Backport version to the 5.4-stable tree of the commit:
f85086f95fa3 ("mm: don't rely on system state to detect hot-plug operations")
Cc: stable@vger.kernel.org # 4.19.y Signed-off-by: Laurent Dufour ldufour@linux.ibm.com --- drivers/base/node.c | 84 ++++++++++++++++++++++++++++---------------- include/linux/node.h | 11 +++--- mm/memory_hotplug.c | 3 +- 3 files changed, 63 insertions(+), 35 deletions(-)
diff --git a/drivers/base/node.c b/drivers/base/node.c index f3565c2dbc52..503e2f90e58e 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -403,10 +403,32 @@ static int __ref get_nid_for_pfn(unsigned long pfn) return pfn_to_nid(pfn); }
+static int do_register_memory_block_under_node(int nid, + struct memory_block *mem_blk) +{ + int ret; + + /* + * If this memory block spans multiple nodes, we only indicate + * the last processed node. + */ + mem_blk->nid = nid; + + ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj, + &mem_blk->dev.kobj, + kobject_name(&mem_blk->dev.kobj)); + if (ret) + return ret; + + return sysfs_create_link_nowarn(&mem_blk->dev.kobj, + &node_devices[nid]->dev.kobj, + kobject_name(&node_devices[nid]->dev.kobj)); +} + /* register memory section under specified node if it spans that node */ -int register_mem_sect_under_node(struct memory_block *mem_blk, void *arg) +int register_mem_block_under_node_early(struct memory_block *mem_blk, void *arg) { - int ret, nid = *(int *)arg; + int nid = *(int *)arg; unsigned long pfn, sect_start_pfn, sect_end_pfn;
sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr); @@ -426,38 +448,33 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, void *arg) }
/* - * We need to check if page belongs to nid only for the boot - * case, during hotplug we know that all pages in the memory - * block belong to the same node. - */ - if (system_state == SYSTEM_BOOTING) { - page_nid = get_nid_for_pfn(pfn); - if (page_nid < 0) - continue; - if (page_nid != nid) - continue; - } - - /* - * If this memory block spans multiple nodes, we only indicate - * the last processed node. + * We need to check if page belongs to nid only at the boot + * case because node's ranges can be interleaved. */ - mem_blk->nid = nid; - - ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj, - &mem_blk->dev.kobj, - kobject_name(&mem_blk->dev.kobj)); - if (ret) - return ret; + page_nid = get_nid_for_pfn(pfn); + if (page_nid < 0) + continue; + if (page_nid != nid) + continue;
- return sysfs_create_link_nowarn(&mem_blk->dev.kobj, - &node_devices[nid]->dev.kobj, - kobject_name(&node_devices[nid]->dev.kobj)); + return do_register_memory_block_under_node(nid, mem_blk); } /* mem section does not span the specified node */ return 0; }
+/* + * During hotplug we know that all pages in the memory block belong to the same + * node. + */ +static int register_mem_block_under_node_hotplug(struct memory_block *mem_blk, + void *arg) +{ + int nid = *(int *)arg; + + return do_register_memory_block_under_node(nid, mem_blk); +} + /* * Unregister a memory block device under the node it spans. Memory blocks * with multiple nodes cannot be offlined and therefore also never be removed. @@ -473,10 +490,17 @@ void unregister_memory_block_under_nodes(struct memory_block *mem_blk) kobject_name(&node_devices[mem_blk->nid]->dev.kobj)); }
-int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn) +int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn, + enum meminit_context context) { - return walk_memory_range(start_pfn, end_pfn, (void *)&nid, - register_mem_sect_under_node); + walk_memory_blocks_func_t func; + + if (context == MEMINIT_HOTPLUG) + func = register_mem_block_under_node_hotplug; + else + func = register_mem_block_under_node_early; + + return walk_memory_range(start_pfn, end_pfn, (void *)&nid, func); }
#ifdef CONFIG_HUGETLBFS diff --git a/include/linux/node.h b/include/linux/node.h index 708939bae9aa..a79ec4492650 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -32,11 +32,13 @@ extern struct node *node_devices[]; typedef void (*node_registration_func_t)(struct node *);
#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA) -extern int link_mem_sections(int nid, unsigned long start_pfn, - unsigned long end_pfn); +int link_mem_sections(int nid, unsigned long start_pfn, + unsigned long end_pfn, + enum meminit_context context); #else static inline int link_mem_sections(int nid, unsigned long start_pfn, - unsigned long end_pfn) + unsigned long end_pfn, + enum meminit_context context) { return 0; } @@ -61,7 +63,8 @@ static inline int register_one_node(int nid) if (error) return error; /* link memory sections under this node */ - error = link_mem_sections(nid, start_pfn, end_pfn); + error = link_mem_sections(nid, start_pfn, end_pfn, + MEMINIT_EARLY); }
return error; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index c839c4ad4871..e60e28131f67 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1102,7 +1102,8 @@ int __ref add_memory_resource(int nid, struct resource *res, bool online) }
/* link memory sections under this node.*/ - ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1)); + ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1), + MEMINIT_HOTPLUG); BUG_ON(ret);
/* create new memmap entry */