... and call node_dev_init() after memory_dev_init() from driver_init(),
so before any of the existing arch/subsys calls. All online nodes should
be known at that point: early during boot, arch code determines node and
zone ranges and sets the relevant nodes online; usually this happens in
setup_arch().
This is in line with memory_dev_init(), which initializes the memory
device subsystem and creates all memory block devices.
Similar to memory_dev_init(), panic() if anything goes wrong, we don't
want to continue with such basic initialization errors.
The important part is that node_dev_init() gets called after
memory_dev_init() and after cpu_dev_init(), but before any of the
relevant archs call register_cpu() to register the new cpu device under
the node device. The latter should be the case for the current users
of topology_init().
Reviewed-by: Oscar Salvador <osalvador@xxxxxxx>
Tested-by: Anatoly Pugachev <matorola@xxxxxxxxx> (sparc64)
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Oscar Salvador <osalvador@xxxxxxx>
Cc: Mike Rapoport <rppt@xxxxxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Thomas Bogendoerfer <tsbogend@xxxxxxxxxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Cc: Paul Mackerras <paulus@xxxxxxxxx>
Cc: Paul Walmsley <paul.walmsley@xxxxxxxxxx>
Cc: Palmer Dabbelt <palmer@xxxxxxxxxxx>
Cc: Albert Ou <aou@xxxxxxxxxxxxxxxxx>
Cc: Heiko Carstens <hca@xxxxxxxxxxxxx>
Cc: Vasily Gorbik <gor@xxxxxxxxxxxxx>
Cc: Yoshinori Sato <ysato@xxxxxxxxxxxxxxxxxxxx>
Cc: Rich Felker <dalias@xxxxxxxx>
Cc: "David S. Miller" <davem@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: "Rafael J. Wysocki" <rafael@xxxxxxxxxx>
Cc: x86@xxxxxxxxxx
Cc: linux-arm-kernel@xxxxxxxxxxxxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
Cc: linux-ia64@xxxxxxxxxxxxxxx
Cc: linux-mips@xxxxxxxxxxxxxxx
Cc: linuxppc-dev@xxxxxxxxxxxxxxxx
Cc: linux-riscv@xxxxxxxxxxxxxxxxxxx
Cc: linux-s390@xxxxxxxxxxxxxxx
Cc: linux-sh@xxxxxxxxxxxxxxx
Cc: sparclinux@xxxxxxxxxxxxxxx
Cc: linux-mm@xxxxxxxxx
Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
---
RFC v1 -> v1:
* Extended patch description slighly
* Tested on x86-64, s390x, ppc64 and aarch64
* Added Rb and Tested-by.
---
arch/arm64/kernel/setup.c | 3 ---
arch/ia64/kernel/topology.c | 10 ----------
arch/mips/kernel/topology.c | 5 -----
arch/powerpc/kernel/sysfs.c | 17 -----------------
arch/riscv/kernel/setup.c | 3 ---
arch/s390/kernel/numa.c | 7 -------
arch/sh/kernel/topology.c | 5 -----
arch/sparc/kernel/sysfs.c | 12 ------------
arch/x86/kernel/topology.c | 5 -----
drivers/base/init.c | 1 +
drivers/base/node.c | 30 +++++++++++++++++-------------
include/linux/node.h | 4 ++++
12 files changed, 22 insertions(+), 80 deletions(-)
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index f70573928f1b..3505789cf4bd 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -406,9 +406,6 @@ static int __init topology_init(void)
{
int i;
- for_each_online_node(i)
- register_one_node(i);
-
for_each_possible_cpu(i) {
struct cpu *cpu = &per_cpu(cpu_data.cpu, i);
cpu->hotpluggable = cpu_can_disable(i);
diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c
index e4992917a24b..94a848b06f15 100644
--- a/arch/ia64/kernel/topology.c
+++ b/arch/ia64/kernel/topology.c
@@ -70,16 +70,6 @@ static int __init topology_init(void)
{
int i, err = 0;
-#ifdef CONFIG_NUMA
- /*
- * MCD - Do we want to register all ONLINE nodes, or all POSSIBLE nodes?
- */
- for_each_online_node(i) {
- if ((err = register_one_node(i)))
- goto out;
- }
-#endif
-
sysfs_cpus = kcalloc(NR_CPUS, sizeof(struct ia64_cpu), GFP_KERNEL);
if (!sysfs_cpus)
panic("kzalloc in topology_init failed - NR_CPUS too big?");
diff --git a/arch/mips/kernel/topology.c b/arch/mips/kernel/topology.c
index 08ad6371fbe0..9429d85a4703 100644
--- a/arch/mips/kernel/topology.c
+++ b/arch/mips/kernel/topology.c
@@ -12,11 +12,6 @@ static int __init topology_init(void)
{
int i, ret;
-#ifdef CONFIG_NUMA
- for_each_online_node(i)
- register_one_node(i);
-#endif /* CONFIG_NUMA */
-
for_each_present_cpu(i) {
struct cpu *c = &per_cpu(cpu_devices, i);
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index d45a415d5374..2069bbb90a9a 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -1110,14 +1110,6 @@ EXPORT_SYMBOL_GPL(cpu_remove_dev_attr_group);
/* NUMA stuff */
#ifdef CONFIG_NUMA
-static void __init register_nodes(void)
-{
- int i;
-
- for (i = 0; i < MAX_NUMNODES; i++)
- register_one_node(i);
-}
-
int sysfs_add_device_to_node(struct device *dev, int nid)
{
struct node *node = node_devices[nid];
@@ -1132,13 +1124,6 @@ void sysfs_remove_device_from_node(struct device *dev, int nid)
sysfs_remove_link(&node->dev.kobj, kobject_name(&dev->kobj));
}
EXPORT_SYMBOL_GPL(sysfs_remove_device_from_node);
-
-#else
-static void __init register_nodes(void)
-{
- return;
-}
-
#endif
/* Only valid if CPU is present. */
@@ -1155,8 +1140,6 @@ static int __init topology_init(void)
{
int cpu, r;
- register_nodes();
-
for_each_possible_cpu(cpu) {
struct cpu *c = &per_cpu(cpu_devices, cpu);
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index b42bfdc67482..834eb652a7b9 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -301,9 +301,6 @@ static int __init topology_init(void)
{
int i, ret;
- for_each_online_node(i)
- register_one_node(i);
-
for_each_possible_cpu(i) {
struct cpu *cpu = &per_cpu(cpu_devices, i);
diff --git a/arch/s390/kernel/numa.c b/arch/s390/kernel/numa.c
index 51c5a9f6e525..23ab9f02f278 100644
--- a/arch/s390/kernel/numa.c
+++ b/arch/s390/kernel/numa.c
@@ -33,10 +33,3 @@ void __init numa_setup(void)
NODE_DATA(0)->node_spanned_pages = memblock_end_of_DRAM() >> PAGE_SHIFT;
NODE_DATA(0)->node_id = 0;
}
-
-static int __init numa_init_late(void)
-{
- register_one_node(0);
- return 0;
-}
-arch_initcall(numa_init_late);
diff --git a/arch/sh/kernel/topology.c b/arch/sh/kernel/topology.c
index 76af6db9daa2..2d2a7509b565 100644
--- a/arch/sh/kernel/topology.c
+++ b/arch/sh/kernel/topology.c
@@ -46,11 +46,6 @@ static int __init topology_init(void)
{
int i, ret;
-#ifdef CONFIG_NUMA
- for_each_online_node(i)
- register_one_node(i);
-#endif
-
for_each_present_cpu(i) {
struct cpu *c = &per_cpu(cpu_devices, i);
diff --git a/arch/sparc/kernel/sysfs.c b/arch/sparc/kernel/sysfs.c
index 6d60d416f0dd..f19487e4cc71 100644
--- a/arch/sparc/kernel/sysfs.c
+++ b/arch/sparc/kernel/sysfs.c
@@ -244,22 +244,10 @@ static void __init check_mmu_stats(void)
mmu_stats_supported = 1;
}
-static void register_nodes(void)
-{
-#ifdef CONFIG_NUMA
- int i;
-
- for (i = 0; i < MAX_NUMNODES; i++)
- register_one_node(i);
-#endif
-}
-
static int __init topology_init(void)
{
int cpu, ret;
- register_nodes();
-
check_mmu_stats();
for_each_possible_cpu(cpu) {
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index bd83748e2bde..8617d1ed9d31 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -154,11 +154,6 @@ static int __init topology_init(void)
{
int i;
-#ifdef CONFIG_NUMA
- for_each_online_node(i)
- register_one_node(i);
-#endif
-
for_each_present_cpu(i)
arch_register_cpu(i);
diff --git a/drivers/base/init.c b/drivers/base/init.c
index a9f57c22fb9e..d8d0fe687111 100644
--- a/drivers/base/init.c
+++ b/drivers/base/init.c
@@ -35,5 +35,6 @@ void __init driver_init(void)
auxiliary_bus_init();
cpu_dev_init();
memory_dev_init();
+ node_dev_init();
container_dev_init();
}
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 87acc47e8951..a133981a12fc 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -1065,26 +1065,30 @@ static const struct attribute_group *cpu_root_attr_groups[] = {
};
#define NODE_CALLBACK_PRI 2 /* lower than SLAB */
-static int __init register_node_type(void)
+void __init node_dev_init(void)
{
- int ret;
+ static struct notifier_block node_memory_callback_nb = {
+ .notifier_call = node_memory_callback,
+ .priority = NODE_CALLBACK_PRI,
+ };
+ int ret, i;
BUILD_BUG_ON(ARRAY_SIZE(node_state_attr) != NR_NODE_STATES);
BUILD_BUG_ON(ARRAY_SIZE(node_state_attrs)-1 != NR_NODE_STATES);
ret = subsys_system_register(&node_subsys, cpu_root_attr_groups);
- if (!ret) {
- static struct notifier_block node_memory_callback_nb = {
- .notifier_call = node_memory_callback,
- .priority = NODE_CALLBACK_PRI,
- };
- register_hotmemory_notifier(&node_memory_callback_nb);
- }
+ if (ret)
+ panic("%s() failed to register subsystem: %d\n", __func__, ret);
+
+ register_hotmemory_notifier(&node_memory_callback_nb);
/*
- * Note: we're not going to unregister the node class if we fail
- * to register the node state class attribute files.
+ * Create all node devices, which will properly link the node
+ * to applicable memory block devices and already created cpu devices.
*/
- return ret;
+ for_each_online_node(i) {
+ ret = register_one_node(i);
+ if (ret)
+ panic("%s() failed to add node: %d\n", __func__, ret);
+ }
}
-postcore_initcall(register_node_type);
diff --git a/include/linux/node.h b/include/linux/node.h
index bb21fd631b16..f3be6ccfebed 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -112,6 +112,7 @@ static inline void link_mem_sections(int nid, unsigned long start_pfn,
extern void unregister_node(struct node *node);
#ifdef CONFIG_NUMA
+extern void node_dev_init(void);
/* Core of the node registration - only memory hotplug should use this */
extern int __register_one_node(int nid);
@@ -149,6 +150,9 @@ extern void register_hugetlbfs_with_node(node_registration_func_t doregister,
node_registration_func_t unregister);
#endif
#else
+static inline void node_dev_init(void)
+{
+}
static inline int __register_one_node(int nid)
{
return 0;
base-commit: 26291c54e111ff6ba87a164d85d4a4e134b7315c
--
2.34.1
