Re: [PATCH v4 11/14] arm64/numa: support HAVE_MEMORYLESS_NODES

[Leizhen (ThunderTown)]

On 2016/6/8 12:45, Ganapatrao Kulkarni wrote:
> On Wed, Jun 8, 2016 at 7:46 AM, Leizhen (ThunderTown)
>  wrote:
>>
>>
>> On 2016/6/7 22:01, Ganapatrao Kulkarni wrote:
>>> On Tue, Jun 7, 2016 at 6:27 PM, Leizhen (ThunderTown)
>>>  wrote:


 On 2016/6/7 16:31, Ganapatrao Kulkarni wrote:
> On Tue, Jun 7, 2016 at 1:38 PM, Zhen Lei  
> wrote:
>> Some numa nodes may have no memory. For example:
>> 1. cpu0 on node0
>> 2. cpu1 on node1
>> 3. device0 access the momory from node0 and node1 take the same time.
>
> i am wondering, if access to both nodes is same, then why you need numa.
> the example you are quoting is against the basic principle of "numa"
> what is device0 here? cpu?
 The device0 can also be a cpu. I drew a simple diagram:

   cpu0 cpu1cpu2/device0
 ||  |
 ||  |
DDR0 DDR1No DIMM slots or no DIMM plugged
  (node0)  (node1) (node2)

>>>
>>> thanks for the clarification. your example is for 3 node system, where
>>> third node is memory less node.
>>> do you see any issue in supporting this topology with existing code?
>> If opened HAVE_MEMORYLESS_NODES, it will pick the nearest node for the cpus 
>> on
>> memoryless node.
> 
> i see couple of arch enabled HAVE_MEMORYLESS_NODES, but i don't see
> any code in arch specific numa code for this
> is that means the core code will take care of this?
I just spent some time to read the implementation code of HAVE_MEMORYLESS_NODES 
on PPC and IA64.
For NODE_DATA initialization, it's similar to mine on IA64. But PPC have no 
special process, it's
similar to yours. I think the developers of PPC need to fix it.

I picked the code on IA64 as below:
static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize)
{
void *ptr = NULL;
u8 best = 0xff;
int bestnode = -1, node, anynode = 0;

for_each_online_node(node) {
if (node_isset(node, memory_less_mask))
continue;
else if (node_distance(nid, node) < best) {
best = node_distance(nid, node);
bestnode = node;
}
anynode = node;
}

if (bestnode == -1)
bestnode = anynode;

ptr = __alloc_bootmem_node(pgdat_list[bestnode], pernodesize,
PERCPU_PAGE_SIZE, __pa(MAX_DMA_ADDRESS));

return ptr;
}

/**
 * memory_less_nodes - allocate and initialize CPU only nodes pernode
 *  information.
 */
static void __init memory_less_nodes(void)
{
unsigned long pernodesize;
void *pernode;
int node;

for_each_node_mask(node, memory_less_mask) {
pernodesize = compute_pernodesize(node);
pernode = memory_less_node_alloc(node, pernodesize);
fill_pernode(node, __pa(pernode), pernodesize);
}

return;
}



> 
>>
>> For example, in include/linux/topology.h
>> #ifdef CONFIG_HAVE_MEMORYLESS_NODES
>> ...
>> static inline int cpu_to_mem(int cpu)
>> {
>> return per_cpu(_numa_mem_, cpu);
>> }
>> ...
>> #else
>> ...
>> static inline int cpu_to_mem(int cpu)
>> {
>> return cpu_to_node(cpu);
>> }
>> ...
>> #endif
>>
>>> I think, this use case should be supported with present code.
>>>
>>
>> So, we can not simply classify device0 to node0 or node1, but we can
>> define a node2 which distances to node0 and node1 are the same.
>>
>> Signed-off-by: Zhen Lei 
>> ---
>>  arch/arm64/Kconfig  |  4 
>>  arch/arm64/kernel/smp.c |  1 +
>>  arch/arm64/mm/numa.c| 43 +--
>>  3 files changed, 46 insertions(+), 2 deletions(-)
>>
>> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
>> index 05c1bf1..5904a62 100644
>> --- a/arch/arm64/Kconfig
>> +++ b/arch/arm64/Kconfig
>> @@ -581,6 +581,10 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK
>> def_bool y
>> depends on NUMA
>>
>> +config HAVE_MEMORYLESS_NODES
>> +   def_bool y
>> +   depends on NUMA
>> +
>>  source kernel/Kconfig.preempt
>>  source kernel/Kconfig.hz
>>
>> diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
>> index d099306..9e15297 100644
>> --- a/arch/arm64/kernel/smp.c
>> +++ b/arch/arm64/kernel/smp.c
>> @@ -620,6 +620,7 @@ static void __init of_parse_and_init_cpus(void)
>> }
>>
>> bootcpu_valid = true;
>> +   early_map_cpu_to_node(0, of_node_to_nid(dn));
>>
>> /*
>>  * cpu_logical_map has already been
>> diff --git a/arch/arm64/mm/numa.c 

Re: [PATCH v4 11/14] arm64/numa: support HAVE_MEMORYLESS_NODES

[Leizhen (ThunderTown)]

On 2016/6/8 12:45, Ganapatrao Kulkarni wrote:
> On Wed, Jun 8, 2016 at 7:46 AM, Leizhen (ThunderTown)
>  wrote:
>>
>>
>> On 2016/6/7 22:01, Ganapatrao Kulkarni wrote:
>>> On Tue, Jun 7, 2016 at 6:27 PM, Leizhen (ThunderTown)
>>>  wrote:


 On 2016/6/7 16:31, Ganapatrao Kulkarni wrote:
> On Tue, Jun 7, 2016 at 1:38 PM, Zhen Lei  
> wrote:
>> Some numa nodes may have no memory. For example:
>> 1. cpu0 on node0
>> 2. cpu1 on node1
>> 3. device0 access the momory from node0 and node1 take the same time.
>
> i am wondering, if access to both nodes is same, then why you need numa.
> the example you are quoting is against the basic principle of "numa"
> what is device0 here? cpu?
 The device0 can also be a cpu. I drew a simple diagram:

   cpu0 cpu1cpu2/device0
 ||  |
 ||  |
DDR0 DDR1No DIMM slots or no DIMM plugged
  (node0)  (node1) (node2)

>>>
>>> thanks for the clarification. your example is for 3 node system, where
>>> third node is memory less node.
>>> do you see any issue in supporting this topology with existing code?
>> If opened HAVE_MEMORYLESS_NODES, it will pick the nearest node for the cpus 
>> on
>> memoryless node.
> 
> i see couple of arch enabled HAVE_MEMORYLESS_NODES, but i don't see
> any code in arch specific numa code for this
> is that means the core code will take care of this?
I just spent some time to read the implementation code of HAVE_MEMORYLESS_NODES 
on PPC and IA64.
For NODE_DATA initialization, it's similar to mine on IA64. But PPC have no 
special process, it's
similar to yours. I think the developers of PPC need to fix it.

I picked the code on IA64 as below:
static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize)
{
void *ptr = NULL;
u8 best = 0xff;
int bestnode = -1, node, anynode = 0;

for_each_online_node(node) {
if (node_isset(node, memory_less_mask))
continue;
else if (node_distance(nid, node) < best) {
best = node_distance(nid, node);
bestnode = node;
}
anynode = node;
}

if (bestnode == -1)
bestnode = anynode;

ptr = __alloc_bootmem_node(pgdat_list[bestnode], pernodesize,
PERCPU_PAGE_SIZE, __pa(MAX_DMA_ADDRESS));

return ptr;
}

/**
 * memory_less_nodes - allocate and initialize CPU only nodes pernode
 *  information.
 */
static void __init memory_less_nodes(void)
{
unsigned long pernodesize;
void *pernode;
int node;

for_each_node_mask(node, memory_less_mask) {
pernodesize = compute_pernodesize(node);
pernode = memory_less_node_alloc(node, pernodesize);
fill_pernode(node, __pa(pernode), pernodesize);
}

return;
}



> 
>>
>> For example, in include/linux/topology.h
>> #ifdef CONFIG_HAVE_MEMORYLESS_NODES
>> ...
>> static inline int cpu_to_mem(int cpu)
>> {
>> return per_cpu(_numa_mem_, cpu);
>> }
>> ...
>> #else
>> ...
>> static inline int cpu_to_mem(int cpu)
>> {
>> return cpu_to_node(cpu);
>> }
>> ...
>> #endif
>>
>>> I think, this use case should be supported with present code.
>>>
>>
>> So, we can not simply classify device0 to node0 or node1, but we can
>> define a node2 which distances to node0 and node1 are the same.
>>
>> Signed-off-by: Zhen Lei 
>> ---
>>  arch/arm64/Kconfig  |  4 
>>  arch/arm64/kernel/smp.c |  1 +
>>  arch/arm64/mm/numa.c| 43 +--
>>  3 files changed, 46 insertions(+), 2 deletions(-)
>>
>> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
>> index 05c1bf1..5904a62 100644
>> --- a/arch/arm64/Kconfig
>> +++ b/arch/arm64/Kconfig
>> @@ -581,6 +581,10 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK
>> def_bool y
>> depends on NUMA
>>
>> +config HAVE_MEMORYLESS_NODES
>> +   def_bool y
>> +   depends on NUMA
>> +
>>  source kernel/Kconfig.preempt
>>  source kernel/Kconfig.hz
>>
>> diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
>> index d099306..9e15297 100644
>> --- a/arch/arm64/kernel/smp.c
>> +++ b/arch/arm64/kernel/smp.c
>> @@ -620,6 +620,7 @@ static void __init of_parse_and_init_cpus(void)
>> }
>>
>> bootcpu_valid = true;
>> +   early_map_cpu_to_node(0, of_node_to_nid(dn));
>>
>> /*
>>  * cpu_logical_map has already been
>> diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
>> index df5c842..d73b0a0 100644
>> --- a/arch/arm64/mm/numa.c
>> +++ 

Re: [PATCH v4 11/14] arm64/numa: support HAVE_MEMORYLESS_NODES

[Ganapatrao Kulkarni]

On Wed, Jun 8, 2016 at 7:46 AM, Leizhen (ThunderTown)
 wrote:
>
>
> On 2016/6/7 22:01, Ganapatrao Kulkarni wrote:
>> On Tue, Jun 7, 2016 at 6:27 PM, Leizhen (ThunderTown)
>>  wrote:
>>>
>>>
>>> On 2016/6/7 16:31, Ganapatrao Kulkarni wrote:
 On Tue, Jun 7, 2016 at 1:38 PM, Zhen Lei  
 wrote:
> Some numa nodes may have no memory. For example:
> 1. cpu0 on node0
> 2. cpu1 on node1
> 3. device0 access the momory from node0 and node1 take the same time.

 i am wondering, if access to both nodes is same, then why you need numa.
 the example you are quoting is against the basic principle of "numa"
 what is device0 here? cpu?
>>> The device0 can also be a cpu. I drew a simple diagram:
>>>
>>>   cpu0 cpu1cpu2/device0
>>> ||  |
>>> ||  |
>>>DDR0 DDR1No DIMM slots or no DIMM plugged
>>>  (node0)  (node1) (node2)
>>>
>>
>> thanks for the clarification. your example is for 3 node system, where
>> third node is memory less node.
>> do you see any issue in supporting this topology with existing code?
> If opened HAVE_MEMORYLESS_NODES, it will pick the nearest node for the cpus on
> memoryless node.

i see couple of arch enabled HAVE_MEMORYLESS_NODES, but i don't see
any code in arch specific numa code for this.
is that means the core code will take care of this?

>
> For example, in include/linux/topology.h
> #ifdef CONFIG_HAVE_MEMORYLESS_NODES
> ...
> static inline int cpu_to_mem(int cpu)
> {
> return per_cpu(_numa_mem_, cpu);
> }
> ...
> #else
> ...
> static inline int cpu_to_mem(int cpu)
> {
> return cpu_to_node(cpu);
> }
> ...
> #endif
>
>> I think, this use case should be supported with present code.
>>
>
> So, we can not simply classify device0 to node0 or node1, but we can
> define a node2 which distances to node0 and node1 are the same.
>
> Signed-off-by: Zhen Lei 
> ---
>  arch/arm64/Kconfig  |  4 
>  arch/arm64/kernel/smp.c |  1 +
>  arch/arm64/mm/numa.c| 43 +--
>  3 files changed, 46 insertions(+), 2 deletions(-)
>
> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index 05c1bf1..5904a62 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -581,6 +581,10 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK
> def_bool y
> depends on NUMA
>
> +config HAVE_MEMORYLESS_NODES
> +   def_bool y
> +   depends on NUMA
> +
>  source kernel/Kconfig.preempt
>  source kernel/Kconfig.hz
>
> diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
> index d099306..9e15297 100644
> --- a/arch/arm64/kernel/smp.c
> +++ b/arch/arm64/kernel/smp.c
> @@ -620,6 +620,7 @@ static void __init of_parse_and_init_cpus(void)
> }
>
> bootcpu_valid = true;
> +   early_map_cpu_to_node(0, of_node_to_nid(dn));
>
> /*
>  * cpu_logical_map has already been
> diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
> index df5c842..d73b0a0 100644
> --- a/arch/arm64/mm/numa.c
> +++ b/arch/arm64/mm/numa.c
> @@ -128,6 +128,14 @@ void __init early_map_cpu_to_node(unsigned int cpu, 
> int nid)
> nid = 0;
>
> cpu_to_node_map[cpu] = nid;
> +
> +   /*
> +* We should set the numa node of cpu0 as soon as possible, 
> because it
> +* has already been set up online before. cpu_to_node(0) will 
> soon be
> +* called.
> +*/
> +   if (!cpu)
> +   set_cpu_numa_node(cpu, nid);
>  }
>
>  #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
> @@ -215,6 +223,35 @@ int __init numa_add_memblk(int nid, u64 start, u64 
> end)
> return ret;
>  }
>
> +static u64 __init alloc_node_data_from_nearest_node(int nid, const 
> size_t size)
> +{
> +   int i, best_nid, distance;
> +   u64 pa;
> +   DECLARE_BITMAP(nodes_map, MAX_NUMNODES);
> +
> +   bitmap_zero(nodes_map, MAX_NUMNODES);
> +   bitmap_set(nodes_map, nid, 1);
> +
> +find_nearest_node:
> +   best_nid = NUMA_NO_NODE;
> +   distance = INT_MAX;
> +
> +   for_each_clear_bit(i, nodes_map, MAX_NUMNODES)
> +   if (numa_distance[nid][i] < distance) {
> +   best_nid = i;
> +   distance = numa_distance[nid][i];
> +   }
> +
> +   pa = memblock_alloc_nid(size, SMP_CACHE_BYTES, best_nid);
> +   if (!pa) {
> +   BUG_ON(best_nid == NUMA_NO_NODE);
> +   

Re: [PATCH v4 11/14] arm64/numa: support HAVE_MEMORYLESS_NODES

[Ganapatrao Kulkarni]

On Wed, Jun 8, 2016 at 7:46 AM, Leizhen (ThunderTown)
 wrote:
>
>
> On 2016/6/7 22:01, Ganapatrao Kulkarni wrote:
>> On Tue, Jun 7, 2016 at 6:27 PM, Leizhen (ThunderTown)
>>  wrote:
>>>
>>>
>>> On 2016/6/7 16:31, Ganapatrao Kulkarni wrote:
 On Tue, Jun 7, 2016 at 1:38 PM, Zhen Lei  
 wrote:
> Some numa nodes may have no memory. For example:
> 1. cpu0 on node0
> 2. cpu1 on node1
> 3. device0 access the momory from node0 and node1 take the same time.

 i am wondering, if access to both nodes is same, then why you need numa.
 the example you are quoting is against the basic principle of "numa"
 what is device0 here? cpu?
>>> The device0 can also be a cpu. I drew a simple diagram:
>>>
>>>   cpu0 cpu1cpu2/device0
>>> ||  |
>>> ||  |
>>>DDR0 DDR1No DIMM slots or no DIMM plugged
>>>  (node0)  (node1) (node2)
>>>
>>
>> thanks for the clarification. your example is for 3 node system, where
>> third node is memory less node.
>> do you see any issue in supporting this topology with existing code?
> If opened HAVE_MEMORYLESS_NODES, it will pick the nearest node for the cpus on
> memoryless node.

i see couple of arch enabled HAVE_MEMORYLESS_NODES, but i don't see
any code in arch specific numa code for this.
is that means the core code will take care of this?

>
> For example, in include/linux/topology.h
> #ifdef CONFIG_HAVE_MEMORYLESS_NODES
> ...
> static inline int cpu_to_mem(int cpu)
> {
> return per_cpu(_numa_mem_, cpu);
> }
> ...
> #else
> ...
> static inline int cpu_to_mem(int cpu)
> {
> return cpu_to_node(cpu);
> }
> ...
> #endif
>
>> I think, this use case should be supported with present code.
>>
>
> So, we can not simply classify device0 to node0 or node1, but we can
> define a node2 which distances to node0 and node1 are the same.
>
> Signed-off-by: Zhen Lei 
> ---
>  arch/arm64/Kconfig  |  4 
>  arch/arm64/kernel/smp.c |  1 +
>  arch/arm64/mm/numa.c| 43 +--
>  3 files changed, 46 insertions(+), 2 deletions(-)
>
> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index 05c1bf1..5904a62 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -581,6 +581,10 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK
> def_bool y
> depends on NUMA
>
> +config HAVE_MEMORYLESS_NODES
> +   def_bool y
> +   depends on NUMA
> +
>  source kernel/Kconfig.preempt
>  source kernel/Kconfig.hz
>
> diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
> index d099306..9e15297 100644
> --- a/arch/arm64/kernel/smp.c
> +++ b/arch/arm64/kernel/smp.c
> @@ -620,6 +620,7 @@ static void __init of_parse_and_init_cpus(void)
> }
>
> bootcpu_valid = true;
> +   early_map_cpu_to_node(0, of_node_to_nid(dn));
>
> /*
>  * cpu_logical_map has already been
> diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
> index df5c842..d73b0a0 100644
> --- a/arch/arm64/mm/numa.c
> +++ b/arch/arm64/mm/numa.c
> @@ -128,6 +128,14 @@ void __init early_map_cpu_to_node(unsigned int cpu, 
> int nid)
> nid = 0;
>
> cpu_to_node_map[cpu] = nid;
> +
> +   /*
> +* We should set the numa node of cpu0 as soon as possible, 
> because it
> +* has already been set up online before. cpu_to_node(0) will 
> soon be
> +* called.
> +*/
> +   if (!cpu)
> +   set_cpu_numa_node(cpu, nid);
>  }
>
>  #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
> @@ -215,6 +223,35 @@ int __init numa_add_memblk(int nid, u64 start, u64 
> end)
> return ret;
>  }
>
> +static u64 __init alloc_node_data_from_nearest_node(int nid, const 
> size_t size)
> +{
> +   int i, best_nid, distance;
> +   u64 pa;
> +   DECLARE_BITMAP(nodes_map, MAX_NUMNODES);
> +
> +   bitmap_zero(nodes_map, MAX_NUMNODES);
> +   bitmap_set(nodes_map, nid, 1);
> +
> +find_nearest_node:
> +   best_nid = NUMA_NO_NODE;
> +   distance = INT_MAX;
> +
> +   for_each_clear_bit(i, nodes_map, MAX_NUMNODES)
> +   if (numa_distance[nid][i] < distance) {
> +   best_nid = i;
> +   distance = numa_distance[nid][i];
> +   }
> +
> +   pa = memblock_alloc_nid(size, SMP_CACHE_BYTES, best_nid);
> +   if (!pa) {
> +   BUG_ON(best_nid == NUMA_NO_NODE);
> +   bitmap_set(nodes_map, best_nid, 1);
> +   goto find_nearest_node;
> +   }
> +

Re: [PATCH v4 11/14] arm64/numa: support HAVE_MEMORYLESS_NODES

[Leizhen (ThunderTown)]

On 2016/6/7 22:01, Ganapatrao Kulkarni wrote:
> On Tue, Jun 7, 2016 at 6:27 PM, Leizhen (ThunderTown)
>  wrote:
>>
>>
>> On 2016/6/7 16:31, Ganapatrao Kulkarni wrote:
>>> On Tue, Jun 7, 2016 at 1:38 PM, Zhen Lei  wrote:
 Some numa nodes may have no memory. For example:
 1. cpu0 on node0
 2. cpu1 on node1
 3. device0 access the momory from node0 and node1 take the same time.
>>>
>>> i am wondering, if access to both nodes is same, then why you need numa.
>>> the example you are quoting is against the basic principle of "numa"
>>> what is device0 here? cpu?
>> The device0 can also be a cpu. I drew a simple diagram:
>>
>>   cpu0 cpu1cpu2/device0
>> ||  |
>> ||  |
>>DDR0 DDR1No DIMM slots or no DIMM plugged
>>  (node0)  (node1) (node2)
>>
> 
> thanks for the clarification. your example is for 3 node system, where
> third node is memory less node.
> do you see any issue in supporting this topology with existing code?
If opened HAVE_MEMORYLESS_NODES, it will pick the nearest node for the cpus on
memoryless node.

For example, in include/linux/topology.h
#ifdef CONFIG_HAVE_MEMORYLESS_NODES
...
static inline int cpu_to_mem(int cpu)
{
return per_cpu(_numa_mem_, cpu);
}
...
#else
...
static inline int cpu_to_mem(int cpu)
{
return cpu_to_node(cpu);
}
...
#endif

> I think, this use case should be supported with present code.
> 

 So, we can not simply classify device0 to node0 or node1, but we can
 define a node2 which distances to node0 and node1 are the same.

 Signed-off-by: Zhen Lei 
 ---
  arch/arm64/Kconfig  |  4 
  arch/arm64/kernel/smp.c |  1 +
  arch/arm64/mm/numa.c| 43 +--
  3 files changed, 46 insertions(+), 2 deletions(-)

 diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
 index 05c1bf1..5904a62 100644
 --- a/arch/arm64/Kconfig
 +++ b/arch/arm64/Kconfig
 @@ -581,6 +581,10 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK
 def_bool y
 depends on NUMA

 +config HAVE_MEMORYLESS_NODES
 +   def_bool y
 +   depends on NUMA
 +
  source kernel/Kconfig.preempt
  source kernel/Kconfig.hz

 diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
 index d099306..9e15297 100644
 --- a/arch/arm64/kernel/smp.c
 +++ b/arch/arm64/kernel/smp.c
 @@ -620,6 +620,7 @@ static void __init of_parse_and_init_cpus(void)
 }

 bootcpu_valid = true;
 +   early_map_cpu_to_node(0, of_node_to_nid(dn));

 /*
  * cpu_logical_map has already been
 diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
 index df5c842..d73b0a0 100644
 --- a/arch/arm64/mm/numa.c
 +++ b/arch/arm64/mm/numa.c
 @@ -128,6 +128,14 @@ void __init early_map_cpu_to_node(unsigned int cpu, 
 int nid)
 nid = 0;

 cpu_to_node_map[cpu] = nid;
 +
 +   /*
 +* We should set the numa node of cpu0 as soon as possible, 
 because it
 +* has already been set up online before. cpu_to_node(0) will soon 
 be
 +* called.
 +*/
 +   if (!cpu)
 +   set_cpu_numa_node(cpu, nid);
  }

  #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
 @@ -215,6 +223,35 @@ int __init numa_add_memblk(int nid, u64 start, u64 
 end)
 return ret;
  }

 +static u64 __init alloc_node_data_from_nearest_node(int nid, const size_t 
 size)
 +{
 +   int i, best_nid, distance;
 +   u64 pa;
 +   DECLARE_BITMAP(nodes_map, MAX_NUMNODES);
 +
 +   bitmap_zero(nodes_map, MAX_NUMNODES);
 +   bitmap_set(nodes_map, nid, 1);
 +
 +find_nearest_node:
 +   best_nid = NUMA_NO_NODE;
 +   distance = INT_MAX;
 +
 +   for_each_clear_bit(i, nodes_map, MAX_NUMNODES)
 +   if (numa_distance[nid][i] < distance) {
 +   best_nid = i;
 +   distance = numa_distance[nid][i];
 +   }
 +
 +   pa = memblock_alloc_nid(size, SMP_CACHE_BYTES, best_nid);
 +   if (!pa) {
 +   BUG_ON(best_nid == NUMA_NO_NODE);
 +   bitmap_set(nodes_map, best_nid, 1);
 +   goto find_nearest_node;
 +   }
 +
 +   return pa;
 +}
 +
> 
> why do we need this function in arch specific code.
I also considered put these code(include HAVE_SETUP_PER_CPU_AREA) into 
drivers/of/of_numa.c,
but if I do that, it will make acpi numa dependent on of numa.

> dont you think common code will take care of this? when 

Re: [PATCH v4 11/14] arm64/numa: support HAVE_MEMORYLESS_NODES

[Leizhen (ThunderTown)]

On 2016/6/7 22:01, Ganapatrao Kulkarni wrote:
> On Tue, Jun 7, 2016 at 6:27 PM, Leizhen (ThunderTown)
>  wrote:
>>
>>
>> On 2016/6/7 16:31, Ganapatrao Kulkarni wrote:
>>> On Tue, Jun 7, 2016 at 1:38 PM, Zhen Lei  wrote:
 Some numa nodes may have no memory. For example:
 1. cpu0 on node0
 2. cpu1 on node1
 3. device0 access the momory from node0 and node1 take the same time.
>>>
>>> i am wondering, if access to both nodes is same, then why you need numa.
>>> the example you are quoting is against the basic principle of "numa"
>>> what is device0 here? cpu?
>> The device0 can also be a cpu. I drew a simple diagram:
>>
>>   cpu0 cpu1cpu2/device0
>> ||  |
>> ||  |
>>DDR0 DDR1No DIMM slots or no DIMM plugged
>>  (node0)  (node1) (node2)
>>
> 
> thanks for the clarification. your example is for 3 node system, where
> third node is memory less node.
> do you see any issue in supporting this topology with existing code?
If opened HAVE_MEMORYLESS_NODES, it will pick the nearest node for the cpus on
memoryless node.

For example, in include/linux/topology.h
#ifdef CONFIG_HAVE_MEMORYLESS_NODES
...
static inline int cpu_to_mem(int cpu)
{
return per_cpu(_numa_mem_, cpu);
}
...
#else
...
static inline int cpu_to_mem(int cpu)
{
return cpu_to_node(cpu);
}
...
#endif

> I think, this use case should be supported with present code.
> 

 So, we can not simply classify device0 to node0 or node1, but we can
 define a node2 which distances to node0 and node1 are the same.

 Signed-off-by: Zhen Lei 
 ---
  arch/arm64/Kconfig  |  4 
  arch/arm64/kernel/smp.c |  1 +
  arch/arm64/mm/numa.c| 43 +--
  3 files changed, 46 insertions(+), 2 deletions(-)

 diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
 index 05c1bf1..5904a62 100644
 --- a/arch/arm64/Kconfig
 +++ b/arch/arm64/Kconfig
 @@ -581,6 +581,10 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK
 def_bool y
 depends on NUMA

 +config HAVE_MEMORYLESS_NODES
 +   def_bool y
 +   depends on NUMA
 +
  source kernel/Kconfig.preempt
  source kernel/Kconfig.hz

 diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
 index d099306..9e15297 100644
 --- a/arch/arm64/kernel/smp.c
 +++ b/arch/arm64/kernel/smp.c
 @@ -620,6 +620,7 @@ static void __init of_parse_and_init_cpus(void)
 }

 bootcpu_valid = true;
 +   early_map_cpu_to_node(0, of_node_to_nid(dn));

 /*
  * cpu_logical_map has already been
 diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
 index df5c842..d73b0a0 100644
 --- a/arch/arm64/mm/numa.c
 +++ b/arch/arm64/mm/numa.c
 @@ -128,6 +128,14 @@ void __init early_map_cpu_to_node(unsigned int cpu, 
 int nid)
 nid = 0;

 cpu_to_node_map[cpu] = nid;
 +
 +   /*
 +* We should set the numa node of cpu0 as soon as possible, 
 because it
 +* has already been set up online before. cpu_to_node(0) will soon 
 be
 +* called.
 +*/
 +   if (!cpu)
 +   set_cpu_numa_node(cpu, nid);
  }

  #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
 @@ -215,6 +223,35 @@ int __init numa_add_memblk(int nid, u64 start, u64 
 end)
 return ret;
  }

 +static u64 __init alloc_node_data_from_nearest_node(int nid, const size_t 
 size)
 +{
 +   int i, best_nid, distance;
 +   u64 pa;
 +   DECLARE_BITMAP(nodes_map, MAX_NUMNODES);
 +
 +   bitmap_zero(nodes_map, MAX_NUMNODES);
 +   bitmap_set(nodes_map, nid, 1);
 +
 +find_nearest_node:
 +   best_nid = NUMA_NO_NODE;
 +   distance = INT_MAX;
 +
 +   for_each_clear_bit(i, nodes_map, MAX_NUMNODES)
 +   if (numa_distance[nid][i] < distance) {
 +   best_nid = i;
 +   distance = numa_distance[nid][i];
 +   }
 +
 +   pa = memblock_alloc_nid(size, SMP_CACHE_BYTES, best_nid);
 +   if (!pa) {
 +   BUG_ON(best_nid == NUMA_NO_NODE);
 +   bitmap_set(nodes_map, best_nid, 1);
 +   goto find_nearest_node;
 +   }
 +
 +   return pa;
 +}
 +
> 
> why do we need this function in arch specific code.
I also considered put these code(include HAVE_SETUP_PER_CPU_AREA) into 
drivers/of/of_numa.c,
but if I do that, it will make acpi numa dependent on of numa.

> dont you think common code will take care of this? when you define
> HAVE_MEMORYLESS_NODES

I have searched CONFIG_HAVE_MEMORYLESS_NODES in 

Re: [PATCH v4 11/14] arm64/numa: support HAVE_MEMORYLESS_NODES

[Ganapatrao Kulkarni]

On Tue, Jun 7, 2016 at 6:27 PM, Leizhen (ThunderTown)
 wrote:
>
>
> On 2016/6/7 16:31, Ganapatrao Kulkarni wrote:
>> On Tue, Jun 7, 2016 at 1:38 PM, Zhen Lei  wrote:
>>> Some numa nodes may have no memory. For example:
>>> 1. cpu0 on node0
>>> 2. cpu1 on node1
>>> 3. device0 access the momory from node0 and node1 take the same time.
>>
>> i am wondering, if access to both nodes is same, then why you need numa.
>> the example you are quoting is against the basic principle of "numa"
>> what is device0 here? cpu?
> The device0 can also be a cpu. I drew a simple diagram:
>
>   cpu0 cpu1cpu2/device0
> ||  |
> ||  |
>DDR0 DDR1No DIMM slots or no DIMM plugged
>  (node0)  (node1) (node2)
>

thanks for the clarification. your example is for 3 node system, where
third node is memory less node.
do you see any issue in supporting this topology with existing code?
I think, this use case should be supported with present code.

>>>
>>> So, we can not simply classify device0 to node0 or node1, but we can
>>> define a node2 which distances to node0 and node1 are the same.
>>>
>>> Signed-off-by: Zhen Lei 
>>> ---
>>>  arch/arm64/Kconfig  |  4 
>>>  arch/arm64/kernel/smp.c |  1 +
>>>  arch/arm64/mm/numa.c| 43 +--
>>>  3 files changed, 46 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
>>> index 05c1bf1..5904a62 100644
>>> --- a/arch/arm64/Kconfig
>>> +++ b/arch/arm64/Kconfig
>>> @@ -581,6 +581,10 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK
>>> def_bool y
>>> depends on NUMA
>>>
>>> +config HAVE_MEMORYLESS_NODES
>>> +   def_bool y
>>> +   depends on NUMA
>>> +
>>>  source kernel/Kconfig.preempt
>>>  source kernel/Kconfig.hz
>>>
>>> diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
>>> index d099306..9e15297 100644
>>> --- a/arch/arm64/kernel/smp.c
>>> +++ b/arch/arm64/kernel/smp.c
>>> @@ -620,6 +620,7 @@ static void __init of_parse_and_init_cpus(void)
>>> }
>>>
>>> bootcpu_valid = true;
>>> +   early_map_cpu_to_node(0, of_node_to_nid(dn));
>>>
>>> /*
>>>  * cpu_logical_map has already been
>>> diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
>>> index df5c842..d73b0a0 100644
>>> --- a/arch/arm64/mm/numa.c
>>> +++ b/arch/arm64/mm/numa.c
>>> @@ -128,6 +128,14 @@ void __init early_map_cpu_to_node(unsigned int cpu, 
>>> int nid)
>>> nid = 0;
>>>
>>> cpu_to_node_map[cpu] = nid;
>>> +
>>> +   /*
>>> +* We should set the numa node of cpu0 as soon as possible, because 
>>> it
>>> +* has already been set up online before. cpu_to_node(0) will soon 
>>> be
>>> +* called.
>>> +*/
>>> +   if (!cpu)
>>> +   set_cpu_numa_node(cpu, nid);
>>>  }
>>>
>>>  #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
>>> @@ -215,6 +223,35 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
>>> return ret;
>>>  }
>>>
>>> +static u64 __init alloc_node_data_from_nearest_node(int nid, const size_t 
>>> size)
>>> +{
>>> +   int i, best_nid, distance;
>>> +   u64 pa;
>>> +   DECLARE_BITMAP(nodes_map, MAX_NUMNODES);
>>> +
>>> +   bitmap_zero(nodes_map, MAX_NUMNODES);
>>> +   bitmap_set(nodes_map, nid, 1);
>>> +
>>> +find_nearest_node:
>>> +   best_nid = NUMA_NO_NODE;
>>> +   distance = INT_MAX;
>>> +
>>> +   for_each_clear_bit(i, nodes_map, MAX_NUMNODES)
>>> +   if (numa_distance[nid][i] < distance) {
>>> +   best_nid = i;
>>> +   distance = numa_distance[nid][i];
>>> +   }
>>> +
>>> +   pa = memblock_alloc_nid(size, SMP_CACHE_BYTES, best_nid);
>>> +   if (!pa) {
>>> +   BUG_ON(best_nid == NUMA_NO_NODE);
>>> +   bitmap_set(nodes_map, best_nid, 1);
>>> +   goto find_nearest_node;
>>> +   }
>>> +
>>> +   return pa;
>>> +}
>>> +

why do we need this function in arch specific code.
dont you think common code will take care of this? when you define
HAVE_MEMORYLESS_NODES

>>>  /**
>>>   * Initialize NODE_DATA for a node on the local memory
>>>   */
>>> @@ -228,7 +265,9 @@ static void __init setup_node_data(int nid, u64 
>>> start_pfn, u64 end_pfn)
>>> pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
>>> nid, start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
>>>
>>> -   nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);

this function try to allocate from a nid, if fails, it allocates from
node 0(local node).
this is ok for memory less node i guess.

>>> +   nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
>>> +   if (!nd_pa)
>>> +   nd_pa = 

Re: [PATCH v4 11/14] arm64/numa: support HAVE_MEMORYLESS_NODES

[Ganapatrao Kulkarni]

On Tue, Jun 7, 2016 at 6:27 PM, Leizhen (ThunderTown)
 wrote:
>
>
> On 2016/6/7 16:31, Ganapatrao Kulkarni wrote:
>> On Tue, Jun 7, 2016 at 1:38 PM, Zhen Lei  wrote:
>>> Some numa nodes may have no memory. For example:
>>> 1. cpu0 on node0
>>> 2. cpu1 on node1
>>> 3. device0 access the momory from node0 and node1 take the same time.
>>
>> i am wondering, if access to both nodes is same, then why you need numa.
>> the example you are quoting is against the basic principle of "numa"
>> what is device0 here? cpu?
> The device0 can also be a cpu. I drew a simple diagram:
>
>   cpu0 cpu1cpu2/device0
> ||  |
> ||  |
>DDR0 DDR1No DIMM slots or no DIMM plugged
>  (node0)  (node1) (node2)
>

thanks for the clarification. your example is for 3 node system, where
third node is memory less node.
do you see any issue in supporting this topology with existing code?
I think, this use case should be supported with present code.

>>>
>>> So, we can not simply classify device0 to node0 or node1, but we can
>>> define a node2 which distances to node0 and node1 are the same.
>>>
>>> Signed-off-by: Zhen Lei 
>>> ---
>>>  arch/arm64/Kconfig  |  4 
>>>  arch/arm64/kernel/smp.c |  1 +
>>>  arch/arm64/mm/numa.c| 43 +--
>>>  3 files changed, 46 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
>>> index 05c1bf1..5904a62 100644
>>> --- a/arch/arm64/Kconfig
>>> +++ b/arch/arm64/Kconfig
>>> @@ -581,6 +581,10 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK
>>> def_bool y
>>> depends on NUMA
>>>
>>> +config HAVE_MEMORYLESS_NODES
>>> +   def_bool y
>>> +   depends on NUMA
>>> +
>>>  source kernel/Kconfig.preempt
>>>  source kernel/Kconfig.hz
>>>
>>> diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
>>> index d099306..9e15297 100644
>>> --- a/arch/arm64/kernel/smp.c
>>> +++ b/arch/arm64/kernel/smp.c
>>> @@ -620,6 +620,7 @@ static void __init of_parse_and_init_cpus(void)
>>> }
>>>
>>> bootcpu_valid = true;
>>> +   early_map_cpu_to_node(0, of_node_to_nid(dn));
>>>
>>> /*
>>>  * cpu_logical_map has already been
>>> diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
>>> index df5c842..d73b0a0 100644
>>> --- a/arch/arm64/mm/numa.c
>>> +++ b/arch/arm64/mm/numa.c
>>> @@ -128,6 +128,14 @@ void __init early_map_cpu_to_node(unsigned int cpu, 
>>> int nid)
>>> nid = 0;
>>>
>>> cpu_to_node_map[cpu] = nid;
>>> +
>>> +   /*
>>> +* We should set the numa node of cpu0 as soon as possible, because 
>>> it
>>> +* has already been set up online before. cpu_to_node(0) will soon 
>>> be
>>> +* called.
>>> +*/
>>> +   if (!cpu)
>>> +   set_cpu_numa_node(cpu, nid);
>>>  }
>>>
>>>  #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
>>> @@ -215,6 +223,35 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
>>> return ret;
>>>  }
>>>
>>> +static u64 __init alloc_node_data_from_nearest_node(int nid, const size_t 
>>> size)
>>> +{
>>> +   int i, best_nid, distance;
>>> +   u64 pa;
>>> +   DECLARE_BITMAP(nodes_map, MAX_NUMNODES);
>>> +
>>> +   bitmap_zero(nodes_map, MAX_NUMNODES);
>>> +   bitmap_set(nodes_map, nid, 1);
>>> +
>>> +find_nearest_node:
>>> +   best_nid = NUMA_NO_NODE;
>>> +   distance = INT_MAX;
>>> +
>>> +   for_each_clear_bit(i, nodes_map, MAX_NUMNODES)
>>> +   if (numa_distance[nid][i] < distance) {
>>> +   best_nid = i;
>>> +   distance = numa_distance[nid][i];
>>> +   }
>>> +
>>> +   pa = memblock_alloc_nid(size, SMP_CACHE_BYTES, best_nid);
>>> +   if (!pa) {
>>> +   BUG_ON(best_nid == NUMA_NO_NODE);
>>> +   bitmap_set(nodes_map, best_nid, 1);
>>> +   goto find_nearest_node;
>>> +   }
>>> +
>>> +   return pa;
>>> +}
>>> +

why do we need this function in arch specific code.
dont you think common code will take care of this? when you define
HAVE_MEMORYLESS_NODES

>>>  /**
>>>   * Initialize NODE_DATA for a node on the local memory
>>>   */
>>> @@ -228,7 +265,9 @@ static void __init setup_node_data(int nid, u64 
>>> start_pfn, u64 end_pfn)
>>> pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
>>> nid, start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
>>>
>>> -   nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);

this function try to allocate from a nid, if fails, it allocates from
node 0(local node).
this is ok for memory less node i guess.

>>> +   nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
>>> +   if (!nd_pa)
>>> +   nd_pa = alloc_node_data_from_nearest_node(nid, nd_size);
>>> nd = __va(nd_pa);
>>>
>>> /* 

Re: [PATCH v4 11/14] arm64/numa: support HAVE_MEMORYLESS_NODES

[Leizhen (ThunderTown)]

On 2016/6/7 16:31, Ganapatrao Kulkarni wrote:
> On Tue, Jun 7, 2016 at 1:38 PM, Zhen Lei  wrote:
>> Some numa nodes may have no memory. For example:
>> 1. cpu0 on node0
>> 2. cpu1 on node1
>> 3. device0 access the momory from node0 and node1 take the same time.
> 
> i am wondering, if access to both nodes is same, then why you need numa.
> the example you are quoting is against the basic principle of "numa"
> what is device0 here? cpu?
The device0 can also be a cpu. I drew a simple diagram:

  cpu0 cpu1cpu2/device0
||  |
||  |
   DDR0 DDR1No DIMM slots or no DIMM plugged
 (node0)  (node1) (node2)

>>
>> So, we can not simply classify device0 to node0 or node1, but we can
>> define a node2 which distances to node0 and node1 are the same.
>>
>> Signed-off-by: Zhen Lei 
>> ---
>>  arch/arm64/Kconfig  |  4 
>>  arch/arm64/kernel/smp.c |  1 +
>>  arch/arm64/mm/numa.c| 43 +--
>>  3 files changed, 46 insertions(+), 2 deletions(-)
>>
>> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
>> index 05c1bf1..5904a62 100644
>> --- a/arch/arm64/Kconfig
>> +++ b/arch/arm64/Kconfig
>> @@ -581,6 +581,10 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK
>> def_bool y
>> depends on NUMA
>>
>> +config HAVE_MEMORYLESS_NODES
>> +   def_bool y
>> +   depends on NUMA
>> +
>>  source kernel/Kconfig.preempt
>>  source kernel/Kconfig.hz
>>
>> diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
>> index d099306..9e15297 100644
>> --- a/arch/arm64/kernel/smp.c
>> +++ b/arch/arm64/kernel/smp.c
>> @@ -620,6 +620,7 @@ static void __init of_parse_and_init_cpus(void)
>> }
>>
>> bootcpu_valid = true;
>> +   early_map_cpu_to_node(0, of_node_to_nid(dn));
>>
>> /*
>>  * cpu_logical_map has already been
>> diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
>> index df5c842..d73b0a0 100644
>> --- a/arch/arm64/mm/numa.c
>> +++ b/arch/arm64/mm/numa.c
>> @@ -128,6 +128,14 @@ void __init early_map_cpu_to_node(unsigned int cpu, int 
>> nid)
>> nid = 0;
>>
>> cpu_to_node_map[cpu] = nid;
>> +
>> +   /*
>> +* We should set the numa node of cpu0 as soon as possible, because 
>> it
>> +* has already been set up online before. cpu_to_node(0) will soon be
>> +* called.
>> +*/
>> +   if (!cpu)
>> +   set_cpu_numa_node(cpu, nid);
>>  }
>>
>>  #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
>> @@ -215,6 +223,35 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
>> return ret;
>>  }
>>
>> +static u64 __init alloc_node_data_from_nearest_node(int nid, const size_t 
>> size)
>> +{
>> +   int i, best_nid, distance;
>> +   u64 pa;
>> +   DECLARE_BITMAP(nodes_map, MAX_NUMNODES);
>> +
>> +   bitmap_zero(nodes_map, MAX_NUMNODES);
>> +   bitmap_set(nodes_map, nid, 1);
>> +
>> +find_nearest_node:
>> +   best_nid = NUMA_NO_NODE;
>> +   distance = INT_MAX;
>> +
>> +   for_each_clear_bit(i, nodes_map, MAX_NUMNODES)
>> +   if (numa_distance[nid][i] < distance) {
>> +   best_nid = i;
>> +   distance = numa_distance[nid][i];
>> +   }
>> +
>> +   pa = memblock_alloc_nid(size, SMP_CACHE_BYTES, best_nid);
>> +   if (!pa) {
>> +   BUG_ON(best_nid == NUMA_NO_NODE);
>> +   bitmap_set(nodes_map, best_nid, 1);
>> +   goto find_nearest_node;
>> +   }
>> +
>> +   return pa;
>> +}
>> +
>>  /**
>>   * Initialize NODE_DATA for a node on the local memory
>>   */
>> @@ -228,7 +265,9 @@ static void __init setup_node_data(int nid, u64 
>> start_pfn, u64 end_pfn)
>> pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
>> nid, start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
>>
>> -   nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
>> +   nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
>> +   if (!nd_pa)
>> +   nd_pa = alloc_node_data_from_nearest_node(nid, nd_size);
>> nd = __va(nd_pa);
>>
>> /* report and initialize */
>> @@ -238,7 +277,7 @@ static void __init setup_node_data(int nid, u64 
>> start_pfn, u64 end_pfn)
>> if (tnid != nid)
>> pr_info("NODE_DATA(%d) on node %d\n", nid, tnid);
>>
>> -   node_data[nid] = nd;
>> +   NODE_DATA(nid) = nd;
>> memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
>> NODE_DATA(nid)->node_id = nid;
>> NODE_DATA(nid)->node_start_pfn = start_pfn;
>> --
>> 2.5.0
>>
>>
> Ganapat
>>
>> ___
>> linux-arm-kernel mailing list
>> linux-arm-ker...@lists.infradead.org
>> 

Re: [PATCH v4 11/14] arm64/numa: support HAVE_MEMORYLESS_NODES

[Leizhen (ThunderTown)]

On 2016/6/7 16:31, Ganapatrao Kulkarni wrote:
> On Tue, Jun 7, 2016 at 1:38 PM, Zhen Lei  wrote:
>> Some numa nodes may have no memory. For example:
>> 1. cpu0 on node0
>> 2. cpu1 on node1
>> 3. device0 access the momory from node0 and node1 take the same time.
> 
> i am wondering, if access to both nodes is same, then why you need numa.
> the example you are quoting is against the basic principle of "numa"
> what is device0 here? cpu?
The device0 can also be a cpu. I drew a simple diagram:

  cpu0 cpu1cpu2/device0
||  |
||  |
   DDR0 DDR1No DIMM slots or no DIMM plugged
 (node0)  (node1) (node2)

>>
>> So, we can not simply classify device0 to node0 or node1, but we can
>> define a node2 which distances to node0 and node1 are the same.
>>
>> Signed-off-by: Zhen Lei 
>> ---
>>  arch/arm64/Kconfig  |  4 
>>  arch/arm64/kernel/smp.c |  1 +
>>  arch/arm64/mm/numa.c| 43 +--
>>  3 files changed, 46 insertions(+), 2 deletions(-)
>>
>> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
>> index 05c1bf1..5904a62 100644
>> --- a/arch/arm64/Kconfig
>> +++ b/arch/arm64/Kconfig
>> @@ -581,6 +581,10 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK
>> def_bool y
>> depends on NUMA
>>
>> +config HAVE_MEMORYLESS_NODES
>> +   def_bool y
>> +   depends on NUMA
>> +
>>  source kernel/Kconfig.preempt
>>  source kernel/Kconfig.hz
>>
>> diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
>> index d099306..9e15297 100644
>> --- a/arch/arm64/kernel/smp.c
>> +++ b/arch/arm64/kernel/smp.c
>> @@ -620,6 +620,7 @@ static void __init of_parse_and_init_cpus(void)
>> }
>>
>> bootcpu_valid = true;
>> +   early_map_cpu_to_node(0, of_node_to_nid(dn));
>>
>> /*
>>  * cpu_logical_map has already been
>> diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
>> index df5c842..d73b0a0 100644
>> --- a/arch/arm64/mm/numa.c
>> +++ b/arch/arm64/mm/numa.c
>> @@ -128,6 +128,14 @@ void __init early_map_cpu_to_node(unsigned int cpu, int 
>> nid)
>> nid = 0;
>>
>> cpu_to_node_map[cpu] = nid;
>> +
>> +   /*
>> +* We should set the numa node of cpu0 as soon as possible, because 
>> it
>> +* has already been set up online before. cpu_to_node(0) will soon be
>> +* called.
>> +*/
>> +   if (!cpu)
>> +   set_cpu_numa_node(cpu, nid);
>>  }
>>
>>  #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
>> @@ -215,6 +223,35 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
>> return ret;
>>  }
>>
>> +static u64 __init alloc_node_data_from_nearest_node(int nid, const size_t 
>> size)
>> +{
>> +   int i, best_nid, distance;
>> +   u64 pa;
>> +   DECLARE_BITMAP(nodes_map, MAX_NUMNODES);
>> +
>> +   bitmap_zero(nodes_map, MAX_NUMNODES);
>> +   bitmap_set(nodes_map, nid, 1);
>> +
>> +find_nearest_node:
>> +   best_nid = NUMA_NO_NODE;
>> +   distance = INT_MAX;
>> +
>> +   for_each_clear_bit(i, nodes_map, MAX_NUMNODES)
>> +   if (numa_distance[nid][i] < distance) {
>> +   best_nid = i;
>> +   distance = numa_distance[nid][i];
>> +   }
>> +
>> +   pa = memblock_alloc_nid(size, SMP_CACHE_BYTES, best_nid);
>> +   if (!pa) {
>> +   BUG_ON(best_nid == NUMA_NO_NODE);
>> +   bitmap_set(nodes_map, best_nid, 1);
>> +   goto find_nearest_node;
>> +   }
>> +
>> +   return pa;
>> +}
>> +
>>  /**
>>   * Initialize NODE_DATA for a node on the local memory
>>   */
>> @@ -228,7 +265,9 @@ static void __init setup_node_data(int nid, u64 
>> start_pfn, u64 end_pfn)
>> pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
>> nid, start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
>>
>> -   nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
>> +   nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
>> +   if (!nd_pa)
>> +   nd_pa = alloc_node_data_from_nearest_node(nid, nd_size);
>> nd = __va(nd_pa);
>>
>> /* report and initialize */
>> @@ -238,7 +277,7 @@ static void __init setup_node_data(int nid, u64 
>> start_pfn, u64 end_pfn)
>> if (tnid != nid)
>> pr_info("NODE_DATA(%d) on node %d\n", nid, tnid);
>>
>> -   node_data[nid] = nd;
>> +   NODE_DATA(nid) = nd;
>> memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
>> NODE_DATA(nid)->node_id = nid;
>> NODE_DATA(nid)->node_start_pfn = start_pfn;
>> --
>> 2.5.0
>>
>>
> Ganapat
>>
>> ___
>> linux-arm-kernel mailing list
>> linux-arm-ker...@lists.infradead.org
>> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
> 
> .
> 

Re: [PATCH v4 11/14] arm64/numa: support HAVE_MEMORYLESS_NODES

[Ganapatrao Kulkarni]

On Tue, Jun 7, 2016 at 1:38 PM, Zhen Lei  wrote:
> Some numa nodes may have no memory. For example:
> 1. cpu0 on node0
> 2. cpu1 on node1
> 3. device0 access the momory from node0 and node1 take the same time.

i am wondering, if access to both nodes is same, then why you need numa.
the example you are quoting is against the basic principle of "numa"
what is device0 here? cpu?
>
> So, we can not simply classify device0 to node0 or node1, but we can
> define a node2 which distances to node0 and node1 are the same.
>
> Signed-off-by: Zhen Lei 
> ---
>  arch/arm64/Kconfig  |  4 
>  arch/arm64/kernel/smp.c |  1 +
>  arch/arm64/mm/numa.c| 43 +--
>  3 files changed, 46 insertions(+), 2 deletions(-)
>
> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index 05c1bf1..5904a62 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -581,6 +581,10 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK
> def_bool y
> depends on NUMA
>
> +config HAVE_MEMORYLESS_NODES
> +   def_bool y
> +   depends on NUMA
> +
>  source kernel/Kconfig.preempt
>  source kernel/Kconfig.hz
>
> diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
> index d099306..9e15297 100644
> --- a/arch/arm64/kernel/smp.c
> +++ b/arch/arm64/kernel/smp.c
> @@ -620,6 +620,7 @@ static void __init of_parse_and_init_cpus(void)
> }
>
> bootcpu_valid = true;
> +   early_map_cpu_to_node(0, of_node_to_nid(dn));
>
> /*
>  * cpu_logical_map has already been
> diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
> index df5c842..d73b0a0 100644
> --- a/arch/arm64/mm/numa.c
> +++ b/arch/arm64/mm/numa.c
> @@ -128,6 +128,14 @@ void __init early_map_cpu_to_node(unsigned int cpu, int 
> nid)
> nid = 0;
>
> cpu_to_node_map[cpu] = nid;
> +
> +   /*
> +* We should set the numa node of cpu0 as soon as possible, because it
> +* has already been set up online before. cpu_to_node(0) will soon be
> +* called.
> +*/
> +   if (!cpu)
> +   set_cpu_numa_node(cpu, nid);
>  }
>
>  #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
> @@ -215,6 +223,35 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
> return ret;
>  }
>
> +static u64 __init alloc_node_data_from_nearest_node(int nid, const size_t 
> size)
> +{
> +   int i, best_nid, distance;
> +   u64 pa;
> +   DECLARE_BITMAP(nodes_map, MAX_NUMNODES);
> +
> +   bitmap_zero(nodes_map, MAX_NUMNODES);
> +   bitmap_set(nodes_map, nid, 1);
> +
> +find_nearest_node:
> +   best_nid = NUMA_NO_NODE;
> +   distance = INT_MAX;
> +
> +   for_each_clear_bit(i, nodes_map, MAX_NUMNODES)
> +   if (numa_distance[nid][i] < distance) {
> +   best_nid = i;
> +   distance = numa_distance[nid][i];
> +   }
> +
> +   pa = memblock_alloc_nid(size, SMP_CACHE_BYTES, best_nid);
> +   if (!pa) {
> +   BUG_ON(best_nid == NUMA_NO_NODE);
> +   bitmap_set(nodes_map, best_nid, 1);
> +   goto find_nearest_node;
> +   }
> +
> +   return pa;
> +}
> +
>  /**
>   * Initialize NODE_DATA for a node on the local memory
>   */
> @@ -228,7 +265,9 @@ static void __init setup_node_data(int nid, u64 
> start_pfn, u64 end_pfn)
> pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
> nid, start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
>
> -   nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
> +   nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
> +   if (!nd_pa)
> +   nd_pa = alloc_node_data_from_nearest_node(nid, nd_size);
> nd = __va(nd_pa);
>
> /* report and initialize */
> @@ -238,7 +277,7 @@ static void __init setup_node_data(int nid, u64 
> start_pfn, u64 end_pfn)
> if (tnid != nid)
> pr_info("NODE_DATA(%d) on node %d\n", nid, tnid);
>
> -   node_data[nid] = nd;
> +   NODE_DATA(nid) = nd;
> memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
> NODE_DATA(nid)->node_id = nid;
> NODE_DATA(nid)->node_start_pfn = start_pfn;
> --
> 2.5.0
>
>
Ganapat
>
> ___
> linux-arm-kernel mailing list
> linux-arm-ker...@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Re: [PATCH v4 11/14] arm64/numa: support HAVE_MEMORYLESS_NODES

[Ganapatrao Kulkarni]

On Tue, Jun 7, 2016 at 1:38 PM, Zhen Lei  wrote:
> Some numa nodes may have no memory. For example:
> 1. cpu0 on node0
> 2. cpu1 on node1
> 3. device0 access the momory from node0 and node1 take the same time.

i am wondering, if access to both nodes is same, then why you need numa.
the example you are quoting is against the basic principle of "numa"
what is device0 here? cpu?
>
> So, we can not simply classify device0 to node0 or node1, but we can
> define a node2 which distances to node0 and node1 are the same.
>
> Signed-off-by: Zhen Lei 
> ---
>  arch/arm64/Kconfig  |  4 
>  arch/arm64/kernel/smp.c |  1 +
>  arch/arm64/mm/numa.c| 43 +--
>  3 files changed, 46 insertions(+), 2 deletions(-)
>
> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index 05c1bf1..5904a62 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -581,6 +581,10 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK
> def_bool y
> depends on NUMA
>
> +config HAVE_MEMORYLESS_NODES
> +   def_bool y
> +   depends on NUMA
> +
>  source kernel/Kconfig.preempt
>  source kernel/Kconfig.hz
>
> diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
> index d099306..9e15297 100644
> --- a/arch/arm64/kernel/smp.c
> +++ b/arch/arm64/kernel/smp.c
> @@ -620,6 +620,7 @@ static void __init of_parse_and_init_cpus(void)
> }
>
> bootcpu_valid = true;
> +   early_map_cpu_to_node(0, of_node_to_nid(dn));
>
> /*
>  * cpu_logical_map has already been
> diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
> index df5c842..d73b0a0 100644
> --- a/arch/arm64/mm/numa.c
> +++ b/arch/arm64/mm/numa.c
> @@ -128,6 +128,14 @@ void __init early_map_cpu_to_node(unsigned int cpu, int 
> nid)
> nid = 0;
>
> cpu_to_node_map[cpu] = nid;
> +
> +   /*
> +* We should set the numa node of cpu0 as soon as possible, because it
> +* has already been set up online before. cpu_to_node(0) will soon be
> +* called.
> +*/
> +   if (!cpu)
> +   set_cpu_numa_node(cpu, nid);
>  }
>
>  #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
> @@ -215,6 +223,35 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
> return ret;
>  }
>
> +static u64 __init alloc_node_data_from_nearest_node(int nid, const size_t 
> size)
> +{
> +   int i, best_nid, distance;
> +   u64 pa;
> +   DECLARE_BITMAP(nodes_map, MAX_NUMNODES);
> +
> +   bitmap_zero(nodes_map, MAX_NUMNODES);
> +   bitmap_set(nodes_map, nid, 1);
> +
> +find_nearest_node:
> +   best_nid = NUMA_NO_NODE;
> +   distance = INT_MAX;
> +
> +   for_each_clear_bit(i, nodes_map, MAX_NUMNODES)
> +   if (numa_distance[nid][i] < distance) {
> +   best_nid = i;
> +   distance = numa_distance[nid][i];
> +   }
> +
> +   pa = memblock_alloc_nid(size, SMP_CACHE_BYTES, best_nid);
> +   if (!pa) {
> +   BUG_ON(best_nid == NUMA_NO_NODE);
> +   bitmap_set(nodes_map, best_nid, 1);
> +   goto find_nearest_node;
> +   }
> +
> +   return pa;
> +}
> +
>  /**
>   * Initialize NODE_DATA for a node on the local memory
>   */
> @@ -228,7 +265,9 @@ static void __init setup_node_data(int nid, u64 
> start_pfn, u64 end_pfn)
> pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
> nid, start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
>
> -   nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
> +   nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
> +   if (!nd_pa)
> +   nd_pa = alloc_node_data_from_nearest_node(nid, nd_size);
> nd = __va(nd_pa);
>
> /* report and initialize */
> @@ -238,7 +277,7 @@ static void __init setup_node_data(int nid, u64 
> start_pfn, u64 end_pfn)
> if (tnid != nid)
> pr_info("NODE_DATA(%d) on node %d\n", nid, tnid);
>
> -   node_data[nid] = nd;
> +   NODE_DATA(nid) = nd;
> memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
> NODE_DATA(nid)->node_id = nid;
> NODE_DATA(nid)->node_start_pfn = start_pfn;
> --
> 2.5.0
>
>
Ganapat
>
> ___
> linux-arm-kernel mailing list
> linux-arm-ker...@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v4 11/14] arm64/numa: support HAVE_MEMORYLESS_NODES

[Zhen Lei]

Some numa nodes may have no memory. For example:
1. cpu0 on node0
2. cpu1 on node1
3. device0 access the momory from node0 and node1 take the same time.

So, we can not simply classify device0 to node0 or node1, but we can
define a node2 which distances to node0 and node1 are the same.

Signed-off-by: Zhen Lei 
---
 arch/arm64/Kconfig  |  4 
 arch/arm64/kernel/smp.c |  1 +
 arch/arm64/mm/numa.c| 43 +--
 3 files changed, 46 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 05c1bf1..5904a62 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -581,6 +581,10 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK
def_bool y
depends on NUMA

+config HAVE_MEMORYLESS_NODES
+   def_bool y
+   depends on NUMA
+
 source kernel/Kconfig.preempt
 source kernel/Kconfig.hz

diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index d099306..9e15297 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -620,6 +620,7 @@ static void __init of_parse_and_init_cpus(void)
}

bootcpu_valid = true;
+   early_map_cpu_to_node(0, of_node_to_nid(dn));

/*
 * cpu_logical_map has already been
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index df5c842..d73b0a0 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -128,6 +128,14 @@ void __init early_map_cpu_to_node(unsigned int cpu, int 
nid)
nid = 0;

cpu_to_node_map[cpu] = nid;
+
+   /*
+* We should set the numa node of cpu0 as soon as possible, because it
+* has already been set up online before. cpu_to_node(0) will soon be
+* called.
+*/
+   if (!cpu)
+   set_cpu_numa_node(cpu, nid);
 }

 #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
@@ -215,6 +223,35 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
return ret;
 }

+static u64 __init alloc_node_data_from_nearest_node(int nid, const size_t size)
+{
+   int i, best_nid, distance;
+   u64 pa;
+   DECLARE_BITMAP(nodes_map, MAX_NUMNODES);
+
+   bitmap_zero(nodes_map, MAX_NUMNODES);
+   bitmap_set(nodes_map, nid, 1);
+
+find_nearest_node:
+   best_nid = NUMA_NO_NODE;
+   distance = INT_MAX;
+
+   for_each_clear_bit(i, nodes_map, MAX_NUMNODES)
+   if (numa_distance[nid][i] < distance) {
+   best_nid = i;
+   distance = numa_distance[nid][i];
+   }
+
+   pa = memblock_alloc_nid(size, SMP_CACHE_BYTES, best_nid);
+   if (!pa) {
+   BUG_ON(best_nid == NUMA_NO_NODE);
+   bitmap_set(nodes_map, best_nid, 1);
+   goto find_nearest_node;
+   }
+
+   return pa;
+}
+
 /**
  * Initialize NODE_DATA for a node on the local memory
  */
@@ -228,7 +265,9 @@ static void __init setup_node_data(int nid, u64 start_pfn, 
u64 end_pfn)
pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
nid, start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);

-   nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
+   nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
+   if (!nd_pa)
+   nd_pa = alloc_node_data_from_nearest_node(nid, nd_size);
nd = __va(nd_pa);

/* report and initialize */
@@ -238,7 +277,7 @@ static void __init setup_node_data(int nid, u64 start_pfn, 
u64 end_pfn)
if (tnid != nid)
pr_info("NODE_DATA(%d) on node %d\n", nid, tnid);

-   node_data[nid] = nd;
+   NODE_DATA(nid) = nd;
memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
NODE_DATA(nid)->node_id = nid;
NODE_DATA(nid)->node_start_pfn = start_pfn;
--
2.5.0

[PATCH v4 11/14] arm64/numa: support HAVE_MEMORYLESS_NODES

[Zhen Lei]

Some numa nodes may have no memory. For example:
1. cpu0 on node0
2. cpu1 on node1
3. device0 access the momory from node0 and node1 take the same time.

So, we can not simply classify device0 to node0 or node1, but we can
define a node2 which distances to node0 and node1 are the same.

Signed-off-by: Zhen Lei 
---
 arch/arm64/Kconfig  |  4 
 arch/arm64/kernel/smp.c |  1 +
 arch/arm64/mm/numa.c| 43 +--
 3 files changed, 46 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 05c1bf1..5904a62 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -581,6 +581,10 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK
def_bool y
depends on NUMA

+config HAVE_MEMORYLESS_NODES
+   def_bool y
+   depends on NUMA
+
 source kernel/Kconfig.preempt
 source kernel/Kconfig.hz

diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index d099306..9e15297 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -620,6 +620,7 @@ static void __init of_parse_and_init_cpus(void)
}

bootcpu_valid = true;
+   early_map_cpu_to_node(0, of_node_to_nid(dn));

/*
 * cpu_logical_map has already been
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index df5c842..d73b0a0 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -128,6 +128,14 @@ void __init early_map_cpu_to_node(unsigned int cpu, int 
nid)
nid = 0;

cpu_to_node_map[cpu] = nid;
+
+   /*
+* We should set the numa node of cpu0 as soon as possible, because it
+* has already been set up online before. cpu_to_node(0) will soon be
+* called.
+*/
+   if (!cpu)
+   set_cpu_numa_node(cpu, nid);
 }

 #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
@@ -215,6 +223,35 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
return ret;
 }

+static u64 __init alloc_node_data_from_nearest_node(int nid, const size_t size)
+{
+   int i, best_nid, distance;
+   u64 pa;
+   DECLARE_BITMAP(nodes_map, MAX_NUMNODES);
+
+   bitmap_zero(nodes_map, MAX_NUMNODES);
+   bitmap_set(nodes_map, nid, 1);
+
+find_nearest_node:
+   best_nid = NUMA_NO_NODE;
+   distance = INT_MAX;
+
+   for_each_clear_bit(i, nodes_map, MAX_NUMNODES)
+   if (numa_distance[nid][i] < distance) {
+   best_nid = i;
+   distance = numa_distance[nid][i];
+   }
+
+   pa = memblock_alloc_nid(size, SMP_CACHE_BYTES, best_nid);
+   if (!pa) {
+   BUG_ON(best_nid == NUMA_NO_NODE);
+   bitmap_set(nodes_map, best_nid, 1);
+   goto find_nearest_node;
+   }
+
+   return pa;
+}
+
 /**
  * Initialize NODE_DATA for a node on the local memory
  */
@@ -228,7 +265,9 @@ static void __init setup_node_data(int nid, u64 start_pfn, 
u64 end_pfn)
pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
nid, start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);

-   nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
+   nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
+   if (!nd_pa)
+   nd_pa = alloc_node_data_from_nearest_node(nid, nd_size);
nd = __va(nd_pa);

/* report and initialize */
@@ -238,7 +277,7 @@ static void __init setup_node_data(int nid, u64 start_pfn, 
u64 end_pfn)
if (tnid != nid)
pr_info("NODE_DATA(%d) on node %d\n", nid, tnid);

-   node_data[nid] = nd;
+   NODE_DATA(nid) = nd;
memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
NODE_DATA(nid)->node_id = nid;
NODE_DATA(nid)->node_start_pfn = start_pfn;
--
2.5.0