From 859a85ddf90e714092dea71a0e54c7b9896621be Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 7 Sep 2021 19:54:52 -0700 Subject: mm: remove pfn_valid_within() and CONFIG_HOLES_IN_ZONE Patch series "mm: remove pfn_valid_within() and CONFIG_HOLES_IN_ZONE". After recent updates to freeing unused parts of the memory map, no architecture can have holes in the memory map within a pageblock. This makes pfn_valid_within() check and CONFIG_HOLES_IN_ZONE configuration option redundant. The first patch removes them both in a mechanical way and the second patch simplifies memory_hotplug::test_pages_in_a_zone() that had pfn_valid_within() surrounded by more logic than simple if. This patch (of 2): After recent changes in freeing of the unused parts of the memory map and rework of pfn_valid() in arm and arm64 there are no architectures that can have holes in the memory map within a pageblock and so nothing can enable CONFIG_HOLES_IN_ZONE which guards non trivial implementation of pfn_valid_within(). With that, pfn_valid_within() is always hardwired to 1 and can be completely removed. Remove calls to pfn_valid_within() and CONFIG_HOLES_IN_ZONE. Link: https://lkml.kernel.org/r/20210713080035.7464-1-rppt@kernel.org Link: https://lkml.kernel.org/r/20210713080035.7464-2-rppt@kernel.org Signed-off-by: Mike Rapoport Acked-by: David Hildenbrand Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/Kconfig | 3 --- mm/compaction.c | 20 +++++++------------- mm/memory_hotplug.c | 4 ---- mm/page_alloc.c | 24 ++---------------------- mm/page_isolation.c | 7 +------ mm/page_owner.c | 14 +------------- 6 files changed, 11 insertions(+), 61 deletions(-) (limited to 'mm') diff --git a/mm/Kconfig b/mm/Kconfig index 40a9bfcd5062..14d5d2837737 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -96,9 +96,6 @@ config HAVE_FAST_GUP depends on MMU bool -config HOLES_IN_ZONE - bool - # Don't discard allocated memory used to track "memory" and "reserved" memblocks # after early boot, so it can still be used to test for validity of memory. # Also, memblocks are updated with memory hot(un)plug. diff --git a/mm/compaction.c b/mm/compaction.c index 621508e0ecd5..ed37e1cb4369 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -306,16 +306,14 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source, * is necessary for the block to be a migration source/target. */ do { - if (pfn_valid_within(pfn)) { - if (check_source && PageLRU(page)) { - clear_pageblock_skip(page); - return true; - } + if (check_source && PageLRU(page)) { + clear_pageblock_skip(page); + return true; + } - if (check_target && PageBuddy(page)) { - clear_pageblock_skip(page); - return true; - } + if (check_target && PageBuddy(page)) { + clear_pageblock_skip(page); + return true; } page += (1 << PAGE_ALLOC_COSTLY_ORDER); @@ -585,8 +583,6 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, break; nr_scanned++; - if (!pfn_valid_within(blockpfn)) - goto isolate_fail; /* * For compound pages such as THP and hugetlbfs, we can save @@ -885,8 +881,6 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, cond_resched(); } - if (!pfn_valid_within(low_pfn)) - goto isolate_fail; nr_scanned++; page = pfn_to_page(low_pfn); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 86c3af79e874..8d3376f66f01 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1308,10 +1308,6 @@ struct zone *test_pages_in_a_zone(unsigned long start_pfn, for (; pfn < sec_end_pfn && pfn < end_pfn; pfn += MAX_ORDER_NR_PAGES) { i = 0; - /* This is just a CONFIG_HOLES_IN_ZONE check.*/ - while ((i < MAX_ORDER_NR_PAGES) && - !pfn_valid_within(pfn + i)) - i++; if (i == MAX_ORDER_NR_PAGES || pfn + i >= end_pfn) continue; /* Check if we got outside of the zone */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index eeb3a9cb36bb..79a2fc5b6c6f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -594,8 +594,6 @@ static int page_outside_zone_boundaries(struct zone *zone, struct page *page) static int page_is_consistent(struct zone *zone, struct page *page) { - if (!pfn_valid_within(page_to_pfn(page))) - return 0; if (zone != page_zone(page)) return 0; @@ -1025,16 +1023,12 @@ buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn, if (order >= MAX_ORDER - 2) return false; - if (!pfn_valid_within(buddy_pfn)) - return false; - combined_pfn = buddy_pfn & pfn; higher_page = page + (combined_pfn - pfn); buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1); higher_buddy = higher_page + (buddy_pfn - combined_pfn); - return pfn_valid_within(buddy_pfn) && - page_is_buddy(higher_page, higher_buddy, order + 1); + return page_is_buddy(higher_page, higher_buddy, order + 1); } /* @@ -1095,8 +1089,6 @@ continue_merging: buddy_pfn = __find_buddy_pfn(pfn, order); buddy = page + (buddy_pfn - pfn); - if (!pfn_valid_within(buddy_pfn)) - goto done_merging; if (!page_is_buddy(page, buddy, order)) goto done_merging; /* @@ -1754,9 +1746,7 @@ void __init memblock_free_pages(struct page *page, unsigned long pfn, /* * Check that the whole (or subset of) a pageblock given by the interval of * [start_pfn, end_pfn) is valid and within the same zone, before scanning it - * with the migration of free compaction scanner. The scanners then need to - * use only pfn_valid_within() check for arches that allow holes within - * pageblocks. + * with the migration of free compaction scanner. * * Return struct page pointer of start_pfn, or NULL if checks were not passed. * @@ -1872,8 +1862,6 @@ static inline void __init pgdat_init_report_one_done(void) */ static inline bool __init deferred_pfn_valid(unsigned long pfn) { - if (!pfn_valid_within(pfn)) - return false; if (!(pfn & (pageblock_nr_pages - 1)) && !pfn_valid(pfn)) return false; return true; @@ -2520,11 +2508,6 @@ static int move_freepages(struct zone *zone, int pages_moved = 0; for (pfn = start_pfn; pfn <= end_pfn;) { - if (!pfn_valid_within(pfn)) { - pfn++; - continue; - } - page = pfn_to_page(pfn); if (!PageBuddy(page)) { /* @@ -8814,9 +8797,6 @@ struct page *has_unmovable_pages(struct zone *zone, struct page *page, } for (; iter < pageblock_nr_pages - offset; iter++) { - if (!pfn_valid_within(pfn + iter)) - continue; - page = pfn_to_page(pfn + iter); /* diff --git a/mm/page_isolation.c b/mm/page_isolation.c index bddf788f45bf..471e3a13b541 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -93,8 +93,7 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype) buddy_pfn = __find_buddy_pfn(pfn, order); buddy = page + (buddy_pfn - pfn); - if (pfn_valid_within(buddy_pfn) && - !is_migrate_isolate_page(buddy)) { + if (!is_migrate_isolate_page(buddy)) { __isolate_free_page(page, order); isolated_page = true; } @@ -250,10 +249,6 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn, struct page *page; while (pfn < end_pfn) { - if (!pfn_valid_within(pfn)) { - pfn++; - continue; - } page = pfn_to_page(pfn); if (PageBuddy(page)) /* diff --git a/mm/page_owner.c b/mm/page_owner.c index f51a57e92aa3..62402d22539b 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -276,9 +276,6 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m, pageblock_mt = get_pageblock_migratetype(page); for (; pfn < block_end_pfn; pfn++) { - if (!pfn_valid_within(pfn)) - continue; - /* The pageblock is online, no need to recheck. */ page = pfn_to_page(pfn); @@ -479,10 +476,6 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) continue; } - /* Check for holes within a MAX_ORDER area */ - if (!pfn_valid_within(pfn)) - continue; - page = pfn_to_page(pfn); if (PageBuddy(page)) { unsigned long freepage_order = buddy_order_unsafe(page); @@ -560,14 +553,9 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone) block_end_pfn = min(block_end_pfn, end_pfn); for (; pfn < block_end_pfn; pfn++) { - struct page *page; + struct page *page = pfn_to_page(pfn); struct page_ext *page_ext; - if (!pfn_valid_within(pfn)) - continue; - - page = pfn_to_page(pfn); - if (page_zone(page) != zone) continue; -- cgit v1.2.3 From 673d40c82eb2200da32ae9cc9cac8c584b66b5a9 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 7 Sep 2021 19:54:55 -0700 Subject: mm: memory_hotplug: cleanup after removal of pfn_valid_within() When test_pages_in_a_zone() used pfn_valid_within() is has some logic surrounding pfn_valid_within() checks. Since pfn_valid_within() is gone, this logic can be removed. Link: https://lkml.kernel.org/r/20210713080035.7464-3-rppt@kernel.org Signed-off-by: Mike Rapoport Acked-by: David Hildenbrand Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'mm') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 8d3376f66f01..f829805fe1ca 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1298,7 +1298,7 @@ struct zone *test_pages_in_a_zone(unsigned long start_pfn, unsigned long pfn, sec_end_pfn; struct zone *zone = NULL; struct page *page; - int i; + for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn + 1); pfn < end_pfn; pfn = sec_end_pfn, sec_end_pfn += PAGES_PER_SECTION) { @@ -1307,13 +1307,10 @@ struct zone *test_pages_in_a_zone(unsigned long start_pfn, continue; for (; pfn < sec_end_pfn && pfn < end_pfn; pfn += MAX_ORDER_NR_PAGES) { - i = 0; - if (i == MAX_ORDER_NR_PAGES || pfn + i >= end_pfn) - continue; /* Check if we got outside of the zone */ - if (zone && !zone_spans_pfn(zone, pfn + i)) + if (zone && !zone_spans_pfn(zone, pfn)) return NULL; - page = pfn_to_page(pfn + i); + page = pfn_to_page(pfn); if (zone && page_zone(page) != zone) return NULL; zone = page_zone(page); -- cgit v1.2.3 From 7cf209ba8a86410939a24cb1aeb279479a7e0ca6 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 7 Sep 2021 19:54:59 -0700 Subject: mm/memory_hotplug: use "unsigned long" for PFN in zone_for_pfn_range() Patch series "mm/memory_hotplug: preparatory patches for new online policy and memory" These are all cleanups and one fix previously sent as part of [1]: [PATCH v1 00/12] mm/memory_hotplug: "auto-movable" online policy and memory groups. These patches make sense even without the other series, therefore I pulled them out to make the other series easier to digest. [1] https://lkml.kernel.org/r/20210607195430.48228-1-david@redhat.com This patch (of 4): Checkpatch complained on a follow-up patch that we are using "unsigned" here, which defaults to "unsigned int" and checkpatch is correct. As we will search for a fitting zone using the wrong pfn, we might end up onlining memory to one of the special kernel zones, such as ZONE_DMA, which can end badly as the onlined memory does not satisfy properties of these zones. Use "unsigned long" instead, just as we do in other places when handling PFNs. This can bite us once we have physical addresses in the range of multiple TB. Link: https://lkml.kernel.org/r/20210712124052.26491-2-david@redhat.com Fixes: e5e689302633 ("mm, memory_hotplug: display allowed zones in the preferred ordering") Signed-off-by: David Hildenbrand Reviewed-by: Pankaj Gupta Reviewed-by: Muchun Song Reviewed-by: Oscar Salvador Cc: David Hildenbrand Cc: Vitaly Kuznetsov Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: Pankaj Gupta Cc: Wei Yang Cc: Michal Hocko Cc: Dan Williams Cc: Anshuman Khandual Cc: Dave Hansen Cc: Vlastimil Babka Cc: Mike Rapoport Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Pavel Tatashin Cc: Heiko Carstens Cc: Michael Ellerman Cc: Catalin Marinas Cc: virtualization@lists.linux-foundation.org Cc: Andy Lutomirski Cc: "Aneesh Kumar K.V" Cc: Anton Blanchard Cc: Ard Biesheuvel Cc: Baoquan He Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Dave Jiang Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jia He Cc: Joe Perches Cc: Kefeng Wang Cc: Laurent Dufour Cc: Michel Lespinasse Cc: Nathan Lynch Cc: Nicholas Piggin Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Pierre Morel Cc: "Rafael J. Wysocki" Cc: Rich Felker Cc: Scott Cheloha Cc: Sergei Trofimovich Cc: Thiago Jung Bauermann Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vishal Verma Cc: Will Deacon Cc: Yoshinori Sato Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 4 ++-- mm/memory_hotplug.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index a7fd2c3ccb77..d01b504ce06f 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -339,8 +339,8 @@ extern void sparse_remove_section(struct mem_section *ms, unsigned long map_offset, struct vmem_altmap *altmap); extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); -extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn, - unsigned long nr_pages); +extern struct zone *zone_for_pfn_range(int online_type, int nid, + unsigned long start_pfn, unsigned long nr_pages); 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); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index f829805fe1ca..fa349acb8810 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -708,8 +708,8 @@ static inline struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn return movable_node_enabled ? movable_zone : kernel_zone; } -struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn, - unsigned long nr_pages) +struct zone *zone_for_pfn_range(int online_type, int nid, + unsigned long start_pfn, unsigned long nr_pages) { if (online_type == MMOP_ONLINE_KERNEL) return default_kernel_zone_for_pfn(nid, start_pfn, nr_pages); -- cgit v1.2.3 From 65a2aa5f482ed0c1b5afb9e6b0b9e0b16bb8b616 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 7 Sep 2021 19:55:04 -0700 Subject: mm/memory_hotplug: remove nid parameter from arch_remove_memory() The parameter is unused, let's remove it. Link: https://lkml.kernel.org/r/20210712124052.26491-3-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Catalin Marinas Acked-by: Michael Ellerman [powerpc] Acked-by: Heiko Carstens [s390] Reviewed-by: Pankaj Gupta Reviewed-by: Oscar Salvador Cc: Catalin Marinas Cc: Will Deacon Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: Yoshinori Sato Cc: Rich Felker Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Anshuman Khandual Cc: Ard Biesheuvel Cc: Mike Rapoport Cc: Nicholas Piggin Cc: Pavel Tatashin Cc: Baoquan He Cc: Laurent Dufour Cc: Sergei Trofimovich Cc: Kefeng Wang Cc: Michel Lespinasse Cc: Christophe Leroy Cc: "Aneesh Kumar K.V" Cc: Thiago Jung Bauermann Cc: Joe Perches Cc: Pierre Morel Cc: Jia He Cc: Anton Blanchard Cc: Dan Williams Cc: Dave Jiang Cc: Jason Wang Cc: Len Brown Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Nathan Lynch Cc: Pankaj Gupta Cc: "Rafael J. Wysocki" Cc: "Rafael J. Wysocki" Cc: Scott Cheloha Cc: Vishal Verma Cc: Vitaly Kuznetsov Cc: Vlastimil Babka Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/mm/mmu.c | 3 +-- arch/ia64/mm/init.c | 3 +-- arch/powerpc/mm/mem.c | 3 +-- arch/s390/mm/init.c | 3 +-- arch/sh/mm/init.c | 3 +-- arch/x86/mm/init_32.c | 3 +-- arch/x86/mm/init_64.c | 3 +-- include/linux/memory_hotplug.h | 3 +-- mm/memory_hotplug.c | 4 ++-- mm/memremap.c | 5 +---- 10 files changed, 11 insertions(+), 22 deletions(-) (limited to 'mm') diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 9ff0de1b2b93..cfd9deb347c3 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1502,8 +1502,7 @@ int arch_add_memory(int nid, u64 start, u64 size, return ret; } -void arch_remove_memory(int nid, u64 start, u64 size, - struct vmem_altmap *altmap) +void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 064a967a7b6e..5c6da8d83c1a 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -484,8 +484,7 @@ int arch_add_memory(int nid, u64 start, u64 size, return ret; } -void arch_remove_memory(int nid, u64 start, u64 size, - struct vmem_altmap *altmap) +void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index ad198b439222..c3c4e31462ec 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -119,8 +119,7 @@ int __ref arch_add_memory(int nid, u64 start, u64 size, return rc; } -void __ref arch_remove_memory(int nid, u64 start, u64 size, - struct vmem_altmap *altmap) +void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 8ac710de1ab1..d85bd7f5d8dc 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -306,8 +306,7 @@ int arch_add_memory(int nid, u64 start, u64 size, return rc; } -void arch_remove_memory(int nid, u64 start, u64 size, - struct vmem_altmap *altmap) +void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index ce26c7f8950a..506784702430 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -414,8 +414,7 @@ int arch_add_memory(int nid, u64 start, u64 size, return ret; } -void arch_remove_memory(int nid, u64 start, u64 size, - struct vmem_altmap *altmap) +void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = PFN_DOWN(start); unsigned long nr_pages = size >> PAGE_SHIFT; diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 74b78840182d..bd90b8fe81e4 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -801,8 +801,7 @@ int arch_add_memory(int nid, u64 start, u64 size, return __add_pages(nid, start_pfn, nr_pages, params); } -void arch_remove_memory(int nid, u64 start, u64 size, - struct vmem_altmap *altmap) +void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index ddeaba947eb3..a6e11763763f 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1255,8 +1255,7 @@ kernel_physical_mapping_remove(unsigned long start, unsigned long end) remove_pagetable(start, end, true, NULL); } -void __ref arch_remove_memory(int nid, u64 start, u64 size, - struct vmem_altmap *altmap) +void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index d01b504ce06f..010a192298b5 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -130,8 +130,7 @@ static inline bool movable_node_is_enabled(void) return movable_node_enabled; } -extern void arch_remove_memory(int nid, u64 start, u64 size, - struct vmem_altmap *altmap); +extern void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap); extern void __remove_pages(unsigned long start_pfn, unsigned long nr_pages, struct vmem_altmap *altmap); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index fa349acb8810..14c4f6051c13 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1106,7 +1106,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) /* create memory block devices after memory was added */ ret = create_memory_block_devices(start, size, mhp_altmap.alloc); if (ret) { - arch_remove_memory(nid, start, size, NULL); + arch_remove_memory(start, size, NULL); goto error; } @@ -1886,7 +1886,7 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) mem_hotplug_begin(); - arch_remove_memory(nid, start, size, altmap); + arch_remove_memory(start, size, altmap); if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { memblock_free(start, size); diff --git a/mm/memremap.c b/mm/memremap.c index 15a074ffb8d7..ed593bf87109 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -140,14 +140,11 @@ static void pageunmap_range(struct dev_pagemap *pgmap, int range_id) { struct range *range = &pgmap->ranges[range_id]; struct page *first_page; - int nid; /* make sure to access a memmap that was actually initialized */ first_page = pfn_to_page(pfn_first(pgmap, range_id)); /* pages are dead and unused, undo the arch mapping */ - nid = page_to_nid(first_page); - mem_hotplug_begin(); remove_pfn_range_from_zone(page_zone(first_page), PHYS_PFN(range->start), PHYS_PFN(range_len(range))); @@ -155,7 +152,7 @@ static void pageunmap_range(struct dev_pagemap *pgmap, int range_id) __remove_pages(PHYS_PFN(range->start), PHYS_PFN(range_len(range)), NULL); } else { - arch_remove_memory(nid, range->start, range_len(range), + arch_remove_memory(range->start, range_len(range), pgmap_altmap(pgmap)); kasan_remove_zero_shadow(__va(range->start), range_len(range)); } -- cgit v1.2.3 From e1c158e4956612e7bada4c03dfb99210af4d6cde Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 7 Sep 2021 19:55:09 -0700 Subject: mm/memory_hotplug: remove nid parameter from remove_memory() and friends There is only a single user remaining. We can simply lookup the nid only used for node offlining purposes when walking our memory blocks. We don't expect to remove multi-nid ranges; and if we'd ever do, we most probably don't care about removing multi-nid ranges that actually result in empty nodes. If ever required, we can detect the "multi-nid" scenario and simply try offlining all online nodes. Link: https://lkml.kernel.org/r/20210712124052.26491-4-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Michael Ellerman (powerpc) Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Dan Williams Cc: Vishal Verma Cc: Dave Jiang Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: Nathan Lynch Cc: Laurent Dufour Cc: "Aneesh Kumar K.V" Cc: Scott Cheloha Cc: Anton Blanchard Cc: Andy Lutomirski Cc: Anshuman Khandual Cc: Ard Biesheuvel Cc: Baoquan He Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Dave Hansen Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jia He Cc: Joe Perches Cc: Kefeng Wang Cc: Michal Hocko Cc: Michel Lespinasse Cc: Mike Rapoport Cc: Nicholas Piggin Cc: Oscar Salvador Cc: Pankaj Gupta Cc: Pankaj Gupta Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Pierre Morel Cc: "Rafael J. Wysocki" Cc: Rich Felker Cc: Sergei Trofimovich Cc: Thiago Jung Bauermann Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vitaly Kuznetsov Cc: Vlastimil Babka Cc: Wei Yang Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/platforms/pseries/hotplug-memory.c | 9 ++++---- drivers/acpi/acpi_memhotplug.c | 7 +------ drivers/dax/kmem.c | 3 +-- drivers/virtio/virtio_mem.c | 4 ++-- include/linux/memory_hotplug.h | 10 ++++----- mm/memory_hotplug.c | 28 +++++++++++++++---------- 6 files changed, 30 insertions(+), 31 deletions(-) (limited to 'mm') diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 377d852f5a9a..ef5c24b42cf1 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -286,7 +286,7 @@ static int pseries_remove_memblock(unsigned long base, unsigned long memblock_si { unsigned long block_sz, start_pfn; int sections_per_block; - int i, nid; + int i; start_pfn = base >> PAGE_SHIFT; @@ -297,10 +297,9 @@ static int pseries_remove_memblock(unsigned long base, unsigned long memblock_si block_sz = pseries_memory_block_size(); sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE; - nid = memory_add_physaddr_to_nid(base); for (i = 0; i < sections_per_block; i++) { - __remove_memory(nid, base, MIN_MEMORY_BLOCK_SIZE); + __remove_memory(base, MIN_MEMORY_BLOCK_SIZE); base += MIN_MEMORY_BLOCK_SIZE; } @@ -387,7 +386,7 @@ static int dlpar_remove_lmb(struct drmem_lmb *lmb) block_sz = pseries_memory_block_size(); - __remove_memory(mem_block->nid, lmb->base_addr, block_sz); + __remove_memory(lmb->base_addr, block_sz); put_device(&mem_block->dev); /* Update memory regions for memory remove */ @@ -660,7 +659,7 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) rc = dlpar_online_lmb(lmb); if (rc) { - __remove_memory(nid, lmb->base_addr, block_sz); + __remove_memory(lmb->base_addr, block_sz); invalidate_lmb_associativity_index(lmb); } else { lmb->flags |= DRCONF_MEM_ASSIGNED; diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c index 8cc195c4c861..1d01d9414c40 100644 --- a/drivers/acpi/acpi_memhotplug.c +++ b/drivers/acpi/acpi_memhotplug.c @@ -239,19 +239,14 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device) static void acpi_memory_remove_memory(struct acpi_memory_device *mem_device) { - acpi_handle handle = mem_device->device->handle; struct acpi_memory_info *info, *n; - int nid = acpi_get_node(handle); list_for_each_entry_safe(info, n, &mem_device->res_list, list) { if (!info->enabled) continue; - if (nid == NUMA_NO_NODE) - nid = memory_add_physaddr_to_nid(info->start_addr); - acpi_unbind_memory_blocks(info); - __remove_memory(nid, info->start_addr, info->length); + __remove_memory(info->start_addr, info->length); list_del(&info->list); kfree(info); } diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c index ac231cc36359..99e0f60c4c26 100644 --- a/drivers/dax/kmem.c +++ b/drivers/dax/kmem.c @@ -156,8 +156,7 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax) if (rc) continue; - rc = remove_memory(dev_dax->target_node, range.start, - range_len(&range)); + rc = remove_memory(range.start, range_len(&range)); if (rc == 0) { release_resource(data->res[i]); kfree(data->res[i]); diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index b91bc810a87e..7e83ed373e00 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -677,7 +677,7 @@ static int virtio_mem_remove_memory(struct virtio_mem *vm, uint64_t addr, dev_dbg(&vm->vdev->dev, "removing memory: 0x%llx - 0x%llx\n", addr, addr + size - 1); - rc = remove_memory(vm->nid, addr, size); + rc = remove_memory(addr, size); if (!rc) { atomic64_sub(size, &vm->offline_size); /* @@ -720,7 +720,7 @@ static int virtio_mem_offline_and_remove_memory(struct virtio_mem *vm, "offlining and removing memory: 0x%llx - 0x%llx\n", addr, addr + size - 1); - rc = offline_and_remove_memory(vm->nid, addr, size); + rc = offline_and_remove_memory(addr, size); if (!rc) { atomic64_sub(size, &vm->offline_size); /* diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 010a192298b5..068e3dcf4690 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -292,9 +292,9 @@ static inline void pgdat_resize_init(struct pglist_data *pgdat) {} extern void try_offline_node(int nid); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); -extern int remove_memory(int nid, u64 start, u64 size); -extern void __remove_memory(int nid, u64 start, u64 size); -extern int offline_and_remove_memory(int nid, u64 start, u64 size); +extern int remove_memory(u64 start, u64 size); +extern void __remove_memory(u64 start, u64 size); +extern int offline_and_remove_memory(u64 start, u64 size); #else static inline void try_offline_node(int nid) {} @@ -304,12 +304,12 @@ static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages) return -EINVAL; } -static inline int remove_memory(int nid, u64 start, u64 size) +static inline int remove_memory(u64 start, u64 size) { return -EBUSY; } -static inline void __remove_memory(int nid, u64 start, u64 size) {} +static inline void __remove_memory(u64 start, u64 size) {} #endif /* CONFIG_MEMORY_HOTREMOVE */ extern void set_zone_contiguous(struct zone *zone); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 14c4f6051c13..6ea62efe2a8f 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1739,7 +1739,9 @@ failed_removal: static int check_memblock_offlined_cb(struct memory_block *mem, void *arg) { int ret = !is_memblock_offlined(mem); + int *nid = arg; + *nid = mem->nid; if (unlikely(ret)) { phys_addr_t beginpa, endpa; @@ -1832,12 +1834,12 @@ void try_offline_node(int nid) } EXPORT_SYMBOL(try_offline_node); -static int __ref try_remove_memory(int nid, u64 start, u64 size) +static int __ref try_remove_memory(u64 start, u64 size) { - int rc = 0; struct vmem_altmap mhp_altmap = {}; struct vmem_altmap *altmap = NULL; unsigned long nr_vmemmap_pages; + int rc = 0, nid = NUMA_NO_NODE; BUG_ON(check_hotplug_memory_range(start, size)); @@ -1845,8 +1847,12 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) * All memory blocks must be offlined before removing memory. Check * whether all memory blocks in question are offline and return error * if this is not the case. + * + * While at it, determine the nid. Note that if we'd have mixed nodes, + * we'd only try to offline the last determined one -- which is good + * enough for the cases we care about. */ - rc = walk_memory_blocks(start, size, NULL, check_memblock_offlined_cb); + rc = walk_memory_blocks(start, size, &nid, check_memblock_offlined_cb); if (rc) return rc; @@ -1895,7 +1901,8 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) release_mem_region_adjustable(start, size); - try_offline_node(nid); + if (nid != NUMA_NO_NODE) + try_offline_node(nid); mem_hotplug_done(); return 0; @@ -1903,7 +1910,6 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) /** * __remove_memory - Remove memory if every memory block is offline - * @nid: the node ID * @start: physical address of the region to remove * @size: size of the region to remove * @@ -1911,14 +1917,14 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) * and online/offline operations before this call, as required by * try_offline_node(). */ -void __remove_memory(int nid, u64 start, u64 size) +void __remove_memory(u64 start, u64 size) { /* * trigger BUG() if some memory is not offlined prior to calling this * function */ - if (try_remove_memory(nid, start, size)) + if (try_remove_memory(start, size)) BUG(); } @@ -1926,12 +1932,12 @@ void __remove_memory(int nid, u64 start, u64 size) * Remove memory if every memory block is offline, otherwise return -EBUSY is * some memory is not offline */ -int remove_memory(int nid, u64 start, u64 size) +int remove_memory(u64 start, u64 size) { int rc; lock_device_hotplug(); - rc = try_remove_memory(nid, start, size); + rc = try_remove_memory(start, size); unlock_device_hotplug(); return rc; @@ -1991,7 +1997,7 @@ static int try_reonline_memory_block(struct memory_block *mem, void *arg) * unplugged all memory (so it's no longer in use) and want to offline + remove * that memory. */ -int offline_and_remove_memory(int nid, u64 start, u64 size) +int offline_and_remove_memory(u64 start, u64 size) { const unsigned long mb_count = size / memory_block_size_bytes(); uint8_t *online_types, *tmp; @@ -2027,7 +2033,7 @@ int offline_and_remove_memory(int nid, u64 start, u64 size) * This cannot fail as it cannot get onlined in the meantime. */ if (!rc) { - rc = try_remove_memory(nid, start, size); + rc = try_remove_memory(start, size); if (rc) pr_err("%s: Failed to remove memory: %d", __func__, rc); } -- cgit v1.2.3 From 4b0970024408afb17886e0c76e9761c4264db2a8 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 7 Sep 2021 19:55:19 -0700 Subject: mm: track present early pages per zone Patch series "mm/memory_hotplug: "auto-movable" online policy and memory groups", v3. I. Goal The goal of this series is improving in-kernel auto-online support. It tackles the fundamental problems that: 1) We can create zone imbalances when onlining all memory blindly to ZONE_MOVABLE, in the worst case crashing the system. We have to know upfront how much memory we are going to hotplug such that we can safely enable auto-onlining of all hotplugged memory to ZONE_MOVABLE via "online_movable". This is far from practical and only applicable in limited setups -- like inside VMs under the RHV/oVirt hypervisor which will never hotplug more than 3 times the boot memory (and the limitation is only in place due to the Linux limitation). 2) We see more setups that implement dynamic VM resizing, hot(un)plugging memory to resize VM memory. In these setups, we might hotplug a lot of memory, but it might happen in various small steps in both directions (e.g., 2 GiB -> 8 GiB -> 4 GiB -> 16 GiB ...). virtio-mem is the primary driver of this upstream right now, performing such dynamic resizing NUMA-aware via multiple virtio-mem devices. Onlining all hotplugged memory to ZONE_NORMAL means we basically have no hotunplug guarantees. Onlining all to ZONE_MOVABLE means we can easily run into zone imbalances when growing a VM. We want a mixture, and we want as much memory as reasonable/configured in ZONE_MOVABLE. Details regarding zone imbalances can be found at [1]. 3) Memory devices consist of 1..X memory block devices, however, the kernel doesn't really track the relationship. Consequently, also user space has no idea. We want to make per-device decisions. As one example, for memory hotunplug it doesn't make sense to use a mixture of zones within a single DIMM: we want all MOVABLE if possible, otherwise all !MOVABLE, because any !MOVABLE part will easily block the whole DIMM from getting hotunplugged. As another example, virtio-mem operates on individual units that span 1..X memory blocks. Similar to a DIMM, we want a unit to either be all MOVABLE or !MOVABLE. A "unit" can be thought of like a DIMM, however, all units of a virtio-mem device logically belong together and are managed (added/removed) by a single driver. We want as much memory of a virtio-mem device to be MOVABLE as possible. 4) We want memory onlining to be done right from the kernel while adding memory, not triggered by user space via udev rules; for example, this is reqired for fast memory hotplug for drivers that add individual memory blocks, like virito-mem. We want a way to configure a policy in the kernel and avoid implementing advanced policies in user space. The auto-onlining support we have in the kernel is not sufficient. All we have is a) online everything MOVABLE (online_movable) b) online everything !MOVABLE (online_kernel) c) keep zones contiguous (online). This series allows configuring c) to mean instead "online movable if possible according to the coniguration, driven by a maximum MOVABLE:KERNEL ratio" -- a new onlining policy. II. Approach This series does 3 things: 1) Introduces the "auto-movable" online policy that initially operates on individual memory blocks only. It uses a maximum MOVABLE:KERNEL ratio to make a decision whether a memory block will be onlined to ZONE_MOVABLE or not. However, in the basic form, hotplugged KERNEL memory does not allow for more MOVABLE memory (details in the patches). CMA memory is treated like MOVABLE memory. 2) Introduces static (e.g., DIMM) and dynamic (e.g., virtio-mem) memory groups and uses group information to make decisions in the "auto-movable" online policy across memory blocks of a single memory device (modeled as memory group). More details can be found in patch #3 or in the DIMM example below. 3) Maximizes ZONE_MOVABLE memory within dynamic memory groups, by allowing ZONE_NORMAL memory within a dynamic memory group to allow for more ZONE_MOVABLE memory within the same memory group. The target use case is dynamic VM resizing using virtio-mem. See the virtio-mem example below. I remember that the basic idea of using a ratio to implement a policy in the kernel was once mentioned by Vitaly Kuznetsov, but I might be wrong (I lost the pointer to that discussion). For me, the main use case is using it along with virtio-mem (and DIMMs / ppc64 dlpar where necessary) for dynamic resizing of VMs, increasing the amount of memory we can hotunplug reliably again if we might eventually hotplug a lot of memory to a VM. III. Target Usage The target usage will be: 1) Linux boots with "mhp_default_online_type=offline" 2) User space (e.g., systemd unit) configures memory onlining (according to a config file and system properties), for example: * Setting memory_hotplug.online_policy=auto-movable * Setting memory_hotplug.auto_movable_ratio=301 * Setting memory_hotplug.auto_movable_numa_aware=true 3) User space enabled auto onlining via "echo online > /sys/devices/system/memory/auto_online_blocks" 4) User space triggers manual onlining of all already-offline memory blocks (go over offline memory blocks and set them to "online") IV. Example For DIMMs, hotplugging 4 GiB DIMMs to a 4 GiB VM with a configured ratio of 301% results in the following layout: Memory block 0-15: DMA32 (early) Memory block 32-47: Normal (early) Memory block 48-79: Movable (DIMM 0) Memory block 80-111: Movable (DIMM 1) Memory block 112-143: Movable (DIMM 2) Memory block 144-275: Normal (DIMM 3) Memory block 176-207: Normal (DIMM 4) ... all Normal (-> hotplugged Normal memory does not allow for more Movable memory) For virtio-mem, using a simple, single virtio-mem device with a 4 GiB VM will result in the following layout: Memory block 0-15: DMA32 (early) Memory block 32-47: Normal (early) Memory block 48-143: Movable (virtio-mem, first 12 GiB) Memory block 144: Normal (virtio-mem, next 128 MiB) Memory block 145-147: Movable (virtio-mem, next 384 MiB) Memory block 148: Normal (virtio-mem, next 128 MiB) Memory block 149-151: Movable (virtio-mem, next 384 MiB) ... Normal/Movable mixture as above (-> hotplugged Normal memory allows for more Movable memory within the same device) Which gives us maximum flexibility when dynamically growing/shrinking a VM in smaller steps. V. Doc Update I'll update the memory-hotplug.rst documentation, once the overhaul [1] is usptream. Until then, details can be found in patch #2. VI. Future Work 1) Use memory groups for ppc64 dlpar 2) Being able to specify a portion of (early) kernel memory that will be excluded from the ratio. Like "128 MiB globally/per node" are excluded. This might be helpful when starting VMs with extremely small memory footprint (e.g., 128 MiB) and hotplugging memory later -- not wanting the first hotplugged units getting onlined to ZONE_MOVABLE. One alternative would be a trigger to not consider ZONE_DMA memory in the ratio. We'll have to see if this is really rrequired. 3) Indicate to user space that MOVABLE might be a bad idea -- especially relevant when memory ballooning without support for balloon compaction is active. This patch (of 9): For implementing a new memory onlining policy, which determines when to online memory blocks to ZONE_MOVABLE semi-automatically, we need the number of present early (boot) pages -- present pages excluding hotplugged pages. Let's track these pages per zone. Pass a page instead of the zone to adjust_present_page_count(), similar as adjust_managed_page_count() and derive the zone from the page. It's worth noting that a memory block to be offlined/onlined is either completely "early" or "not early". add_memory() and friends can only add complete memory blocks and we only online/offline complete (individual) memory blocks. Link: https://lkml.kernel.org/r/20210806124715.17090-1-david@redhat.com Link: https://lkml.kernel.org/r/20210806124715.17090-2-david@redhat.com Signed-off-by: David Hildenbrand Cc: Vitaly Kuznetsov Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: Marek Kedzierski Cc: Hui Zhu Cc: Pankaj Gupta Cc: Wei Yang Cc: Oscar Salvador Cc: Michal Hocko Cc: Dan Williams Cc: Anshuman Khandual Cc: Dave Hansen Cc: Vlastimil Babka Cc: Mike Rapoport Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Pavel Tatashin Cc: Greg Kroah-Hartman Cc: Rafael J. Wysocki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/memory.c | 14 +++++++------- include/linux/memory_hotplug.h | 2 +- include/linux/mmzone.h | 7 +++++++ mm/memory_hotplug.c | 14 +++++++++++--- mm/page_alloc.c | 3 +++ 5 files changed, 29 insertions(+), 11 deletions(-) (limited to 'mm') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index aa31a21f33d7..86ec2dc82fc2 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -205,7 +205,8 @@ static int memory_block_online(struct memory_block *mem) * now already properly populated. */ if (nr_vmemmap_pages) - adjust_present_page_count(zone, nr_vmemmap_pages); + adjust_present_page_count(pfn_to_page(start_pfn), + nr_vmemmap_pages); return ret; } @@ -215,24 +216,23 @@ 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; /* * Unaccount before offlining, such that unpopulated zone and kthreads * can properly be torn down in offline_pages(). */ - if (nr_vmemmap_pages) { - zone = page_zone(pfn_to_page(start_pfn)); - adjust_present_page_count(zone, -nr_vmemmap_pages); - } + if (nr_vmemmap_pages) + adjust_present_page_count(pfn_to_page(start_pfn), + -nr_vmemmap_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); + adjust_present_page_count(pfn_to_page(start_pfn), + nr_vmemmap_pages); return ret; } diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 068e3dcf4690..39b04e99a30e 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -95,7 +95,7 @@ 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); +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); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ee3a86830519..1c0e3bf42521 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -540,6 +540,10 @@ struct zone { * is calculated as: * present_pages = spanned_pages - absent_pages(pages in holes); * + * present_early_pages is present pages existing within the zone + * located on memory available since early boot, excluding hotplugged + * memory. + * * managed_pages is present pages managed by the buddy system, which * is calculated as (reserved_pages includes pages allocated by the * bootmem allocator): @@ -572,6 +576,9 @@ struct zone { atomic_long_t managed_pages; unsigned long spanned_pages; unsigned long present_pages; +#if defined(CONFIG_MEMORY_HOTPLUG) + unsigned long present_early_pages; +#endif #ifdef CONFIG_CMA unsigned long cma_pages; #endif diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 6ea62efe2a8f..8a99fa6d096c 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -724,8 +724,16 @@ struct zone *zone_for_pfn_range(int online_type, int nid, * 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) +void adjust_present_page_count(struct page *page, long nr_pages) { + struct zone *zone = page_zone(page); + + /* + * We only support onlining/offlining/adding/removing of complete + * memory blocks; therefore, either all is either early or hotplugged. + */ + if (early_section(__pfn_to_section(page_to_pfn(page)))) + zone->present_early_pages += nr_pages; zone->present_pages += nr_pages; zone->zone_pgdat->node_present_pages += nr_pages; } @@ -826,7 +834,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *z } online_pages_range(pfn, nr_pages); - adjust_present_page_count(zone, nr_pages); + adjust_present_page_count(pfn_to_page(pfn), nr_pages); node_states_set_node(nid, &arg); if (need_zonelists_rebuild) @@ -1697,7 +1705,7 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages) /* removal success */ adjust_managed_page_count(pfn_to_page(start_pfn), -nr_pages); - adjust_present_page_count(zone, -nr_pages); + adjust_present_page_count(pfn_to_page(start_pfn), -nr_pages); /* reinitialise watermarks and update pcp limits */ init_per_zone_wmark_min(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 79a2fc5b6c6f..9353418892a7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7240,6 +7240,9 @@ static void __init calculate_node_totalpages(struct pglist_data *pgdat, zone->zone_start_pfn = 0; zone->spanned_pages = size; zone->present_pages = real_size; +#if defined(CONFIG_MEMORY_HOTPLUG) + zone->present_early_pages = real_size; +#endif totalpages += size; realtotalpages += real_size; -- cgit v1.2.3 From e83a437faa625efb2e70924fd3c32ba95610c502 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 7 Sep 2021 19:55:23 -0700 Subject: mm/memory_hotplug: introduce "auto-movable" online policy When onlining without specifying a zone (using "online" instead of "online_kernel" or "online_movable"), we currently select a zone such that existing zones are kept contiguous. This online policy made sense in the past, where contiguous zones where required. We'd like to implement smarter policies, however: * User space has little insight. As one example, it has no idea which memory blocks logically belong together (e.g., to a DIMM or to a virtio-mem device). * Drivers that add memory in separate memory blocks, especially virtio-mem, want memory to get onlined right from the kernel when adding. So we really want to have onlining to differing zones managed in the kernel, configured by user space. We see more and more cases where we might eventually hotplug a lot of memory in the future (e.g., eventually grow a 2 GiB VM to 64 GiB), however: * Resizing happens dynamically, in smaller steps in both directions (e.g., 2 GiB -> 8 GiB -> 4 GiB -> 16 GiB ...) * We still want as much flexibility as possible, especially, hotunplugging as much memory as possible later. We can really only use "online_movable" if we know that the amount of memory we are going to hotplug upfront, and we know that it won't result in a zone imbalance. So in our example, a 2 GiB VM that could grow to 64 GiB could currently not use "online_movable", and instead, "online_kernel" would have to be used, resulting in worse (no) memory hotunplug reliability. Let's add a new "auto-movable" online policy that considers the current zone ratios (global, per-node) to determine, whether we a memory block can be onlined to ZONE_MOVABLE: MOVABLE : KERNEL However, internally we'll only consider the following ratio for now: MOVABLE : KERNEL_EARLY For now, we don't allow for hotplugged KERNEL memory to allow for more MOVABLE memory, because there is no coordination across memory devices. In follow-up patches, we will allow for more KERNEL memory within a memory device to allow for more MOVABLE memory within the same memory device -- which only makes sense for special memory device types. We base our calculation on "present pages", see the code comments for details. Hotplugged memory will get online to ZONE_MOVABLE if the configured ratio allows for it. Depending on the setup, this can result in fragmented zones, which can make compaction slower and dynamic allocation of gigantic pages when not using CMA less reliable (... which is already pretty unreliable). The old policy will be the default and called "contig-zones". In follow-up patches, our new policy will use additional information, such as memory groups, to make even smarter decisions across memory blocks. Configuration: * memory_hotplug.online_policy is used to switch between both polices and defaults to "contig-zones". * memory_hotplug.auto_movable_ratio defines the maximum ratio is in percent and defaults to "301" -- allowing e.g., most 8 GiB machines to grow to 32 GiB and have all hotplugged memory in ZONE_MOVABLE. The additional percent accounts for a handful of lost present pages (e.g., firmware allocations). User space is expected to adjust this ratio when enabling the new "auto-movable" policy, though. * memory_hotplug.auto_movable_numa_aware considers numa node stats in addition to global stats, and defaults to "true". Note: just like the old policy, the new policy won't take things like unmovable huge pages or memory ballooning that doesn't support balloon compaction into account. User space has to configure onlining accordingly. Link: https://lkml.kernel.org/r/20210806124715.17090-3-david@redhat.com Signed-off-by: David Hildenbrand Cc: Anshuman Khandual Cc: Dan Williams Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: Hui Zhu Cc: Jason Wang Cc: Len Brown Cc: Marek Kedzierski Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Oscar Salvador Cc: Pankaj Gupta Cc: Pavel Tatashin Cc: Rafael J. Wysocki Cc: "Rafael J. Wysocki" Cc: Vitaly Kuznetsov Cc: Vlastimil Babka Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 191 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 191 insertions(+) (limited to 'mm') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 8a99fa6d096c..f9d320828067 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -52,6 +52,73 @@ module_param(memmap_on_memory, bool, 0444); MODULE_PARM_DESC(memmap_on_memory, "Enable memmap on memory for memory hotplug"); #endif +enum { + ONLINE_POLICY_CONTIG_ZONES = 0, + ONLINE_POLICY_AUTO_MOVABLE, +}; + +const char *online_policy_to_str[] = { + [ONLINE_POLICY_CONTIG_ZONES] = "contig-zones", + [ONLINE_POLICY_AUTO_MOVABLE] = "auto-movable", +}; + +static int set_online_policy(const char *val, const struct kernel_param *kp) +{ + int ret = sysfs_match_string(online_policy_to_str, val); + + if (ret < 0) + return ret; + *((int *)kp->arg) = ret; + return 0; +} + +static int get_online_policy(char *buffer, const struct kernel_param *kp) +{ + return sprintf(buffer, "%s\n", online_policy_to_str[*((int *)kp->arg)]); +} + +/* + * memory_hotplug.online_policy: configure online behavior when onlining without + * specifying a zone (MMOP_ONLINE) + * + * "contig-zones": keep zone contiguous + * "auto-movable": online memory to ZONE_MOVABLE if the configuration + * (auto_movable_ratio, auto_movable_numa_aware) allows for it + */ +static int online_policy __read_mostly = ONLINE_POLICY_CONTIG_ZONES; +static const struct kernel_param_ops online_policy_ops = { + .set = set_online_policy, + .get = get_online_policy, +}; +module_param_cb(online_policy, &online_policy_ops, &online_policy, 0644); +MODULE_PARM_DESC(online_policy, + "Set the online policy (\"contig-zones\", \"auto-movable\") " + "Default: \"contig-zones\""); + +/* + * memory_hotplug.auto_movable_ratio: specify maximum MOVABLE:KERNEL ratio + * + * The ratio represent an upper limit and the kernel might decide to not + * online some memory to ZONE_MOVABLE -- e.g., because hotplugged KERNEL memory + * doesn't allow for more MOVABLE memory. + */ +static unsigned int auto_movable_ratio __read_mostly = 301; +module_param(auto_movable_ratio, uint, 0644); +MODULE_PARM_DESC(auto_movable_ratio, + "Set the maximum ratio of MOVABLE:KERNEL memory in the system " + "in percent for \"auto-movable\" online policy. Default: 301"); + +/* + * memory_hotplug.auto_movable_numa_aware: consider numa node stats + */ +#ifdef CONFIG_NUMA +static bool auto_movable_numa_aware __read_mostly = true; +module_param(auto_movable_numa_aware, bool, 0644); +MODULE_PARM_DESC(auto_movable_numa_aware, + "Consider numa node stats in addition to global stats in " + "\"auto-movable\" online policy. Default: true"); +#endif /* CONFIG_NUMA */ + /* * online_page_callback contains pointer to current page onlining function. * Initially it is generic_online_page(). If it is required it could be @@ -663,6 +730,61 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, set_zone_contiguous(zone); } +struct auto_movable_stats { + unsigned long kernel_early_pages; + unsigned long movable_pages; +}; + +static void auto_movable_stats_account_zone(struct auto_movable_stats *stats, + struct zone *zone) +{ + if (zone_idx(zone) == ZONE_MOVABLE) { + stats->movable_pages += zone->present_pages; + } else { + stats->kernel_early_pages += zone->present_early_pages; +#ifdef CONFIG_CMA + /* + * CMA pages (never on hotplugged memory) behave like + * ZONE_MOVABLE. + */ + stats->movable_pages += zone->cma_pages; + stats->kernel_early_pages -= zone->cma_pages; +#endif /* CONFIG_CMA */ + } +} + +static bool auto_movable_can_online_movable(int nid, unsigned long nr_pages) +{ + struct auto_movable_stats stats = {}; + unsigned long kernel_early_pages, movable_pages; + pg_data_t *pgdat = NODE_DATA(nid); + struct zone *zone; + int i; + + /* Walk all relevant zones and collect MOVABLE vs. KERNEL stats. */ + if (nid == NUMA_NO_NODE) { + /* TODO: cache values */ + for_each_populated_zone(zone) + auto_movable_stats_account_zone(&stats, zone); + } else { + for (i = 0; i < MAX_NR_ZONES; i++) { + zone = pgdat->node_zones + i; + if (populated_zone(zone)) + auto_movable_stats_account_zone(&stats, zone); + } + } + + kernel_early_pages = stats.kernel_early_pages; + movable_pages = stats.movable_pages; + + /* + * Test if we could online the given number of pages to ZONE_MOVABLE + * and still stay in the configured ratio. + */ + movable_pages += nr_pages; + return movable_pages <= (auto_movable_ratio * kernel_early_pages) / 100; +} + /* * Returns a default kernel memory zone for the given pfn range. * If no kernel zone covers this pfn range it will automatically go @@ -684,6 +806,72 @@ static struct zone *default_kernel_zone_for_pfn(int nid, unsigned long start_pfn return &pgdat->node_zones[ZONE_NORMAL]; } +/* + * Determine to which zone to online memory dynamically based on user + * configuration and system stats. We care about the following ratio: + * + * MOVABLE : KERNEL + * + * Whereby MOVABLE is memory in ZONE_MOVABLE and KERNEL is memory in + * one of the kernel zones. CMA pages inside one of the kernel zones really + * behaves like ZONE_MOVABLE, so we treat them accordingly. + * + * We don't allow for hotplugged memory in a KERNEL zone to increase the + * amount of MOVABLE memory we can have, so we end up with: + * + * MOVABLE : KERNEL_EARLY + * + * Whereby KERNEL_EARLY is memory in one of the kernel zones, available sinze + * boot. We base our calculation on KERNEL_EARLY internally, because: + * + * a) Hotplugged memory in one of the kernel zones can sometimes still get + * hotunplugged, especially when hot(un)plugging individual memory blocks. + * There is no coordination across memory devices, therefore "automatic" + * hotunplugging, as implemented in hypervisors, could result in zone + * imbalances. + * b) Early/boot memory in one of the kernel zones can usually not get + * hotunplugged again (e.g., no firmware interface to unplug, fragmented + * with unmovable allocations). While there are corner cases where it might + * still work, it is barely relevant in practice. + * + * We rely on "present pages" instead of "managed pages", as the latter is + * highly unreliable and dynamic in virtualized environments, and does not + * consider boot time allocations. For example, memory ballooning adjusts the + * managed pages when inflating/deflating the balloon, and balloon compaction + * can even migrate inflated pages between zones. + * + * Using "present pages" is better but some things to keep in mind are: + * + * a) Some memblock allocations, such as for the crashkernel area, are + * effectively unused by the kernel, yet they account to "present pages". + * Fortunately, these allocations are comparatively small in relevant setups + * (e.g., fraction of system memory). + * b) Some hotplugged memory blocks in virtualized environments, esecially + * hotplugged by virtio-mem, look like they are completely present, however, + * only parts of the memory block are actually currently usable. + * "present pages" is an upper limit that can get reached at runtime. As + * we base our calculations on KERNEL_EARLY, this is not an issue. + */ +static struct zone *auto_movable_zone_for_pfn(int nid, unsigned long pfn, + unsigned long nr_pages) +{ + if (!auto_movable_ratio) + goto kernel_zone; + + if (!auto_movable_can_online_movable(NUMA_NO_NODE, nr_pages)) + goto kernel_zone; + +#ifdef CONFIG_NUMA + if (auto_movable_numa_aware && + !auto_movable_can_online_movable(nid, nr_pages)) + goto kernel_zone; +#endif /* CONFIG_NUMA */ + + return &NODE_DATA(nid)->node_zones[ZONE_MOVABLE]; +kernel_zone: + return default_kernel_zone_for_pfn(nid, pfn, nr_pages); +} + static inline struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn, unsigned long nr_pages) { @@ -717,6 +905,9 @@ struct zone *zone_for_pfn_range(int online_type, int nid, if (online_type == MMOP_ONLINE_MOVABLE) return &NODE_DATA(nid)->node_zones[ZONE_MOVABLE]; + if (online_policy == ONLINE_POLICY_AUTO_MOVABLE) + return auto_movable_zone_for_pfn(nid, start_pfn, nr_pages); + return default_zone_for_pfn(nid, start_pfn, nr_pages); } -- cgit v1.2.3 From 028fc57a1c361116e3bcebfeba4ca87878baaf4f Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 7 Sep 2021 19:55:26 -0700 Subject: drivers/base/memory: introduce "memory groups" to logically group memory blocks In our "auto-movable" memory onlining policy, we want to make decisions across memory blocks of a single memory device. Examples of memory devices include ACPI memory devices (in the simplest case a single DIMM) and virtio-mem. For now, we don't have a connection between a single memory block device and the real memory device. Each memory device consists of 1..X memory block devices. Let's logically group memory blocks belonging to the same memory device in "memory groups". Memory groups can span multiple physical ranges and a memory group itself does not contain any information regarding physical ranges, only properties (e.g., "max_pages") necessary for improved memory onlining. Introduce two memory group types: 1) Static memory group: E.g., a single ACPI memory device, consisting of 1..X memory resources. A memory group consists of 1..Y memory blocks. The whole group is added/removed in one go. If any part cannot get offlined, the whole group cannot be removed. 2) Dynamic memory group: E.g., a single virtio-mem device. Memory is dynamically added/removed in a fixed granularity, called a "unit", consisting of 1..X memory blocks. A unit is added/removed in one go. If any part of a unit cannot get offlined, the whole unit cannot be removed. In case of 1) we usually want either all memory managed by ZONE_MOVABLE or none. In case of 2) we usually want to have as many units as possible managed by ZONE_MOVABLE. We want a single unit to be of the same type. For now, memory groups are an internal concept that is not exposed to user space; we might want to change that in the future, though. add_memory() users can specify a mgid instead of a nid when passing the MHP_NID_IS_MGID flag. Link: https://lkml.kernel.org/r/20210806124715.17090-4-david@redhat.com Signed-off-by: David Hildenbrand Cc: Anshuman Khandual Cc: Dan Williams Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: Hui Zhu Cc: Jason Wang Cc: Len Brown Cc: Marek Kedzierski Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Oscar Salvador Cc: Pankaj Gupta Cc: Pavel Tatashin Cc: Rafael J. Wysocki Cc: "Rafael J. Wysocki" Cc: Vitaly Kuznetsov Cc: Vlastimil Babka Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/memory.c | 159 +++++++++++++++++++++++++++++++++++++++-- include/linux/memory.h | 46 +++++++++++- include/linux/memory_hotplug.h | 5 ++ mm/memory_hotplug.c | 11 ++- 4 files changed, 215 insertions(+), 6 deletions(-) (limited to 'mm') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 86ec2dc82fc2..16f5a3610229 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -82,6 +82,11 @@ static struct bus_type memory_subsys = { */ static DEFINE_XARRAY(memory_blocks); +/* + * Memory groups, indexed by memory group id (mgid). + */ +static DEFINE_XARRAY_FLAGS(memory_groups, XA_FLAGS_ALLOC); + static BLOCKING_NOTIFIER_HEAD(memory_chain); int register_memory_notifier(struct notifier_block *nb) @@ -634,7 +639,8 @@ int register_memory(struct memory_block *memory) } static int init_memory_block(unsigned long block_id, unsigned long state, - unsigned long nr_vmemmap_pages) + unsigned long nr_vmemmap_pages, + struct memory_group *group) { struct memory_block *mem; int ret = 0; @@ -652,6 +658,12 @@ static int init_memory_block(unsigned long block_id, unsigned long state, mem->state = state; mem->nid = NUMA_NO_NODE; mem->nr_vmemmap_pages = nr_vmemmap_pages; + INIT_LIST_HEAD(&mem->group_next); + + if (group) { + mem->group = group; + list_add(&mem->group_next, &group->memory_blocks); + } ret = register_memory(mem); @@ -671,7 +683,7 @@ 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, 0); + MEM_ONLINE, 0, NULL); } static void unregister_memory(struct memory_block *memory) @@ -681,6 +693,11 @@ static void unregister_memory(struct memory_block *memory) WARN_ON(xa_erase(&memory_blocks, memory->dev.id) == NULL); + if (memory->group) { + list_del(&memory->group_next); + memory->group = NULL; + } + /* drop the ref. we got via find_memory_block() */ put_device(&memory->dev); device_unregister(&memory->dev); @@ -694,7 +711,8 @@ static void unregister_memory(struct memory_block *memory) * Called under device_hotplug_lock. */ int create_memory_block_devices(unsigned long start, unsigned long size, - unsigned long vmemmap_pages) + unsigned long vmemmap_pages, + struct memory_group *group) { 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)); @@ -707,7 +725,8 @@ 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, vmemmap_pages); + ret = init_memory_block(block_id, MEM_OFFLINE, vmemmap_pages, + group); if (ret) break; } @@ -891,3 +910,135 @@ int for_each_memory_block(void *arg, walk_memory_blocks_func_t func) return bus_for_each_dev(&memory_subsys, NULL, &cb_data, for_each_memory_block_cb); } + +/* + * This is an internal helper to unify allocation and initialization of + * memory groups. Note that the passed memory group will be copied to a + * dynamically allocated memory group. After this call, the passed + * memory group should no longer be used. + */ +static int memory_group_register(struct memory_group group) +{ + struct memory_group *new_group; + uint32_t mgid; + int ret; + + if (!node_possible(group.nid)) + return -EINVAL; + + new_group = kzalloc(sizeof(group), GFP_KERNEL); + if (!new_group) + return -ENOMEM; + *new_group = group; + INIT_LIST_HEAD(&new_group->memory_blocks); + + ret = xa_alloc(&memory_groups, &mgid, new_group, xa_limit_31b, + GFP_KERNEL); + if (ret) { + kfree(new_group); + return ret; + } + return mgid; +} + +/** + * memory_group_register_static() - Register a static memory group. + * @nid: The node id. + * @max_pages: The maximum number of pages we'll have in this static memory + * group. + * + * Register a new static memory group and return the memory group id. + * All memory in the group belongs to a single unit, such as a DIMM. All + * memory belonging to a static memory group is added in one go to be removed + * in one go -- it's static. + * + * Returns an error if out of memory, if the node id is invalid, if no new + * memory groups can be registered, or if max_pages is invalid (0). Otherwise, + * returns the new memory group id. + */ +int memory_group_register_static(int nid, unsigned long max_pages) +{ + struct memory_group group = { + .nid = nid, + .s = { + .max_pages = max_pages, + }, + }; + + if (!max_pages) + return -EINVAL; + return memory_group_register(group); +} +EXPORT_SYMBOL_GPL(memory_group_register_static); + +/** + * memory_group_register_dynamic() - Register a dynamic memory group. + * @nid: The node id. + * @unit_pages: Unit in pages in which is memory added/removed in this dynamic + * memory group. + * + * Register a new dynamic memory group and return the memory group id. + * Memory within a dynamic memory group is added/removed dynamically + * in unit_pages. + * + * Returns an error if out of memory, if the node id is invalid, if no new + * memory groups can be registered, or if unit_pages is invalid (0, not a + * power of two, smaller than a single memory block). Otherwise, returns the + * new memory group id. + */ +int memory_group_register_dynamic(int nid, unsigned long unit_pages) +{ + struct memory_group group = { + .nid = nid, + .is_dynamic = true, + .d = { + .unit_pages = unit_pages, + }, + }; + + if (!unit_pages || !is_power_of_2(unit_pages) || + unit_pages < PHYS_PFN(memory_block_size_bytes())) + return -EINVAL; + return memory_group_register(group); +} +EXPORT_SYMBOL_GPL(memory_group_register_dynamic); + +/** + * memory_group_unregister() - Unregister a memory group. + * @mgid: the memory group id + * + * Unregister a memory group. If any memory block still belongs to this + * memory group, unregistering will fail. + * + * Returns -EINVAL if the memory group id is invalid, returns -EBUSY if some + * memory blocks still belong to this memory group and returns 0 if + * unregistering succeeded. + */ +int memory_group_unregister(int mgid) +{ + struct memory_group *group; + + if (mgid < 0) + return -EINVAL; + + group = xa_load(&memory_groups, mgid); + if (!group) + return -EINVAL; + if (!list_empty(&group->memory_blocks)) + return -EBUSY; + xa_erase(&memory_groups, mgid); + kfree(group); + return 0; +} +EXPORT_SYMBOL_GPL(memory_group_unregister); + +/* + * This is an internal helper only to be used in core memory hotplug code to + * lookup a memory group. We don't care about locking, as we don't expect a + * memory group to get unregistered while adding memory to it -- because + * the group and the memory is managed by the same driver. + */ +struct memory_group *memory_group_find_by_id(int mgid) +{ + return xa_load(&memory_groups, mgid); +} diff --git a/include/linux/memory.h b/include/linux/memory.h index 97e92e8b556a..d505c12c5c77 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -23,6 +23,42 @@ #define MIN_MEMORY_BLOCK_SIZE (1UL << SECTION_SIZE_BITS) +/** + * struct memory_group - a logical group of memory blocks + * @nid: The node id for all memory blocks inside the memory group. + * @blocks: List of all memory blocks belonging to this memory group. + * @is_dynamic: The memory group type: static vs. dynamic + * @s.max_pages: Valid with &memory_group.is_dynamic == false. The maximum + * number of pages we'll have in this static memory group. + * @d.unit_pages: Valid with &memory_group.is_dynamic == true. Unit in pages + * in which memory is added/removed in this dynamic memory group. + * This granularity defines the alignment of a unit in physical + * address space; it has to be at least as big as a single + * memory block. + * + * A memory group logically groups memory blocks; each memory block + * belongs to at most one memory group. A memory group corresponds to + * a memory device, such as a DIMM or a NUMA node, which spans multiple + * memory blocks and might even span multiple non-contiguous physical memory + * ranges. + * + * Modification of members after registration is serialized by memory + * hot(un)plug code. + */ +struct memory_group { + int nid; + struct list_head memory_blocks; + bool is_dynamic; + union { + struct { + unsigned long max_pages; + } s; + struct { + unsigned long unit_pages; + } d; + }; +}; + struct memory_block { unsigned long start_section_nr; unsigned long state; /* serialized by the dev->lock */ @@ -34,6 +70,8 @@ struct memory_block { * lay at the beginning of the memory block. */ unsigned long nr_vmemmap_pages; + struct memory_group *group; /* group (if any) for this block */ + struct list_head group_next; /* next block inside memory group */ }; int arch_get_memory_phys_device(unsigned long start_pfn); @@ -86,7 +124,8 @@ static inline int memory_notify(unsigned long val, void *v) 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, - unsigned long vmemmap_pages); + unsigned long vmemmap_pages, + struct memory_group *group); 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); @@ -96,6 +135,11 @@ extern int walk_memory_blocks(unsigned long start, unsigned long size, void *arg, walk_memory_blocks_func_t func); extern int for_each_memory_block(void *arg, walk_memory_blocks_func_t func); #define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION<nid; + } + if (!node_possible(nid)) { WARN(1, "node %d was absent from the node_possible_map\n", nid); return -EINVAL; @@ -1303,7 +1311,8 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) goto error; /* create memory block devices after memory was added */ - ret = create_memory_block_devices(start, size, mhp_altmap.alloc); + ret = create_memory_block_devices(start, size, mhp_altmap.alloc, + group); if (ret) { arch_remove_memory(start, size, NULL); goto error; -- cgit v1.2.3 From 836809ec75cc07c6d07c43036e3844affbe0d46f Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 7 Sep 2021 19:55:30 -0700 Subject: mm/memory_hotplug: track present pages in memory groups Let's track all present pages in each memory group. Especially, track memory present in ZONE_MOVABLE and memory present in one of the kernel zones (which really only is ZONE_NORMAL right now as memory groups only apply to hotplugged memory) separately within a memory group, to prepare for making smart auto-online decision for individual memory blocks within a memory group based on group statistics. Link: https://lkml.kernel.org/r/20210806124715.17090-5-david@redhat.com Signed-off-by: David Hildenbrand Cc: Anshuman Khandual Cc: Dan Williams Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: Hui Zhu Cc: Jason Wang Cc: Len Brown Cc: Marek Kedzierski Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Oscar Salvador Cc: Pankaj Gupta Cc: Pavel Tatashin Cc: Rafael J. Wysocki Cc: "Rafael J. Wysocki" Cc: Vitaly Kuznetsov Cc: Vlastimil Babka Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/memory.c | 10 +++++----- include/linux/memory.h | 6 ++++++ include/linux/memory_hotplug.h | 13 +++++++++---- mm/memory_hotplug.c | 19 ++++++++++++++----- 4 files changed, 34 insertions(+), 14 deletions(-) (limited to 'mm') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 16f5a3610229..a1082013e10c 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -198,7 +198,7 @@ static int memory_block_online(struct memory_block *mem) } ret = online_pages(start_pfn + nr_vmemmap_pages, - nr_pages - nr_vmemmap_pages, zone); + nr_pages - nr_vmemmap_pages, zone, mem->group); if (ret) { if (nr_vmemmap_pages) mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); @@ -210,7 +210,7 @@ static int memory_block_online(struct memory_block *mem) * now already properly populated. */ if (nr_vmemmap_pages) - adjust_present_page_count(pfn_to_page(start_pfn), + adjust_present_page_count(pfn_to_page(start_pfn), mem->group, nr_vmemmap_pages); return ret; @@ -228,16 +228,16 @@ static int memory_block_offline(struct memory_block *mem) * can properly be torn down in offline_pages(). */ if (nr_vmemmap_pages) - adjust_present_page_count(pfn_to_page(start_pfn), + adjust_present_page_count(pfn_to_page(start_pfn), mem->group, -nr_vmemmap_pages); ret = offline_pages(start_pfn + nr_vmemmap_pages, - nr_pages - nr_vmemmap_pages); + nr_pages - nr_vmemmap_pages, mem->group); if (ret) { /* offline_pages() failed. Account back. */ if (nr_vmemmap_pages) adjust_present_page_count(pfn_to_page(start_pfn), - nr_vmemmap_pages); + mem->group, nr_vmemmap_pages); return ret; } diff --git a/include/linux/memory.h b/include/linux/memory.h index d505c12c5c77..6ffdc1db385f 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -27,6 +27,10 @@ * struct memory_group - a logical group of memory blocks * @nid: The node id for all memory blocks inside the memory group. * @blocks: List of all memory blocks belonging to this memory group. + * @present_kernel_pages: Present (online) memory outside ZONE_MOVABLE of this + * memory group. + * @present_movable_pages: Present (online) memory in ZONE_MOVABLE of this + * memory group. * @is_dynamic: The memory group type: static vs. dynamic * @s.max_pages: Valid with &memory_group.is_dynamic == false. The maximum * number of pages we'll have in this static memory group. @@ -48,6 +52,8 @@ struct memory_group { int nid; struct list_head memory_blocks; + unsigned long present_kernel_pages; + unsigned long present_movable_pages; bool is_dynamic; union { struct { diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 5d341978b4bc..cf3f423c8a74 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -12,6 +12,7 @@ struct zone; struct pglist_data; struct mem_section; struct memory_block; +struct memory_group; struct resource; struct vmem_altmap; @@ -100,13 +101,15 @@ 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 page *page, long nr_pages); +extern void adjust_present_page_count(struct page *page, + struct memory_group *group, + 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, - struct zone *zone); + struct zone *zone, struct memory_group *group); 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, @@ -296,7 +299,8 @@ static inline void pgdat_resize_init(struct pglist_data *pgdat) {} #ifdef CONFIG_MEMORY_HOTREMOVE extern void try_offline_node(int nid); -extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); +extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages, + struct memory_group *group); extern int remove_memory(u64 start, u64 size); extern void __remove_memory(u64 start, u64 size); extern int offline_and_remove_memory(u64 start, u64 size); @@ -304,7 +308,8 @@ extern int offline_and_remove_memory(u64 start, u64 size); #else static inline void try_offline_node(int nid) {} -static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages) +static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages, + struct memory_group *group) { return -EINVAL; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index fd57a296dd27..8199a4f98b2b 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -915,9 +915,11 @@ struct zone *zone_for_pfn_range(int online_type, int nid, * This function should only be called by memory_block_{online,offline}, * and {online,offline}_pages. */ -void adjust_present_page_count(struct page *page, long nr_pages) +void adjust_present_page_count(struct page *page, struct memory_group *group, + long nr_pages) { struct zone *zone = page_zone(page); + const bool movable = zone_idx(zone) == ZONE_MOVABLE; /* * We only support onlining/offlining/adding/removing of complete @@ -927,6 +929,11 @@ void adjust_present_page_count(struct page *page, long nr_pages) zone->present_early_pages += nr_pages; zone->present_pages += nr_pages; zone->zone_pgdat->node_present_pages += nr_pages; + + if (group && movable) + group->present_movable_pages += nr_pages; + else if (group && !movable) + group->present_kernel_pages += nr_pages; } int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, @@ -972,7 +979,8 @@ void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long 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) +int __ref online_pages(unsigned long pfn, unsigned long nr_pages, + struct zone *zone, struct memory_group *group) { unsigned long flags; int need_zonelists_rebuild = 0; @@ -1025,7 +1033,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *z } online_pages_range(pfn, nr_pages); - adjust_present_page_count(pfn_to_page(pfn), nr_pages); + adjust_present_page_count(pfn_to_page(pfn), group, nr_pages); node_states_set_node(nid, &arg); if (need_zonelists_rebuild) @@ -1769,7 +1777,8 @@ static int count_system_ram_pages_cb(unsigned long start_pfn, return 0; } -int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages) +int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, + struct memory_group *group) { const unsigned long end_pfn = start_pfn + nr_pages; unsigned long pfn, system_ram_pages = 0; @@ -1905,7 +1914,7 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages) /* removal success */ adjust_managed_page_count(pfn_to_page(start_pfn), -nr_pages); - adjust_present_page_count(pfn_to_page(start_pfn), -nr_pages); + adjust_present_page_count(pfn_to_page(start_pfn), group, -nr_pages); /* reinitialise watermarks and update pcp limits */ init_per_zone_wmark_min(); -- cgit v1.2.3 From 445fcf7c721450dd1d4ec6c217b3c6a932602a44 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 7 Sep 2021 19:55:45 -0700 Subject: mm/memory_hotplug: memory group aware "auto-movable" online policy Use memory groups to improve our "auto-movable" onlining policy: 1. For static memory groups (e.g., a DIMM), online a memory block MOVABLE only if all other memory blocks in the group are either MOVABLE or could be onlined MOVABLE. A DIMM will either be MOVABLE or not, not a mixture. 2. For dynamic memory groups (e.g., a virtio-mem device), online a memory block MOVABLE only if all other memory blocks inside the current unit are either MOVABLE or could be onlined MOVABLE. For a virtio-mem device with a device block size with 512 MiB, all 128 MiB memory blocks wihin a 512 MiB unit will either be MOVABLE or not, not a mixture. We have to pass the memory group to zone_for_pfn_range() to take the memory group into account. Note: for now, there seems to be no compelling reason to make this behavior configurable. Link: https://lkml.kernel.org/r/20210806124715.17090-9-david@redhat.com Signed-off-by: David Hildenbrand Cc: Anshuman Khandual Cc: Dan Williams Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: Hui Zhu Cc: Jason Wang Cc: Len Brown Cc: Marek Kedzierski Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Oscar Salvador Cc: Pankaj Gupta Cc: Pavel Tatashin Cc: Rafael J. Wysocki Cc: "Rafael J. Wysocki" Cc: Vitaly Kuznetsov Cc: Vlastimil Babka Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/memory.c | 18 +++++++++------- include/linux/memory_hotplug.h | 3 ++- mm/memory_hotplug.c | 48 +++++++++++++++++++++++++++++++++++++++--- 3 files changed, 57 insertions(+), 12 deletions(-) (limited to 'mm') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index a1082013e10c..b699ddc42693 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -182,7 +182,8 @@ static int memory_block_online(struct memory_block *mem) struct zone *zone; int ret; - zone = zone_for_pfn_range(mem->online_type, mem->nid, start_pfn, nr_pages); + zone = zone_for_pfn_range(mem->online_type, mem->nid, mem->group, + start_pfn, nr_pages); /* * Although vmemmap pages have a different lifecycle than the pages @@ -379,12 +380,13 @@ static ssize_t phys_device_show(struct device *dev, #ifdef CONFIG_MEMORY_HOTREMOVE static int print_allowed_zone(char *buf, int len, int nid, + struct memory_group *group, unsigned long start_pfn, unsigned long nr_pages, int online_type, struct zone *default_zone) { struct zone *zone; - zone = zone_for_pfn_range(online_type, nid, start_pfn, nr_pages); + zone = zone_for_pfn_range(online_type, nid, group, start_pfn, nr_pages); if (zone == default_zone) return 0; @@ -397,9 +399,10 @@ static ssize_t valid_zones_show(struct device *dev, struct memory_block *mem = to_memory_block(dev); unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; + struct memory_group *group = mem->group; struct zone *default_zone; + int nid = mem->nid; int len = 0; - int nid; /* * Check the existing zone. Make sure that we do that only on the @@ -418,14 +421,13 @@ static ssize_t valid_zones_show(struct device *dev, goto out; } - nid = mem->nid; - default_zone = zone_for_pfn_range(MMOP_ONLINE, nid, start_pfn, - nr_pages); + default_zone = zone_for_pfn_range(MMOP_ONLINE, nid, group, + start_pfn, nr_pages); len += sysfs_emit_at(buf, len, "%s", default_zone->name); - len += print_allowed_zone(buf, len, nid, start_pfn, nr_pages, + len += print_allowed_zone(buf, len, nid, group, start_pfn, nr_pages, MMOP_ONLINE_KERNEL, default_zone); - len += print_allowed_zone(buf, len, nid, start_pfn, nr_pages, + len += print_allowed_zone(buf, len, nid, group, start_pfn, nr_pages, MMOP_ONLINE_MOVABLE, default_zone); out: len += sysfs_emit_at(buf, len, "\n"); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index cf3f423c8a74..e5a867c950b2 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -349,7 +349,8 @@ extern void sparse_remove_section(struct mem_section *ms, extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); extern struct zone *zone_for_pfn_range(int online_type, int nid, - unsigned long start_pfn, unsigned long nr_pages); + struct memory_group *group, unsigned long start_pfn, + unsigned long nr_pages); 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); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 8199a4f98b2b..248e2ba4ac59 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -852,12 +852,53 @@ static struct zone *default_kernel_zone_for_pfn(int nid, unsigned long start_pfn * "present pages" is an upper limit that can get reached at runtime. As * we base our calculations on KERNEL_EARLY, this is not an issue. */ -static struct zone *auto_movable_zone_for_pfn(int nid, unsigned long pfn, +static struct zone *auto_movable_zone_for_pfn(int nid, + struct memory_group *group, + unsigned long pfn, unsigned long nr_pages) { + unsigned long online_pages = 0, max_pages, end_pfn; + struct page *page; + if (!auto_movable_ratio) goto kernel_zone; + if (group && !group->is_dynamic) { + max_pages = group->s.max_pages; + online_pages = group->present_movable_pages; + + /* If anything is !MOVABLE online the rest !MOVABLE. */ + if (group->present_kernel_pages) + goto kernel_zone; + } else if (!group || group->d.unit_pages == nr_pages) { + max_pages = nr_pages; + } else { + max_pages = group->d.unit_pages; + /* + * Take a look at all online sections in the current unit. + * We can safely assume that all pages within a section belong + * to the same zone, because dynamic memory groups only deal + * with hotplugged memory. + */ + pfn = ALIGN_DOWN(pfn, group->d.unit_pages); + end_pfn = pfn + group->d.unit_pages; + for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) { + page = pfn_to_online_page(pfn); + if (!page) + continue; + /* If anything is !MOVABLE online the rest !MOVABLE. */ + if (page_zonenum(page) != ZONE_MOVABLE) + goto kernel_zone; + online_pages += PAGES_PER_SECTION; + } + } + + /* + * Online MOVABLE if we could *currently* online all remaining parts + * MOVABLE. We expect to (add+) online them immediately next, so if + * nobody interferes, all will be MOVABLE if possible. + */ + nr_pages = max_pages - online_pages; if (!auto_movable_can_online_movable(NUMA_NO_NODE, nr_pages)) goto kernel_zone; @@ -897,7 +938,8 @@ static inline struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn } struct zone *zone_for_pfn_range(int online_type, int nid, - unsigned long start_pfn, unsigned long nr_pages) + struct memory_group *group, unsigned long start_pfn, + unsigned long nr_pages) { if (online_type == MMOP_ONLINE_KERNEL) return default_kernel_zone_for_pfn(nid, start_pfn, nr_pages); @@ -906,7 +948,7 @@ struct zone *zone_for_pfn_range(int online_type, int nid, return &NODE_DATA(nid)->node_zones[ZONE_MOVABLE]; if (online_policy == ONLINE_POLICY_AUTO_MOVABLE) - return auto_movable_zone_for_pfn(nid, start_pfn, nr_pages); + return auto_movable_zone_for_pfn(nid, group, start_pfn, nr_pages); return default_zone_for_pfn(nid, start_pfn, nr_pages); } -- cgit v1.2.3 From 3fcebf90209a7f52d384ad7701425aa91be309ab Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 7 Sep 2021 19:55:48 -0700 Subject: mm/memory_hotplug: improved dynamic memory group aware "auto-movable" online policy Currently, the "auto-movable" online policy does not allow for hotplugged KERNEL (ZONE_NORMAL) memory to increase the amount of MOVABLE memory we can have, primarily, because there is no coordiantion across memory devices and we don't want to create zone-imbalances accidentially when unplugging memory. However, within a single memory device it's different. Let's allow for KERNEL memory within a dynamic memory group to allow for more MOVABLE within the same memory group. The only thing we have to take care of is that the managing driver avoids zone imbalances by unplugging MOVABLE memory first, otherwise there can be corner cases where unplug of memory could result in (accidential) zone imbalances. virtio-mem is the only user of dynamic memory groups and recently added support for prioritizing unplug of ZONE_MOVABLE over ZONE_NORMAL, so we don't need a new toggle to enable it for dynamic memory groups. We limit this handling to dynamic memory groups, because: * We want to keep the runtime overhead for collecting stats when onlining a single memory block small. We tend to have only a handful of dynamic memory groups, but we can have quite some static memory groups (e.g., 256 DIMMs). * It doesn't make too much sense for static memory groups, as we try onlining all applicable memory blocks either completely to ZONE_MOVABLE or not. In ordinary operation, we won't have a mixture of zones within a static memory group. When adding memory to a dynamic memory group, we'll first online memory to ZONE_MOVABLE as long as early KERNEL memory allows for it. Then, we'll online the next unit(s) to ZONE_NORMAL, until we can online the next unit(s) to ZONE_MOVABLE. For a simple virtio-mem device with a MOVABLE:KERNEL ratio of 3:1, it will result in a layout like: [M][M][M][M][M][M][M][M][N][M][M][M][N][M][M][M]... ^ movable memory due to early kernel memory ^ allows for more movable memory ... ^-----^ ... here ^ allows for more movable memory ... ^-----^ ... here While the created layout is sub-optimal when it comes to contiguous zones, it gives us the maximum flexibility when dynamically growing/shrinking a device; we can grow small VMs really big in small steps, and still shrink reliably to e.g., 1/4 of the maximum VM size in this example, removing full memory blocks along with meta data more reliably. Mark dynamic memory groups in the xarray such that we can efficiently iterate over them when collecting stats. In usual setups, we have one virtio-mem device per NUMA node, and usually only a small number of NUMA nodes. Note: for now, there seems to be no compelling reason to make this behavior configurable. Link: https://lkml.kernel.org/r/20210806124715.17090-10-david@redhat.com Signed-off-by: David Hildenbrand Cc: Anshuman Khandual Cc: Dan Williams Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: Hui Zhu Cc: Jason Wang Cc: Len Brown Cc: Marek Kedzierski Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Oscar Salvador Cc: Pankaj Gupta Cc: Pavel Tatashin Cc: Rafael J. Wysocki Cc: "Rafael J. Wysocki" Cc: Vitaly Kuznetsov Cc: Vlastimil Babka Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/memory.c | 30 +++++++++++++++++++++++++ include/linux/memory.h | 3 +++ mm/memory_hotplug.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++---- 3 files changed, 89 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index b699ddc42693..440fd656c002 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -86,6 +86,7 @@ static DEFINE_XARRAY(memory_blocks); * Memory groups, indexed by memory group id (mgid). */ static DEFINE_XARRAY_FLAGS(memory_groups, XA_FLAGS_ALLOC); +#define MEMORY_GROUP_MARK_DYNAMIC XA_MARK_1 static BLOCKING_NOTIFIER_HEAD(memory_chain); @@ -939,6 +940,8 @@ static int memory_group_register(struct memory_group group) if (ret) { kfree(new_group); return ret; + } else if (group.is_dynamic) { + xa_set_mark(&memory_groups, mgid, MEMORY_GROUP_MARK_DYNAMIC); } return mgid; } @@ -1044,3 +1047,30 @@ struct memory_group *memory_group_find_by_id(int mgid) { return xa_load(&memory_groups, mgid); } + +/* + * This is an internal helper only to be used in core memory hotplug code to + * walk all dynamic memory groups excluding a given memory group, either + * belonging to a specific node, or belonging to any node. + */ +int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, + struct memory_group *excluded, void *arg) +{ + struct memory_group *group; + unsigned long index; + int ret = 0; + + xa_for_each_marked(&memory_groups, index, group, + MEMORY_GROUP_MARK_DYNAMIC) { + if (group == excluded) + continue; +#ifdef CONFIG_NUMA + if (nid != NUMA_NO_NODE && group->nid != nid) + continue; +#endif /* CONFIG_NUMA */ + ret = func(group, arg); + if (ret) + break; + } + return ret; +} diff --git a/include/linux/memory.h b/include/linux/memory.h index 6ffdc1db385f..cbcc43ad2b97 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -146,6 +146,9 @@ extern int memory_group_register_static(int nid, unsigned long max_pages); extern int memory_group_register_dynamic(int nid, unsigned long unit_pages); extern int memory_group_unregister(int mgid); struct memory_group *memory_group_find_by_id(int mgid); +typedef int (*walk_memory_groups_func_t)(struct memory_group *, void *); +int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, + struct memory_group *excluded, void *arg); #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ #ifdef CONFIG_MEMORY_HOTPLUG diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 248e2ba4ac59..b80fb8164fb8 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -752,11 +752,44 @@ static void auto_movable_stats_account_zone(struct auto_movable_stats *stats, #endif /* CONFIG_CMA */ } } +struct auto_movable_group_stats { + unsigned long movable_pages; + unsigned long req_kernel_early_pages; +}; -static bool auto_movable_can_online_movable(int nid, unsigned long nr_pages) +static int auto_movable_stats_account_group(struct memory_group *group, + void *arg) +{ + const int ratio = READ_ONCE(auto_movable_ratio); + struct auto_movable_group_stats *stats = arg; + long pages; + + /* + * We don't support modifying the config while the auto-movable online + * policy is already enabled. Just avoid the division by zero below. + */ + if (!ratio) + return 0; + + /* + * Calculate how many early kernel pages this group requires to + * satisfy the configured zone ratio. + */ + pages = group->present_movable_pages * 100 / ratio; + pages -= group->present_kernel_pages; + + if (pages > 0) + stats->req_kernel_early_pages += pages; + stats->movable_pages += group->present_movable_pages; + return 0; +} + +static bool auto_movable_can_online_movable(int nid, struct memory_group *group, + unsigned long nr_pages) { - struct auto_movable_stats stats = {}; unsigned long kernel_early_pages, movable_pages; + struct auto_movable_group_stats group_stats = {}; + struct auto_movable_stats stats = {}; pg_data_t *pgdat = NODE_DATA(nid); struct zone *zone; int i; @@ -777,6 +810,21 @@ static bool auto_movable_can_online_movable(int nid, unsigned long nr_pages) kernel_early_pages = stats.kernel_early_pages; movable_pages = stats.movable_pages; + /* + * Kernel memory inside dynamic memory group allows for more MOVABLE + * memory within the same group. Remove the effect of all but the + * current group from the stats. + */ + walk_dynamic_memory_groups(nid, auto_movable_stats_account_group, + group, &group_stats); + if (kernel_early_pages <= group_stats.req_kernel_early_pages) + return false; + kernel_early_pages -= group_stats.req_kernel_early_pages; + movable_pages -= group_stats.movable_pages; + + if (group && group->is_dynamic) + kernel_early_pages += group->present_kernel_pages; + /* * Test if we could online the given number of pages to ZONE_MOVABLE * and still stay in the configured ratio. @@ -834,6 +882,10 @@ static struct zone *default_kernel_zone_for_pfn(int nid, unsigned long start_pfn * with unmovable allocations). While there are corner cases where it might * still work, it is barely relevant in practice. * + * Exceptions are dynamic memory groups, which allow for more MOVABLE + * memory within the same memory group -- because in that case, there is + * coordination within the single memory device managed by a single driver. + * * We rely on "present pages" instead of "managed pages", as the latter is * highly unreliable and dynamic in virtualized environments, and does not * consider boot time allocations. For example, memory ballooning adjusts the @@ -899,12 +951,12 @@ static struct zone *auto_movable_zone_for_pfn(int nid, * nobody interferes, all will be MOVABLE if possible. */ nr_pages = max_pages - online_pages; - if (!auto_movable_can_online_movable(NUMA_NO_NODE, nr_pages)) + if (!auto_movable_can_online_movable(NUMA_NO_NODE, group, nr_pages)) goto kernel_zone; #ifdef CONFIG_NUMA if (auto_movable_numa_aware && - !auto_movable_can_online_movable(nid, nr_pages)) + !auto_movable_can_online_movable(nid, group, nr_pages)) goto kernel_zone; #endif /* CONFIG_NUMA */ -- cgit v1.2.3 From 5ef5f810199f421cb6455aa018fb8f21151b4a16 Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Tue, 7 Sep 2021 19:55:52 -0700 Subject: mm/memory_hotplug: use helper zone_is_zone_device() to simplify the code Patch series "Cleanup and fixups for memory hotplug". This series contains cleanup to use helper function to simplify the code. Also we fix some potential bugs. More details can be found in the respective changelogs. This patch (of 3): Use helper zone_is_zone_device() to simplify the code and remove some explicit CONFIG_ZONE_DEVICE codes. Link: https://lkml.kernel.org/r/20210821094246.10149-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20210821094246.10149-2-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Reviewed-by: David Hildenbrand Reviewed-by: Oscar Salvador Reviewed-by: Naoya Horiguchi Cc: Michal Hocko Cc: Minchan Kim Cc: Chris Goldsworthy Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index b80fb8164fb8..10030518e3d6 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -477,15 +477,13 @@ void __ref remove_pfn_range_from_zone(struct zone *zone, sizeof(struct page) * cur_nr_pages); } -#ifdef CONFIG_ZONE_DEVICE /* * Zone shrinking code cannot properly deal with ZONE_DEVICE. So * we will not try to shrink the zones - which is okay as * set_zone_contiguous() cannot deal with ZONE_DEVICE either way. */ - if (zone_idx(zone) == ZONE_DEVICE) + if (zone_is_zone_device(zone)) return; -#endif clear_zone_contiguous(zone); -- cgit v1.2.3 From fe3df441ef885a75a3eff5e151ead1a92266d222 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 7 Sep 2021 19:55:55 -0700 Subject: mm: remove redundant compound_head() calling There is a READ_ONCE() in the macro of compound_head(), which will prevent compiler from optimizing the code when there are more than once calling of it in a function. Remove the redundant calling of compound_head() from page_to_index() and page_add_file_rmap() for better code generation. Link: https://lkml.kernel.org/r/20210811101431.83940-1-songmuchun@bytedance.com Signed-off-by: Muchun Song Reviewed-by: David Howells Cc: Matthew Wilcox (Oracle) Cc: William Kucharski Cc: Kirill A. Shutemov Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 7 +++---- mm/rmap.c | 6 ++++-- 2 files changed, 7 insertions(+), 6 deletions(-) (limited to 'mm') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ed02aa522263..904e57db3a7d 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -521,18 +521,17 @@ static inline struct page *read_mapping_page(struct address_space *mapping, */ static inline pgoff_t page_to_index(struct page *page) { - pgoff_t pgoff; + struct page *head; if (likely(!PageTransTail(page))) return page->index; + head = compound_head(page); /* * We don't initialize ->index for tail pages: calculate based on * head page */ - pgoff = compound_head(page)->index; - pgoff += page - compound_head(page); - return pgoff; + return head->index + page - head; } extern pgoff_t hugetlb_basepage_index(struct page *page); diff --git a/mm/rmap.c b/mm/rmap.c index b9eb5c12f3fe..b2cebf35ffe7 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1230,11 +1230,13 @@ void page_add_file_rmap(struct page *page, bool compound) nr_pages); } else { if (PageTransCompound(page) && page_mapping(page)) { + struct page *head = compound_head(page); + VM_WARN_ON_ONCE(!PageLocked(page)); - SetPageDoubleMap(compound_head(page)); + SetPageDoubleMap(head); if (PageMlocked(page)) - clear_page_mlock(compound_head(page)); + clear_page_mlock(head); } if (!atomic_inc_and_test(&page->_mapcount)) goto out; -- cgit v1.2.3 From 82a70ce0426dd7c4099516175019dccbd18cebf9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 7 Sep 2021 19:56:01 -0700 Subject: mm: move ioremap_page_range to vmalloc.c Patch series "small ioremap cleanups". The first patch moves a little code around the vmalloc/ioremap boundary following a bigger move by Nick earlier. The second enforces non-executable mapping on ioremap just like we do for vmap. No driver currently uses executable mappings anyway, as they should. This patch (of 2): This keeps it together with the implementation, and to remove the vmap_range wrapper. Link: https://lkml.kernel.org/r/20210824091259.1324527-1-hch@lst.de Link: https://lkml.kernel.org/r/20210824091259.1324527-2-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Nicholas Piggin Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 3 --- mm/Makefile | 3 ++- mm/ioremap.c | 25 ------------------------- mm/vmalloc.c | 22 +++++++++++++++++----- 4 files changed, 19 insertions(+), 34 deletions(-) (limited to 'mm') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 2644425b6dce..671d402c3778 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -225,9 +225,6 @@ static inline bool is_vm_area_hugepages(const void *addr) } #ifdef CONFIG_MMU -int vmap_range(unsigned long addr, unsigned long end, - phys_addr_t phys_addr, pgprot_t prot, - unsigned int max_page_shift); void vunmap_range(unsigned long addr, unsigned long end); static inline void set_vm_flush_reset_perms(void *addr) { diff --git a/mm/Makefile b/mm/Makefile index e3436741d539..0e0a5a6fe127 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -38,7 +38,7 @@ mmu-y := nommu.o mmu-$(CONFIG_MMU) := highmem.o memory.o mincore.o \ mlock.o mmap.o mmu_gather.o mprotect.o mremap.o \ msync.o page_vma_mapped.o pagewalk.o \ - pgtable-generic.o rmap.o vmalloc.o ioremap.o + pgtable-generic.o rmap.o vmalloc.o ifdef CONFIG_CROSS_MEMORY_ATTACH @@ -128,3 +128,4 @@ obj-$(CONFIG_PTDUMP_CORE) += ptdump.o obj-$(CONFIG_PAGE_REPORTING) += page_reporting.o obj-$(CONFIG_IO_MAPPING) += io-mapping.o obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o +obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o diff --git a/mm/ioremap.c b/mm/ioremap.c index 8ee0136f8cb0..5fe598ecd9b7 100644 --- a/mm/ioremap.c +++ b/mm/ioremap.c @@ -8,33 +8,9 @@ */ #include #include -#include #include #include -#include -#include "pgalloc-track.h" - -#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP -static unsigned int __ro_after_init iomap_max_page_shift = BITS_PER_LONG - 1; - -static int __init set_nohugeiomap(char *str) -{ - iomap_max_page_shift = PAGE_SHIFT; - return 0; -} -early_param("nohugeiomap", set_nohugeiomap); -#else /* CONFIG_HAVE_ARCH_HUGE_VMAP */ -static const unsigned int iomap_max_page_shift = PAGE_SHIFT; -#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ - -int ioremap_page_range(unsigned long addr, - unsigned long end, phys_addr_t phys_addr, pgprot_t prot) -{ - return vmap_range(addr, end, phys_addr, prot, iomap_max_page_shift); -} - -#ifdef CONFIG_GENERIC_IOREMAP void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot) { unsigned long offset, vaddr; @@ -71,4 +47,3 @@ void iounmap(volatile void __iomem *addr) vunmap((void *)((unsigned long)addr & PAGE_MASK)); } EXPORT_SYMBOL(iounmap); -#endif /* CONFIG_GENERIC_IOREMAP */ diff --git a/mm/vmalloc.c b/mm/vmalloc.c index d5cd52805149..e44983fb2d15 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -44,6 +44,19 @@ #include "internal.h" #include "pgalloc-track.h" +#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +static unsigned int __ro_after_init ioremap_max_page_shift = BITS_PER_LONG - 1; + +static int __init set_nohugeiomap(char *str) +{ + ioremap_max_page_shift = PAGE_SHIFT; + return 0; +} +early_param("nohugeiomap", set_nohugeiomap); +#else /* CONFIG_HAVE_ARCH_HUGE_VMAP */ +static const unsigned int ioremap_max_page_shift = PAGE_SHIFT; +#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ + #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC static bool __ro_after_init vmap_allow_huge = true; @@ -298,15 +311,14 @@ static int vmap_range_noflush(unsigned long addr, unsigned long end, return err; } -int vmap_range(unsigned long addr, unsigned long end, - phys_addr_t phys_addr, pgprot_t prot, - unsigned int max_page_shift) +int ioremap_page_range(unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot) { int err; - err = vmap_range_noflush(addr, end, phys_addr, prot, max_page_shift); + err = vmap_range_noflush(addr, end, phys_addr, prot, + ioremap_max_page_shift); flush_cache_vmap(addr, end); - return err; } -- cgit v1.2.3 From 8491502f787c4a902bd4f223b578ef47d3490264 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 7 Sep 2021 19:56:04 -0700 Subject: mm: don't allow executable ioremap mappings There is no need to execute from iomem (and most platforms it is impossible anyway), so add the pgprot_nx() call similar to vmap. Link: https://lkml.kernel.org/r/20210824091259.1324527-3-hch@lst.de Signed-off-by: Christoph Hellwig Cc: Nicholas Piggin Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmalloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/vmalloc.c b/mm/vmalloc.c index e44983fb2d15..3055f04b486b 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -316,7 +316,7 @@ int ioremap_page_range(unsigned long addr, unsigned long end, { int err; - err = vmap_range_noflush(addr, end, phys_addr, prot, + err = vmap_range_noflush(addr, end, phys_addr, pgprot_nx(prot), ioremap_max_page_shift); flush_cache_vmap(addr, end); return err; -- cgit v1.2.3 From 395519b4b6e82741f29aaf6defa66cbdf3466584 Mon Sep 17 00:00:00 2001 From: Weizhao Ouyang Date: Tue, 7 Sep 2021 19:56:06 -0700 Subject: mm/early_ioremap.c: remove redundant early_ioremap_shutdown() early_ioremap_reset() reserved a weak function so that architectures can provide a specific cleanup. Now no architectures use it, remove this redundant function. Link: https://lkml.kernel.org/r/20210901082917.399953-1-o451686892@gmail.com Signed-off-by: Weizhao Ouyang Reviewed-by: David Hildenbrand Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/early_ioremap.h | 6 ------ mm/early_ioremap.c | 5 ----- 2 files changed, 11 deletions(-) (limited to 'mm') diff --git a/include/asm-generic/early_ioremap.h b/include/asm-generic/early_ioremap.h index 9def22e6e2b3..9d0479f50f97 100644 --- a/include/asm-generic/early_ioremap.h +++ b/include/asm-generic/early_ioremap.h @@ -19,12 +19,6 @@ extern void *early_memremap_prot(resource_size_t phys_addr, extern void early_iounmap(void __iomem *addr, unsigned long size); extern void early_memunmap(void *addr, unsigned long size); -/* - * Weak function called by early_ioremap_reset(). It does nothing, but - * architectures may provide their own version to do any needed cleanups. - */ -extern void early_ioremap_shutdown(void); - #if defined(CONFIG_GENERIC_EARLY_IOREMAP) && defined(CONFIG_MMU) /* Arch-specific initialization */ extern void early_ioremap_init(void); diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c index 164607c7cdf1..74984c23a87e 100644 --- a/mm/early_ioremap.c +++ b/mm/early_ioremap.c @@ -38,13 +38,8 @@ pgprot_t __init __weak early_memremap_pgprot_adjust(resource_size_t phys_addr, return prot; } -void __init __weak early_ioremap_shutdown(void) -{ -} - void __init early_ioremap_reset(void) { - early_ioremap_shutdown(); after_paging_init = 1; } -- cgit v1.2.3 From ea0eafead4b66543b8218ebfbe14173315feb7d1 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Tue, 7 Sep 2021 19:56:12 -0700 Subject: mm: in_irq() cleanup Replace the obsolete and ambiguos macro in_irq() with new macro in_hardirq(). Link: https://lkml.kernel.org/r/20210813145245.86070-1-changbin.du@gmail.com Signed-off-by: Changbin Du Acked-by: Catalin Marinas [kmemleak] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/highmem.c | 2 +- mm/kmemleak.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/highmem.c b/mm/highmem.c index 4fb51d735aa6..4212ad0e4a19 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -436,7 +436,7 @@ EXPORT_SYMBOL(zero_user_segments); static inline int kmap_local_idx_push(void) { - WARN_ON_ONCE(in_irq() && !irqs_disabled()); + WARN_ON_ONCE(in_hardirq() && !irqs_disabled()); current->kmap_ctrl.idx += KM_INCR; BUG_ON(current->kmap_ctrl.idx >= KM_MAX_IDX); return current->kmap_ctrl.idx - 1; diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 73d46d16d575..b59f1761d817 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -598,7 +598,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size, object->checksum = 0; /* task information */ - if (in_irq()) { + if (in_hardirq()) { object->pid = 0; strncpy(object->comm, "hardirq", sizeof(object->comm)); } else if (in_serving_softirq()) { -- cgit v1.2.3 From 110860541f443f950c1274f217a1a3e298670a33 Mon Sep 17 00:00:00 2001 From: Jordy Zomer Date: Tue, 7 Sep 2021 19:56:18 -0700 Subject: mm/secretmem: use refcount_t instead of atomic_t When a secret memory region is active, memfd_secret disables hibernation. One of the goals is to keep the secret data from being written to persistent-storage. It accomplishes this by maintaining a reference count to `secretmem_users`. Once this reference is held your system can not be hibernated due to the check in `hibernation_available()`. However, because `secretmem_users` is of type `atomic_t`, reference counter overflows are possible. As you can see there's an `atomic_inc` for each `memfd` that is opened in the `memfd_secret` syscall. If a local attacker succeeds to open 2^32 memfd's, the counter will wrap around to 0. This implies that you may hibernate again, even though there are still regions of this secret memory, thereby bypassing the security check. In an attempt to fix this I have used `refcount_t` instead of `atomic_t` which prevents reference counter overflows. Link: https://lkml.kernel.org/r/20210820043339.2151352-1-jordy@pwning.systems Signed-off-by: Jordy Zomer Cc: Kees Cook , Cc: Jordy Zomer Cc: James Bottomley Cc: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/secretmem.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/secretmem.c b/mm/secretmem.c index 030f02ddc7c1..1fea68b8d5a6 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -18,6 +18,7 @@ #include #include #include +#include #include @@ -40,11 +41,11 @@ module_param_named(enable, secretmem_enable, bool, 0400); MODULE_PARM_DESC(secretmem_enable, "Enable secretmem and memfd_secret(2) system call"); -static atomic_t secretmem_users; +static refcount_t secretmem_users; bool secretmem_active(void) { - return !!atomic_read(&secretmem_users); + return !!refcount_read(&secretmem_users); } static vm_fault_t secretmem_fault(struct vm_fault *vmf) @@ -103,7 +104,7 @@ static const struct vm_operations_struct secretmem_vm_ops = { static int secretmem_release(struct inode *inode, struct file *file) { - atomic_dec(&secretmem_users); + refcount_dec(&secretmem_users); return 0; } @@ -217,7 +218,7 @@ SYSCALL_DEFINE1(memfd_secret, unsigned int, flags) file->f_flags |= O_LARGEFILE; fd_install(fd, file); - atomic_inc(&secretmem_users); + refcount_inc(&secretmem_users); return fd; err_put_fd: -- cgit v1.2.3 From 4bbf04aa9aa88ae41205e387d35743a9bf5e933d Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 7 Sep 2021 19:56:21 -0700 Subject: kfence: show cpu and timestamp in alloc/free info Record cpu and timestamp on allocations and frees, and show them in reports. Upon an error, this can help correlate earlier messages in the kernel log via allocation and free timestamps. Link: https://lkml.kernel.org/r/20210714175312.2947941-1-elver@google.com Suggested-by: Joern Engel Signed-off-by: Marco Elver Acked-by: Alexander Potapenko Acked-by: Joern Engel Cc: Yuanyuan Zhong Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/dev-tools/kfence.rst | 98 +++++++++++++++++++++----------------- mm/kfence/core.c | 3 ++ mm/kfence/kfence.h | 2 + mm/kfence/report.c | 19 +++++--- 4 files changed, 71 insertions(+), 51 deletions(-) (limited to 'mm') diff --git a/Documentation/dev-tools/kfence.rst b/Documentation/dev-tools/kfence.rst index fdf04e741ea5..0fbe3308bf37 100644 --- a/Documentation/dev-tools/kfence.rst +++ b/Documentation/dev-tools/kfence.rst @@ -65,25 +65,27 @@ Error reports A typical out-of-bounds access looks like this:: ================================================================== - BUG: KFENCE: out-of-bounds read in test_out_of_bounds_read+0xa3/0x22b + BUG: KFENCE: out-of-bounds read in test_out_of_bounds_read+0xa6/0x234 - Out-of-bounds read at 0xffffffffb672efff (1B left of kfence-#17): - test_out_of_bounds_read+0xa3/0x22b - kunit_try_run_case+0x51/0x85 + Out-of-bounds read at 0xffff8c3f2e291fff (1B left of kfence-#72): + test_out_of_bounds_read+0xa6/0x234 + kunit_try_run_case+0x61/0xa0 kunit_generic_run_threadfn_adapter+0x16/0x30 - kthread+0x137/0x160 + kthread+0x176/0x1b0 ret_from_fork+0x22/0x30 - kfence-#17 [0xffffffffb672f000-0xffffffffb672f01f, size=32, cache=kmalloc-32] allocated by task 507: - test_alloc+0xf3/0x25b - test_out_of_bounds_read+0x98/0x22b - kunit_try_run_case+0x51/0x85 + kfence-#72: 0xffff8c3f2e292000-0xffff8c3f2e29201f, size=32, cache=kmalloc-32 + + allocated by task 484 on cpu 0 at 32.919330s: + test_alloc+0xfe/0x738 + test_out_of_bounds_read+0x9b/0x234 + kunit_try_run_case+0x61/0xa0 kunit_generic_run_threadfn_adapter+0x16/0x30 - kthread+0x137/0x160 + kthread+0x176/0x1b0 ret_from_fork+0x22/0x30 - CPU: 4 PID: 107 Comm: kunit_try_catch Not tainted 5.8.0-rc6+ #7 - Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014 + CPU: 0 PID: 484 Comm: kunit_try_catch Not tainted 5.13.0-rc3+ #7 + Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 ================================================================== The header of the report provides a short summary of the function involved in @@ -96,30 +98,32 @@ Use-after-free accesses are reported as:: ================================================================== BUG: KFENCE: use-after-free read in test_use_after_free_read+0xb3/0x143 - Use-after-free read at 0xffffffffb673dfe0 (in kfence-#24): + Use-after-free read at 0xffff8c3f2e2a0000 (in kfence-#79): test_use_after_free_read+0xb3/0x143 - kunit_try_run_case+0x51/0x85 + kunit_try_run_case+0x61/0xa0 kunit_generic_run_threadfn_adapter+0x16/0x30 - kthread+0x137/0x160 + kthread+0x176/0x1b0 ret_from_fork+0x22/0x30 - kfence-#24 [0xffffffffb673dfe0-0xffffffffb673dfff, size=32, cache=kmalloc-32] allocated by task 507: - test_alloc+0xf3/0x25b + kfence-#79: 0xffff8c3f2e2a0000-0xffff8c3f2e2a001f, size=32, cache=kmalloc-32 + + allocated by task 488 on cpu 2 at 33.871326s: + test_alloc+0xfe/0x738 test_use_after_free_read+0x76/0x143 - kunit_try_run_case+0x51/0x85 + kunit_try_run_case+0x61/0xa0 kunit_generic_run_threadfn_adapter+0x16/0x30 - kthread+0x137/0x160 + kthread+0x176/0x1b0 ret_from_fork+0x22/0x30 - freed by task 507: + freed by task 488 on cpu 2 at 33.871358s: test_use_after_free_read+0xa8/0x143 - kunit_try_run_case+0x51/0x85 + kunit_try_run_case+0x61/0xa0 kunit_generic_run_threadfn_adapter+0x16/0x30 - kthread+0x137/0x160 + kthread+0x176/0x1b0 ret_from_fork+0x22/0x30 - CPU: 4 PID: 109 Comm: kunit_try_catch Tainted: G W 5.8.0-rc6+ #7 - Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014 + CPU: 2 PID: 488 Comm: kunit_try_catch Tainted: G B 5.13.0-rc3+ #7 + Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 ================================================================== KFENCE also reports on invalid frees, such as double-frees:: @@ -127,30 +131,32 @@ KFENCE also reports on invalid frees, such as double-frees:: ================================================================== BUG: KFENCE: invalid free in test_double_free+0xdc/0x171 - Invalid free of 0xffffffffb6741000: + Invalid free of 0xffff8c3f2e2a4000 (in kfence-#81): test_double_free+0xdc/0x171 - kunit_try_run_case+0x51/0x85 + kunit_try_run_case+0x61/0xa0 kunit_generic_run_threadfn_adapter+0x16/0x30 - kthread+0x137/0x160 + kthread+0x176/0x1b0 ret_from_fork+0x22/0x30 - kfence-#26 [0xffffffffb6741000-0xffffffffb674101f, size=32, cache=kmalloc-32] allocated by task 507: - test_alloc+0xf3/0x25b + kfence-#81: 0xffff8c3f2e2a4000-0xffff8c3f2e2a401f, size=32, cache=kmalloc-32 + + allocated by task 490 on cpu 1 at 34.175321s: + test_alloc+0xfe/0x738 test_double_free+0x76/0x171 - kunit_try_run_case+0x51/0x85 + kunit_try_run_case+0x61/0xa0 kunit_generic_run_threadfn_adapter+0x16/0x30 - kthread+0x137/0x160 + kthread+0x176/0x1b0 ret_from_fork+0x22/0x30 - freed by task 507: + freed by task 490 on cpu 1 at 34.175348s: test_double_free+0xa8/0x171 - kunit_try_run_case+0x51/0x85 + kunit_try_run_case+0x61/0xa0 kunit_generic_run_threadfn_adapter+0x16/0x30 - kthread+0x137/0x160 + kthread+0x176/0x1b0 ret_from_fork+0x22/0x30 - CPU: 4 PID: 111 Comm: kunit_try_catch Tainted: G W 5.8.0-rc6+ #7 - Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014 + CPU: 1 PID: 490 Comm: kunit_try_catch Tainted: G B 5.13.0-rc3+ #7 + Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 ================================================================== KFENCE also uses pattern-based redzones on the other side of an object's guard @@ -160,23 +166,25 @@ These are reported on frees:: ================================================================== BUG: KFENCE: memory corruption in test_kmalloc_aligned_oob_write+0xef/0x184 - Corrupted memory at 0xffffffffb6797ff9 [ 0xac . . . . . . ] (in kfence-#69): + Corrupted memory at 0xffff8c3f2e33aff9 [ 0xac . . . . . . ] (in kfence-#156): test_kmalloc_aligned_oob_write+0xef/0x184 - kunit_try_run_case+0x51/0x85 + kunit_try_run_case+0x61/0xa0 kunit_generic_run_threadfn_adapter+0x16/0x30 - kthread+0x137/0x160 + kthread+0x176/0x1b0 ret_from_fork+0x22/0x30 - kfence-#69 [0xffffffffb6797fb0-0xffffffffb6797ff8, size=73, cache=kmalloc-96] allocated by task 507: - test_alloc+0xf3/0x25b + kfence-#156: 0xffff8c3f2e33afb0-0xffff8c3f2e33aff8, size=73, cache=kmalloc-96 + + allocated by task 502 on cpu 7 at 42.159302s: + test_alloc+0xfe/0x738 test_kmalloc_aligned_oob_write+0x57/0x184 - kunit_try_run_case+0x51/0x85 + kunit_try_run_case+0x61/0xa0 kunit_generic_run_threadfn_adapter+0x16/0x30 - kthread+0x137/0x160 + kthread+0x176/0x1b0 ret_from_fork+0x22/0x30 - CPU: 4 PID: 120 Comm: kunit_try_catch Tainted: G W 5.8.0-rc6+ #7 - Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014 + CPU: 7 PID: 502 Comm: kunit_try_catch Tainted: G B 5.13.0-rc3+ #7 + Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014 ================================================================== For such errors, the address where the corruption occurred as well as the diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 575c685aa642..7a97db8bc8e7 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -196,6 +197,8 @@ static noinline void metadata_update_state(struct kfence_metadata *meta, */ track->num_stack_entries = stack_trace_save(track->stack_entries, KFENCE_STACK_DEPTH, 1); track->pid = task_pid_nr(current); + track->cpu = raw_smp_processor_id(); + track->ts_nsec = local_clock(); /* Same source as printk timestamps. */ /* * Pairs with READ_ONCE() in diff --git a/mm/kfence/kfence.h b/mm/kfence/kfence.h index 24065321ff8a..c1f23c61e5f9 100644 --- a/mm/kfence/kfence.h +++ b/mm/kfence/kfence.h @@ -36,6 +36,8 @@ enum kfence_object_state { /* Alloc/free tracking information. */ struct kfence_track { pid_t pid; + int cpu; + u64 ts_nsec; int num_stack_entries; unsigned long stack_entries[KFENCE_STACK_DEPTH]; }; diff --git a/mm/kfence/report.c b/mm/kfence/report.c index 2a319c21c939..cbdd8d442d0b 100644 --- a/mm/kfence/report.c +++ b/mm/kfence/report.c @@ -9,6 +9,7 @@ #include #include +#include #include #include #include @@ -100,6 +101,13 @@ static void kfence_print_stack(struct seq_file *seq, const struct kfence_metadat bool show_alloc) { const struct kfence_track *track = show_alloc ? &meta->alloc_track : &meta->free_track; + u64 ts_sec = track->ts_nsec; + unsigned long rem_nsec = do_div(ts_sec, NSEC_PER_SEC); + + /* Timestamp matches printk timestamp format. */ + seq_con_printf(seq, "%s by task %d on cpu %d at %lu.%06lus:\n", + show_alloc ? "allocated" : "freed", track->pid, + track->cpu, (unsigned long)ts_sec, rem_nsec / 1000); if (track->num_stack_entries) { /* Skip allocation/free internals stack. */ @@ -126,15 +134,14 @@ void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *met return; } - seq_con_printf(seq, - "kfence-#%td [0x%p-0x%p" - ", size=%d, cache=%s] allocated by task %d:\n", - meta - kfence_metadata, (void *)start, (void *)(start + size - 1), size, - (cache && cache->name) ? cache->name : "", meta->alloc_track.pid); + seq_con_printf(seq, "kfence-#%td: 0x%p-0x%p, size=%d, cache=%s\n\n", + meta - kfence_metadata, (void *)start, (void *)(start + size - 1), + size, (cache && cache->name) ? cache->name : ""); + kfence_print_stack(seq, meta, true); if (meta->state == KFENCE_OBJECT_FREED) { - seq_con_printf(seq, "\nfreed by task %d:\n", meta->free_track.pid); + seq_con_printf(seq, "\n"); kfence_print_stack(seq, meta, false); } } -- cgit v1.2.3 From c40c6e593bf978e232bae1fab81f4111f2e2c956 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 7 Sep 2021 19:56:24 -0700 Subject: kfence: test: fail fast if disabled at boot Fail kfence_test fast if KFENCE was disabled at boot, instead of each test case trying several seconds to allocate from KFENCE and failing. KUnit will fail all test cases if kunit_suite::init returns an error. Even if KFENCE was disabled, we still want the test to fail, so that CI systems that parse KUnit output will alert on KFENCE being disabled (accidentally or otherwise). Link: https://lkml.kernel.org/r/20210825105533.1247922-1-elver@google.com Signed-off-by: Marco Elver Reported-by: Kefeng Wang Tested-by: Kefeng Wang Acked-by: Alexander Potapenko Cc: Dmitry Vyukov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kfence/kfence_test.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'mm') diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c index 942cbc16ad26..b936137f3ec3 100644 --- a/mm/kfence/kfence_test.c +++ b/mm/kfence/kfence_test.c @@ -789,6 +789,9 @@ static int test_init(struct kunit *test) unsigned long flags; int i; + if (!__kfence_pool) + return -EINVAL; + spin_lock_irqsave(&observed.lock, flags); for (i = 0; i < ARRAY_SIZE(observed.lines); i++) observed.lines[i][0] = '\0'; -- cgit v1.2.3 From 2224d8485492e499ca2e5d25407f8502cc06f149 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 7 Sep 2021 19:56:28 -0700 Subject: mm: introduce Data Access MONitor (DAMON) Patch series "Introduce Data Access MONitor (DAMON)", v34. Introduction ============ DAMON is a data access monitoring framework for the Linux kernel. The core mechanisms of DAMON called 'region based sampling' and 'adaptive regions adjustment' (refer to 'mechanisms.rst' in the 11th patch of this patchset for the detail) make it - accurate (The monitored information is useful for DRAM level memory management. It might not appropriate for Cache-level accuracy, though.), - light-weight (The monitoring overhead is low enough to be applied online while making no impact on the performance of the target workloads.), and - scalable (the upper-bound of the instrumentation overhead is controllable regardless of the size of target workloads.). Using this framework, therefore, several memory management mechanisms such as reclamation and THP can be optimized to aware real data access patterns. Experimental access pattern aware memory management optimization works that incurring high instrumentation overhead will be able to have another try. Though DAMON is for kernel subsystems, it can be easily exposed to the user space by writing a DAMON-wrapper kernel subsystem. Then, user space users who have some special workloads will be able to write personalized tools or applications for deeper understanding and specialized optimizations of their systems. DAMON is also merged in two public Amazon Linux kernel trees that based on v5.4.y[1] and v5.10.y[2]. [1] https://github.com/amazonlinux/linux/tree/amazon-5.4.y/master/mm/damon [2] https://github.com/amazonlinux/linux/tree/amazon-5.10.y/master/mm/damon The userspace tool[1] is available, released under GPLv2, and actively being maintained. I am also planning to implement another basic user interface in perf[2]. Also, the basic test suite for DAMON is available under GPLv2[3]. [1] https://github.com/awslabs/damo [2] https://lore.kernel.org/linux-mm/20210107120729.22328-1-sjpark@amazon.com/ [3] https://github.com/awslabs/damon-tests Long-term Plan -------------- DAMON is a part of a project called Data Access-aware Operating System (DAOS). As the name implies, I want to improve the performance and efficiency of systems using fine-grained data access patterns. The optimizations are for both kernel and user spaces. I will therefore modify or create kernel subsystems, export some of those to user space and implement user space library / tools. Below shows the layers and components for the project. --------------------------------------------------------------------------- Primitives: PTE Accessed bit, PG_idle, rmap, (Intel CMT), ... Framework: DAMON Features: DAMOS, virtual addr, physical addr, ... Applications: DAMON-debugfs, (DARC), ... ^^^^^^^^^^^^^^^^^^^^^^^ KERNEL SPACE ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Raw Interface: debugfs, (sysfs), (damonfs), tracepoints, (sys_damon), ... vvvvvvvvvvvvvvvvvvvvvvv USER SPACE vvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvv Library: (libdamon), ... Tools: DAMO, (perf), ... --------------------------------------------------------------------------- The components in parentheses or marked as '...' are not implemented yet but in the future plan. IOW, those are the TODO tasks of DAOS project. For more detail, please refer to the plans: https://lore.kernel.org/linux-mm/20201202082731.24828-1-sjpark@amazon.com/ Evaluations =========== We evaluated DAMON's overhead, monitoring quality and usefulness using 24 realistic workloads on my QEMU/KVM based virtual machine running a kernel that v24 DAMON patchset is applied. DAMON is lightweight. It increases system memory usage by 0.39% and slows target workloads down by 1.16%. DAMON is accurate and useful for memory management optimizations. An experimental DAMON-based operation scheme for THP, namely 'ethp', removes 76.15% of THP memory overheads while preserving 51.25% of THP speedup. Another experimental DAMON-based 'proactive reclamation' implementation, 'prcl', reduces 93.38% of residential sets and 23.63% of system memory footprint while incurring only 1.22% runtime overhead in the best case (parsec3/freqmine). NOTE that the experimental THP optimization and proactive reclamation are not for production but only for proof of concepts. Please refer to the official document[1] or "Documentation/admin-guide/mm: Add a document for DAMON" patch in this patchset for detailed evaluation setup and results. [1] https://damonitor.github.io/doc/html/latest-damon/admin-guide/mm/damon/eval.html Real-world User Story ===================== In summary, DAMON has used on production systems and proved its usefulness. DAMON as a profiler ------------------- We analyzed characteristics of a large scale production systems of our customers using DAMON. The systems utilize 70GB DRAM and 36 CPUs. From this, we were able to find interesting things below. There were obviously different access pattern under idle workload and active workload. Under the idle workload, it accessed large memory regions with low frequency, while the active workload accessed small memory regions with high freuqnecy. DAMON found a 7GB memory region that showing obviously high access frequency under the active workload. We believe this is the performance-effective working set and need to be protected. There was a 4KB memory region that showing highest access frequency under not only active but also idle workloads. We think this must be a hottest code section like thing that should never be paged out. For this analysis, DAMON used only 0.3-1% of single CPU time. Because we used recording-based analysis, it consumed about 3-12 MB of disk space per 20 minutes. This is only small amount of disk space, but we can further reduce the disk usage by using non-recording-based DAMON features. I'd like to argue that only DAMON can do such detailed analysis (finding 4KB highest region in 70GB memory) with the light overhead. DAMON as a system optimization tool ----------------------------------- We also found below potential performance problems on the systems and made DAMON-based solutions. The system doesn't want to make the workload suffer from the page reclamation and thus it utilizes enough DRAM but no swap device. However, we found the system is actively reclaiming file-backed pages, because the system has intensive file IO. The file IO turned out to be not performance critical for the workload, but the customer wanted to ensure performance critical file-backed pages like code section to not mistakenly be evicted. Using direct IO should or `mlock()` would be a straightforward solution, but modifying the user space code is not easy for the customer. Alternatively, we could use DAMON-based operation scheme[1]. By using it, we can ask DAMON to track access frequency of each region and make 'process_madvise(MADV_WILLNEED)[2]' call for regions having specific size and access frequency for a time interval. We also found the system is having high number of TLB misses. We tried 'always' THP enabled policy and it greatly reduced TLB misses, but the page reclamation also been more frequent due to the THP internal fragmentation caused memory bloat. We could try another DAMON-based operation scheme that applies 'MADV_HUGEPAGE' to memory regions having >=2MB size and high access frequency, while applying 'MADV_NOHUGEPAGE' to regions having <2MB size and low access frequency. We do not own the systems so we only reported the analysis results and possible optimization solutions to the customers. The customers satisfied about the analysis results and promised to try the optimization guides. [1] https://lore.kernel.org/linux-mm/20201006123931.5847-1-sjpark@amazon.com/ [2] https://lore.kernel.org/linux-api/20200622192900.22757-4-minchan@kernel.org/ Comparison with Idle Page Tracking ================================== Idle Page Tracking allows users to set and read idleness of pages using a bitmap file which represents each page with each bit of the file. One recommended usage of it is working set size detection. Users can do that by 1. find PFN of each page for workloads in interest, 2. set all the pages as idle by doing writes to the bitmap file, 3. wait until the workload accesses its working set, and 4. read the idleness of the pages again and count pages became not idle. NOTE: While Idle Page Tracking is for user space users, DAMON is primarily designed for kernel subsystems though it can easily exposed to the user space. Hence, this section only assumes such user space use of DAMON. For what use cases Idle Page Tracking would be better? ------------------------------------------------------ 1. Flexible usecases other than hotness monitoring. Because Idle Page Tracking allows users to control the primitive (Page idleness) by themselves, Idle Page Tracking users can do anything they want. Meanwhile, DAMON is primarily designed to monitor the hotness of each memory region. For this, DAMON asks users to provide sampling interval and aggregation interval. For the reason, there could be some use case that using Idle Page Tracking is simpler. 2. Physical memory monitoring. Idle Page Tracking receives PFN range as input, so natively supports physical memory monitoring. DAMON is designed to be extensible for multiple address spaces and use cases by implementing and using primitives for the given use case. Therefore, by theory, DAMON has no limitation in the type of target address space as long as primitives for the given address space exists. However, the default primitives introduced by this patchset supports only virtual address spaces. Therefore, for physical memory monitoring, you should implement your own primitives and use it, or simply use Idle Page Tracking. Nonetheless, RFC patchsets[1] for the physical memory address space primitives is already available. It also supports user memory same to Idle Page Tracking. [1] https://lore.kernel.org/linux-mm/20200831104730.28970-1-sjpark@amazon.com/ For what use cases DAMON is better? ----------------------------------- 1. Hotness Monitoring. Idle Page Tracking let users know only if a page frame is accessed or not. For hotness check, the user should write more code and use more memory. DAMON do that by itself. 2. Low Monitoring Overhead DAMON receives user's monitoring request with one step and then provide the results. So, roughly speaking, DAMON require only O(1) user/kernel context switches. In case of Idle Page Tracking, however, because the interface receives contiguous page frames, the number of user/kernel context switches increases as the monitoring target becomes complex and huge. As a result, the context switch overhead could be not negligible. Moreover, DAMON is born to handle with the monitoring overhead. Because the core mechanism is pure logical, Idle Page Tracking users might be able to implement the mechanism on their own, but it would be time consuming and the user/kernel context switching will still more frequent than that of DAMON. Also, the kernel subsystems cannot use the logic in this case. 3. Page granularity working set size detection. Until v22 of this patchset, this was categorized as the thing Idle Page Tracking could do better, because DAMON basically maintains additional metadata for each of the monitoring target regions. So, in the page granularity working set size detection use case, DAMON would incur (number of monitoring target pages * size of metadata) memory overhead. Size of the single metadata item is about 54 bytes, so assuming 4KB pages, about 1.3% of monitoring target pages will be additionally used. All essential metadata for Idle Page Tracking are embedded in 'struct page' and page table entries. Therefore, in this use case, only one counter variable for working set size accounting is required if Idle Page Tracking is used. There are more details to consider, but roughly speaking, this is true in most cases. However, the situation changed from v23. Now DAMON supports arbitrary types of monitoring targets, which don't use the metadata. Using that, DAMON can do the working set size detection with no additional space overhead but less user-kernel context switch. A first draft for the implementation of monitoring primitives for this usage is available in a DAMON development tree[1]. An RFC patchset for it based on this patchset will also be available soon. Since v24, the arbitrary type support is dropped from this patchset because this patchset doesn't introduce real use of the type. You can still get it from the DAMON development tree[2], though. [1] https://github.com/sjp38/linux/tree/damon/pgidle_hack [2] https://github.com/sjp38/linux/tree/damon/master 4. More future usecases While Idle Page Tracking has tight coupling with base primitives (PG_Idle and page table Accessed bits), DAMON is designed to be extensible for many use cases and address spaces. If you need some special address type or want to use special h/w access check primitives, you can write your own primitives for that and configure DAMON to use those. Therefore, if your use case could be changed a lot in future, using DAMON could be better. Can I use both Idle Page Tracking and DAMON? -------------------------------------------- Yes, though using them concurrently for overlapping memory regions could result in interference to each other. Nevertheless, such use case would be rare or makes no sense at all. Even in the case, the noise would bot be really significant. So, you can choose whatever you want depending on the characteristics of your use cases. More Information ================ We prepared a showcase web site[1] that you can get more information. There are - the official documentations[2], - the heatmap format dynamic access pattern of various realistic workloads for heap area[3], mmap()-ed area[4], and stack[5] area, - the dynamic working set size distribution[6] and chronological working set size changes[7], and - the latest performance test results[8]. [1] https://damonitor.github.io/_index [2] https://damonitor.github.io/doc/html/latest-damon [3] https://damonitor.github.io/test/result/visual/latest/rec.heatmap.0.png.html [4] https://damonitor.github.io/test/result/visual/latest/rec.heatmap.1.png.html [5] https://damonitor.github.io/test/result/visual/latest/rec.heatmap.2.png.html [6] https://damonitor.github.io/test/result/visual/latest/rec.wss_sz.png.html [7] https://damonitor.github.io/test/result/visual/latest/rec.wss_time.png.html [8] https://damonitor.github.io/test/result/perf/latest/html/index.html Baseline and Complete Git Trees =============================== The patches are based on the latest -mm tree, specifically v5.14-rc1-mmots-2021-07-15-18-47 of https://github.com/hnaz/linux-mm. You can also clone the complete git tree: $ git clone git://github.com/sjp38/linux -b damon/patches/v34 The web is also available: https://github.com/sjp38/linux/releases/tag/damon/patches/v34 Development Trees ----------------- There are a couple of trees for entire DAMON patchset series and features for future release. - For latest release: https://github.com/sjp38/linux/tree/damon/master - For next release: https://github.com/sjp38/linux/tree/damon/next Long-term Support Trees ----------------------- For people who want to test DAMON but using LTS kernels, there are another couple of trees based on two latest LTS kernels respectively and containing the 'damon/master' backports. - For v5.4.y: https://github.com/sjp38/linux/tree/damon/for-v5.4.y - For v5.10.y: https://github.com/sjp38/linux/tree/damon/for-v5.10.y Amazon Linux Kernel Trees ------------------------- DAMON is also merged in two public Amazon Linux kernel trees that based on v5.4.y[1] and v5.10.y[2]. [1] https://github.com/amazonlinux/linux/tree/amazon-5.4.y/master/mm/damon [2] https://github.com/amazonlinux/linux/tree/amazon-5.10.y/master/mm/damon Git Tree for Diff of Patches ============================ For easy review of diff between different versions of each patch, I prepared a git tree containing all versions of the DAMON patchset series: https://github.com/sjp38/damon-patches You can clone it and use 'diff' for easy review of changes between different versions of the patchset. For example: $ git clone https://github.com/sjp38/damon-patches && cd damon-patches $ diff -u damon/v33 damon/v34 Sequence Of Patches =================== First three patches implement the core logics of DAMON. The 1st patch introduces basic sampling based hotness monitoring for arbitrary types of targets. Following two patches implement the core mechanisms for control of overhead and accuracy, namely regions based sampling (patch 2) and adaptive regions adjustment (patch 3). Now the essential parts of DAMON is complete, but it cannot work unless someone provides monitoring primitives for a specific use case. The following two patches make it just work for virtual address spaces monitoring. The 4th patch makes 'PG_idle' can be used by DAMON and the 5th patch implements the virtual memory address space specific monitoring primitives using page table Accessed bits and the 'PG_idle' page flag. Now DAMON just works for virtual address space monitoring via the kernel space api. To let the user space users can use DAMON, following four patches add interfaces for them. The 6th patch adds a tracepoint for monitoring results. The 7th patch implements a DAMON application kernel module, namely damon-dbgfs, that simply wraps DAMON and exposes DAMON interface to the user space via the debugfs interface. The 8th patch further exports pid of monitoring thread (kdamond) to user space for easier cpu usage accounting, and the 9th patch makes the debugfs interface to support multiple contexts. Three patches for maintainability follows. The 10th patch adds documentations for both the user space and the kernel space. The 11th patch provides unit tests (based on the kunit) while the 12th patch adds user space tests (based on the kselftest). Finally, the last patch (13th) updates the MAINTAINERS file. This patch (of 13): DAMON is a data access monitoring framework for the Linux kernel. The core mechanisms of DAMON make it - accurate (the monitoring output is useful enough for DRAM level performance-centric memory management; It might be inappropriate for CPU cache levels, though), - light-weight (the monitoring overhead is normally low enough to be applied online), and - scalable (the upper-bound of the overhead is in constant range regardless of the size of target workloads). Using this framework, hence, we can easily write efficient kernel space data access monitoring applications. For example, the kernel's memory management mechanisms can make advanced decisions using this. Experimental data access aware optimization works that incurring high access monitoring overhead could again be implemented on top of this. Due to its simple and flexible interface, providing user space interface would be also easy. Then, user space users who have some special workloads can write personalized applications for better understanding and optimizations of their workloads and systems. === Nevertheless, this commit is defining and implementing only basic access check part without the overhead-accuracy handling core logic. The basic access check is as below. The output of DAMON says what memory regions are how frequently accessed for a given duration. The resolution of the access frequency is controlled by setting ``sampling interval`` and ``aggregation interval``. In detail, DAMON checks access to each page per ``sampling interval`` and aggregates the results. In other words, counts the number of the accesses to each region. After each ``aggregation interval`` passes, DAMON calls callback functions that previously registered by users so that users can read the aggregated results and then clears the results. This can be described in below simple pseudo-code:: init() while monitoring_on: for page in monitoring_target: if accessed(page): nr_accesses[page] += 1 if time() % aggregation_interval == 0: for callback in user_registered_callbacks: callback(monitoring_target, nr_accesses) for page in monitoring_target: nr_accesses[page] = 0 if time() % update_interval == 0: update() sleep(sampling interval) The target regions constructed at the beginning of the monitoring and updated after each ``regions_update_interval``, because the target regions could be dynamically changed (e.g., mmap() or memory hotplug). The monitoring overhead of this mechanism will arbitrarily increase as the size of the target workload grows. The basic monitoring primitives for actual access check and dynamic target regions construction aren't in the core part of DAMON. Instead, it allows users to implement their own primitives that are optimized for their use case and configure DAMON to use those. In other words, users cannot use current version of DAMON without some additional works. Following commits will implement the core mechanisms for the overhead-accuracy control and default primitives implementations. Link: https://lkml.kernel.org/r/20210716081449.22187-1-sj38.park@gmail.com Link: https://lkml.kernel.org/r/20210716081449.22187-2-sj38.park@gmail.com Signed-off-by: SeongJae Park Reviewed-by: Leonard Foerster Reviewed-by: Fernand Sieber Acked-by: Shakeel Butt Cc: Jonathan Cameron Cc: Alexander Shishkin Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Jonathan Corbet Cc: David Hildenbrand Cc: David Woodhouse Cc: Marco Elver Cc: Fan Du Cc: Greg Kroah-Hartman Cc: Greg Thelen Cc: Joe Perches Cc: Mel Gorman Cc: Maximilian Heyne Cc: Minchan Kim Cc: Ingo Molnar Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Rik van Riel Cc: David Rientjes Cc: Steven Rostedt (VMware) Cc: Shuah Khan Cc: Vlastimil Babka Cc: Vladimir Davydov Cc: Brendan Higgins Cc: Markus Boehme Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 167 ++++++++++++++++++++++++++ mm/Kconfig | 2 + mm/Makefile | 1 + mm/damon/Kconfig | 15 +++ mm/damon/Makefile | 3 + mm/damon/core.c | 320 ++++++++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 508 insertions(+) create mode 100644 include/linux/damon.h create mode 100644 mm/damon/Kconfig create mode 100644 mm/damon/Makefile create mode 100644 mm/damon/core.c (limited to 'mm') diff --git a/include/linux/damon.h b/include/linux/damon.h new file mode 100644 index 000000000000..2f652602b1ea --- /dev/null +++ b/include/linux/damon.h @@ -0,0 +1,167 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * DAMON api + * + * Author: SeongJae Park + */ + +#ifndef _DAMON_H_ +#define _DAMON_H_ + +#include +#include +#include + +struct damon_ctx; + +/** + * struct damon_primitive Monitoring primitives for given use cases. + * + * @init: Initialize primitive-internal data structures. + * @update: Update primitive-internal data structures. + * @prepare_access_checks: Prepare next access check of target regions. + * @check_accesses: Check the accesses to target regions. + * @reset_aggregated: Reset aggregated accesses monitoring results. + * @target_valid: Determine if the target is valid. + * @cleanup: Clean up the context. + * + * DAMON can be extended for various address spaces and usages. For this, + * users should register the low level primitives for their target address + * space and usecase via the &damon_ctx.primitive. Then, the monitoring thread + * (&damon_ctx.kdamond) calls @init and @prepare_access_checks before starting + * the monitoring, @update after each &damon_ctx.primitive_update_interval, and + * @check_accesses, @target_valid and @prepare_access_checks after each + * &damon_ctx.sample_interval. Finally, @reset_aggregated is called after each + * &damon_ctx.aggr_interval. + * + * @init should initialize primitive-internal data structures. For example, + * this could be used to construct proper monitoring target regions and link + * those to @damon_ctx.target. + * @update should update the primitive-internal data structures. For example, + * this could be used to update monitoring target regions for current status. + * @prepare_access_checks should manipulate the monitoring regions to be + * prepared for the next access check. + * @check_accesses should check the accesses to each region that made after the + * last preparation and update the number of observed accesses of each region. + * @reset_aggregated should reset the access monitoring results that aggregated + * by @check_accesses. + * @target_valid should check whether the target is still valid for the + * monitoring. + * @cleanup is called from @kdamond just before its termination. + */ +struct damon_primitive { + void (*init)(struct damon_ctx *context); + void (*update)(struct damon_ctx *context); + void (*prepare_access_checks)(struct damon_ctx *context); + void (*check_accesses)(struct damon_ctx *context); + void (*reset_aggregated)(struct damon_ctx *context); + bool (*target_valid)(void *target); + void (*cleanup)(struct damon_ctx *context); +}; + +/* + * struct damon_callback Monitoring events notification callbacks. + * + * @before_start: Called before starting the monitoring. + * @after_sampling: Called after each sampling. + * @after_aggregation: Called after each aggregation. + * @before_terminate: Called before terminating the monitoring. + * @private: User private data. + * + * The monitoring thread (&damon_ctx.kdamond) calls @before_start and + * @before_terminate just before starting and finishing the monitoring, + * respectively. Therefore, those are good places for installing and cleaning + * @private. + * + * The monitoring thread calls @after_sampling and @after_aggregation for each + * of the sampling intervals and aggregation intervals, respectively. + * Therefore, users can safely access the monitoring results without additional + * protection. For the reason, users are recommended to use these callback for + * the accesses to the results. + * + * If any callback returns non-zero, monitoring stops. + */ +struct damon_callback { + void *private; + + int (*before_start)(struct damon_ctx *context); + int (*after_sampling)(struct damon_ctx *context); + int (*after_aggregation)(struct damon_ctx *context); + int (*before_terminate)(struct damon_ctx *context); +}; + +/** + * struct damon_ctx - Represents a context for each monitoring. This is the + * main interface that allows users to set the attributes and get the results + * of the monitoring. + * + * @sample_interval: The time between access samplings. + * @aggr_interval: The time between monitor results aggregations. + * @primitive_update_interval: The time between monitoring primitive updates. + * + * For each @sample_interval, DAMON checks whether each region is accessed or + * not. It aggregates and keeps the access information (number of accesses to + * each region) for @aggr_interval time. DAMON also checks whether the target + * memory regions need update (e.g., by ``mmap()`` calls from the application, + * in case of virtual memory monitoring) and applies the changes for each + * @primitive_update_interval. All time intervals are in micro-seconds. + * Please refer to &struct damon_primitive and &struct damon_callback for more + * detail. + * + * @kdamond: Kernel thread who does the monitoring. + * @kdamond_stop: Notifies whether kdamond should stop. + * @kdamond_lock: Mutex for the synchronizations with @kdamond. + * + * For each monitoring context, one kernel thread for the monitoring is + * created. The pointer to the thread is stored in @kdamond. + * + * Once started, the monitoring thread runs until explicitly required to be + * terminated or every monitoring target is invalid. The validity of the + * targets is checked via the &damon_primitive.target_valid of @primitive. The + * termination can also be explicitly requested by writing non-zero to + * @kdamond_stop. The thread sets @kdamond to NULL when it terminates. + * Therefore, users can know whether the monitoring is ongoing or terminated by + * reading @kdamond. Reads and writes to @kdamond and @kdamond_stop from + * outside of the monitoring thread must be protected by @kdamond_lock. + * + * Note that the monitoring thread protects only @kdamond and @kdamond_stop via + * @kdamond_lock. Accesses to other fields must be protected by themselves. + * + * @primitive: Set of monitoring primitives for given use cases. + * @callback: Set of callbacks for monitoring events notifications. + * + * @target: Pointer to the user-defined monitoring target. + */ +struct damon_ctx { + unsigned long sample_interval; + unsigned long aggr_interval; + unsigned long primitive_update_interval; + +/* private: internal use only */ + struct timespec64 last_aggregation; + struct timespec64 last_primitive_update; + +/* public: */ + struct task_struct *kdamond; + bool kdamond_stop; + struct mutex kdamond_lock; + + struct damon_primitive primitive; + struct damon_callback callback; + + void *target; +}; + +#ifdef CONFIG_DAMON + +struct damon_ctx *damon_new_ctx(void); +void damon_destroy_ctx(struct damon_ctx *ctx); +int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, + unsigned long aggr_int, unsigned long primitive_upd_int); + +int damon_start(struct damon_ctx **ctxs, int nr_ctxs); +int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); + +#endif /* CONFIG_DAMON */ + +#endif /* _DAMON_H */ diff --git a/mm/Kconfig b/mm/Kconfig index 14d5d2837737..8459167b0294 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -886,4 +886,6 @@ config IO_MAPPING config SECRETMEM def_bool ARCH_HAS_SET_DIRECT_MAP && !EMBEDDED +source "mm/damon/Kconfig" + endmenu diff --git a/mm/Makefile b/mm/Makefile index 0e0a5a6fe127..fc60a40ce954 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -118,6 +118,7 @@ obj-$(CONFIG_CMA_SYSFS) += cma_sysfs.o obj-$(CONFIG_USERFAULTFD) += userfaultfd.o obj-$(CONFIG_IDLE_PAGE_TRACKING) += page_idle.o obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o +obj-$(CONFIG_DAMON) += damon/ obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o obj-$(CONFIG_ZONE_DEVICE) += memremap.o diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig new file mode 100644 index 000000000000..d00e99ac1a15 --- /dev/null +++ b/mm/damon/Kconfig @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0-only + +menu "Data Access Monitoring" + +config DAMON + bool "DAMON: Data Access Monitoring Framework" + help + This builds a framework that allows kernel subsystems to monitor + access frequency of each memory region. The information can be useful + for performance-centric DRAM level memory management. + + See https://damonitor.github.io/doc/html/latest-damon/index.html for + more information. + +endmenu diff --git a/mm/damon/Makefile b/mm/damon/Makefile new file mode 100644 index 000000000000..4fd2edb4becf --- /dev/null +++ b/mm/damon/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_DAMON) := core.o diff --git a/mm/damon/core.c b/mm/damon/core.c new file mode 100644 index 000000000000..651590bf49b1 --- /dev/null +++ b/mm/damon/core.c @@ -0,0 +1,320 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Data Access Monitor + * + * Author: SeongJae Park + */ + +#define pr_fmt(fmt) "damon: " fmt + +#include +#include +#include +#include + +static DEFINE_MUTEX(damon_lock); +static int nr_running_ctxs; + +struct damon_ctx *damon_new_ctx(void) +{ + struct damon_ctx *ctx; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return NULL; + + ctx->sample_interval = 5 * 1000; + ctx->aggr_interval = 100 * 1000; + ctx->primitive_update_interval = 60 * 1000 * 1000; + + ktime_get_coarse_ts64(&ctx->last_aggregation); + ctx->last_primitive_update = ctx->last_aggregation; + + mutex_init(&ctx->kdamond_lock); + + ctx->target = NULL; + + return ctx; +} + +void damon_destroy_ctx(struct damon_ctx *ctx) +{ + if (ctx->primitive.cleanup) + ctx->primitive.cleanup(ctx); + kfree(ctx); +} + +/** + * damon_set_attrs() - Set attributes for the monitoring. + * @ctx: monitoring context + * @sample_int: time interval between samplings + * @aggr_int: time interval between aggregations + * @primitive_upd_int: time interval between monitoring primitive updates + * + * This function should not be called while the kdamond is running. + * Every time interval is in micro-seconds. + * + * Return: 0 on success, negative error code otherwise. + */ +int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, + unsigned long aggr_int, unsigned long primitive_upd_int) +{ + ctx->sample_interval = sample_int; + ctx->aggr_interval = aggr_int; + ctx->primitive_update_interval = primitive_upd_int; + + return 0; +} + +static bool damon_kdamond_running(struct damon_ctx *ctx) +{ + bool running; + + mutex_lock(&ctx->kdamond_lock); + running = ctx->kdamond != NULL; + mutex_unlock(&ctx->kdamond_lock); + + return running; +} + +static int kdamond_fn(void *data); + +/* + * __damon_start() - Starts monitoring with given context. + * @ctx: monitoring context + * + * This function should be called while damon_lock is hold. + * + * Return: 0 on success, negative error code otherwise. + */ +static int __damon_start(struct damon_ctx *ctx) +{ + int err = -EBUSY; + + mutex_lock(&ctx->kdamond_lock); + if (!ctx->kdamond) { + err = 0; + ctx->kdamond_stop = false; + ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d", + nr_running_ctxs); + if (IS_ERR(ctx->kdamond)) { + err = PTR_ERR(ctx->kdamond); + ctx->kdamond = 0; + } + } + mutex_unlock(&ctx->kdamond_lock); + + return err; +} + +/** + * damon_start() - Starts the monitorings for a given group of contexts. + * @ctxs: an array of the pointers for contexts to start monitoring + * @nr_ctxs: size of @ctxs + * + * This function starts a group of monitoring threads for a group of monitoring + * contexts. One thread per each context is created and run in parallel. The + * caller should handle synchronization between the threads by itself. If a + * group of threads that created by other 'damon_start()' call is currently + * running, this function does nothing but returns -EBUSY. + * + * Return: 0 on success, negative error code otherwise. + */ +int damon_start(struct damon_ctx **ctxs, int nr_ctxs) +{ + int i; + int err = 0; + + mutex_lock(&damon_lock); + if (nr_running_ctxs) { + mutex_unlock(&damon_lock); + return -EBUSY; + } + + for (i = 0; i < nr_ctxs; i++) { + err = __damon_start(ctxs[i]); + if (err) + break; + nr_running_ctxs++; + } + mutex_unlock(&damon_lock); + + return err; +} + +/* + * __damon_stop() - Stops monitoring of given context. + * @ctx: monitoring context + * + * Return: 0 on success, negative error code otherwise. + */ +static int __damon_stop(struct damon_ctx *ctx) +{ + mutex_lock(&ctx->kdamond_lock); + if (ctx->kdamond) { + ctx->kdamond_stop = true; + mutex_unlock(&ctx->kdamond_lock); + while (damon_kdamond_running(ctx)) + usleep_range(ctx->sample_interval, + ctx->sample_interval * 2); + return 0; + } + mutex_unlock(&ctx->kdamond_lock); + + return -EPERM; +} + +/** + * damon_stop() - Stops the monitorings for a given group of contexts. + * @ctxs: an array of the pointers for contexts to stop monitoring + * @nr_ctxs: size of @ctxs + * + * Return: 0 on success, negative error code otherwise. + */ +int damon_stop(struct damon_ctx **ctxs, int nr_ctxs) +{ + int i, err = 0; + + for (i = 0; i < nr_ctxs; i++) { + /* nr_running_ctxs is decremented in kdamond_fn */ + err = __damon_stop(ctxs[i]); + if (err) + return err; + } + + return err; +} + +/* + * damon_check_reset_time_interval() - Check if a time interval is elapsed. + * @baseline: the time to check whether the interval has elapsed since + * @interval: the time interval (microseconds) + * + * See whether the given time interval has passed since the given baseline + * time. If so, it also updates the baseline to current time for next check. + * + * Return: true if the time interval has passed, or false otherwise. + */ +static bool damon_check_reset_time_interval(struct timespec64 *baseline, + unsigned long interval) +{ + struct timespec64 now; + + ktime_get_coarse_ts64(&now); + if ((timespec64_to_ns(&now) - timespec64_to_ns(baseline)) < + interval * 1000) + return false; + *baseline = now; + return true; +} + +/* + * Check whether it is time to flush the aggregated information + */ +static bool kdamond_aggregate_interval_passed(struct damon_ctx *ctx) +{ + return damon_check_reset_time_interval(&ctx->last_aggregation, + ctx->aggr_interval); +} + +/* + * Check whether it is time to check and apply the target monitoring regions + * + * Returns true if it is. + */ +static bool kdamond_need_update_primitive(struct damon_ctx *ctx) +{ + return damon_check_reset_time_interval(&ctx->last_primitive_update, + ctx->primitive_update_interval); +} + +/* + * Check whether current monitoring should be stopped + * + * The monitoring is stopped when either the user requested to stop, or all + * monitoring targets are invalid. + * + * Returns true if need to stop current monitoring. + */ +static bool kdamond_need_stop(struct damon_ctx *ctx) +{ + bool stop; + + mutex_lock(&ctx->kdamond_lock); + stop = ctx->kdamond_stop; + mutex_unlock(&ctx->kdamond_lock); + if (stop) + return true; + + if (!ctx->primitive.target_valid) + return false; + + return !ctx->primitive.target_valid(ctx->target); +} + +static void set_kdamond_stop(struct damon_ctx *ctx) +{ + mutex_lock(&ctx->kdamond_lock); + ctx->kdamond_stop = true; + mutex_unlock(&ctx->kdamond_lock); +} + +/* + * The monitoring daemon that runs as a kernel thread + */ +static int kdamond_fn(void *data) +{ + struct damon_ctx *ctx = (struct damon_ctx *)data; + + mutex_lock(&ctx->kdamond_lock); + pr_info("kdamond (%d) starts\n", ctx->kdamond->pid); + mutex_unlock(&ctx->kdamond_lock); + + if (ctx->primitive.init) + ctx->primitive.init(ctx); + if (ctx->callback.before_start && ctx->callback.before_start(ctx)) + set_kdamond_stop(ctx); + + while (!kdamond_need_stop(ctx)) { + if (ctx->primitive.prepare_access_checks) + ctx->primitive.prepare_access_checks(ctx); + if (ctx->callback.after_sampling && + ctx->callback.after_sampling(ctx)) + set_kdamond_stop(ctx); + + usleep_range(ctx->sample_interval, ctx->sample_interval + 1); + + if (ctx->primitive.check_accesses) + ctx->primitive.check_accesses(ctx); + + if (kdamond_aggregate_interval_passed(ctx)) { + if (ctx->callback.after_aggregation && + ctx->callback.after_aggregation(ctx)) + set_kdamond_stop(ctx); + if (ctx->primitive.reset_aggregated) + ctx->primitive.reset_aggregated(ctx); + } + + if (kdamond_need_update_primitive(ctx)) { + if (ctx->primitive.update) + ctx->primitive.update(ctx); + } + } + + if (ctx->callback.before_terminate && + ctx->callback.before_terminate(ctx)) + set_kdamond_stop(ctx); + if (ctx->primitive.cleanup) + ctx->primitive.cleanup(ctx); + + pr_debug("kdamond (%d) finishes\n", ctx->kdamond->pid); + mutex_lock(&ctx->kdamond_lock); + ctx->kdamond = NULL; + mutex_unlock(&ctx->kdamond_lock); + + mutex_lock(&damon_lock); + nr_running_ctxs--; + mutex_unlock(&damon_lock); + + do_exit(0); +} -- cgit v1.2.3 From f23b8eee1871a6db5c37f90831147de5426c40b7 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 7 Sep 2021 19:56:32 -0700 Subject: mm/damon/core: implement region-based sampling To avoid the unbounded increase of the overhead, DAMON groups adjacent pages that are assumed to have the same access frequencies into a region. As long as the assumption (pages in a region have the same access frequencies) is kept, only one page in the region is required to be checked. Thus, for each ``sampling interval``, 1. the 'prepare_access_checks' primitive picks one page in each region, 2. waits for one ``sampling interval``, 3. checks whether the page is accessed meanwhile, and 4. increases the access count of the region if so. Therefore, the monitoring overhead is controllable by adjusting the number of regions. DAMON allows both the underlying primitives and user callbacks to adjust regions for the trade-off. In other words, this commit makes DAMON to use not only time-based sampling but also space-based sampling. This scheme, however, cannot preserve the quality of the output if the assumption is not guaranteed. Next commit will address this problem. Link: https://lkml.kernel.org/r/20210716081449.22187-3-sj38.park@gmail.com Signed-off-by: SeongJae Park Reviewed-by: Leonard Foerster Reviewed-by: Fernand Sieber Acked-by: Shakeel Butt Cc: Alexander Shishkin Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Fan Du Cc: Greg Kroah-Hartman Cc: Greg Thelen Cc: Ingo Molnar Cc: Joe Perches Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Marco Elver Cc: Markus Boehme Cc: Maximilian Heyne Cc: Mel Gorman Cc: Minchan Kim Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Rik van Riel Cc: Shuah Khan Cc: Steven Rostedt (VMware) Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 77 +++++++++++++++++++++++++-- mm/damon/core.c | 143 ++++++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 213 insertions(+), 7 deletions(-) (limited to 'mm') diff --git a/include/linux/damon.h b/include/linux/damon.h index 2f652602b1ea..67db309ad61b 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -12,6 +12,48 @@ #include #include +/** + * struct damon_addr_range - Represents an address region of [@start, @end). + * @start: Start address of the region (inclusive). + * @end: End address of the region (exclusive). + */ +struct damon_addr_range { + unsigned long start; + unsigned long end; +}; + +/** + * struct damon_region - Represents a monitoring target region. + * @ar: The address range of the region. + * @sampling_addr: Address of the sample for the next access check. + * @nr_accesses: Access frequency of this region. + * @list: List head for siblings. + */ +struct damon_region { + struct damon_addr_range ar; + unsigned long sampling_addr; + unsigned int nr_accesses; + struct list_head list; +}; + +/** + * struct damon_target - Represents a monitoring target. + * @id: Unique identifier for this target. + * @regions_list: Head of the monitoring target regions of this target. + * @list: List head for siblings. + * + * Each monitoring context could have multiple targets. For example, a context + * for virtual memory address spaces could have multiple target processes. The + * @id of each target should be unique among the targets of the context. For + * example, in the virtual address monitoring context, it could be a pidfd or + * an address of an mm_struct. + */ +struct damon_target { + unsigned long id; + struct list_head regions_list; + struct list_head list; +}; + struct damon_ctx; /** @@ -36,7 +78,7 @@ struct damon_ctx; * * @init should initialize primitive-internal data structures. For example, * this could be used to construct proper monitoring target regions and link - * those to @damon_ctx.target. + * those to @damon_ctx.adaptive_targets. * @update should update the primitive-internal data structures. For example, * this could be used to update monitoring target regions for current status. * @prepare_access_checks should manipulate the monitoring regions to be @@ -130,7 +172,7 @@ struct damon_callback { * @primitive: Set of monitoring primitives for given use cases. * @callback: Set of callbacks for monitoring events notifications. * - * @target: Pointer to the user-defined monitoring target. + * @region_targets: Head of monitoring targets (&damon_target) list. */ struct damon_ctx { unsigned long sample_interval; @@ -149,11 +191,40 @@ struct damon_ctx { struct damon_primitive primitive; struct damon_callback callback; - void *target; + struct list_head region_targets; }; +#define damon_next_region(r) \ + (container_of(r->list.next, struct damon_region, list)) + +#define damon_prev_region(r) \ + (container_of(r->list.prev, struct damon_region, list)) + +#define damon_for_each_region(r, t) \ + list_for_each_entry(r, &t->regions_list, list) + +#define damon_for_each_region_safe(r, next, t) \ + list_for_each_entry_safe(r, next, &t->regions_list, list) + +#define damon_for_each_target(t, ctx) \ + list_for_each_entry(t, &(ctx)->region_targets, list) + +#define damon_for_each_target_safe(t, next, ctx) \ + list_for_each_entry_safe(t, next, &(ctx)->region_targets, list) + #ifdef CONFIG_DAMON +struct damon_region *damon_new_region(unsigned long start, unsigned long end); +inline void damon_insert_region(struct damon_region *r, + struct damon_region *prev, struct damon_region *next); +void damon_add_region(struct damon_region *r, struct damon_target *t); +void damon_destroy_region(struct damon_region *r); + +struct damon_target *damon_new_target(unsigned long id); +void damon_add_target(struct damon_ctx *ctx, struct damon_target *t); +void damon_free_target(struct damon_target *t); +void damon_destroy_target(struct damon_target *t); + struct damon_ctx *damon_new_ctx(void); void damon_destroy_ctx(struct damon_ctx *ctx); int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, diff --git a/mm/damon/core.c b/mm/damon/core.c index 651590bf49b1..947486a150ce 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -15,6 +15,101 @@ static DEFINE_MUTEX(damon_lock); static int nr_running_ctxs; +/* + * Construct a damon_region struct + * + * Returns the pointer to the new struct if success, or NULL otherwise + */ +struct damon_region *damon_new_region(unsigned long start, unsigned long end) +{ + struct damon_region *region; + + region = kmalloc(sizeof(*region), GFP_KERNEL); + if (!region) + return NULL; + + region->ar.start = start; + region->ar.end = end; + region->nr_accesses = 0; + INIT_LIST_HEAD(®ion->list); + + return region; +} + +/* + * Add a region between two other regions + */ +inline void damon_insert_region(struct damon_region *r, + struct damon_region *prev, struct damon_region *next) +{ + __list_add(&r->list, &prev->list, &next->list); +} + +void damon_add_region(struct damon_region *r, struct damon_target *t) +{ + list_add_tail(&r->list, &t->regions_list); +} + +static void damon_del_region(struct damon_region *r) +{ + list_del(&r->list); +} + +static void damon_free_region(struct damon_region *r) +{ + kfree(r); +} + +void damon_destroy_region(struct damon_region *r) +{ + damon_del_region(r); + damon_free_region(r); +} + +/* + * Construct a damon_target struct + * + * Returns the pointer to the new struct if success, or NULL otherwise + */ +struct damon_target *damon_new_target(unsigned long id) +{ + struct damon_target *t; + + t = kmalloc(sizeof(*t), GFP_KERNEL); + if (!t) + return NULL; + + t->id = id; + INIT_LIST_HEAD(&t->regions_list); + + return t; +} + +void damon_add_target(struct damon_ctx *ctx, struct damon_target *t) +{ + list_add_tail(&t->list, &ctx->region_targets); +} + +static void damon_del_target(struct damon_target *t) +{ + list_del(&t->list); +} + +void damon_free_target(struct damon_target *t) +{ + struct damon_region *r, *next; + + damon_for_each_region_safe(r, next, t) + damon_free_region(r); + kfree(t); +} + +void damon_destroy_target(struct damon_target *t) +{ + damon_del_target(t); + damon_free_target(t); +} + struct damon_ctx *damon_new_ctx(void) { struct damon_ctx *ctx; @@ -32,15 +127,27 @@ struct damon_ctx *damon_new_ctx(void) mutex_init(&ctx->kdamond_lock); - ctx->target = NULL; + INIT_LIST_HEAD(&ctx->region_targets); return ctx; } -void damon_destroy_ctx(struct damon_ctx *ctx) +static void damon_destroy_targets(struct damon_ctx *ctx) { - if (ctx->primitive.cleanup) + struct damon_target *t, *next_t; + + if (ctx->primitive.cleanup) { ctx->primitive.cleanup(ctx); + return; + } + + damon_for_each_target_safe(t, next_t, ctx) + damon_destroy_target(t); +} + +void damon_destroy_ctx(struct damon_ctx *ctx) +{ + damon_destroy_targets(ctx); kfree(ctx); } @@ -217,6 +324,21 @@ static bool kdamond_aggregate_interval_passed(struct damon_ctx *ctx) ctx->aggr_interval); } +/* + * Reset the aggregated monitoring results ('nr_accesses' of each region). + */ +static void kdamond_reset_aggregated(struct damon_ctx *c) +{ + struct damon_target *t; + + damon_for_each_target(t, c) { + struct damon_region *r; + + damon_for_each_region(r, t) + r->nr_accesses = 0; + } +} + /* * Check whether it is time to check and apply the target monitoring regions * @@ -238,6 +360,7 @@ static bool kdamond_need_update_primitive(struct damon_ctx *ctx) */ static bool kdamond_need_stop(struct damon_ctx *ctx) { + struct damon_target *t; bool stop; mutex_lock(&ctx->kdamond_lock); @@ -249,7 +372,12 @@ static bool kdamond_need_stop(struct damon_ctx *ctx) if (!ctx->primitive.target_valid) return false; - return !ctx->primitive.target_valid(ctx->target); + damon_for_each_target(t, ctx) { + if (ctx->primitive.target_valid(t)) + return false; + } + + return true; } static void set_kdamond_stop(struct damon_ctx *ctx) @@ -265,6 +393,8 @@ static void set_kdamond_stop(struct damon_ctx *ctx) static int kdamond_fn(void *data) { struct damon_ctx *ctx = (struct damon_ctx *)data; + struct damon_target *t; + struct damon_region *r, *next; mutex_lock(&ctx->kdamond_lock); pr_info("kdamond (%d) starts\n", ctx->kdamond->pid); @@ -291,6 +421,7 @@ static int kdamond_fn(void *data) if (ctx->callback.after_aggregation && ctx->callback.after_aggregation(ctx)) set_kdamond_stop(ctx); + kdamond_reset_aggregated(ctx); if (ctx->primitive.reset_aggregated) ctx->primitive.reset_aggregated(ctx); } @@ -300,6 +431,10 @@ static int kdamond_fn(void *data) ctx->primitive.update(ctx); } } + damon_for_each_target(t, ctx) { + damon_for_each_region_safe(r, next, t) + damon_destroy_region(r); + } if (ctx->callback.before_terminate && ctx->callback.before_terminate(ctx)) -- cgit v1.2.3 From b9a6ac4e4ede4172d165c133398b93e3233b0ba7 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 7 Sep 2021 19:56:36 -0700 Subject: mm/damon: adaptively adjust regions Even somehow the initial monitoring target regions are well constructed to fulfill the assumption (pages in same region have similar access frequencies), the data access pattern can be dynamically changed. This will result in low monitoring quality. To keep the assumption as much as possible, DAMON adaptively merges and splits each region based on their access frequency. For each ``aggregation interval``, it compares the access frequencies of adjacent regions and merges those if the frequency difference is small. Then, after it reports and clears the aggregated access frequency of each region, it splits each region into two or three regions if the total number of regions will not exceed the user-specified maximum number of regions after the split. In this way, DAMON provides its best-effort quality and minimal overhead while keeping the upper-bound overhead that users set. Link: https://lkml.kernel.org/r/20210716081449.22187-4-sj38.park@gmail.com Signed-off-by: SeongJae Park Reviewed-by: Leonard Foerster Reviewed-by: Fernand Sieber Acked-by: Shakeel Butt Cc: Alexander Shishkin Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Fan Du Cc: Greg Kroah-Hartman Cc: Greg Thelen Cc: Ingo Molnar Cc: Joe Perches Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Marco Elver Cc: Markus Boehme Cc: Maximilian Heyne Cc: Mel Gorman Cc: Minchan Kim Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Rik van Riel Cc: Shuah Khan Cc: Steven Rostedt (VMware) Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 30 +++++-- mm/damon/core.c | 224 ++++++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 237 insertions(+), 17 deletions(-) (limited to 'mm') diff --git a/include/linux/damon.h b/include/linux/damon.h index 67db309ad61b..ce2a84b26cd7 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -12,6 +12,9 @@ #include #include +/* Minimal region size. Every damon_region is aligned by this. */ +#define DAMON_MIN_REGION PAGE_SIZE + /** * struct damon_addr_range - Represents an address region of [@start, @end). * @start: Start address of the region (inclusive). @@ -39,6 +42,7 @@ struct damon_region { /** * struct damon_target - Represents a monitoring target. * @id: Unique identifier for this target. + * @nr_regions: Number of monitoring target regions of this target. * @regions_list: Head of the monitoring target regions of this target. * @list: List head for siblings. * @@ -50,6 +54,7 @@ struct damon_region { */ struct damon_target { unsigned long id; + unsigned int nr_regions; struct list_head regions_list; struct list_head list; }; @@ -85,6 +90,8 @@ struct damon_ctx; * prepared for the next access check. * @check_accesses should check the accesses to each region that made after the * last preparation and update the number of observed accesses of each region. + * It should also return max number of observed accesses that made as a result + * of its update. The value will be used for regions adjustment threshold. * @reset_aggregated should reset the access monitoring results that aggregated * by @check_accesses. * @target_valid should check whether the target is still valid for the @@ -95,7 +102,7 @@ struct damon_primitive { void (*init)(struct damon_ctx *context); void (*update)(struct damon_ctx *context); void (*prepare_access_checks)(struct damon_ctx *context); - void (*check_accesses)(struct damon_ctx *context); + unsigned int (*check_accesses)(struct damon_ctx *context); void (*reset_aggregated)(struct damon_ctx *context); bool (*target_valid)(void *target); void (*cleanup)(struct damon_ctx *context); @@ -172,7 +179,9 @@ struct damon_callback { * @primitive: Set of monitoring primitives for given use cases. * @callback: Set of callbacks for monitoring events notifications. * - * @region_targets: Head of monitoring targets (&damon_target) list. + * @min_nr_regions: The minimum number of adaptive monitoring regions. + * @max_nr_regions: The maximum number of adaptive monitoring regions. + * @adaptive_targets: Head of monitoring targets (&damon_target) list. */ struct damon_ctx { unsigned long sample_interval; @@ -191,7 +200,9 @@ struct damon_ctx { struct damon_primitive primitive; struct damon_callback callback; - struct list_head region_targets; + unsigned long min_nr_regions; + unsigned long max_nr_regions; + struct list_head adaptive_targets; }; #define damon_next_region(r) \ @@ -207,28 +218,31 @@ struct damon_ctx { list_for_each_entry_safe(r, next, &t->regions_list, list) #define damon_for_each_target(t, ctx) \ - list_for_each_entry(t, &(ctx)->region_targets, list) + list_for_each_entry(t, &(ctx)->adaptive_targets, list) #define damon_for_each_target_safe(t, next, ctx) \ - list_for_each_entry_safe(t, next, &(ctx)->region_targets, list) + list_for_each_entry_safe(t, next, &(ctx)->adaptive_targets, list) #ifdef CONFIG_DAMON struct damon_region *damon_new_region(unsigned long start, unsigned long end); inline void damon_insert_region(struct damon_region *r, - struct damon_region *prev, struct damon_region *next); + struct damon_region *prev, struct damon_region *next, + struct damon_target *t); void damon_add_region(struct damon_region *r, struct damon_target *t); -void damon_destroy_region(struct damon_region *r); +void damon_destroy_region(struct damon_region *r, struct damon_target *t); struct damon_target *damon_new_target(unsigned long id); void damon_add_target(struct damon_ctx *ctx, struct damon_target *t); void damon_free_target(struct damon_target *t); void damon_destroy_target(struct damon_target *t); +unsigned int damon_nr_regions(struct damon_target *t); struct damon_ctx *damon_new_ctx(void); void damon_destroy_ctx(struct damon_ctx *ctx); int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, - unsigned long aggr_int, unsigned long primitive_upd_int); + unsigned long aggr_int, unsigned long primitive_upd_int, + unsigned long min_nr_reg, unsigned long max_nr_reg); int damon_start(struct damon_ctx **ctxs, int nr_ctxs); int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); diff --git a/mm/damon/core.c b/mm/damon/core.c index 947486a150ce..28a2c78914fa 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -10,8 +10,12 @@ #include #include #include +#include #include +/* Get a random number in [l, r) */ +#define damon_rand(l, r) (l + prandom_u32_max(r - l)) + static DEFINE_MUTEX(damon_lock); static int nr_running_ctxs; @@ -40,19 +44,23 @@ struct damon_region *damon_new_region(unsigned long start, unsigned long end) * Add a region between two other regions */ inline void damon_insert_region(struct damon_region *r, - struct damon_region *prev, struct damon_region *next) + struct damon_region *prev, struct damon_region *next, + struct damon_target *t) { __list_add(&r->list, &prev->list, &next->list); + t->nr_regions++; } void damon_add_region(struct damon_region *r, struct damon_target *t) { list_add_tail(&r->list, &t->regions_list); + t->nr_regions++; } -static void damon_del_region(struct damon_region *r) +static void damon_del_region(struct damon_region *r, struct damon_target *t) { list_del(&r->list); + t->nr_regions--; } static void damon_free_region(struct damon_region *r) @@ -60,9 +68,9 @@ static void damon_free_region(struct damon_region *r) kfree(r); } -void damon_destroy_region(struct damon_region *r) +void damon_destroy_region(struct damon_region *r, struct damon_target *t) { - damon_del_region(r); + damon_del_region(r, t); damon_free_region(r); } @@ -80,6 +88,7 @@ struct damon_target *damon_new_target(unsigned long id) return NULL; t->id = id; + t->nr_regions = 0; INIT_LIST_HEAD(&t->regions_list); return t; @@ -87,7 +96,7 @@ struct damon_target *damon_new_target(unsigned long id) void damon_add_target(struct damon_ctx *ctx, struct damon_target *t) { - list_add_tail(&t->list, &ctx->region_targets); + list_add_tail(&t->list, &ctx->adaptive_targets); } static void damon_del_target(struct damon_target *t) @@ -110,6 +119,11 @@ void damon_destroy_target(struct damon_target *t) damon_free_target(t); } +unsigned int damon_nr_regions(struct damon_target *t) +{ + return t->nr_regions; +} + struct damon_ctx *damon_new_ctx(void) { struct damon_ctx *ctx; @@ -127,7 +141,10 @@ struct damon_ctx *damon_new_ctx(void) mutex_init(&ctx->kdamond_lock); - INIT_LIST_HEAD(&ctx->region_targets); + ctx->min_nr_regions = 10; + ctx->max_nr_regions = 1000; + + INIT_LIST_HEAD(&ctx->adaptive_targets); return ctx; } @@ -157,6 +174,8 @@ void damon_destroy_ctx(struct damon_ctx *ctx) * @sample_int: time interval between samplings * @aggr_int: time interval between aggregations * @primitive_upd_int: time interval between monitoring primitive updates + * @min_nr_reg: minimal number of regions + * @max_nr_reg: maximum number of regions * * This function should not be called while the kdamond is running. * Every time interval is in micro-seconds. @@ -164,15 +183,49 @@ void damon_destroy_ctx(struct damon_ctx *ctx) * Return: 0 on success, negative error code otherwise. */ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, - unsigned long aggr_int, unsigned long primitive_upd_int) + unsigned long aggr_int, unsigned long primitive_upd_int, + unsigned long min_nr_reg, unsigned long max_nr_reg) { + if (min_nr_reg < 3) { + pr_err("min_nr_regions (%lu) must be at least 3\n", + min_nr_reg); + return -EINVAL; + } + if (min_nr_reg > max_nr_reg) { + pr_err("invalid nr_regions. min (%lu) > max (%lu)\n", + min_nr_reg, max_nr_reg); + return -EINVAL; + } + ctx->sample_interval = sample_int; ctx->aggr_interval = aggr_int; ctx->primitive_update_interval = primitive_upd_int; + ctx->min_nr_regions = min_nr_reg; + ctx->max_nr_regions = max_nr_reg; return 0; } +/* Returns the size upper limit for each monitoring region */ +static unsigned long damon_region_sz_limit(struct damon_ctx *ctx) +{ + struct damon_target *t; + struct damon_region *r; + unsigned long sz = 0; + + damon_for_each_target(t, ctx) { + damon_for_each_region(r, t) + sz += r->ar.end - r->ar.start; + } + + if (ctx->min_nr_regions) + sz /= ctx->min_nr_regions; + if (sz < DAMON_MIN_REGION) + sz = DAMON_MIN_REGION; + + return sz; +} + static bool damon_kdamond_running(struct damon_ctx *ctx) { bool running; @@ -339,6 +392,150 @@ static void kdamond_reset_aggregated(struct damon_ctx *c) } } +#define sz_damon_region(r) (r->ar.end - r->ar.start) + +/* + * Merge two adjacent regions into one region + */ +static void damon_merge_two_regions(struct damon_target *t, + struct damon_region *l, struct damon_region *r) +{ + unsigned long sz_l = sz_damon_region(l), sz_r = sz_damon_region(r); + + l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) / + (sz_l + sz_r); + l->ar.end = r->ar.end; + damon_destroy_region(r, t); +} + +#define diff_of(a, b) (a > b ? a - b : b - a) + +/* + * Merge adjacent regions having similar access frequencies + * + * t target affected by this merge operation + * thres '->nr_accesses' diff threshold for the merge + * sz_limit size upper limit of each region + */ +static void damon_merge_regions_of(struct damon_target *t, unsigned int thres, + unsigned long sz_limit) +{ + struct damon_region *r, *prev = NULL, *next; + + damon_for_each_region_safe(r, next, t) { + if (prev && prev->ar.end == r->ar.start && + diff_of(prev->nr_accesses, r->nr_accesses) <= thres && + sz_damon_region(prev) + sz_damon_region(r) <= sz_limit) + damon_merge_two_regions(t, prev, r); + else + prev = r; + } +} + +/* + * Merge adjacent regions having similar access frequencies + * + * threshold '->nr_accesses' diff threshold for the merge + * sz_limit size upper limit of each region + * + * This function merges monitoring target regions which are adjacent and their + * access frequencies are similar. This is for minimizing the monitoring + * overhead under the dynamically changeable access pattern. If a merge was + * unnecessarily made, later 'kdamond_split_regions()' will revert it. + */ +static void kdamond_merge_regions(struct damon_ctx *c, unsigned int threshold, + unsigned long sz_limit) +{ + struct damon_target *t; + + damon_for_each_target(t, c) + damon_merge_regions_of(t, threshold, sz_limit); +} + +/* + * Split a region in two + * + * r the region to be split + * sz_r size of the first sub-region that will be made + */ +static void damon_split_region_at(struct damon_ctx *ctx, + struct damon_target *t, struct damon_region *r, + unsigned long sz_r) +{ + struct damon_region *new; + + new = damon_new_region(r->ar.start + sz_r, r->ar.end); + if (!new) + return; + + r->ar.end = new->ar.start; + + damon_insert_region(new, r, damon_next_region(r), t); +} + +/* Split every region in the given target into 'nr_subs' regions */ +static void damon_split_regions_of(struct damon_ctx *ctx, + struct damon_target *t, int nr_subs) +{ + struct damon_region *r, *next; + unsigned long sz_region, sz_sub = 0; + int i; + + damon_for_each_region_safe(r, next, t) { + sz_region = r->ar.end - r->ar.start; + + for (i = 0; i < nr_subs - 1 && + sz_region > 2 * DAMON_MIN_REGION; i++) { + /* + * Randomly select size of left sub-region to be at + * least 10 percent and at most 90% of original region + */ + sz_sub = ALIGN_DOWN(damon_rand(1, 10) * + sz_region / 10, DAMON_MIN_REGION); + /* Do not allow blank region */ + if (sz_sub == 0 || sz_sub >= sz_region) + continue; + + damon_split_region_at(ctx, t, r, sz_sub); + sz_region = sz_sub; + } + } +} + +/* + * Split every target region into randomly-sized small regions + * + * This function splits every target region into random-sized small regions if + * current total number of the regions is equal or smaller than half of the + * user-specified maximum number of regions. This is for maximizing the + * monitoring accuracy under the dynamically changeable access patterns. If a + * split was unnecessarily made, later 'kdamond_merge_regions()' will revert + * it. + */ +static void kdamond_split_regions(struct damon_ctx *ctx) +{ + struct damon_target *t; + unsigned int nr_regions = 0; + static unsigned int last_nr_regions; + int nr_subregions = 2; + + damon_for_each_target(t, ctx) + nr_regions += damon_nr_regions(t); + + if (nr_regions > ctx->max_nr_regions / 2) + return; + + /* Maybe the middle of the region has different access frequency */ + if (last_nr_regions == nr_regions && + nr_regions < ctx->max_nr_regions / 3) + nr_subregions = 3; + + damon_for_each_target(t, ctx) + damon_split_regions_of(ctx, t, nr_subregions); + + last_nr_regions = nr_regions; +} + /* * Check whether it is time to check and apply the target monitoring regions * @@ -395,6 +592,8 @@ static int kdamond_fn(void *data) struct damon_ctx *ctx = (struct damon_ctx *)data; struct damon_target *t; struct damon_region *r, *next; + unsigned int max_nr_accesses = 0; + unsigned long sz_limit = 0; mutex_lock(&ctx->kdamond_lock); pr_info("kdamond (%d) starts\n", ctx->kdamond->pid); @@ -405,6 +604,8 @@ static int kdamond_fn(void *data) if (ctx->callback.before_start && ctx->callback.before_start(ctx)) set_kdamond_stop(ctx); + sz_limit = damon_region_sz_limit(ctx); + while (!kdamond_need_stop(ctx)) { if (ctx->primitive.prepare_access_checks) ctx->primitive.prepare_access_checks(ctx); @@ -415,13 +616,17 @@ static int kdamond_fn(void *data) usleep_range(ctx->sample_interval, ctx->sample_interval + 1); if (ctx->primitive.check_accesses) - ctx->primitive.check_accesses(ctx); + max_nr_accesses = ctx->primitive.check_accesses(ctx); if (kdamond_aggregate_interval_passed(ctx)) { + kdamond_merge_regions(ctx, + max_nr_accesses / 10, + sz_limit); if (ctx->callback.after_aggregation && ctx->callback.after_aggregation(ctx)) set_kdamond_stop(ctx); kdamond_reset_aggregated(ctx); + kdamond_split_regions(ctx); if (ctx->primitive.reset_aggregated) ctx->primitive.reset_aggregated(ctx); } @@ -429,11 +634,12 @@ static int kdamond_fn(void *data) if (kdamond_need_update_primitive(ctx)) { if (ctx->primitive.update) ctx->primitive.update(ctx); + sz_limit = damon_region_sz_limit(ctx); } } damon_for_each_target(t, ctx) { damon_for_each_region_safe(r, next, t) - damon_destroy_region(r); + damon_destroy_region(r, t); } if (ctx->callback.before_terminate && -- cgit v1.2.3 From 1c676e0d9b1a59b98885b24a0e16a81fe4cc8301 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 7 Sep 2021 19:56:40 -0700 Subject: mm/idle_page_tracking: make PG_idle reusable PG_idle and PG_young allow the two PTE Accessed bit users, Idle Page Tracking and the reclaim logic concurrently work while not interfering with each other. That is, when they need to clear the Accessed bit, they set PG_young to represent the previous state of the bit, respectively. And when they need to read the bit, if the bit is cleared, they further read the PG_young to know whether the other has cleared the bit meanwhile or not. For yet another user of the PTE Accessed bit, we could add another page flag, or extend the mechanism to use the flags. For the DAMON usecase, however, we don't need to do that just yet. IDLE_PAGE_TRACKING and DAMON are mutually exclusive, so there's only ever going to be one user of the current set of flags. In this commit, we split out the CONFIG options to allow for the use of PG_young and PG_idle outside of idle page tracking. In the next commit, DAMON's reference implementation of the virtual memory address space monitoring primitives will use it. [sjpark@amazon.de: set PAGE_EXTENSION for non-64BIT] Link: https://lkml.kernel.org/r/20210806095153.6444-1-sj38.park@gmail.com [akpm@linux-foundation.org: tweak Kconfig text] [sjpark@amazon.de: hide PAGE_IDLE_FLAG from users] Link: https://lkml.kernel.org/r/20210813081238.34705-1-sj38.park@gmail.com Link: https://lkml.kernel.org/r/20210716081449.22187-5-sj38.park@gmail.com Signed-off-by: SeongJae Park Reviewed-by: Shakeel Butt Reviewed-by: Fernand Sieber Cc: Alexander Shishkin Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Fan Du Cc: Greg Kroah-Hartman Cc: Greg Thelen Cc: Ingo Molnar Cc: Joe Perches Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Maximilian Heyne Cc: Mel Gorman Cc: Minchan Kim Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Rik van Riel Cc: Shuah Khan Cc: Steven Rostedt (VMware) Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 4 ++-- include/linux/page_ext.h | 2 +- include/linux/page_idle.h | 6 +++--- include/trace/events/mmflags.h | 2 +- mm/Kconfig | 10 +++++++++- mm/page_ext.c | 12 +++++++++++- mm/page_idle.c | 10 ---------- 7 files changed, 27 insertions(+), 19 deletions(-) (limited to 'mm') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 6b8d66965145..0a51dd1bb6b1 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -131,7 +131,7 @@ enum pageflags { #ifdef CONFIG_MEMORY_FAILURE PG_hwpoison, /* hardware poisoned page. Don't touch */ #endif -#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) +#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT) PG_young, PG_idle, #endif @@ -441,7 +441,7 @@ PAGEFLAG_FALSE(HWPoison) #define __PG_HWPOISON 0 #endif -#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) +#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT) TESTPAGEFLAG(Young, young, PF_ANY) SETPAGEFLAG(Young, young, PF_ANY) TESTCLEARFLAG(Young, young, PF_ANY) diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index aff81ba31bd8..fabb2e1e087f 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -19,7 +19,7 @@ struct page_ext_operations { enum page_ext_flags { PAGE_EXT_OWNER, PAGE_EXT_OWNER_ALLOCATED, -#if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT) +#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) PAGE_EXT_YOUNG, PAGE_EXT_IDLE, #endif diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h index 1e894d34bdce..d8a6aecf99cb 100644 --- a/include/linux/page_idle.h +++ b/include/linux/page_idle.h @@ -6,7 +6,7 @@ #include #include -#ifdef CONFIG_IDLE_PAGE_TRACKING +#ifdef CONFIG_PAGE_IDLE_FLAG #ifdef CONFIG_64BIT static inline bool page_is_young(struct page *page) @@ -106,7 +106,7 @@ static inline void clear_page_idle(struct page *page) } #endif /* CONFIG_64BIT */ -#else /* !CONFIG_IDLE_PAGE_TRACKING */ +#else /* !CONFIG_PAGE_IDLE_FLAG */ static inline bool page_is_young(struct page *page) { @@ -135,6 +135,6 @@ static inline void clear_page_idle(struct page *page) { } -#endif /* CONFIG_IDLE_PAGE_TRACKING */ +#endif /* CONFIG_PAGE_IDLE_FLAG */ #endif /* _LINUX_MM_PAGE_IDLE_H */ diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index f160484afc5c..a26dbefdf294 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -75,7 +75,7 @@ #define IF_HAVE_PG_HWPOISON(flag,string) #endif -#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) +#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT) #define IF_HAVE_PG_IDLE(flag,string) ,{1UL << flag, string} #else #define IF_HAVE_PG_IDLE(flag,string) diff --git a/mm/Kconfig b/mm/Kconfig index 8459167b0294..d16ba9249bc5 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -739,10 +739,18 @@ config DEFERRED_STRUCT_PAGE_INIT lifetime of the system until these kthreads finish the initialisation. +config PAGE_IDLE_FLAG + bool + select PAGE_EXTENSION if !64BIT + help + This adds PG_idle and PG_young flags to 'struct page'. PTE Accessed + bit writers can set the state of the bit in the flags so that PTE + Accessed bit readers may avoid disturbance. + config IDLE_PAGE_TRACKING bool "Enable idle page tracking" depends on SYSFS && MMU - select PAGE_EXTENSION if !64BIT + select PAGE_IDLE_FLAG help This feature allows to estimate the amount of user pages that have not been touched during a given period of time. This information can diff --git a/mm/page_ext.c b/mm/page_ext.c index 293b2685fc48..dfb91653d359 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -58,11 +58,21 @@ * can utilize this callback to initialize the state of it correctly. */ +#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) +static bool need_page_idle(void) +{ + return true; +} +struct page_ext_operations page_idle_ops = { + .need = need_page_idle, +}; +#endif + static struct page_ext_operations *page_ext_ops[] = { #ifdef CONFIG_PAGE_OWNER &page_owner_ops, #endif -#if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT) +#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) &page_idle_ops, #endif }; diff --git a/mm/page_idle.c b/mm/page_idle.c index 64e5344a992c..edead6a8a5f9 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -207,16 +207,6 @@ static const struct attribute_group page_idle_attr_group = { .name = "page_idle", }; -#ifndef CONFIG_64BIT -static bool need_page_idle(void) -{ - return true; -} -struct page_ext_operations page_idle_ops = { - .need = need_page_idle, -}; -#endif - static int __init page_idle_init(void) { int err; -- cgit v1.2.3 From 3f49584b262cf8f42b25f4c1ad9f5bfd3bdc1bca Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 7 Sep 2021 19:56:44 -0700 Subject: mm/damon: implement primitives for the virtual memory address spaces This commit introduces a reference implementation of the address space specific low level primitives for the virtual address space, so that users of DAMON can easily monitor the data accesses on virtual address spaces of specific processes by simply configuring the implementation to be used by DAMON. The low level primitives for the fundamental access monitoring are defined in two parts: 1. Identification of the monitoring target address range for the address space. 2. Access check of specific address range in the target space. The reference implementation for the virtual address space does the works as below. PTE Accessed-bit Based Access Check ----------------------------------- The implementation uses PTE Accessed-bit for basic access checks. That is, it clears the bit for the next sampling target page and checks whether it is set again after one sampling period. This could disturb the reclaim logic. DAMON uses ``PG_idle`` and ``PG_young`` page flags to solve the conflict, as Idle page tracking does. VMA-based Target Address Range Construction ------------------------------------------- Only small parts in the super-huge virtual address space of the processes are mapped to physical memory and accessed. Thus, tracking the unmapped address regions is just wasteful. However, because DAMON can deal with some level of noise using the adaptive regions adjustment mechanism, tracking every mapping is not strictly required but could even incur a high overhead in some cases. That said, too huge unmapped areas inside the monitoring target should be removed to not take the time for the adaptive mechanism. For the reason, this implementation converts the complex mappings to three distinct regions that cover every mapped area of the address space. Also, the two gaps between the three regions are the two biggest unmapped areas in the given address space. The two biggest unmapped areas would be the gap between the heap and the uppermost mmap()-ed region, and the gap between the lowermost mmap()-ed region and the stack in most of the cases. Because these gaps are exceptionally huge in usual address spaces, excluding these will be sufficient to make a reasonable trade-off. Below shows this in detail:: (small mmap()-ed regions and munmap()-ed regions) [akpm@linux-foundation.org: mm/damon/vaddr.c needs highmem.h for kunmap_atomic()] [sjpark@amazon.de: remove unnecessary PAGE_EXTENSION setup] Link: https://lkml.kernel.org/r/20210806095153.6444-2-sj38.park@gmail.com [sjpark@amazon.de: safely walk page table] Link: https://lkml.kernel.org/r/20210831161800.29419-1-sj38.park@gmail.com Link: https://lkml.kernel.org/r/20210716081449.22187-6-sj38.park@gmail.com Signed-off-by: SeongJae Park Reviewed-by: Leonard Foerster Reviewed-by: Fernand Sieber Acked-by: Shakeel Butt Cc: Alexander Shishkin Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Fan Du Cc: Greg Kroah-Hartman Cc: Greg Thelen Cc: Ingo Molnar Cc: Joe Perches Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Marco Elver Cc: Markus Boehme Cc: Maximilian Heyne Cc: Mel Gorman Cc: Minchan Kim Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Rik van Riel Cc: Shuah Khan Cc: Steven Rostedt (VMware) Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 13 + mm/damon/Kconfig | 8 + mm/damon/Makefile | 1 + mm/damon/vaddr.c | 665 ++++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 687 insertions(+) create mode 100644 mm/damon/vaddr.c (limited to 'mm') diff --git a/include/linux/damon.h b/include/linux/damon.h index ce2a84b26cd7..edb350e52b93 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -249,4 +249,17 @@ int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); #endif /* CONFIG_DAMON */ +#ifdef CONFIG_DAMON_VADDR + +/* Monitoring primitives for virtual memory address spaces */ +void damon_va_init(struct damon_ctx *ctx); +void damon_va_update(struct damon_ctx *ctx); +void damon_va_prepare_access_checks(struct damon_ctx *ctx); +unsigned int damon_va_check_accesses(struct damon_ctx *ctx); +bool damon_va_target_valid(void *t); +void damon_va_cleanup(struct damon_ctx *ctx); +void damon_va_set_primitives(struct damon_ctx *ctx); + +#endif /* CONFIG_DAMON_VADDR */ + #endif /* _DAMON_H */ diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig index d00e99ac1a15..5cbb5db54158 100644 --- a/mm/damon/Kconfig +++ b/mm/damon/Kconfig @@ -12,4 +12,12 @@ config DAMON See https://damonitor.github.io/doc/html/latest-damon/index.html for more information. +config DAMON_VADDR + bool "Data access monitoring primitives for virtual address spaces" + depends on DAMON && MMU + select PAGE_IDLE_FLAG + help + This builds the default data access monitoring primitives for DAMON + that works for virtual address spaces. + endmenu diff --git a/mm/damon/Makefile b/mm/damon/Makefile index 4fd2edb4becf..6ebbd08aed67 100644 --- a/mm/damon/Makefile +++ b/mm/damon/Makefile @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_DAMON) := core.o +obj-$(CONFIG_DAMON_VADDR) += vaddr.o diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c new file mode 100644 index 000000000000..897aa8cf96c8 --- /dev/null +++ b/mm/damon/vaddr.c @@ -0,0 +1,665 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DAMON Primitives for Virtual Address Spaces + * + * Author: SeongJae Park + */ + +#define pr_fmt(fmt) "damon-va: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* Get a random number in [l, r) */ +#define damon_rand(l, r) (l + prandom_u32_max(r - l)) + +/* + * 't->id' should be the pointer to the relevant 'struct pid' having reference + * count. Caller must put the returned task, unless it is NULL. + */ +#define damon_get_task_struct(t) \ + (get_pid_task((struct pid *)t->id, PIDTYPE_PID)) + +/* + * Get the mm_struct of the given target + * + * Caller _must_ put the mm_struct after use, unless it is NULL. + * + * Returns the mm_struct of the target on success, NULL on failure + */ +static struct mm_struct *damon_get_mm(struct damon_target *t) +{ + struct task_struct *task; + struct mm_struct *mm; + + task = damon_get_task_struct(t); + if (!task) + return NULL; + + mm = get_task_mm(task); + put_task_struct(task); + return mm; +} + +/* + * Functions for the initial monitoring target regions construction + */ + +/* + * Size-evenly split a region into 'nr_pieces' small regions + * + * Returns 0 on success, or negative error code otherwise. + */ +static int damon_va_evenly_split_region(struct damon_target *t, + struct damon_region *r, unsigned int nr_pieces) +{ + unsigned long sz_orig, sz_piece, orig_end; + struct damon_region *n = NULL, *next; + unsigned long start; + + if (!r || !nr_pieces) + return -EINVAL; + + orig_end = r->ar.end; + sz_orig = r->ar.end - r->ar.start; + sz_piece = ALIGN_DOWN(sz_orig / nr_pieces, DAMON_MIN_REGION); + + if (!sz_piece) + return -EINVAL; + + r->ar.end = r->ar.start + sz_piece; + next = damon_next_region(r); + for (start = r->ar.end; start + sz_piece <= orig_end; + start += sz_piece) { + n = damon_new_region(start, start + sz_piece); + if (!n) + return -ENOMEM; + damon_insert_region(n, r, next, t); + r = n; + } + /* complement last region for possible rounding error */ + if (n) + n->ar.end = orig_end; + + return 0; +} + +static unsigned long sz_range(struct damon_addr_range *r) +{ + return r->end - r->start; +} + +static void swap_ranges(struct damon_addr_range *r1, + struct damon_addr_range *r2) +{ + struct damon_addr_range tmp; + + tmp = *r1; + *r1 = *r2; + *r2 = tmp; +} + +/* + * Find three regions separated by two biggest unmapped regions + * + * vma the head vma of the target address space + * regions an array of three address ranges that results will be saved + * + * This function receives an address space and finds three regions in it which + * separated by the two biggest unmapped regions in the space. Please refer to + * below comments of '__damon_va_init_regions()' function to know why this is + * necessary. + * + * Returns 0 if success, or negative error code otherwise. + */ +static int __damon_va_three_regions(struct vm_area_struct *vma, + struct damon_addr_range regions[3]) +{ + struct damon_addr_range gap = {0}, first_gap = {0}, second_gap = {0}; + struct vm_area_struct *last_vma = NULL; + unsigned long start = 0; + struct rb_root rbroot; + + /* Find two biggest gaps so that first_gap > second_gap > others */ + for (; vma; vma = vma->vm_next) { + if (!last_vma) { + start = vma->vm_start; + goto next; + } + + if (vma->rb_subtree_gap <= sz_range(&second_gap)) { + rbroot.rb_node = &vma->vm_rb; + vma = rb_entry(rb_last(&rbroot), + struct vm_area_struct, vm_rb); + goto next; + } + + gap.start = last_vma->vm_end; + gap.end = vma->vm_start; + if (sz_range(&gap) > sz_range(&second_gap)) { + swap_ranges(&gap, &second_gap); + if (sz_range(&second_gap) > sz_range(&first_gap)) + swap_ranges(&second_gap, &first_gap); + } +next: + last_vma = vma; + } + + if (!sz_range(&second_gap) || !sz_range(&first_gap)) + return -EINVAL; + + /* Sort the two biggest gaps by address */ + if (first_gap.start > second_gap.start) + swap_ranges(&first_gap, &second_gap); + + /* Store the result */ + regions[0].start = ALIGN(start, DAMON_MIN_REGION); + regions[0].end = ALIGN(first_gap.start, DAMON_MIN_REGION); + regions[1].start = ALIGN(first_gap.end, DAMON_MIN_REGION); + regions[1].end = ALIGN(second_gap.start, DAMON_MIN_REGION); + regions[2].start = ALIGN(second_gap.end, DAMON_MIN_REGION); + regions[2].end = ALIGN(last_vma->vm_end, DAMON_MIN_REGION); + + return 0; +} + +/* + * Get the three regions in the given target (task) + * + * Returns 0 on success, negative error code otherwise. + */ +static int damon_va_three_regions(struct damon_target *t, + struct damon_addr_range regions[3]) +{ + struct mm_struct *mm; + int rc; + + mm = damon_get_mm(t); + if (!mm) + return -EINVAL; + + mmap_read_lock(mm); + rc = __damon_va_three_regions(mm->mmap, regions); + mmap_read_unlock(mm); + + mmput(mm); + return rc; +} + +/* + * Initialize the monitoring target regions for the given target (task) + * + * t the given target + * + * Because only a number of small portions of the entire address space + * is actually mapped to the memory and accessed, monitoring the unmapped + * regions is wasteful. That said, because we can deal with small noises, + * tracking every mapping is not strictly required but could even incur a high + * overhead if the mapping frequently changes or the number of mappings is + * high. The adaptive regions adjustment mechanism will further help to deal + * with the noise by simply identifying the unmapped areas as a region that + * has no access. Moreover, applying the real mappings that would have many + * unmapped areas inside will make the adaptive mechanism quite complex. That + * said, too huge unmapped areas inside the monitoring target should be removed + * to not take the time for the adaptive mechanism. + * + * For the reason, we convert the complex mappings to three distinct regions + * that cover every mapped area of the address space. Also the two gaps + * between the three regions are the two biggest unmapped areas in the given + * address space. In detail, this function first identifies the start and the + * end of the mappings and the two biggest unmapped areas of the address space. + * Then, it constructs the three regions as below: + * + * [mappings[0]->start, big_two_unmapped_areas[0]->start) + * [big_two_unmapped_areas[0]->end, big_two_unmapped_areas[1]->start) + * [big_two_unmapped_areas[1]->end, mappings[nr_mappings - 1]->end) + * + * As usual memory map of processes is as below, the gap between the heap and + * the uppermost mmap()-ed region, and the gap between the lowermost mmap()-ed + * region and the stack will be two biggest unmapped regions. Because these + * gaps are exceptionally huge areas in usual address space, excluding these + * two biggest unmapped regions will be sufficient to make a trade-off. + * + * + * + * + * (other mmap()-ed regions and small unmapped regions) + * + * + * + */ +static void __damon_va_init_regions(struct damon_ctx *ctx, + struct damon_target *t) +{ + struct damon_region *r; + struct damon_addr_range regions[3]; + unsigned long sz = 0, nr_pieces; + int i; + + if (damon_va_three_regions(t, regions)) { + pr_err("Failed to get three regions of target %lu\n", t->id); + return; + } + + for (i = 0; i < 3; i++) + sz += regions[i].end - regions[i].start; + if (ctx->min_nr_regions) + sz /= ctx->min_nr_regions; + if (sz < DAMON_MIN_REGION) + sz = DAMON_MIN_REGION; + + /* Set the initial three regions of the target */ + for (i = 0; i < 3; i++) { + r = damon_new_region(regions[i].start, regions[i].end); + if (!r) { + pr_err("%d'th init region creation failed\n", i); + return; + } + damon_add_region(r, t); + + nr_pieces = (regions[i].end - regions[i].start) / sz; + damon_va_evenly_split_region(t, r, nr_pieces); + } +} + +/* Initialize '->regions_list' of every target (task) */ +void damon_va_init(struct damon_ctx *ctx) +{ + struct damon_target *t; + + damon_for_each_target(t, ctx) { + /* the user may set the target regions as they want */ + if (!damon_nr_regions(t)) + __damon_va_init_regions(ctx, t); + } +} + +/* + * Functions for the dynamic monitoring target regions update + */ + +/* + * Check whether a region is intersecting an address range + * + * Returns true if it is. + */ +static bool damon_intersect(struct damon_region *r, struct damon_addr_range *re) +{ + return !(r->ar.end <= re->start || re->end <= r->ar.start); +} + +/* + * Update damon regions for the three big regions of the given target + * + * t the given target + * bregions the three big regions of the target + */ +static void damon_va_apply_three_regions(struct damon_target *t, + struct damon_addr_range bregions[3]) +{ + struct damon_region *r, *next; + unsigned int i = 0; + + /* Remove regions which are not in the three big regions now */ + damon_for_each_region_safe(r, next, t) { + for (i = 0; i < 3; i++) { + if (damon_intersect(r, &bregions[i])) + break; + } + if (i == 3) + damon_destroy_region(r, t); + } + + /* Adjust intersecting regions to fit with the three big regions */ + for (i = 0; i < 3; i++) { + struct damon_region *first = NULL, *last; + struct damon_region *newr; + struct damon_addr_range *br; + + br = &bregions[i]; + /* Get the first and last regions which intersects with br */ + damon_for_each_region(r, t) { + if (damon_intersect(r, br)) { + if (!first) + first = r; + last = r; + } + if (r->ar.start >= br->end) + break; + } + if (!first) { + /* no damon_region intersects with this big region */ + newr = damon_new_region( + ALIGN_DOWN(br->start, + DAMON_MIN_REGION), + ALIGN(br->end, DAMON_MIN_REGION)); + if (!newr) + continue; + damon_insert_region(newr, damon_prev_region(r), r, t); + } else { + first->ar.start = ALIGN_DOWN(br->start, + DAMON_MIN_REGION); + last->ar.end = ALIGN(br->end, DAMON_MIN_REGION); + } + } +} + +/* + * Update regions for current memory mappings + */ +void damon_va_update(struct damon_ctx *ctx) +{ + struct damon_addr_range three_regions[3]; + struct damon_target *t; + + damon_for_each_target(t, ctx) { + if (damon_va_three_regions(t, three_regions)) + continue; + damon_va_apply_three_regions(t, three_regions); + } +} + +/* + * Get an online page for a pfn if it's in the LRU list. Otherwise, returns + * NULL. + * + * The body of this function is stolen from the 'page_idle_get_page()'. We + * steal rather than reuse it because the code is quite simple. + */ +static struct page *damon_get_page(unsigned long pfn) +{ + struct page *page = pfn_to_online_page(pfn); + + if (!page || !PageLRU(page) || !get_page_unless_zero(page)) + return NULL; + + if (unlikely(!PageLRU(page))) { + put_page(page); + page = NULL; + } + return page; +} + +static void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, + unsigned long addr) +{ + bool referenced = false; + struct page *page = damon_get_page(pte_pfn(*pte)); + + if (!page) + return; + + if (pte_young(*pte)) { + referenced = true; + *pte = pte_mkold(*pte); + } + +#ifdef CONFIG_MMU_NOTIFIER + if (mmu_notifier_clear_young(mm, addr, addr + PAGE_SIZE)) + referenced = true; +#endif /* CONFIG_MMU_NOTIFIER */ + + if (referenced) + set_page_young(page); + + set_page_idle(page); + put_page(page); +} + +static void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, + unsigned long addr) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + bool referenced = false; + struct page *page = damon_get_page(pmd_pfn(*pmd)); + + if (!page) + return; + + if (pmd_young(*pmd)) { + referenced = true; + *pmd = pmd_mkold(*pmd); + } + +#ifdef CONFIG_MMU_NOTIFIER + if (mmu_notifier_clear_young(mm, addr, + addr + ((1UL) << HPAGE_PMD_SHIFT))) + referenced = true; +#endif /* CONFIG_MMU_NOTIFIER */ + + if (referenced) + set_page_young(page); + + set_page_idle(page); + put_page(page); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +} + +static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pte_t *pte; + spinlock_t *ptl; + + if (pmd_huge(*pmd)) { + ptl = pmd_lock(walk->mm, pmd); + if (pmd_huge(*pmd)) { + damon_pmdp_mkold(pmd, walk->mm, addr); + spin_unlock(ptl); + return 0; + } + spin_unlock(ptl); + } + + if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) + return 0; + pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + if (!pte_present(*pte)) + goto out; + damon_ptep_mkold(pte, walk->mm, addr); +out: + pte_unmap_unlock(pte, ptl); + return 0; +} + +static struct mm_walk_ops damon_mkold_ops = { + .pmd_entry = damon_mkold_pmd_entry, +}; + +static void damon_va_mkold(struct mm_struct *mm, unsigned long addr) +{ + mmap_read_lock(mm); + walk_page_range(mm, addr, addr + 1, &damon_mkold_ops, NULL); + mmap_read_unlock(mm); +} + +/* + * Functions for the access checking of the regions + */ + +static void damon_va_prepare_access_check(struct damon_ctx *ctx, + struct mm_struct *mm, struct damon_region *r) +{ + r->sampling_addr = damon_rand(r->ar.start, r->ar.end); + + damon_va_mkold(mm, r->sampling_addr); +} + +void damon_va_prepare_access_checks(struct damon_ctx *ctx) +{ + struct damon_target *t; + struct mm_struct *mm; + struct damon_region *r; + + damon_for_each_target(t, ctx) { + mm = damon_get_mm(t); + if (!mm) + continue; + damon_for_each_region(r, t) + damon_va_prepare_access_check(ctx, mm, r); + mmput(mm); + } +} + +struct damon_young_walk_private { + unsigned long *page_sz; + bool young; +}; + +static int damon_young_pmd_entry(pmd_t *pmd, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pte_t *pte; + spinlock_t *ptl; + struct page *page; + struct damon_young_walk_private *priv = walk->private; + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (pmd_huge(*pmd)) { + ptl = pmd_lock(walk->mm, pmd); + if (!pmd_huge(*pmd)) { + spin_unlock(ptl); + goto regular_page; + } + page = damon_get_page(pmd_pfn(*pmd)); + if (!page) + goto huge_out; + if (pmd_young(*pmd) || !page_is_idle(page) || + mmu_notifier_test_young(walk->mm, + addr)) { + *priv->page_sz = ((1UL) << HPAGE_PMD_SHIFT); + priv->young = true; + } + put_page(page); +huge_out: + spin_unlock(ptl); + return 0; + } + +regular_page: +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + + if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) + return -EINVAL; + pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + if (!pte_present(*pte)) + goto out; + page = damon_get_page(pte_pfn(*pte)); + if (!page) + goto out; + if (pte_young(*pte) || !page_is_idle(page) || + mmu_notifier_test_young(walk->mm, addr)) { + *priv->page_sz = PAGE_SIZE; + priv->young = true; + } + put_page(page); +out: + pte_unmap_unlock(pte, ptl); + return 0; +} + +static struct mm_walk_ops damon_young_ops = { + .pmd_entry = damon_young_pmd_entry, +}; + +static bool damon_va_young(struct mm_struct *mm, unsigned long addr, + unsigned long *page_sz) +{ + struct damon_young_walk_private arg = { + .page_sz = page_sz, + .young = false, + }; + + mmap_read_lock(mm); + walk_page_range(mm, addr, addr + 1, &damon_young_ops, &arg); + mmap_read_unlock(mm); + return arg.young; +} + +/* + * Check whether the region was accessed after the last preparation + * + * mm 'mm_struct' for the given virtual address space + * r the region to be checked + */ +static void damon_va_check_access(struct damon_ctx *ctx, + struct mm_struct *mm, struct damon_region *r) +{ + static struct mm_struct *last_mm; + static unsigned long last_addr; + static unsigned long last_page_sz = PAGE_SIZE; + static bool last_accessed; + + /* If the region is in the last checked page, reuse the result */ + if (mm == last_mm && (ALIGN_DOWN(last_addr, last_page_sz) == + ALIGN_DOWN(r->sampling_addr, last_page_sz))) { + if (last_accessed) + r->nr_accesses++; + return; + } + + last_accessed = damon_va_young(mm, r->sampling_addr, &last_page_sz); + if (last_accessed) + r->nr_accesses++; + + last_mm = mm; + last_addr = r->sampling_addr; +} + +unsigned int damon_va_check_accesses(struct damon_ctx *ctx) +{ + struct damon_target *t; + struct mm_struct *mm; + struct damon_region *r; + unsigned int max_nr_accesses = 0; + + damon_for_each_target(t, ctx) { + mm = damon_get_mm(t); + if (!mm) + continue; + damon_for_each_region(r, t) { + damon_va_check_access(ctx, mm, r); + max_nr_accesses = max(r->nr_accesses, max_nr_accesses); + } + mmput(mm); + } + + return max_nr_accesses; +} + +/* + * Functions for the target validity check and cleanup + */ + +bool damon_va_target_valid(void *target) +{ + struct damon_target *t = target; + struct task_struct *task; + + task = damon_get_task_struct(t); + if (task) { + put_task_struct(task); + return true; + } + + return false; +} + +void damon_va_set_primitives(struct damon_ctx *ctx) +{ + ctx->primitive.init = damon_va_init; + ctx->primitive.update = damon_va_update; + ctx->primitive.prepare_access_checks = damon_va_prepare_access_checks; + ctx->primitive.check_accesses = damon_va_check_accesses; + ctx->primitive.reset_aggregated = NULL; + ctx->primitive.target_valid = damon_va_target_valid; + ctx->primitive.cleanup = NULL; +} -- cgit v1.2.3 From 2fcb93629ad8911c846cdc44521c746e53cc4e6d Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 7 Sep 2021 19:56:48 -0700 Subject: mm/damon: add a tracepoint This commit adds a tracepoint for DAMON. It traces the monitoring results of each region for each aggregation interval. Using this, DAMON can easily integrated with tracepoints supporting tools such as perf. Link: https://lkml.kernel.org/r/20210716081449.22187-7-sj38.park@gmail.com Signed-off-by: SeongJae Park Reviewed-by: Leonard Foerster Reviewed-by: Steven Rostedt (VMware) Reviewed-by: Fernand Sieber Acked-by: Shakeel Butt Cc: Alexander Shishkin Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Fan Du Cc: Greg Kroah-Hartman Cc: Greg Thelen Cc: Ingo Molnar Cc: Joe Perches Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Marco Elver Cc: Markus Boehme Cc: Maximilian Heyne Cc: Mel Gorman Cc: Minchan Kim Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Rik van Riel Cc: Shuah Khan Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/damon.h | 43 +++++++++++++++++++++++++++++++++++++++++++ mm/damon/core.c | 7 ++++++- 2 files changed, 49 insertions(+), 1 deletion(-) create mode 100644 include/trace/events/damon.h (limited to 'mm') diff --git a/include/trace/events/damon.h b/include/trace/events/damon.h new file mode 100644 index 000000000000..2f422f4f1fb9 --- /dev/null +++ b/include/trace/events/damon.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM damon + +#if !defined(_TRACE_DAMON_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_DAMON_H + +#include +#include +#include + +TRACE_EVENT(damon_aggregated, + + TP_PROTO(struct damon_target *t, struct damon_region *r, + unsigned int nr_regions), + + TP_ARGS(t, r, nr_regions), + + TP_STRUCT__entry( + __field(unsigned long, target_id) + __field(unsigned int, nr_regions) + __field(unsigned long, start) + __field(unsigned long, end) + __field(unsigned int, nr_accesses) + ), + + TP_fast_assign( + __entry->target_id = t->id; + __entry->nr_regions = nr_regions; + __entry->start = r->ar.start; + __entry->end = r->ar.end; + __entry->nr_accesses = r->nr_accesses; + ), + + TP_printk("target_id=%lu nr_regions=%u %lu-%lu: %u", + __entry->target_id, __entry->nr_regions, + __entry->start, __entry->end, __entry->nr_accesses) +); + +#endif /* _TRACE_DAMON_H */ + +/* This part must be outside protection */ +#include diff --git a/mm/damon/core.c b/mm/damon/core.c index 28a2c78914fa..ee24d64e8019 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -13,6 +13,9 @@ #include #include +#define CREATE_TRACE_POINTS +#include + /* Get a random number in [l, r) */ #define damon_rand(l, r) (l + prandom_u32_max(r - l)) @@ -387,8 +390,10 @@ static void kdamond_reset_aggregated(struct damon_ctx *c) damon_for_each_target(t, c) { struct damon_region *r; - damon_for_each_region(r, t) + damon_for_each_region(r, t) { + trace_damon_aggregated(t, r, damon_nr_regions(t)); r->nr_accesses = 0; + } } } -- cgit v1.2.3 From 4bc05954d0076655cfaf6f0135585bdc20cd6b11 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 7 Sep 2021 19:56:53 -0700 Subject: mm/damon: implement a debugfs-based user space interface DAMON is designed to be used by kernel space code such as the memory management subsystems, and therefore it provides only kernel space API. That said, letting the user space control DAMON could provide some benefits to them. For example, it will allow user space to analyze their specific workloads and make their own special optimizations. For such cases, this commit implements a simple DAMON application kernel module, namely 'damon-dbgfs', which merely wraps the DAMON api and exports those to the user space via the debugfs. 'damon-dbgfs' exports three files, ``attrs``, ``target_ids``, and ``monitor_on`` under its debugfs directory, ``/damon/``. Attributes ---------- Users can read and write the ``sampling interval``, ``aggregation interval``, ``regions update interval``, and min/max number of monitoring target regions by reading from and writing to the ``attrs`` file. For example, below commands set those values to 5 ms, 100 ms, 1,000 ms, 10, 1000 and check it again:: # cd /damon # echo 5000 100000 1000000 10 1000 > attrs # cat attrs 5000 100000 1000000 10 1000 Target IDs ---------- Some types of address spaces supports multiple monitoring target. For example, the virtual memory address spaces monitoring can have multiple processes as the monitoring targets. Users can set the targets by writing relevant id values of the targets to, and get the ids of the current targets by reading from the ``target_ids`` file. In case of the virtual address spaces monitoring, the values should be pids of the monitoring target processes. For example, below commands set processes having pids 42 and 4242 as the monitoring targets and check it again:: # cd /damon # echo 42 4242 > target_ids # cat target_ids 42 4242 Note that setting the target ids doesn't start the monitoring. Turning On/Off -------------- Setting the files as described above doesn't incur effect unless you explicitly start the monitoring. You can start, stop, and check the current status of the monitoring by writing to and reading from the ``monitor_on`` file. Writing ``on`` to the file starts the monitoring of the targets with the attributes. Writing ``off`` to the file stops those. DAMON also stops if every targets are invalidated (in case of the virtual memory monitoring, target processes are invalidated when terminated). Below example commands turn on, off, and check the status of DAMON:: # cd /damon # echo on > monitor_on # echo off > monitor_on # cat monitor_on off Please note that you cannot write to the above-mentioned debugfs files while the monitoring is turned on. If you write to the files while DAMON is running, an error code such as ``-EBUSY`` will be returned. [akpm@linux-foundation.org: remove unneeded "alloc failed" printks] [akpm@linux-foundation.org: replace macro with static inline] Link: https://lkml.kernel.org/r/20210716081449.22187-8-sj38.park@gmail.com Signed-off-by: SeongJae Park Reviewed-by: Leonard Foerster Reviewed-by: Fernand Sieber Cc: Alexander Shishkin Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Fan Du Cc: Greg Kroah-Hartman Cc: Greg Thelen Cc: Ingo Molnar Cc: Joe Perches Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Marco Elver Cc: Markus Boehme Cc: Maximilian Heyne Cc: Mel Gorman Cc: Minchan Kim Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Rik van Riel Cc: Shakeel Butt Cc: Shuah Khan Cc: Steven Rostedt (VMware) Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 3 + mm/damon/Kconfig | 9 ++ mm/damon/Makefile | 1 + mm/damon/core.c | 47 ++++++ mm/damon/dbgfs.c | 397 ++++++++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 457 insertions(+) create mode 100644 mm/damon/dbgfs.c (limited to 'mm') diff --git a/include/linux/damon.h b/include/linux/damon.h index edb350e52b93..d68b67b8d458 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -240,9 +240,12 @@ unsigned int damon_nr_regions(struct damon_target *t); struct damon_ctx *damon_new_ctx(void); void damon_destroy_ctx(struct damon_ctx *ctx); +int damon_set_targets(struct damon_ctx *ctx, + unsigned long *ids, ssize_t nr_ids); int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, unsigned long aggr_int, unsigned long primitive_upd_int, unsigned long min_nr_reg, unsigned long max_nr_reg); +int damon_nr_running_ctxs(void); int damon_start(struct damon_ctx **ctxs, int nr_ctxs); int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig index 5cbb5db54158..c8e3dba6fb4c 100644 --- a/mm/damon/Kconfig +++ b/mm/damon/Kconfig @@ -20,4 +20,13 @@ config DAMON_VADDR This builds the default data access monitoring primitives for DAMON that works for virtual address spaces. +config DAMON_DBGFS + bool "DAMON debugfs interface" + depends on DAMON_VADDR && DEBUG_FS + help + This builds the debugfs interface for DAMON. The user space admins + can use the interface for arbitrary data access monitoring. + + If unsure, say N. + endmenu diff --git a/mm/damon/Makefile b/mm/damon/Makefile index 6ebbd08aed67..fed4be3bace3 100644 --- a/mm/damon/Makefile +++ b/mm/damon/Makefile @@ -2,3 +2,4 @@ obj-$(CONFIG_DAMON) := core.o obj-$(CONFIG_DAMON_VADDR) += vaddr.o +obj-$(CONFIG_DAMON_DBGFS) += dbgfs.o diff --git a/mm/damon/core.c b/mm/damon/core.c index ee24d64e8019..59033488402e 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -171,6 +171,39 @@ void damon_destroy_ctx(struct damon_ctx *ctx) kfree(ctx); } +/** + * damon_set_targets() - Set monitoring targets. + * @ctx: monitoring context + * @ids: array of target ids + * @nr_ids: number of entries in @ids + * + * This function should not be called while the kdamond is running. + * + * Return: 0 on success, negative error code otherwise. + */ +int damon_set_targets(struct damon_ctx *ctx, + unsigned long *ids, ssize_t nr_ids) +{ + ssize_t i; + struct damon_target *t, *next; + + damon_destroy_targets(ctx); + + for (i = 0; i < nr_ids; i++) { + t = damon_new_target(ids[i]); + if (!t) { + pr_err("Failed to alloc damon_target\n"); + /* The caller should do cleanup of the ids itself */ + damon_for_each_target_safe(t, next, ctx) + damon_destroy_target(t); + return -ENOMEM; + } + damon_add_target(ctx, t); + } + + return 0; +} + /** * damon_set_attrs() - Set attributes for the monitoring. * @ctx: monitoring context @@ -209,6 +242,20 @@ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, return 0; } +/** + * damon_nr_running_ctxs() - Return number of currently running contexts. + */ +int damon_nr_running_ctxs(void) +{ + int nr_ctxs; + + mutex_lock(&damon_lock); + nr_ctxs = nr_running_ctxs; + mutex_unlock(&damon_lock); + + return nr_ctxs; +} + /* Returns the size upper limit for each monitoring region */ static unsigned long damon_region_sz_limit(struct damon_ctx *ctx) { diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c new file mode 100644 index 000000000000..d2e0a547eb3f --- /dev/null +++ b/mm/damon/dbgfs.c @@ -0,0 +1,397 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DAMON Debugfs Interface + * + * Author: SeongJae Park + */ + +#define pr_fmt(fmt) "damon-dbgfs: " fmt + +#include +#include +#include +#include +#include +#include +#include + +static struct damon_ctx **dbgfs_ctxs; +static int dbgfs_nr_ctxs; +static struct dentry **dbgfs_dirs; + +/* + * Returns non-empty string on success, negative error code otherwise. + */ +static char *user_input_str(const char __user *buf, size_t count, loff_t *ppos) +{ + char *kbuf; + ssize_t ret; + + /* We do not accept continuous write */ + if (*ppos) + return ERR_PTR(-EINVAL); + + kbuf = kmalloc(count + 1, GFP_KERNEL); + if (!kbuf) + return ERR_PTR(-ENOMEM); + + ret = simple_write_to_buffer(kbuf, count + 1, ppos, buf, count); + if (ret != count) { + kfree(kbuf); + return ERR_PTR(-EIO); + } + kbuf[ret] = '\0'; + + return kbuf; +} + +static ssize_t dbgfs_attrs_read(struct file *file, + char __user *buf, size_t count, loff_t *ppos) +{ + struct damon_ctx *ctx = file->private_data; + char kbuf[128]; + int ret; + + mutex_lock(&ctx->kdamond_lock); + ret = scnprintf(kbuf, ARRAY_SIZE(kbuf), "%lu %lu %lu %lu %lu\n", + ctx->sample_interval, ctx->aggr_interval, + ctx->primitive_update_interval, ctx->min_nr_regions, + ctx->max_nr_regions); + mutex_unlock(&ctx->kdamond_lock); + + return simple_read_from_buffer(buf, count, ppos, kbuf, ret); +} + +static ssize_t dbgfs_attrs_write(struct file *file, + const char __user *buf, size_t count, loff_t *ppos) +{ + struct damon_ctx *ctx = file->private_data; + unsigned long s, a, r, minr, maxr; + char *kbuf; + ssize_t ret = count; + int err; + + kbuf = user_input_str(buf, count, ppos); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); + + if (sscanf(kbuf, "%lu %lu %lu %lu %lu", + &s, &a, &r, &minr, &maxr) != 5) { + ret = -EINVAL; + goto out; + } + + mutex_lock(&ctx->kdamond_lock); + if (ctx->kdamond) { + ret = -EBUSY; + goto unlock_out; + } + + err = damon_set_attrs(ctx, s, a, r, minr, maxr); + if (err) + ret = err; +unlock_out: + mutex_unlock(&ctx->kdamond_lock); +out: + kfree(kbuf); + return ret; +} + +static inline bool targetid_is_pid(const struct damon_ctx *ctx) +{ + return ctx->primitive.target_valid == damon_va_target_valid; +} + +static ssize_t sprint_target_ids(struct damon_ctx *ctx, char *buf, ssize_t len) +{ + struct damon_target *t; + unsigned long id; + int written = 0; + int rc; + + damon_for_each_target(t, ctx) { + id = t->id; + if (targetid_is_pid(ctx)) + /* Show pid numbers to debugfs users */ + id = (unsigned long)pid_vnr((struct pid *)id); + + rc = scnprintf(&buf[written], len - written, "%lu ", id); + if (!rc) + return -ENOMEM; + written += rc; + } + if (written) + written -= 1; + written += scnprintf(&buf[written], len - written, "\n"); + return written; +} + +static ssize_t dbgfs_target_ids_read(struct file *file, + char __user *buf, size_t count, loff_t *ppos) +{ + struct damon_ctx *ctx = file->private_data; + ssize_t len; + char ids_buf[320]; + + mutex_lock(&ctx->kdamond_lock); + len = sprint_target_ids(ctx, ids_buf, 320); + mutex_unlock(&ctx->kdamond_lock); + if (len < 0) + return len; + + return simple_read_from_buffer(buf, count, ppos, ids_buf, len); +} + +/* + * Converts a string into an array of unsigned long integers + * + * Returns an array of unsigned long integers if the conversion success, or + * NULL otherwise. + */ +static unsigned long *str_to_target_ids(const char *str, ssize_t len, + ssize_t *nr_ids) +{ + unsigned long *ids; + const int max_nr_ids = 32; + unsigned long id; + int pos = 0, parsed, ret; + + *nr_ids = 0; + ids = kmalloc_array(max_nr_ids, sizeof(id), GFP_KERNEL); + if (!ids) + return NULL; + while (*nr_ids < max_nr_ids && pos < len) { + ret = sscanf(&str[pos], "%lu%n", &id, &parsed); + pos += parsed; + if (ret != 1) + break; + ids[*nr_ids] = id; + *nr_ids += 1; + } + + return ids; +} + +static void dbgfs_put_pids(unsigned long *ids, int nr_ids) +{ + int i; + + for (i = 0; i < nr_ids; i++) + put_pid((struct pid *)ids[i]); +} + +static ssize_t dbgfs_target_ids_write(struct file *file, + const char __user *buf, size_t count, loff_t *ppos) +{ + struct damon_ctx *ctx = file->private_data; + char *kbuf, *nrs; + unsigned long *targets; + ssize_t nr_targets; + ssize_t ret = count; + int i; + int err; + + kbuf = user_input_str(buf, count, ppos); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); + + nrs = kbuf; + + targets = str_to_target_ids(nrs, ret, &nr_targets); + if (!targets) { + ret = -ENOMEM; + goto out; + } + + if (targetid_is_pid(ctx)) { + for (i = 0; i < nr_targets; i++) { + targets[i] = (unsigned long)find_get_pid( + (int)targets[i]); + if (!targets[i]) { + dbgfs_put_pids(targets, i); + ret = -EINVAL; + goto free_targets_out; + } + } + } + + mutex_lock(&ctx->kdamond_lock); + if (ctx->kdamond) { + if (targetid_is_pid(ctx)) + dbgfs_put_pids(targets, nr_targets); + ret = -EBUSY; + goto unlock_out; + } + + err = damon_set_targets(ctx, targets, nr_targets); + if (err) { + if (targetid_is_pid(ctx)) + dbgfs_put_pids(targets, nr_targets); + ret = err; + } + +unlock_out: + mutex_unlock(&ctx->kdamond_lock); +free_targets_out: + kfree(targets); +out: + kfree(kbuf); + return ret; +} + +static int damon_dbgfs_open(struct inode *inode, struct file *file) +{ + file->private_data = inode->i_private; + + return nonseekable_open(inode, file); +} + +static const struct file_operations attrs_fops = { + .open = damon_dbgfs_open, + .read = dbgfs_attrs_read, + .write = dbgfs_attrs_write, +}; + +static const struct file_operations target_ids_fops = { + .open = damon_dbgfs_open, + .read = dbgfs_target_ids_read, + .write = dbgfs_target_ids_write, +}; + +static void dbgfs_fill_ctx_dir(struct dentry *dir, struct damon_ctx *ctx) +{ + const char * const file_names[] = {"attrs", "target_ids"}; + const struct file_operations *fops[] = {&attrs_fops, &target_ids_fops}; + int i; + + for (i = 0; i < ARRAY_SIZE(file_names); i++) + debugfs_create_file(file_names[i], 0600, dir, ctx, fops[i]); +} + +static int dbgfs_before_terminate(struct damon_ctx *ctx) +{ + struct damon_target *t, *next; + + if (!targetid_is_pid(ctx)) + return 0; + + damon_for_each_target_safe(t, next, ctx) { + put_pid((struct pid *)t->id); + damon_destroy_target(t); + } + return 0; +} + +static struct damon_ctx *dbgfs_new_ctx(void) +{ + struct damon_ctx *ctx; + + ctx = damon_new_ctx(); + if (!ctx) + return NULL; + + damon_va_set_primitives(ctx); + ctx->callback.before_terminate = dbgfs_before_terminate; + return ctx; +} + +static ssize_t dbgfs_monitor_on_read(struct file *file, + char __user *buf, size_t count, loff_t *ppos) +{ + char monitor_on_buf[5]; + bool monitor_on = damon_nr_running_ctxs() != 0; + int len; + + len = scnprintf(monitor_on_buf, 5, monitor_on ? "on\n" : "off\n"); + + return simple_read_from_buffer(buf, count, ppos, monitor_on_buf, len); +} + +static ssize_t dbgfs_monitor_on_write(struct file *file, + const char __user *buf, size_t count, loff_t *ppos) +{ + ssize_t ret = count; + char *kbuf; + int err; + + kbuf = user_input_str(buf, count, ppos); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); + + /* Remove white space */ + if (sscanf(kbuf, "%s", kbuf) != 1) { + kfree(kbuf); + return -EINVAL; + } + + if (!strncmp(kbuf, "on", count)) + err = damon_start(dbgfs_ctxs, dbgfs_nr_ctxs); + else if (!strncmp(kbuf, "off", count)) + err = damon_stop(dbgfs_ctxs, dbgfs_nr_ctxs); + else + err = -EINVAL; + + if (err) + ret = err; + kfree(kbuf); + return ret; +} + +static const struct file_operations monitor_on_fops = { + .read = dbgfs_monitor_on_read, + .write = dbgfs_monitor_on_write, +}; + +static int __init __damon_dbgfs_init(void) +{ + struct dentry *dbgfs_root; + const char * const file_names[] = {"monitor_on"}; + const struct file_operations *fops[] = {&monitor_on_fops}; + int i; + + dbgfs_root = debugfs_create_dir("damon", NULL); + + for (i = 0; i < ARRAY_SIZE(file_names); i++) + debugfs_create_file(file_names[i], 0600, dbgfs_root, NULL, + fops[i]); + dbgfs_fill_ctx_dir(dbgfs_root, dbgfs_ctxs[0]); + + dbgfs_dirs = kmalloc_array(1, sizeof(dbgfs_root), GFP_KERNEL); + if (!dbgfs_dirs) { + debugfs_remove(dbgfs_root); + return -ENOMEM; + } + dbgfs_dirs[0] = dbgfs_root; + + return 0; +} + +/* + * Functions for the initialization + */ + +static int __init damon_dbgfs_init(void) +{ + int rc; + + dbgfs_ctxs = kmalloc(sizeof(*dbgfs_ctxs), GFP_KERNEL); + if (!dbgfs_ctxs) + return -ENOMEM; + dbgfs_ctxs[0] = dbgfs_new_ctx(); + if (!dbgfs_ctxs[0]) { + kfree(dbgfs_ctxs); + return -ENOMEM; + } + dbgfs_nr_ctxs = 1; + + rc = __damon_dbgfs_init(); + if (rc) { + kfree(dbgfs_ctxs[0]); + kfree(dbgfs_ctxs); + pr_err("%s: dbgfs init failed\n", __func__); + } + + return rc; +} + +module_init(damon_dbgfs_init); -- cgit v1.2.3 From 429538e85410c3ae12719ec42b89ab873ed6d47b Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 7 Sep 2021 19:56:57 -0700 Subject: mm/damon/dbgfs: export kdamond pid to the user space For CPU usage accounting, knowing pid of the monitoring thread could be helpful. For example, users could use cpuaccount cgroups with the pid. This commit therefore exports the pid of currently running monitoring thread to the user space via 'kdamond_pid' file in the debugfs directory. Link: https://lkml.kernel.org/r/20210716081449.22187-9-sj38.park@gmail.com Signed-off-by: SeongJae Park Reviewed-by: Fernand Sieber Cc: Alexander Shishkin Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Fan Du Cc: Greg Kroah-Hartman Cc: Greg Thelen Cc: Ingo Molnar Cc: Joe Perches Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Maximilian Heyne Cc: Mel Gorman Cc: Minchan Kim Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Rik van Riel Cc: Shakeel Butt Cc: Shuah Khan Cc: Steven Rostedt (VMware) Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/dbgfs.c | 37 +++++++++++++++++++++++++++++++++++-- 1 file changed, 35 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index d2e0a547eb3f..e850be4077f5 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -239,6 +239,32 @@ out: return ret; } +static ssize_t dbgfs_kdamond_pid_read(struct file *file, + char __user *buf, size_t count, loff_t *ppos) +{ + struct damon_ctx *ctx = file->private_data; + char *kbuf; + ssize_t len; + + kbuf = kmalloc(count, GFP_KERNEL); + if (!kbuf) + return -ENOMEM; + + mutex_lock(&ctx->kdamond_lock); + if (ctx->kdamond) + len = scnprintf(kbuf, count, "%d\n", ctx->kdamond->pid); + else + len = scnprintf(kbuf, count, "none\n"); + mutex_unlock(&ctx->kdamond_lock); + if (!len) + goto out; + len = simple_read_from_buffer(buf, count, ppos, kbuf, len); + +out: + kfree(kbuf); + return len; +} + static int damon_dbgfs_open(struct inode *inode, struct file *file) { file->private_data = inode->i_private; @@ -258,10 +284,17 @@ static const struct file_operations target_ids_fops = { .write = dbgfs_target_ids_write, }; +static const struct file_operations kdamond_pid_fops = { + .open = damon_dbgfs_open, + .read = dbgfs_kdamond_pid_read, +}; + static void dbgfs_fill_ctx_dir(struct dentry *dir, struct damon_ctx *ctx) { - const char * const file_names[] = {"attrs", "target_ids"}; - const struct file_operations *fops[] = {&attrs_fops, &target_ids_fops}; + const char * const file_names[] = {"attrs", "target_ids", + "kdamond_pid"}; + const struct file_operations *fops[] = {&attrs_fops, &target_ids_fops, + &kdamond_pid_fops}; int i; for (i = 0; i < ARRAY_SIZE(file_names); i++) -- cgit v1.2.3 From 75c1c2b53c78bf3b3188ebb7b3508dadbf98bba1 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 7 Sep 2021 19:57:01 -0700 Subject: mm/damon/dbgfs: support multiple contexts In some use cases, users would want to run multiple monitoring context. For example, if a user wants a high precision monitoring and dedicating multiple CPUs for the job is ok, because DAMON creates one monitoring thread per one context, the user can split the monitoring target regions into multiple small regions and create one context for each region. Or, someone might want to simultaneously monitor different address spaces, e.g., both virtual address space and physical address space. The DAMON's API allows such usage, but 'damon-dbgfs' does not. Therefore, only kernel space DAMON users can do multiple contexts monitoring. This commit allows the user space DAMON users to use multiple contexts monitoring by introducing two new 'damon-dbgfs' debugfs files, 'mk_context' and 'rm_context'. Users can create a new monitoring context by writing the desired name of the new context to 'mk_context'. Then, a new directory with the name and having the files for setting of the context ('attrs', 'target_ids' and 'record') will be created under the debugfs directory. Writing the name of the context to remove to 'rm_context' will remove the related context and directory. Link: https://lkml.kernel.org/r/20210716081449.22187-10-sj38.park@gmail.com Signed-off-by: SeongJae Park Reviewed-by: Fernand Sieber Cc: Alexander Shishkin Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Fan Du Cc: Greg Kroah-Hartman Cc: Greg Thelen Cc: Ingo Molnar Cc: Joe Perches Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Maximilian Heyne Cc: Mel Gorman Cc: Minchan Kim Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Rik van Riel Cc: Shakeel Butt Cc: Shuah Khan Cc: Steven Rostedt (VMware) Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/dbgfs.c | 195 ++++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 193 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index e850be4077f5..31ad550ecba2 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -18,6 +18,7 @@ static struct damon_ctx **dbgfs_ctxs; static int dbgfs_nr_ctxs; static struct dentry **dbgfs_dirs; +static DEFINE_MUTEX(damon_dbgfs_lock); /* * Returns non-empty string on success, negative error code otherwise. @@ -328,6 +329,186 @@ static struct damon_ctx *dbgfs_new_ctx(void) return ctx; } +static void dbgfs_destroy_ctx(struct damon_ctx *ctx) +{ + damon_destroy_ctx(ctx); +} + +/* + * Make a context of @name and create a debugfs directory for it. + * + * This function should be called while holding damon_dbgfs_lock. + * + * Returns 0 on success, negative error code otherwise. + */ +static int dbgfs_mk_context(char *name) +{ + struct dentry *root, **new_dirs, *new_dir; + struct damon_ctx **new_ctxs, *new_ctx; + + if (damon_nr_running_ctxs()) + return -EBUSY; + + new_ctxs = krealloc(dbgfs_ctxs, sizeof(*dbgfs_ctxs) * + (dbgfs_nr_ctxs + 1), GFP_KERNEL); + if (!new_ctxs) + return -ENOMEM; + dbgfs_ctxs = new_ctxs; + + new_dirs = krealloc(dbgfs_dirs, sizeof(*dbgfs_dirs) * + (dbgfs_nr_ctxs + 1), GFP_KERNEL); + if (!new_dirs) + return -ENOMEM; + dbgfs_dirs = new_dirs; + + root = dbgfs_dirs[0]; + if (!root) + return -ENOENT; + + new_dir = debugfs_create_dir(name, root); + dbgfs_dirs[dbgfs_nr_ctxs] = new_dir; + + new_ctx = dbgfs_new_ctx(); + if (!new_ctx) { + debugfs_remove(new_dir); + dbgfs_dirs[dbgfs_nr_ctxs] = NULL; + return -ENOMEM; + } + + dbgfs_ctxs[dbgfs_nr_ctxs] = new_ctx; + dbgfs_fill_ctx_dir(dbgfs_dirs[dbgfs_nr_ctxs], + dbgfs_ctxs[dbgfs_nr_ctxs]); + dbgfs_nr_ctxs++; + + return 0; +} + +static ssize_t dbgfs_mk_context_write(struct file *file, + const char __user *buf, size_t count, loff_t *ppos) +{ + char *kbuf; + char *ctx_name; + ssize_t ret = count; + int err; + + kbuf = user_input_str(buf, count, ppos); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); + ctx_name = kmalloc(count + 1, GFP_KERNEL); + if (!ctx_name) { + kfree(kbuf); + return -ENOMEM; + } + + /* Trim white space */ + if (sscanf(kbuf, "%s", ctx_name) != 1) { + ret = -EINVAL; + goto out; + } + + mutex_lock(&damon_dbgfs_lock); + err = dbgfs_mk_context(ctx_name); + if (err) + ret = err; + mutex_unlock(&damon_dbgfs_lock); + +out: + kfree(kbuf); + kfree(ctx_name); + return ret; +} + +/* + * Remove a context of @name and its debugfs directory. + * + * This function should be called while holding damon_dbgfs_lock. + * + * Return 0 on success, negative error code otherwise. + */ +static int dbgfs_rm_context(char *name) +{ + struct dentry *root, *dir, **new_dirs; + struct damon_ctx **new_ctxs; + int i, j; + + if (damon_nr_running_ctxs()) + return -EBUSY; + + root = dbgfs_dirs[0]; + if (!root) + return -ENOENT; + + dir = debugfs_lookup(name, root); + if (!dir) + return -ENOENT; + + new_dirs = kmalloc_array(dbgfs_nr_ctxs - 1, sizeof(*dbgfs_dirs), + GFP_KERNEL); + if (!new_dirs) + return -ENOMEM; + + new_ctxs = kmalloc_array(dbgfs_nr_ctxs - 1, sizeof(*dbgfs_ctxs), + GFP_KERNEL); + if (!new_ctxs) { + kfree(new_dirs); + return -ENOMEM; + } + + for (i = 0, j = 0; i < dbgfs_nr_ctxs; i++) { + if (dbgfs_dirs[i] == dir) { + debugfs_remove(dbgfs_dirs[i]); + dbgfs_destroy_ctx(dbgfs_ctxs[i]); + continue; + } + new_dirs[j] = dbgfs_dirs[i]; + new_ctxs[j++] = dbgfs_ctxs[i]; + } + + kfree(dbgfs_dirs); + kfree(dbgfs_ctxs); + + dbgfs_dirs = new_dirs; + dbgfs_ctxs = new_ctxs; + dbgfs_nr_ctxs--; + + return 0; +} + +static ssize_t dbgfs_rm_context_write(struct file *file, + const char __user *buf, size_t count, loff_t *ppos) +{ + char *kbuf; + ssize_t ret = count; + int err; + char *ctx_name; + + kbuf = user_input_str(buf, count, ppos); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); + ctx_name = kmalloc(count + 1, GFP_KERNEL); + if (!ctx_name) { + kfree(kbuf); + return -ENOMEM; + } + + /* Trim white space */ + if (sscanf(kbuf, "%s", ctx_name) != 1) { + ret = -EINVAL; + goto out; + } + + mutex_lock(&damon_dbgfs_lock); + err = dbgfs_rm_context(ctx_name); + if (err) + ret = err; + mutex_unlock(&damon_dbgfs_lock); + +out: + kfree(kbuf); + kfree(ctx_name); + return ret; +} + static ssize_t dbgfs_monitor_on_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -370,6 +551,14 @@ static ssize_t dbgfs_monitor_on_write(struct file *file, return ret; } +static const struct file_operations mk_contexts_fops = { + .write = dbgfs_mk_context_write, +}; + +static const struct file_operations rm_contexts_fops = { + .write = dbgfs_rm_context_write, +}; + static const struct file_operations monitor_on_fops = { .read = dbgfs_monitor_on_read, .write = dbgfs_monitor_on_write, @@ -378,8 +567,10 @@ static const struct file_operations monitor_on_fops = { static int __init __damon_dbgfs_init(void) { struct dentry *dbgfs_root; - const char * const file_names[] = {"monitor_on"}; - const struct file_operations *fops[] = {&monitor_on_fops}; + const char * const file_names[] = {"mk_contexts", "rm_contexts", + "monitor_on"}; + const struct file_operations *fops[] = {&mk_contexts_fops, + &rm_contexts_fops, &monitor_on_fops}; int i; dbgfs_root = debugfs_create_dir("damon", NULL); -- cgit v1.2.3 From 17ccae8bb5c928946f6f3af14626ec458f74e6ad Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Tue, 7 Sep 2021 19:57:09 -0700 Subject: mm/damon: add kunit tests This commit adds kunit based unit tests for the core and the virtual address spaces monitoring primitives of DAMON. Link: https://lkml.kernel.org/r/20210716081449.22187-12-sj38.park@gmail.com Signed-off-by: SeongJae Park Reviewed-by: Brendan Higgins Cc: Alexander Shishkin Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Fan Du Cc: Fernand Sieber Cc: Greg Kroah-Hartman Cc: Greg Thelen Cc: Ingo Molnar Cc: Joe Perches Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Maximilian Heyne Cc: Mel Gorman Cc: Minchan Kim Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Rik van Riel Cc: Shakeel Butt Cc: Shuah Khan Cc: Steven Rostedt (VMware) Cc: Vladimir Davydov Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/damon/Kconfig | 36 ++++++ mm/damon/core-test.h | 253 ++++++++++++++++++++++++++++++++++++++ mm/damon/core.c | 7 ++ mm/damon/dbgfs-test.h | 126 +++++++++++++++++++ mm/damon/dbgfs.c | 2 + mm/damon/vaddr-test.h | 329 ++++++++++++++++++++++++++++++++++++++++++++++++++ mm/damon/vaddr.c | 7 ++ 7 files changed, 760 insertions(+) create mode 100644 mm/damon/core-test.h create mode 100644 mm/damon/dbgfs-test.h create mode 100644 mm/damon/vaddr-test.h (limited to 'mm') diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig index c8e3dba6fb4c..37024798a97c 100644 --- a/mm/damon/Kconfig +++ b/mm/damon/Kconfig @@ -12,6 +12,18 @@ config DAMON See https://damonitor.github.io/doc/html/latest-damon/index.html for more information. +config DAMON_KUNIT_TEST + bool "Test for damon" if !KUNIT_ALL_TESTS + depends on DAMON && KUNIT=y + default KUNIT_ALL_TESTS + help + This builds the DAMON Kunit test suite. + + For more information on KUnit and unit tests in general, please refer + to the KUnit documentation. + + If unsure, say N. + config DAMON_VADDR bool "Data access monitoring primitives for virtual address spaces" depends on DAMON && MMU @@ -20,6 +32,18 @@ config DAMON_VADDR This builds the default data access monitoring primitives for DAMON that works for virtual address spaces. +config DAMON_VADDR_KUNIT_TEST + bool "Test for DAMON primitives" if !KUNIT_ALL_TESTS + depends on DAMON_VADDR && KUNIT=y + default KUNIT_ALL_TESTS + help + This builds the DAMON virtual addresses primitives Kunit test suite. + + For more information on KUnit and unit tests in general, please refer + to the KUnit documentation. + + If unsure, say N. + config DAMON_DBGFS bool "DAMON debugfs interface" depends on DAMON_VADDR && DEBUG_FS @@ -29,4 +53,16 @@ config DAMON_DBGFS If unsure, say N. +config DAMON_DBGFS_KUNIT_TEST + bool "Test for damon debugfs interface" if !KUNIT_ALL_TESTS + depends on DAMON_DBGFS && KUNIT=y + default KUNIT_ALL_TESTS + help + This builds the DAMON debugfs interface Kunit test suite. + + For more information on KUnit and unit tests in general, please refer + to the KUnit documentation. + + If unsure, say N. + endmenu diff --git a/mm/damon/core-test.h b/mm/damon/core-test.h new file mode 100644 index 000000000000..c938a9c34e6c --- /dev/null +++ b/mm/damon/core-test.h @@ -0,0 +1,253 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Data Access Monitor Unit Tests + * + * Copyright 2019 Amazon.com, Inc. or its affiliates. All rights reserved. + * + * Author: SeongJae Park + */ + +#ifdef CONFIG_DAMON_KUNIT_TEST + +#ifndef _DAMON_CORE_TEST_H +#define _DAMON_CORE_TEST_H + +#include + +static void damon_test_regions(struct kunit *test) +{ + struct damon_region *r; + struct damon_target *t; + + r = damon_new_region(1, 2); + KUNIT_EXPECT_EQ(test, 1ul, r->ar.start); + KUNIT_EXPECT_EQ(test, 2ul, r->ar.end); + KUNIT_EXPECT_EQ(test, 0u, r->nr_accesses); + + t = damon_new_target(42); + KUNIT_EXPECT_EQ(test, 0u, damon_nr_regions(t)); + + damon_add_region(r, t); + KUNIT_EXPECT_EQ(test, 1u, damon_nr_regions(t)); + + damon_del_region(r, t); + KUNIT_EXPECT_EQ(test, 0u, damon_nr_regions(t)); + + damon_free_target(t); +} + +static unsigned int nr_damon_targets(struct damon_ctx *ctx) +{ + struct damon_target *t; + unsigned int nr_targets = 0; + + damon_for_each_target(t, ctx) + nr_targets++; + + return nr_targets; +} + +static void damon_test_target(struct kunit *test) +{ + struct damon_ctx *c = damon_new_ctx(); + struct damon_target *t; + + t = damon_new_target(42); + KUNIT_EXPECT_EQ(test, 42ul, t->id); + KUNIT_EXPECT_EQ(test, 0u, nr_damon_targets(c)); + + damon_add_target(c, t); + KUNIT_EXPECT_EQ(test, 1u, nr_damon_targets(c)); + + damon_destroy_target(t); + KUNIT_EXPECT_EQ(test, 0u, nr_damon_targets(c)); + + damon_destroy_ctx(c); +} + +/* + * Test kdamond_reset_aggregated() + * + * DAMON checks access to each region and aggregates this information as the + * access frequency of each region. In detail, it increases '->nr_accesses' of + * regions that an access has confirmed. 'kdamond_reset_aggregated()' flushes + * the aggregated information ('->nr_accesses' of each regions) to the result + * buffer. As a result of the flushing, the '->nr_accesses' of regions are + * initialized to zero. + */ +static void damon_test_aggregate(struct kunit *test) +{ + struct damon_ctx *ctx = damon_new_ctx(); + unsigned long target_ids[] = {1, 2, 3}; + unsigned long saddr[][3] = {{10, 20, 30}, {5, 42, 49}, {13, 33, 55} }; + unsigned long eaddr[][3] = {{15, 27, 40}, {31, 45, 55}, {23, 44, 66} }; + unsigned long accesses[][3] = {{42, 95, 84}, {10, 20, 30}, {0, 1, 2} }; + struct damon_target *t; + struct damon_region *r; + int it, ir; + + damon_set_targets(ctx, target_ids, 3); + + it = 0; + damon_for_each_target(t, ctx) { + for (ir = 0; ir < 3; ir++) { + r = damon_new_region(saddr[it][ir], eaddr[it][ir]); + r->nr_accesses = accesses[it][ir]; + damon_add_region(r, t); + } + it++; + } + kdamond_reset_aggregated(ctx); + it = 0; + damon_for_each_target(t, ctx) { + ir = 0; + /* '->nr_accesses' should be zeroed */ + damon_for_each_region(r, t) { + KUNIT_EXPECT_EQ(test, 0u, r->nr_accesses); + ir++; + } + /* regions should be preserved */ + KUNIT_EXPECT_EQ(test, 3, ir); + it++; + } + /* targets also should be preserved */ + KUNIT_EXPECT_EQ(test, 3, it); + + damon_destroy_ctx(ctx); +} + +static void damon_test_split_at(struct kunit *test) +{ + struct damon_ctx *c = damon_new_ctx(); + struct damon_target *t; + struct damon_region *r; + + t = damon_new_target(42); + r = damon_new_region(0, 100); + damon_add_region(r, t); + damon_split_region_at(c, t, r, 25); + KUNIT_EXPECT_EQ(test, r->ar.start, 0ul); + KUNIT_EXPECT_EQ(test, r->ar.end, 25ul); + + r = damon_next_region(r); + KUNIT_EXPECT_EQ(test, r->ar.start, 25ul); + KUNIT_EXPECT_EQ(test, r->ar.end, 100ul); + + damon_free_target(t); + damon_destroy_ctx(c); +} + +static void damon_test_merge_two(struct kunit *test) +{ + struct damon_target *t; + struct damon_region *r, *r2, *r3; + int i; + + t = damon_new_target(42); + r = damon_new_region(0, 100); + r->nr_accesses = 10; + damon_add_region(r, t); + r2 = damon_new_region(100, 300); + r2->nr_accesses = 20; + damon_add_region(r2, t); + + damon_merge_two_regions(t, r, r2); + KUNIT_EXPECT_EQ(test, r->ar.start, 0ul); + KUNIT_EXPECT_EQ(test, r->ar.end, 300ul); + KUNIT_EXPECT_EQ(test, r->nr_accesses, 16u); + + i = 0; + damon_for_each_region(r3, t) { + KUNIT_EXPECT_PTR_EQ(test, r, r3); + i++; + } + KUNIT_EXPECT_EQ(test, i, 1); + + damon_free_target(t); +} + +static struct damon_region *__nth_region_of(struct damon_target *t, int idx) +{ + struct damon_region *r; + unsigned int i = 0; + + damon_for_each_region(r, t) { + if (i++ == idx) + return r; + } + + return NULL; +} + +static void damon_test_merge_regions_of(struct kunit *test) +{ + struct damon_target *t; + struct damon_region *r; + unsigned long sa[] = {0, 100, 114, 122, 130, 156, 170, 184}; + unsigned long ea[] = {100, 112, 122, 130, 156, 170, 184, 230}; + unsigned int nrs[] = {0, 0, 10, 10, 20, 30, 1, 2}; + + unsigned long saddrs[] = {0, 114, 130, 156, 170}; + unsigned long eaddrs[] = {112, 130, 156, 170, 230}; + int i; + + t = damon_new_target(42); + for (i = 0; i < ARRAY_SIZE(sa); i++) { + r = damon_new_region(sa[i], ea[i]); + r->nr_accesses = nrs[i]; + damon_add_region(r, t); + } + + damon_merge_regions_of(t, 9, 9999); + /* 0-112, 114-130, 130-156, 156-170 */ + KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 5u); + for (i = 0; i < 5; i++) { + r = __nth_region_of(t, i); + KUNIT_EXPECT_EQ(test, r->ar.start, saddrs[i]); + KUNIT_EXPECT_EQ(test, r->ar.end, eaddrs[i]); + } + damon_free_target(t); +} + +static void damon_test_split_regions_of(struct kunit *test) +{ + struct damon_ctx *c = damon_new_ctx(); + struct damon_target *t; + struct damon_region *r; + + t = damon_new_target(42); + r = damon_new_region(0, 22); + damon_add_region(r, t); + damon_split_regions_of(c, t, 2); + KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 2u); + damon_free_target(t); + + t = damon_new_target(42); + r = damon_new_region(0, 220); + damon_add_region(r, t); + damon_split_regions_of(c, t, 4); + KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 4u); + damon_free_target(t); + damon_destroy_ctx(c); +} + +static struct kunit_case damon_test_cases[] = { + KUNIT_CASE(damon_test_target), + KUNIT_CASE(damon_test_regions), + KUNIT_CASE(damon_test_aggregate), + KUNIT_CASE(damon_test_split_at), + KUNIT_CASE(damon_test_merge_two), + KUNIT_CASE(damon_test_merge_regions_of), + KUNIT_CASE(damon_test_split_regions_of), + {}, +}; + +static struct kunit_suite damon_test_suite = { + .name = "damon", + .test_cases = damon_test_cases, +}; +kunit_test_suite(damon_test_suite); + +#endif /* _DAMON_CORE_TEST_H */ + +#endif /* CONFIG_DAMON_KUNIT_TEST */ diff --git a/mm/damon/core.c b/mm/damon/core.c index 59033488402e..30e9211f494a 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -16,6 +16,11 @@ #define CREATE_TRACE_POINTS #include +#ifdef CONFIG_DAMON_KUNIT_TEST +#undef DAMON_MIN_REGION +#define DAMON_MIN_REGION 1 +#endif + /* Get a random number in [l, r) */ #define damon_rand(l, r) (l + prandom_u32_max(r - l)) @@ -711,3 +716,5 @@ static int kdamond_fn(void *data) do_exit(0); } + +#include "core-test.h" diff --git a/mm/damon/dbgfs-test.h b/mm/damon/dbgfs-test.h new file mode 100644 index 000000000000..930e83bceef0 --- /dev/null +++ b/mm/damon/dbgfs-test.h @@ -0,0 +1,126 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * DAMON Debugfs Interface Unit Tests + * + * Author: SeongJae Park + */ + +#ifdef CONFIG_DAMON_DBGFS_KUNIT_TEST + +#ifndef _DAMON_DBGFS_TEST_H +#define _DAMON_DBGFS_TEST_H + +#include + +static void damon_dbgfs_test_str_to_target_ids(struct kunit *test) +{ + char *question; + unsigned long *answers; + unsigned long expected[] = {12, 35, 46}; + ssize_t nr_integers = 0, i; + + question = "123"; + answers = str_to_target_ids(question, strnlen(question, 128), + &nr_integers); + KUNIT_EXPECT_EQ(test, (ssize_t)1, nr_integers); + KUNIT_EXPECT_EQ(test, 123ul, answers[0]); + kfree(answers); + + question = "123abc"; + answers = str_to_target_ids(question, strnlen(question, 128), + &nr_integers); + KUNIT_EXPECT_EQ(test, (ssize_t)1, nr_integers); + KUNIT_EXPECT_EQ(test, 123ul, answers[0]); + kfree(answers); + + question = "a123"; + answers = str_to_target_ids(question, strnlen(question, 128), + &nr_integers); + KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers); + kfree(answers); + + question = "12 35"; + answers = str_to_target_ids(question, strnlen(question, 128), + &nr_integers); + KUNIT_EXPECT_EQ(test, (ssize_t)2, nr_integers); + for (i = 0; i < nr_integers; i++) + KUNIT_EXPECT_EQ(test, expected[i], answers[i]); + kfree(answers); + + question = "12 35 46"; + answers = str_to_target_ids(question, strnlen(question, 128), + &nr_integers); + KUNIT_EXPECT_EQ(test, (ssize_t)3, nr_integers); + for (i = 0; i < nr_integers; i++) + KUNIT_EXPECT_EQ(test, expected[i], answers[i]); + kfree(answers); + + question = "12 35 abc 46"; + answers = str_to_target_ids(question, strnlen(question, 128), + &nr_integers); + KUNIT_EXPECT_EQ(test, (ssize_t)2, nr_integers); + for (i = 0; i < 2; i++) + KUNIT_EXPECT_EQ(test, expected[i], answers[i]); + kfree(answers); + + question = ""; + answers = str_to_target_ids(question, strnlen(question, 128), + &nr_integers); + KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers); + kfree(answers); + + question = "\n"; + answers = str_to_target_ids(question, strnlen(question, 128), + &nr_integers); + KUNIT_EXPECT_EQ(test, (ssize_t)0, nr_integers); + kfree(answers); +} + +static void damon_dbgfs_test_set_targets(struct kunit *test) +{ + struct damon_ctx *ctx = dbgfs_new_ctx(); + unsigned long ids[] = {1, 2, 3}; + char buf[64]; + + /* Make DAMON consider target id as plain number */ + ctx->primitive.target_valid = NULL; + ctx->primitive.cleanup = NULL; + + damon_set_targets(ctx, ids, 3); + sprint_target_ids(ctx, buf, 64); + KUNIT_EXPECT_STREQ(test, (char *)buf, "1 2 3\n"); + + damon_set_targets(ctx, NULL, 0); + sprint_target_ids(ctx, buf, 64); + KUNIT_EXPECT_STREQ(test, (char *)buf, "\n"); + + damon_set_targets(ctx, (unsigned long []){1, 2}, 2); + sprint_target_ids(ctx, buf, 64); + KUNIT_EXPECT_STREQ(test, (char *)buf, "1 2\n"); + + damon_set_targets(ctx, (unsigned long []){2}, 1); + sprint_target_ids(ctx, buf, 64); + KUNIT_EXPECT_STREQ(test, (char *)buf, "2\n"); + + damon_set_targets(ctx, NULL, 0); + sprint_target_ids(ctx, buf, 64); + KUNIT_EXPECT_STREQ(test, (char *)buf, "\n"); + + dbgfs_destroy_ctx(ctx); +} + +static struct kunit_case damon_test_cases[] = { + KUNIT_CASE(damon_dbgfs_test_str_to_target_ids), + KUNIT_CASE(damon_dbgfs_test_set_targets), + {}, +}; + +static struct kunit_suite damon_test_suite = { + .name = "damon-dbgfs", + .test_cases = damon_test_cases, +}; +kunit_test_suite(damon_test_suite); + +#endif /* _DAMON_TEST_H */ + +#endif /* CONFIG_DAMON_KUNIT_TEST */ diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index 31ad550ecba2..faee070977d8 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -619,3 +619,5 @@ static int __init damon_dbgfs_init(void) } module_init(damon_dbgfs_init); + +#include "dbgfs-test.h" diff --git a/mm/damon/vaddr-test.h b/mm/damon/vaddr-test.h new file mode 100644 index 000000000000..1f5c13257dba --- /dev/null +++ b/mm/damon/vaddr-test.h @@ -0,0 +1,329 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Data Access Monitor Unit Tests + * + * Copyright 2019 Amazon.com, Inc. or its affiliates. All rights reserved. + * + * Author: SeongJae Park + */ + +#ifdef CONFIG_DAMON_VADDR_KUNIT_TEST + +#ifndef _DAMON_VADDR_TEST_H +#define _DAMON_VADDR_TEST_H + +#include + +static void __link_vmas(struct vm_area_struct *vmas, ssize_t nr_vmas) +{ + int i, j; + unsigned long largest_gap, gap; + + if (!nr_vmas) + return; + + for (i = 0; i < nr_vmas - 1; i++) { + vmas[i].vm_next = &vmas[i + 1]; + + vmas[i].vm_rb.rb_left = NULL; + vmas[i].vm_rb.rb_right = &vmas[i + 1].vm_rb; + + largest_gap = 0; + for (j = i; j < nr_vmas; j++) { + if (j == 0) + continue; + gap = vmas[j].vm_start - vmas[j - 1].vm_end; + if (gap > largest_gap) + largest_gap = gap; + } + vmas[i].rb_subtree_gap = largest_gap; + } + vmas[i].vm_next = NULL; + vmas[i].vm_rb.rb_right = NULL; + vmas[i].rb_subtree_gap = 0; +} + +/* + * Test __damon_va_three_regions() function + * + * In case of virtual memory address spaces monitoring, DAMON converts the + * complex and dynamic memory mappings of each target task to three + * discontiguous regions which cover every mapped areas. However, the three + * regions should not include the two biggest unmapped areas in the original + * mapping, because the two biggest areas are normally the areas between 1) + * heap and the mmap()-ed regions, and 2) the mmap()-ed regions and stack. + * Because these two unmapped areas are very huge but obviously never accessed, + * covering the region is just a waste. + * + * '__damon_va_three_regions() receives an address space of a process. It + * first identifies the start of mappings, end of mappings, and the two biggest + * unmapped areas. After that, based on the information, it constructs the + * three regions and returns. For more detail, refer to the comment of + * 'damon_init_regions_of()' function definition in 'mm/damon.c' file. + * + * For example, suppose virtual address ranges of 10-20, 20-25, 200-210, + * 210-220, 300-305, and 307-330 (Other comments represent this mappings in + * more short form: 10-20-25, 200-210-220, 300-305, 307-330) of a process are + * mapped. To cover every mappings, the three regions should start with 10, + * and end with 305. The process also has three unmapped areas, 25-200, + * 220-300, and 305-307. Among those, 25-200 and 220-300 are the biggest two + * unmapped areas, and thus it should be converted to three regions of 10-25, + * 200-220, and 300-330. + */ +static void damon_test_three_regions_in_vmas(struct kunit *test) +{ + struct damon_addr_range regions[3] = {0,}; + /* 10-20-25, 200-210-220, 300-305, 307-330 */ + struct vm_area_struct vmas[] = { + (struct vm_area_struct) {.vm_start = 10, .vm_end = 20}, + (struct vm_area_struct) {.vm_start = 20, .vm_end = 25}, + (struct vm_area_struct) {.vm_start = 200, .vm_end = 210}, + (struct vm_area_struct) {.vm_start = 210, .vm_end = 220}, + (struct vm_area_struct) {.vm_start = 300, .vm_end = 305}, + (struct vm_area_struct) {.vm_start = 307, .vm_end = 330}, + }; + + __link_vmas(vmas, 6); + + __damon_va_three_regions(&vmas[0], regions); + + KUNIT_EXPECT_EQ(test, 10ul, regions[0].start); + KUNIT_EXPECT_EQ(test, 25ul, regions[0].end); + KUNIT_EXPECT_EQ(test, 200ul, regions[1].start); + KUNIT_EXPECT_EQ(test, 220ul, regions[1].end); + KUNIT_EXPECT_EQ(test, 300ul, regions[2].start); + KUNIT_EXPECT_EQ(test, 330ul, regions[2].end); +} + +static struct damon_region *__nth_region_of(struct damon_target *t, int idx) +{ + struct damon_region *r; + unsigned int i = 0; + + damon_for_each_region(r, t) { + if (i++ == idx) + return r; + } + + return NULL; +} + +/* + * Test 'damon_va_apply_three_regions()' + * + * test kunit object + * regions an array containing start/end addresses of current + * monitoring target regions + * nr_regions the number of the addresses in 'regions' + * three_regions The three regions that need to be applied now + * expected start/end addresses of monitoring target regions that + * 'three_regions' are applied + * nr_expected the number of addresses in 'expected' + * + * The memory mapping of the target processes changes dynamically. To follow + * the change, DAMON periodically reads the mappings, simplifies it to the + * three regions, and updates the monitoring target regions to fit in the three + * regions. The update of current target regions is the role of + * 'damon_va_apply_three_regions()'. + * + * This test passes the given target regions and the new three regions that + * need to be applied to the function and check whether it updates the regions + * as expected. + */ +static void damon_do_test_apply_three_regions(struct kunit *test, + unsigned long *regions, int nr_regions, + struct damon_addr_range *three_regions, + unsigned long *expected, int nr_expected) +{ + struct damon_ctx *ctx = damon_new_ctx(); + struct damon_target *t; + struct damon_region *r; + int i; + + t = damon_new_target(42); + for (i = 0; i < nr_regions / 2; i++) { + r = damon_new_region(regions[i * 2], regions[i * 2 + 1]); + damon_add_region(r, t); + } + damon_add_target(ctx, t); + + damon_va_apply_three_regions(t, three_regions); + + for (i = 0; i < nr_expected / 2; i++) { + r = __nth_region_of(t, i); + KUNIT_EXPECT_EQ(test, r->ar.start, expected[i * 2]); + KUNIT_EXPECT_EQ(test, r->ar.end, expected[i * 2 + 1]); + } + + damon_destroy_ctx(ctx); +} + +/* + * This function test most common case where the three big regions are only + * slightly changed. Target regions should adjust their boundary (10-20-30, + * 50-55, 70-80, 90-100) to fit with the new big regions or remove target + * regions (57-79) that now out of the three regions. + */ +static void damon_test_apply_three_regions1(struct kunit *test) +{ + /* 10-20-30, 50-55-57-59, 70-80-90-100 */ + unsigned long regions[] = {10, 20, 20, 30, 50, 55, 55, 57, 57, 59, + 70, 80, 80, 90, 90, 100}; + /* 5-27, 45-55, 73-104 */ + struct damon_addr_range new_three_regions[3] = { + (struct damon_addr_range){.start = 5, .end = 27}, + (struct damon_addr_range){.start = 45, .end = 55}, + (struct damon_addr_range){.start = 73, .end = 104} }; + /* 5-20-27, 45-55, 73-80-90-104 */ + unsigned long expected[] = {5, 20, 20, 27, 45, 55, + 73, 80, 80, 90, 90, 104}; + + damon_do_test_apply_three_regions(test, regions, ARRAY_SIZE(regions), + new_three_regions, expected, ARRAY_SIZE(expected)); +} + +/* + * Test slightly bigger change. Similar to above, but the second big region + * now require two target regions (50-55, 57-59) to be removed. + */ +static void damon_test_apply_three_regions2(struct kunit *test) +{ + /* 10-20-30, 50-55-57-59, 70-80-90-100 */ + unsigned long regions[] = {10, 20, 20, 30, 50, 55, 55, 57, 57, 59, + 70, 80, 80, 90, 90, 100}; + /* 5-27, 56-57, 65-104 */ + struct damon_addr_range new_three_regions[3] = { + (struct damon_addr_range){.start = 5, .end = 27}, + (struct damon_addr_range){.start = 56, .end = 57}, + (struct damon_addr_range){.start = 65, .end = 104} }; + /* 5-20-27, 56-57, 65-80-90-104 */ + unsigned long expected[] = {5, 20, 20, 27, 56, 57, + 65, 80, 80, 90, 90, 104}; + + damon_do_test_apply_three_regions(test, regions, ARRAY_SIZE(regions), + new_three_regions, expected, ARRAY_SIZE(expected)); +} + +/* + * Test a big change. The second big region has totally freed and mapped to + * different area (50-59 -> 61-63). The target regions which were in the old + * second big region (50-55-57-59) should be removed and new target region + * covering the second big region (61-63) should be created. + */ +static void damon_test_apply_three_regions3(struct kunit *test) +{ + /* 10-20-30, 50-55-57-59, 70-80-90-100 */ + unsigned long regions[] = {10, 20, 20, 30, 50, 55, 55, 57, 57, 59, + 70, 80, 80, 90, 90, 100}; + /* 5-27, 61-63, 65-104 */ + struct damon_addr_range new_three_regions[3] = { + (struct damon_addr_range){.start = 5, .end = 27}, + (struct damon_addr_range){.start = 61, .end = 63}, + (struct damon_addr_range){.start = 65, .end = 104} }; + /* 5-20-27, 61-63, 65-80-90-104 */ + unsigned long expected[] = {5, 20, 20, 27, 61, 63, + 65, 80, 80, 90, 90, 104}; + + damon_do_test_apply_three_regions(test, regions, ARRAY_SIZE(regions), + new_three_regions, expected, ARRAY_SIZE(expected)); +} + +/* + * Test another big change. Both of the second and third big regions (50-59 + * and 70-100) has totally freed and mapped to different area (30-32 and + * 65-68). The target regions which were in the old second and third big + * regions should now be removed and new target regions covering the new second + * and third big regions should be crated. + */ +static void damon_test_apply_three_regions4(struct kunit *test) +{ + /* 10-20-30, 50-55-57-59, 70-80-90-100 */ + unsigned long regions[] = {10, 20, 20, 30, 50, 55, 55, 57, 57, 59, + 70, 80, 80, 90, 90, 100}; + /* 5-7, 30-32, 65-68 */ + struct damon_addr_range new_three_regions[3] = { + (struct damon_addr_range){.start = 5, .end = 7}, + (struct damon_addr_range){.start = 30, .end = 32}, + (struct damon_addr_range){.start = 65, .end = 68} }; + /* expect 5-7, 30-32, 65-68 */ + unsigned long expected[] = {5, 7, 30, 32, 65, 68}; + + damon_do_test_apply_three_regions(test, regions, ARRAY_SIZE(regions), + new_three_regions, expected, ARRAY_SIZE(expected)); +} + +static void damon_test_split_evenly(struct kunit *test) +{ + struct damon_ctx *c = damon_new_ctx(); + struct damon_target *t; + struct damon_region *r; + unsigned long i; + + KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(NULL, NULL, 5), + -EINVAL); + + t = damon_new_target(42); + r = damon_new_region(0, 100); + KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 0), -EINVAL); + + damon_add_region(r, t); + KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 10), 0); + KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 10u); + + i = 0; + damon_for_each_region(r, t) { + KUNIT_EXPECT_EQ(test, r->ar.start, i++ * 10); + KUNIT_EXPECT_EQ(test, r->ar.end, i * 10); + } + damon_free_target(t); + + t = damon_new_target(42); + r = damon_new_region(5, 59); + damon_add_region(r, t); + KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 5), 0); + KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 5u); + + i = 0; + damon_for_each_region(r, t) { + if (i == 4) + break; + KUNIT_EXPECT_EQ(test, r->ar.start, 5 + 10 * i++); + KUNIT_EXPECT_EQ(test, r->ar.end, 5 + 10 * i); + } + KUNIT_EXPECT_EQ(test, r->ar.start, 5 + 10 * i); + KUNIT_EXPECT_EQ(test, r->ar.end, 59ul); + damon_free_target(t); + + t = damon_new_target(42); + r = damon_new_region(5, 6); + damon_add_region(r, t); + KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 2), -EINVAL); + KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1u); + + damon_for_each_region(r, t) { + KUNIT_EXPECT_EQ(test, r->ar.start, 5ul); + KUNIT_EXPECT_EQ(test, r->ar.end, 6ul); + } + damon_free_target(t); + damon_destroy_ctx(c); +} + +static struct kunit_case damon_test_cases[] = { + KUNIT_CASE(damon_test_three_regions_in_vmas), + KUNIT_CASE(damon_test_apply_three_regions1), + KUNIT_CASE(damon_test_apply_three_regions2), + KUNIT_CASE(damon_test_apply_three_regions3), + KUNIT_CASE(damon_test_apply_three_regions4), + KUNIT_CASE(damon_test_split_evenly), + {}, +}; + +static struct kunit_suite damon_test_suite = { + .name = "damon-primitives", + .test_cases = damon_test_cases, +}; +kunit_test_suite(damon_test_suite); + +#endif /* _DAMON_VADDR_TEST_H */ + +#endif /* CONFIG_DAMON_VADDR_KUNIT_TEST */ diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 897aa8cf96c8..58c1fb2aafa9 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -18,6 +18,11 @@ #include #include +#ifdef CONFIG_DAMON_VADDR_KUNIT_TEST +#undef DAMON_MIN_REGION +#define DAMON_MIN_REGION 1 +#endif + /* Get a random number in [l, r) */ #define damon_rand(l, r) (l + prandom_u32_max(r - l)) @@ -663,3 +668,5 @@ void damon_va_set_primitives(struct damon_ctx *ctx) ctx->primitive.target_valid = damon_va_target_valid; ctx->primitive.cleanup = NULL; } + +#include "vaddr-test.h" -- cgit v1.2.3 From 3843c50a782c397422765cf0839a95e75e523229 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 7 Sep 2021 19:57:27 -0700 Subject: percpu: remove export of pcpu_base_addr This is not needed by any modules, so remove the export. Link: https://lkml.kernel.org/r/20210722185814.504541-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman Reviewed-by: Christoph Hellwig Cc: Dennis Zhou Cc: Tejun Heo Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/percpu.c | 1 - 1 file changed, 1 deletion(-) (limited to 'mm') diff --git a/mm/percpu.c b/mm/percpu.c index 7f2e0151c4e2..a43039629aa4 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -146,7 +146,6 @@ static unsigned int pcpu_high_unit_cpu __ro_after_init; /* the address of the first chunk which starts with the kernel static area */ void *pcpu_base_addr __ro_after_init; -EXPORT_SYMBOL_GPL(pcpu_base_addr); static const int *pcpu_unit_map __ro_after_init; /* cpu -> unit */ const unsigned long *pcpu_unit_offsets __ro_after_init; /* cpu -> unit offset */ -- cgit v1.2.3 From 560a870570287aeb0e77825ae0fa1aba47031cf9 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 7 Sep 2021 20:00:56 -0700 Subject: mm/workingset: correct kernel-doc notations Use the documented kernel-doc format to prevent kernel-doc warnings. mm/workingset.c:256: warning: No description found for return value of 'workingset_eviction' mm/workingset.c:285: warning: Function parameter or member 'folio' not described in 'workingset_refault' mm/workingset.c:285: warning: Excess function parameter 'page' description in 'workingset_refault' Link: https://lkml.kernel.org/r/20210808203153.10678-1-rdunlap@infradead.org Signed-off-by: Randy Dunlap Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/workingset.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/workingset.c b/mm/workingset.c index 5ba3e42446fa..d4268d8e9a82 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -249,7 +249,7 @@ void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages) * @target_memcg: the cgroup that is causing the reclaim * @page: the page being evicted * - * Returns a shadow entry to be stored in @page->mapping->i_pages in place + * Return: a shadow entry to be stored in @page->mapping->i_pages in place * of the evicted @page so that a later refault can be detected. */ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg) -- cgit v1.2.3