diff mbox series

[v4,2/4] riscv: entry: Split ret_from_fork() into user and kernel

Message ID 20250127-riscv_optimize_entry-v4-2-868cf7702dc9@rivosinc.com (mailing list archive)
State New
Headers show
Series entry: Move ret_from_fork() to C and inline syscall_exit_to_user_mode() | expand

Checks

Context Check Description
bjorn/pre-ci_am success Success
bjorn/build-rv32-defconfig success build-rv32-defconfig
bjorn/build-rv64-clang-allmodconfig success build-rv64-clang-allmodconfig
bjorn/build-rv64-gcc-allmodconfig success build-rv64-gcc-allmodconfig
bjorn/build-rv64-nommu-k210-defconfig success build-rv64-nommu-k210-defconfig
bjorn/build-rv64-nommu-k210-virt success build-rv64-nommu-k210-virt
bjorn/checkpatch warning checkpatch
bjorn/dtb-warn-rv64 success dtb-warn-rv64
bjorn/header-inline success header-inline
bjorn/kdoc success kdoc
bjorn/module-param success module-param
bjorn/verify-fixes success verify-fixes
bjorn/verify-signedoff success verify-signedoff

Commit Message

Charlie Jenkins Jan. 28, 2025, 5:33 a.m. UTC 
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 mbox series

Patch

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;
 }