powerpc: differentiate kthread from user kernel thread start

Kernel created user threads start similarly to kernel threads in that
they call a kernel function after first returning from _switch, so
they share ret_from_kernel_thread for this. Kernel threads never return
from that function though, whereas user threads often do (although some
don't, e.g., IO threads).

Split these startup functions in two, and catch kernel threads that
improperly return from their function. This is intended to make the
complicated code a little bit easier to understand.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20230325122904.2375060-7-npiggin@gmail.com

diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index c3fdb30..47f0dd9 100644 (file)
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -186,8 +186,8 @@ ret_from_fork:
        li      r3,0    /* fork() return value */
        b       ret_from_syscall
 
-       .globl  ret_from_kernel_thread
-ret_from_kernel_thread:
+       .globl  ret_from_kernel_user_thread
+ret_from_kernel_user_thread:
        bl      schedule_tail
        mtctr   r14
        mr      r3,r15
@@ -196,6 +196,22 @@ ret_from_kernel_thread:
        li      r3,0
        b       ret_from_syscall
 
+       .globl  start_kernel_thread
+start_kernel_thread:
+       bl      schedule_tail
+       mtctr   r14
+       mr      r3,r15
+       PPC440EP_ERR42
+       bctrl
+       /*
+        * This must not return. We actually want to BUG here, not WARN,
+        * because BUG will exit the process which is what the kernel thread
+        * should have done, which may give some hope of continuing.
+        */
+100:   trap
+       EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,0
+
+
 /*
  * This routine switches between two different tasks.  The process
  * state of one is saved on its kernel stack.  Then the state

diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S
index bac1f89..a44c8aa 100644 (file)
--- a/arch/powerpc/kernel/interrupt_64.S
+++ b/arch/powerpc/kernel/interrupt_64.S
@@ -739,7 +739,7 @@ _GLOBAL(ret_from_fork)
        li      r3,0    /* fork() return value */
        b       .Lsyscall_exit
 
-_GLOBAL(ret_from_kernel_thread)
+_GLOBAL(ret_from_kernel_user_thread)
        bl      schedule_tail
        mtctr   r14
        mr      r3,r15
@@ -749,3 +749,19 @@ _GLOBAL(ret_from_kernel_thread)
        bctrl
        li      r3,0
        b       .Lsyscall_exit
+
+_GLOBAL(start_kernel_thread)
+       bl      schedule_tail
+       mtctr   r14
+       mr      r3,r15
+#ifdef CONFIG_PPC64_ELF_ABI_V2
+       mr      r12,r14
+#endif
+       bctrl
+       /*
+        * This must not return. We actually want to BUG here, not WARN,
+        * because BUG will exit the process which is what the kernel thread
+        * should have done, which may give some hope of continuing.
+        */
+100:   trap
+       EMIT_BUG_ENTRY 100b,__FILE__,__LINE__,0

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 88898ca..14fe470 100644 (file)
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1741,7 +1741,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
        struct pt_regs *kregs; /* Switch frame regs */
        extern void ret_from_fork(void);
        extern void ret_from_fork_scv(void);
-       extern void ret_from_kernel_thread(void);
+       extern void ret_from_kernel_user_thread(void);
+       extern void start_kernel_thread(void);
        void (*f)(void);
        unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE;
        struct thread_info *ti = task_thread_info(p);
@@ -1758,7 +1759,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
                sp -= STACK_FRAME_MIN_SIZE;
                ((unsigned long *)sp)[0] = 0;
 
-               f = ret_from_kernel_thread;
+               f = start_kernel_thread;
                p->thread.regs = NULL;  /* no user register state */
                clear_tsk_compat_task(p);
        } else {
@@ -1784,7 +1785,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
                        childregs->softe = IRQS_ENABLED;
 #endif
                        ti->flags |= _TIF_RESTOREALL;
-                       f = ret_from_kernel_thread;
+                       f = ret_from_kernel_user_thread;
                } else {
                        struct pt_regs *regs = current_pt_regs();
                        unsigned long clone_flags = args->flags;