From 9afaf30f7a1aab2022961715a66f644275b8daec Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Tue, 4 May 2021 18:39:04 -0700 Subject: mm/gup: do not migrate zero page On some platforms ZERO_PAGE(0) might end-up in a movable zone. Do not migrate zero page in gup during longterm pinning as migration of zero page is not allowed. For example, in x86 QEMU with 16G of memory and kernelcore=5G parameter, I see the following: Boot#1: zero_pfn 0x48a8d zero_pfn zone: ZONE_DMA32 Boot#2: zero_pfn 0x20168d zero_pfn zone: ZONE_MOVABLE On x86, empty_zero_page is declared in .bss and depending on the loader may end up in different physical locations during boots. Also, move is_zero_pfn() my_zero_pfn() functions under CONFIG_MMU, because zero_pfn that they are using is declared in memory.c which is compiled with CONFIG_MMU. Link: https://lkml.kernel.org/r/20210215161349.246722-9-pasha.tatashin@soleen.com Signed-off-by: Pavel Tatashin Cc: Dan Williams Cc: David Hildenbrand Cc: David Rientjes Cc: Ingo Molnar Cc: Ira Weiny Cc: James Morris Cc: Jason Gunthorpe Cc: Jason Gunthorpe Cc: John Hubbard Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Cc: Michal Hocko Cc: Mike Kravetz Cc: Oscar Salvador Cc: Peter Zijlstra Cc: Sasha Levin Cc: Steven Rostedt (VMware) Cc: Tyler Hicks Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/mmzone.h') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 3b2205741048..92b44149d5b9 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -427,6 +427,10 @@ enum zone_type { * techniques might use alloc_contig_range() to hide previously * exposed pages from the buddy again (e.g., to implement some sort * of memory unplug in virtio-mem). + * 6. ZERO_PAGE(0), kernelcore/movablecore setups might create + * situations where ZERO_PAGE(0) which is allocated differently + * on different platforms may end up in a movable zone. ZERO_PAGE(0) + * cannot be migrated. * * In general, no unmovable allocations that degrade memory offlining * should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range()) -- cgit v1.2.3 From d1e153fea2a8940273174fc17733c44323d35cd5 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Tue, 4 May 2021 18:39:08 -0700 Subject: mm/gup: migrate pinned pages out of movable zone We should not pin pages in ZONE_MOVABLE. Currently, we do not pin only movable CMA pages. Generalize the function that migrates CMA pages to migrate all movable pages. Use is_pinnable_page() to check which pages need to be migrated Link: https://lkml.kernel.org/r/20210215161349.246722-10-pasha.tatashin@soleen.com Signed-off-by: Pavel Tatashin Reviewed-by: John Hubbard Cc: Dan Williams Cc: David Hildenbrand Cc: David Rientjes Cc: Ingo Molnar Cc: Ira Weiny Cc: James Morris Cc: Jason Gunthorpe Cc: Jason Gunthorpe Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Cc: Michal Hocko Cc: Mike Kravetz Cc: Oscar Salvador Cc: Peter Zijlstra Cc: Sasha Levin Cc: Steven Rostedt (VMware) Cc: Tyler Hicks Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 1 + include/linux/mmzone.h | 9 ++++-- include/trace/events/migrate.h | 3 +- mm/gup.c | 67 +++++++++++++++++++++--------------------- 4 files changed, 44 insertions(+), 36 deletions(-) (limited to 'include/linux/mmzone.h') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 175ef15ae9e8..4bb4e519e3f5 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -27,6 +27,7 @@ enum migrate_reason { MR_MEMPOLICY_MBIND, MR_NUMA_MISPLACED, MR_CONTIG_RANGE, + MR_LONGTERM_PIN, MR_TYPES }; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 92b44149d5b9..e8922a67d1a4 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -407,8 +407,13 @@ enum zone_type { * to increase the number of THP/huge pages. Notable special cases are: * * 1. Pinned pages: (long-term) pinning of movable pages might - * essentially turn such pages unmovable. Memory offlining might - * retry a long time. + * essentially turn such pages unmovable. Therefore, we do not allow + * pinning long-term pages in ZONE_MOVABLE. When pages are pinned and + * faulted, they come from the right zone right away. However, it is + * still possible that address space already has pages in + * ZONE_MOVABLE at the time when pages are pinned (i.e. user has + * touches that memory before pinning). In such case we migrate them + * to a different zone. When migration fails - pinning fails. * 2. memblock allocations: kernelcore/movablecore setups might create * situations where ZONE_MOVABLE contains unmovable allocations * after boot. Memory offlining and allocations fail early. diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h index f2c990603888..9fb2a3bbcdfb 100644 --- a/include/trace/events/migrate.h +++ b/include/trace/events/migrate.h @@ -20,7 +20,8 @@ EM( MR_SYSCALL, "syscall_or_cpuset") \ EM( MR_MEMPOLICY_MBIND, "mempolicy_mbind") \ EM( MR_NUMA_MISPLACED, "numa_misplaced") \ - EMe(MR_CONTIG_RANGE, "contig_range") + EM( MR_CONTIG_RANGE, "contig_range") \ + EMe(MR_LONGTERM_PIN, "longterm_pin") /* * First define the enums in the above macros to be exported to userspace diff --git a/mm/gup.c b/mm/gup.c index a1eff7ad31da..4bc57420f535 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -87,11 +87,12 @@ __maybe_unused struct page *try_grab_compound_head(struct page *page, int orig_refs = refs; /* - * Can't do FOLL_LONGTERM + FOLL_PIN with CMA in the gup fast - * path, so fail and let the caller fall back to the slow path. + * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a + * right zone, so fail and let the caller fall back to the slow + * path. */ - if (unlikely(flags & FOLL_LONGTERM) && - is_migrate_cma_page(page)) + if (unlikely((flags & FOLL_LONGTERM) && + !is_pinnable_page(page))) return NULL; /* @@ -1600,17 +1601,17 @@ struct page *get_dump_page(unsigned long addr) } #endif /* CONFIG_ELF_CORE */ -#ifdef CONFIG_CMA -static long check_and_migrate_cma_pages(struct mm_struct *mm, - unsigned long start, - unsigned long nr_pages, - struct page **pages, - struct vm_area_struct **vmas, - unsigned int gup_flags) +#ifdef CONFIG_MIGRATION +static long check_and_migrate_movable_pages(struct mm_struct *mm, + unsigned long start, + unsigned long nr_pages, + struct page **pages, + struct vm_area_struct **vmas, + unsigned int gup_flags) { unsigned long i, isolation_error_count; bool drain_allow; - LIST_HEAD(cma_page_list); + LIST_HEAD(movable_page_list); long ret = nr_pages; struct page *prev_head, *head; struct migration_target_control mtc = { @@ -1628,13 +1629,12 @@ check_again: continue; prev_head = head; /* - * If we get a page from the CMA zone, since we are going to - * be pinning these entries, we might as well move them out - * of the CMA zone if possible. + * If we get a movable page, since we are going to be pinning + * these entries, try to move them out if possible. */ - if (is_migrate_cma_page(head)) { + if (!is_pinnable_page(head)) { if (PageHuge(head)) { - if (!isolate_huge_page(head, &cma_page_list)) + if (!isolate_huge_page(head, &movable_page_list)) isolation_error_count++; } else { if (!PageLRU(head) && drain_allow) { @@ -1646,7 +1646,7 @@ check_again: isolation_error_count++; continue; } - list_add_tail(&head->lru, &cma_page_list); + list_add_tail(&head->lru, &movable_page_list); mod_node_page_state(page_pgdat(head), NR_ISOLATED_ANON + page_is_file_lru(head), @@ -1659,10 +1659,10 @@ check_again: * If list is empty, and no isolation errors, means that all pages are * in the correct zone. */ - if (list_empty(&cma_page_list) && !isolation_error_count) + if (list_empty(&movable_page_list) && !isolation_error_count) return ret; - if (!list_empty(&cma_page_list)) { + if (!list_empty(&movable_page_list)) { /* * drop the above get_user_pages reference. */ @@ -1672,12 +1672,12 @@ check_again: for (i = 0; i < nr_pages; i++) put_page(pages[i]); - ret = migrate_pages(&cma_page_list, alloc_migration_target, + ret = migrate_pages(&movable_page_list, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, - MR_CONTIG_RANGE); + MR_LONGTERM_PIN); if (ret) { - if (!list_empty(&cma_page_list)) - putback_movable_pages(&cma_page_list); + if (!list_empty(&movable_page_list)) + putback_movable_pages(&movable_page_list); return ret > 0 ? -ENOMEM : ret; } @@ -1696,16 +1696,16 @@ check_again: goto check_again; } #else -static long check_and_migrate_cma_pages(struct mm_struct *mm, - unsigned long start, - unsigned long nr_pages, - struct page **pages, - struct vm_area_struct **vmas, - unsigned int gup_flags) +static long check_and_migrate_movable_pages(struct mm_struct *mm, + unsigned long start, + unsigned long nr_pages, + struct page **pages, + struct vm_area_struct **vmas, + unsigned int gup_flags) { return nr_pages; } -#endif /* CONFIG_CMA */ +#endif /* CONFIG_MIGRATION */ /* * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which @@ -1729,8 +1729,9 @@ static long __gup_longterm_locked(struct mm_struct *mm, if (gup_flags & FOLL_LONGTERM) { if (rc > 0) - rc = check_and_migrate_cma_pages(mm, start, rc, pages, - vmas, gup_flags); + rc = check_and_migrate_movable_pages(mm, start, rc, + pages, vmas, + gup_flags); memalloc_pin_restore(flags); } return rc; -- cgit v1.2.3 From a08a2ae3461383c2d50d0997dcc6cd1dd1fefb08 Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Tue, 4 May 2021 18:39:42 -0700 Subject: mm,memory_hotplug: allocate memmap from the added memory range Physical memory hotadd has to allocate a memmap (struct page array) for the newly added memory section. Currently, alloc_pages_node() is used for those allocations. This has some disadvantages: a) an existing memory is consumed for that purpose (eg: ~2MB per 128MB memory section on x86_64) This can even lead to extreme cases where system goes OOM because the physically hotplugged memory depletes the available memory before it is onlined. b) if the whole node is movable then we have off-node struct pages which has performance drawbacks. c) It might be there are no PMD_ALIGNED chunks so memmap array gets populated with base pages. This can be improved when CONFIG_SPARSEMEM_VMEMMAP is enabled. Vmemap page tables can map arbitrary memory. That means that we can reserve a part of the physically hotadded memory to back vmemmap page tables. This implementation uses the beginning of the hotplugged memory for that purpose. There are some non-obviously things to consider though. Vmemmap pages are allocated/freed during the memory hotplug events (add_memory_resource(), try_remove_memory()) when the memory is added/removed. This means that the reserved physical range is not online although it is used. The most obvious side effect is that pfn_to_online_page() returns NULL for those pfns. The current design expects that this should be OK as the hotplugged memory is considered a garbage until it is onlined. For example hibernation wouldn't save the content of those vmmemmaps into the image so it wouldn't be restored on resume but this should be OK as there no real content to recover anyway while metadata is reachable from other data structures (e.g. vmemmap page tables). The reserved space is therefore (de)initialized during the {on,off}line events (mhp_{de}init_memmap_on_memory). That is done by extracting page allocator independent initialization from the regular onlining path. The primary reason to handle the reserved space outside of {on,off}line_pages is to make each initialization specific to the purpose rather than special case them in a single function. As per above, the functions that are introduced are: - mhp_init_memmap_on_memory: Initializes vmemmap pages by calling move_pfn_range_to_zone(), calls kasan_add_zero_shadow(), and onlines as many sections as vmemmap pages fully span. - mhp_deinit_memmap_on_memory: Offlines as many sections as vmemmap pages fully span, removes the range from zhe zone by remove_pfn_range_from_zone(), and calls kasan_remove_zero_shadow() for the range. The new function memory_block_online() calls mhp_init_memmap_on_memory() before doing the actual online_pages(). Should online_pages() fail, we clean up by calling mhp_deinit_memmap_on_memory(). Adjusting of present_pages is done at the end once we know that online_pages() succedeed. On offline, memory_block_offline() needs to unaccount vmemmap pages from present_pages() before calling offline_pages(). This is necessary because offline_pages() tears down some structures based on the fact whether the node or the zone become empty. If offline_pages() fails, we account back vmemmap pages. If it succeeds, we call mhp_deinit_memmap_on_memory(). Hot-remove: We need to be careful when removing memory, as adding and removing memory needs to be done with the same granularity. To check that this assumption is not violated, we check the memory range we want to remove and if a) any memory block has vmemmap pages and b) the range spans more than a single memory block, we scream out loud and refuse to proceed. If all is good and the range was using memmap on memory (aka vmemmap pages), we construct an altmap structure so free_hugepage_table does the right thing and calls vmem_altmap_free instead of free_pagetable. Link: https://lkml.kernel.org/r/20210421102701.25051-5-osalvador@suse.de Signed-off-by: Oscar Salvador Reviewed-by: David Hildenbrand Acked-by: Michal Hocko Cc: Anshuman Khandual Cc: Pavel Tatashin Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/memory.c | 72 ++++++++++++++++-- include/linux/memory.h | 8 +- include/linux/memory_hotplug.h | 15 +++- include/linux/memremap.h | 2 +- include/linux/mmzone.h | 7 +- mm/Kconfig | 5 ++ mm/memory_hotplug.c | 161 ++++++++++++++++++++++++++++++++++++++--- mm/sparse.c | 2 - 8 files changed, 250 insertions(+), 22 deletions(-) (limited to 'include/linux/mmzone.h') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index f209925a5d4e..b31b3af5c490 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -173,16 +173,73 @@ 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 = mem->nr_vmemmap_pages; + struct zone *zone; + int ret; + + zone = zone_for_pfn_range(mem->online_type, mem->nid, start_pfn, nr_pages); + + /* + * Although vmemmap pages have a different lifecycle than the pages + * they describe (they remain until the memory is unplugged), doing + * their initialization and accounting at memory onlining/offlining + * stage helps to keep accounting easier to follow - e.g vmemmaps + * belong to the same zone as the memory they backed. + */ + if (nr_vmemmap_pages) { + ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone); + if (ret) + return ret; + } + + ret = online_pages(start_pfn + nr_vmemmap_pages, + nr_pages - nr_vmemmap_pages, zone); + if (ret) { + if (nr_vmemmap_pages) + mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); + return ret; + } + + /* + * Account once onlining succeeded. If the zone was unpopulated, it is + * now already properly populated. + */ + if (nr_vmemmap_pages) + adjust_present_page_count(zone, nr_vmemmap_pages); - return online_pages(start_pfn, nr_pages, mem->online_type, mem->nid); + return ret; } 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 = mem->nr_vmemmap_pages; + struct zone *zone; + int ret; + + zone = page_zone(pfn_to_page(start_pfn)); + + /* + * Unaccount before offlining, such that unpopulated zone and kthreads + * can properly be torn down in offline_pages(). + */ + if (nr_vmemmap_pages) + adjust_present_page_count(zone, -nr_vmemmap_pages); - return offline_pages(start_pfn, nr_pages); + ret = offline_pages(start_pfn + nr_vmemmap_pages, + nr_pages - nr_vmemmap_pages); + if (ret) { + /* offline_pages() failed. Account back. */ + if (nr_vmemmap_pages) + adjust_present_page_count(zone, nr_vmemmap_pages); + return ret; + } + + if (nr_vmemmap_pages) + mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); + + return ret; } /* @@ -576,7 +633,8 @@ int register_memory(struct memory_block *memory) return ret; } -static int init_memory_block(unsigned long block_id, unsigned long state) +static int init_memory_block(unsigned long block_id, unsigned long state, + unsigned long nr_vmemmap_pages) { struct memory_block *mem; int ret = 0; @@ -593,6 +651,7 @@ static int init_memory_block(unsigned long block_id, unsigned long state) mem->start_section_nr = block_id * sections_per_block; mem->state = state; mem->nid = NUMA_NO_NODE; + mem->nr_vmemmap_pages = nr_vmemmap_pages; ret = register_memory(mem); @@ -612,7 +671,7 @@ static int add_memory_block(unsigned long base_section_nr) if (section_count == 0) return 0; return init_memory_block(memory_block_id(base_section_nr), - MEM_ONLINE); + MEM_ONLINE, 0); } static void unregister_memory(struct memory_block *memory) @@ -634,7 +693,8 @@ static void unregister_memory(struct memory_block *memory) * * Called under device_hotplug_lock. */ -int create_memory_block_devices(unsigned long start, unsigned long size) +int create_memory_block_devices(unsigned long start, unsigned long size, + unsigned long vmemmap_pages) { const unsigned long start_block_id = pfn_to_block_id(PFN_DOWN(start)); unsigned long end_block_id = pfn_to_block_id(PFN_DOWN(start + size)); @@ -647,7 +707,7 @@ int create_memory_block_devices(unsigned long start, unsigned long size) return -EINVAL; for (block_id = start_block_id; block_id != end_block_id; block_id++) { - ret = init_memory_block(block_id, MEM_OFFLINE); + ret = init_memory_block(block_id, MEM_OFFLINE, vmemmap_pages); if (ret) break; } diff --git a/include/linux/memory.h b/include/linux/memory.h index 4da95e684e20..97e92e8b556a 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -29,6 +29,11 @@ struct memory_block { int online_type; /* for passing data to online routine */ int nid; /* NID for this memory block */ struct device dev; + /* + * Number of vmemmap pages. These pages + * lay at the beginning of the memory block. + */ + unsigned long nr_vmemmap_pages; }; int arch_get_memory_phys_device(unsigned long start_pfn); @@ -80,7 +85,8 @@ static inline int memory_notify(unsigned long val, void *v) #else extern int register_memory_notifier(struct notifier_block *nb); extern void unregister_memory_notifier(struct notifier_block *nb); -int create_memory_block_devices(unsigned long start, unsigned long size); +int create_memory_block_devices(unsigned long start, unsigned long size, + unsigned long vmemmap_pages); void remove_memory_block_devices(unsigned long start, unsigned long size); extern void memory_dev_init(void); extern int memory_notify(unsigned long val, void *v); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 7288aa5ef73b..28f32fd00fe9 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -55,6 +55,14 @@ typedef int __bitwise mhp_t; */ #define MHP_MERGE_RESOURCE ((__force mhp_t)BIT(0)) +/* + * We want memmap (struct page array) to be self contained. + * To do so, we will use the beginning of the hot-added range to build + * the page tables for the memmap array that describes the entire range. + * Only selected architectures support it with SPARSE_VMEMMAP. + */ +#define MHP_MEMMAP_ON_MEMORY ((__force mhp_t)BIT(1)) + /* * Extended parameters for memory hotplug: * altmap: alternative allocator for memmap array (optional) @@ -99,9 +107,13 @@ static inline void zone_seqlock_init(struct zone *zone) extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages); extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages); extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); +extern void adjust_present_page_count(struct zone *zone, 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); +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, - int online_type, int nid); + struct zone *zone); extern struct zone *test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn); extern void __offline_isolated_pages(unsigned long start_pfn, @@ -359,6 +371,7 @@ extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_ extern int arch_create_linear_mapping(int nid, u64 start, u64 size, struct mhp_params *params); void arch_remove_linear_mapping(u64 start, u64 size); +extern bool mhp_supports_memmap_on_memory(unsigned long size); #endif /* CONFIG_MEMORY_HOTPLUG */ #endif /* __LINUX_MEMORY_HOTPLUG_H */ diff --git a/include/linux/memremap.h b/include/linux/memremap.h index f5b464daeeca..45a79da89c5f 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -17,7 +17,7 @@ struct device; * @alloc: track pages consumed, private to vmemmap_populate() */ struct vmem_altmap { - const unsigned long base_pfn; + unsigned long base_pfn; const unsigned long end_pfn; const unsigned long reserve; unsigned long free; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index e8922a67d1a4..917bd6c604d5 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -436,6 +436,11 @@ enum zone_type { * situations where ZERO_PAGE(0) which is allocated differently * on different platforms may end up in a movable zone. ZERO_PAGE(0) * cannot be migrated. + * 7. Memory-hotplug: when using memmap_on_memory and onlining the + * memory to the MOVABLE zone, the vmemmap pages are also placed in + * such zone. Such pages cannot be really moved around as they are + * self-stored in the range, but they are treated as movable when + * the range they describe is about to be offlined. * * In general, no unmovable allocations that degrade memory offlining * should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range()) @@ -1392,10 +1397,8 @@ static inline int online_section_nr(unsigned long nr) #ifdef CONFIG_MEMORY_HOTPLUG void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn); -#ifdef CONFIG_MEMORY_HOTREMOVE void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn); #endif -#endif static inline struct mem_section *__pfn_to_section(unsigned long pfn) { diff --git a/mm/Kconfig b/mm/Kconfig index fe4897c3c81b..02d44e3420f5 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -188,6 +188,11 @@ config MEMORY_HOTREMOVE depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE depends on MIGRATION +config MHP_MEMMAP_ON_MEMORY + def_bool y + depends on MEMORY_HOTPLUG && SPARSEMEM_VMEMMAP + depends on ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE + # Heavily threaded applications may benefit from splitting the mm-wide # page_table_lock, so that faults on different parts of the user address # space can be handled with less contention: split it at this NR_CPUS. diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 04f01fabc150..0b3157836814 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -42,6 +42,8 @@ #include "internal.h" #include "shuffle.h" +static bool memmap_on_memory; + /* * online_page_callback contains pointer to current page onlining function. * Initially it is generic_online_page(). If it is required it could be @@ -648,9 +650,16 @@ static void online_pages_range(unsigned long start_pfn, unsigned long nr_pages) * decide to not expose all pages to the buddy (e.g., expose them * later). We account all pages as being online and belonging to this * zone ("present"). + * When using memmap_on_memory, the range might not be aligned to + * MAX_ORDER_NR_PAGES - 1, but pageblock aligned. __ffs() will detect + * this and the first chunk to online will be pageblock_nr_pages. */ - for (pfn = start_pfn; pfn < end_pfn; pfn += MAX_ORDER_NR_PAGES) - (*online_page_callback)(pfn_to_page(pfn), MAX_ORDER - 1); + for (pfn = start_pfn; pfn < end_pfn;) { + int order = min(MAX_ORDER - 1UL, __ffs(pfn)); + + (*online_page_callback)(pfn_to_page(pfn), order); + pfn += (1UL << order); + } /* mark all involved sections as online */ online_mem_sections(start_pfn, end_pfn); @@ -829,7 +838,11 @@ struct zone * zone_for_pfn_range(int online_type, int nid, unsigned start_pfn, return default_zone_for_pfn(nid, start_pfn, nr_pages); } -static void adjust_present_page_count(struct zone *zone, long nr_pages) +/* + * This function should only be called by memory_block_{online,offline}, + * and {online,offline}_pages. + */ +void adjust_present_page_count(struct zone *zone, long nr_pages) { unsigned long flags; @@ -839,12 +852,54 @@ static void adjust_present_page_count(struct zone *zone, long nr_pages) pgdat_resize_unlock(zone->zone_pgdat, &flags); } -int __ref online_pages(unsigned long pfn, unsigned long nr_pages, - int online_type, int nid) +int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, + struct zone *zone) +{ + unsigned long end_pfn = pfn + nr_pages; + int ret; + + ret = kasan_add_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages)); + if (ret) + return ret; + + move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_UNMOVABLE); + + /* + * It might be that the vmemmap_pages fully span sections. If that is + * the case, mark those sections online here as otherwise they will be + * left offline. + */ + if (nr_pages >= PAGES_PER_SECTION) + online_mem_sections(pfn, ALIGN_DOWN(end_pfn, PAGES_PER_SECTION)); + + return ret; +} + +void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages) +{ + unsigned long end_pfn = pfn + nr_pages; + + /* + * It might be that the vmemmap_pages fully span sections. If that is + * the case, mark those sections offline here as otherwise they will be + * left online. + */ + if (nr_pages >= PAGES_PER_SECTION) + offline_mem_sections(pfn, ALIGN_DOWN(end_pfn, PAGES_PER_SECTION)); + + /* + * The pages associated with this vmemmap have been offlined, so + * we can reset its state here. + */ + remove_pfn_range_from_zone(page_zone(pfn_to_page(pfn)), pfn, nr_pages); + kasan_remove_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages)); +} + +int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone) { unsigned long flags; - struct zone *zone; int need_zonelists_rebuild = 0; + const int nid = zone_to_nid(zone); int ret; struct memory_notify arg; @@ -863,7 +918,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, mem_hotplug_begin(); /* associate pfn range with the zone */ - zone = zone_for_pfn_range(online_type, nid, pfn, nr_pages); move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_ISOLATE); arg.start_pfn = pfn; @@ -1077,6 +1131,45 @@ static int online_memory_block(struct memory_block *mem, void *arg) return device_online(&mem->dev); } +bool mhp_supports_memmap_on_memory(unsigned long size) +{ + unsigned long nr_vmemmap_pages = size / PAGE_SIZE; + unsigned long vmemmap_size = nr_vmemmap_pages * sizeof(struct page); + unsigned long remaining_size = size - vmemmap_size; + + /* + * Besides having arch support and the feature enabled at runtime, we + * need a few more assumptions to hold true: + * + * a) We span a single memory block: memory onlining/offlinin;g happens + * in memory block granularity. We don't want the vmemmap of online + * memory blocks to reside on offline memory blocks. In the future, + * we might want to support variable-sized memory blocks to make the + * feature more versatile. + * + * b) The vmemmap pages span complete PMDs: We don't want vmemmap code + * to populate memory from the altmap for unrelated parts (i.e., + * other memory blocks) + * + * c) The vmemmap pages (and thereby the pages that will be exposed to + * the buddy) have to cover full pageblocks: memory onlining/offlining + * code requires applicable ranges to be page-aligned, for example, to + * set the migratetypes properly. + * + * TODO: Although we have a check here to make sure that vmemmap pages + * fully populate a PMD, it is not the right place to check for + * this. A much better solution involves improving vmemmap code + * to fallback to base pages when trying to populate vmemmap using + * altmap as an alternative source of memory, and we do not exactly + * populate a single PMD. + */ + return memmap_on_memory && + IS_ENABLED(CONFIG_MHP_MEMMAP_ON_MEMORY) && + size == memory_block_size_bytes() && + IS_ALIGNED(vmemmap_size, PMD_SIZE) && + IS_ALIGNED(remaining_size, (pageblock_nr_pages << PAGE_SHIFT)); +} + /* * NOTE: The caller must call lock_device_hotplug() to serialize hotplug * and online/offline operations (triggered e.g. by sysfs). @@ -1086,6 +1179,7 @@ static int online_memory_block(struct memory_block *mem, void *arg) int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) { struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) }; + struct vmem_altmap mhp_altmap = {}; u64 start, size; bool new_node = false; int ret; @@ -1112,13 +1206,26 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) goto error; new_node = ret; + /* + * Self hosted memmap array + */ + if (mhp_flags & MHP_MEMMAP_ON_MEMORY) { + if (!mhp_supports_memmap_on_memory(size)) { + ret = -EINVAL; + goto error; + } + mhp_altmap.free = PHYS_PFN(size); + mhp_altmap.base_pfn = PHYS_PFN(start); + params.altmap = &mhp_altmap; + } + /* call arch's memory hotadd */ ret = arch_add_memory(nid, start, size, ¶ms); if (ret < 0) goto error; /* create memory block devices after memory was added */ - ret = create_memory_block_devices(start, size); + ret = create_memory_block_devices(start, size, mhp_altmap.alloc); if (ret) { arch_remove_memory(nid, start, size, NULL); goto error; @@ -1767,6 +1874,14 @@ static int check_memblock_offlined_cb(struct memory_block *mem, void *arg) return 0; } +static int get_nr_vmemmap_pages_cb(struct memory_block *mem, void *arg) +{ + /* + * If not set, continue with the next block. + */ + return mem->nr_vmemmap_pages; +} + static int check_cpu_on_node(pg_data_t *pgdat) { int cpu; @@ -1841,6 +1956,9 @@ EXPORT_SYMBOL(try_offline_node); static int __ref try_remove_memory(int nid, u64 start, u64 size) { int rc = 0; + struct vmem_altmap mhp_altmap = {}; + struct vmem_altmap *altmap = NULL; + unsigned long nr_vmemmap_pages; BUG_ON(check_hotplug_memory_range(start, size)); @@ -1853,6 +1971,31 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) if (rc) return rc; + /* + * We only support removing memory added with MHP_MEMMAP_ON_MEMORY in + * the same granularity it was added - a single memory block. + */ + if (memmap_on_memory) { + nr_vmemmap_pages = walk_memory_blocks(start, size, NULL, + get_nr_vmemmap_pages_cb); + if (nr_vmemmap_pages) { + if (size != memory_block_size_bytes()) { + pr_warn("Refuse to remove %#llx - %#llx," + "wrong granularity\n", + start, start + size); + return -EINVAL; + } + + /* + * Let remove_pmd_table->free_hugepage_table do the + * right thing if we used vmem_altmap when hot-adding + * the range. + */ + mhp_altmap.alloc = nr_vmemmap_pages; + altmap = &mhp_altmap; + } + } + /* remove memmap entry */ firmware_map_remove(start, start + size, "System RAM"); @@ -1864,7 +2007,7 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) mem_hotplug_begin(); - arch_remove_memory(nid, start, size, NULL); + arch_remove_memory(nid, start, size, altmap); if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { memblock_free(start, size); diff --git a/mm/sparse.c b/mm/sparse.c index 33406ea2ecc4..d3fbed26e64e 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -624,7 +624,6 @@ void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn) } } -#ifdef CONFIG_MEMORY_HOTREMOVE /* Mark all memory sections within the pfn range as offline */ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn) { @@ -645,7 +644,6 @@ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn) ms->section_mem_map &= ~SECTION_IS_ONLINE; } } -#endif #ifdef CONFIG_SPARSEMEM_VMEMMAP static struct page * __meminit populate_section_memmap(unsigned long pfn, -- cgit v1.2.3 From cb152a1a95606aadd81df7a537dde9ef16da4b80 Mon Sep 17 00:00:00 2001 From: Shijie Luo Date: Thu, 6 May 2021 18:05:51 -0700 Subject: mm: fix some typos and code style problems fix some typos and code style problems in mm. gfp.h: s/MAXNODES/MAX_NUMNODES mmzone.h: s/then/than rmap.c: s/__vma_split()/__vma_adjust() swap.c: s/__mod_zone_page_stat/__mod_zone_page_state, s/is is/is swap_state.c: s/whoes/whose z3fold.c: code style problem fix in z3fold_unregister_migration zsmalloc.c: s/of/or, s/give/given Link: https://lkml.kernel.org/r/20210419083057.64820-1-luoshijie1@huawei.com Signed-off-by: Shijie Luo Signed-off-by: Miaohe Lin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 +- include/linux/mmzone.h | 2 +- mm/rmap.c | 2 +- mm/swap.c | 4 ++-- mm/swap_state.c | 2 +- mm/z3fold.c | 2 +- mm/zsmalloc.c | 4 ++-- 7 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux/mmzone.h') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 8a5f6c3d7dba..11da8af06704 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -490,7 +490,7 @@ static inline int gfp_zonelist(gfp_t flags) /* * We get the zone list from the current node and the gfp_mask. - * This zone list contains a maximum of MAXNODES*MAX_NR_ZONES zones. + * This zone list contains a maximum of MAX_NUMNODES*MAX_NR_ZONES zones. * There are two zonelists per node, one for all zones with memory and * one containing just zones from the node the zonelist belongs to. * diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 917bd6c604d5..0d53eba1c383 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -55,7 +55,7 @@ enum migratetype { * pageblocks to MIGRATE_CMA which can be done by * __free_pageblock_cma() function. What is important though * is that a range of pageblocks must be aligned to - * MAX_ORDER_NR_PAGES should biggest page be bigger then + * MAX_ORDER_NR_PAGES should biggest page be bigger than * a single pageblock. */ MIGRATE_CMA, diff --git a/mm/rmap.c b/mm/rmap.c index b0fc27e77d6d..693a610e181d 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -257,7 +257,7 @@ static inline void unlock_anon_vma_root(struct anon_vma *root) * Attach the anon_vmas from src to dst. * Returns 0 on success, -ENOMEM on failure. * - * anon_vma_clone() is called by __vma_split(), __split_vma(), copy_vma() and + * anon_vma_clone() is called by __vma_adjust(), __split_vma(), copy_vma() and * anon_vma_fork(). The first three want an exact copy of src, while the last * one, anon_vma_fork(), may try to reuse an existing anon_vma to prevent * endless growth of anon_vma. Since dst->anon_vma is set to NULL before call, diff --git a/mm/swap.c b/mm/swap.c index a75a8265302b..dfb48cf9c2c9 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -496,7 +496,7 @@ void lru_cache_add_inactive_or_unevictable(struct page *page, if (unlikely(unevictable) && !TestSetPageMlocked(page)) { int nr_pages = thp_nr_pages(page); /* - * We use the irq-unsafe __mod_zone_page_stat because this + * We use the irq-unsafe __mod_zone_page_state because this * counter is not modified from interrupt context, and the pte * lock is held(spinlock), which implies preemption disabled. */ @@ -808,7 +808,7 @@ inline void __lru_add_drain_all(bool force_all_cpus) * below which drains the page vectors. * * Let x, y, and z represent some system CPU numbers, where x < y < z. - * Assume CPU #z is is in the middle of the for_each_online_cpu loop + * Assume CPU #z is in the middle of the for_each_online_cpu loop * below and has already reached CPU #y's per-cpu data. CPU #x comes * along, adds some pages to its per-cpu vectors, then calls * lru_add_drain_all(). diff --git a/mm/swap_state.c b/mm/swap_state.c index 3a1259c13f3b..272ea2108c9d 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -792,7 +792,7 @@ static void swap_ra_info(struct vm_fault *vmf, * * Returns the struct page for entry and addr, after queueing swapin. * - * Primitive swap readahead code. We simply read in a few pages whoes + * Primitive swap readahead code. We simply read in a few pages whose * virtual addresses are around the fault address in the same vma. * * Caller must hold read mmap_lock if vmf->vma is not NULL. diff --git a/mm/z3fold.c b/mm/z3fold.c index 9d889ad2bb86..7fe7adaaad01 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -391,7 +391,7 @@ static void z3fold_unregister_migration(struct z3fold_pool *pool) { if (pool->inode) iput(pool->inode); - } +} /* Initializes the z3fold header of a newly allocated z3fold page */ static struct z3fold_header *init_z3fold_page(struct page *page, bool headless, diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 58697f7a43f8..5004c176b045 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -61,7 +61,7 @@ #define ZSPAGE_MAGIC 0x58 /* - * This must be power of 2 and greater than of equal to sizeof(link_free). + * This must be power of 2 and greater than or equal to sizeof(link_free). * These two conditions ensure that any 'struct link_free' itself doesn't * span more than 1 page which avoids complex case of mapping 2 pages simply * to restore link_free pointer values. @@ -530,7 +530,7 @@ static void set_zspage_mapping(struct zspage *zspage, * class maintains a list of zspages where each zspage is divided * into equal sized chunks. Each allocation falls into one of these * classes depending on its size. This function returns index of the - * size class which has chunk size big enough to hold the give size. + * size class which has chunk size big enough to hold the given size. */ static int get_size_class_index(int size) { -- cgit v1.2.3