From 3212b535f200c85b5a67cbfaea18431da71b5c72 Mon Sep 17 00:00:00 2001 From: Steve Capper Date: Tue, 23 Apr 2013 12:35:02 +0100 Subject: mm: hugetlb: Copy huge_pmd_share from x86 to mm. Under x86, multiple puds can be made to reference the same bank of huge pmds provided that they represent a full PUD_SIZE of shared huge memory that is aligned to a PUD_SIZE boundary. The code to share pmds does not require any architecture specific knowledge other than the fact that pmds can be indexed, thus can be beneficial to some other architectures. This patch copies the huge pmd sharing (and unsharing) logic from x86/ to mm/ and introduces a new config option to activate it: CONFIG_ARCH_WANTS_HUGE_PMD_SHARE Signed-off-by: Steve Capper Acked-by: Catalin Marinas Acked-by: Andrew Morton --- mm/hugetlb.c | 122 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 122 insertions(+) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f8feeeca6686..b0bfb292350e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3169,6 +3169,128 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed) hugetlb_acct_memory(h, -(chg - freed)); } +#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +static unsigned long page_table_shareable(struct vm_area_struct *svma, + struct vm_area_struct *vma, + unsigned long addr, pgoff_t idx) +{ + unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) + + svma->vm_start; + unsigned long sbase = saddr & PUD_MASK; + unsigned long s_end = sbase + PUD_SIZE; + + /* Allow segments to share if only one is marked locked */ + unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED; + unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED; + + /* + * match the virtual addresses, permission and the alignment of the + * page table page. + */ + if (pmd_index(addr) != pmd_index(saddr) || + vm_flags != svm_flags || + sbase < svma->vm_start || svma->vm_end < s_end) + return 0; + + return saddr; +} + +static int vma_shareable(struct vm_area_struct *vma, unsigned long addr) +{ + unsigned long base = addr & PUD_MASK; + unsigned long end = base + PUD_SIZE; + + /* + * check on proper vm_flags and page table alignment + */ + if (vma->vm_flags & VM_MAYSHARE && + vma->vm_start <= base && end <= vma->vm_end) + return 1; + return 0; +} + +/* + * 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 + * !shared pmd case because we can allocate the pmd later as well, it makes the + * code much cleaner. pmd allocation is essential for the shared case because + * pud has to be populated inside the same i_mmap_mutex section - otherwise + * racing tasks could either miss the sharing (see huge_pte_offset) or select a + * bad pmd for sharing. + */ +pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) +{ + struct vm_area_struct *vma = find_vma(mm, addr); + struct address_space *mapping = vma->vm_file->f_mapping; + pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + + vma->vm_pgoff; + struct vm_area_struct *svma; + unsigned long saddr; + pte_t *spte = NULL; + pte_t *pte; + + if (!vma_shareable(vma, addr)) + return (pte_t *)pmd_alloc(mm, pud, addr); + + mutex_lock(&mapping->i_mmap_mutex); + vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { + if (svma == vma) + continue; + + saddr = page_table_shareable(svma, vma, addr, idx); + if (saddr) { + spte = huge_pte_offset(svma->vm_mm, saddr); + if (spte) { + get_page(virt_to_page(spte)); + break; + } + } + } + + if (!spte) + goto out; + + spin_lock(&mm->page_table_lock); + if (pud_none(*pud)) + pud_populate(mm, pud, + (pmd_t *)((unsigned long)spte & PAGE_MASK)); + else + put_page(virt_to_page(spte)); + spin_unlock(&mm->page_table_lock); +out: + pte = (pte_t *)pmd_alloc(mm, pud, addr); + mutex_unlock(&mapping->i_mmap_mutex); + return pte; +} + +/* + * unmap huge page backed by shared pte. + * + * Hugetlb pte page is ref counted at the time of mapping. If pte is shared + * indicated by page_count > 1, unmap is achieved by clearing pud and + * decrementing the ref count. If count == 1, the pte page is not shared. + * + * called with vma->vm_mm->page_table_lock held. + * + * returns: 1 successfully unmapped a shared pte page + * 0 the underlying pte page is not shared, or it is the last user + */ +int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) +{ + pgd_t *pgd = pgd_offset(mm, *addr); + pud_t *pud = pud_offset(pgd, *addr); + + BUG_ON(page_count(virt_to_page(ptep)) == 0); + if (page_count(virt_to_page(ptep)) == 1) + return 0; + + pud_clear(pud); + put_page(virt_to_page(ptep)); + *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE; + return 1; +} +#endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ + #ifdef CONFIG_MEMORY_FAILURE /* Should be called in hugetlb_lock */ -- cgit v1.2.3 From 9e5fc74c30250566ff9154effdb17d6d18952052 Mon Sep 17 00:00:00 2001 From: Steve Capper Date: Tue, 30 Apr 2013 08:02:03 +0100 Subject: mm: hugetlb: Copy general hugetlb code from x86 to mm. The huge_pte_alloc, huge_pte_offset and follow_huge_p[mu]d functions in x86/mm/hugetlbpage.c do not rely on any architecture specific knowledge other than the fact that pmds and puds can be treated as huge ptes. To allow other architectures to use this code (and reduce the need for code duplication), this patch copies these functions into mm, replaces the use of pud_large with pud_huge and provides a config flag to activate them: CONFIG_ARCH_WANT_GENERAL_HUGETLB If CONFIG_ARCH_WANT_HUGE_PMD_SHARE is also active then the huge_pmd_share code will be called by huge_pte_alloc (othewise we call pmd_alloc and skip the sharing code). Signed-off-by: Steve Capper Acked-by: Catalin Marinas Acked-by: Andrew Morton --- mm/hugetlb.c | 97 ++++++++++++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 88 insertions(+), 9 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b0bfb292350e..63217261fd14 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2931,15 +2931,6 @@ out_mutex: return ret; } -/* Can be overriden by architectures */ -__attribute__((weak)) struct page * -follow_huge_pud(struct mm_struct *mm, unsigned long address, - pud_t *pud, int write) -{ - BUG(); - return NULL; -} - long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page **pages, struct vm_area_struct **vmas, unsigned long *position, unsigned long *nr_pages, @@ -3289,8 +3280,96 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE; return 1; } +#define want_pmd_share() (1) +#else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ +pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) +{ + return NULL; +} +#define want_pmd_share() (0) #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ +#ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) +{ + pgd_t *pgd; + pud_t *pud; + pte_t *pte = NULL; + + pgd = pgd_offset(mm, addr); + pud = pud_alloc(mm, pgd, addr); + if (pud) { + if (sz == PUD_SIZE) { + pte = (pte_t *)pud; + } else { + BUG_ON(sz != PMD_SIZE); + if (want_pmd_share() && pud_none(*pud)) + pte = huge_pmd_share(mm, addr, pud); + else + pte = (pte_t *)pmd_alloc(mm, pud, addr); + } + } + BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte)); + + return pte; +} + +pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd = NULL; + + pgd = pgd_offset(mm, addr); + if (pgd_present(*pgd)) { + pud = pud_offset(pgd, addr); + if (pud_present(*pud)) { + if (pud_huge(*pud)) + return (pte_t *)pud; + pmd = pmd_offset(pud, addr); + } + } + return (pte_t *) pmd; +} + +struct page * +follow_huge_pmd(struct mm_struct *mm, unsigned long address, + pmd_t *pmd, int write) +{ + struct page *page; + + page = pte_page(*(pte_t *)pmd); + if (page) + page += ((address & ~PMD_MASK) >> PAGE_SHIFT); + return page; +} + +struct page * +follow_huge_pud(struct mm_struct *mm, unsigned long address, + pud_t *pud, int write) +{ + struct page *page; + + page = pte_page(*(pte_t *)pud); + if (page) + page += ((address & ~PUD_MASK) >> PAGE_SHIFT); + return page; +} + +#else /* !CONFIG_ARCH_WANT_GENERAL_HUGETLB */ + +/* Can be overriden by architectures */ +__attribute__((weak)) struct page * +follow_huge_pud(struct mm_struct *mm, unsigned long address, + pud_t *pud, int write) +{ + BUG(); + return NULL; +} + +#endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ + #ifdef CONFIG_MEMORY_FAILURE /* Should be called in hugetlb_lock */ -- cgit v1.2.3 From 13d60f4b6ab5b702dc8d2ee20999f98a93728aec Mon Sep 17 00:00:00 2001 From: Zhang Yi Date: Tue, 25 Jun 2013 21:19:31 +0800 Subject: futex: Take hugepages into account when generating futex_key The futex_keys of process shared futexes are generated from the page offset, the mapping host and the mapping index of the futex user space address. This should result in an unique identifier for each futex. Though this is not true when futexes are located in different subpages of an hugepage. The reason is, that the mapping index for all those futexes evaluates to the index of the base page of the hugetlbfs mapping. So a futex at offset 0 of the hugepage mapping and another one at offset PAGE_SIZE of the same hugepage mapping have identical futex_keys. This happens because the futex code blindly uses page->index. Steps to reproduce the bug: 1. Map a file from hugetlbfs. Initialize pthread_mutex1 at offset 0 and pthread_mutex2 at offset PAGE_SIZE of the hugetlbfs mapping. The mutexes must be initialized as PTHREAD_PROCESS_SHARED because PTHREAD_PROCESS_PRIVATE mutexes are not affected by this issue as their keys solely depend on the user space address. 2. Lock mutex1 and mutex2 3. Create thread1 and in the thread function lock mutex1, which results in thread1 blocking on the locked mutex1. 4. Create thread2 and in the thread function lock mutex2, which results in thread2 blocking on the locked mutex2. 5. Unlock mutex2. Despite the fact that mutex2 got unlocked, thread2 still blocks on mutex2 because the futex_key points to mutex1. To solve this issue we need to take the normal page index of the page which contains the futex into account, if the futex is in an hugetlbfs mapping. In other words, we calculate the normal page mapping index of the subpage in the hugetlbfs mapping. Mappings which are not based on hugetlbfs are not affected and still use page->index. Thanks to Mel Gorman who provided a patch for adding proper evaluation functions to the hugetlbfs code to avoid exposing hugetlbfs specific details to the futex code. [ tglx: Massaged changelog ] Signed-off-by: Zhang Yi Reviewed-by: Jiang Biao Tested-by: Ma Chenggong Reviewed-by: 'Mel Gorman' Acked-by: 'Darren Hart' Cc: 'Peter Zijlstra' Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/000101ce71a6%24a83c5880%24f8b50980%24@com Signed-off-by: Thomas Gleixner --- mm/hugetlb.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f8feeeca6686..aea87ced4268 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -690,6 +690,23 @@ int PageHuge(struct page *page) } EXPORT_SYMBOL_GPL(PageHuge); +pgoff_t __basepage_index(struct page *page) +{ + struct page *page_head = compound_head(page); + pgoff_t index = page_index(page_head); + unsigned long compound_idx; + + if (!PageHuge(page_head)) + return page_index(page); + + if (compound_order(page_head) >= MAX_ORDER) + compound_idx = page_to_pfn(page) - page_to_pfn(page_head); + else + compound_idx = page - page_head; + + return (index << compound_order(page_head)) + compound_idx; +} + static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) { struct page *page; -- cgit v1.2.3 From 2415cf12e04d415b16d9c2f2a705bcd6cd9a0474 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Wed, 3 Jul 2013 15:02:43 -0700 Subject: mm/hugetlb: use already existing interface huge_page_shift Use the already existing interface huge_page_shift instead of h->order + PAGE_SHIFT. Signed-off-by: Wanpeng Li Cc: KAMEZAWA Hiroyuki Cc: David Rientjes Cc: Benjamin Herrenschmidt Reviewed-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index aed085ad11a8..fe095158859e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -319,7 +319,7 @@ unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) hstate = hstate_vma(vma); - return 1UL << (hstate->order + PAGE_SHIFT); + return 1UL << huge_page_shift(hstate); } EXPORT_SYMBOL_GPL(vma_kernel_pagesize); -- cgit v1.2.3 From 3dcc0571cd64816309765b7c7e4691a4cadf2ee7 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Wed, 3 Jul 2013 15:03:21 -0700 Subject: mm: correctly update zone->managed_pages Enhance adjust_managed_page_count() to adjust totalhigh_pages for highmem pages. And change code which directly adjusts totalram_pages to use adjust_managed_page_count() because it adjusts totalram_pages, totalhigh_pages and zone->managed_pages altogether in a safe way. Remove inc_totalhigh_pages() and dec_totalhigh_pages() from xen/balloon driver bacause adjust_managed_page_count() has already adjusted totalhigh_pages. This patch also fixes two bugs: 1) enhances virtio_balloon driver to adjust totalhigh_pages when reserve/unreserve pages. 2) enhance memory_hotplug.c to adjust totalhigh_pages when hot-removing memory. We still need to deal with modifications of totalram_pages in file arch/powerpc/platforms/pseries/cmm.c, but need help from PPC experts. [akpm@linux-foundation.org: remove ifdef, per Wanpeng Li, virtio_balloon.c cleanup, per Sergei] [akpm@linux-foundation.org: export adjust_managed_page_count() to modules, for drivers/virtio/virtio_balloon.c] Signed-off-by: Jiang Liu Cc: Chris Metcalf Cc: Rusty Russell Cc: "Michael S. Tsirkin" Cc: Konrad Rzeszutek Wilk Cc: Jeremy Fitzhardinge Cc: Wen Congyang Cc: Tang Chen Cc: Yasuaki Ishimatsu Cc: Mel Gorman Cc: Minchan Kim Cc: "H. Peter Anvin" Cc: Cc: Arnd Bergmann Cc: Catalin Marinas Cc: David Howells Cc: Geert Uytterhoeven Cc: Ingo Molnar Cc: Jianguo Wu Cc: Joonsoo Kim Cc: Kamezawa Hiroyuki Cc: Marek Szyprowski Cc: Michel Lespinasse Cc: Rik van Riel Cc: Tejun Heo Cc: Thomas Gleixner Cc: Will Deacon Cc: Yinghai Lu Cc: Russell King Cc: Sergei Shtylyov Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index fe095158859e..83aff0a4d093 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1263,7 +1263,7 @@ static void __init gather_bootmem_prealloc(void) * side-effects, like CommitLimit going negative. */ if (h->order > (MAX_ORDER - 1)) - totalram_pages += 1 << h->order; + adjust_managed_page_count(page, 1 << h->order); } } -- cgit v1.2.3