[PATCH v3 0/4] entry: Move ret_from_fork() to C and inline syscall_exit_to_user_mode()

[PATCH v3 0/4] entry: Move ret_from_fork() to C and inline syscall_exit_to_user_mode()

[Charlie Jenkins]

Similar to commit 221a164035fd ("entry: Move
syscall_enter_from_user_mode() to header file"), move
syscall_exit_to_user_mode() to the header file as well.

Testing was done with the byte-unixbench [1] syscall benchmark (which
calls getpid) and QEMU. On riscv I measured a 7.09246% improvement, on
x86 a 2.98843% improvement, on loongarch a 6.07954% improvement, and on
s390 a 11.1328% improvement.

Since this is on QEMU, I know these numbers are not perfect, but they
show a trend of general improvement across all architectures that use
the generic entry code.

[1] https://github.com/kdlucas/byte-unixbench

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
---
Changes in v3:
- Fixup comment to properly reflect args (Alex)
- Fix prototypes for loongarch (Huacai)
- Link to v2: https://lore.kernel.org/r/20250123-riscv_optimize_entry-v2-0-7c259492d508@rivosinc.com

Changes in v2:
- Fixup compilation issues for loongarch
- Fixup compilation issues with CONFIG_CONTEXT_TRACKING_USER
- Link to v1: https://lore.kernel.org/r/20250122-riscv_optimize_entry-v1-0-4ee95559cfd0@rivosinc.com

---
Charlie Jenkins (4):
      riscv: entry: Convert ret_from_fork() to C
      riscv: entry: Split ret_from_fork() into user and kernel
      LoongArch: entry: Migrate ret_from_fork() to C
      entry: Inline syscall_exit_to_user_mode()

 arch/loongarch/include/asm/asm-prototypes.h |  8 +++++
 arch/loongarch/kernel/entry.S               | 22 ++++++-------
 arch/loongarch/kernel/process.c             | 33 +++++++++++++++----
 arch/riscv/include/asm/asm-prototypes.h     |  2 ++
 arch/riscv/kernel/entry.S                   | 20 +++++++-----
 arch/riscv/kernel/process.c                 | 21 +++++++++++--
 include/linux/entry-common.h                | 43 +++++++++++++++++++++++--
 kernel/entry/common.c                       | 49 +----------------------------
 8 files changed, 119 insertions(+), 79 deletions(-)
---
base-commit: ffd294d346d185b70e28b1a28abe367bbfe53c04
change-id: 20240402-riscv_optimize_entry-583843420325
-- 
- Charlie

[PATCH v3 1/4] riscv: entry: Convert ret_from_fork() to C

[Charlie Jenkins]

Move the main section of ret_from_fork() to C to allow inlining of
syscall_exit_to_user_mode().

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
---
 arch/riscv/include/asm/asm-prototypes.h |  1 +
 arch/riscv/kernel/entry.S               | 15 ++++++---------
 arch/riscv/kernel/process.c             | 14 ++++++++++++--
 3 files changed, 19 insertions(+), 11 deletions(-)

diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h
index cd627ec289f163a630b73dd03dd52a6b28692997..733ff609778797001006c33bba9e3cc5b1f15387 100644
--- a/arch/riscv/include/asm/asm-prototypes.h
+++ b/arch/riscv/include/asm/asm-prototypes.h
@@ -52,6 +52,7 @@ DECLARE_DO_ERROR_INFO(do_trap_ecall_s);
 DECLARE_DO_ERROR_INFO(do_trap_ecall_m);
 DECLARE_DO_ERROR_INFO(do_trap_break);
 
+asmlinkage void ret_from_fork(void *fn_arg, int (*fn)(void *), struct pt_regs *regs);
 asmlinkage void handle_bad_stack(struct pt_regs *regs);
 asmlinkage void do_page_fault(struct pt_regs *regs);
 asmlinkage void do_irq(struct pt_regs *regs);
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 33a5a9f2a0d4e1eeccfb3621b9e518b88e1b0704..b2dc5e7c7b3a843fa4aa02eba2a911eb3ce31d1f 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -319,17 +319,14 @@ SYM_CODE_END(handle_kernel_stack_overflow)
 ASM_NOKPROBE(handle_kernel_stack_overflow)
 #endif
 
-SYM_CODE_START(ret_from_fork)
+SYM_CODE_START(ret_from_fork_asm)
 	call schedule_tail
-	beqz s0, 1f	/* not from kernel thread */
-	/* Call fn(arg) */
-	move a0, s1
-	jalr s0
-1:
-	move a0, sp /* pt_regs */
-	call syscall_exit_to_user_mode
+	move a0, s1 /* fn_arg */
+	move a1, s0 /* fn */
+	move a2, sp /* pt_regs */
+	call ret_from_fork
 	j ret_from_exception
-SYM_CODE_END(ret_from_fork)
+SYM_CODE_END(ret_from_fork_asm)
 
 #ifdef CONFIG_IRQ_STACKS
 /*
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 58b6482c2bf662bf5224ca50c8e21a68760a6b41..0d07e6d8f6b57beba438dbba5e8c74a014582bee 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -17,7 +17,9 @@
 #include <linux/ptrace.h>
 #include <linux/uaccess.h>
 #include <linux/personality.h>
+#include <linux/entry-common.h>
 
+#include <asm/asm-prototypes.h>
 #include <asm/unistd.h>
 #include <asm/processor.h>
 #include <asm/csr.h>
@@ -36,7 +38,7 @@ unsigned long __stack_chk_guard __read_mostly;
 EXPORT_SYMBOL(__stack_chk_guard);
 #endif
 
-extern asmlinkage void ret_from_fork(void);
+extern asmlinkage void ret_from_fork_asm(void);
 
 void noinstr arch_cpu_idle(void)
 {
@@ -206,6 +208,14 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	return 0;
 }
 
+asmlinkage void ret_from_fork(void *fn_arg, int (*fn)(void *), struct pt_regs *regs)
+{
+	if (unlikely(fn))
+		fn(fn_arg);
+
+	syscall_exit_to_user_mode(regs);
+}
+
 int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
@@ -242,7 +252,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	p->thread.riscv_v_flags = 0;
 	if (has_vector())
 		riscv_v_thread_alloc(p);
-	p->thread.ra = (unsigned long)ret_from_fork;
+	p->thread.ra = (unsigned long)ret_from_fork_asm;
 	p->thread.sp = (unsigned long)childregs; /* kernel sp */
 	return 0;
 }

-- 
2.43.0

[PATCH v3 2/4] riscv: entry: Split ret_from_fork() into user and kernel

[Charlie Jenkins]

This function was unified into a single function in commit ab9164dae273
("riscv: entry: Consolidate ret_from_kernel_thread into ret_from_fork").
However that imposed a performance degradation. Partially reverting this
commit to have ret_from_fork() split again results in a 1% increase on
the number of times fork is able to be called per second.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
---
 arch/riscv/include/asm/asm-prototypes.h |  3 ++-
 arch/riscv/kernel/entry.S               | 13 ++++++++++---
 arch/riscv/kernel/process.c             | 17 +++++++++++------
 3 files changed, 23 insertions(+), 10 deletions(-)

diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h
index 733ff609778797001006c33bba9e3cc5b1f15387..bfc8ea5f9319b19449ec59493b45b926df888832 100644
--- a/arch/riscv/include/asm/asm-prototypes.h
+++ b/arch/riscv/include/asm/asm-prototypes.h
@@ -52,7 +52,8 @@ DECLARE_DO_ERROR_INFO(do_trap_ecall_s);
 DECLARE_DO_ERROR_INFO(do_trap_ecall_m);
 DECLARE_DO_ERROR_INFO(do_trap_break);
 
-asmlinkage void ret_from_fork(void *fn_arg, int (*fn)(void *), struct pt_regs *regs);
+asmlinkage void ret_from_fork_kernel(void *fn_arg, int (*fn)(void *), struct pt_regs *regs);
+asmlinkage void ret_from_fork_user(struct pt_regs *regs);
 asmlinkage void handle_bad_stack(struct pt_regs *regs);
 asmlinkage void do_page_fault(struct pt_regs *regs);
 asmlinkage void do_irq(struct pt_regs *regs);
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index b2dc5e7c7b3a843fa4aa02eba2a911eb3ce31d1f..0fb338000c6dc0358742cd03497fa54b9e9d1aec 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -319,14 +319,21 @@ SYM_CODE_END(handle_kernel_stack_overflow)
 ASM_NOKPROBE(handle_kernel_stack_overflow)
 #endif
 
-SYM_CODE_START(ret_from_fork_asm)
+SYM_CODE_START(ret_from_fork_kernel_asm)
 	call schedule_tail
 	move a0, s1 /* fn_arg */
 	move a1, s0 /* fn */
 	move a2, sp /* pt_regs */
-	call ret_from_fork
+	call ret_from_fork_kernel
 	j ret_from_exception
-SYM_CODE_END(ret_from_fork_asm)
+SYM_CODE_END(ret_from_fork_kernel_asm)
+
+SYM_CODE_START(ret_from_fork_user_asm)
+	call schedule_tail
+	move a0, sp /* pt_regs */
+	call ret_from_fork_user
+	j ret_from_exception
+SYM_CODE_END(ret_from_fork_user_asm)
 
 #ifdef CONFIG_IRQ_STACKS
 /*
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 0d07e6d8f6b57beba438dbba5e8c74a014582bee..5f15236cb526bd9fe61636ed372b4b76c94df946 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -38,7 +38,8 @@ unsigned long __stack_chk_guard __read_mostly;
 EXPORT_SYMBOL(__stack_chk_guard);
 #endif
 
-extern asmlinkage void ret_from_fork_asm(void);
+extern asmlinkage void ret_from_fork_kernel_asm(void);
+extern asmlinkage void ret_from_fork_user_asm(void);
 
 void noinstr arch_cpu_idle(void)
 {
@@ -208,14 +209,18 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	return 0;
 }
 
-asmlinkage void ret_from_fork(void *fn_arg, int (*fn)(void *), struct pt_regs *regs)
+asmlinkage void ret_from_fork_kernel(void *fn_arg, int (*fn)(void *), struct pt_regs *regs)
 {
-	if (unlikely(fn))
-		fn(fn_arg);
+	fn(fn_arg);
 
 	syscall_exit_to_user_mode(regs);
 }
 
+asmlinkage void ret_from_fork_user(struct pt_regs *regs)
+{
+	syscall_exit_to_user_mode(regs);
+}
+
 int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
 	unsigned long clone_flags = args->flags;
@@ -238,6 +243,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 
 		p->thread.s[0] = (unsigned long)args->fn;
 		p->thread.s[1] = (unsigned long)args->fn_arg;
+		p->thread.ra = (unsigned long)ret_from_fork_kernel_asm;
 	} else {
 		*childregs = *(current_pt_regs());
 		/* Turn off status.VS */
@@ -247,12 +253,11 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		if (clone_flags & CLONE_SETTLS)
 			childregs->tp = tls;
 		childregs->a0 = 0; /* Return value of fork() */
-		p->thread.s[0] = 0;
+		p->thread.ra = (unsigned long)ret_from_fork_user_asm;
 	}
 	p->thread.riscv_v_flags = 0;
 	if (has_vector())
 		riscv_v_thread_alloc(p);
-	p->thread.ra = (unsigned long)ret_from_fork_asm;
 	p->thread.sp = (unsigned long)childregs; /* kernel sp */
 	return 0;
 }

-- 
2.43.0

[PATCH v3 3/4] LoongArch: entry: Migrate ret_from_fork() to C

[Charlie Jenkins]

LoongArch is the only architecture that calls
syscall_exit_to_user_mode() from asm. Move the call into C so that this
function can be inlined across all architectures.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
---
 arch/loongarch/include/asm/asm-prototypes.h |  8 +++++++
 arch/loongarch/kernel/entry.S               | 22 +++++++++----------
 arch/loongarch/kernel/process.c             | 33 +++++++++++++++++++++++------
 3 files changed, 45 insertions(+), 18 deletions(-)

diff --git a/arch/loongarch/include/asm/asm-prototypes.h b/arch/loongarch/include/asm/asm-prototypes.h
index 51f224bcfc654228ae423e9a066b25b35102a5b9..704066b4f7368be15be960fadbcd6c2574bbf6c0 100644
--- a/arch/loongarch/include/asm/asm-prototypes.h
+++ b/arch/loongarch/include/asm/asm-prototypes.h
@@ -12,3 +12,11 @@ __int128_t __ashlti3(__int128_t a, int b);
 __int128_t __ashrti3(__int128_t a, int b);
 __int128_t __lshrti3(__int128_t a, int b);
 #endif
+
+asmlinkage void noinstr __no_stack_protector ret_from_fork(struct task_struct *prev,
+							   struct pt_regs *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);
diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S
index 48e7e34e355e83eae8165957ba2eac05a8bf17df..2abc29e573810e000f2fef4646ddca0dbb80eabe 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/process.c b/arch/loongarch/kernel/process.c
index 6e58f65455c7ca3eae2e88ed852c8655a6701e5c..98bc60d7c550fcc0225e8452f81a7d6cd7888015 100644
--- a/arch/loongarch/kernel/process.c
+++ b/arch/loongarch/kernel/process.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
+#include <linux/entry-common.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task.h>
@@ -33,6 +34,7 @@
 #include <linux/prctl.h>
 #include <linux/nmi.h>
 
+#include <asm/asm-prototypes.h>
 #include <asm/asm.h>
 #include <asm/bootinfo.h>
 #include <asm/cpu.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

-- 
2.43.0

[PATCH v3 4/4] entry: Inline syscall_exit_to_user_mode()

[Charlie Jenkins]

Architectures using the generic entry code can be optimized by having
syscall_exit_to_user_mode inlined.

Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
---
 include/linux/entry-common.h | 43 ++++++++++++++++++++++++++++++++++++--
 kernel/entry/common.c        | 49 +-------------------------------------------
 2 files changed, 42 insertions(+), 50 deletions(-)

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index fc61d0205c97084acc89c8e45e088946f5e6d9b2..ee1c400bc0eb0ebb5850f95e856b819fca7b3577 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -14,6 +14,7 @@
 #include <linux/kmsan.h>
 
 #include <asm/entry-common.h>
+#include <asm/syscall.h>
 
 /*
  * Define dummy _TIF work flags if not defined by the architecture or for
@@ -366,6 +367,15 @@ static __always_inline void exit_to_user_mode(void)
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 
+/**
+ * syscall_exit_work - Handle work before returning to user mode
+ * @regs:	Pointer to current pt_regs
+ * @work:	Current thread syscall work
+ *
+ * Do one-time syscall specific work.
+ */
+void syscall_exit_work(struct pt_regs *regs, unsigned long work);
+
 /**
  * syscall_exit_to_user_mode_work - Handle work before returning to user mode
  * @regs:	Pointer to currents pt_regs
@@ -379,7 +389,30 @@ static __always_inline void exit_to_user_mode(void)
  * make the final state transitions. Interrupts must stay disabled between
  * return from this function and the invocation of exit_to_user_mode().
  */
-void syscall_exit_to_user_mode_work(struct pt_regs *regs);
+static __always_inline void syscall_exit_to_user_mode_work(struct pt_regs *regs)
+{
+	unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
+	unsigned long nr = syscall_get_nr(current, regs);
+
+	CT_WARN_ON(ct_state() != PERF_CONTEXT_KERNEL);
+
+	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
+		if (WARN(irqs_disabled(), "syscall %lu left IRQs disabled", nr))
+			local_irq_enable();
+	}
+
+	rseq_syscall(regs);
+
+	/*
+	 * Do one-time syscall specific work. If these work items are
+	 * enabled, we want to run them exactly once per syscall exit with
+	 * interrupts enabled.
+	 */
+	if (unlikely(work & SYSCALL_WORK_EXIT))
+		syscall_exit_work(regs, work);
+	local_irq_disable_exit_to_user();
+	exit_to_user_mode_prepare(regs);
+}
 
 /**
  * syscall_exit_to_user_mode - Handle work before returning to user mode
@@ -410,7 +443,13 @@ void syscall_exit_to_user_mode_work(struct pt_regs *regs);
  * exit_to_user_mode(). This function is preferred unless there is a
  * compelling architectural reason to use the separate functions.
  */
-void syscall_exit_to_user_mode(struct pt_regs *regs);
+static __always_inline void syscall_exit_to_user_mode(struct pt_regs *regs)
+{
+	instrumentation_begin();
+	syscall_exit_to_user_mode_work(regs);
+	instrumentation_end();
+	exit_to_user_mode();
+}
 
 /**
  * irqentry_enter_from_user_mode - Establish state before invoking the irq handler
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index e33691d5adf7aab4af54cf2bf8e5ef5bd6ad1424..f55e421fb196dd5f9d4e34dd85ae096c774cf879 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -146,7 +146,7 @@ static inline bool report_single_step(unsigned long work)
 	return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP;
 }
 
-static void syscall_exit_work(struct pt_regs *regs, unsigned long work)
+void syscall_exit_work(struct pt_regs *regs, unsigned long work)
 {
 	bool step;
 
@@ -173,53 +173,6 @@ static void syscall_exit_work(struct pt_regs *regs, unsigned long work)
 		ptrace_report_syscall_exit(regs, step);
 }
 
-/*
- * Syscall specific exit to user mode preparation. Runs with interrupts
- * enabled.
- */
-static void syscall_exit_to_user_mode_prepare(struct pt_regs *regs)
-{
-	unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
-	unsigned long nr = syscall_get_nr(current, regs);
-
-	CT_WARN_ON(ct_state() != CT_STATE_KERNEL);
-
-	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
-		if (WARN(irqs_disabled(), "syscall %lu left IRQs disabled", nr))
-			local_irq_enable();
-	}
-
-	rseq_syscall(regs);
-
-	/*
-	 * Do one-time syscall specific work. If these work items are
-	 * enabled, we want to run them exactly once per syscall exit with
-	 * interrupts enabled.
-	 */
-	if (unlikely(work & SYSCALL_WORK_EXIT))
-		syscall_exit_work(regs, work);
-}
-
-static __always_inline void __syscall_exit_to_user_mode_work(struct pt_regs *regs)
-{
-	syscall_exit_to_user_mode_prepare(regs);
-	local_irq_disable_exit_to_user();
-	exit_to_user_mode_prepare(regs);
-}
-
-void syscall_exit_to_user_mode_work(struct pt_regs *regs)
-{
-	__syscall_exit_to_user_mode_work(regs);
-}
-
-__visible noinstr void syscall_exit_to_user_mode(struct pt_regs *regs)
-{
-	instrumentation_begin();
-	__syscall_exit_to_user_mode_work(regs);
-	instrumentation_end();
-	exit_to_user_mode();
-}
-
 noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
 {
 	enter_from_user_mode(regs);

-- 
2.43.0

Re: [PATCH v3 4/4] entry: Inline syscall_exit_to_user_mode()

[kernel test robot]

Hello,

kernel test robot noticed "WARNING:at_include/linux/entry-common.h:#ret_from_fork" on:

commit: af2a35e015974bdfa788eebda365a2896b2db87c ("[PATCH v3 4/4] entry: Inline syscall_exit_to_user_mode()")
url: https://github.com/intel-lab-lkp/linux/commits/Charlie-Jenkins/riscv-entry-Convert-ret_from_fork-to-C/20250125-063418
patch link: https://lore.kernel.org/all/20250124-riscv_optimize_entry-v3-4-869f36b9e43b@rivosinc.com/
patch subject: [PATCH v3 4/4] entry: Inline syscall_exit_to_user_mode()

in testcase: boot

config: x86_64-randconfig-004-20250126
compiler: gcc-12
test machine: qemu-system-x86_64 -enable-kvm -cpu SandyBridge -smp 2 -m 16G

(please refer to attached dmesg/kmsg for entire log/backtrace)


+---------------------------------------------------------------+------------+------------+
|                                                               | d05f6a7fc5 | af2a35e015 |
+---------------------------------------------------------------+------------+------------+
| boot_successes                                                | 21         | 0          |
| boot_failures                                                 | 0          | 21         |
| WARNING:at_include/linux/entry-common.h:#ret_from_fork        | 0          | 21         |
| RIP:ret_from_fork                                             | 0          | 21         |
| WARNING:at_include/linux/entry-common.h:#do_int80_emulation   | 0          | 15         |
| RIP:do_int80_emulation                                        | 0          | 15         |
| WARNING:at_include/linux/entry-common.h:#__do_fast_syscall_32 | 0          | 15         |
| RIP:__do_fast_syscall_32                                      | 0          | 15         |
| WARNING:at_include/linux/entry-common.h:#do_syscall_64        | 0          | 6          |
| RIP:do_syscall_64                                             | 0          | 6          |
+---------------------------------------------------------------+------------+------------+


If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <oliver.sang@intel.com>
| Closes: https://lore.kernel.org/oe-lkp/202501272352.d9bc5c3-lkp@intel.com


[  112.344122][   T69] ------------[ cut here ]------------
[ 112.345019][ T69] WARNING: CPU: 0 PID: 69 at include/linux/entry-common.h:397 ret_from_fork (include/linux/entry-common.h:397 include/linux/entry-common.h:449 arch/x86/kernel/process.c:156) 
[  112.346485][   T69] Modules linked in:
[  112.347163][   T69] CPU: 0 UID: 0 PID: 69 Comm: modprobe Not tainted 6.13.0-00004-gaf2a35e01597 #1 214e9f59286a53f9934969c01f519fb8074cbd24
[  112.348970][   T69] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-debian-1.16.2-1 04/01/2014
[ 112.350385][ T69] RIP: 0010:ret_from_fork (include/linux/entry-common.h:397 include/linux/entry-common.h:449 arch/x86/kernel/process.c:156) 
[ 112.351202][ T69] Code: f8 83 e0 07 83 c0 03 38 d0 7c 09 84 d2 74 05 e8 e2 f1 4a 00 41 8b 85 a8 56 1f 00 65 ff 0d 25 06 1b 7f 75 05 0f 1f 44 00 00 90 <0f> 0b 90 9c 58 0f ba e0 09 72 1b 90 48 c7 c7 00 ad 22 83 48 63 f5
All code
========
   0:	f8                   	clc
   1:	83 e0 07             	and    $0x7,%eax
   4:	83 c0 03             	add    $0x3,%eax
   7:	38 d0                	cmp    %dl,%al
   9:	7c 09                	jl     0x14
   b:	84 d2                	test   %dl,%dl
   d:	74 05                	je     0x14
   f:	e8 e2 f1 4a 00       	call   0x4af1f6
  14:	41 8b 85 a8 56 1f 00 	mov    0x1f56a8(%r13),%eax
  1b:	65 ff 0d 25 06 1b 7f 	decl   %gs:0x7f1b0625(%rip)        # 0x7f1b0647
  22:	75 05                	jne    0x29
  24:	0f 1f 44 00 00       	nopl   0x0(%rax,%rax,1)
  29:	90                   	nop
  2a:*	0f 0b                	ud2		<-- trapping instruction
  2c:	90                   	nop
  2d:	9c                   	pushf
  2e:	58                   	pop    %rax
  2f:	0f ba e0 09          	bt     $0x9,%eax
  33:	72 1b                	jb     0x50
  35:	90                   	nop
  36:	48 c7 c7 00 ad 22 83 	mov    $0xffffffff8322ad00,%rdi
  3d:	48 63 f5             	movslq %ebp,%rsi

Code starting with the faulting instruction
===========================================
   0:	0f 0b                	ud2
   2:	90                   	nop
   3:	9c                   	pushf
   4:	58                   	pop    %rax
   5:	0f ba e0 09          	bt     $0x9,%eax
   9:	72 1b                	jb     0x26
   b:	90                   	nop
   c:	48 c7 c7 00 ad 22 83 	mov    $0xffffffff8322ad00,%rdi
  13:	48 63 f5             	movslq %ebp,%rsi
[  112.353759][   T69] RSP: 0000:ffffc900016eff20 EFLAGS: 00010246
[  112.354637][   T69] RAX: 000000000001256c RBX: ffffc900016eff48 RCX: 1ffffffff0aab891
[  112.355762][   T69] RDX: 1ffff11075d7ea00 RSI: 0000000000000006 RDI: ffff8883aebf56a8
[  112.356876][   T69] RBP: 000000000000003b R08: fffffbfff0aac275 R09: 0000000000000000
[  112.358011][   T69] R10: ffffffff8133b7bb R11: fffffbfff0aac274 R12: 0000000000000000
[  112.359131][   T69] R13: ffff8883aea00000 R14: 0000000000000000 R15: 0000000000000000
[  112.360256][   T69] FS:  0000000000000000(0000) GS:ffff8883aea00000(0000) knlGS:0000000000000000
[  112.361495][   T69] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  112.362410][   T69] CR2: 00007fff006efef9 CR3: 000000014ab4d000 CR4: 00000000000406b0
[  112.364674][   T69] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  112.365489][   T69] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  112.366294][   T69] Call Trace:
[  112.366677][   T69]  <TASK>
[ 112.367020][ T69] ? __warn (kernel/panic.c:748) 
[ 112.367509][ T69] ? ret_from_fork (include/linux/entry-common.h:397 include/linux/entry-common.h:449 arch/x86/kernel/process.c:156) 
[ 112.368006][ T69] ? report_bug (lib/bug.c:201 lib/bug.c:219) 
[ 112.368605][ T69] ? ret_from_fork (include/linux/entry-common.h:397 include/linux/entry-common.h:449 arch/x86/kernel/process.c:156) 
[ 112.369094][ T69] ? handle_bug (arch/x86/kernel/traps.c:285) 
[ 112.369551][ T69] ? exc_invalid_op (arch/x86/kernel/traps.c:309 (discriminator 1)) 
[ 112.370039][ T69] ? asm_exc_invalid_op (arch/x86/include/asm/idtentry.h:621) 
[ 112.370572][ T69] ? trace_irq_enable+0xa1/0xda 
[ 112.371195][ T69] ? ret_from_fork (include/linux/entry-common.h:397 include/linux/entry-common.h:449 arch/x86/kernel/process.c:156) 
[ 112.371685][ T69] ? umh_complete (kernel/umh.c:64) 
[ 112.372160][ T69] ret_from_fork_asm (arch/x86/entry/entry_64.S:254) 
[  112.372670][   T69]  </TASK>
[  112.373019][   T69] irq event stamp: 1233
[ 112.373460][ T69] hardirqs last enabled at (1243): __up_console_sem (arch/x86/include/asm/irqflags.h:26 (discriminator 1) arch/x86/include/asm/irqflags.h:87 (discriminator 1) arch/x86/include/asm/irqflags.h:147 (discriminator 1) kernel/printk/printk.c:344 (discriminator 1)) 
[ 112.374413][ T69] hardirqs last disabled at (1254): __up_console_sem (kernel/printk/printk.c:342 (discriminator 1)) 
[ 112.375342][ T69] softirqs last enabled at (928): handle_softirqs (arch/x86/include/asm/preempt.h:26 kernel/softirq.c:408 kernel/softirq.c:589) 
[ 112.376269][ T69] softirqs last disabled at (917): __irq_exit_rcu (kernel/softirq.c:435 kernel/softirq.c:662) 
[  112.377174][   T69] ---[ end trace 0000000000000000 ]---


The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20250127/202501272352.d9bc5c3-lkp@intel.com



-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki