Re: [PATCH 0/2] [GIT PULL] tracing: various bug fixes

[Steven Rostedt <rostedt@goodmis.org>]

On Thu, 23 Apr 2009, Steven Rostedt wrote:
> 
> static inline void __native_flush_tlb_global(void)
> {
>         unsigned long flags;
>         unsigned long cr4;
> 
>         /*
>          * Read-modify-write to CR4 - protect it from preemption and
>          * from interrupts. (Use the raw variant because this code can
>          * be called from deep inside debugging code.)
>          */
>         raw_local_irq_save(flags);
> 
>         cr4 = read_cr4();
>         /* clear PGE */
>         write_cr4(cr4 & ~X86_CR4_PGE);
>         /* write old PGE again and flush TLBs */
>         write_cr4(cr4);
> 
>         raw_local_irq_restore(flags);
> }
> 
> 
> Each of those read_cr4 and write_cr4 can be traced. But I still do not see 
> how this can cause corruption in the current task struct.
> 
> The TLB just caches the pages we are using, not the contents inside. I 
> still do not see how this can corrupt a bit. Unless a register leaked :-/

Ah, this is a lockdep thing.

The raw_local_irq_save/restore in __native_flush_tlb_global does not 
update hardirqs_enabled.

When we call into ftrace, when we cross page bounderies, we disable 
interrupts using the normal local_irq_save/restore calls.

But when we restore, it detects that interrupts are not going to be 
enabled, and keeps hardirqs_enabled off.

The printk solved the issue because it called local_irq_restore, which set 
the variable back.

I guess there's two solutions here. One, we can change the 
raw_local_irq_enable/disable variants in __native_flush_tlb_global to the 
non-raw type (it should protect against recursion).

or we can try to make the ring buffer use the raw_local_irq variants too. 
I tried this once before, and it did cause issues.

Note, there's a "check_flags" in lockdep, but it is only called on 
locking, it is not called when we only disable/enable interrupts.

-- Steve