From ebd574994c63164d538a197172157318f58ac647 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 23 May 2017 10:37:29 -0500 Subject: [PATCH] Revert "x86/entry: Fix the end of the stack for newly forked tasks" Petr Mladek reported the following warning when loading the livepatch sample module: WARNING: CPU: 1 PID: 3699 at arch/x86/kernel/stacktrace.c:132 save_stack_trace_tsk_reliable+0x133/0x1a0 ... Call Trace: __schedule+0x273/0x820 schedule+0x36/0x80 kthreadd+0x305/0x310 ? kthread_create_on_cpu+0x80/0x80 ? icmp_echo.part.32+0x50/0x50 ret_from_fork+0x2c/0x40 That warning means the end of the stack is no longer recognized as such for newly forked tasks. The problem was introduced with the following commit: ff3f7e2475bb ("x86/entry: Fix the end of the stack for newly forked tasks") ... which was completely misguided. It only partially fixed the reported issue, and it introduced another bug in the process. None of the other entry code saves the frame pointer before calling into C code, so it doesn't make sense for ret_from_fork to do so either. Contrary to what I originally thought, the original issue wasn't related to newly forked tasks. It was actually related to ftrace. When entry code calls into a function which then calls into an ftrace handler, the stack frame looks different than normal. The original issue will be fixed in the unwinder, in a subsequent patch. Reported-by: Petr Mladek Signed-off-by: Josh Poimboeuf Acked-by: Thomas Gleixner Cc: Dave Jones Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Steven Rostedt Cc: live-patching@vger.kernel.org Fixes: ff3f7e2475bb ("x86/entry: Fix the end of the stack for newly forked tasks") Link: http://lkml.kernel.org/r/f350760f7e82f0750c8d1dd093456eb212751caa.1495553739.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_32.S | 30 +++++++++++++++++++----------- arch/x86/entry/entry_64.S | 11 ++++------- 2 files changed, 23 insertions(+), 18 deletions(-) diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 50bc26949e9e..48ef7bb32c42 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -251,6 +251,23 @@ ENTRY(__switch_to_asm) jmp __switch_to 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. * @@ -259,24 +276,15 @@ END(__switch_to_asm) * edi: kernel thread arg */ ENTRY(ret_from_fork) - FRAME_BEGIN /* help unwinder find end of stack */ - - /* - * schedule_tail() is asmlinkage so we have to put its 'prev' argument - * on the stack. - */ - pushl %eax - call schedule_tail - popl %eax + call schedule_tail_wrapper testl %ebx, %ebx jnz 1f /* kernel threads are uncommon */ 2: /* When we fork, we trace the syscall return in the child, too. */ - leal FRAME_OFFSET(%esp), %eax + movl %esp, %eax call syscall_return_slowpath - FRAME_END jmp restore_all /* kernel thread */ diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 607d72c4a485..4a4c0834f965 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -36,7 +36,6 @@ #include #include #include -#include #include .code64 @@ -406,19 +405,17 @@ END(__switch_to_asm) * r12: kernel thread arg */ ENTRY(ret_from_fork) - FRAME_BEGIN /* help unwinder find end of stack */ movq %rax, %rdi - call schedule_tail /* rdi: 'prev' task parameter */ + call schedule_tail /* rdi: 'prev' task parameter */ - testq %rbx, %rbx /* from kernel_thread? */ - jnz 1f /* kernel threads are uncommon */ + testq %rbx, %rbx /* from kernel_thread? */ + jnz 1f /* kernel threads are uncommon */ 2: - leaq FRAME_OFFSET(%rsp),%rdi /* pt_regs pointer */ + movq %rsp, %rdi call syscall_return_slowpath /* returns with IRQs disabled */ TRACE_IRQS_ON /* user mode is traced as IRQS on */ SWAPGS - FRAME_END jmp restore_regs_and_iret 1: