x86: Fix kthread unwind

The rewrite of ret_from_form() misplaced an unwind hint which caused
all kthread stack unwinds to be marked unreliable, breaking
livepatching.

Restore the annotation and add a comment to explain the how and why of
things.

Fixes: 3aec4ecb3d1f ("x86: Rewrite ret_from_fork() in C")
Reported-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Petr Mladek <pmladek@suse.com>
Link: https://lkml.kernel.org/r/20230719201538.GA3553016@hirez.programming.kicks-ass.net

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 91f6818..43606de 100644 (file)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -285,7 +285,15 @@ SYM_FUNC_END(__switch_to_asm)
  */
 .pushsection .text, "ax"
 SYM_CODE_START(ret_from_fork_asm)
-       UNWIND_HINT_REGS
+       /*
+        * This is the start of the kernel stack; even through there's a
+        * register set at the top, the regset isn't necessarily coherent
+        * (consider kthreads) and one cannot unwind further.
+        *
+        * This ensures stack unwinds of kernel threads terminate in a known
+        * good state.
+        */
+       UNWIND_HINT_END_OF_STACK
        ANNOTATE_NOENDBR // copy_thread
        CALL_DEPTH_ACCOUNT
 
@@ -295,6 +303,12 @@ SYM_CODE_START(ret_from_fork_asm)
        movq    %r12, %rcx              /* fn_arg */
        call    ret_from_fork
 
+       /*
+        * Set the stack state to what is expected for the target function
+        * -- at this point the register set should be a valid user set
+        * and unwind should work normally.
+        */
+       UNWIND_HINT_REGS
        jmp     swapgs_restore_regs_and_return_to_usermode
 SYM_CODE_END(ret_from_fork_asm)
 .popsection