Revert "x86/entry: Fix the end of the stack for newly forked tasks"

commit ebd574994c63164d538a197172157318f58ac647 upstream.

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 <pmladek@suse.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Dave Jones <davej@codemonkey.org.uk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
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 <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 57f7ec35216ef5e2a78efa0d303f8f343b010d68..701d29f8e4d300ac01553e5d8317a5e40dbdcc6d 100644 (file)
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -254,6 +254,23 @@ 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.
  *
@@ -262,24 +279,15 @@ 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 044d18ebc43ce96a512abd1e5f36eb8dfaee0636..5b219707c2f236cfcf1a856cf9a5023dd93775c3 100644 (file)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -36,7 +36,6 @@
 #include <asm/smap.h>
 #include <asm/pgtable_types.h>
 #include <asm/export.h>
-#include <asm/frame.h>
 #include <linux/err.h>
 
 .code64
@@ -409,19 +408,17 @@ 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: