diff mbox

[v7,11/14] arm64/numa: support HAVE_MEMORYLESS_NODES

Message ID 1472024693-12912-12-git-send-email-thunder.leizhen@huawei.com
State New
Headers show

Commit Message

Zhen Lei Aug. 24, 2016, 7:44 a.m. UTC
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 <thunder.leizhen@huawei.com>

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

--
2.5.0

Comments

Will Deacon Aug. 26, 2016, 3:43 p.m. UTC | #1
On Wed, Aug 24, 2016 at 03:44:50PM +0800, 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.

> 

> 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 <thunder.leizhen@huawei.com>

> ---

>  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 2815af6..3a2b6ed 100644

> --- a/arch/arm64/Kconfig

> +++ b/arch/arm64/Kconfig

> @@ -611,6 +611,10 @@ 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 d93d433..4879085 100644

> --- a/arch/arm64/kernel/smp.c

> +++ b/arch/arm64/kernel/smp.c

> @@ -619,6 +619,7 @@ static void __init of_parse_and_init_cpus(void)

>  			}

> 

>  			bootcpu_valid = true;

> +			early_map_cpu_to_node(0, of_node_to_nid(dn));


This seems unrelated?

>  			/*

>  			 * cpu_logical_map has already been

> diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c

> index 6853db7..114180f 100644

> --- a/arch/arm64/mm/numa.c

> +++ b/arch/arm64/mm/numa.c

> @@ -129,6 +129,14 @@ 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);


Likewise.

>  }

> 

>  #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA

> @@ -211,6 +219,35 @@ 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

>   */

> @@ -224,7 +261,9 @@ 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);


Why not add memblock_alloc_near_nid to the core code, and make it do
what you need there?

Will
Zhen Lei Aug. 27, 2016, 11:05 a.m. UTC | #2
On 2016/8/26 23:43, Will Deacon wrote:
> On Wed, Aug 24, 2016 at 03:44:50PM +0800, 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.

>>

>> 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 <thunder.leizhen@huawei.com>

>> ---

>>  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 2815af6..3a2b6ed 100644

>> --- a/arch/arm64/Kconfig

>> +++ b/arch/arm64/Kconfig

>> @@ -611,6 +611,10 @@ 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 d93d433..4879085 100644

>> --- a/arch/arm64/kernel/smp.c

>> +++ b/arch/arm64/kernel/smp.c

>> @@ -619,6 +619,7 @@ static void __init of_parse_and_init_cpus(void)

>>  			}

>>

>>  			bootcpu_valid = true;

>> +			early_map_cpu_to_node(0, of_node_to_nid(dn));

> 

> This seems unrelated?

I will get off my work soon. Maybe I need put it into patch 12.

> 

>>  			/*

>>  			 * cpu_logical_map has already been

>> diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c

>> index 6853db7..114180f 100644

>> --- a/arch/arm64/mm/numa.c

>> +++ b/arch/arm64/mm/numa.c

>> @@ -129,6 +129,14 @@ 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);

> 

> Likewise.

> 

>>  }

>>

>>  #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA

>> @@ -211,6 +219,35 @@ 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

>>   */

>> @@ -224,7 +261,9 @@ 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);

> 

> Why not add memblock_alloc_near_nid to the core code, and make it do

> what you need there?

I'm thinking about it next week. But some ARCHs like X86/IA64 have their own implementation.

> 

> Will

> 

> .

>
diff mbox

Patch

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 2815af6..3a2b6ed 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -611,6 +611,10 @@  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 d93d433..4879085 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -619,6 +619,7 @@  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 6853db7..114180f 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -129,6 +129,14 @@  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
@@ -211,6 +219,35 @@  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
  */
@@ -224,7 +261,9 @@  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 */
@@ -234,7 +273,7 @@  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;