WIDTH)
+	EX	fld.d	$f20, \base, (20 * FPU_REG_WIDTH)
+	EX	fld.d	$f21, \base, (21 * FPU_REG_WIDTH)
+	EX	fld.d	$f22, \base, (22 * FPU_REG_WIDTH)
+	EX	fld.d	$f23, \base, (23 * FPU_REG_WIDTH)
+	EX	fld.d	$f24, \base, (24 * FPU_REG_WIDTH)
+	EX	fld.d	$f25, \base, (25 * FPU_REG_WIDTH)
+	EX	fld.d	$f26, \base, (26 * FPU_REG_WIDTH)
+	EX	fld.d	$f27, \base, (27 * FPU_REG_WIDTH)
+	EX	fld.d	$f28, \base, (28 * FPU_REG_WIDTH)
+	EX	fld.d	$f29, \base, (29 * FPU_REG_WIDTH)
+	EX	fld.d	$f30, \base, (30 * FPU_REG_WIDTH)
+	EX	fld.d	$f31, \base, (31 * FPU_REG_WIDTH)
 	.endm
 
 	.macro sc_save_fcc base, tmp0, tmp1
 	movcf2gr	\tmp0, $fcc0
-	move	\tmp1, \tmp0
+	move		\tmp1, \tmp0
 	movcf2gr	\tmp0, $fcc1
 	bstrins.d	\tmp1, \tmp0, 15, 8
 	movcf2gr	\tmp0, $fcc2
@@ -113,11 +113,11 @@
 	bstrins.d	\tmp1, \tmp0, 55, 48
 	movcf2gr	\tmp0, $fcc7
 	bstrins.d	\tmp1, \tmp0, 63, 56
-	EX	st.d \tmp1, \base, 0
+	EX	st.d	\tmp1, \base, 0
 	.endm
 
 	.macro sc_restore_fcc base, tmp0, tmp1
-	EX	ld.d \tmp0, \base, 0
+	EX	ld.d	\tmp0, \base, 0
 	bstrpick.d	\tmp1, \tmp0, 7, 0
 	movgr2cf	$fcc0, \tmp1
 	bstrpick.d	\tmp1, \tmp0, 15, 8
@@ -138,11 +138,11 @@
 
 	.macro sc_save_fcsr base, tmp0
 	movfcsr2gr	\tmp0, fcsr0
-	EX	st.w \tmp0, \base, 0
+	EX	st.w	\tmp0, \base, 0
 	.endm
 
 	.macro sc_restore_fcsr base, tmp0
-	EX	ld.w \tmp0, \base, 0
+	EX	ld.w	\tmp0, \base, 0
 	movgr2fcsr	fcsr0, \tmp0
 	.endm
 
@@ -151,9 +151,9 @@
  */
 SYM_FUNC_START(_save_fp)
 	fpu_save_csr	a0 t1
-	fpu_save_double a0 t1			# clobbers t1
+	fpu_save_double	a0 t1			# clobbers t1
 	fpu_save_cc	a0 t1 t2		# clobbers t1, t2
-	jirl zero, ra, 0
+	jr		ra
 SYM_FUNC_END(_save_fp)
 EXPORT_SYMBOL(_save_fp)
 
@@ -161,10 +161,10 @@ EXPORT_SYMBOL(_save_fp)
  * Restore a thread's fp context.
  */
 SYM_FUNC_START(_restore_fp)
-	fpu_restore_double a0 t1		# clobbers t1
-	fpu_restore_csr	a0 t1
-	fpu_restore_cc	a0 t1 t2		# clobbers t1, t2
-	jirl zero, ra, 0
+	fpu_restore_double	a0 t1		# clobbers t1
+	fpu_restore_csr		a0 t1
+	fpu_restore_cc		a0 t1 t2	# clobbers t1, t2
+	jr			ra
 SYM_FUNC_END(_restore_fp)
 
 /*
@@ -216,7 +216,7 @@ SYM_FUNC_START(_init_fpu)
 	movgr2fr.d	$f30, t1
 	movgr2fr.d	$f31, t1
 
-	jirl zero, ra, 0
+	jr	ra
 SYM_FUNC_END(_init_fpu)
 
 /*
@@ -225,11 +225,11 @@ SYM_FUNC_END(_init_fpu)
  * a2: fcsr
  */
 SYM_FUNC_START(_save_fp_context)
-	sc_save_fcc a1 t1 t2
-	sc_save_fcsr a2 t1
-	sc_save_fp a0
-	li.w	a0, 0					# success
-	jirl zero, ra, 0
+	sc_save_fcc	a1 t1 t2
+	sc_save_fcsr	a2 t1
+	sc_save_fp	a0
+	li.w		a0, 0				# success
+	jr		ra
 SYM_FUNC_END(_save_fp_context)
 
 /*
@@ -238,14 +238,14 @@ SYM_FUNC_END(_save_fp_context)
  * a2: fcsr
  */
 SYM_FUNC_START(_restore_fp_context)
-	sc_restore_fp a0
-	sc_restore_fcc a1 t1 t2
-	sc_restore_fcsr a2 t1
-	li.w	a0, 0					# success
-	jirl zero, ra, 0
+	sc_restore_fp	a0
+	sc_restore_fcc	a1 t1 t2
+	sc_restore_fcsr	a2 t1
+	li.w		a0, 0				# success
+	jr		ra
 SYM_FUNC_END(_restore_fp_context)
 
 SYM_FUNC_START(fault)
 	li.w	a0, -EFAULT				# failure
-	jirl zero, ra, 0
+	jr	ra
 SYM_FUNC_END(fault)
diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S
index 93496852b3cc..75e5be807a0d 100644
--- a/arch/loongarch/kernel/genex.S
+++ b/arch/loongarch/kernel/genex.S
@@ -28,23 +28,23 @@ SYM_FUNC_START(__arch_cpu_idle)
 	nop
 	idle	0
 	/* end of rollback region */
-1:	jirl	zero, ra, 0
+1:	jr	ra
 SYM_FUNC_END(__arch_cpu_idle)
 
 SYM_FUNC_START(handle_vint)
 	BACKUP_T0T1
 	SAVE_ALL
 	la.abs	t1, __arch_cpu_idle
-	LONG_L  t0, sp, PT_ERA
+	LONG_L	t0, sp, PT_ERA
 	/* 32 byte rollback region */
 	ori	t0, t0, 0x1f
 	xori	t0, t0, 0x1f
 	bne	t0, t1, 1f
-	LONG_S  t0, sp, PT_ERA
+	LONG_S	t0, sp, PT_ERA
 1:	move	a0, sp
 	move	a1, sp
 	la.abs	t0, do_vint
-	jirl    ra, t0, 0
+	jirl	ra, t0, 0
 	RESTORE_ALL_AND_RET
 SYM_FUNC_END(handle_vint)
 
@@ -72,7 +72,7 @@ SYM_FUNC_END(except_vec_cex)
 	build_prep_\prep
 	move	a0, sp
 	la.abs	t0, do_\handler
-	jirl    ra, t0, 0
+	jirl	ra, t0, 0
 	RESTORE_ALL_AND_RET
 	SYM_FUNC_END(handle_\exception)
 	.endm
@@ -91,5 +91,5 @@ SYM_FUNC_END(except_vec_cex)
 
 SYM_FUNC_START(handle_sys)
 	la.abs	t0, handle_syscall
-	jirl    zero, t0, 0
+	jr	t0
 SYM_FUNC_END(handle_sys)
diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S
index d01e62dd414f..7062cdf0e33e 100644
--- a/arch/loongarch/kernel/head.S
+++ b/arch/loongarch/kernel/head.S
@@ -32,7 +32,7 @@ SYM_CODE_START(kernel_entry)			# kernel entry point
 	/* We might not get launched at the address the kernel is linked to,
 	   so we jump there.  */
 	la.abs		t0, 0f
-	jirl		zero, t0, 0
+	jr		t0
 0:
 	la		t0, __bss_start		# clear .bss
 	st.d		zero, t0, 0
@@ -50,7 +50,7 @@ SYM_CODE_START(kernel_entry)			# kernel entry point
 	/* KSave3 used for percpu base, initialized as 0 */
 	csrwr		zero, PERCPU_BASE_KS
 	/* GPR21 used for percpu base (runtime), initialized as 0 */
-	or		u0, zero, zero
+	move		u0, zero
 
 	la		tp, init_thread_union
 	/* Set the SP after an empty pt_regs.  */
@@ -85,8 +85,8 @@ SYM_CODE_START(smpboot_entry)
 	ld.d		sp, t0, CPU_BOOT_STACK
 	ld.d		tp, t0, CPU_BOOT_TINFO
 
-	la.abs	t0, 0f
-	jirl	zero, t0, 0
+	la.abs		t0, 0f
+	jr		t0
 0:
 	bl		start_secondary
 SYM_CODE_END(smpboot_entry)
diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c
index e6ab87948e1d..dc2b82ea894c 100644
--- a/arch/loongarch/kernel/ptrace.c
+++ b/arch/loongarch/kernel/ptrace.c
@@ -193,7 +193,7 @@ static int fpr_set(struct task_struct *target,
 		   const void *kbuf, const void __user *ubuf)
 {
 	const int fcc_start = NUM_FPU_REGS * sizeof(elf_fpreg_t);
-	const int fcc_end = fcc_start + sizeof(u64);
+	const int fcsr_start = fcc_start + sizeof(u64);
 	int err;
 
 	BUG_ON(count % sizeof(elf_fpreg_t));
@@ -209,10 +209,12 @@ static int fpr_set(struct task_struct *target,
 	if (err)
 		return err;
 
-	if (count > 0)
-		err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-					  &target->thread.fpu.fcc,
-					  fcc_start, fcc_end);
+	err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.fpu.fcc, fcc_start,
+				  fcc_start + sizeof(u64));
+	err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.fpu.fcsr, fcsr_start,
+				  fcsr_start + sizeof(u32));
 
 	return err;
 }
diff --git a/arch/loongarch/kernel/reset.c b/arch/loongarch/kernel/reset.c
index 2b86469e4718..800c965a17ea 100644
--- a/arch/loongarch/kernel/reset.c
+++ b/arch/loongarch/kernel/reset.c
@@ -13,7 +13,6 @@
 #include <linux/console.h>
 
 #include <acpi/reboot.h>
-#include <asm/compiler.h>
 #include <asm/idle.h>
 #include <asm/loongarch.h>
 #include <asm/reboot.h>
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index c74860b53375..8f5c2f9a1a83 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -126,7 +126,7 @@ static void __init parse_bios_table(const struct dmi_header *dm)
 	char *dmi_data = (char *)dm;
 
 	bios_extern = *(dmi_data + SMBIOS_BIOSEXTERN_OFFSET);
-	b_info.bios_size = *(dmi_data + SMBIOS_BIOSSIZE_OFFSET);
+	b_info.bios_size = (*(dmi_data + SMBIOS_BIOSSIZE_OFFSET) + 1) << 6;
 
 	if (bios_extern & LOONGSON_EFI_ENABLE)
 		set_bit(EFI_BOOT, &efi.flags);
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index 73cec62504fb..09743103d9b3 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -278,116 +278,29 @@ void loongson3_cpu_die(unsigned int cpu)
 	mb();
 }
 
-/*
- * The target CPU should go to XKPRANGE (uncached area) and flush
- * ICache/DCache/VCache before the control CPU can safely disable its clock.
- */
-static void loongson3_play_dead(int *state_addr)
+void play_dead(void)
 {
-	register int val;
-	register void *addr;
+	register uint64_t addr;
 	register void (*init_fn)(void);
 
-	__asm__ __volatile__(
-		"   li.d %[addr], 0x8000000000000000\n"
-		"1: cacop 0x8, %[addr], 0           \n" /* flush ICache */
-		"   cacop 0x8, %[addr], 1           \n"
-		"   cacop 0x8, %[addr], 2           \n"
-		"   cacop 0x8, %[addr], 3           \n"
-		"   cacop 0x9, %[addr], 0           \n" /* flush DCache */
-		"   cacop 0x9, %[addr], 1           \n"
-		"   cacop 0x9, %[addr], 2           \n"
-		"   cacop 0x9, %[addr], 3           \n"
-		"   addi.w %[sets], %[sets], -1     \n"
-		"   addi.d %[addr], %[addr], 0x40   \n"
-		"   bnez %[sets], 1b                \n"
-		"   li.d %[addr], 0x8000000000000000\n"
-		"2: cacop 0xa, %[addr], 0           \n" /* flush VCache */
-		"   cacop 0xa, %[addr], 1           \n"
-		"   cacop 0xa, %[addr], 2           \n"
-		"   cacop 0xa, %[addr], 3           \n"
-		"   cacop 0xa, %[addr], 4           \n"
-		"   cacop 0xa, %[addr], 5           \n"
-		"   cacop 0xa, %[addr], 6           \n"
-		"   cacop 0xa, %[addr], 7           \n"
-		"   cacop 0xa, %[addr], 8           \n"
-		"   cacop 0xa, %[addr], 9           \n"
-		"   cacop 0xa, %[addr], 10          \n"
-		"   cacop 0xa, %[addr], 11          \n"
-		"   cacop 0xa, %[addr], 12          \n"
-		"   cacop 0xa, %[addr], 13          \n"
-		"   cacop 0xa, %[addr], 14          \n"
-		"   cacop 0xa, %[addr], 15          \n"
-		"   addi.w %[vsets], %[vsets], -1   \n"
-		"   addi.d %[addr], %[addr], 0x40   \n"
-		"   bnez   %[vsets], 2b             \n"
-		"   li.w   %[val], 0x7              \n" /* *state_addr = CPU_DEAD; */
-		"   st.w   %[val], %[state_addr], 0 \n"
-		"   dbar 0                          \n"
-		"   cacop 0x11, %[state_addr], 0    \n" /* flush entry of *state_addr */
-		: [addr] "=&r" (addr), [val] "=&r" (val)
-		: [state_addr] "r" (state_addr),
-		  [sets] "r" (cpu_data[smp_processor_id()].dcache.sets),
-		  [vsets] "r" (cpu_data[smp_processor_id()].vcache.sets));
-
+	idle_task_exit();
 	local_irq_enable();
-	change_csr_ecfg(ECFG0_IM, ECFGF_IPI);
+	set_csr_ecfg(ECFGF_IPI);
+	__this_cpu_write(cpu_state, CPU_DEAD);
 
-	__asm__ __volatile__(
-		"   idle      0			    \n"
-		"   li.w      $t0, 0x1020	    \n"
-		"   iocsrrd.d %[init_fn], $t0	    \n" /* Get init PC */
-		: [init_fn] "=&r" (addr)
-		: /* No Input */
-		: "a0");
-	init_fn = __va(addr);
+	__smp_mb();
+	do {
+		__asm__ __volatile__("idle 0\n\t");
+		addr = iocsr_read64(LOONGARCH_IOCSR_MBUF0);
+	} while (addr == 0);
+
+	init_fn = (void *)TO_CACHE(addr);
+	iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_CLEAR);
 
 	init_fn();
 	unreachable();
 }
 
-void play_dead(void)
-{
-	int *state_addr;
-	unsigned int cpu = smp_processor_id();
-	void (*play_dead_uncached)(int *s);
-
-	idle_task_exit();
-	play_dead_uncached = (void *)TO_UNCACHE(__pa((unsigned long)loongson3_play_dead));
-	state_addr = &per_cpu(cpu_state, cpu);
-	mb();
-	play_dead_uncached(state_addr);
-}
-
-static int loongson3_enable_clock(unsigned int cpu)
-{
-	uint64_t core_id = cpu_data[cpu].core;
-	uint64_t package_id = cpu_data[cpu].package;
-
-	LOONGSON_FREQCTRL(package_id) |= 1 << (core_id * 4 + 3);
-
-	return 0;
-}
-
-static int loongson3_disable_clock(unsigned int cpu)
-{
-	uint64_t core_id = cpu_data[cpu].core;
-	uint64_t package_id = cpu_data[cpu].package;
-
-	LOONGSON_FREQCTRL(package_id) &= ~(1 << (core_id * 4 + 3));
-
-	return 0;
-}
-
-static int register_loongson3_notifier(void)
-{
-	return cpuhp_setup_state_nocalls(CPUHP_LOONGARCH_SOC_PREPARE,
-					 "loongarch/loongson:prepare",
-					 loongson3_enable_clock,
-					 loongson3_disable_clock);
-}
-early_initcall(register_loongson3_notifier);
-
 #endif
 
 /*
diff --git a/arch/loongarch/kernel/switch.S b/arch/loongarch/kernel/switch.S
index 53e2fa8e580e..37e84ac8ffc2 100644
--- a/arch/loongarch/kernel/switch.S
+++ b/arch/loongarch/kernel/switch.S
@@ -24,8 +24,8 @@ SYM_FUNC_START(__switch_to)
 	move	tp, a2
 	cpu_restore_nonscratch a1
 
-	li.w	t0, _THREAD_SIZE - 32
-	PTR_ADD	t0, t0, tp
+	li.w		t0, _THREAD_SIZE - 32
+	PTR_ADD		t0, t0, tp
 	set_saved_sp	t0, t1, t2
 
 	ldptr.d	t1, a1, THREAD_CSRPRMD
diff --git a/arch/loongarch/lib/clear_user.S b/arch/loongarch/lib/clear_user.S
index 25d9be5fbb19..16ba2b8dd68a 100644
--- a/arch/loongarch/lib/clear_user.S
+++ b/arch/loongarch/lib/clear_user.S
@@ -32,7 +32,7 @@ SYM_FUNC_START(__clear_user)
 1:	st.b	zero, a0, 0
 	addi.d	a0, a0, 1
 	addi.d	a1, a1, -1
-	bgt	a1, zero, 1b
+	bgtz	a1, 1b
 
 2:	move	a0, a1
 	jr	ra
diff --git a/arch/loongarch/lib/copy_user.S b/arch/loongarch/lib/copy_user.S
index 9ae507f851b5..97d20327a69e 100644
--- a/arch/loongarch/lib/copy_user.S
+++ b/arch/loongarch/lib/copy_user.S
@@ -35,7 +35,7 @@ SYM_FUNC_START(__copy_user)
 	addi.d	a0, a0, 1
 	addi.d	a1, a1, 1
 	addi.d	a2, a2, -1
-	bgt	a2, zero, 1b
+	bgtz	a2, 1b
 
 3:	move	a0, a2
 	jr	ra
diff --git a/arch/loongarch/lib/delay.c b/arch/loongarch/lib/delay.c
index 5d856694fcfe..831d4761f385 100644
--- a/arch/loongarch/lib/delay.c
+++ b/arch/loongarch/lib/delay.c
@@ -7,7 +7,6 @@
 #include <linux/smp.h>
 #include <linux/timex.h>
 
-#include <asm/compiler.h>
 #include <asm/processor.h>
 
 void __delay(unsigned long cycles)
diff --git a/arch/loongarch/mm/page.S b/arch/loongarch/mm/page.S
index ddc78ab33c7b..4c874a7af0ad 100644
--- a/arch/loongarch/mm/page.S
+++ b/arch/loongarch/mm/page.S
@@ -10,75 +10,75 @@
 
 	.align 5
 SYM_FUNC_START(clear_page)
-	lu12i.w  t0, 1 << (PAGE_SHIFT - 12)
-	add.d    t0, t0, a0
+	lu12i.w	t0, 1 << (PAGE_SHIFT - 12)
+	add.d	t0, t0, a0
 1:
-	st.d     zero, a0, 0
-	st.d     zero, a0, 8
-	st.d     zero, a0, 16
-	st.d     zero, a0, 24
-	st.d     zero, a0, 32
-	st.d     zero, a0, 40
-	st.d     zero, a0, 48
-	st.d     zero, a0, 56
-	addi.d   a0,   a0, 128
-	st.d     zero, a0, -64
-	st.d     zero, a0, -56
-	st.d     zero, a0, -48
-	st.d     zero, a0, -40
-	st.d     zero, a0, -32
-	st.d     zero, a0, -24
-	st.d     zero, a0, -16
-	st.d     zero, a0, -8
-	bne      t0,   a0, 1b
+	st.d	zero, a0, 0
+	st.d	zero, a0, 8
+	st.d	zero, a0, 16
+	st.d	zero, a0, 24
+	st.d	zero, a0, 32
+	st.d	zero, a0, 40
+	st.d	zero, a0, 48
+	st.d	zero, a0, 56
+	addi.d	a0,   a0, 128
+	st.d	zero, a0, -64
+	st.d	zero, a0, -56
+	st.d	zero, a0, -48
+	st.d	zero, a0, -40
+	st.d	zero, a0, -32
+	st.d	zero, a0, -24
+	st.d	zero, a0, -16
+	st.d	zero, a0, -8
+	bne	t0,   a0, 1b
 
-	jirl     $r0, ra, 0
+	jr	ra
 SYM_FUNC_END(clear_page)
 EXPORT_SYMBOL(clear_page)
 
 .align 5
 SYM_FUNC_START(copy_page)
-	lu12i.w  t8, 1 << (PAGE_SHIFT - 12)
-	add.d    t8, t8, a0
+	lu12i.w	t8, 1 << (PAGE_SHIFT - 12)
+	add.d	t8, t8, a0
 1:
-	ld.d     t0, a1,  0
-	ld.d     t1, a1,  8
-	ld.d     t2, a1,  16
-	ld.d     t3, a1,  24
-	ld.d     t4, a1,  32
-	ld.d     t5, a1,  40
-	ld.d     t6, a1,  48
-	ld.d     t7, a1,  56
+	ld.d	t0, a1, 0
+	ld.d	t1, a1, 8
+	ld.d	t2, a1, 16
+	ld.d	t3, a1, 24
+	ld.d	t4, a1, 32
+	ld.d	t5, a1, 40
+	ld.d	t6, a1, 48
+	ld.d	t7, a1, 56
 
-	st.d     t0, a0,  0
-	st.d     t1, a0,  8
-	ld.d     t0, a1,  64
-	ld.d     t1, a1,  72
-	st.d     t2, a0,  16
-	st.d     t3, a0,  24
-	ld.d     t2, a1,  80
-	ld.d     t3, a1,  88
-	st.d     t4, a0,  32
-	st.d     t5, a0,  40
-	ld.d     t4, a1,  96
-	ld.d     t5, a1,  104
-	st.d     t6, a0,  48
-	st.d     t7, a0,  56
-	ld.d     t6, a1,  112
-	ld.d     t7, a1,  120
-	addi.d   a0, a0,  128
-	addi.d   a1, a1,  128
+	st.d	t0, a0, 0
+	st.d	t1, a0, 8
+	ld.d	t0, a1, 64
+	ld.d	t1, a1, 72
+	st.d	t2, a0, 16
+	st.d	t3, a0, 24
+	ld.d	t2, a1, 80
+	ld.d	t3, a1, 88
+	st.d	t4, a0, 32
+	st.d	t5, a0, 40
+	ld.d	t4, a1, 96
+	ld.d	t5, a1, 104
+	st.d	t6, a0, 48
+	st.d	t7, a0, 56
+	ld.d	t6, a1, 112
+	ld.d	t7, a1, 120
+	addi.d	a0, a0, 128
+	addi.d	a1, a1, 128
 
-	st.d     t0, a0,  -64
-	st.d     t1, a0,  -56
-	st.d     t2, a0,  -48
-	st.d     t3, a0,  -40
-	st.d     t4, a0,  -32
-	st.d     t5, a0,  -24
-	st.d     t6, a0,  -16
-	st.d     t7, a0,  -8
+	st.d	t0, a0, -64
+	st.d	t1, a0, -56
+	st.d	t2, a0, -48
+	st.d	t3, a0, -40
+	st.d	t4, a0, -32
+	st.d	t5, a0, -24
+	st.d	t6, a0, -16
+	st.d	t7, a0, -8
 
-	bne      t8, a0, 1b
-	jirl     $r0, ra, 0
+	bne	t8, a0, 1b
+	jr	ra
 SYM_FUNC_END(copy_page)
 EXPORT_SYMBOL(copy_page)
diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S
index 7eee40271577..de19fa2d7f0d 100644
--- a/arch/loongarch/mm/tlbex.S
+++ b/arch/loongarch/mm/tlbex.S
@@ -18,7 +18,7 @@
 	REG_S	a2, sp, PT_BVADDR
 	li.w	a1, \write
 	la.abs	t0, do_page_fault
-	jirl    ra, t0, 0
+	jirl	ra, t0, 0
 	RESTORE_ALL_AND_RET
 	SYM_FUNC_END(tlb_do_page_fault_\write)
 	.endm
@@ -34,7 +34,7 @@ SYM_FUNC_START(handle_tlb_protect)
 	csrrd	a2, LOONGARCH_CSR_BADV
 	REG_S	a2, sp, PT_BVADDR
 	la.abs	t0, do_page_fault
-	jirl    ra, t0, 0
+	jirl	ra, t0, 0
 	RESTORE_ALL_AND_RET
 SYM_FUNC_END(handle_tlb_protect)
 
@@ -47,7 +47,7 @@ SYM_FUNC_START(handle_tlb_load)
 	 * The vmalloc handling is not in the hotpath.
 	 */
 	csrrd	t0, LOONGARCH_CSR_BADV
-	blt	t0, $r0, vmalloc_load
+	bltz	t0, vmalloc_load
 	csrrd	t1, LOONGARCH_CSR_PGDL
 
 vmalloc_done_load:
@@ -80,7 +80,7 @@ vmalloc_done_load:
 	 * see if we need to jump to huge tlb processing.
 	 */
 	andi	t0, ra, _PAGE_HUGE
-	bne	t0, $r0, tlb_huge_update_load
+	bnez	t0, tlb_huge_update_load
 
 	csrrd	t0, LOONGARCH_CSR_BADV
 	srli.d	t0, t0, (PAGE_SHIFT + PTE_ORDER)
@@ -100,12 +100,12 @@ smp_pgtable_change_load:
 
 	srli.d	ra, t0, _PAGE_PRESENT_SHIFT
 	andi	ra, ra, 1
-	beq	ra, $r0, nopage_tlb_load
+	beqz	ra, nopage_tlb_load
 
 	ori	t0, t0, _PAGE_VALID
 #ifdef CONFIG_SMP
 	sc.d	t0, t1, 0
-	beq	t0, $r0, smp_pgtable_change_load
+	beqz	t0, smp_pgtable_change_load
 #else
 	st.d	t0, t1, 0
 #endif
@@ -139,23 +139,23 @@ tlb_huge_update_load:
 #endif
 	srli.d	ra, t0, _PAGE_PRESENT_SHIFT
 	andi	ra, ra, 1
-	beq	ra, $r0, nopage_tlb_load
+	beqz	ra, nopage_tlb_load
 	tlbsrch
 
 	ori	t0, t0, _PAGE_VALID
 #ifdef CONFIG_SMP
 	sc.d	t0, t1, 0
-	beq	t0, $r0, tlb_huge_update_load
+	beqz	t0, tlb_huge_update_load
 	ld.d	t0, t1, 0
 #else
 	st.d	t0, t1, 0
 #endif
-	addu16i.d	t1, $r0, -(CSR_TLBIDX_EHINV >> 16)
-	addi.d	ra, t1, 0
-	csrxchg	ra, t1, LOONGARCH_CSR_TLBIDX
+	addu16i.d	t1, zero, -(CSR_TLBIDX_EHINV >> 16)
+	addi.d		ra, t1, 0
+	csrxchg		ra, t1, LOONGARCH_CSR_TLBIDX
 	tlbwr
 
-	csrxchg	$r0, t1, LOONGARCH_CSR_TLBIDX
+	csrxchg	zero, t1, LOONGARCH_CSR_TLBIDX
 
 	/*
 	 * A huge PTE describes an area the size of the
@@ -178,27 +178,27 @@ tlb_huge_update_load:
 	addi.d	t0, ra, 0
 
 	/* Convert to entrylo1 */
-	addi.d	t1, $r0, 1
+	addi.d	t1, zero, 1
 	slli.d	t1, t1, (HPAGE_SHIFT - 1)
 	add.d	t0, t0, t1
 	csrwr	t0, LOONGARCH_CSR_TLBELO1
 
 	/* Set huge page tlb entry size */
-	addu16i.d	t0, $r0, (CSR_TLBIDX_PS >> 16)
-	addu16i.d	t1, $r0, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
+	addu16i.d	t0, zero, (CSR_TLBIDX_PS >> 16)
+	addu16i.d	t1, zero, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
 	csrxchg		t1, t0, LOONGARCH_CSR_TLBIDX
 
 	tlbfill
 
-	addu16i.d	t0, $r0, (CSR_TLBIDX_PS >> 16)
-	addu16i.d	t1, $r0, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
+	addu16i.d	t0, zero, (CSR_TLBIDX_PS >> 16)
+	addu16i.d	t1, zero, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
 	csrxchg		t1, t0, LOONGARCH_CSR_TLBIDX
 
 nopage_tlb_load:
 	dbar	0
 	csrrd	ra, EXCEPTION_KS2
 	la.abs	t0, tlb_do_page_fault_0
-	jirl	$r0, t0, 0
+	jr	t0
 SYM_FUNC_END(handle_tlb_load)
 
 SYM_FUNC_START(handle_tlb_store)
@@ -210,7 +210,7 @@ SYM_FUNC_START(handle_tlb_store)
 	 * The vmalloc handling is not in the hotpath.
 	 */
 	csrrd	t0, LOONGARCH_CSR_BADV
-	blt	t0, $r0, vmalloc_store
+	bltz	t0, vmalloc_store
 	csrrd	t1, LOONGARCH_CSR_PGDL
 
 vmalloc_done_store:
@@ -244,7 +244,7 @@ vmalloc_done_store:
 	 * see if we need to jump to huge tlb processing.
 	 */
 	andi	t0, ra, _PAGE_HUGE
-	bne	t0, $r0, tlb_huge_update_store
+	bnez	t0, tlb_huge_update_store
 
 	csrrd	t0, LOONGARCH_CSR_BADV
 	srli.d	t0, t0, (PAGE_SHIFT + PTE_ORDER)
@@ -265,12 +265,12 @@ smp_pgtable_change_store:
 	srli.d	ra, t0, _PAGE_PRESENT_SHIFT
 	andi	ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT)
 	xori	ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT)
-	bne	ra, $r0, nopage_tlb_store
+	bnez	ra, nopage_tlb_store
 
 	ori	t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
 #ifdef CONFIG_SMP
 	sc.d	t0, t1, 0
-	beq	t0, $r0, smp_pgtable_change_store
+	beqz	t0, smp_pgtable_change_store
 #else
 	st.d	t0, t1, 0
 #endif
@@ -306,24 +306,24 @@ tlb_huge_update_store:
 	srli.d	ra, t0, _PAGE_PRESENT_SHIFT
 	andi	ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT)
 	xori	ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT)
-	bne	ra, $r0, nopage_tlb_store
+	bnez	ra, nopage_tlb_store
 
 	tlbsrch
 	ori	t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
 
 #ifdef CONFIG_SMP
 	sc.d	t0, t1, 0
-	beq	t0, $r0, tlb_huge_update_store
+	beqz	t0, tlb_huge_update_store
 	ld.d	t0, t1, 0
 #else
 	st.d	t0, t1, 0
 #endif
-	addu16i.d	t1, $r0, -(CSR_TLBIDX_EHINV >> 16)
-	addi.d	ra, t1, 0
-	csrxchg	ra, t1, LOONGARCH_CSR_TLBIDX
+	addu16i.d	t1, zero, -(CSR_TLBIDX_EHINV >> 16)
+	addi.d		ra, t1, 0
+	csrxchg		ra, t1, LOONGARCH_CSR_TLBIDX
 	tlbwr
 
-	csrxchg	$r0, t1, LOONGARCH_CSR_TLBIDX
+	csrxchg	zero, t1, LOONGARCH_CSR_TLBIDX
 	/*
 	 * A huge PTE describes an area the size of the
 	 * configured huge page size. This is twice the
@@ -345,28 +345,28 @@ tlb_huge_update_store:
 	addi.d	t0, ra, 0
 
 	/* Convert to entrylo1 */
-	addi.d	t1, $r0, 1
+	addi.d	t1, zero, 1
 	slli.d	t1, t1, (HPAGE_SHIFT - 1)
 	add.d	t0, t0, t1
 	csrwr	t0, LOONGARCH_CSR_TLBELO1
 
 	/* Set huge page tlb entry size */
-	addu16i.d	t0, $r0, (CSR_TLBIDX_PS >> 16)
-	addu16i.d	t1, $r0, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
+	addu16i.d	t0, zero, (CSR_TLBIDX_PS >> 16)
+	addu16i.d	t1, zero, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
 	csrxchg		t1, t0, LOONGARCH_CSR_TLBIDX
 
 	tlbfill
 
 	/* Reset default page size */
-	addu16i.d	t0, $r0, (CSR_TLBIDX_PS >> 16)
-	addu16i.d	t1, $r0, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
+	addu16i.d	t0, zero, (CSR_TLBIDX_PS >> 16)
+	addu16i.d	t1, zero, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
 	csrxchg		t1, t0, LOONGARCH_CSR_TLBIDX
 
 nopage_tlb_store:
 	dbar	0
 	csrrd	ra, EXCEPTION_KS2
 	la.abs	t0, tlb_do_page_fault_1
-	jirl	$r0, t0, 0
+	jr	t0
 SYM_FUNC_END(handle_tlb_store)
 
 SYM_FUNC_START(handle_tlb_modify)
@@ -378,7 +378,7 @@ SYM_FUNC_START(handle_tlb_modify)
 	 * The vmalloc handling is not in the hotpath.
 	 */
 	csrrd	t0, LOONGARCH_CSR_BADV
-	blt	t0, $r0, vmalloc_modify
+	bltz	t0, vmalloc_modify
 	csrrd	t1, LOONGARCH_CSR_PGDL
 
 vmalloc_done_modify:
@@ -411,7 +411,7 @@ vmalloc_done_modify:
 	 * see if we need to jump to huge tlb processing.
 	 */
 	andi	t0, ra, _PAGE_HUGE
-	bne	t0, $r0, tlb_huge_update_modify
+	bnez	t0, tlb_huge_update_modify
 
 	csrrd	t0, LOONGARCH_CSR_BADV
 	srli.d	t0, t0, (PAGE_SHIFT + PTE_ORDER)
@@ -431,12 +431,12 @@ smp_pgtable_change_modify:
 
 	srli.d	ra, t0, _PAGE_WRITE_SHIFT
 	andi	ra, ra, 1
-	beq	ra, $r0, nopage_tlb_modify
+	beqz	ra, nopage_tlb_modify
 
 	ori	t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
 #ifdef CONFIG_SMP
 	sc.d	t0, t1, 0
-	beq	t0, $r0, smp_pgtable_change_modify
+	beqz	t0, smp_pgtable_change_modify
 #else
 	st.d	t0, t1, 0
 #endif
@@ -454,7 +454,7 @@ leave_modify:
 	ertn
 #ifdef CONFIG_64BIT
 vmalloc_modify:
-	la.abs  t1, swapper_pg_dir
+	la.abs	t1, swapper_pg_dir
 	b	vmalloc_done_modify
 #endif
 
@@ -471,14 +471,14 @@ tlb_huge_update_modify:
 
 	srli.d	ra, t0, _PAGE_WRITE_SHIFT
 	andi	ra, ra, 1
-	beq	ra, $r0, nopage_tlb_modify
+	beqz	ra, nopage_tlb_modify
 
 	tlbsrch
 	ori	t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
 
 #ifdef CONFIG_SMP
 	sc.d	t0, t1, 0
-	beq	t0, $r0, tlb_huge_update_modify
+	beqz	t0, tlb_huge_update_modify
 	ld.d	t0, t1, 0
 #else
 	st.d	t0, t1, 0
@@ -504,28 +504,28 @@ tlb_huge_update_modify:
 	addi.d	t0, ra, 0
 
 	/* Convert to entrylo1 */
-	addi.d	t1, $r0, 1
+	addi.d	t1, zero, 1
 	slli.d	t1, t1, (HPAGE_SHIFT - 1)
 	add.d	t0, t0, t1
 	csrwr	t0, LOONGARCH_CSR_TLBELO1
 
 	/* Set huge page tlb entry size */
-	addu16i.d	t0, $r0, (CSR_TLBIDX_PS >> 16)
-	addu16i.d	t1, $r0, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
-	csrxchg	t1, t0, LOONGARCH_CSR_TLBIDX
+	addu16i.d	t0, zero, (CSR_TLBIDX_PS >> 16)
+	addu16i.d	t1, zero, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
+	csrxchg		t1, t0, LOONGARCH_CSR_TLBIDX
 
 	tlbwr
 
 	/* Reset default page size */
-	addu16i.d	t0, $r0, (CSR_TLBIDX_PS >> 16)
-	addu16i.d	t1, $r0, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
-	csrxchg	t1, t0, LOONGARCH_CSR_TLBIDX
+	addu16i.d	t0, zero, (CSR_TLBIDX_PS >> 16)
+	addu16i.d	t1, zero, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
+	csrxchg		t1, t0, LOONGARCH_CSR_TLBIDX
 
 nopage_tlb_modify:
 	dbar	0
 	csrrd	ra, EXCEPTION_KS2
 	la.abs	t0, tlb_do_page_fault_1
-	jirl	$r0, t0, 0
+	jr	t0
 SYM_FUNC_END(handle_tlb_modify)
 
 SYM_FUNC_START(handle_tlb_refill)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index c235648fae23..4d8f26c1399b 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -282,6 +282,10 @@ config PPC
 	# Please keep this list sorted alphabetically.
 	#
 
+config PPC_LONG_DOUBLE_128
+	depends on PPC64
+	def_bool $(success,test "$(shell,echo __LONG_DOUBLE_128__ | $(CC) -E -P -)" = 1)
+
 config PPC_BARRIER_NOSPEC
 	bool
 	default y
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index f91f0f29a566..c8cf924bf9c0 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -20,6 +20,7 @@ CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
 CFLAGS_prom_init.o += -fno-stack-protector
 CFLAGS_prom_init.o += -DDISABLE_BRANCH_PROFILING
 CFLAGS_prom_init.o += -ffreestanding
+CFLAGS_prom_init.o += $(call cc-option, -ftrivial-auto-var-init=uninitialized)
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace early boot code
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index a4c46a03d2e2..81029d40a672 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -111,7 +111,7 @@ PHONY += vdso_install
 vdso_install:
 	$(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso $@
 	$(if $(CONFIG_COMPAT),$(Q)$(MAKE) \
-		$(build)=arch/riscv/kernel/compat_vdso $@)
+		$(build)=arch/riscv/kernel/compat_vdso compat_$@)
 
 ifeq ($(KBUILD_EXTMOD),)
 ifeq ($(CONFIG_MMU),y)
diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index 0ba0598eba20..ec6771e87e73 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -6,7 +6,7 @@ config DRM_AMD_DC
 	bool "AMD DC - Enable new display engine"
 	default y
 	select SND_HDA_COMPONENT if SND_HDA_CORE
-	select DRM_AMD_DC_DCN if X86 && !(KCOV_INSTRUMENT_ALL && KCOV_ENABLE_COMPARISONS)
+	select DRM_AMD_DC_DCN if (X86 || PPC_LONG_DOUBLE_128) && !(KCOV_INSTRUMENT_ALL && KCOV_ENABLE_COMPARISONS)
 	help
 	  Choose this option if you want to use the new display engine
 	  support for AMDGPU. This adds required support for Vega and
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index 7ba66ad68a8a..16356611b5b9 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -680,7 +680,11 @@ nouveau_dmem_migrate_vma(struct nouveau_drm *drm,
 		goto out_free_dma;
 
 	for (i = 0; i < npages; i += max) {
-		args.end = start + (max << PAGE_SHIFT);
+		if (args.start + (max << PAGE_SHIFT) > end)
+			args.end = end;
+		else
+			args.end = args.start + (max << PAGE_SHIFT);
+
 		ret = migrate_vma_setup(&args);
 		if (ret)
 			goto out_free_pfns;
diff --git a/drivers/gpu/drm/tiny/simpledrm.c b/drivers/gpu/drm/tiny/simpledrm.c
index 768242a78e2b..5422363690e7 100644
--- a/drivers/gpu/drm/tiny/simpledrm.c
+++ b/drivers/gpu/drm/tiny/simpledrm.c
@@ -627,7 +627,7 @@ static const struct drm_connector_funcs simpledrm_connector_funcs = {
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 };
 
-static int
+static enum drm_mode_status
 simpledrm_simple_display_pipe_mode_valid(struct drm_simple_display_pipe *pipe,
 				    const struct drm_display_mode *mode)
 {
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index f5c6802aa6c3..907700d1e78e 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -162,7 +162,13 @@ static __cpuidle int intel_idle_irq(struct cpuidle_device *dev,
 
 	raw_local_irq_enable();
 	ret = __intel_idle(dev, drv, index);
-	raw_local_irq_disable();
+
+	/*
+	 * The lockdep hardirqs state may be changed to 'on' with timer
+	 * tick interrupt followed by __do_softirq(). Use local_irq_disable()
+	 * to keep the hardirqs state correct.
+	 */
+	local_irq_disable();
 
 	return ret;
 }
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 58c72d55769a..73d9fcba3b1c 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3515,6 +3515,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1e49, 0x0041),   /* ZHITAI TiPro7000 NVMe SSD */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
+	{ PCI_DEVICE(0xc0a9, 0x540a),   /* Crucial P2 */
+		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061),
 		.driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065),
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index b519f4b59d30..5e8887fa02c8 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -11386,6 +11386,7 @@ scsih_shutdown(struct pci_dev *pdev)
 	_scsih_ir_shutdown(ioc);
 	_scsih_nvme_shutdown(ioc);
 	mpt3sas_base_mask_interrupts(ioc);
+	mpt3sas_base_stop_watchdog(ioc);
 	ioc->shost_recovery = 1;
 	mpt3sas_base_make_ioc_ready(ioc, SOFT_RESET);
 	ioc->shost_recovery = 0;
diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c
index a480c4d589f5..729e309e6034 100644
--- a/drivers/scsi/scsi_ioctl.c
+++ b/drivers/scsi/scsi_ioctl.c
@@ -450,7 +450,7 @@ static int sg_io(struct scsi_device *sdev, struct sg_io_hdr *hdr, fmode_t mode)
 		goto out_put_request;
 
 	ret = 0;
-	if (hdr->iovec_count) {
+	if (hdr->iovec_count && hdr->dxfer_len) {
 		struct iov_iter i;
 		struct iovec *iov = NULL;
 
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 5de42023cf0c..3f347d03f9fc 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -2973,37 +2973,59 @@ ufshcd_dev_cmd_completion(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 static int ufshcd_wait_for_dev_cmd(struct ufs_hba *hba,
 		struct ufshcd_lrb *lrbp, int max_timeout)
 {
-	int err = 0;
-	unsigned long time_left;
+	unsigned long time_left = msecs_to_jiffies(max_timeout);
 	unsigned long flags;
+	bool pending;
+	int err;
 
+retry:
 	time_left = wait_for_completion_timeout(hba->dev_cmd.complete,
-			msecs_to_jiffies(max_timeout));
+						time_left);
 
-	spin_lock_irqsave(hba->host->host_lock, flags);
-	hba->dev_cmd.complete = NULL;
 	if (likely(time_left)) {
+		/*
+		 * The completion handler called complete() and the caller of
+		 * this function still owns the @lrbp tag so the code below does
+		 * not trigger any race conditions.
+		 */
+		hba->dev_cmd.complete = NULL;
 		err = ufshcd_get_tr_ocs(lrbp);
 		if (!err)
 			err = ufshcd_dev_cmd_completion(hba, lrbp);
-	}
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
-
-	if (!time_left) {
+	} else {
 		err = -ETIMEDOUT;
 		dev_dbg(hba->dev, "%s: dev_cmd request timedout, tag %d\n",
 			__func__, lrbp->task_tag);
-		if (!ufshcd_clear_cmds(hba, 1U << lrbp->task_tag))
+		if (ufshcd_clear_cmds(hba, 1U << lrbp->task_tag) == 0) {
 			/* successfully cleared the command, retry if needed */
 			err = -EAGAIN;
-		/*
-		 * in case of an error, after clearing the doorbell,
-		 * we also need to clear the outstanding_request
-		 * field in hba
-		 */
-		spin_lock_irqsave(&hba->outstanding_lock, flags);
-		__clear_bit(lrbp->task_tag, &hba->outstanding_reqs);
-		spin_unlock_irqrestore(&hba->outstanding_lock, flags);
+			/*
+			 * Since clearing the command succeeded we also need to
+			 * clear the task tag bit from the outstanding_reqs
+			 * variable.
+			 */
+			spin_lock_irqsave(&hba->outstanding_lock, flags);
+			pending = test_bit(lrbp->task_tag,
+					   &hba->outstanding_reqs);
+			if (pending) {
+				hba->dev_cmd.complete = NULL;
+				__clear_bit(lrbp->task_tag,
+					    &hba->outstanding_reqs);
+			}
+			spin_unlock_irqrestore(&hba->outstanding_lock, flags);
+
+			if (!pending) {
+				/*
+				 * The completion handler ran while we tried to
+				 * clear the command.
+				 */
+				time_left = 1;
+				goto retry;
+			}
+		} else {
+			dev_err(hba->dev, "%s: failed to clear tag %d\n",
+				__func__, lrbp->task_tag);
+		}
 	}
 
 	return err;
diff --git a/drivers/ufs/host/ufshcd-pltfrm.c b/drivers/ufs/host/ufshcd-pltfrm.c
index e7332cc65b1f..173aea8e9997 100644
--- a/drivers/ufs/host/ufshcd-pltfrm.c
+++ b/drivers/ufs/host/ufshcd-pltfrm.c
@@ -108,9 +108,20 @@ static int ufshcd_parse_clock_info(struct ufs_hba *hba)
 	return ret;
 }
 
+static bool phandle_exists(const struct device_node *np,
+			   const char *phandle_name, int index)
+{
+	struct device_node *parse_np = of_parse_phandle(np, phandle_name, index);
+
+	if (parse_np)
+		of_node_put(parse_np);
+
+	return parse_np != NULL;
+}
+
 #define MAX_PROP_SIZE 32
 static int ufshcd_populate_vreg(struct device *dev, const char *name,
-		struct ufs_vreg **out_vreg)
+				struct ufs_vreg **out_vreg)
 {
 	char prop_name[MAX_PROP_SIZE];
 	struct ufs_vreg *vreg = NULL;
@@ -122,7 +133,7 @@ static int ufshcd_populate_vreg(struct device *dev, const char *name,
 	}
 
 	snprintf(prop_name, MAX_PROP_SIZE, "%s-supply", name);
-	if (!of_parse_phandle(np, prop_name, 0)) {
+	if (!phandle_exists(np, prop_name, 0)) {
 		dev_info(dev, "%s: Unable to find %s regulator, assuming enabled\n",
 				__func__, prop_name);
 		goto out;
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 19f0dbfdd7fe..b66c5f389159 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -130,7 +130,6 @@ enum cpuhp_state {
 	CPUHP_ZCOMP_PREPARE,
 	CPUHP_TIMERS_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
-	CPUHP_LOONGARCH_SOC_PREPARE,
 	CPUHP_BP_PREPARE_DYN,
 	CPUHP_BP_PREPARE_DYN_END		= CPUHP_BP_PREPARE_DYN + 20,
 	CPUHP_BRINGUP_CPU,
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 8d33b7d2260c..aa68dde03aa6 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -5005,7 +5005,10 @@ static void unbind_workers(int cpu)
 
 		for_each_pool_worker(worker, pool) {
 			kthread_set_per_cpu(worker->task, -1);
-			WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, wq_unbound_cpumask) < 0);
+			if (cpumask_intersects(wq_unbound_cpumask, cpu_active_mask))
+				WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, wq_unbound_cpumask) < 0);
+			else
+				WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0);
 		}
 
 		mutex_unlock(&wq_pool_attach_mutex);
diff --git a/mm/hmm.c b/mm/hmm.c
index 3fd3242c5e50..f2aa63b94d9b 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -212,14 +212,6 @@ int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
 		unsigned long end, unsigned long hmm_pfns[], pmd_t pmd);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-static inline bool hmm_is_device_private_entry(struct hmm_range *range,
-		swp_entry_t entry)
-{
-	return is_device_private_entry(entry) &&
-		pfn_swap_entry_to_page(entry)->pgmap->owner ==
-		range->dev_private_owner;
-}
-
 static inline unsigned long pte_to_hmm_pfn_flags(struct hmm_range *range,
 						 pte_t pte)
 {
@@ -252,10 +244,12 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 		swp_entry_t entry = pte_to_swp_entry(pte);
 
 		/*
-		 * Never fault in device private pages, but just report
-		 * the PFN even if not present.
+		 * Don't fault in device private pages owned by the caller,
+		 * just report the PFN.
 		 */
-		if (hmm_is_device_private_entry(range, entry)) {
+		if (is_device_private_entry(entry) &&
+		    pfn_swap_entry_to_page(entry)->pgmap->owner ==
+		    range->dev_private_owner) {
 			cpu_flags = HMM_PFN_VALID;
 			if (is_writable_device_private_entry(entry))
 				cpu_flags |= HMM_PFN_WRITE;
@@ -273,6 +267,9 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 		if (!non_swap_entry(entry))
 			goto fault;
 
+		if (is_device_private_entry(entry))
+			goto fault;
+
 		if (is_device_exclusive_entry(entry))
 			goto fault;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e008a3df0485..b5b14b78c4fd 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3968,11 +3968,15 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
 	 * need to be calculated.
 	 */
 	if (!order) {
-		long fast_free;
+		long usable_free;
+		long reserved;
 
-		fast_free = free_pages;
-		fast_free -= __zone_watermark_unusable_free(z, 0, alloc_flags);
-		if (fast_free > mark + z->lowmem_reserve[highest_zoneidx])
+		usable_free = free_pages;
+		reserved = __zone_watermark_unusable_free(z, 0, alloc_flags);
+
+		/* reserved may over estimate high-atomic reserves. */
+		usable_free -= min(usable_free, reserved);
+		if (usable_free > mark + z->lowmem_reserve[highest_zoneidx])
 			return true;
 	}
 
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 00f5227c8459..a77b915d36a8 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -302,6 +302,7 @@
 #define X86_FEATURE_RETPOLINE_LFENCE	(11*32+13) /* "" Use LFENCE for Spectre variant 2 */
 #define X86_FEATURE_RETHUNK		(11*32+14) /* "" Use REturn THUNK */
 #define X86_FEATURE_UNRET		(11*32+15) /* "" AMD BTB untrain return */
+#define X86_FEATURE_USE_IBPB_FW		(11*32+16) /* "" Use IBPB during runtime firmware calls */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
diff --git a/tools/perf/scripts/python/arm-cs-trace-disasm.py b/tools/perf/scripts/python/arm-cs-trace-disasm.py
index 5f57d9829956..4339692a8d0b 100755
--- a/tools/perf/scripts/python/arm-cs-trace-disasm.py
+++ b/tools/perf/scripts/python/arm-cs-trace-disasm.py
@@ -61,7 +61,7 @@ def get_optional(perf_dict, field):
 
 def get_offset(perf_dict, field):
 	if field in perf_dict:
-		return f"+0x{perf_dict[field]:x}"
+		return "+%#x" % perf_dict[field]
 	return ""
 
 def get_dso_file_path(dso_name, dso_build_id):
@@ -76,7 +76,7 @@ def get_dso_file_path(dso_name, dso_build_id):
 	else:
 		append = "/elf"
 
-	dso_path = f"{os.environ['PERF_BUILDID_DIR']}/{dso_name}/{dso_build_id}{append}"
+	dso_path = os.environ['PERF_BUILDID_DIR'] + "/" + dso_name + "/" + dso_build_id + append;
 	# Replace duplicate slash chars to single slash char
 	dso_path = dso_path.replace('//', '/', 1)
 	return dso_path
@@ -94,8 +94,8 @@ def read_disam(dso_fname, dso_start, start_addr, stop_addr):
 		start_addr = start_addr - dso_start;
 		stop_addr = stop_addr - dso_start;
 		disasm = [ options.objdump_name, "-d", "-z",
-			   f"--start-address=0x{start_addr:x}",
-			   f"--stop-address=0x{stop_addr:x}" ]
+			   "--start-address="+format(start_addr,"#x"),
+			   "--stop-address="+format(stop_addr,"#x") ]
 		disasm += [ dso_fname ]
 		disasm_output = check_output(disasm).decode('utf-8').split('\n')
 		disasm_cache[addr_range] = disasm_output
@@ -109,12 +109,14 @@ def print_disam(dso_fname, dso_start, start_addr, stop_addr):
 			m = disasm_re.search(line)
 			if m is None:
 				continue
-		print(f"\t{line}")
+		print("\t" + line)
 
 def print_sample(sample):
-	print(f"Sample = {{ cpu: {sample['cpu']:04} addr: 0x{sample['addr']:016x} " \
-	      f"phys_addr: 0x{sample['phys_addr']:016x} ip: 0x{sample['ip']:016x} " \
-	      f"pid: {sample['pid']} tid: {sample['tid']} period: {sample['period']} time: {sample['time']} }}")
+	print("Sample = { cpu: %04d addr: 0x%016x phys_addr: 0x%016x ip: 0x%016x " \
+	      "pid: %d tid: %d period: %d time: %d }" % \
+	      (sample['cpu'], sample['addr'], sample['phys_addr'], \
+	       sample['ip'], sample['pid'], sample['tid'], \
+	       sample['period'], sample['time']))
 
 def trace_begin():
 	print('ARM CoreSight Trace Data Assembler Dump')
@@ -131,7 +133,7 @@ def common_start_str(comm, sample):
 	cpu = sample["cpu"]
 	pid = sample["pid"]
 	tid = sample["tid"]
-	return f"{comm:>16} {pid:>5}/{tid:<5} [{cpu:04}] {sec:9}.{ns:09}  "
+	return "%16s %5u/%-5u [%04u] %9u.%09u  " % (comm, pid, tid, cpu, sec, ns)
 
 # This code is copied from intel-pt-events.py for printing source code
 # line and symbols.
@@ -171,7 +173,7 @@ def print_srccode(comm, param_dict, sample, symbol, dso):
 	glb_line_number = line_number
 	glb_source_file_name = source_file_name
 
-	print(f"{start_str}{src_str}")
+	print(start_str, src_str)
 
 def process_event(param_dict):
 	global cache_size
@@ -188,7 +190,7 @@ def process_event(param_dict):
 	symbol = get_optional(param_dict, "symbol")
 
 	if (options.verbose == True):
-		print(f"Event type: {name}")
+		print("Event type: %s" % name)
 		print_sample(sample)
 
 	# If cannot find dso so cannot dump assembler, bail out
@@ -197,7 +199,7 @@ def process_event(param_dict):
 
 	# Validate dso start and end addresses
 	if ((dso_start == '[unknown]') or (dso_end == '[unknown]')):
-		print(f"Failed to find valid dso map for dso {dso}")
+		print("Failed to find valid dso map for dso %s" % dso)
 		return
 
 	if (name[0:12] == "instructions"):
@@ -244,15 +246,15 @@ def process_event(param_dict):
 
 	# Handle CS_ETM_TRACE_ON packet if start_addr=0 and stop_addr=4
 	if (start_addr == 0 and stop_addr == 4):
-		print(f"CPU{cpu}: CS_ETM_TRACE_ON packet is inserted")
+		print("CPU%d: CS_ETM_TRACE_ON packet is inserted" % cpu)
 		return
 
 	if (start_addr < int(dso_start) or start_addr > int(dso_end)):
-		print(f"Start address 0x{start_addr:x} is out of range [ 0x{dso_start:x} .. 0x{dso_end:x} ] for dso {dso}")
+		print("Start address 0x%x is out of range [ 0x%x .. 0x%x ] for dso %s" % (start_addr, int(dso_start), int(dso_end), dso))
 		return
 
 	if (stop_addr < int(dso_start) or stop_addr > int(dso_end)):
-		print(f"Stop address 0x{stop_addr:x} is out of range [ 0x{dso_start:x} .. 0x{dso_end:x} ] for dso {dso}")
+		print("Stop address 0x%x is out of range [ 0x%x .. 0x%x ] for dso %s" % (stop_addr, int(dso_start), int(dso_end), dso))
 		return
 
 	if (options.objdump_name != None):
@@ -267,6 +269,6 @@ def process_event(param_dict):
 		if path.exists(dso_fname):
 			print_disam(dso_fname, dso_vm_start, start_addr, stop_addr)
 		else:
-			print(f"Failed to find dso {dso} for address range [ 0x{start_addr:x} .. 0x{stop_addr:x} ]")
+			print("Failed to find dso %s for address range [ 0x%x .. 0x%x ]" % (dso, start_addr, stop_addr))
 
 	print_srccode(comm, param_dict, sample, symbol, dso)
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index f8ad581ea247..cdd6463a5b68 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -63,20 +63,16 @@ static struct hashmap *bpf_map_hash;
 static struct bpf_perf_object *
 bpf_perf_object__next(struct bpf_perf_object *prev)
 {
-	struct bpf_perf_object *next;
+	if (!prev) {
+		if (list_empty(&bpf_objects_list))
+			return NULL;
 
-	if (!prev)
-		next = list_first_entry(&bpf_objects_list,
-					struct bpf_perf_object,
-					list);
-	else
-		next = list_next_entry(prev, list);
-
-	/* Empty list is noticed here so don't need checking on entry. */
-	if (&next->list == &bpf_objects_list)
+		return list_first_entry(&bpf_objects_list, struct bpf_perf_object, list);
+	}
+	if (list_is_last(&prev->list, &bpf_objects_list))
 		return NULL;
 
-	return next;
+	return list_next_entry(prev, list);
 }
 
 #define bpf_perf_object__for_each(perf_obj, tmp)	\
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index ecd377938eea..b3be5b1d9dbb 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -233,6 +233,33 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
 	return NULL;
 }
 
+static int elf_read_program_header(Elf *elf, u64 vaddr, GElf_Phdr *phdr)
+{
+	size_t i, phdrnum;
+	u64 sz;
+
+	if (elf_getphdrnum(elf, &phdrnum))
+		return -1;
+
+	for (i = 0; i < phdrnum; i++) {
+		if (gelf_getphdr(elf, i, phdr) == NULL)
+			return -1;
+
+		if (phdr->p_type != PT_LOAD)
+			continue;
+
+		sz = max(phdr->p_memsz, phdr->p_filesz);
+		if (!sz)
+			continue;
+
+		if (vaddr >= phdr->p_vaddr && (vaddr < phdr->p_vaddr + sz))
+			return 0;
+	}
+
+	/* Not found any valid program header */
+	return -1;
+}
+
 static bool want_demangle(bool is_kernel_sym)
 {
 	return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
@@ -1209,6 +1236,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 					sym.st_value);
 			used_opd = true;
 		}
+
 		/*
 		 * When loading symbols in a data mapping, ABS symbols (which
 		 * has a value of SHN_ABS in its st_shndx) failed at
@@ -1227,6 +1255,17 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 
 		gelf_getshdr(sec, &shdr);
 
+		/*
+		 * If the attribute bit SHF_ALLOC is not set, the section
+		 * doesn't occupy memory during process execution.
+		 * E.g. ".gnu.warning.*" section is used by linker to generate
+		 * warnings when calling deprecated functions, the symbols in
+		 * the section aren't loaded to memory during process execution,
+		 * so skip them.
+		 */
+		if (!(shdr.sh_flags & SHF_ALLOC))
+			continue;
+
 		secstrs = secstrs_sym;
 
 		/*
@@ -1262,11 +1301,20 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 				goto out_elf_end;
 		} else if ((used_opd && runtime_ss->adjust_symbols) ||
 			   (!used_opd && syms_ss->adjust_symbols)) {
+			GElf_Phdr phdr;
+
+			if (elf_read_program_header(syms_ss->elf,
+						    (u64)sym.st_value, &phdr)) {
+				pr_warning("%s: failed to find program header for "
+					   "symbol: %s st_value: %#" PRIx64 "\n",
+					   __func__, elf_name, (u64)sym.st_value);
+				continue;
+			}
 			pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
-				  "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__,
-				  (u64)sym.st_value, (u64)shdr.sh_addr,
-				  (u64)shdr.sh_offset);
-			sym.st_value -= shdr.sh_addr - shdr.sh_offset;
+				  "p_vaddr: %#" PRIx64 " p_offset: %#" PRIx64 "\n",
+				  __func__, (u64)sym.st_value, (u64)phdr.p_vaddr,
+				  (u64)phdr.p_offset);
+			sym.st_value -= phdr.p_vaddr - phdr.p_offset;
 		}
 
 		demangled = demangle_sym(dso, kmodule, elf_name);