Thanks to all the recent x86 entry code refactoring, most tasks' kernel stacks start at the same offset right below their saved pt_regs, regardless of which syscall was used to enter the kernel. That creates a nice convention which makes it straightforward to identify the end of the stack, which can be useful for the unwinder to verify the stack is sane.
Calling schedule_tail() directly breaks that convention because its an asmlinkage function so its argument has to be pushed on the stack. Add a wrapper which creates a proper "end of stack" frame header before the call. Signed-off-by: Josh Poimboeuf <jpoim...@redhat.com> --- arch/x86/entry/entry_32.S | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index deef561..f0a7444 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -44,6 +44,7 @@ #include <asm/alternative-asm.h> #include <asm/asm.h> #include <asm/smap.h> +#include <asm/frame.h> .section .entry.text, "ax" @@ -237,6 +238,23 @@ ENTRY(__switch_to_asm) END(__switch_to_asm) /* + * The unwinder expects the last frame on the stack to always be at the same + * offset from the end of the page, which allows it to validate the stack. + * Calling schedule_tail() directly would break that convention because its an + * asmlinkage function so its argument has to be pushed on the stack. This + * wrapper creates a proper "end of stack" frame header before the call. + */ +ENTRY(schedule_tail_wrapper) + FRAME_BEGIN + + pushl %eax + call schedule_tail + popl %eax + + FRAME_END + ret +ENDPROC(schedule_tail_wrapper) +/* * A newly forked process directly context switches into this address. * * eax: prev task we switched from @@ -244,9 +262,7 @@ END(__switch_to_asm) * edi: kernel thread arg */ ENTRY(ret_from_fork) - pushl %eax - call schedule_tail - popl %eax + call schedule_tail_wrapper testl %ebx, %ebx jnz 1f /* kernel threads are uncommon */ -- 2.7.4