Re: stack unwinder warning.

[Josh Poimboeuf]

On Fri, Jan 06, 2017 at 12:09:47AM -0500, Dave Jones wrote:
> On Thu, Jan 05, 2017 at 11:02:14AM -0600, Josh Poimboeuf wrote:
>  > On Thu, Jan 05, 2017 at 08:52:49AM -0600, Josh Poimboeuf wrote:
>  > > On Tue, Dec 27, 2016 at 02:00:30PM -0500, Dave Jones wrote:
>  > > > I'm not sure what to make of this. Josh ?  (4.10-rc1)
>  > > > 
>  > > > WARNING: kernel stack frame pointer at ffffc900003e7858 in trinity-c6:29122 has bad value ffffffff82103a80
>  > > > unwind stack type:0 next_sp:          (null) mask:2 graph_idx:0
>  > > > ffffc900003e7808: ffffffff811a02e5 (ring_buffer_lock_reserve+0x1d5/0x580)
>  > > > ffffc900003e7810: ffffffff8119adc3 (rb_commit+0x93/0x350)
>  > > > ffffc900003e7818: ffffffff811b31d4 (function_trace_call+0x104/0x1f0)
>  > > > ffffc900003e7820: ffff8804f10ec000 (0xffff8804f10ec000)
>  > > > ffffc900003e7828: 0000000000000000 ...
>  > > > ffffc900003e7830: ffffffff8119b3ae (ring_buffer_unlock_commit+0x8e/0x120)
>  > > > ffffc900003e7838: 0000000000000001 (0x1)
>  > > > ffffc900003e7840: ffffea0002854e00 (0xffffea0002854e00)
>  > > > ffffc900003e7848: 000000000000000a (0xa)
>  > > > ffffc900003e7850: ffffea0002854ec0 (0xffffea0002854ec0)
>  > > > ffffc900003e7858: ffffea000287c480 (0xffffea000287c480)
>  > > 
>  > > The value reported by the warning contradicts the value reported by the
>  > > dump.  So this seems to have been caused by dumping the stack of a task
>  > > which is running on another CPU.  There are still some places in the
>  > > code where that's possible.  So I'm going to need to remove these
>  > > unwinder warnings for now.
>  > 
>  > I'll be submitting the following patch soon, which I think should
>  > silence the warning.  If the warning is recreatable, would you mind
>  > testing it?
> 
> I didn't wait long enough..
> 
> WARNING: kernel stack frame pointer at ffffc90001443f30 in kworker/u8:8:30468 has bad value           (null)
> unwind stack type:0 next_sp:          (null) mask:6 graph_idx:0

This is actually a separate issue.  The below patch should fix it.

Would you mind running it for a bit along with the other patch?


diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 5b21970..044d18e 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -36,6 +36,7 @@
 #include <asm/smap.h>
 #include <asm/pgtable_types.h>
 #include <asm/export.h>
+#include <asm/frame.h>
 #include <linux/err.h>
 
 .code64
@@ -408,17 +409,19 @@ 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:
-	movq	%rsp, %rdi
+	leaq	FRAME_OFFSET(%rsp),%rdi	/* pt_regs pointer */
 	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: