From 7534612123e0f5d020aba1076a6bb505db0e6bfe Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Fri, 21 Sep 2018 23:19:00 +0530 Subject: mm/migrate: Use spin_trylock() while resetting rate limit Since this spinlock will only serialize the migrate rate limiting, convert the spin_lock() to a spin_trylock(). If another thread is updating, this task can move on. Specjbb2005 results (8 warehouses) Higher bops are better 2 Socket - 2 Node Haswell - X86 JVMS Prev Current %Change 4 205332 198512 -3.32145 1 319785 313559 -1.94693 2 Socket - 4 Node Power8 - PowerNV JVMS Prev Current %Change 8 74912 74761.9 -0.200368 1 206585 214874 4.01239 2 Socket - 2 Node Power9 - PowerNV JVMS Prev Current %Change 4 189162 180536 -4.56011 1 213760 210281 -1.62753 4 Socket - 4 Node Power7 - PowerVM JVMS Prev Current %Change 8 58736.8 56511.4 -3.78877 1 105419 104899 -0.49327 Avoiding stretching of window intervals may be the reason for the regression. Also code now uses READ_ONCE/WRITE_ONCE. That may also be hurting performance to some extent. Some events stats before and after applying the patch. perf stats 8th warehouse Multi JVM 2 Socket - 2 Node Haswell - X86 Event Before After cs 14,285,708 13,818,546 migrations 1,180,621 1,149,960 faults 339,114 385,583 cache-misses 55,205,631,894 55,259,546,768 sched:sched_move_numa 843 2,257 sched:sched_stick_numa 6 9 sched:sched_swap_numa 219 512 migrate:mm_migrate_pages 365 2,225 vmstat 8th warehouse Multi JVM 2 Socket - 2 Node Haswell - X86 Event Before After numa_hint_faults 26907 72692 numa_hint_faults_local 24279 62270 numa_hit 239771 238762 numa_huge_pte_updates 0 48 numa_interleave 68 75 numa_local 239688 238676 numa_other 83 86 numa_pages_migrated 363 2225 numa_pte_updates 27415 98557 perf stats 8th warehouse Single JVM 2 Socket - 2 Node Haswell - X86 Event Before After cs 3,202,779 3,173,490 migrations 37,186 36,966 faults 106,076 108,776 cache-misses 12,024,873,744 12,200,075,320 sched:sched_move_numa 931 1,264 sched:sched_stick_numa 0 0 sched:sched_swap_numa 1 0 migrate:mm_migrate_pages 637 899 vmstat 8th warehouse Single JVM 2 Socket - 2 Node Haswell - X86 Event Before After numa_hint_faults 17409 21109 numa_hint_faults_local 14367 17120 numa_hit 73953 72934 numa_huge_pte_updates 20 42 numa_interleave 25 33 numa_local 73892 72866 numa_other 61 68 numa_pages_migrated 668 915 numa_pte_updates 27276 42326 perf stats 8th warehouse Multi JVM 2 Socket - 2 Node Power9 - PowerNV Event Before After cs 8,474,013 8,312,022 migrations 254,934 231,705 faults 320,506 310,242 cache-misses 110,580,458 402,324,573 sched:sched_move_numa 725 193 sched:sched_stick_numa 0 0 sched:sched_swap_numa 7 3 migrate:mm_migrate_pages 145 93 vmstat 8th warehouse Multi JVM 2 Socket - 2 Node Power9 - PowerNV Event Before After numa_hint_faults 22797 11838 numa_hint_faults_local 21539 11216 numa_hit 89308 90689 numa_huge_pte_updates 0 0 numa_interleave 865 1579 numa_local 88955 89634 numa_other 353 1055 numa_pages_migrated 149 92 numa_pte_updates 22930 12109 perf stats 8th warehouse Single JVM 2 Socket - 2 Node Power9 - PowerNV Event Before After cs 2,195,628 2,170,481 migrations 11,179 10,126 faults 149,656 160,962 cache-misses 8,117,515 10,834,845 sched:sched_move_numa 49 10 sched:sched_stick_numa 0 0 sched:sched_swap_numa 0 0 migrate:mm_migrate_pages 5 2 vmstat 8th warehouse Single JVM 2 Socket - 2 Node Power9 - PowerNV Event Before After numa_hint_faults 3577 403 numa_hint_faults_local 3476 358 numa_hit 26142 25898 numa_huge_pte_updates 0 0 numa_interleave 358 207 numa_local 26042 25860 numa_other 100 38 numa_pages_migrated 5 2 numa_pte_updates 3587 400 perf stats 8th warehouse Multi JVM 4 Socket - 4 Node Power7 - PowerVM Event Before After cs 100,602,296 110,339,633 migrations 4,135,630 4,139,812 faults 789,256 863,622 cache-misses 226,160,621,058 231,838,045,660 sched:sched_move_numa 1,366 2,196 sched:sched_stick_numa 16 33 sched:sched_swap_numa 374 544 migrate:mm_migrate_pages 1,350 2,469 vmstat 8th warehouse Multi JVM 4 Socket - 4 Node Power7 - PowerVM Event Before After numa_hint_faults 47857 85748 numa_hint_faults_local 39768 66831 numa_hit 240165 242213 numa_huge_pte_updates 0 0 numa_interleave 0 0 numa_local 240165 242211 numa_other 0 2 numa_pages_migrated 1224 2376 numa_pte_updates 48354 86233 perf stats 8th warehouse Single JVM 4 Socket - 4 Node Power7 - PowerVM Event Before After cs 58,515,496 59,331,057 migrations 564,845 552,019 faults 245,807 266,586 cache-misses 73,603,757,976 73,796,312,990 sched:sched_move_numa 996 981 sched:sched_stick_numa 10 54 sched:sched_swap_numa 193 286 migrate:mm_migrate_pages 646 713 vmstat 8th warehouse Single JVM 4 Socket - 4 Node Power7 - PowerVM Event Before After numa_hint_faults 13422 14807 numa_hint_faults_local 5619 5738 numa_hit 36118 36230 numa_huge_pte_updates 0 0 numa_interleave 0 0 numa_local 36116 36228 numa_other 2 2 numa_pages_migrated 616 703 numa_pte_updates 13374 14742 Suggested-by: Peter Zijlstra Signed-off-by: Srikar Dronamraju Signed-off-by: Peter Zijlstra (Intel) Cc: Jirka Hladky Cc: Linus Torvalds Cc: Mel Gorman Cc: Mike Galbraith Cc: Rik van Riel Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1537552141-27815-6-git-send-email-srikar@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- mm/migrate.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/migrate.c b/mm/migrate.c index d6a2e89b086a..4f1d894835b5 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1867,16 +1867,24 @@ static unsigned int ratelimit_pages __read_mostly = 128 << (20 - PAGE_SHIFT); static bool numamigrate_update_ratelimit(pg_data_t *pgdat, unsigned long nr_pages) { + unsigned long next_window, interval; + + next_window = READ_ONCE(pgdat->numabalancing_migrate_next_window); + interval = msecs_to_jiffies(migrate_interval_millisecs); + /* * Rate-limit the amount of data that is being migrated to a node. * Optimal placement is no good if the memory bus is saturated and * all the time is being spent migrating! */ - if (time_after(jiffies, pgdat->numabalancing_migrate_next_window)) { - spin_lock(&pgdat->numabalancing_migrate_lock); + if (time_after(jiffies, next_window) && + spin_trylock(&pgdat->numabalancing_migrate_lock)) { pgdat->numabalancing_migrate_nr_pages = 0; - pgdat->numabalancing_migrate_next_window = jiffies + - msecs_to_jiffies(migrate_interval_millisecs); + do { + next_window += interval; + } while (unlikely(time_after(jiffies, next_window))); + + WRITE_ONCE(pgdat->numabalancing_migrate_next_window, next_window); spin_unlock(&pgdat->numabalancing_migrate_lock); } if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) { -- cgit v1.2.3 From efaffc5e40aeced0bcb497ed7a0a5b8c14abfcdf Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 1 Oct 2018 11:05:24 +0100 Subject: mm, sched/numa: Remove rate-limiting of automatic NUMA balancing migration Rate limiting of page migrations due to automatic NUMA balancing was introduced to mitigate the worst-case scenario of migrating at high frequency due to false sharing or slowly ping-ponging between nodes. Since then, a lot of effort was spent on correctly identifying these pages and avoiding unnecessary migrations and the safety net may no longer be required. Jirka Hladky reported a regression in 4.17 due to a scheduler patch that avoids spreading STREAM tasks wide prematurely. However, once the task was properly placed, it delayed migrating the memory due to rate limiting. Increasing the limit fixed the problem for him. Currently, the limit is hard-coded and does not account for the real capabilities of the hardware. Even if an estimate was attempted, it would not properly account for the number of memory controllers and it could not account for the amount of bandwidth used for normal accesses. Rather than fudging, this patch simply eliminates the rate limiting. However, Jirka reports that a STREAM configuration using multiple processes achieved similar performance to 4.16. In local tests, this patch improved performance of STREAM relative to the baseline but it is somewhat machine-dependent. Most workloads show little or not performance difference implying that there is not a heavily reliance on the throttling mechanism and it is safe to remove. STREAM on 2-socket machine 4.19.0-rc5 4.19.0-rc5 numab-v1r1 noratelimit-v1r1 MB/sec copy 43298.52 ( 0.00%) 44673.38 ( 3.18%) MB/sec scale 30115.06 ( 0.00%) 31293.06 ( 3.91%) MB/sec add 32825.12 ( 0.00%) 34883.62 ( 6.27%) MB/sec triad 32549.52 ( 0.00%) 34906.60 ( 7.24% Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel Acked-by: Peter Zijlstra Cc: Jirka Hladky Cc: Linus Torvalds Cc: Linux-MM Cc: Srikar Dronamraju Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20181001100525.29789-2-mgorman@techsingularity.net Signed-off-by: Ingo Molnar --- include/linux/mmzone.h | 6 ---- include/trace/events/migrate.h | 27 ------------------ mm/migrate.c | 65 ------------------------------------------ mm/page_alloc.c | 2 -- 4 files changed, 100 deletions(-) (limited to 'mm') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1e22d96734e0..3f4c0b167333 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -671,12 +671,6 @@ typedef struct pglist_data { #ifdef CONFIG_NUMA_BALANCING /* Lock serializing the migrate rate limiting window */ spinlock_t numabalancing_migrate_lock; - - /* Rate limiting time interval */ - unsigned long numabalancing_migrate_next_window; - - /* Number of pages migrated during the rate limiting time interval */ - unsigned long numabalancing_migrate_nr_pages; #endif /* * This is a per-node reserve of pages that are not available diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h index 711372845945..705b33d1e395 100644 --- a/include/trace/events/migrate.h +++ b/include/trace/events/migrate.h @@ -70,33 +70,6 @@ TRACE_EVENT(mm_migrate_pages, __print_symbolic(__entry->mode, MIGRATE_MODE), __print_symbolic(__entry->reason, MIGRATE_REASON)) ); - -TRACE_EVENT(mm_numa_migrate_ratelimit, - - TP_PROTO(struct task_struct *p, int dst_nid, unsigned long nr_pages), - - TP_ARGS(p, dst_nid, nr_pages), - - TP_STRUCT__entry( - __array( char, comm, TASK_COMM_LEN) - __field( pid_t, pid) - __field( int, dst_nid) - __field( unsigned long, nr_pages) - ), - - TP_fast_assign( - memcpy(__entry->comm, p->comm, TASK_COMM_LEN); - __entry->pid = p->pid; - __entry->dst_nid = dst_nid; - __entry->nr_pages = nr_pages; - ), - - TP_printk("comm=%s pid=%d dst_nid=%d nr_pages=%lu", - __entry->comm, - __entry->pid, - __entry->dst_nid, - __entry->nr_pages) -); #endif /* _TRACE_MIGRATE_H */ /* This part must be outside protection */ diff --git a/mm/migrate.c b/mm/migrate.c index 4f1d894835b5..5e285c1249a0 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1855,54 +1855,6 @@ static struct page *alloc_misplaced_dst_page(struct page *page, return newpage; } -/* - * page migration rate limiting control. - * Do not migrate more than @pages_to_migrate in a @migrate_interval_millisecs - * window of time. Default here says do not migrate more than 1280M per second. - */ -static unsigned int migrate_interval_millisecs __read_mostly = 100; -static unsigned int ratelimit_pages __read_mostly = 128 << (20 - PAGE_SHIFT); - -/* Returns true if the node is migrate rate-limited after the update */ -static bool numamigrate_update_ratelimit(pg_data_t *pgdat, - unsigned long nr_pages) -{ - unsigned long next_window, interval; - - next_window = READ_ONCE(pgdat->numabalancing_migrate_next_window); - interval = msecs_to_jiffies(migrate_interval_millisecs); - - /* - * Rate-limit the amount of data that is being migrated to a node. - * Optimal placement is no good if the memory bus is saturated and - * all the time is being spent migrating! - */ - if (time_after(jiffies, next_window) && - spin_trylock(&pgdat->numabalancing_migrate_lock)) { - pgdat->numabalancing_migrate_nr_pages = 0; - do { - next_window += interval; - } while (unlikely(time_after(jiffies, next_window))); - - WRITE_ONCE(pgdat->numabalancing_migrate_next_window, next_window); - spin_unlock(&pgdat->numabalancing_migrate_lock); - } - if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) { - trace_mm_numa_migrate_ratelimit(current, pgdat->node_id, - nr_pages); - return true; - } - - /* - * This is an unlocked non-atomic update so errors are possible. - * The consequences are failing to migrate when we potentiall should - * have which is not severe enough to warrant locking. If it is ever - * a problem, it can be converted to a per-cpu counter. - */ - pgdat->numabalancing_migrate_nr_pages += nr_pages; - return false; -} - static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) { int page_lru; @@ -1975,14 +1927,6 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, if (page_is_file_cache(page) && PageDirty(page)) goto out; - /* - * Rate-limit the amount of data that is being migrated to a node. - * Optimal placement is no good if the memory bus is saturated and - * all the time is being spent migrating! - */ - if (numamigrate_update_ratelimit(pgdat, 1)) - goto out; - isolated = numamigrate_isolate_page(pgdat, page); if (!isolated) goto out; @@ -2029,14 +1973,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, unsigned long mmun_start = address & HPAGE_PMD_MASK; unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE; - /* - * Rate-limit the amount of data that is being migrated to a node. - * Optimal placement is no good if the memory bus is saturated and - * all the time is being spent migrating! - */ - if (numamigrate_update_ratelimit(pgdat, HPAGE_PMD_NR)) - goto out_dropref; - new_page = alloc_pages_node(node, (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE), HPAGE_PMD_ORDER); @@ -2133,7 +2069,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, out_fail: count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); -out_dropref: ptl = pmd_lock(mm, pmd); if (pmd_same(*pmd, entry)) { entry = pmd_modify(entry, vma->vm_page_prot); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 89d2a2ab3fe6..706a738c0aee 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6197,8 +6197,6 @@ static unsigned long __init calc_memmap_size(unsigned long spanned_pages, static void pgdat_init_numabalancing(struct pglist_data *pgdat) { spin_lock_init(&pgdat->numabalancing_migrate_lock); - pgdat->numabalancing_migrate_nr_pages = 0; - pgdat->numabalancing_migrate_next_window = jiffies; } #else static void pgdat_init_numabalancing(struct pglist_data *pgdat) {} -- cgit v1.2.3 From 017b1660df89f5fb4bfe66c34e35f7d2031100c7 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 5 Oct 2018 15:51:29 -0700 Subject: mm: migration: fix migration of huge PMD shared pages The page migration code employs try_to_unmap() to try and unmap the source page. This is accomplished by using rmap_walk to find all vmas where the page is mapped. This search stops when page mapcount is zero. For shared PMD huge pages, the page map count is always 1 no matter the number of mappings. Shared mappings are tracked via the reference count of the PMD page. Therefore, try_to_unmap stops prematurely and does not completely unmap all mappings of the source page. This problem can result is data corruption as writes to the original source page can happen after contents of the page are copied to the target page. Hence, data is lost. This problem was originally seen as DB corruption of shared global areas after a huge page was soft offlined due to ECC memory errors. DB developers noticed they could reproduce the issue by (hotplug) offlining memory used to back huge pages. A simple testcase can reproduce the problem by creating a shared PMD mapping (note that this must be at least PUD_SIZE in size and PUD_SIZE aligned (1GB on x86)), and using migrate_pages() to migrate process pages between nodes while continually writing to the huge pages being migrated. To fix, have the try_to_unmap_one routine check for huge PMD sharing by calling huge_pmd_unshare for hugetlbfs huge pages. If it is a shared mapping it will be 'unshared' which removes the page table entry and drops the reference on the PMD page. After this, flush caches and TLB. mmu notifiers are called before locking page tables, but we can not be sure of PMD sharing until page tables are locked. Therefore, check for the possibility of PMD sharing before locking so that notifiers can prepare for the worst possible case. Link: http://lkml.kernel.org/r/20180823205917.16297-2-mike.kravetz@oracle.com [mike.kravetz@oracle.com: make _range_in_vma() a static inline] Link: http://lkml.kernel.org/r/6063f215-a5c8-2f0c-465a-2c515ddc952d@oracle.com Fixes: 39dde65c9940 ("shared page table for hugetlb page") Signed-off-by: Mike Kravetz Acked-by: Kirill A. Shutemov Reviewed-by: Naoya Horiguchi Acked-by: Michal Hocko Cc: Vlastimil Babka Cc: Davidlohr Bueso Cc: Jerome Glisse Cc: Mike Kravetz Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/linux/hugetlb.h | 14 ++++++++++++++ include/linux/mm.h | 6 ++++++ mm/hugetlb.c | 37 +++++++++++++++++++++++++++++++++++-- mm/rmap.c | 42 +++++++++++++++++++++++++++++++++++++++--- 4 files changed, 94 insertions(+), 5 deletions(-) (limited to 'mm') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 6b68e345f0ca..087fd5f48c91 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -140,6 +140,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep); +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end); struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, int write); struct page *follow_huge_pd(struct vm_area_struct *vma, @@ -170,6 +172,18 @@ static inline unsigned long hugetlb_total_pages(void) return 0; } +static inline int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, + pte_t *ptep) +{ + return 0; +} + +static inline void adjust_range_if_pmd_sharing_possible( + struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ +} + #define follow_hugetlb_page(m,v,p,vs,a,b,i,w,n) ({ BUG(); 0; }) #define follow_huge_addr(mm, addr, write) ERR_PTR(-EINVAL) #define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; }) diff --git a/include/linux/mm.h b/include/linux/mm.h index a61ebe8ad4ca..0416a7204be3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2455,6 +2455,12 @@ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, return vma; } +static inline bool range_in_vma(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + return (vma && vma->vm_start <= start && end <= vma->vm_end); +} + #ifdef CONFIG_MMU pgprot_t vm_get_page_prot(unsigned long vm_flags); void vma_set_page_prot(struct vm_area_struct *vma); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3c21775f196b..b903d746e132 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4545,12 +4545,40 @@ static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr) /* * check on proper vm_flags and page table alignment */ - if (vma->vm_flags & VM_MAYSHARE && - vma->vm_start <= base && end <= vma->vm_end) + if (vma->vm_flags & VM_MAYSHARE && range_in_vma(vma, base, end)) return true; return false; } +/* + * Determine if start,end range within vma could be mapped by shared pmd. + * If yes, adjust start and end to cover range associated with possible + * shared pmd mappings. + */ +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ + unsigned long check_addr = *start; + + if (!(vma->vm_flags & VM_MAYSHARE)) + return; + + for (check_addr = *start; check_addr < *end; check_addr += PUD_SIZE) { + unsigned long a_start = check_addr & PUD_MASK; + unsigned long a_end = a_start + PUD_SIZE; + + /* + * If sharing is possible, adjust start/end if necessary. + */ + if (range_in_vma(vma, a_start, a_end)) { + if (a_start < *start) + *start = a_start; + if (a_end > *end) + *end = a_end; + } + } +} + /* * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() * and returns the corresponding pte. While this is not necessary for the @@ -4648,6 +4676,11 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) { return 0; } + +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ +} #define want_pmd_share() (0) #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ diff --git a/mm/rmap.c b/mm/rmap.c index eb477809a5c0..1e79fac3186b 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1362,11 +1362,21 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } /* - * We have to assume the worse case ie pmd for invalidation. Note that - * the page can not be free in this function as call of try_to_unmap() - * must hold a reference on the page. + * For THP, we have to assume the worse case ie pmd for invalidation. + * For hugetlb, it could be much worse if we need to do pud + * invalidation in the case of pmd sharing. + * + * Note that the page can not be free in this function as call of + * try_to_unmap() must hold a reference on the page. */ end = min(vma->vm_end, start + (PAGE_SIZE << compound_order(page))); + if (PageHuge(page)) { + /* + * If sharing is possible, start and end will be adjusted + * accordingly. + */ + adjust_range_if_pmd_sharing_possible(vma, &start, &end); + } mmu_notifier_invalidate_range_start(vma->vm_mm, start, end); while (page_vma_mapped_walk(&pvmw)) { @@ -1409,6 +1419,32 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); address = pvmw.address; + if (PageHuge(page)) { + if (huge_pmd_unshare(mm, &address, pvmw.pte)) { + /* + * huge_pmd_unshare unmapped an entire PMD + * page. There is no way of knowing exactly + * which PMDs may be cached for this mm, so + * we must flush them all. start/end were + * already adjusted above to cover this range. + */ + flush_cache_range(vma, start, end); + flush_tlb_range(vma, start, end); + mmu_notifier_invalidate_range(mm, start, end); + + /* + * The ref count of the PMD page was dropped + * which is part of the way map counting + * is done for shared PMDs. Return 'true' + * here. When there is no other sharing, + * huge_pmd_unshare returns false and we will + * unmap the actual page and drop map count + * to zero. + */ + page_vma_mapped_walk_done(&pvmw); + break; + } + } if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) && -- cgit v1.2.3 From dff11abe280b47c21b804a8ace318e0638bb9a49 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 5 Oct 2018 15:51:33 -0700 Subject: hugetlb: take PMD sharing into account when flushing tlb/caches When fixing an issue with PMD sharing and migration, it was discovered via code inspection that other callers of huge_pmd_unshare potentially have an issue with cache and tlb flushing. Use the routine adjust_range_if_pmd_sharing_possible() to calculate worst case ranges for mmu notifiers. Ensure that this range is flushed if huge_pmd_unshare succeeds and unmaps a PUD_SUZE area. Link: http://lkml.kernel.org/r/20180823205917.16297-3-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Acked-by: Kirill A. Shutemov Reviewed-by: Naoya Horiguchi Cc: Vlastimil Babka Cc: Davidlohr Bueso Cc: Michal Hocko Cc: Jerome Glisse Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/hugetlb.c | 53 ++++++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 44 insertions(+), 9 deletions(-) (limited to 'mm') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b903d746e132..5c390f5a5207 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3326,8 +3326,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, struct page *page; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); - const unsigned long mmun_start = start; /* For mmu_notifiers */ - const unsigned long mmun_end = end; /* For mmu_notifiers */ + unsigned long mmun_start = start; /* For mmu_notifiers */ + unsigned long mmun_end = end; /* For mmu_notifiers */ WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); @@ -3339,6 +3339,11 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, */ tlb_remove_check_page_size_change(tlb, sz); tlb_start_vma(tlb, vma); + + /* + * If sharing possible, alert mmu notifiers of worst case. + */ + adjust_range_if_pmd_sharing_possible(vma, &mmun_start, &mmun_end); mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); address = start; for (; address < end; address += sz) { @@ -3349,6 +3354,10 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, &address, ptep)) { spin_unlock(ptl); + /* + * We just unmapped a page of PMDs by clearing a PUD. + * The caller's TLB flush range should cover this area. + */ continue; } @@ -3431,12 +3440,23 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, { struct mm_struct *mm; struct mmu_gather tlb; + unsigned long tlb_start = start; + unsigned long tlb_end = end; + + /* + * If shared PMDs were possibly used within this vma range, adjust + * start/end for worst case tlb flushing. + * Note that we can not be sure if PMDs are shared until we try to + * unmap pages. However, we want to make sure TLB flushing covers + * the largest possible range. + */ + adjust_range_if_pmd_sharing_possible(vma, &tlb_start, &tlb_end); mm = vma->vm_mm; - tlb_gather_mmu(&tlb, mm, start, end); + tlb_gather_mmu(&tlb, mm, tlb_start, tlb_end); __unmap_hugepage_range(&tlb, vma, start, end, ref_page); - tlb_finish_mmu(&tlb, start, end); + tlb_finish_mmu(&tlb, tlb_start, tlb_end); } /* @@ -4298,11 +4318,21 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, pte_t pte; struct hstate *h = hstate_vma(vma); unsigned long pages = 0; + unsigned long f_start = start; + unsigned long f_end = end; + bool shared_pmd = false; + + /* + * In the case of shared PMDs, the area to flush could be beyond + * start/end. Set f_start/f_end to cover the maximum possible + * range if PMD sharing is possible. + */ + adjust_range_if_pmd_sharing_possible(vma, &f_start, &f_end); BUG_ON(address >= end); - flush_cache_range(vma, address, end); + flush_cache_range(vma, f_start, f_end); - mmu_notifier_invalidate_range_start(mm, start, end); + mmu_notifier_invalidate_range_start(mm, f_start, f_end); i_mmap_lock_write(vma->vm_file->f_mapping); for (; address < end; address += huge_page_size(h)) { spinlock_t *ptl; @@ -4313,6 +4343,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, if (huge_pmd_unshare(mm, &address, ptep)) { pages++; spin_unlock(ptl); + shared_pmd = true; continue; } pte = huge_ptep_get(ptep); @@ -4348,9 +4379,13 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare * may have cleared our pud entry and done put_page on the page table: * once we release i_mmap_rwsem, another task can do the final put_page - * and that page table be reused and filled with junk. + * and that page table be reused and filled with junk. If we actually + * did unshare a page of pmds, flush the range corresponding to the pud. */ - flush_hugetlb_tlb_range(vma, start, end); + if (shared_pmd) + flush_hugetlb_tlb_range(vma, f_start, f_end); + else + flush_hugetlb_tlb_range(vma, start, end); /* * No need to call mmu_notifier_invalidate_range() we are downgrading * page table protection not changing it to point to a new page. @@ -4358,7 +4393,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, * See Documentation/vm/mmu_notifier.rst */ i_mmap_unlock_write(vma->vm_file->f_mapping); - mmu_notifier_invalidate_range_end(mm, start, end); + mmu_notifier_invalidate_range_end(mm, f_start, f_end); return pages << h->order; } -- cgit v1.2.3 From e125fe405abedc1dc8a5b2229b80ee91c1434015 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 5 Oct 2018 15:51:41 -0700 Subject: mm, thp: fix mlocking THP page with migration enabled A transparent huge page is represented by a single entry on an LRU list. Therefore, we can only make unevictable an entire compound page, not individual subpages. If a user tries to mlock() part of a huge page, we want the rest of the page to be reclaimable. We handle this by keeping PTE-mapped huge pages on normal LRU lists: the PMD on border of VM_LOCKED VMA will be split into PTE table. Introduction of THP migration breaks[1] the rules around mlocking THP pages. If we had a single PMD mapping of the page in mlocked VMA, the page will get mlocked, regardless of PTE mappings of the page. For tmpfs/shmem it's easy to fix by checking PageDoubleMap() in remove_migration_pmd(). Anon THP pages can only be shared between processes via fork(). Mlocked page can only be shared if parent mlocked it before forking, otherwise CoW will be triggered on mlock(). For Anon-THP, we can fix the issue by munlocking the page on removing PTE migration entry for the page. PTEs for the page will always come after mlocked PMD: rmap walks VMAs from oldest to newest. Test-case: #include #include #include #include #include int main(void) { unsigned long nodemask = 4; void *addr; addr = mmap((void *)0x20000000UL, 2UL << 20, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_LOCKED, -1, 0); if (fork()) { wait(NULL); return 0; } mlock(addr, 4UL << 10); mbind(addr, 2UL << 20, MPOL_PREFERRED | MPOL_F_RELATIVE_NODES, &nodemask, 4, MPOL_MF_MOVE); return 0; } [1] https://lkml.kernel.org/r/CAOMGZ=G52R-30rZvhGxEbkTw7rLLwBGadVYeo--iizcD3upL3A@mail.gmail.com Link: http://lkml.kernel.org/r/20180917133816.43995-1-kirill.shutemov@linux.intel.com Fixes: 616b8371539a ("mm: thp: enable thp migration in generic path") Signed-off-by: Kirill A. Shutemov Reported-by: Vegard Nossum Reviewed-by: Zi Yan Cc: Naoya Horiguchi Cc: Vlastimil Babka Cc: Andrea Arcangeli Cc: [4.14+] Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/huge_memory.c | 2 +- mm/migrate.c | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 533f9b00147d..00704060b7f7 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2931,7 +2931,7 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) else page_add_file_rmap(new, true); set_pmd_at(mm, mmun_start, pvmw->pmd, pmde); - if (vma->vm_flags & VM_LOCKED) + if ((vma->vm_flags & VM_LOCKED) && !PageDoubleMap(new)) mlock_vma_page(new); update_mmu_cache_pmd(vma, address, pvmw->pmd); } diff --git a/mm/migrate.c b/mm/migrate.c index d6a2e89b086a..9d374011c244 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -275,6 +275,9 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, if (vma->vm_flags & VM_LOCKED && !PageTransCompound(new)) mlock_vma_page(new); + if (PageTransHuge(page) && PageMlocked(page)) + clear_page_mlock(page); + /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, pvmw.address, pvmw.pte); } -- cgit v1.2.3 From 51896864579d5a3349740847083f4db5c6487164 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Fri, 5 Oct 2018 15:51:44 -0700 Subject: mm/gup_benchmark: fix unsigned comparison to zero in __gup_benchmark_ioctl get_user_pages_fast() will return negative value if no pages were pinned, then be converted to a unsigned, which is compared to zero, giving the wrong result. Link: http://lkml.kernel.org/r/20180921095015.26088-1-yuehaibing@huawei.com Fixes: 09e35a4a1ca8 ("mm/gup_benchmark: handle gup failures") Signed-off-by: YueHaibing Reviewed-by: Andrew Morton Cc: Michael S. Tsirkin Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/gup_benchmark.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c index 6a473709e9b6..7405c9d89d65 100644 --- a/mm/gup_benchmark.c +++ b/mm/gup_benchmark.c @@ -19,7 +19,8 @@ static int __gup_benchmark_ioctl(unsigned int cmd, struct gup_benchmark *gup) { ktime_t start_time, end_time; - unsigned long i, nr, nr_pages, addr, next; + unsigned long i, nr_pages, addr, next; + int nr; struct page **pages; nr_pages = gup->size / PAGE_SIZE; -- cgit v1.2.3 From e6112fc300702f96374f34368513d57795fc6d23 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Fri, 5 Oct 2018 15:51:51 -0700 Subject: mm/migrate.c: split only transparent huge pages when allocation fails split_huge_page_to_list() fails on HugeTLB pages. I was experimenting with moving 32MB contig HugeTLB pages on arm64 (with a debug patch applied) and hit the following stack trace when the kernel crashed. [ 3732.462797] Call trace: [ 3732.462835] split_huge_page_to_list+0x3b0/0x858 [ 3732.462913] migrate_pages+0x728/0xc20 [ 3732.462999] soft_offline_page+0x448/0x8b0 [ 3732.463097] __arm64_sys_madvise+0x724/0x850 [ 3732.463197] el0_svc_handler+0x74/0x110 [ 3732.463297] el0_svc+0x8/0xc [ 3732.463347] Code: d1000400 f90b0e60 f2fbd5a2 a94982a1 (f9000420) When unmap_and_move[_huge_page]() fails due to lack of memory, the splitting should happen only for transparent huge pages not for HugeTLB pages. PageTransHuge() returns true for both THP and HugeTLB pages. Hence the conditonal check should test PagesHuge() flag to make sure that given pages is not a HugeTLB one. Link: http://lkml.kernel.org/r/1537798495-4996-1-git-send-email-anshuman.khandual@arm.com Fixes: 94723aafb9 ("mm: unclutter THP migration") Signed-off-by: Anshuman Khandual Acked-by: Michal Hocko Acked-by: Naoya Horiguchi Cc: Kirill A. Shutemov Cc: Zi Yan Cc: Mike Kravetz Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/migrate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/migrate.c b/mm/migrate.c index 9d374011c244..9ba72c2365e6 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1414,7 +1414,7 @@ retry: * we encounter them after the rest of the list * is processed. */ - if (PageTransHuge(page)) { + if (PageTransHuge(page) && !PageHuge(page)) { lock_page(page); rc = split_huge_page_to_list(page, from); unlock_page(page); -- cgit v1.2.3 From 28e2c4bb99aa40f9d5f07ac130cbc4da0ea93079 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Fri, 5 Oct 2018 15:52:03 -0700 Subject: mm/vmstat.c: fix outdated vmstat_text 7a9cdebdcc17 ("mm: get rid of vmacache_flush_all() entirely") removed the VMACACHE_FULL_FLUSHES statistics, but didn't remove the corresponding entry in vmstat_text. This causes an out-of-bounds access in vmstat_show(). Luckily this only affects kernels with CONFIG_DEBUG_VM_VMACACHE=y, which is probably very rare. Link: http://lkml.kernel.org/r/20181001143138.95119-1-jannh@google.com Fixes: 7a9cdebdcc17 ("mm: get rid of vmacache_flush_all() entirely") Signed-off-by: Jann Horn Reviewed-by: Kees Cook Reviewed-by: Andrew Morton Acked-by: Michal Hocko Acked-by: Roman Gushchin Cc: Davidlohr Bueso Cc: Oleg Nesterov Cc: Christoph Lameter Cc: Kemi Wang Cc: Andy Lutomirski Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/vmstat.c | 1 - 1 file changed, 1 deletion(-) (limited to 'mm') diff --git a/mm/vmstat.c b/mm/vmstat.c index 8ba0870ecddd..4cea7b8f519d 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1283,7 +1283,6 @@ const char * const vmstat_text[] = { #ifdef CONFIG_DEBUG_VM_VMACACHE "vmacache_find_calls", "vmacache_find_hits", - "vmacache_full_flushes", #endif #ifdef CONFIG_SWAP "swap_ra", -- cgit v1.2.3 From 58bc4c34d249bf1bc50730a9a209139347cfacfe Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Fri, 5 Oct 2018 15:52:07 -0700 Subject: mm/vmstat.c: skip NR_TLB_REMOTE_FLUSH* properly 5dd0b16cdaff ("mm/vmstat: Make NR_TLB_REMOTE_FLUSH_RECEIVED available even on UP") made the availability of the NR_TLB_REMOTE_FLUSH* counters inside the kernel unconditional to reduce #ifdef soup, but (either to avoid showing dummy zero counters to userspace, or because that code was missed) didn't update the vmstat_array, meaning that all following counters would be shown with incorrect values. This only affects kernel builds with CONFIG_VM_EVENT_COUNTERS=y && CONFIG_DEBUG_TLBFLUSH=y && CONFIG_SMP=n. Link: http://lkml.kernel.org/r/20181001143138.95119-2-jannh@google.com Fixes: 5dd0b16cdaff ("mm/vmstat: Make NR_TLB_REMOTE_FLUSH_RECEIVED available even on UP") Signed-off-by: Jann Horn Reviewed-by: Kees Cook Reviewed-by: Andrew Morton Acked-by: Michal Hocko Acked-by: Roman Gushchin Cc: Davidlohr Bueso Cc: Oleg Nesterov Cc: Christoph Lameter Cc: Kemi Wang Cc: Andy Lutomirski Cc: Ingo Molnar Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/vmstat.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'mm') diff --git a/mm/vmstat.c b/mm/vmstat.c index 4cea7b8f519d..7878da76abf2 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1275,6 +1275,9 @@ const char * const vmstat_text[] = { #ifdef CONFIG_SMP "nr_tlb_remote_flush", "nr_tlb_remote_flush_received", +#else + "", /* nr_tlb_remote_flush */ + "", /* nr_tlb_remote_flush_received */ #endif /* CONFIG_SMP */ "nr_tlb_local_flush_all", "nr_tlb_local_flush_one", -- cgit v1.2.3 From b8e57efa2c98cc56c49461c4950cf026422c29e9 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Fri, 5 Oct 2018 15:52:10 -0700 Subject: mm/vmscan.c: fix int overflow in callers of do_shrink_slab() do_shrink_slab() returns unsigned long value, and the placing into int variable cuts high bytes off. Then we compare ret and 0xfffffffe (since SHRINK_EMPTY is converted to ret type). Thus a large number of objects returned by do_shrink_slab() may be interpreted as SHRINK_EMPTY, if low bytes of their value are equal to 0xfffffffe. Fix that by declaration ret as unsigned long in these functions. Link: http://lkml.kernel.org/r/153813407177.17544.14888305435570723973.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Reported-by: Cyrill Gorcunov Acked-by: Cyrill Gorcunov Reviewed-by: Josef Bacik Cc: Michal Hocko Cc: Andrey Ryabinin Cc: Johannes Weiner Cc: Tetsuo Handa Cc: Shakeel Butt Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/vmscan.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/vmscan.c b/mm/vmscan.c index c7ce2c161225..c5ef7240cbcb 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -580,8 +580,8 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { struct memcg_shrinker_map *map; - unsigned long freed = 0; - int ret, i; + unsigned long ret, freed = 0; + int i; if (!memcg_kmem_enabled() || !mem_cgroup_online(memcg)) return 0; @@ -677,9 +677,8 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { + unsigned long ret, freed = 0; struct shrinker *shrinker; - unsigned long freed = 0; - int ret; if (!mem_cgroup_is_root(memcg)) return shrink_slab_memcg(gfp_mask, nid, memcg, priority); -- cgit v1.2.3 From d41aa5252394c065d1f04d1ceea885b70d00c9c6 Mon Sep 17 00:00:00 2001 From: Daniel Black Date: Fri, 5 Oct 2018 15:52:19 -0700 Subject: mm: madvise(MADV_DODUMP): allow hugetlbfs pages Reproducer, assuming 2M of hugetlbfs available: Hugetlbfs mounted, size=2M and option user=testuser # mount | grep ^hugetlbfs hugetlbfs on /dev/hugepages type hugetlbfs (rw,pagesize=2M,user=dan) # sysctl vm.nr_hugepages=1 vm.nr_hugepages = 1 # grep Huge /proc/meminfo AnonHugePages: 0 kB ShmemHugePages: 0 kB HugePages_Total: 1 HugePages_Free: 1 HugePages_Rsvd: 0 HugePages_Surp: 0 Hugepagesize: 2048 kB Hugetlb: 2048 kB Code: #include #include #define SIZE 2*1024*1024 int main() { void *ptr; ptr = mmap(NULL, SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_HUGETLB | MAP_ANONYMOUS, -1, 0); madvise(ptr, SIZE, MADV_DONTDUMP); madvise(ptr, SIZE, MADV_DODUMP); } Compile and strace: mmap(NULL, 2097152, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS|MAP_HUGETLB, -1, 0) = 0x7ff7c9200000 madvise(0x7ff7c9200000, 2097152, MADV_DONTDUMP) = 0 madvise(0x7ff7c9200000, 2097152, MADV_DODUMP) = -1 EINVAL (Invalid argument) hugetlbfs pages have VM_DONTEXPAND in the VmFlags driver pages based on author testing with analysis from Florian Weimer[1]. The inclusion of VM_DONTEXPAND into the VM_SPECIAL defination was a consequence of the large useage of VM_DONTEXPAND in device drivers. A consequence of [2] is that VM_DONTEXPAND marked pages are unable to be marked DODUMP. A user could quite legitimately madvise(MADV_DONTDUMP) their hugetlbfs memory for a while and later request that madvise(MADV_DODUMP) on the same memory. We correct this omission by allowing madvice(MADV_DODUMP) on hugetlbfs pages. [1] https://stackoverflow.com/questions/52548260/madvisedodump-on-the-same-ptr-size-as-a-successful-madvisedontdump-fails-wit [2] commit 0103bd16fb90 ("mm: prepare VM_DONTDUMP for using in drivers") Link: http://lkml.kernel.org/r/20180930054629.29150-1-daniel@linux.ibm.com Link: https://lists.launchpad.net/maria-discuss/msg05245.html Fixes: 0103bd16fb90 ("mm: prepare VM_DONTDUMP for using in drivers") Reported-by: Kenneth Penza Signed-off-by: Daniel Black Reviewed-by: Mike Kravetz Cc: Konstantin Khlebnikov Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/madvise.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/madvise.c b/mm/madvise.c index 972a9eaa898b..71d21df2a3f3 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -96,7 +96,7 @@ static long madvise_behavior(struct vm_area_struct *vma, new_flags |= VM_DONTDUMP; break; case MADV_DODUMP: - if (new_flags & VM_SPECIAL) { + if (!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL) { error = -EINVAL; goto out; } -- cgit v1.2.3