[PATCH] powerpc/pseries: Perform full re-add of CPU for topology update post-migration

[Michael Bringmann]

On 10/29/18 1:43 PM, Nathan Fontenot wrote:
> On pseries systems, performing a partition migration can result in
> altering the nodes a CPU is assigned to on the destination system. For
> exampl, pre-migration on the source system CPUs are in node 1 and 3,
> post-migration on the destination system CPUs are in nodes 2 and 3.
> 
> Handling the node change for a CPU can cause corruption in the slab
> cache if we hit a timing where a CPUs node is changed while cache_reap()
> is invoked. The corruption occurs because the slab cache code appears
> to rely on the CPU and slab cache pages being on the same node.
> 
> The current dynamic updating of a CPUs node done in arch/powerpc/mm/numa.c
> does not prevent us from hitting this scenario.
> 
> Changing the device tree property update notification handler that
> recognizes an affinity change for a CPU to do a full DLPAR remove and
> add of the CPU instead of dynamically changing its node resolves this
> issue.
> 
> Signed-off-by: Nathan Fontenot <nfont at linux.vnet.ibm.com
Signed-off-by: Michael W. Bringmann <mwb at linux.vnet.ibm.com>

> ---
>  arch/powerpc/include/asm/topology.h          |    2 ++
>  arch/powerpc/mm/numa.c                       |    9 +--------
>  arch/powerpc/platforms/pseries/hotplug-cpu.c |   19 +++++++++++++++++++
>  3 files changed, 22 insertions(+), 8 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
> index a4a718dbfec6..f85e2b01c3df 100644
> --- a/arch/powerpc/include/asm/topology.h
> +++ b/arch/powerpc/include/asm/topology.h
> @@ -132,6 +132,8 @@ static inline void shared_proc_topology_init(void) {}
>  #define topology_sibling_cpumask(cpu)	(per_cpu(cpu_sibling_map, cpu))
>  #define topology_core_cpumask(cpu)	(per_cpu(cpu_core_map, cpu))
>  #define topology_core_id(cpu)		(cpu_to_core_id(cpu))
> +
> +int dlpar_cpu_readd(int cpu);
>  #endif
>  #endif
> 
> diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
> index 693ae1c1acba..bb6a7b56bef7 100644
> --- a/arch/powerpc/mm/numa.c
> +++ b/arch/powerpc/mm/numa.c
> @@ -1461,13 +1461,6 @@ static void reset_topology_timer(void)
> 
>  #ifdef CONFIG_SMP
> 
> -static void stage_topology_update(int core_id)
> -{
> -	cpumask_or(&cpu_associativity_changes_mask,
> -		&cpu_associativity_changes_mask, cpu_sibling_mask(core_id));
> -	reset_topology_timer();
> -}
> -
>  static int dt_update_callback(struct notifier_block *nb,
>  				unsigned long action, void *data)
>  {
> @@ -1480,7 +1473,7 @@ static int dt_update_callback(struct notifier_block *nb,
>  		    !of_prop_cmp(update->prop->name, "ibm,associativity")) {
>  			u32 core_id;
>  			of_property_read_u32(update->dn, "reg", &core_id);
> -			stage_topology_update(core_id);
> +			rc = dlpar_cpu_readd(core_id);
>  			rc = NOTIFY_OK;
>  		}
>  		break;
> diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
> index 2f8e62163602..97feb6e79f1a 100644
> --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
> +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
> @@ -802,6 +802,25 @@ static int dlpar_cpu_add_by_count(u32 cpus_to_add)
>  	return rc;
>  }
> 
> +int dlpar_cpu_readd(int cpu)
> +{
> +	struct device_node *dn;
> +	struct device *dev;
> +	u32 drc_index;
> +	int rc;
> +
> +	dev = get_cpu_device(cpu);
> +	dn = dev->of_node;
> +
> +	rc = of_property_read_u32(dn, "ibm,my-drc-index", &drc_index);
> +
> +	rc = dlpar_cpu_remove_by_index(drc_index);
> +	if (!rc)
> +		rc = dlpar_cpu_add(drc_index);
> +
> +	return rc;
> +}
> +
>  int dlpar_cpu(struct pseries_hp_errorlog *hp_elog)
>  {
>  	u32 count, drc_index;
> 
> 

-- 
Michael W. Bringmann
Linux Technology Center
IBM Corporation
Tie-Line  363-5196
External: (512) 286-5196
Cell:       (512) 466-0650
mwb at linux.vnet.ibm.com