[PATCH] powerpc: Fix hcall tracepoint recursion

[Li Zefan]

Anton Blanchard wrote:
> Hi,
> 
>> This is a dead loop:
>>
>> trace_hcall_entry() -> trace_clock_global() -> trace_hcall_entry() ..
>>
>> And this is a PPC specific bug. Hope some ppc guys will fix it?
>> Or we kill trace_clock_global() if no one actually uses it..
> 
> Nasty! How does the patch below look? I had to disable irqs otherwise
> we would sometimes drop valid events (if we take an interrupt anywhere
> in the region where depth is elevated, then the entire interrupt will
> be blocked from calling hcall tracepoints.
> 

Thanks!

Subrata, could you test the patch below?

> Anton
> --
> 
> Subject: [PATCH] powerpc: Fix hcall tracepoint recursion
> 
> Spinlocks on shared processor partitions use H_YIELD to notify the
> hypervisor we are waiting on another virtual CPU. Unfortunately this means
> the hcall tracepoints can recurse.
> 
> The patch below adds a percpu depth and checks it on both the entry and
> exit hcall tracepoints.
> 
> Signed-off-by: Anton Blanchard <anton at samba.org>
> ---
> 
> Index: powerpc.git/arch/powerpc/platforms/pseries/lpar.c
> ===================================================================
> --- powerpc.git.orig/arch/powerpc/platforms/pseries/lpar.c	2010-10-21 17:32:00.980003644 +1100
> +++ powerpc.git/arch/powerpc/platforms/pseries/lpar.c	2010-10-21 17:34:54.942681273 +1100
> @@ -701,6 +701,13 @@ EXPORT_SYMBOL(arch_free_page);
>  /* NB: reg/unreg are called while guarded with the tracepoints_mutex */
>  extern long hcall_tracepoint_refcount;
>  
> +/* 
> + * Since the tracing code might execute hcalls we need to guard against
> + * recursion. One example of this are spinlocks calling H_YIELD on
> + * shared processor partitions.
> + */
> +static DEFINE_PER_CPU(unsigned int, hcall_trace_depth);
> +
>  void hcall_tracepoint_regfunc(void)
>  {
>  	hcall_tracepoint_refcount++;
> @@ -713,12 +720,42 @@ void hcall_tracepoint_unregfunc(void)
>  
>  void __trace_hcall_entry(unsigned long opcode, unsigned long *args)
>  {
> +	unsigned long flags;
> +	unsigned int *depth;
> +
> +	local_irq_save(flags);
> +
> +	depth = &__get_cpu_var(hcall_trace_depth);
> +
> +	if (*depth)
> +		goto out;
> +
> +	(*depth)++;
>  	trace_hcall_entry(opcode, args);
> +	(*depth)--;
> +
> +out:
> +	local_irq_restore(flags);
>  }
>  
>  void __trace_hcall_exit(long opcode, unsigned long retval,
>  			unsigned long *retbuf)
>  {
> +	unsigned long flags;
> +	unsigned int *depth;
> +
> +	local_irq_save(flags);
> +
> +	depth = &__get_cpu_var(hcall_trace_depth);
> +
> +	if (*depth)
> +		goto out;
> +
> +	(*depth)++;
>  	trace_hcall_exit(opcode, retval, retbuf);
> +	(*depth)--;
> +
> +out:
> +	local_irq_restore(flags);
>  }
>  #endif
> 
>