7 files changed, 65 insertions, 35 deletions

diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S
index 48e7e34e355e..2abc29e57381 100644
--- a/arch/loongarch/kernel/entry.S
+++ b/arch/loongarch/kernel/entry.S
@@ -77,24 +77,22 @@ SYM_CODE_START(handle_syscall)
 SYM_CODE_END(handle_syscall)
 _ASM_NOKPROBE(handle_syscall)
 
-SYM_CODE_START(ret_from_fork)
+SYM_CODE_START(ret_from_fork_asm)
 	UNWIND_HINT_REGS
-	bl		schedule_tail		# a0 = struct task_struct *prev
-	move		a0, sp
-	bl 		syscall_exit_to_user_mode
+	move		a1, sp
+	bl 		ret_from_fork
 	RESTORE_STATIC
 	RESTORE_SOME
 	RESTORE_SP_AND_RET
-SYM_CODE_END(ret_from_fork)
+SYM_CODE_END(ret_from_fork_asm)
 
-SYM_CODE_START(ret_from_kernel_thread)
+SYM_CODE_START(ret_from_kernel_thread_asm)
 	UNWIND_HINT_REGS
-	bl		schedule_tail		# a0 = struct task_struct *prev
-	move		a0, s1
-	jirl		ra, s0, 0
-	move		a0, sp
-	bl		syscall_exit_to_user_mode
+	move		a1, sp
+	move		a2, s0
+	move		a3, s1
+	bl		ret_from_kernel_thread
 	RESTORE_STATIC
 	RESTORE_SOME
 	RESTORE_SP_AND_RET
-SYM_CODE_END(ret_from_kernel_thread)
+SYM_CODE_END(ret_from_kernel_thread_asm)
diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S
index 4f0912141781..733a7665e434 100644
--- a/arch/loongarch/kernel/genex.S
+++ b/arch/loongarch/kernel/genex.S
@@ -16,6 +16,7 @@
 #include <asm/stackframe.h>
 #include <asm/thread_info.h>
 
+	.section .cpuidle.text, "ax"
 	.align	5
 SYM_FUNC_START(__arch_cpu_idle)
 	/* start of idle interrupt region */
@@ -31,14 +32,16 @@ SYM_FUNC_START(__arch_cpu_idle)
 	 */
 	idle	0
 	/* end of idle interrupt region */
-1:	jr	ra
+idle_exit:
+	jr	ra
 SYM_FUNC_END(__arch_cpu_idle)
+	.previous
 
 SYM_CODE_START(handle_vint)
 	UNWIND_HINT_UNDEFINED
 	BACKUP_T0T1
 	SAVE_ALL
-	la_abs	t1, 1b
+	la_abs	t1, idle_exit
 	LONG_L	t0, sp, PT_ERA
 	/* 3 instructions idle interrupt region */
 	ori	t0, t0, 0b1100
diff --git a/arch/loongarch/kernel/kfpu.c b/arch/loongarch/kernel/kfpu.c
index ec5b28e570c9..4c476904227f 100644
--- a/arch/loongarch/kernel/kfpu.c
+++ b/arch/loongarch/kernel/kfpu.c
@@ -18,11 +18,28 @@ static unsigned int euen_mask = CSR_EUEN_FPEN;
 static DEFINE_PER_CPU(bool, in_kernel_fpu);
 static DEFINE_PER_CPU(unsigned int, euen_current);
 
+static inline void fpregs_lock(void)
+{
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		preempt_disable();
+	else
+		local_bh_disable();
+}
+
+static inline void fpregs_unlock(void)
+{
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		preempt_enable();
+	else
+		local_bh_enable();
+}
+
 void kernel_fpu_begin(void)
 {
 	unsigned int *euen_curr;
 
-	preempt_disable();
+	if (!irqs_disabled())
+		fpregs_lock();
 
 	WARN_ON(this_cpu_read(in_kernel_fpu));
 
@@ -73,7 +90,8 @@ void kernel_fpu_end(void)
 
 	this_cpu_write(in_kernel_fpu, false);
 
-	preempt_enable();
+	if (!irqs_disabled())
+		fpregs_unlock();
 }
 EXPORT_SYMBOL_GPL(kernel_fpu_end);
 
diff --git a/arch/loongarch/kernel/perf_event.c b/arch/loongarch/kernel/perf_event.c
index f86a4b838dd7..8ad098703488 100644
--- a/arch/loongarch/kernel/perf_event.c
+++ b/arch/loongarch/kernel/perf_event.c
@@ -479,8 +479,7 @@ static void handle_associated_event(struct cpu_hw_events *cpuc, int idx,
 	if (!loongarch_pmu_event_set_period(event, hwc, idx))
 		return;
 
-	if (perf_event_overflow(event, data, regs))
-		loongarch_pmu_disable_event(idx);
+	perf_event_overflow(event, data, regs);
 }
 
 static irqreturn_t pmu_handle_irq(int irq, void *dev)
diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c
index 6e58f65455c7..3582f591bab2 100644
--- a/arch/loongarch/kernel/process.c
+++ b/arch/loongarch/kernel/process.c
@@ -13,6 +13,7 @@
 #include <linux/cpu.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/entry-common.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
@@ -34,6 +35,7 @@
 #include <linux/nmi.h>
 
 #include <asm/asm.h>
+#include <asm/asm-prototypes.h>
 #include <asm/bootinfo.h>
 #include <asm/cpu.h>
 #include <asm/elf.h>
@@ -47,6 +49,7 @@
 #include <asm/pgtable.h>
 #include <asm/processor.h>
 #include <asm/reg.h>
+#include <asm/switch_to.h>
 #include <asm/unwind.h>
 #include <asm/vdso.h>
 
@@ -63,8 +66,9 @@ EXPORT_SYMBOL(__stack_chk_guard);
 unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE;
 EXPORT_SYMBOL(boot_option_idle_override);
 
-asmlinkage void ret_from_fork(void);
-asmlinkage void ret_from_kernel_thread(void);
+asmlinkage void restore_and_ret(void);
+asmlinkage void ret_from_fork_asm(void);
+asmlinkage void ret_from_kernel_thread_asm(void);
 
 void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp)
 {
@@ -138,6 +142,23 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	return 0;
 }
 
+asmlinkage void noinstr __no_stack_protector ret_from_fork(struct task_struct *prev,
+							   struct pt_regs *regs)
+{
+	schedule_tail(prev);
+	syscall_exit_to_user_mode(regs);
+}
+
+asmlinkage void noinstr __no_stack_protector ret_from_kernel_thread(struct task_struct *prev,
+								    struct pt_regs *regs,
+								    int (*fn)(void *),
+								    void *fn_arg)
+{
+	schedule_tail(prev);
+	fn(fn_arg);
+	syscall_exit_to_user_mode(regs);
+}
+
 /*
  * Copy architecture-specific thread state
  */
@@ -165,8 +186,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		p->thread.reg03 = childksp;
 		p->thread.reg23 = (unsigned long)args->fn;
 		p->thread.reg24 = (unsigned long)args->fn_arg;
-		p->thread.reg01 = (unsigned long)ret_from_kernel_thread;
-		p->thread.sched_ra = (unsigned long)ret_from_kernel_thread;
+		p->thread.reg01 = (unsigned long)ret_from_kernel_thread_asm;
+		p->thread.sched_ra = (unsigned long)ret_from_kernel_thread_asm;
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->csr_euen = p->thread.csr_euen;
 		childregs->csr_crmd = p->thread.csr_crmd;
@@ -182,8 +203,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		childregs->regs[3] = usp;
 
 	p->thread.reg03 = (unsigned long) childregs;
-	p->thread.reg01 = (unsigned long) ret_from_fork;
-	p->thread.sched_ra = (unsigned long) ret_from_fork;
+	p->thread.reg01 = (unsigned long) ret_from_fork_asm;
+	p->thread.sched_ra = (unsigned long) ret_from_fork_asm;
 
 	/*
 	 * New tasks lose permission to use the fpu. This accelerates context
diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c
index e2d3bfeb6366..bc75a3a69fc8 100644
--- a/arch/loongarch/kernel/time.c
+++ b/arch/loongarch/kernel/time.c
@@ -111,7 +111,7 @@ static unsigned long __init get_loops_per_jiffy(void)
 	return lpj;
 }
 
-static long init_offset __nosavedata;
+static long init_offset;
 
 void save_counter(void)
 {
diff --git a/arch/loongarch/kernel/uprobes.c b/arch/loongarch/kernel/uprobes.c
index 87abc7137b73..6022eb0f71db 100644
--- a/arch/loongarch/kernel/uprobes.c
+++ b/arch/loongarch/kernel/uprobes.c
@@ -42,7 +42,6 @@ int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	utask->autask.saved_trap_nr = current->thread.trap_nr;
 	current->thread.trap_nr = UPROBE_TRAP_NR;
 	instruction_pointer_set(regs, utask->xol_vaddr);
-	user_enable_single_step(current);
 
 	return 0;
 }
@@ -53,13 +52,7 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 
 	WARN_ON_ONCE(current->thread.trap_nr != UPROBE_TRAP_NR);
 	current->thread.trap_nr = utask->autask.saved_trap_nr;
-
-	if (auprobe->simulate)
-		instruction_pointer_set(regs, auprobe->resume_era);
-	else
-		instruction_pointer_set(regs, utask->vaddr + LOONGARCH_INSN_SIZE);
-
-	user_disable_single_step(current);
+	instruction_pointer_set(regs, utask->vaddr + LOONGARCH_INSN_SIZE);
 
 	return 0;
 }
@@ -70,7 +63,6 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 
 	current->thread.trap_nr = utask->autask.saved_trap_nr;
 	instruction_pointer_set(regs, utask->vaddr);
-	user_disable_single_step(current);
 }
 
 bool arch_uprobe_xol_was_trapped(struct task_struct *t)
@@ -90,7 +82,6 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
 
 	insn.word = auprobe->insn[0];
 	arch_simulate_insn(insn, regs);
-	auprobe->resume_era = regs->csr_era;
 
 	return true;
 }