Merge tag 'loongarch-7.2' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson

Pull LoongArch updates from Huacai Chen:

 - Add THREAD_INFO_IN_TASK implementation

 - Add build salt to the vDSO

 - Add some BPF JIT inline helpers

 - Update DTS for I2C clocks and clock-frequency

 - Some bug fixes and other small changes

* tag 'loongarch-7.2' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson:
  selftests/bpf: Test jited inline of bpf_get_smp_processor_id() for LoongArch
  selftests/bpf: Test jited inline of bpf_get_current_task() for LoongArch
  selftests/bpf: Add __arch_loongarch to limit test cases for LoongArch
  selftests/bpf: Add get_preempt_count() support for LoongArch
  LoongArch: dts: Add i2c clocks and clock-frequency properties to LS2K2000
  LoongArch: dts: Add i2c clocks and clock-frequency properties to LS2K1000
  LoongArch: dts: Add i2c clocks and clock-frequency properties to LS2K0500
  LoongArch: BPF: Inline bpf_get_smp_processor_id() helper
  LoongArch: BPF: Inline bpf_get_current_task/_btf() helpers
  LoongArch: BPF: Fix off-by-one error in tail call
  LoongArch: BPF: Fix outdated tail call comments
  LoongArch: Add build salt to the vDSO
  LoongArch: Fix nr passing in set_direct_map_valid_noflush()
  LoongArch: Fix missing dirty page tracking in {pte,pmd}_wrprotect()
  LoongArch: Move struct kimage forward declaration before use
  LoongArch: Report dying CPU to RCU in stop_this_cpu()
  LoongArch: Add PIO for early access before ACPI PCI root register
  LoongArch: Add THREAD_INFO_IN_TASK implementation

32 files changed, 226 insertions, 50 deletions

diff --git a/Documentation/features/core/thread-info-in-task/arch-support.txt b/Documentation/features/core/thread-info-in-task/arch-support.txt
index f3d744c76061..e26efdfbb6b4 100644
--- a/Documentation/features/core/thread-info-in-task/arch-support.txt
+++ b/Documentation/features/core/thread-info-in-task/arch-support.txt
@@ -12,7 +12,7 @@
     |       arm64: |  ok  |
     |        csky: | TODO |
     |     hexagon: | TODO |
-    |   loongarch: | TODO |
+    |   loongarch: |  ok  |
     |        m68k: | TODO |
     |  microblaze: | TODO |
     |        mips: | TODO |
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index bec7cc1d72ee..d8d252325017 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -209,6 +209,7 @@ config LOONGARCH
 	select SYSCTL_ARCH_UNALIGN_NO_WARN
 	select SYSCTL_EXCEPTION_TRACE
 	select SWIOTLB if 64BIT
+	select THREAD_INFO_IN_TASK
 	select TRACE_IRQFLAGS_SUPPORT
 	select USE_PERCPU_NUMA_NODE_ID
 	select USER_STACKTRACE_SUPPORT
diff --git a/arch/loongarch/boot/dts/loongson-2k0500.dtsi b/arch/loongarch/boot/dts/loongson-2k0500.dtsi
index 1b502064df11..992b1d0de9ec 100644
--- a/arch/loongarch/boot/dts/loongson-2k0500.dtsi
+++ b/arch/loongarch/boot/dts/loongson-2k0500.dtsi
@@ -405,6 +405,8 @@
 		i2c0: i2c@1ff48000 {
 			compatible = "loongson,ls2k-i2c";
 			reg = <0x0 0x1ff48000 0x0 0x0800>;
+			clock-frequency = <100000>;
+			clocks = <&clk LOONGSON2_APB_CLK>;
 			interrupt-parent = <&eiointc>;
 			interrupts = <14>;
 			status = "disabled";
@@ -413,6 +415,8 @@
 		i2c@1ff48800 {
 			compatible = "loongson,ls2k-i2c";
 			reg = <0x0 0x1ff48800 0x0 0x0800>;
+			clock-frequency = <100000>;
+			clocks = <&clk LOONGSON2_APB_CLK>;
 			interrupt-parent = <&eiointc>;
 			interrupts = <15>;
 			status = "disabled";
@@ -421,6 +425,8 @@
 		i2c@1ff49000 {
 			compatible = "loongson,ls2k-i2c";
 			reg = <0x0 0x1ff49000 0x0 0x0800>;
+			clock-frequency = <100000>;
+			clocks = <&clk LOONGSON2_APB_CLK>;
 			interrupt-parent = <&eiointc>;
 			interrupts = <16>;
 			status = "disabled";
@@ -429,6 +435,8 @@
 		i2c@1ff49800 {
 			compatible = "loongson,ls2k-i2c";
 			reg = <0x0 0x1ff49800 0x0 0x0800>;
+			clock-frequency = <100000>;
+			clocks = <&clk LOONGSON2_APB_CLK>;
 			interrupt-parent = <&eiointc>;
 			interrupts = <17>;
 			status = "disabled";
@@ -437,6 +445,8 @@
 		i2c@1ff4a000 {
 			compatible = "loongson,ls2k-i2c";
 			reg = <0x0 0x1ff4a000 0x0 0x0800>;
+			clock-frequency = <100000>;
+			clocks = <&clk LOONGSON2_APB_CLK>;
 			interrupt-parent = <&eiointc>;
 			interrupts = <18>;
 			status = "disabled";
@@ -445,6 +455,8 @@
 		i2c@1ff4a800 {
 			compatible = "loongson,ls2k-i2c";
 			reg = <0x0 0x1ff4a800 0x0 0x0800>;
+			clock-frequency = <100000>;
+			clocks = <&clk LOONGSON2_APB_CLK>;
 			interrupt-parent = <&eiointc>;
 			interrupts = <19>;
 			status = "disabled";
diff --git a/arch/loongarch/boot/dts/loongson-2k1000.dtsi b/arch/loongarch/boot/dts/loongson-2k1000.dtsi
index ab6a55937e9e..e6f0fe093ab3 100644
--- a/arch/loongarch/boot/dts/loongson-2k1000.dtsi
+++ b/arch/loongarch/boot/dts/loongson-2k1000.dtsi
@@ -311,6 +311,8 @@
 		i2c2: i2c@1fe21000 {
 			compatible = "loongson,ls2k-i2c";
 			reg = <0x0 0x1fe21000 0x0 0x8>;
+			clock-frequency = <100000>;
+			clocks = <&clk LOONGSON2_APB_CLK>;
 			interrupt-parent = <&liointc0>;
 			interrupts = <22 IRQ_TYPE_LEVEL_HIGH>;
 			status = "disabled";
@@ -319,6 +321,8 @@
 		i2c3: i2c@1fe21800 {
 			compatible = "loongson,ls2k-i2c";
 			reg = <0x0 0x1fe21800 0x0 0x8>;
+			clock-frequency = <100000>;
+			clocks = <&clk LOONGSON2_APB_CLK>;
 			interrupt-parent = <&liointc0>;
 			interrupts = <23 IRQ_TYPE_LEVEL_HIGH>;
 			status = "disabled";
diff --git a/arch/loongarch/boot/dts/loongson-2k2000.dtsi b/arch/loongarch/boot/dts/loongson-2k2000.dtsi
index 3678c084adf7..7fdc4192d2f2 100644
--- a/arch/loongarch/boot/dts/loongson-2k2000.dtsi
+++ b/arch/loongarch/boot/dts/loongson-2k2000.dtsi
@@ -239,6 +239,8 @@
 		i2c@1fe00120 {
 			compatible = "loongson,ls2k-i2c";
 			reg = <0x0 0x1fe00120 0x0 0x8>;
+			clock-frequency = <100000>;
+			clocks = <&clk LOONGSON2_MISC_CLK>;
 			interrupt-parent = <&liointc>;
 			interrupts = <8 IRQ_TYPE_LEVEL_HIGH>;
 			status = "disabled";
@@ -247,6 +249,8 @@
 		i2c@1fe00130 {
 			compatible = "loongson,ls2k-i2c";
 			reg = <0x0 0x1fe00130 0x0 0x8>;
+			clock-frequency = <100000>;
+			clocks = <&clk LOONGSON2_MISC_CLK>;
 			interrupt-parent = <&liointc>;
 			interrupts = <9 IRQ_TYPE_LEVEL_HIGH>;
 			status = "disabled";
diff --git a/arch/loongarch/include/asm/acpi.h b/arch/loongarch/include/asm/acpi.h
index eda9d4d0a493..c05168aedcaa 100644
--- a/arch/loongarch/include/asm/acpi.h
+++ b/arch/loongarch/include/asm/acpi.h
@@ -38,6 +38,8 @@ static inline bool acpi_has_cpu_in_madt(void)
 extern struct list_head acpi_wakeup_device_list;
 extern struct acpi_madt_core_pic acpi_core_pic[MAX_CORE_PIC];
 
+extern void acpi_add_early_pio(void);
+extern void acpi_remove_early_pio(void);
 extern int __init parse_acpi_topology(void);
 
 #endif /* !CONFIG_ACPI */
diff --git a/arch/loongarch/include/asm/current.h b/arch/loongarch/include/asm/current.h
new file mode 100644
index 000000000000..fa4fb7987075
--- /dev/null
+++ b/arch/loongarch/include/asm/current.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_LOONGARCH_CURRENT_H
+#define __ASM_LOONGARCH_CURRENT_H
+
+#include <linux/compiler.h>
+
+#ifndef __ASSEMBLER__
+
+#include <asm/percpu.h>
+
+struct task_struct;
+
+DECLARE_PER_CPU(struct task_struct *, cpu_tasks);
+
+register struct task_struct *current_thread_pointer __asm__("$tp");
+
+static __always_inline struct task_struct *get_current(void)
+{
+	return current_thread_pointer;
+}
+
+#define current get_current()
+
+static __always_inline void set_current(struct task_struct *task)
+{
+	__this_cpu_write(cpu_tasks, task);
+}
+
+#endif /* __ASSEMBLER__ */
+
+#endif /* __ASM_LOONGARCH_CURRENT_H */
diff --git a/arch/loongarch/include/asm/kexec.h b/arch/loongarch/include/asm/kexec.h
index 209fa43222e1..6be136e9f0a0 100644
--- a/arch/loongarch/include/asm/kexec.h
+++ b/arch/loongarch/include/asm/kexec.h
@@ -41,6 +41,8 @@ struct kimage_arch {
 	unsigned long systable_ptr;
 };
 
+struct kimage;
+
 #ifdef CONFIG_KEXEC_FILE
 extern const struct kexec_file_ops kexec_efi_ops;
 extern const struct kexec_file_ops kexec_elf_ops;
@@ -59,7 +61,6 @@ typedef void (*do_kexec_t)(unsigned long efi_boot,
 			   unsigned long start_addr,
 			   unsigned long first_ind_entry);
 
-struct kimage;
 extern const unsigned char relocate_new_kernel[];
 extern const size_t relocate_new_kernel_size;
 extern void kexec_reboot(void);
diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h
index 583f2466262f..500c51754ea5 100644
--- a/arch/loongarch/include/asm/percpu.h
+++ b/arch/loongarch/include/asm/percpu.h
@@ -5,7 +5,6 @@
 #ifndef __ASM_PERCPU_H
 #define __ASM_PERCPU_H
 
-#include <asm/cmpxchg.h>
 #include <asm/loongarch.h>
 
 /*
diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index 2a0b63ae421f..223528c04d73 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -429,6 +429,8 @@ static inline pte_t pte_mkwrite_novma(pte_t pte)
 
 static inline pte_t pte_wrprotect(pte_t pte)
 {
+	if (pte_val(pte) & _PAGE_DIRTY)
+		pte_val(pte) |= _PAGE_MODIFIED;
 	pte_val(pte) &= ~(_PAGE_WRITE | _PAGE_DIRTY);
 	return pte;
 }
@@ -535,6 +537,8 @@ static inline pmd_t pmd_mkwrite_novma(pmd_t pmd)
 
 static inline pmd_t pmd_wrprotect(pmd_t pmd)
 {
+	if (pmd_val(pmd) & _PAGE_DIRTY)
+		pmd_val(pmd) |= _PAGE_MODIFIED;
 	pmd_val(pmd) &= ~(_PAGE_WRITE | _PAGE_DIRTY);
 	return pmd;
 }
diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h
index 3a47f52959a8..dd1457065690 100644
--- a/arch/loongarch/include/asm/smp.h
+++ b/arch/loongarch/include/asm/smp.h
@@ -81,8 +81,9 @@ extern int __cpu_logical_map[NR_CPUS];
 struct seq_file;
 
 struct secondary_data {
+	unsigned long task;
 	unsigned long stack;
-	unsigned long thread_info;
+	unsigned long offset;
 };
 extern struct secondary_data cpuboot_data;
 
diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h
index ecc8e50fffa8..79526fa423a7 100644
--- a/arch/loongarch/include/asm/stackframe.h
+++ b/arch/loongarch/include/asm/stackframe.h
@@ -184,6 +184,7 @@
 	.cfi_rel_offset ra, PT_ERA
 	.endif
 	cfi_st	tp, PT_R2, \docfi
+	cfi_st  u0, PT_R21, \docfi
 	cfi_st	fp, PT_R22, \docfi
 
 	/* Set thread_info if we're coming from user mode */
@@ -191,10 +192,13 @@
 	andi	t0, t0, 0x3	/* extract pplv bit */
 	beqz	t0, 9f
 
-	LONG_LI	tp, ~_THREAD_MASK
-	and	tp, tp, sp
-	cfi_st  u0, PT_R21, \docfi
 	csrrd	u0, PERCPU_BASE_KS
+
+	la_abs	t1, cpu_tasks
+#ifdef CONFIG_SMP
+	LONG_ADD t1, t1, u0
+#endif
+	LONG_L	tp, t1, 0
 9:
 #ifdef CONFIG_KGDB
 	li.w	t0, CSR_CRMD_WE
diff --git a/arch/loongarch/include/asm/switch_to.h b/arch/loongarch/include/asm/switch_to.h
index 5b225aff3ba2..27acbf913774 100644
--- a/arch/loongarch/include/asm/switch_to.h
+++ b/arch/loongarch/include/asm/switch_to.h
@@ -15,7 +15,6 @@ struct task_struct;
  * __switch_to - switch execution of a task
  * @prev:	The task previously executed.
  * @next:	The task to begin executing.
- * @next_ti:	task_thread_info(next).
  * @sched_ra:	__schedule return address.
  * @sched_cfa:	__schedule call frame address.
  *
@@ -23,8 +22,7 @@ struct task_struct;
  * the context of next. Returns prev.
  */
 extern asmlinkage struct task_struct *__switch_to(struct task_struct *prev,
-			struct task_struct *next, struct thread_info *next_ti,
-			void *sched_ra, void *sched_cfa);
+			struct task_struct *next, void *sched_ra, void *sched_cfa);
 
 /*
  * For newly created kernel threads switch_to() will return to
@@ -37,7 +35,8 @@ do {										\
 	lose_fpu_inatomic(1, prev);						\
 	lose_lbt_inatomic(1, prev);						\
 	hw_breakpoint_thread_switch(next);					\
-	(last) = __switch_to(prev, next, task_thread_info(next),		\
+	set_current(next);							\
+	(last) = __switch_to(prev, next,					\
 		 __builtin_return_address(0), __builtin_frame_address(0));	\
 } while (0)
 
diff --git a/arch/loongarch/include/asm/thread_info.h b/arch/loongarch/include/asm/thread_info.h
index 4d7117fcdc78..41eabe4fb647 100644
--- a/arch/loongarch/include/asm/thread_info.h
+++ b/arch/loongarch/include/asm/thread_info.h
@@ -22,7 +22,6 @@
  *   must also be changed
  */
 struct thread_info {
-	struct task_struct	*task;		/* main task structure */
 	unsigned long		flags;		/* low level flags */
 	unsigned long		tp_value;	/* thread pointer */
 	__u32			cpu;		/* current CPU */
@@ -37,20 +36,11 @@ struct thread_info {
  */
 #define INIT_THREAD_INFO(tsk)			\
 {						\
-	.task		= &tsk,			\
 	.flags		= _TIF_FIXADE,		\
 	.cpu		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 }
 
-/* How to get the thread information struct from C. */
-register struct thread_info *__current_thread_info __asm__("$tp");
-
-static inline struct thread_info *current_thread_info(void)
-{
-	return __current_thread_info;
-}
-
 register unsigned long current_stack_pointer __asm__("$sp");
 
 #endif /* !__ASSEMBLER__ */
diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
index 058f0dbe8e8f..8f650c9ffecd 100644
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@@ -16,6 +16,7 @@
 #include <linux/memblock.h>
 #include <linux/of_fdt.h>
 #include <linux/serial_core.h>
+#include <linux/vmalloc.h>
 #include <asm/io.h>
 #include <asm/numa.h>
 #include <asm/loongson.h>
@@ -59,6 +60,33 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
 		return ioremap_cache(phys, size);
 }
 
+#define PIO_BASE (unsigned long)PCI_IOBASE
+#define PIO_SIZE ALIGN(ISA_IOSIZE, PAGE_SIZE)
+
+static bool acpi_pio;
+
+/* Add PIO for early access */
+void acpi_add_early_pio(void)
+{
+	if (!acpi_disabled) {
+		acpi_pio = true;
+		vmap_page_range(PIO_BASE, PIO_BASE + PIO_SIZE,
+				LOONGSON_LIO_BASE, pgprot_device(PAGE_KERNEL));
+	}
+}
+
+/* Remove PIO for PCI register */
+void acpi_remove_early_pio(void)
+{
+	if (!acpi_pio)
+		return;
+
+	if (!acpi_disabled) {
+		acpi_pio = false;
+		vunmap_range(PIO_BASE, PIO_BASE + PIO_SIZE);
+	}
+}
+
 #ifdef CONFIG_SMP
 static int set_processor_mask(u32 id, u32 pass)
 {
diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c
index 2cc953f113ac..1b861cbc5e10 100644
--- a/arch/loongarch/kernel/asm-offsets.c
+++ b/arch/loongarch/kernel/asm-offsets.c
@@ -70,7 +70,7 @@ static void __used output_task_defines(void)
 {
 	COMMENT("LoongArch task_struct offsets.");
 	OFFSET(TASK_STATE, task_struct, __state);
-	OFFSET(TASK_THREAD_INFO, task_struct, stack);
+	OFFSET(TASK_STACK, task_struct, stack);
 	OFFSET(TASK_FLAGS, task_struct, flags);
 	OFFSET(TASK_MM, task_struct, mm);
 	OFFSET(TASK_PID, task_struct, pid);
@@ -84,7 +84,6 @@ static void __used output_task_defines(void)
 static void __used output_thread_info_defines(void)
 {
 	COMMENT("LoongArch thread_info offsets.");
-	OFFSET(TI_TASK, thread_info, task);
 	OFFSET(TI_FLAGS, thread_info, flags);
 	OFFSET(TI_TP_VALUE, thread_info, tp_value);
 	OFFSET(TI_CPU, thread_info, cpu);
@@ -266,8 +265,9 @@ static void __used output_signal_defines(void)
 static void __used output_smpboot_defines(void)
 {
 	COMMENT("Linux smp cpu boot offsets.");
+	OFFSET(CPU_BOOT_TASK, secondary_data, task);
 	OFFSET(CPU_BOOT_STACK, secondary_data, stack);
-	OFFSET(CPU_BOOT_TINFO, secondary_data, thread_info);
+	OFFSET(CPU_BOOT_OFFSET, secondary_data, offset);
 	BLANK();
 }
 #endif
diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S
index b53d333a7c42..53bce27f516b 100644
--- a/arch/loongarch/kernel/entry.S
+++ b/arch/loongarch/kernel/entry.S
@@ -67,8 +67,11 @@ SYM_CODE_START(handle_syscall)
 #endif
 
 	move		u0, t0
-	LONG_LI		tp, ~_THREAD_MASK
-	and		tp, tp, sp
+	la_abs		t1, cpu_tasks
+#ifdef CONFIG_SMP
+	LONG_ADD	t1, t1, u0
+#endif
+	LONG_L		tp, t1, 0
 
 	move		a0, sp
 	bl		do_syscall
diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S
index 4eed7bc312a8..601ddd78b233 100644
--- a/arch/loongarch/kernel/head.S
+++ b/arch/loongarch/kernel/head.S
@@ -74,10 +74,11 @@ SYM_CODE_START(kernel_entry)			# kernel entry point
 	/* GPR21 used for percpu base (runtime), initialized as 0 */
 	move		u0, zero
 
-	la.pcrel	tp, init_thread_union
-	/* Set the SP after an empty pt_regs.  */
-	PTR_LI		sp, (_THREAD_SIZE - PT_SIZE)
-	PTR_ADD		sp, sp, tp
+	la.pcrel	tp, init_task
+	la.pcrel	t0, init_stack
+	PTR_LI		t1, _THREAD_SIZE
+	PTR_ADD		t0, t0, t1
+	PTR_ADDI	sp, t0, -PT_SIZE
 	set_saved_sp	sp, t0, t1
 
 #ifdef CONFIG_RELOCATABLE
@@ -86,8 +87,10 @@ SYM_CODE_START(kernel_entry)			# kernel entry point
 
 #ifdef CONFIG_RANDOMIZE_BASE
 	/* Repoint the sp into the new kernel */
-	PTR_LI		sp, (_THREAD_SIZE - PT_SIZE)
-	PTR_ADD		sp, sp, tp
+	LONG_LPTR	t0, tp, TASK_STACK
+	PTR_LI		t1, _THREAD_SIZE
+	PTR_ADD		t0, t0, t1
+	PTR_ADDI	sp, t0, -PT_SIZE
 	set_saved_sp	sp, t0, t1
 
 	/* Jump to the new kernel: new_pc = current_pc + random_offset */
@@ -127,8 +130,9 @@ SYM_CODE_START(smpboot_entry)
 	csrxchg		t0, t1, LOONGARCH_CSR_IMPCTL1
 #endif
 	la.pcrel	t0, cpuboot_data
+	ld.d		tp, t0, CPU_BOOT_TASK
 	ld.d		sp, t0, CPU_BOOT_STACK
-	ld.d		tp, t0, CPU_BOOT_TINFO
+	ld.d		u0, t0, CPU_BOOT_OFFSET
 
 	bl		start_secondary
 	ASM_BUG()
diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c
index 5505fc355e1b..baa683fbfc53 100644
--- a/arch/loongarch/kernel/process.c
+++ b/arch/loongarch/kernel/process.c
@@ -60,6 +60,8 @@ unsigned long __stack_chk_guard __read_mostly;
 EXPORT_SYMBOL(__stack_chk_guard);
 #endif
 
+DEFINE_PER_CPU(struct task_struct *, cpu_tasks);
+
 /*
  * Idle related variables and functions
  */
diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c
index 4b61a9632a98..2a42874e5eb7 100644
--- a/arch/loongarch/kernel/relocate.c
+++ b/arch/loongarch/kernel/relocate.c
@@ -313,7 +313,7 @@ unsigned long __init relocate_kernel(void)
 		reloc_offset += random_offset;
 
 		/* The current thread is now within the relocated kernel */
-		__current_thread_info = RELOCATED_KASLR(__current_thread_info);
+		current_thread_pointer = RELOCATED_KASLR(current_thread_pointer);
 
 		update_reloc_offset(&reloc_offset, random_offset);
 	}
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index 839b23edee87..eaebb52bd36e 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -502,6 +502,8 @@ static __init int arch_reserve_pio_range(void)
 {
 	struct device_node *np;
 
+	acpi_add_early_pio();
+
 	for_each_node_by_name(np, "isa") {
 		struct of_range range;
 		struct of_range_parser parser;
@@ -593,6 +595,7 @@ void __init setup_arch(char **cmdline_p)
 {
 	cpu_probe();
 	unwind_init();
+	set_current(current);
 
 	init_environ();
 	efi_init();
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index 50922610758b..5d792256bbb9 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -400,8 +400,9 @@ void loongson_boot_secondary(int cpu, struct task_struct *idle)
 	pr_info("Booting CPU#%d...\n", cpu);
 
 	entry = __pa_symbol((unsigned long)&smpboot_entry);
-	cpuboot_data.stack = (unsigned long)__KSTK_TOS(idle);
-	cpuboot_data.thread_info = (unsigned long)task_thread_info(idle);
+	cpuboot_data.task = (unsigned long)idle;
+	cpuboot_data.stack = (unsigned long)task_pt_regs(idle);
+	cpuboot_data.offset = per_cpu_offset(cpu);
 
 	csr_mail_send(entry, cpu_logical_map(cpu), 0);
 
@@ -663,6 +664,7 @@ asmlinkage void start_secondary(void)
 	set_my_cpu_offset(per_cpu_offset(cpu));
 
 	cpu_probe();
+	set_current(current);
 	constant_clockevent_init();
 	loongson_init_secondary();
 
@@ -705,6 +707,7 @@ static void stop_this_cpu(void *dummy)
 	set_cpu_online(smp_processor_id(), false);
 	calculate_cpu_foreign_map();
 	local_irq_disable();
+	rcutree_report_cpu_dead();
 	while (true);
 }
 
diff --git a/arch/loongarch/kernel/switch.S b/arch/loongarch/kernel/switch.S
index f377d8f5c51a..d6e0d05d6fd3 100644
--- a/arch/loongarch/kernel/switch.S
+++ b/arch/loongarch/kernel/switch.S
@@ -12,7 +12,7 @@
 
 /*
  * task_struct *__switch_to(task_struct *prev, task_struct *next,
- *			    struct thread_info *next_ti, void *sched_ra, void *sched_cfa)
+ *			    void *sched_ra, void *sched_cfa)
  */
 	.align	5
 SYM_FUNC_START(__switch_to)
@@ -24,8 +24,8 @@ SYM_FUNC_START(__switch_to)
 	LONG_SPTR	t1, a0, (THREAD_CSRPRMD - TASK_STRUCT_OFFSET)
 
 	cpu_save_nonscratch a0
-	LONG_SPTR	a3, a0, (THREAD_SCHED_RA - TASK_STRUCT_OFFSET)
-	LONG_SPTR	a4, a0, (THREAD_SCHED_CFA - TASK_STRUCT_OFFSET)
+	LONG_SPTR	a2, a0, (THREAD_SCHED_RA - TASK_STRUCT_OFFSET)
+	LONG_SPTR	a3, a0, (THREAD_SCHED_CFA - TASK_STRUCT_OFFSET)
 
 #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_SMP)
 	la		t7, __stack_chk_guard
@@ -33,11 +33,12 @@ SYM_FUNC_START(__switch_to)
 	LONG_SPTR	t8, t7, 0
 #endif
 
-	move	tp, a2
+	move		tp, a1
 	cpu_restore_nonscratch a1
 
-	li.w		t0, _THREAD_SIZE
-	PTR_ADD		t0, t0, tp
+	LONG_LPTR	t0, a1, (TASK_STACK - TASK_STRUCT_OFFSET)
+	PTR_LI		t1, _THREAD_SIZE
+	PTR_ADD		t0, t0, t1
 	set_saved_sp	t0, t1, t2
 
 	LONG_LPTR	t1, a1, (THREAD_CSRPRMD - TASK_STRUCT_OFFSET)
@@ -45,6 +46,7 @@ SYM_FUNC_START(__switch_to)
 
 #ifdef CONFIG_32BIT
 	PTR_ADDI	a0, a0, -TASK_STRUCT_OFFSET
+	PTR_ADDI	tp, tp, -TASK_STRUCT_OFFSET
 #endif
 	jr	ra
 SYM_FUNC_END(__switch_to)
diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c
index 5d49b742e3bf..776523747ea3 100644
--- a/arch/loongarch/kernel/traps.c
+++ b/arch/loongarch/kernel/traps.c
@@ -107,6 +107,12 @@ static void show_stacktrace(struct task_struct *task,
 	unsigned long stackdata;
 	unsigned long *sp = (unsigned long *)regs->regs[3];
 
+	if (!task)
+		task = current;
+
+	if (!try_get_task_stack(task))
+		return;
+
 	printk("%sStack :", loglvl);
 	i = 0;
 	while ((unsigned long) sp & (PAGE_SIZE - 1)) {
@@ -129,6 +135,8 @@ static void show_stacktrace(struct task_struct *task,
 	}
 	pr_cont("\n");
 	show_backtrace(task, regs, loglvl, user);
+
+	put_task_stack(task);
 }
 
 void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl)
diff --git a/arch/loongarch/mm/pageattr.c b/arch/loongarch/mm/pageattr.c
index f5e910b68229..614ccc7afccb 100644
--- a/arch/loongarch/mm/pageattr.c
+++ b/arch/loongarch/mm/pageattr.c
@@ -234,5 +234,5 @@ int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid)
 		clear = __pgprot(_PAGE_PRESENT | _PAGE_VALID);
 	}
 
-	return __set_memory(addr, 1, set, clear);
+	return __set_memory(addr, nr, set, clear);
 }
diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c
index 058ffbbaad85..ad7e28375aa9 100644
--- a/arch/loongarch/net/bpf_jit.c
+++ b/arch/loongarch/net/bpf_jit.c
@@ -5,11 +5,18 @@
  * Copyright (C) 2022 Loongson Technology Corporation Limited
  */
 #include <linux/memory.h>
+#include <asm/asm-offsets.h>
 #include "bpf_jit.h"
 
 #define LOONGARCH_MAX_REG_ARGS 8
 
+#define LOONGARCH_SAVE_RA_NINSNS   1
 #define LOONGARCH_LONG_JUMP_NINSNS 5
+#define LOONGARCH_TCC_SLOT_NINSNS  1
+
+#define LOONGARCH_PROLOGUE_SKIP_INSNS \
+	(LOONGARCH_SAVE_RA_NINSNS + LOONGARCH_LONG_JUMP_NINSNS + LOONGARCH_TCC_SLOT_NINSNS)
+
 #define LOONGARCH_LONG_JUMP_NBYTES (LOONGARCH_LONG_JUMP_NINSNS * 4)
 
 #define LOONGARCH_FENTRY_NINSNS 2
@@ -143,8 +150,13 @@ static void build_prologue(struct jit_ctx *ctx)
 	stack_adjust = round_up(stack_adjust, 16);
 	stack_adjust += bpf_stack_adjust;
 
+	/*
+	 * Save the original return address to a temporary register to prevent
+	 * it from being overwritten, then reserve space for the long jump and
+	 * fentry trampoline slot for dynamically patching by ftrace at runtime.
+	 * These instructions are bypassed during a tail call invocation.
+	 */
 	move_reg(ctx, LOONGARCH_GPR_T0, LOONGARCH_GPR_RA);
-	/* Reserve space for the move_imm + jirl instruction */
 	for (i = 0; i < LOONGARCH_LONG_JUMP_NINSNS; i++)
 		emit_insn(ctx, nop);
 
@@ -253,10 +265,11 @@ static void __build_epilogue(struct jit_ctx *ctx, bool is_tail_call)
 		emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_RA, 0);
 	} else {
 		/*
-		 * Call the next bpf prog and skip the first instruction
-		 * of TCC initialization.
+		 * Tail call to the next BPF program, passing offset in number
+		 * of instructions to jirl to bypass the initial setup slots.
 		 */
-		emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_T3, 7);
+		emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO,
+			  LOONGARCH_GPR_T3, LOONGARCH_PROLOGUE_SKIP_INSNS);
 	}
 }
 
@@ -312,12 +325,12 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx, int insn)
 	 */
 	emit_insn(ctx, ldd, REG_TCC, LOONGARCH_GPR_SP, tcc_ptr_off);
 	emit_insn(ctx, ldd, t3, REG_TCC, 0);
-	emit_insn(ctx, addid, t3, t3, 1);
-	emit_insn(ctx, std, t3, REG_TCC, 0);
 	emit_insn(ctx, addid, t2, LOONGARCH_GPR_ZERO, MAX_TAIL_CALL_CNT);
-	if (emit_tailcall_jmp(ctx, BPF_JSGT, t3, t2, jmp_offset) < 0)
+	if (emit_tailcall_jmp(ctx, BPF_JSGE, t3, t2, jmp_offset) < 0)
 		goto toofar;
 
+	emit_insn(ctx, addid, t3, t3, 1);
+
 	/*
 	 * prog = array->ptrs[index];
 	 * if (!prog)
@@ -330,6 +343,8 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx, int insn)
 	if (emit_tailcall_jmp(ctx, BPF_JEQ, t2, LOONGARCH_GPR_ZERO, jmp_offset) < 0)
 		goto toofar;
 
+	emit_insn(ctx, std, t3, REG_TCC, 0);
+
 	/* goto *(prog->bpf_func + 4); */
 	off = offsetof(struct bpf_prog, bpf_func);
 	emit_insn(ctx, ldd, t3, t2, off);
@@ -1147,6 +1162,19 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 
 	/* function call */
 	case BPF_JMP | BPF_CALL:
+		/* Implement helper call to bpf_get_current_task/_btf() inline */
+		if (insn->src_reg == 0 && (insn->imm == BPF_FUNC_get_current_task ||
+					   insn->imm == BPF_FUNC_get_current_task_btf)) {
+			move_reg(ctx, regmap[BPF_REG_0], LOONGARCH_GPR_TP);
+			break;
+		}
+
+		/* Implement helper call to bpf_get_smp_processor_id() inline */
+		if (insn->src_reg == 0 && insn->imm == BPF_FUNC_get_smp_processor_id) {
+			emit_insn(ctx, ldwu, regmap[BPF_REG_0], LOONGARCH_GPR_TP, TI_CPU);
+			break;
+		}
+
 		ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass,
 					    &func_addr, &func_addr_fixed);
 		if (ret < 0)
@@ -2367,3 +2395,15 @@ bool bpf_jit_supports_subprog_tailcalls(void)
 {
 	return true;
 }
+
+bool bpf_jit_inlines_helper_call(s32 imm)
+{
+	switch (imm) {
+	case BPF_FUNC_get_current_task:
+	case BPF_FUNC_get_current_task_btf:
+	case BPF_FUNC_get_smp_processor_id:
+		return true;
+	default:
+		return false;
+	}
+}
diff --git a/arch/loongarch/pci/acpi.c b/arch/loongarch/pci/acpi.c
index b02698a338ee..ccbcea61fcd9 100644
--- a/arch/loongarch/pci/acpi.c
+++ b/arch/loongarch/pci/acpi.c
@@ -65,6 +65,8 @@ static int acpi_prepare_root_resources(struct acpi_pci_root_info *ci)
 	struct resource_entry *entry, *tmp;
 	struct acpi_device *device = ci->bridge;
 
+	acpi_remove_early_pio();
+
 	status = acpi_pci_probe_root_resources(ci);
 	if (status > 0) {
 		acpi_evaluate_integer(device->handle, "PCIH", NULL, &pci_h);
diff --git a/arch/loongarch/vdso/elf.S b/arch/loongarch/vdso/elf.S
index 9bb21b9f9583..d6e000003b85 100644
--- a/arch/loongarch/vdso/elf.S
+++ b/arch/loongarch/vdso/elf.S
@@ -7,9 +7,12 @@
 
 #include <asm/vdso/vdso.h>
 
+#include <linux/build-salt.h>
 #include <linux/elfnote.h>
 #include <linux/version.h>
 
 ELFNOTE_START(Linux, 0, "a")
 	.long LINUX_VERSION_CODE
 ELFNOTE_END
+
+BUILD_SALT
diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index d1db355e872b..67ff7882299e 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -423,6 +423,8 @@ static inline int get_preempt_count(void)
 	return bpf_get_current_task_btf()->thread_info.preempt_count;
 #elif defined(bpf_target_s390)
 	return bpf_get_lowcore()->preempt_count;
+#elif defined(bpf_target_loongarch)
+	return bpf_get_current_task_btf()->thread_info.preempt_count;
 #endif
 	return 0;
 }
@@ -433,6 +435,7 @@ static inline int get_preempt_count(void)
  *	* arm64
  *	* powerpc64
  *	* s390x
+ *	* loongarch
  */
 static inline int bpf_in_interrupt(void)
 {
@@ -454,6 +457,7 @@ static inline int bpf_in_interrupt(void)
  *	* arm64
  *	* powerpc64
  *	* s390x
+ *	* loongarch
  */
 static inline int bpf_in_nmi(void)
 {
@@ -466,6 +470,7 @@ static inline int bpf_in_nmi(void)
  *	* arm64
  *	* powerpc64
  *	* s390x
+ *	* loongarch
  */
 static inline int bpf_in_hardirq(void)
 {
@@ -478,6 +483,7 @@ static inline int bpf_in_hardirq(void)
  *	* arm64
  *	* powerpc64
  *	* s390x
+ *	* loongarch
  */
 static inline int bpf_in_serving_softirq(void)
 {
@@ -498,6 +504,7 @@ static inline int bpf_in_serving_softirq(void)
  *	* arm64
  *	* powerpc64
  *	* s390x
+ *	* loongarch
  */
 static inline int bpf_in_task(void)
 {
diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index 9eeb5b0b63d6..b0c441384f20 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -158,6 +158,7 @@
 #define __arch_arm64		__arch("ARM64")
 #define __arch_riscv64		__arch("RISCV64")
 #define __arch_s390x		__arch("s390x")
+#define __arch_loongarch	__arch("LOONGARCH")
 #define __caps_unpriv(caps)	__test_tag("test_caps_unpriv=" EXPAND_QUOTE(caps))
 #define __load_if_JITed()	__test_tag("load_mode=jited")
 #define __load_if_no_JITed()	__test_tag("load_mode=no_jited")
diff --git a/tools/testing/selftests/bpf/progs/verifier_jit_inline.c b/tools/testing/selftests/bpf/progs/verifier_jit_inline.c
index 76d80605ec7f..02e562f56f9d 100644
--- a/tools/testing/selftests/bpf/progs/verifier_jit_inline.c
+++ b/tools/testing/selftests/bpf/progs/verifier_jit_inline.c
@@ -12,6 +12,8 @@ __arch_arm64
 __jited("	mrs	x8, SP_EL0")
 __arch_riscv64
 __jited("	mv	a5, tp")
+__arch_loongarch
+__jited("	move	$a5, $tp")
 int inline_bpf_get_current_task(void)
 {
 	bpf_get_current_task();
@@ -19,4 +21,15 @@ int inline_bpf_get_current_task(void)
 	return 0;
 }
 
+SEC("fentry/bpf_fentry_test2")
+__success __retval(0)
+__arch_loongarch
+__jited("	ld.wu	$a5, $tp, 16")
+int inline_bpf_get_smp_processor_id(void)
+{
+	bpf_get_smp_processor_id();
+
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index abdb9e6e3713..3ce32d134e2c 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -377,6 +377,7 @@ enum arch {
 	ARCH_ARM64	= 0x4,
 	ARCH_RISCV64	= 0x8,
 	ARCH_S390X	= 0x10,
+	ARCH_LOONGARCH	= 0x20,
 };
 
 static int get_current_arch(void)
@@ -389,6 +390,8 @@ static int get_current_arch(void)
 	return ARCH_RISCV64;
 #elif defined(__s390x__)
 	return ARCH_S390X;
+#elif defined(__loongarch__)
+	return ARCH_LOONGARCH;
 #endif
 	return ARCH_UNKNOWN;
 }
@@ -580,6 +583,8 @@ static int parse_test_spec(struct test_loader *tester,
 				arch = ARCH_RISCV64;
 			} else if (strcmp(val, "s390x") == 0) {
 				arch = ARCH_S390X;
+			} else if (strcmp(val, "LOONGARCH") == 0) {
+				arch = ARCH_LOONGARCH;
 			} else {
 				PRINT_FAIL("bad arch spec: '%s'\n", val);
 				err = -EINVAL;