diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 14f964a7719b..c0436f46cfb7 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -188,6 +188,7 @@ static int memory_block_online(struct memory_block *mem) unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; unsigned long nr_vmemmap_pages = 0; + struct memory_notify arg; struct zone *zone; int ret; @@ -207,9 +208,19 @@ static int memory_block_online(struct memory_block *mem) if (mem->altmap) nr_vmemmap_pages = mem->altmap->free; + arg.altmap_start_pfn = start_pfn; + arg.altmap_nr_pages = nr_vmemmap_pages; + arg.start_pfn = start_pfn + nr_vmemmap_pages; + arg.nr_pages = nr_pages - nr_vmemmap_pages; mem_hotplug_begin(); + ret = memory_notify(MEM_PREPARE_ONLINE, &arg); + ret = notifier_to_errno(ret); + if (ret) + goto out_notifier; + if (nr_vmemmap_pages) { - ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone); + ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, + zone, mem->altmap->inaccessible); if (ret) goto out; } @@ -231,7 +242,11 @@ static int memory_block_online(struct memory_block *mem) nr_vmemmap_pages); mem->zone = zone; + mem_hotplug_done(); + return ret; out: + memory_notify(MEM_FINISH_OFFLINE, &arg); +out_notifier: mem_hotplug_done(); return ret; } @@ -244,6 +259,7 @@ static int memory_block_offline(struct memory_block *mem) unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; unsigned long nr_vmemmap_pages = 0; + struct memory_notify arg; int ret; if (!mem->zone) @@ -275,6 +291,11 @@ static int memory_block_offline(struct memory_block *mem) mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); mem->zone = NULL; + arg.altmap_start_pfn = start_pfn; + arg.altmap_nr_pages = nr_vmemmap_pages; + arg.start_pfn = start_pfn + nr_vmemmap_pages; + arg.nr_pages = nr_pages - nr_vmemmap_pages; + memory_notify(MEM_FINISH_OFFLINE, &arg); out: mem_hotplug_done(); return ret; diff --git a/include/linux/memory.h b/include/linux/memory.h index f53cfdaaaa41..939a16bd5cea 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -96,8 +96,17 @@ int set_memory_block_size_order(unsigned int order); #define MEM_GOING_ONLINE (1<<3) #define MEM_CANCEL_ONLINE (1<<4) #define MEM_CANCEL_OFFLINE (1<<5) +#define MEM_PREPARE_ONLINE (1<<6) +#define MEM_FINISH_OFFLINE (1<<7) struct memory_notify { + /* + * The altmap_start_pfn and altmap_nr_pages fields are designated for + * specifying the altmap range and are exclusively intended for use in + * MEM_PREPARE_ONLINE/MEM_FINISH_OFFLINE notifiers. + */ + unsigned long altmap_start_pfn; + unsigned long altmap_nr_pages; unsigned long start_pfn; unsigned long nr_pages; int status_change_nid_normal; diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 7d2076583494..ee00015575aa 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -106,6 +106,22 @@ typedef int __bitwise mhp_t; * implies the node id (nid). */ #define MHP_NID_IS_MGID ((__force mhp_t)BIT(2)) +/* + * The hotplugged memory is completely inaccessible while the memory is + * offline. The memory provider will handle MEM_PREPARE_ONLINE / + * MEM_FINISH_OFFLINE notifications and make the memory accessible. + * + * This flag is only relevant when used along with MHP_MEMMAP_ON_MEMORY, + * because the altmap cannot be written (e.g., poisoned) when adding + * memory -- before it is set online. + * + * This allows for adding memory with an altmap that is not currently + * made available by a hypervisor. When onlining that memory, the + * hypervisor can be instructed to make that memory available, and + * the onlining phase will not require any memory allocations, which is + * helpful in low-memory situations. + */ +#define MHP_OFFLINE_INACCESSIBLE ((__force mhp_t)BIT(3)) /* * Extended parameters for memory hotplug: @@ -154,7 +170,7 @@ extern void adjust_present_page_count(struct page *page, long nr_pages); /* VM interface that may be used by firmware interface */ extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, - struct zone *zone); + struct zone *zone, bool mhp_off_inaccessible); extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages); extern int online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group); diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 744c830f4b13..9837f3e6fb95 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -25,6 +25,7 @@ struct vmem_altmap { unsigned long free; unsigned long align; unsigned long alloc; + bool inaccessible; }; /* diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 21890994c1d3..707027f69150 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1087,7 +1087,7 @@ void adjust_present_page_count(struct page *page, struct memory_group *group, } int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, - struct zone *zone) + struct zone *zone, bool mhp_off_inaccessible) { unsigned long end_pfn = pfn + nr_pages; int ret, i; @@ -1096,6 +1096,15 @@ int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, if (ret) return ret; + /* + * Memory block is accessible at this stage and hence poison the struct + * pages now. If the memory block is accessible during memory hotplug + * addition phase, then page poisining is already performed in + * sparse_add_section(). + */ + if (mhp_off_inaccessible) + page_init_poison(pfn_to_page(pfn), sizeof(struct page) * nr_pages); + move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_UNMOVABLE); for (i = 0; i < nr_pages; i++) @@ -1415,7 +1424,7 @@ static void __ref remove_memory_blocks_and_altmaps(u64 start, u64 size) } static int create_altmaps_and_memory_blocks(int nid, struct memory_group *group, - u64 start, u64 size) + u64 start, u64 size, mhp_t mhp_flags) { unsigned long memblock_size = memory_block_size_bytes(); u64 cur_start; @@ -1431,6 +1440,8 @@ static int create_altmaps_and_memory_blocks(int nid, struct memory_group *group, }; mhp_altmap.free = memory_block_memmap_on_memory_pages(); + if (mhp_flags & MHP_OFFLINE_INACCESSIBLE) + mhp_altmap.inaccessible = true; params.altmap = kmemdup(&mhp_altmap, sizeof(struct vmem_altmap), GFP_KERNEL); if (!params.altmap) { @@ -1516,7 +1527,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) */ if ((mhp_flags & MHP_MEMMAP_ON_MEMORY) && mhp_supports_memmap_on_memory(memory_block_size_bytes())) { - ret = create_altmaps_and_memory_blocks(nid, group, start, size); + ret = create_altmaps_and_memory_blocks(nid, group, start, size, mhp_flags); if (ret) goto error; } else { diff --git a/mm/sparse.c b/mm/sparse.c index 338cf946dee8..aed0951b87fa 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -908,7 +908,8 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn, * Poison uninitialized struct pages in order to catch invalid flags * combinations. */ - page_init_poison(memmap, sizeof(struct page) * nr_pages); + if (!altmap || !altmap->inaccessible) + page_init_poison(memmap, sizeof(struct page) * nr_pages); ms = __nr_to_section(section_nr); set_section_nid(section_nr, nid);