From 78ddc53473419073ffb2e91178001e87bc513524 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 15 Jan 2016 16:52:42 -0800 Subject: thp: rename split_huge_page_pmd() to split_huge_pmd() We are going to decouple splitting THP PMD from splitting underlying compound page. This patch renames split_huge_page_pmd*() functions to split_huge_pmd*() to reflect the fact that it doesn't imply page splitting, only PMD. Signed-off-by: Kirill A. Shutemov Tested-by: Sasha Levin Tested-by: Aneesh Kumar K.V Acked-by: Jerome Marchand Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Hugh Dickins Cc: Dave Hansen Cc: Mel Gorman Cc: Rik van Riel Cc: Naoya Horiguchi Cc: Steve Capper Cc: Johannes Weiner Cc: Michal Hocko Cc: Christoph Lameter Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/vm86_32.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 483231ebbb0b..e574b8546518 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -175,7 +175,11 @@ static void mark_screen_rdonly(struct mm_struct *mm) if (pud_none_or_clear_bad(pud)) goto out; pmd = pmd_offset(pud, 0xA0000); - split_huge_page_pmd_mm(mm, 0xA0000, pmd); + + if (pmd_trans_huge(*pmd)) { + struct vm_area_struct *vma = find_vma(mm, 0xA0000); + split_huge_pmd(vma, pmd, 0xA0000); + } if (pmd_none_or_clear_bad(pmd)) goto out; pte = pte_offset_map_lock(mm, pmd, 0xA0000, &ptl); -- cgit v1.2.3 From ddc58f27f9eee9117219936f77e90ad5b2e00e96 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 15 Jan 2016 16:52:56 -0800 Subject: mm: drop tail page refcounting Tail page refcounting is utterly complicated and painful to support. It uses ->_mapcount on tail pages to store how many times this page is pinned. get_page() bumps ->_mapcount on tail page in addition to ->_count on head. This information is required by split_huge_page() to be able to distribute pins from head of compound page to tails during the split. We will need ->_mapcount to account PTE mappings of subpages of the compound page. We eliminate need in current meaning of ->_mapcount in tail pages by forbidding split entirely if the page is pinned. The only user of tail page refcounting is THP which is marked BROKEN for now. Let's drop all this mess. It makes get_page() and put_page() much simpler. Signed-off-by: Kirill A. Shutemov Tested-by: Sasha Levin Tested-by: Aneesh Kumar K.V Acked-by: Vlastimil Babka Acked-by: Jerome Marchand Cc: Andrea Arcangeli Cc: Hugh Dickins Cc: Dave Hansen Cc: Mel Gorman Cc: Rik van Riel Cc: Naoya Horiguchi Cc: Steve Capper Cc: Johannes Weiner Cc: Michal Hocko Cc: Christoph Lameter Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/mips/mm/gup.c | 4 - arch/powerpc/mm/hugetlbpage.c | 13 +- arch/s390/mm/gup.c | 13 +- arch/sparc/mm/gup.c | 14 +-- arch/x86/mm/gup.c | 4 - include/linux/mm.h | 47 ++------ include/linux/mm_types.h | 17 +-- mm/gup.c | 34 +----- mm/huge_memory.c | 41 +------ mm/hugetlb.c | 2 +- mm/internal.h | 44 ------- mm/swap.c | 273 +++--------------------------------------- 12 files changed, 40 insertions(+), 466 deletions(-) (limited to 'arch/x86') diff --git a/arch/mips/mm/gup.c b/arch/mips/mm/gup.c index 349995d19c7f..36a35115dc2e 100644 --- a/arch/mips/mm/gup.c +++ b/arch/mips/mm/gup.c @@ -87,8 +87,6 @@ static int gup_huge_pmd(pmd_t pmd, unsigned long addr, unsigned long end, do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; - if (PageTail(page)) - get_huge_page_tail(page); (*nr)++; page++; refs++; @@ -153,8 +151,6 @@ static int gup_huge_pud(pud_t pud, unsigned long addr, unsigned long end, do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; - if (PageTail(page)) - get_huge_page_tail(page); (*nr)++; page++; refs++; diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 61b8b7ccea4f..6bd3afa775d3 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -999,7 +999,7 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, { unsigned long mask; unsigned long pte_end; - struct page *head, *page, *tail; + struct page *head, *page; pte_t pte; int refs; @@ -1022,7 +1022,6 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, head = pte_page(pte); page = head + ((addr & (sz-1)) >> PAGE_SHIFT); - tail = page; do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; @@ -1044,15 +1043,5 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, return 0; } - /* - * Any tail page need their mapcount reference taken before we - * return. - */ - while (refs--) { - if (PageTail(tail)) - get_huge_page_tail(tail); - tail++; - } - return 1; } diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c index 21c74a71e2ab..1a2cad52babf 100644 --- a/arch/s390/mm/gup.c +++ b/arch/s390/mm/gup.c @@ -55,7 +55,7 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { unsigned long mask, result; - struct page *head, *page, *tail; + struct page *head, *page; int refs; result = write ? 0 : _SEGMENT_ENTRY_PROTECT; @@ -67,7 +67,6 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, refs = 0; head = pmd_page(pmd); page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - tail = page; do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; @@ -88,16 +87,6 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, return 0; } - /* - * Any tail page need their mapcount reference taken before we - * return. - */ - while (refs--) { - if (PageTail(tail)) - get_huge_page_tail(tail); - tail++; - } - return 1; } diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c index 2e5c4fc2daa9..9091c5daa2e1 100644 --- a/arch/sparc/mm/gup.c +++ b/arch/sparc/mm/gup.c @@ -56,8 +56,6 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, put_page(head); return 0; } - if (head != page) - get_huge_page_tail(page); pages[*nr] = page; (*nr)++; @@ -70,7 +68,7 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { - struct page *head, *page, *tail; + struct page *head, *page; int refs; if (!(pmd_val(pmd) & _PAGE_VALID)) @@ -82,7 +80,6 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, refs = 0; head = pmd_page(pmd); page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - tail = page; do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; @@ -103,15 +100,6 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, return 0; } - /* Any tail page need their mapcount reference taken before we - * return. - */ - while (refs--) { - if (PageTail(tail)) - get_huge_page_tail(tail); - tail++; - } - return 1; } diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index ae9a37bf1371..65b0261d4bf3 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -136,8 +136,6 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, do { VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; - if (PageTail(page)) - get_huge_page_tail(page); (*nr)++; page++; refs++; @@ -212,8 +210,6 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr, do { VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; - if (PageTail(page)) - get_huge_page_tail(page); (*nr)++; page++; refs++; diff --git a/include/linux/mm.h b/include/linux/mm.h index 839d9e9a1c38..34387351930c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -466,44 +466,9 @@ static inline int page_count(struct page *page) return atomic_read(&compound_head(page)->_count); } -static inline bool __compound_tail_refcounted(struct page *page) -{ - return PageAnon(page) && !PageSlab(page) && !PageHeadHuge(page); -} - -/* - * This takes a head page as parameter and tells if the - * tail page reference counting can be skipped. - * - * For this to be safe, PageSlab and PageHeadHuge must remain true on - * any given page where they return true here, until all tail pins - * have been released. - */ -static inline bool compound_tail_refcounted(struct page *page) -{ - VM_BUG_ON_PAGE(!PageHead(page), page); - return __compound_tail_refcounted(page); -} - -static inline void get_huge_page_tail(struct page *page) -{ - /* - * __split_huge_page_refcount() cannot run from under us. - */ - VM_BUG_ON_PAGE(!PageTail(page), page); - VM_BUG_ON_PAGE(page_mapcount(page) < 0, page); - VM_BUG_ON_PAGE(atomic_read(&page->_count) != 0, page); - if (compound_tail_refcounted(compound_head(page))) - atomic_inc(&page->_mapcount); -} - -extern bool __get_page_tail(struct page *page); - static inline void get_page(struct page *page) { - if (unlikely(PageTail(page))) - if (likely(__get_page_tail(page))) - return; + page = compound_head(page); /* * Getting a normal page or the head of a compound page * requires to already have an elevated page->_count. @@ -528,7 +493,15 @@ static inline void init_page_count(struct page *page) atomic_set(&page->_count, 1); } -void put_page(struct page *page); +void __put_page(struct page *page); + +static inline void put_page(struct page *page) +{ + page = compound_head(page); + if (put_page_testzero(page)) + __put_page(page); +} + void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6bc9a0ce2253..faf6fe88d6b3 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -81,20 +81,9 @@ struct page { union { /* - * Count of ptes mapped in - * mms, to show when page is - * mapped & limit reverse map - * searches. - * - * Used also for tail pages - * refcounting instead of - * _count. Tail pages cannot - * be mapped and keeping the - * tail page _count zero at - * all times guarantees - * get_page_unless_zero() will - * never succeed on tail - * pages. + * Count of ptes mapped in mms, to show + * when page is mapped & limit reverse + * map searches. */ atomic_t _mapcount; diff --git a/mm/gup.c b/mm/gup.c index 1c50b506888d..7017abea9fd6 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -130,7 +130,7 @@ retry: } if (flags & FOLL_GET) - get_page_foll(page); + get_page(page); if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) @@ -1153,7 +1153,7 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { - struct page *head, *page, *tail; + struct page *head, *page; int refs; if (write && !pmd_write(orig)) @@ -1162,7 +1162,6 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, refs = 0; head = pmd_page(orig); page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - tail = page; do { VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; @@ -1183,24 +1182,13 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, return 0; } - /* - * Any tail pages need their mapcount reference taken before we - * return. (This allows the THP code to bump their ref count when - * they are split into base pages). - */ - while (refs--) { - if (PageTail(tail)) - get_huge_page_tail(tail); - tail++; - } - return 1; } static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { - struct page *head, *page, *tail; + struct page *head, *page; int refs; if (write && !pud_write(orig)) @@ -1209,7 +1197,6 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, refs = 0; head = pud_page(orig); page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT); - tail = page; do { VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; @@ -1230,12 +1217,6 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, return 0; } - while (refs--) { - if (PageTail(tail)) - get_huge_page_tail(tail); - tail++; - } - return 1; } @@ -1244,7 +1225,7 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, struct page **pages, int *nr) { int refs; - struct page *head, *page, *tail; + struct page *head, *page; if (write && !pgd_write(orig)) return 0; @@ -1252,7 +1233,6 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, refs = 0; head = pgd_page(orig); page = head + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT); - tail = page; do { VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; @@ -1273,12 +1253,6 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, return 0; } - while (refs--) { - if (PageTail(tail)) - get_huge_page_tail(tail); - tail++; - } - return 1; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 016b70ab5ed4..72fd53fe2b61 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1038,37 +1038,6 @@ unlock: spin_unlock(ptl); } -/* - * Save CONFIG_DEBUG_PAGEALLOC from faulting falsely on tail pages - * during copy_user_huge_page()'s copy_page_rep(): in the case when - * the source page gets split and a tail freed before copy completes. - * Called under pmd_lock of checked pmd, so safe from splitting itself. - */ -static void get_user_huge_page(struct page *page) -{ - if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) { - struct page *endpage = page + HPAGE_PMD_NR; - - atomic_add(HPAGE_PMD_NR, &page->_count); - while (++page < endpage) - get_huge_page_tail(page); - } else { - get_page(page); - } -} - -static void put_user_huge_page(struct page *page) -{ - if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) { - struct page *endpage = page + HPAGE_PMD_NR; - - while (page < endpage) - put_page(page++); - } else { - put_page(page); - } -} - static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, @@ -1221,7 +1190,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, ret |= VM_FAULT_WRITE; goto out_unlock; } - get_user_huge_page(page); + get_page(page); spin_unlock(ptl); alloc: if (transparent_hugepage_enabled(vma) && @@ -1242,7 +1211,7 @@ alloc: split_huge_pmd(vma, pmd, address); ret |= VM_FAULT_FALLBACK; } - put_user_huge_page(page); + put_page(page); } count_vm_event(THP_FAULT_FALLBACK); goto out; @@ -1253,7 +1222,7 @@ alloc: put_page(new_page); if (page) { split_huge_pmd(vma, pmd, address); - put_user_huge_page(page); + put_page(page); } else split_huge_pmd(vma, pmd, address); ret |= VM_FAULT_FALLBACK; @@ -1275,7 +1244,7 @@ alloc: spin_lock(ptl); if (page) - put_user_huge_page(page); + put_page(page); if (unlikely(!pmd_same(*pmd, orig_pmd))) { spin_unlock(ptl); mem_cgroup_cancel_charge(new_page, memcg, true); @@ -1360,7 +1329,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; VM_BUG_ON_PAGE(!PageCompound(page), page); if (flags & FOLL_GET) - get_page_foll(page); + get_page(page); out: return page; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e924529f7b38..84af842e828d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3865,7 +3865,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, same_page: if (pages) { pages[i] = mem_map_offset(page, pfn_offset); - get_page_foll(pages[i]); + get_page(pages[i]); } if (vmas) diff --git a/mm/internal.h b/mm/internal.h index 38e24b89e4c4..569facd1f6da 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -66,50 +66,6 @@ static inline void set_page_refcounted(struct page *page) set_page_count(page, 1); } -static inline void __get_page_tail_foll(struct page *page, - bool get_page_head) -{ - /* - * If we're getting a tail page, the elevated page->_count is - * required only in the head page and we will elevate the head - * page->_count and tail page->_mapcount. - * - * We elevate page_tail->_mapcount for tail pages to force - * page_tail->_count to be zero at all times to avoid getting - * false positives from get_page_unless_zero() with - * speculative page access (like in - * page_cache_get_speculative()) on tail pages. - */ - VM_BUG_ON_PAGE(atomic_read(&compound_head(page)->_count) <= 0, page); - if (get_page_head) - atomic_inc(&compound_head(page)->_count); - get_huge_page_tail(page); -} - -/* - * This is meant to be called as the FOLL_GET operation of - * follow_page() and it must be called while holding the proper PT - * lock while the pte (or pmd_trans_huge) is still mapping the page. - */ -static inline void get_page_foll(struct page *page) -{ - if (unlikely(PageTail(page))) - /* - * This is safe only because - * __split_huge_page_refcount() can't run under - * get_page_foll() because we hold the proper PT lock. - */ - __get_page_tail_foll(page, true); - else { - /* - * Getting a normal page or the head of a compound page - * requires to already have an elevated page->_count. - */ - VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page); - atomic_inc(&page->_count); - } -} - extern unsigned long highest_memmap_pfn; /* diff --git a/mm/swap.c b/mm/swap.c index 39395fb549c0..3d65480422e8 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -89,260 +89,14 @@ static void __put_compound_page(struct page *page) (*dtor)(page); } -/** - * Two special cases here: we could avoid taking compound_lock_irqsave - * and could skip the tail refcounting(in _mapcount). - * - * 1. Hugetlbfs page: - * - * PageHeadHuge will remain true until the compound page - * is released and enters the buddy allocator, and it could - * not be split by __split_huge_page_refcount(). - * - * So if we see PageHeadHuge set, and we have the tail page pin, - * then we could safely put head page. - * - * 2. Slab THP page: - * - * PG_slab is cleared before the slab frees the head page, and - * tail pin cannot be the last reference left on the head page, - * because the slab code is free to reuse the compound page - * after a kfree/kmem_cache_free without having to check if - * there's any tail pin left. In turn all tail pinsmust be always - * released while the head is still pinned by the slab code - * and so we know PG_slab will be still set too. - * - * So if we see PageSlab set, and we have the tail page pin, - * then we could safely put head page. - */ -static __always_inline -void put_unrefcounted_compound_page(struct page *page_head, struct page *page) -{ - /* - * If @page is a THP tail, we must read the tail page - * flags after the head page flags. The - * __split_huge_page_refcount side enforces write memory barriers - * between clearing PageTail and before the head page - * can be freed and reallocated. - */ - smp_rmb(); - if (likely(PageTail(page))) { - /* - * __split_huge_page_refcount cannot race - * here, see the comment above this function. - */ - VM_BUG_ON_PAGE(!PageHead(page_head), page_head); - if (put_page_testzero(page_head)) { - /* - * If this is the tail of a slab THP page, - * the tail pin must not be the last reference - * held on the page, because the PG_slab cannot - * be cleared before all tail pins (which skips - * the _mapcount tail refcounting) have been - * released. - * - * If this is the tail of a hugetlbfs page, - * the tail pin may be the last reference on - * the page instead, because PageHeadHuge will - * not go away until the compound page enters - * the buddy allocator. - */ - VM_BUG_ON_PAGE(PageSlab(page_head), page_head); - __put_compound_page(page_head); - } - } else - /* - * __split_huge_page_refcount run before us, - * @page was a THP tail. The split @page_head - * has been freed and reallocated as slab or - * hugetlbfs page of smaller order (only - * possible if reallocated as slab on x86). - */ - if (put_page_testzero(page)) - __put_single_page(page); -} - -static __always_inline -void put_refcounted_compound_page(struct page *page_head, struct page *page) -{ - if (likely(page != page_head && get_page_unless_zero(page_head))) { - unsigned long flags; - - /* - * @page_head wasn't a dangling pointer but it may not - * be a head page anymore by the time we obtain the - * lock. That is ok as long as it can't be freed from - * under us. - */ - flags = compound_lock_irqsave(page_head); - if (unlikely(!PageTail(page))) { - /* __split_huge_page_refcount run before us */ - compound_unlock_irqrestore(page_head, flags); - if (put_page_testzero(page_head)) { - /* - * The @page_head may have been freed - * and reallocated as a compound page - * of smaller order and then freed - * again. All we know is that it - * cannot have become: a THP page, a - * compound page of higher order, a - * tail page. That is because we - * still hold the refcount of the - * split THP tail and page_head was - * the THP head before the split. - */ - if (PageHead(page_head)) - __put_compound_page(page_head); - else - __put_single_page(page_head); - } -out_put_single: - if (put_page_testzero(page)) - __put_single_page(page); - return; - } - VM_BUG_ON_PAGE(page_head != compound_head(page), page); - /* - * We can release the refcount taken by - * get_page_unless_zero() now that - * __split_huge_page_refcount() is blocked on the - * compound_lock. - */ - if (put_page_testzero(page_head)) - VM_BUG_ON_PAGE(1, page_head); - /* __split_huge_page_refcount will wait now */ - VM_BUG_ON_PAGE(page_mapcount(page) <= 0, page); - atomic_dec(&page->_mapcount); - VM_BUG_ON_PAGE(atomic_read(&page_head->_count) <= 0, page_head); - VM_BUG_ON_PAGE(atomic_read(&page->_count) != 0, page); - compound_unlock_irqrestore(page_head, flags); - - if (put_page_testzero(page_head)) { - if (PageHead(page_head)) - __put_compound_page(page_head); - else - __put_single_page(page_head); - } - } else { - /* @page_head is a dangling pointer */ - VM_BUG_ON_PAGE(PageTail(page), page); - goto out_put_single; - } -} - -static void put_compound_page(struct page *page) -{ - struct page *page_head; - - /* - * We see the PageCompound set and PageTail not set, so @page maybe: - * 1. hugetlbfs head page, or - * 2. THP head page. - */ - if (likely(!PageTail(page))) { - if (put_page_testzero(page)) { - /* - * By the time all refcounts have been released - * split_huge_page cannot run anymore from under us. - */ - if (PageHead(page)) - __put_compound_page(page); - else - __put_single_page(page); - } - return; - } - - /* - * We see the PageCompound set and PageTail set, so @page maybe: - * 1. a tail hugetlbfs page, or - * 2. a tail THP page, or - * 3. a split THP page. - * - * Case 3 is possible, as we may race with - * __split_huge_page_refcount tearing down a THP page. - */ - page_head = compound_head(page); - if (!__compound_tail_refcounted(page_head)) - put_unrefcounted_compound_page(page_head, page); - else - put_refcounted_compound_page(page_head, page); -} - -void put_page(struct page *page) +void __put_page(struct page *page) { if (unlikely(PageCompound(page))) - put_compound_page(page); - else if (put_page_testzero(page)) + __put_compound_page(page); + else __put_single_page(page); } -EXPORT_SYMBOL(put_page); - -/* - * This function is exported but must not be called by anything other - * than get_page(). It implements the slow path of get_page(). - */ -bool __get_page_tail(struct page *page) -{ - /* - * This takes care of get_page() if run on a tail page - * returned by one of the get_user_pages/follow_page variants. - * get_user_pages/follow_page itself doesn't need the compound - * lock because it runs __get_page_tail_foll() under the - * proper PT lock that already serializes against - * split_huge_page(). - */ - unsigned long flags; - bool got; - struct page *page_head = compound_head(page); - - /* Ref to put_compound_page() comment. */ - if (!__compound_tail_refcounted(page_head)) { - smp_rmb(); - if (likely(PageTail(page))) { - /* - * This is a hugetlbfs page or a slab - * page. __split_huge_page_refcount - * cannot race here. - */ - VM_BUG_ON_PAGE(!PageHead(page_head), page_head); - __get_page_tail_foll(page, true); - return true; - } else { - /* - * __split_huge_page_refcount run - * before us, "page" was a THP - * tail. The split page_head has been - * freed and reallocated as slab or - * hugetlbfs page of smaller order - * (only possible if reallocated as - * slab on x86). - */ - return false; - } - } - - got = false; - if (likely(page != page_head && get_page_unless_zero(page_head))) { - /* - * page_head wasn't a dangling pointer but it - * may not be a head page anymore by the time - * we obtain the lock. That is ok as long as it - * can't be freed from under us. - */ - flags = compound_lock_irqsave(page_head); - /* here __split_huge_page_refcount won't run anymore */ - if (likely(PageTail(page))) { - __get_page_tail_foll(page, false); - got = true; - } - compound_unlock_irqrestore(page_head, flags); - if (unlikely(!got)) - put_page(page_head); - } - return got; -} -EXPORT_SYMBOL(__get_page_tail); +EXPORT_SYMBOL(__put_page); /** * put_pages_list() - release a list of pages @@ -918,15 +672,6 @@ void release_pages(struct page **pages, int nr, bool cold) for (i = 0; i < nr; i++) { struct page *page = pages[i]; - if (unlikely(PageCompound(page))) { - if (zone) { - spin_unlock_irqrestore(&zone->lru_lock, flags); - zone = NULL; - } - put_compound_page(page); - continue; - } - /* * Make sure the IRQ-safe lock-holding time does not get * excessive with a continuous string of pages from the @@ -937,9 +682,19 @@ void release_pages(struct page **pages, int nr, bool cold) zone = NULL; } + page = compound_head(page); if (!put_page_testzero(page)) continue; + if (PageCompound(page)) { + if (zone) { + spin_unlock_irqrestore(&zone->lru_lock, flags); + zone = NULL; + } + __put_compound_page(page); + continue; + } + if (PageLRU(page)) { struct zone *pagezone = page_zone(page); -- cgit v1.2.3 From 1f19617d775879c0863e697fb648154e56918051 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 15 Jan 2016 16:53:35 -0800 Subject: x86, thp: remove infrastructure for handling splitting PMDs With new refcounting we don't need to mark PMDs splitting. Let's drop code to handle this. Signed-off-by: Kirill A. Shutemov Tested-by: Sasha Levin Acked-by: Jerome Marchand Cc: Aneesh Kumar K.V Cc: Vlastimil Babka Cc: Andrea Arcangeli Cc: Hugh Dickins Cc: Dave Hansen Cc: Mel Gorman Cc: Rik van Riel Cc: Naoya Horiguchi Cc: Steve Capper Cc: Johannes Weiner Cc: Michal Hocko Cc: Christoph Lameter Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/pgtable.h | 9 --------- arch/x86/include/asm/pgtable_types.h | 2 -- arch/x86/mm/gup.c | 13 +------------ arch/x86/mm/pgtable.c | 13 ------------- 4 files changed, 1 insertion(+), 36 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index d3eee663c41f..61e706c9f710 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -162,11 +162,6 @@ static inline int pmd_large(pmd_t pte) } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -static inline int pmd_trans_splitting(pmd_t pmd) -{ - return pmd_val(pmd) & _PAGE_SPLITTING; -} - static inline int pmd_trans_huge(pmd_t pmd) { return pmd_val(pmd) & _PAGE_PSE; @@ -808,10 +803,6 @@ extern int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); -#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH -extern void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmdp); - #define __HAVE_ARCH_PMD_WRITE static inline int pmd_write(pmd_t pmd) { diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index a471cadb9630..d1b76f88ccd1 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -22,7 +22,6 @@ #define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */ #define _PAGE_BIT_SPECIAL _PAGE_BIT_SOFTW1 #define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1 -#define _PAGE_BIT_SPLITTING _PAGE_BIT_SOFTW2 /* only valid on a PSE pmd */ #define _PAGE_BIT_HIDDEN _PAGE_BIT_SOFTW3 /* hidden by kmemcheck */ #define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */ #define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ @@ -46,7 +45,6 @@ #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) #define _PAGE_SPECIAL (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL) #define _PAGE_CPA_TEST (_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST) -#define _PAGE_SPLITTING (_AT(pteval_t, 1) << _PAGE_BIT_SPLITTING) #define __HAVE_ARCH_PTE_SPECIAL #ifdef CONFIG_KMEMCHECK diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index 65b0261d4bf3..f8cb3e8ac250 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -156,18 +156,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, pmd_t pmd = *pmdp; next = pmd_addr_end(addr, end); - /* - * The pmd_trans_splitting() check below explains why - * pmdp_splitting_flush has to flush the tlb, to stop - * this gup-fast code from running while we set the - * splitting bit in the pmd. Returning zero will take - * the slow path that will call wait_split_huge_page() - * if the pmd is still in splitting state. gup-fast - * can't because it has irq disabled and - * wait_split_huge_page() would never return as the - * tlb flush IPI wouldn't run. - */ - if (pmd_none(pmd) || pmd_trans_splitting(pmd)) + if (pmd_none(pmd)) return 0; if (unlikely(pmd_large(pmd) || !pmd_present(pmd))) { /* diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index ee9c2e3a7199..4eb287e25043 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -505,19 +505,6 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, return young; } - -void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp) -{ - int set; - VM_BUG_ON(address & ~HPAGE_PMD_MASK); - set = !test_and_set_bit(_PAGE_BIT_SPLITTING, - (unsigned long *)pmdp); - if (set) { - /* need tlb flush only to serialize against gup-fast */ - flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); - } -} #endif /** -- cgit v1.2.3 From 590a471ce92355bc6c93a48769e8616b80071991 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Fri, 15 Jan 2016 16:55:20 -0800 Subject: arch/x86/include/asm/pgtable.h: add pmd_[dirty|mkclean] for THP MADV_FREE needs pmd_dirty and pmd_mkclean for detecting recent overwrite of the contents since MADV_FREE syscall is called for THP page. This patch adds pmd_dirty and pmd_mkclean for THP page MADV_FREE support. Signed-off-by: Minchan Kim Cc: "James E.J. Bottomley" Cc: "Kirill A. Shutemov" Cc: Shaohua Li Cc: Cc: Andrea Arcangeli Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Chen Gang Cc: Chris Zankel Cc: Daniel Micay Cc: Darrick J. Wong Cc: David S. Miller Cc: Helge Deller Cc: Hugh Dickins Cc: Ivan Kokshaysky Cc: Jason Evans Cc: Johannes Weiner Cc: KOSAKI Motohiro Cc: Kirill A. Shutemov Cc: Matt Turner Cc: Max Filippov Cc: Mel Gorman Cc: Michael Kerrisk Cc: Michal Hocko Cc: Mika Penttil Cc: Ralf Baechle Cc: Richard Henderson Cc: Rik van Riel Cc: Roland Dreier Cc: Russell King Cc: Shaohua Li Cc: Will Deacon Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/pgtable.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 61e706c9f710..4973cc9eacce 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -266,6 +266,11 @@ static inline pmd_t pmd_mkold(pmd_t pmd) return pmd_clear_flags(pmd, _PAGE_ACCESSED); } +static inline pmd_t pmd_mkclean(pmd_t pmd) +{ + return pmd_clear_flags(pmd, _PAGE_DIRTY); +} + static inline pmd_t pmd_wrprotect(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_RW); -- cgit v1.2.3 From 52db400fcd50216dd8511a0880b936235755836f Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 15 Jan 2016 16:55:49 -0800 Subject: pmem, dax: clean up clear_pmem() To date, we have implemented two I/O usage models for persistent memory, PMEM (a persistent "ram disk") and DAX (mmap persistent memory into userspace). This series adds a third, DAX-GUP, that allows DAX mappings to be the target of direct-i/o. It allows userspace to coordinate DMA/RDMA from/to persistent memory. The implementation leverages the ZONE_DEVICE mm-zone that went into 4.3-rc1 (also discussed at kernel summit) to flag pages that are owned and dynamically mapped by a device driver. The pmem driver, after mapping a persistent memory range into the system memmap via devm_memremap_pages(), arranges for DAX to distinguish pfn-only versus page-backed pmem-pfns via flags in the new pfn_t type. The DAX code, upon seeing a PFN_DEV+PFN_MAP flagged pfn, flags the resulting pte(s) inserted into the process page tables with a new _PAGE_DEVMAP flag. Later, when get_user_pages() is walking ptes it keys off _PAGE_DEVMAP to pin the device hosting the page range active. Finally, get_page() and put_page() are modified to take references against the device driver established page mapping. Finally, this need for "struct page" for persistent memory requires memory capacity to store the memmap array. Given the memmap array for a large pool of persistent may exhaust available DRAM introduce a mechanism to allocate the memmap from persistent memory. The new "struct vmem_altmap *" parameter to devm_memremap_pages() enables arch_add_memory() to use reserved pmem capacity rather than the page allocator. This patch (of 25): Both __dax_pmd_fault, and clear_pmem() were taking special steps to clear memory a page at a time to take advantage of non-temporal clear_page() implementations. However, x86_64 does not use non-temporal instructions for clear_page(), and arch_clear_pmem() was always incurring the cost of __arch_wb_cache_pmem(). Clean up the assumption that doing clear_pmem() a page at a time is more performant. Signed-off-by: Dan Williams Reported-by: Dave Hansen Reviewed-by: Ross Zwisler Reviewed-by: Jeff Moyer Cc: "H. Peter Anvin" Cc: Alexander Viro Cc: Andrea Arcangeli Cc: Christoffer Dall Cc: Christoph Hellwig Cc: Dave Chinner Cc: David Airlie Cc: Ingo Molnar Cc: Jan Kara Cc: Jeff Dike Cc: Jens Axboe Cc: Kirill A. Shutemov Cc: Logan Gunthorpe Cc: Matthew Wilcox Cc: Mel Gorman Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Richard Weinberger Cc: Thomas Gleixner Cc: Toshi Kani Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/pmem.h | 7 +------ fs/dax.c | 4 +--- 2 files changed, 2 insertions(+), 9 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h index d8ce3ec816ab..1544fabcd7f9 100644 --- a/arch/x86/include/asm/pmem.h +++ b/arch/x86/include/asm/pmem.h @@ -132,12 +132,7 @@ static inline void arch_clear_pmem(void __pmem *addr, size_t size) { void *vaddr = (void __force *)addr; - /* TODO: implement the zeroing via non-temporal writes */ - if (size == PAGE_SIZE && ((unsigned long)vaddr & ~PAGE_MASK) == 0) - clear_page(vaddr); - else - memset(vaddr, 0, size); - + memset(vaddr, 0, size); __arch_wb_cache_pmem(vaddr, size); } diff --git a/fs/dax.c b/fs/dax.c index 43671b68220e..19492cc65a30 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -641,9 +641,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, goto fallback; if (buffer_unwritten(&bh) || buffer_new(&bh)) { - int i; - for (i = 0; i < PTRS_PER_PMD; i++) - clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE); + clear_pmem(kaddr, PMD_SIZE); wmb_pmem(); count_vm_event(PGMAJFAULT); mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); -- cgit v1.2.3 From ba049e93aef7e8c571567088b1b73f4f5b99272a Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 15 Jan 2016 16:56:11 -0800 Subject: kvm: rename pfn_t to kvm_pfn_t To date, we have implemented two I/O usage models for persistent memory, PMEM (a persistent "ram disk") and DAX (mmap persistent memory into userspace). This series adds a third, DAX-GUP, that allows DAX mappings to be the target of direct-i/o. It allows userspace to coordinate DMA/RDMA from/to persistent memory. The implementation leverages the ZONE_DEVICE mm-zone that went into 4.3-rc1 (also discussed at kernel summit) to flag pages that are owned and dynamically mapped by a device driver. The pmem driver, after mapping a persistent memory range into the system memmap via devm_memremap_pages(), arranges for DAX to distinguish pfn-only versus page-backed pmem-pfns via flags in the new pfn_t type. The DAX code, upon seeing a PFN_DEV+PFN_MAP flagged pfn, flags the resulting pte(s) inserted into the process page tables with a new _PAGE_DEVMAP flag. Later, when get_user_pages() is walking ptes it keys off _PAGE_DEVMAP to pin the device hosting the page range active. Finally, get_page() and put_page() are modified to take references against the device driver established page mapping. Finally, this need for "struct page" for persistent memory requires memory capacity to store the memmap array. Given the memmap array for a large pool of persistent may exhaust available DRAM introduce a mechanism to allocate the memmap from persistent memory. The new "struct vmem_altmap *" parameter to devm_memremap_pages() enables arch_add_memory() to use reserved pmem capacity rather than the page allocator. This patch (of 18): The core has developed a need for a "pfn_t" type [1]. Move the existing pfn_t in KVM to kvm_pfn_t [2]. [1]: https://lists.01.org/pipermail/linux-nvdimm/2015-September/002199.html [2]: https://lists.01.org/pipermail/linux-nvdimm/2015-September/002218.html Signed-off-by: Dan Williams Acked-by: Christoffer Dall Cc: Paolo Bonzini Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/include/asm/kvm_mmu.h | 5 ++-- arch/arm/kvm/mmu.c | 10 ++++---- arch/arm64/include/asm/kvm_mmu.h | 3 ++- arch/mips/include/asm/kvm_host.h | 6 ++--- arch/mips/kvm/emulate.c | 2 +- arch/mips/kvm/tlb.c | 14 +++++------ arch/powerpc/include/asm/kvm_book3s.h | 4 +-- arch/powerpc/include/asm/kvm_ppc.h | 2 +- arch/powerpc/kvm/book3s.c | 6 ++--- arch/powerpc/kvm/book3s_32_mmu_host.c | 2 +- arch/powerpc/kvm/book3s_64_mmu_host.c | 2 +- arch/powerpc/kvm/e500.h | 2 +- arch/powerpc/kvm/e500_mmu_host.c | 8 +++--- arch/powerpc/kvm/trace_pr.h | 2 +- arch/x86/kvm/iommu.c | 11 ++++---- arch/x86/kvm/mmu.c | 37 +++++++++++++-------------- arch/x86/kvm/mmu_audit.c | 2 +- arch/x86/kvm/paging_tmpl.h | 6 ++--- arch/x86/kvm/vmx.c | 2 +- arch/x86/kvm/x86.c | 2 +- include/linux/kvm_host.h | 37 +++++++++++++-------------- include/linux/kvm_types.h | 2 +- virt/kvm/kvm_main.c | 47 ++++++++++++++++++----------------- 23 files changed, 110 insertions(+), 104 deletions(-) (limited to 'arch/x86') diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 9203c21b4673..a520b7987a29 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -182,7 +182,8 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101; } -static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, +static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, + kvm_pfn_t pfn, unsigned long size, bool ipa_uncached) { @@ -246,7 +247,7 @@ static inline void __kvm_flush_dcache_pte(pte_t pte) static inline void __kvm_flush_dcache_pmd(pmd_t pmd) { unsigned long size = PMD_SIZE; - pfn_t pfn = pmd_pfn(pmd); + kvm_pfn_t pfn = pmd_pfn(pmd); while (size) { void *va = kmap_atomic_pfn(pfn); diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 22f7fa0124ec..aba61fd3697a 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -992,9 +992,9 @@ out: return ret; } -static bool transparent_hugepage_adjust(pfn_t *pfnp, phys_addr_t *ipap) +static bool transparent_hugepage_adjust(kvm_pfn_t *pfnp, phys_addr_t *ipap) { - pfn_t pfn = *pfnp; + kvm_pfn_t pfn = *pfnp; gfn_t gfn = *ipap >> PAGE_SHIFT; if (PageTransCompound(pfn_to_page(pfn))) { @@ -1201,7 +1201,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); } -static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, +static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, kvm_pfn_t pfn, unsigned long size, bool uncached) { __coherent_cache_guest_page(vcpu, pfn, size, uncached); @@ -1218,7 +1218,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm *kvm = vcpu->kvm; struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache; struct vm_area_struct *vma; - pfn_t pfn; + kvm_pfn_t pfn; pgprot_t mem_type = PAGE_S2; bool fault_ipa_uncached; bool logging_active = memslot_is_logging(memslot); @@ -1346,7 +1346,7 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) { pmd_t *pmd; pte_t *pte; - pfn_t pfn; + kvm_pfn_t pfn; bool pfn_valid = false; trace_kvm_access_fault(fault_ipa); diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 0bf8b4320a91..736433912a1e 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -230,7 +230,8 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101; } -static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, +static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, + kvm_pfn_t pfn, unsigned long size, bool ipa_uncached) { diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 6ded8d347af9..7c191443c7ea 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -101,9 +101,9 @@ #define CAUSEF_DC (_ULCAST_(1) << 27) extern atomic_t kvm_mips_instance; -extern pfn_t(*kvm_mips_gfn_to_pfn) (struct kvm *kvm, gfn_t gfn); -extern void (*kvm_mips_release_pfn_clean) (pfn_t pfn); -extern bool(*kvm_mips_is_error_pfn) (pfn_t pfn); +extern kvm_pfn_t (*kvm_mips_gfn_to_pfn)(struct kvm *kvm, gfn_t gfn); +extern void (*kvm_mips_release_pfn_clean)(kvm_pfn_t pfn); +extern bool (*kvm_mips_is_error_pfn)(kvm_pfn_t pfn); struct kvm_vm_stat { u32 remote_tlb_flush; diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 41b1b090f56f..1b675c7ce89f 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -1525,7 +1525,7 @@ int kvm_mips_sync_icache(unsigned long va, struct kvm_vcpu *vcpu) struct kvm *kvm = vcpu->kvm; unsigned long pa; gfn_t gfn; - pfn_t pfn; + kvm_pfn_t pfn; gfn = va >> PAGE_SHIFT; diff --git a/arch/mips/kvm/tlb.c b/arch/mips/kvm/tlb.c index aed0ac2a4972..570479c03bdc 100644 --- a/arch/mips/kvm/tlb.c +++ b/arch/mips/kvm/tlb.c @@ -38,13 +38,13 @@ atomic_t kvm_mips_instance; EXPORT_SYMBOL(kvm_mips_instance); /* These function pointers are initialized once the KVM module is loaded */ -pfn_t (*kvm_mips_gfn_to_pfn)(struct kvm *kvm, gfn_t gfn); +kvm_pfn_t (*kvm_mips_gfn_to_pfn)(struct kvm *kvm, gfn_t gfn); EXPORT_SYMBOL(kvm_mips_gfn_to_pfn); -void (*kvm_mips_release_pfn_clean)(pfn_t pfn); +void (*kvm_mips_release_pfn_clean)(kvm_pfn_t pfn); EXPORT_SYMBOL(kvm_mips_release_pfn_clean); -bool (*kvm_mips_is_error_pfn)(pfn_t pfn); +bool (*kvm_mips_is_error_pfn)(kvm_pfn_t pfn); EXPORT_SYMBOL(kvm_mips_is_error_pfn); uint32_t kvm_mips_get_kernel_asid(struct kvm_vcpu *vcpu) @@ -144,7 +144,7 @@ EXPORT_SYMBOL(kvm_mips_dump_guest_tlbs); static int kvm_mips_map_page(struct kvm *kvm, gfn_t gfn) { int srcu_idx, err = 0; - pfn_t pfn; + kvm_pfn_t pfn; if (kvm->arch.guest_pmap[gfn] != KVM_INVALID_PAGE) return 0; @@ -262,7 +262,7 @@ int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr, struct kvm_vcpu *vcpu) { gfn_t gfn; - pfn_t pfn0, pfn1; + kvm_pfn_t pfn0, pfn1; unsigned long vaddr = 0; unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0; int even; @@ -313,7 +313,7 @@ EXPORT_SYMBOL(kvm_mips_handle_kseg0_tlb_fault); int kvm_mips_handle_commpage_tlb_fault(unsigned long badvaddr, struct kvm_vcpu *vcpu) { - pfn_t pfn0, pfn1; + kvm_pfn_t pfn0, pfn1; unsigned long flags, old_entryhi = 0, vaddr = 0; unsigned long entrylo0 = 0, entrylo1 = 0; @@ -360,7 +360,7 @@ int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu, { unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0; struct kvm *kvm = vcpu->kvm; - pfn_t pfn0, pfn1; + kvm_pfn_t pfn0, pfn1; if ((tlb->tlb_hi & VPN2_MASK) == 0) { pfn0 = 0; diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 9fac01cb89c1..8f39796c9da8 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -154,8 +154,8 @@ extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat, bool upper, u32 val); extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr); extern int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu); -extern pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, bool writing, - bool *writable); +extern kvm_pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, + bool writing, bool *writable); extern void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev, unsigned long *rmap, long pte_index, int realmode); extern void kvmppc_update_rmap_change(unsigned long *rmap, unsigned long psize); diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index c6ef05bd0765..2241d5357129 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -515,7 +515,7 @@ void kvmppc_claim_lpid(long lpid); void kvmppc_free_lpid(long lpid); void kvmppc_init_lpid(unsigned long nr_lpids); -static inline void kvmppc_mmu_flush_icache(pfn_t pfn) +static inline void kvmppc_mmu_flush_icache(kvm_pfn_t pfn) { struct page *page; /* diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 099c79d8c160..638c6d9be9e0 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -366,7 +366,7 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvmppc_core_prepare_to_enter); -pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, bool writing, +kvm_pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, bool writing, bool *writable) { ulong mp_pa = vcpu->arch.magic_page_pa & KVM_PAM; @@ -379,9 +379,9 @@ pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, bool writing, gpa &= ~0xFFFULL; if (unlikely(mp_pa) && unlikely((gpa & KVM_PAM) == mp_pa)) { ulong shared_page = ((ulong)vcpu->arch.shared) & PAGE_MASK; - pfn_t pfn; + kvm_pfn_t pfn; - pfn = (pfn_t)virt_to_phys((void*)shared_page) >> PAGE_SHIFT; + pfn = (kvm_pfn_t)virt_to_phys((void*)shared_page) >> PAGE_SHIFT; get_page(pfn_to_page(pfn)); if (writable) *writable = true; diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c index d5c9bfeb0c9c..55c4d51ea3e2 100644 --- a/arch/powerpc/kvm/book3s_32_mmu_host.c +++ b/arch/powerpc/kvm/book3s_32_mmu_host.c @@ -142,7 +142,7 @@ extern char etext[]; int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte, bool iswrite) { - pfn_t hpaddr; + kvm_pfn_t hpaddr; u64 vpn; u64 vsid; struct kvmppc_sid_map *map; diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c index 79ad35abd196..913cd2198fa6 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_host.c +++ b/arch/powerpc/kvm/book3s_64_mmu_host.c @@ -83,7 +83,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte, bool iswrite) { unsigned long vpn; - pfn_t hpaddr; + kvm_pfn_t hpaddr; ulong hash, hpteg; u64 vsid; int ret; diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index 72920bed3ac6..94f04fcb373e 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -41,7 +41,7 @@ enum vcpu_ftr { #define E500_TLB_MAS2_ATTR (0x7f) struct tlbe_ref { - pfn_t pfn; /* valid only for TLB0, except briefly */ + kvm_pfn_t pfn; /* valid only for TLB0, except briefly */ unsigned int flags; /* E500_TLB_* */ }; diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index 34c43fff4adb..b0333cc737dd 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -163,9 +163,9 @@ void kvmppc_map_magic(struct kvm_vcpu *vcpu) struct kvm_book3e_206_tlb_entry magic; ulong shared_page = ((ulong)vcpu->arch.shared) & PAGE_MASK; unsigned int stid; - pfn_t pfn; + kvm_pfn_t pfn; - pfn = (pfn_t)virt_to_phys((void *)shared_page) >> PAGE_SHIFT; + pfn = (kvm_pfn_t)virt_to_phys((void *)shared_page) >> PAGE_SHIFT; get_page(pfn_to_page(pfn)); preempt_disable(); @@ -246,7 +246,7 @@ static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe) static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, struct kvm_book3e_206_tlb_entry *gtlbe, - pfn_t pfn, unsigned int wimg) + kvm_pfn_t pfn, unsigned int wimg) { ref->pfn = pfn; ref->flags = E500_TLB_VALID; @@ -309,7 +309,7 @@ static void kvmppc_e500_setup_stlbe( int tsize, struct tlbe_ref *ref, u64 gvaddr, struct kvm_book3e_206_tlb_entry *stlbe) { - pfn_t pfn = ref->pfn; + kvm_pfn_t pfn = ref->pfn; u32 pr = vcpu->arch.shared->msr & MSR_PR; BUG_ON(!(ref->flags & E500_TLB_VALID)); diff --git a/arch/powerpc/kvm/trace_pr.h b/arch/powerpc/kvm/trace_pr.h index 810507cb688a..d44f324184fb 100644 --- a/arch/powerpc/kvm/trace_pr.h +++ b/arch/powerpc/kvm/trace_pr.h @@ -30,7 +30,7 @@ TRACE_EVENT(kvm_book3s_reenter, #ifdef CONFIG_PPC_BOOK3S_64 TRACE_EVENT(kvm_book3s_64_mmu_map, - TP_PROTO(int rflags, ulong hpteg, ulong va, pfn_t hpaddr, + TP_PROTO(int rflags, ulong hpteg, ulong va, kvm_pfn_t hpaddr, struct kvmppc_pte *orig_pte), TP_ARGS(rflags, hpteg, va, hpaddr, orig_pte), diff --git a/arch/x86/kvm/iommu.c b/arch/x86/kvm/iommu.c index 5c520ebf6343..a22a488b4622 100644 --- a/arch/x86/kvm/iommu.c +++ b/arch/x86/kvm/iommu.c @@ -43,11 +43,11 @@ static int kvm_iommu_unmap_memslots(struct kvm *kvm); static void kvm_iommu_put_pages(struct kvm *kvm, gfn_t base_gfn, unsigned long npages); -static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, +static kvm_pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, unsigned long npages) { gfn_t end_gfn; - pfn_t pfn; + kvm_pfn_t pfn; pfn = gfn_to_pfn_memslot(slot, gfn); end_gfn = gfn + npages; @@ -62,7 +62,8 @@ static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, return pfn; } -static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages) +static void kvm_unpin_pages(struct kvm *kvm, kvm_pfn_t pfn, + unsigned long npages) { unsigned long i; @@ -73,7 +74,7 @@ static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages) int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) { gfn_t gfn, end_gfn; - pfn_t pfn; + kvm_pfn_t pfn; int r = 0; struct iommu_domain *domain = kvm->arch.iommu_domain; int flags; @@ -275,7 +276,7 @@ static void kvm_iommu_put_pages(struct kvm *kvm, { struct iommu_domain *domain; gfn_t end_gfn, gfn; - pfn_t pfn; + kvm_pfn_t pfn; u64 phys; domain = kvm->arch.iommu_domain; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 420a5ca3c0ee..95a955de5964 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -259,7 +259,7 @@ static unsigned get_mmio_spte_access(u64 spte) } static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, - pfn_t pfn, unsigned access) + kvm_pfn_t pfn, unsigned access) { if (unlikely(is_noslot_pfn(pfn))) { mark_mmio_spte(vcpu, sptep, gfn, access); @@ -320,7 +320,7 @@ static int is_last_spte(u64 pte, int level) return 0; } -static pfn_t spte_to_pfn(u64 pte) +static kvm_pfn_t spte_to_pfn(u64 pte) { return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; } @@ -582,7 +582,7 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte) */ static int mmu_spte_clear_track_bits(u64 *sptep) { - pfn_t pfn; + kvm_pfn_t pfn; u64 old_spte = *sptep; if (!spte_has_volatile_bits(old_spte)) @@ -1372,7 +1372,7 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, int need_flush = 0; u64 new_spte; pte_t *ptep = (pte_t *)data; - pfn_t new_pfn; + kvm_pfn_t new_pfn; WARN_ON(pte_huge(*ptep)); new_pfn = pte_pfn(*ptep); @@ -2450,7 +2450,7 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, return 0; } -static bool kvm_is_mmio_pfn(pfn_t pfn) +static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) { if (pfn_valid(pfn)) return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)); @@ -2460,7 +2460,7 @@ static bool kvm_is_mmio_pfn(pfn_t pfn) static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, int level, - gfn_t gfn, pfn_t pfn, bool speculative, + gfn_t gfn, kvm_pfn_t pfn, bool speculative, bool can_unsync, bool host_writable) { u64 spte; @@ -2539,7 +2539,7 @@ done: } static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, - int write_fault, int level, gfn_t gfn, pfn_t pfn, + int write_fault, int level, gfn_t gfn, kvm_pfn_t pfn, bool speculative, bool host_writable) { int was_rmapped = 0; @@ -2602,7 +2602,7 @@ static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, return emulate; } -static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, +static kvm_pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool no_dirty_log) { struct kvm_memory_slot *slot; @@ -2684,7 +2684,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) } static int __direct_map(struct kvm_vcpu *vcpu, int write, int map_writable, - int level, gfn_t gfn, pfn_t pfn, bool prefault) + int level, gfn_t gfn, kvm_pfn_t pfn, bool prefault) { struct kvm_shadow_walk_iterator iterator; struct kvm_mmu_page *sp; @@ -2732,7 +2732,7 @@ static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct * send_sig_info(SIGBUS, &info, tsk); } -static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, pfn_t pfn) +static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) { /* * Do not cache the mmio info caused by writing the readonly gfn @@ -2752,9 +2752,10 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, pfn_t pfn) } static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, - gfn_t *gfnp, pfn_t *pfnp, int *levelp) + gfn_t *gfnp, kvm_pfn_t *pfnp, + int *levelp) { - pfn_t pfn = *pfnp; + kvm_pfn_t pfn = *pfnp; gfn_t gfn = *gfnp; int level = *levelp; @@ -2793,7 +2794,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, } static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, - pfn_t pfn, unsigned access, int *ret_val) + kvm_pfn_t pfn, unsigned access, int *ret_val) { bool ret = true; @@ -2947,7 +2948,7 @@ exit: } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, pfn_t *pfn, bool write, bool *writable); + gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable); static void make_mmu_pages_available(struct kvm_vcpu *vcpu); static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, @@ -2956,7 +2957,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, int r; int level; bool force_pt_level = false; - pfn_t pfn; + kvm_pfn_t pfn; unsigned long mmu_seq; bool map_writable, write = error_code & PFERR_WRITE_MASK; @@ -3410,7 +3411,7 @@ static bool can_do_async_pf(struct kvm_vcpu *vcpu) } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, pfn_t *pfn, bool write, bool *writable) + gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable) { struct kvm_memory_slot *slot; bool async; @@ -3448,7 +3449,7 @@ check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level) static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, bool prefault) { - pfn_t pfn; + kvm_pfn_t pfn; int r; int level; bool force_pt_level; @@ -4601,7 +4602,7 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, u64 *sptep; struct rmap_iterator iter; int need_tlb_flush = 0; - pfn_t pfn; + kvm_pfn_t pfn; struct kvm_mmu_page *sp; restart: diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index 1cee3ec20dd2..dcce533d420c 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -97,7 +97,7 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level) { struct kvm_mmu_page *sp; gfn_t gfn; - pfn_t pfn; + kvm_pfn_t pfn; hpa_t hpa; sp = page_header(__pa(sptep)); diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 91e939b486d1..6c9fed957cce 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -456,7 +456,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, { unsigned pte_access; gfn_t gfn; - pfn_t pfn; + kvm_pfn_t pfn; if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte)) return false; @@ -551,7 +551,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, struct guest_walker *gw, int write_fault, int hlevel, - pfn_t pfn, bool map_writable, bool prefault) + kvm_pfn_t pfn, bool map_writable, bool prefault) { struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; @@ -694,7 +694,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, int user_fault = error_code & PFERR_USER_MASK; struct guest_walker walker; int r; - pfn_t pfn; + kvm_pfn_t pfn; int level = PT_PAGE_TABLE_LEVEL; bool force_pt_level = false; unsigned long mmu_seq; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 04d61d496b14..e2951b6edbbc 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -4251,7 +4251,7 @@ out: static int init_rmode_identity_map(struct kvm *kvm) { int i, idx, r = 0; - pfn_t identity_map_pfn; + kvm_pfn_t identity_map_pfn; u32 tmp; if (!enable_ept) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f53f5b13c677..4244c2baf57d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5148,7 +5148,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, int emulation_type) { gpa_t gpa = cr2; - pfn_t pfn; + kvm_pfn_t pfn; if (emulation_type & EMULTYPE_NO_REEXECUTE) return false; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f707f74055c3..861f690aa791 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -66,7 +66,7 @@ * error pfns indicate that the gfn is in slot but faild to * translate it to pfn on host. */ -static inline bool is_error_pfn(pfn_t pfn) +static inline bool is_error_pfn(kvm_pfn_t pfn) { return !!(pfn & KVM_PFN_ERR_MASK); } @@ -76,13 +76,13 @@ static inline bool is_error_pfn(pfn_t pfn) * translated to pfn - it is not in slot or failed to * translate it to pfn. */ -static inline bool is_error_noslot_pfn(pfn_t pfn) +static inline bool is_error_noslot_pfn(kvm_pfn_t pfn) { return !!(pfn & KVM_PFN_ERR_NOSLOT_MASK); } /* noslot pfn indicates that the gfn is not in slot. */ -static inline bool is_noslot_pfn(pfn_t pfn) +static inline bool is_noslot_pfn(kvm_pfn_t pfn) { return pfn == KVM_PFN_NOSLOT; } @@ -591,19 +591,20 @@ void kvm_release_page_clean(struct page *page); void kvm_release_page_dirty(struct page *page); void kvm_set_page_accessed(struct page *page); -pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn); -pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); -pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, +kvm_pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn); +kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); +kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable); -pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn); -pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn); -pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, - bool *async, bool write_fault, bool *writable); +kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn); +kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn); +kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, + bool atomic, bool *async, bool write_fault, + bool *writable); -void kvm_release_pfn_clean(pfn_t pfn); -void kvm_set_pfn_dirty(pfn_t pfn); -void kvm_set_pfn_accessed(pfn_t pfn); -void kvm_get_pfn(pfn_t pfn); +void kvm_release_pfn_clean(kvm_pfn_t pfn); +void kvm_set_pfn_dirty(kvm_pfn_t pfn); +void kvm_set_pfn_accessed(kvm_pfn_t pfn); +void kvm_get_pfn(kvm_pfn_t pfn); int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len); @@ -629,8 +630,8 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn); struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn); -pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); -pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); +kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); +kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable); @@ -811,7 +812,7 @@ void kvm_arch_sync_events(struct kvm *kvm); int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); -bool kvm_is_reserved_pfn(pfn_t pfn); +bool kvm_is_reserved_pfn(kvm_pfn_t pfn); struct kvm_irq_ack_notifier { struct hlist_node link; @@ -965,7 +966,7 @@ static inline gfn_t gpa_to_gfn(gpa_t gpa) return (gfn_t)(gpa >> PAGE_SHIFT); } -static inline hpa_t pfn_to_hpa(pfn_t pfn) +static inline hpa_t pfn_to_hpa(kvm_pfn_t pfn) { return (hpa_t)pfn << PAGE_SHIFT; } diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 1b47a185c2f0..8bf259dae9f6 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -53,7 +53,7 @@ typedef unsigned long hva_t; typedef u64 hpa_t; typedef u64 hfn_t; -typedef hfn_t pfn_t; +typedef hfn_t kvm_pfn_t; struct gfn_to_hva_cache { u64 generation; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 314c7774652e..a11cfd20a6a0 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -111,7 +111,7 @@ static void hardware_disable_all(void); static void kvm_io_bus_destroy(struct kvm_io_bus *bus); -static void kvm_release_pfn_dirty(pfn_t pfn); +static void kvm_release_pfn_dirty(kvm_pfn_t pfn); static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn); __visible bool kvm_rebooting; @@ -119,7 +119,7 @@ EXPORT_SYMBOL_GPL(kvm_rebooting); static bool largepages_enabled = true; -bool kvm_is_reserved_pfn(pfn_t pfn) +bool kvm_is_reserved_pfn(kvm_pfn_t pfn) { if (pfn_valid(pfn)) return PageReserved(pfn_to_page(pfn)); @@ -1289,7 +1289,7 @@ static inline int check_user_page_hwpoison(unsigned long addr) * true indicates success, otherwise false is returned. */ static bool hva_to_pfn_fast(unsigned long addr, bool atomic, bool *async, - bool write_fault, bool *writable, pfn_t *pfn) + bool write_fault, bool *writable, kvm_pfn_t *pfn) { struct page *page[1]; int npages; @@ -1322,7 +1322,7 @@ static bool hva_to_pfn_fast(unsigned long addr, bool atomic, bool *async, * 1 indicates success, -errno is returned if error is detected. */ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault, - bool *writable, pfn_t *pfn) + bool *writable, kvm_pfn_t *pfn) { struct page *page[1]; int npages = 0; @@ -1386,11 +1386,11 @@ static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault) * 2): @write_fault = false && @writable, @writable will tell the caller * whether the mapping is writable. */ -static pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async, +static kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async, bool write_fault, bool *writable) { struct vm_area_struct *vma; - pfn_t pfn = 0; + kvm_pfn_t pfn = 0; int npages; /* we can do it either atomically or asynchronously, not both */ @@ -1431,8 +1431,9 @@ exit: return pfn; } -pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, - bool *async, bool write_fault, bool *writable) +kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, + bool atomic, bool *async, bool write_fault, + bool *writable) { unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault); @@ -1453,7 +1454,7 @@ pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, } EXPORT_SYMBOL_GPL(__gfn_to_pfn_memslot); -pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, +kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable) { return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, NULL, @@ -1461,37 +1462,37 @@ pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, } EXPORT_SYMBOL_GPL(gfn_to_pfn_prot); -pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn) +kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot); -pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn) +kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn) { return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic); -pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn) +kvm_pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn) { return gfn_to_pfn_memslot_atomic(gfn_to_memslot(kvm, gfn), gfn); } EXPORT_SYMBOL_GPL(gfn_to_pfn_atomic); -pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn) +kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn) { return gfn_to_pfn_memslot_atomic(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn); } EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn_atomic); -pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) +kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) { return gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn); } EXPORT_SYMBOL_GPL(gfn_to_pfn); -pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn) +kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn) { return gfn_to_pfn_memslot(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn); } @@ -1514,7 +1515,7 @@ int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn, } EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic); -static struct page *kvm_pfn_to_page(pfn_t pfn) +static struct page *kvm_pfn_to_page(kvm_pfn_t pfn) { if (is_error_noslot_pfn(pfn)) return KVM_ERR_PTR_BAD_PAGE; @@ -1529,7 +1530,7 @@ static struct page *kvm_pfn_to_page(pfn_t pfn) struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) { - pfn_t pfn; + kvm_pfn_t pfn; pfn = gfn_to_pfn(kvm, gfn); @@ -1539,7 +1540,7 @@ EXPORT_SYMBOL_GPL(gfn_to_page); struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn) { - pfn_t pfn; + kvm_pfn_t pfn; pfn = kvm_vcpu_gfn_to_pfn(vcpu, gfn); @@ -1555,7 +1556,7 @@ void kvm_release_page_clean(struct page *page) } EXPORT_SYMBOL_GPL(kvm_release_page_clean); -void kvm_release_pfn_clean(pfn_t pfn) +void kvm_release_pfn_clean(kvm_pfn_t pfn) { if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn)) put_page(pfn_to_page(pfn)); @@ -1570,13 +1571,13 @@ void kvm_release_page_dirty(struct page *page) } EXPORT_SYMBOL_GPL(kvm_release_page_dirty); -static void kvm_release_pfn_dirty(pfn_t pfn) +static void kvm_release_pfn_dirty(kvm_pfn_t pfn) { kvm_set_pfn_dirty(pfn); kvm_release_pfn_clean(pfn); } -void kvm_set_pfn_dirty(pfn_t pfn) +void kvm_set_pfn_dirty(kvm_pfn_t pfn) { if (!kvm_is_reserved_pfn(pfn)) { struct page *page = pfn_to_page(pfn); @@ -1587,14 +1588,14 @@ void kvm_set_pfn_dirty(pfn_t pfn) } EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty); -void kvm_set_pfn_accessed(pfn_t pfn) +void kvm_set_pfn_accessed(kvm_pfn_t pfn) { if (!kvm_is_reserved_pfn(pfn)) mark_page_accessed(pfn_to_page(pfn)); } EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed); -void kvm_get_pfn(pfn_t pfn) +void kvm_get_pfn(kvm_pfn_t pfn) { if (!kvm_is_reserved_pfn(pfn)) get_page(pfn_to_page(pfn)); -- cgit v1.2.3 From 4b94ffdc4163bae1ec73b6e977ffb7a7da3d06d3 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 15 Jan 2016 16:56:22 -0800 Subject: x86, mm: introduce vmem_altmap to augment vmemmap_populate() In support of providing struct page for large persistent memory capacities, use struct vmem_altmap to change the default policy for allocating memory for the memmap array. The default vmemmap_populate() allocates page table storage area from the page allocator. Given persistent memory capacities relative to DRAM it may not be feasible to store the memmap in 'System Memory'. Instead vmem_altmap represents pre-allocated "device pages" to satisfy vmemmap_alloc_block_buf() requests. Signed-off-by: Dan Williams Reported-by: kbuild test robot Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/mm/init_64.c | 33 ++++++++++++++---- drivers/nvdimm/pmem.c | 6 ++-- include/linux/memory_hotplug.h | 3 +- include/linux/memremap.h | 39 +++++++++++++++++++--- include/linux/mm.h | 9 ++++- kernel/memremap.c | 72 +++++++++++++++++++++++++++++++++++++-- mm/memory_hotplug.c | 67 ++++++++++++++++++++++++++----------- mm/page_alloc.c | 11 +++++- mm/sparse-vmemmap.c | 76 ++++++++++++++++++++++++++++++++++++++++-- mm/sparse.c | 8 +++-- 10 files changed, 282 insertions(+), 42 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 8829482d69ec..5488d21123bd 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include #include @@ -714,6 +715,12 @@ static void __meminit free_pagetable(struct page *page, int order) { unsigned long magic; unsigned int nr_pages = 1 << order; + struct vmem_altmap *altmap = to_vmem_altmap((unsigned long) page); + + if (altmap) { + vmem_altmap_free(altmap, nr_pages); + return; + } /* bootmem page has reserved flag */ if (PageReserved(page)) { @@ -1017,13 +1024,19 @@ int __ref arch_remove_memory(u64 start, u64 size) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; + struct page *page = pfn_to_page(start_pfn); + struct vmem_altmap *altmap; struct zone *zone; int ret; - zone = page_zone(pfn_to_page(start_pfn)); - kernel_physical_mapping_remove(start, start + size); + /* With altmap the first mapped page is offset from @start */ + altmap = to_vmem_altmap((unsigned long) page); + if (altmap) + page += vmem_altmap_offset(altmap); + zone = page_zone(page); ret = __remove_pages(zone, start_pfn, nr_pages); WARN_ON_ONCE(ret); + kernel_physical_mapping_remove(start, start + size); return ret; } @@ -1235,7 +1248,7 @@ static void __meminitdata *p_start, *p_end; static int __meminitdata node_start; static int __meminit vmemmap_populate_hugepages(unsigned long start, - unsigned long end, int node) + unsigned long end, int node, struct vmem_altmap *altmap) { unsigned long addr; unsigned long next; @@ -1258,7 +1271,7 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, if (pmd_none(*pmd)) { void *p; - p = vmemmap_alloc_block_buf(PMD_SIZE, node); + p = __vmemmap_alloc_block_buf(PMD_SIZE, node, altmap); if (p) { pte_t entry; @@ -1279,7 +1292,8 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, addr_end = addr + PMD_SIZE; p_end = p + PMD_SIZE; continue; - } + } else if (altmap) + return -ENOMEM; /* no fallback */ } else if (pmd_large(*pmd)) { vmemmap_verify((pte_t *)pmd, node, addr, next); continue; @@ -1293,11 +1307,16 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) { + struct vmem_altmap *altmap = to_vmem_altmap(start); int err; if (cpu_has_pse) - err = vmemmap_populate_hugepages(start, end, node); - else + err = vmemmap_populate_hugepages(start, end, node, altmap); + else if (altmap) { + pr_err_once("%s: no cpu support for altmap allocations\n", + __func__); + err = -ENOMEM; + } else err = vmemmap_populate_basepages(start, end, node); if (!err) sync_global_pgds(start, end - 1, 0); diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 904629b97c4f..be3f8547b702 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -178,7 +178,8 @@ static struct pmem_device *pmem_alloc(struct device *dev, pmem->pfn_flags = PFN_DEV; if (pmem_should_map_pages(dev)) { - pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, res); + pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, res, + NULL); pmem->pfn_flags |= PFN_MAP; } else pmem->virt_addr = (void __pmem *) devm_memremap(dev, @@ -387,7 +388,8 @@ static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns) /* establish pfn range for lookup, and switch to direct map */ pmem = dev_get_drvdata(dev); devm_memunmap(dev, (void __force *) pmem->virt_addr); - pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, &nsio->res); + pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, &nsio->res, + NULL); pmem->pfn_flags |= PFN_MAP; if (IS_ERR(pmem->virt_addr)) { rc = PTR_ERR(pmem->virt_addr); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 2ea574ff9714..43405992d027 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -275,7 +275,8 @@ extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); extern void remove_memory(int nid, u64 start, u64 size); extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn); -extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms); +extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms, + unsigned long map_offset); extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); diff --git a/include/linux/memremap.h b/include/linux/memremap.h index d90721c178bb..aa3e82a80d7b 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -4,21 +4,53 @@ struct resource; struct device; + +/** + * struct vmem_altmap - pre-allocated storage for vmemmap_populate + * @base_pfn: base of the entire dev_pagemap mapping + * @reserve: pages mapped, but reserved for driver use (relative to @base) + * @free: free pages set aside in the mapping for memmap storage + * @align: pages reserved to meet allocation alignments + * @alloc: track pages consumed, private to vmemmap_populate() + */ +struct vmem_altmap { + const unsigned long base_pfn; + const unsigned long reserve; + unsigned long free; + unsigned long align; + unsigned long alloc; +}; + +unsigned long vmem_altmap_offset(struct vmem_altmap *altmap); +void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns); + +#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_ZONE_DEVICE) +struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start); +#else +static inline struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start) +{ + return NULL; +} +#endif + /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings + * @altmap: pre-allocated/reserved memory for vmemmap allocations * @dev: host device of the mapping for debug */ struct dev_pagemap { - /* TODO: vmem_altmap and percpu_ref count */ + struct vmem_altmap *altmap; + const struct resource *res; struct device *dev; }; #ifdef CONFIG_ZONE_DEVICE -void *devm_memremap_pages(struct device *dev, struct resource *res); +void *devm_memremap_pages(struct device *dev, struct resource *res, + struct vmem_altmap *altmap); struct dev_pagemap *find_dev_pagemap(resource_size_t phys); #else static inline void *devm_memremap_pages(struct device *dev, - struct resource *res) + struct resource *res, struct vmem_altmap *altmap) { /* * Fail attempts to call devm_memremap_pages() without @@ -34,5 +66,4 @@ static inline struct dev_pagemap *find_dev_pagemap(resource_size_t phys) return NULL; } #endif - #endif /* _LINUX_MEMREMAP_H_ */ diff --git a/include/linux/mm.h b/include/linux/mm.h index d9fe12d45c21..8bb0907a3603 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2217,7 +2217,14 @@ pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node); void *vmemmap_alloc_block(unsigned long size, int node); -void *vmemmap_alloc_block_buf(unsigned long size, int node); +struct vmem_altmap; +void *__vmemmap_alloc_block_buf(unsigned long size, int node, + struct vmem_altmap *altmap); +static inline void *vmemmap_alloc_block_buf(unsigned long size, int node) +{ + return __vmemmap_alloc_block_buf(size, node, NULL); +} + void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); int vmemmap_populate_basepages(unsigned long start, unsigned long end, int node); diff --git a/kernel/memremap.c b/kernel/memremap.c index 61cfbf4d3054..562f6471fe90 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -166,6 +166,7 @@ struct page_map { struct resource res; struct percpu_ref *ref; struct dev_pagemap pgmap; + struct vmem_altmap altmap; }; static void pgmap_radix_release(struct resource *res) @@ -183,6 +184,7 @@ static void devm_memremap_pages_release(struct device *dev, void *data) struct page_map *page_map = data; struct resource *res = &page_map->res; resource_size_t align_start, align_size; + struct dev_pagemap *pgmap = &page_map->pgmap; pgmap_radix_release(res); @@ -190,6 +192,8 @@ static void devm_memremap_pages_release(struct device *dev, void *data) align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(resource_size(res), SECTION_SIZE); arch_remove_memory(align_start, align_size); + dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc, + "%s: failed to free all reserved pages\n", __func__); } /* assumes rcu_read_lock() held at entry */ @@ -203,11 +207,23 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys) return page_map ? &page_map->pgmap : NULL; } -void *devm_memremap_pages(struct device *dev, struct resource *res) +/** + * devm_memremap_pages - remap and provide memmap backing for the given resource + * @dev: hosting device for @res + * @res: "host memory" address range + * @altmap: optional descriptor for allocating the memmap from @res + * + * Note, the expectation is that @res is a host memory range that could + * feasibly be treated as a "System RAM" range, i.e. not a device mmio + * range, but this is not enforced. + */ +void *devm_memremap_pages(struct device *dev, struct resource *res, + struct vmem_altmap *altmap) { int is_ram = region_intersects(res->start, resource_size(res), "System RAM"); resource_size_t key, align_start, align_size; + struct dev_pagemap *pgmap; struct page_map *page_map; int error, nid; @@ -220,14 +236,27 @@ void *devm_memremap_pages(struct device *dev, struct resource *res) if (is_ram == REGION_INTERSECTS) return __va(res->start); + if (altmap && !IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP)) { + dev_err(dev, "%s: altmap requires CONFIG_SPARSEMEM_VMEMMAP=y\n", + __func__); + return ERR_PTR(-ENXIO); + } + page_map = devres_alloc_node(devm_memremap_pages_release, sizeof(*page_map), GFP_KERNEL, dev_to_node(dev)); if (!page_map) return ERR_PTR(-ENOMEM); + pgmap = &page_map->pgmap; memcpy(&page_map->res, res, sizeof(*res)); - page_map->pgmap.dev = dev; + pgmap->dev = dev; + if (altmap) { + memcpy(&page_map->altmap, altmap, sizeof(*altmap)); + pgmap->altmap = &page_map->altmap; + } + pgmap->res = &page_map->res; + mutex_lock(&pgmap_lock); error = 0; for (key = res->start; key <= res->end; key += SECTION_SIZE) { @@ -273,4 +302,43 @@ void *devm_memremap_pages(struct device *dev, struct resource *res) return ERR_PTR(error); } EXPORT_SYMBOL(devm_memremap_pages); + +unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) +{ + /* number of pfns from base where pfn_to_page() is valid */ + return altmap->reserve + altmap->free; +} + +void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) +{ + altmap->alloc -= nr_pfns; +} + +#ifdef CONFIG_SPARSEMEM_VMEMMAP +struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start) +{ + /* + * 'memmap_start' is the virtual address for the first "struct + * page" in this range of the vmemmap array. In the case of + * CONFIG_SPARSE_VMEMMAP a page_to_pfn conversion is simple + * pointer arithmetic, so we can perform this to_vmem_altmap() + * conversion without concern for the initialization state of + * the struct page fields. + */ + struct page *page = (struct page *) memmap_start; + struct dev_pagemap *pgmap; + + /* + * Uncoditionally retrieve a dev_pagemap associated with the + * given physical address, this is only for use in the + * arch_{add|remove}_memory() for setting up and tearing down + * the memmap. + */ + rcu_read_lock(); + pgmap = find_dev_pagemap(__pfn_to_phys(page_to_pfn(page))); + rcu_read_unlock(); + + return pgmap ? pgmap->altmap : NULL; +} +#endif /* CONFIG_SPARSEMEM_VMEMMAP */ #endif /* CONFIG_ZONE_DEVICE */ diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 92f95952692b..4af58a3a8ffa 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -506,10 +507,25 @@ int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn, unsigned long i; int err = 0; int start_sec, end_sec; + struct vmem_altmap *altmap; + /* during initialize mem_map, align hot-added range to section */ start_sec = pfn_to_section_nr(phys_start_pfn); end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1); + altmap = to_vmem_altmap((unsigned long) pfn_to_page(phys_start_pfn)); + if (altmap) { + /* + * Validate altmap is within bounds of the total request + */ + if (altmap->base_pfn != phys_start_pfn + || vmem_altmap_offset(altmap) > nr_pages) { + pr_warn_once("memory add fail, invalid altmap\n"); + return -EINVAL; + } + altmap->alloc = 0; + } + for (i = start_sec; i <= end_sec; i++) { err = __add_section(nid, zone, section_nr_to_pfn(i)); @@ -731,7 +747,8 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn) pgdat_resize_unlock(zone->zone_pgdat, &flags); } -static int __remove_section(struct zone *zone, struct mem_section *ms) +static int __remove_section(struct zone *zone, struct mem_section *ms, + unsigned long map_offset) { unsigned long start_pfn; int scn_nr; @@ -748,7 +765,7 @@ static int __remove_section(struct zone *zone, struct mem_section *ms) start_pfn = section_nr_to_pfn(scn_nr); __remove_zone(zone, start_pfn); - sparse_remove_one_section(zone, ms); + sparse_remove_one_section(zone, ms, map_offset); return 0; } @@ -767,9 +784,32 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn, unsigned long nr_pages) { unsigned long i; - int sections_to_remove; - resource_size_t start, size; - int ret = 0; + unsigned long map_offset = 0; + int sections_to_remove, ret = 0; + + /* In the ZONE_DEVICE case device driver owns the memory region */ + if (is_dev_zone(zone)) { + struct page *page = pfn_to_page(phys_start_pfn); + struct vmem_altmap *altmap; + + altmap = to_vmem_altmap((unsigned long) page); + if (altmap) + map_offset = vmem_altmap_offset(altmap); + } else { + resource_size_t start, size; + + start = phys_start_pfn << PAGE_SHIFT; + size = nr_pages * PAGE_SIZE; + + ret = release_mem_region_adjustable(&iomem_resource, start, + size); + if (ret) { + resource_size_t endres = start + size - 1; + + pr_warn("Unable to release resource <%pa-%pa> (%d)\n", + &start, &endres, ret); + } + } /* * We can only remove entire sections @@ -777,23 +817,12 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn, BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK); BUG_ON(nr_pages % PAGES_PER_SECTION); - start = phys_start_pfn << PAGE_SHIFT; - size = nr_pages * PAGE_SIZE; - - /* in the ZONE_DEVICE case device driver owns the memory region */ - if (!is_dev_zone(zone)) - ret = release_mem_region_adjustable(&iomem_resource, start, size); - if (ret) { - resource_size_t endres = start + size - 1; - - pr_warn("Unable to release resource <%pa-%pa> (%d)\n", - &start, &endres, ret); - } - sections_to_remove = nr_pages / PAGES_PER_SECTION; for (i = 0; i < sections_to_remove; i++) { unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION; - ret = __remove_section(zone, __pfn_to_section(pfn)); + + ret = __remove_section(zone, __pfn_to_section(pfn), map_offset); + map_offset = 0; if (ret) break; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 25409714160e..7ca3fe6ef92d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include #include @@ -4485,8 +4486,9 @@ static inline unsigned long wait_table_bits(unsigned long size) void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, unsigned long start_pfn, enum memmap_context context) { - pg_data_t *pgdat = NODE_DATA(nid); + struct vmem_altmap *altmap = to_vmem_altmap(__pfn_to_phys(start_pfn)); unsigned long end_pfn = start_pfn + size; + pg_data_t *pgdat = NODE_DATA(nid); unsigned long pfn; struct zone *z; unsigned long nr_initialised = 0; @@ -4494,6 +4496,13 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, if (highest_memmap_pfn < end_pfn - 1) highest_memmap_pfn = end_pfn - 1; + /* + * Honor reservation requested by the driver for this ZONE_DEVICE + * memory + */ + if (altmap && start_pfn == altmap->base_pfn) + start_pfn += altmap->reserve; + z = &pgdat->node_zones[zone]; for (pfn = start_pfn; pfn < end_pfn; pfn++) { /* diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 4cba9c2783a1..b60802b3e5ea 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -70,7 +71,7 @@ void * __meminit vmemmap_alloc_block(unsigned long size, int node) } /* need to make sure size is all the same during early stage */ -void * __meminit vmemmap_alloc_block_buf(unsigned long size, int node) +static void * __meminit alloc_block_buf(unsigned long size, int node) { void *ptr; @@ -87,6 +88,77 @@ void * __meminit vmemmap_alloc_block_buf(unsigned long size, int node) return ptr; } +static unsigned long __meminit vmem_altmap_next_pfn(struct vmem_altmap *altmap) +{ + return altmap->base_pfn + altmap->reserve + altmap->alloc + + altmap->align; +} + +static unsigned long __meminit vmem_altmap_nr_free(struct vmem_altmap *altmap) +{ + unsigned long allocated = altmap->alloc + altmap->align; + + if (altmap->free > allocated) + return altmap->free - allocated; + return 0; +} + +/** + * vmem_altmap_alloc - allocate pages from the vmem_altmap reservation + * @altmap - reserved page pool for the allocation + * @nr_pfns - size (in pages) of the allocation + * + * Allocations are aligned to the size of the request + */ +static unsigned long __meminit vmem_altmap_alloc(struct vmem_altmap *altmap, + unsigned long nr_pfns) +{ + unsigned long pfn = vmem_altmap_next_pfn(altmap); + unsigned long nr_align; + + nr_align = 1UL << find_first_bit(&nr_pfns, BITS_PER_LONG); + nr_align = ALIGN(pfn, nr_align) - pfn; + + if (nr_pfns + nr_align > vmem_altmap_nr_free(altmap)) + return ULONG_MAX; + altmap->alloc += nr_pfns; + altmap->align += nr_align; + return pfn + nr_align; +} + +static void * __meminit altmap_alloc_block_buf(unsigned long size, + struct vmem_altmap *altmap) +{ + unsigned long pfn, nr_pfns; + void *ptr; + + if (size & ~PAGE_MASK) { + pr_warn_once("%s: allocations must be multiple of PAGE_SIZE (%ld)\n", + __func__, size); + return NULL; + } + + nr_pfns = size >> PAGE_SHIFT; + pfn = vmem_altmap_alloc(altmap, nr_pfns); + if (pfn < ULONG_MAX) + ptr = __va(__pfn_to_phys(pfn)); + else + ptr = NULL; + pr_debug("%s: pfn: %#lx alloc: %ld align: %ld nr: %#lx\n", + __func__, pfn, altmap->alloc, altmap->align, nr_pfns); + + return ptr; +} + +/* need to make sure size is all the same during early stage */ +void * __meminit __vmemmap_alloc_block_buf(unsigned long size, int node, + struct vmem_altmap *altmap) +{ + if (altmap) + return altmap_alloc_block_buf(size, altmap); + return alloc_block_buf(size, node); +} + void __meminit vmemmap_verify(pte_t *pte, int node, unsigned long start, unsigned long end) { @@ -103,7 +175,7 @@ pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node) pte_t *pte = pte_offset_kernel(pmd, addr); if (pte_none(*pte)) { pte_t entry; - void *p = vmemmap_alloc_block_buf(PAGE_SIZE, node); + void *p = alloc_block_buf(PAGE_SIZE, node); if (!p) return NULL; entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL); diff --git a/mm/sparse.c b/mm/sparse.c index d1b48b691ac8..3717ceed4177 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -748,7 +748,7 @@ static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) if (!memmap) return; - for (i = 0; i < PAGES_PER_SECTION; i++) { + for (i = 0; i < nr_pages; i++) { if (PageHWPoison(&memmap[i])) { atomic_long_sub(1, &num_poisoned_pages); ClearPageHWPoison(&memmap[i]); @@ -788,7 +788,8 @@ static void free_section_usemap(struct page *memmap, unsigned long *usemap) free_map_bootmem(memmap); } -void sparse_remove_one_section(struct zone *zone, struct mem_section *ms) +void sparse_remove_one_section(struct zone *zone, struct mem_section *ms, + unsigned long map_offset) { struct page *memmap = NULL; unsigned long *usemap = NULL, flags; @@ -804,7 +805,8 @@ void sparse_remove_one_section(struct zone *zone, struct mem_section *ms) } pgdat_resize_unlock(pgdat, &flags); - clear_hwpoisoned_pages(memmap, PAGES_PER_SECTION); + clear_hwpoisoned_pages(memmap + map_offset, + PAGES_PER_SECTION - map_offset); free_section_usemap(memmap, usemap); } #endif /* CONFIG_MEMORY_HOTREMOVE */ -- cgit v1.2.3 From 69660fd797c3e52f7f20478a27687f293d1a41be Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 15 Jan 2016 16:56:37 -0800 Subject: x86, mm: introduce _PAGE_DEVMAP _PAGE_DEVMAP is a hardware-unused pte bit that will later be used in the get_user_pages() path to identify pfns backed by the dynamic allocation established by devm_memremap_pages. Upon seeing that bit the gup path will lookup and pin the allocation while the pages are in use. Since the _PAGE_DEVMAP bit is > 32 it must be cast to u64 instead of a pteval_t to allow pmd_flags() usage in the realmode boot code to build. Signed-off-by: Dan Williams Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/pgtable_types.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index d1b76f88ccd1..04c27a013165 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -24,7 +24,9 @@ #define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1 #define _PAGE_BIT_HIDDEN _PAGE_BIT_SOFTW3 /* hidden by kmemcheck */ #define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */ -#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ +#define _PAGE_BIT_SOFTW4 58 /* available for programmer */ +#define _PAGE_BIT_DEVMAP _PAGE_BIT_SOFTW4 +#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ /* If _PAGE_BIT_PRESENT is clear, we use these: */ /* - if the user mapped it with PROT_NONE; pte_present gives true */ @@ -83,8 +85,11 @@ #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) #define _PAGE_NX (_AT(pteval_t, 1) << _PAGE_BIT_NX) +#define _PAGE_DEVMAP (_AT(u64, 1) << _PAGE_BIT_DEVMAP) +#define __HAVE_ARCH_PTE_DEVMAP #else #define _PAGE_NX (_AT(pteval_t, 0)) +#define _PAGE_DEVMAP (_AT(pteval_t, 0)) #endif #define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) -- cgit v1.2.3 From 01c8f1c44b83a0825b573e7c723b033cece37b86 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 15 Jan 2016 16:56:40 -0800 Subject: mm, dax, gpu: convert vm_insert_mixed to pfn_t Convert the raw unsigned long 'pfn' argument to pfn_t for the purpose of evaluating the PFN_MAP and PFN_DEV flags. When both are set it triggers _PAGE_DEVMAP to be set in the resulting pte. There are no functional changes to the gpu drivers as a result of this conversion. Signed-off-by: Dan Williams Cc: Dave Hansen Cc: David Airlie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/pgtable.h | 5 +++++ drivers/gpu/drm/exynos/exynos_drm_gem.c | 4 +++- drivers/gpu/drm/gma500/framebuffer.c | 4 +++- drivers/gpu/drm/msm/msm_gem.c | 4 +++- drivers/gpu/drm/omapdrm/omap_gem.c | 7 +++++-- drivers/gpu/drm/ttm/ttm_bo_vm.c | 4 +++- fs/dax.c | 2 +- include/linux/mm.h | 2 +- include/linux/pfn_t.h | 27 +++++++++++++++++++++++++++ mm/memory.c | 16 ++++++++++------ 10 files changed, 61 insertions(+), 14 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 4973cc9eacce..4c668f15a532 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -247,6 +247,11 @@ static inline pte_t pte_mkspecial(pte_t pte) return pte_set_flags(pte, _PAGE_SPECIAL); } +static inline pte_t pte_mkdevmap(pte_t pte) +{ + return pte_set_flags(pte, _PAGE_SPECIAL|_PAGE_DEVMAP); +} + static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set) { pmdval_t v = native_pmd_val(pmd); diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c index 252eb301470c..32358c5e3db4 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gem.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c @@ -14,6 +14,7 @@ #include #include +#include #include #include "exynos_drm_drv.h" @@ -490,7 +491,8 @@ int exynos_drm_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } pfn = page_to_pfn(exynos_gem->pages[page_offset]); - ret = vm_insert_mixed(vma, (unsigned long)vmf->virtual_address, pfn); + ret = vm_insert_mixed(vma, (unsigned long)vmf->virtual_address, + __pfn_to_pfn_t(pfn, PFN_DEV)); out: switch (ret) { diff --git a/drivers/gpu/drm/gma500/framebuffer.c b/drivers/gpu/drm/gma500/framebuffer.c index 2eaf1b31c7bd..72bc979fa0dc 100644 --- a/drivers/gpu/drm/gma500/framebuffer.c +++ b/drivers/gpu/drm/gma500/framebuffer.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -132,7 +133,8 @@ static int psbfb_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) for (i = 0; i < page_num; i++) { pfn = (phys_addr >> PAGE_SHIFT); - ret = vm_insert_mixed(vma, address, pfn); + ret = vm_insert_mixed(vma, address, + __pfn_to_pfn_t(pfn, PFN_DEV)); if (unlikely((ret == -EBUSY) || (ret != 0 && i > 0))) break; else if (unlikely(ret != 0)) { diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index c76cc853b08a..3cedb8d5c855 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -18,6 +18,7 @@ #include #include #include +#include #include "msm_drv.h" #include "msm_gem.h" @@ -222,7 +223,8 @@ int msm_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) VERB("Inserting %p pfn %lx, pa %lx", vmf->virtual_address, pfn, pfn << PAGE_SHIFT); - ret = vm_insert_mixed(vma, (unsigned long)vmf->virtual_address, pfn); + ret = vm_insert_mixed(vma, (unsigned long)vmf->virtual_address, + __pfn_to_pfn_t(pfn, PFN_DEV)); out_unlock: mutex_unlock(&dev->struct_mutex); diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c index 7ed08fdc4c42..ceba5459ceb7 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem.c +++ b/drivers/gpu/drm/omapdrm/omap_gem.c @@ -19,6 +19,7 @@ #include #include +#include #include @@ -385,7 +386,8 @@ static int fault_1d(struct drm_gem_object *obj, VERB("Inserting %p pfn %lx, pa %lx", vmf->virtual_address, pfn, pfn << PAGE_SHIFT); - return vm_insert_mixed(vma, (unsigned long)vmf->virtual_address, pfn); + return vm_insert_mixed(vma, (unsigned long)vmf->virtual_address, + __pfn_to_pfn_t(pfn, PFN_DEV)); } /* Special handling for the case of faulting in 2d tiled buffers */ @@ -478,7 +480,8 @@ static int fault_2d(struct drm_gem_object *obj, pfn, pfn << PAGE_SHIFT); for (i = n; i > 0; i--) { - vm_insert_mixed(vma, (unsigned long)vaddr, pfn); + vm_insert_mixed(vma, (unsigned long)vaddr, + __pfn_to_pfn_t(pfn, PFN_DEV)); pfn += usergart[fmt].stride_pfn; vaddr += PAGE_SIZE * m; } diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 8fb7213277cc..06d26dc438b2 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include #include @@ -229,7 +230,8 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } if (vma->vm_flags & VM_MIXEDMAP) - ret = vm_insert_mixed(&cvma, address, pfn); + ret = vm_insert_mixed(&cvma, address, + __pfn_to_pfn_t(pfn, PFN_DEV)); else ret = vm_insert_pfn(&cvma, address, pfn); diff --git a/fs/dax.c b/fs/dax.c index 6b13d6cd9a9a..574763eed8a3 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -363,7 +363,7 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, } dax_unmap_atomic(bdev, &dax); - error = vm_insert_mixed(vma, vaddr, pfn_t_to_pfn(dax.pfn)); + error = vm_insert_mixed(vma, vaddr, dax.pfn); out: i_mmap_unlock_read(mapping); diff --git a/include/linux/mm.h b/include/linux/mm.h index 8bb0907a3603..a9902152449f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2107,7 +2107,7 @@ int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn); + pfn_t pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index c557a0e0b20c..bdaa275d7623 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -64,4 +64,31 @@ static inline pfn_t page_to_pfn_t(struct page *page) { return pfn_to_pfn_t(page_to_pfn(page)); } + +static inline int pfn_t_valid(pfn_t pfn) +{ + return pfn_valid(pfn_t_to_pfn(pfn)); +} + +#ifdef CONFIG_MMU +static inline pte_t pfn_t_pte(pfn_t pfn, pgprot_t pgprot) +{ + return pfn_pte(pfn_t_to_pfn(pfn), pgprot); +} +#endif + +#ifdef __HAVE_ARCH_PTE_DEVMAP +static inline bool pfn_t_devmap(pfn_t pfn) +{ + const unsigned long flags = PFN_DEV|PFN_MAP; + + return (pfn.val & flags) == flags; +} +#else +static inline bool pfn_t_devmap(pfn_t pfn) +{ + return false; +} +pte_t pte_mkdevmap(pte_t pte); +#endif #endif /* _LINUX_PFN_T_H_ */ diff --git a/mm/memory.c b/mm/memory.c index 5a73c6ed8e5c..7f03652723ea 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -50,6 +50,7 @@ #include #include #include +#include #include #include #include @@ -1500,7 +1501,7 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, EXPORT_SYMBOL(vm_insert_page); static int insert_pfn(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn, pgprot_t prot) + pfn_t pfn, pgprot_t prot) { struct mm_struct *mm = vma->vm_mm; int retval; @@ -1516,7 +1517,10 @@ static int insert_pfn(struct vm_area_struct *vma, unsigned long addr, goto out_unlock; /* Ok, finally just insert the thing.. */ - entry = pte_mkspecial(pfn_pte(pfn, prot)); + if (pfn_t_devmap(pfn)) + entry = pte_mkdevmap(pfn_t_pte(pfn, prot)); + else + entry = pte_mkspecial(pfn_t_pte(pfn, prot)); set_pte_at(mm, addr, pte, entry); update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */ @@ -1566,14 +1570,14 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, if (track_pfn_insert(vma, &pgprot, pfn)) return -EINVAL; - ret = insert_pfn(vma, addr, pfn, pgprot); + ret = insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot); return ret; } EXPORT_SYMBOL(vm_insert_pfn); int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn) + pfn_t pfn) { BUG_ON(!(vma->vm_flags & VM_MIXEDMAP)); @@ -1587,10 +1591,10 @@ int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, * than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP * without pte special, it would there be refcounted as a normal page. */ - if (!HAVE_PTE_SPECIAL && pfn_valid(pfn)) { + if (!HAVE_PTE_SPECIAL && pfn_t_valid(pfn)) { struct page *page; - page = pfn_to_page(pfn); + page = pfn_t_to_page(pfn); return insert_page(vma, addr, page, vma->vm_page_prot); } return insert_pfn(vma, addr, pfn, vma->vm_page_prot); -- cgit v1.2.3 From f25748e3c34eb8bb54853e9adba2d3dcf030503c Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 15 Jan 2016 16:56:43 -0800 Subject: mm, dax: convert vmf_insert_pfn_pmd() to pfn_t Similar to the conversion of vm_insert_mixed() use pfn_t in the vmf_insert_pfn_pmd() to tag the resulting pte with _PAGE_DEVICE when the pfn is backed by a devm_memremap_pages() mapping. Signed-off-by: Dan Williams Cc: Dave Hansen Cc: Matthew Wilcox Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/pgtable.h | 5 +++++ arch/x86/mm/pat.c | 5 +++-- fs/dax.c | 2 +- include/asm-generic/pgtable.h | 6 ++++-- include/linux/huge_mm.h | 2 +- include/linux/pfn_t.h | 8 ++++++++ mm/huge_memory.c | 11 +++++++---- mm/memory.c | 2 +- 8 files changed, 30 insertions(+), 11 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 4c668f15a532..6585a8b10fea 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -286,6 +286,11 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd) return pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); } +static inline pmd_t pmd_mkdevmap(pmd_t pmd) +{ + return pmd_set_flags(pmd, _PAGE_DEVMAP); +} + static inline pmd_t pmd_mkhuge(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_PSE); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 031782e74231..f4ae536b0914 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -949,7 +950,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, } int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, - unsigned long pfn) + pfn_t pfn) { enum page_cache_mode pcm; @@ -957,7 +958,7 @@ int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, return 0; /* Set prot based on lookup */ - pcm = lookup_memtype((resource_size_t)pfn << PAGE_SHIFT); + pcm = lookup_memtype(pfn_t_to_phys(pfn)); *prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) | cachemode2protval(pcm)); diff --git a/fs/dax.c b/fs/dax.c index 574763eed8a3..96ac3072463d 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -693,7 +693,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, dax_unmap_atomic(bdev, &dax); result |= vmf_insert_pfn_pmd(vma, address, pmd, - pfn_t_to_pfn(dax.pfn), write); + dax.pfn, write); } out: diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index af0a6cc81635..0b3c0d39ef75 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1,6 +1,8 @@ #ifndef _ASM_GENERIC_PGTABLE_H #define _ASM_GENERIC_PGTABLE_H +#include + #ifndef __ASSEMBLY__ #ifdef CONFIG_MMU @@ -549,7 +551,7 @@ static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, * by vm_insert_pfn(). */ static inline int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, - unsigned long pfn) + pfn_t pfn) { return 0; } @@ -584,7 +586,7 @@ extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, unsigned long pfn, unsigned long addr, unsigned long size); extern int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, - unsigned long pfn); + pfn_t pfn); extern int track_pfn_copy(struct vm_area_struct *vma); extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size); diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 0160201993d4..8ca35a131904 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -37,7 +37,7 @@ extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, int prot_numa); int vmf_insert_pfn_pmd(struct vm_area_struct *, unsigned long addr, pmd_t *, - unsigned long pfn, bool write); + pfn_t pfn, bool write); enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_FLAG, diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index bdaa275d7623..0703b5360d31 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -77,6 +77,13 @@ static inline pte_t pfn_t_pte(pfn_t pfn, pgprot_t pgprot) } #endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline pmd_t pfn_t_pmd(pfn_t pfn, pgprot_t pgprot) +{ + return pfn_pmd(pfn_t_to_pfn(pfn), pgprot); +} +#endif + #ifdef __HAVE_ARCH_PTE_DEVMAP static inline bool pfn_t_devmap(pfn_t pfn) { @@ -90,5 +97,6 @@ static inline bool pfn_t_devmap(pfn_t pfn) return false; } pte_t pte_mkdevmap(pte_t pte); +pmd_t pmd_mkdevmap(pmd_t pmd); #endif #endif /* _LINUX_PFN_T_H_ */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 996e86dbeb43..d93706013a55 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -931,14 +932,16 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, } static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, unsigned long pfn, pgprot_t prot, bool write) + pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write) { struct mm_struct *mm = vma->vm_mm; pmd_t entry; spinlock_t *ptl; ptl = pmd_lock(mm, pmd); - entry = pmd_mkhuge(pfn_pmd(pfn, prot)); + entry = pmd_mkhuge(pfn_t_pmd(pfn, prot)); + if (pfn_t_devmap(pfn)) + entry = pmd_mkdevmap(entry); if (write) { entry = pmd_mkyoung(pmd_mkdirty(entry)); entry = maybe_pmd_mkwrite(entry, vma); @@ -949,7 +952,7 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, } int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, unsigned long pfn, bool write) + pmd_t *pmd, pfn_t pfn, bool write) { pgprot_t pgprot = vma->vm_page_prot; /* @@ -961,7 +964,7 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); - BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); + BUG_ON(!pfn_t_devmap(pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; diff --git a/mm/memory.c b/mm/memory.c index 7f03652723ea..552ae3d69435 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1567,7 +1567,7 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, if (addr < vma->vm_start || addr >= vma->vm_end) return -EFAULT; - if (track_pfn_insert(vma, &pgprot, pfn)) + if (track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV))) return -EINVAL; ret = insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot); -- cgit v1.2.3 From 5c7fb56e5e3f7035dd798a8e1adee639f87043e5 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 15 Jan 2016 16:56:52 -0800 Subject: mm, dax: dax-pmd vs thp-pmd vs hugetlbfs-pmd A dax-huge-page mapping while it uses some thp helpers is ultimately not a transparent huge page. The distinction is especially important in the get_user_pages() path. pmd_devmap() is used to distinguish dax-pmds from pmd_huge() and pmd_trans_huge() which have slightly different semantics. Explicitly mark the pmd_trans_huge() helpers that dax needs by adding pmd_devmap() checks. [kirill.shutemov@linux.intel.com: fix regression in handling mlocked pages in __split_huge_pmd()] Signed-off-by: Dan Williams Cc: Dave Hansen Cc: Mel Gorman Cc: Peter Zijlstra Cc: Andrea Arcangeli Cc: Matthew Wilcox Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/pgtable.h | 9 ++++++++- include/linux/huge_mm.h | 5 +++-- include/linux/mm.h | 7 +++++++ mm/huge_memory.c | 38 +++++++++++++++++++++----------------- mm/memory.c | 8 ++++---- mm/mprotect.c | 5 +++-- mm/pgtable-generic.c | 2 +- 7 files changed, 47 insertions(+), 27 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 6585a8b10fea..6a0ad82c8d0f 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -164,13 +164,20 @@ static inline int pmd_large(pmd_t pte) #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmd_trans_huge(pmd_t pmd) { - return pmd_val(pmd) & _PAGE_PSE; + return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; } static inline int has_transparent_hugepage(void) { return cpu_has_pse; } + +#ifdef __HAVE_ARCH_PTE_DEVMAP +static inline int pmd_devmap(pmd_t pmd) +{ + return !!(pmd_val(pmd) & _PAGE_DEVMAP); +} +#endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline pte_t pte_set_flags(pte_t pte, pteval_t set) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 8ca35a131904..d39fa60bd6bf 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -104,7 +104,8 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, #define split_huge_pmd(__vma, __pmd, __address) \ do { \ pmd_t *____pmd = (__pmd); \ - if (pmd_trans_huge(*____pmd)) \ + if (pmd_trans_huge(*____pmd) \ + || pmd_devmap(*____pmd)) \ __split_huge_pmd(__vma, __pmd, __address); \ } while (0) @@ -124,7 +125,7 @@ static inline bool pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, spinlock_t **ptl) { VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma); - if (pmd_trans_huge(*pmd)) + if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) return __pmd_trans_huge_lock(pmd, vma, ptl); else return false; diff --git a/include/linux/mm.h b/include/linux/mm.h index a9902152449f..cd123272d28d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -329,6 +329,13 @@ struct inode; #define page_private(page) ((page)->private) #define set_page_private(page, v) ((page)->private = (v)) +#if !defined(__HAVE_ARCH_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE) +static inline int pmd_devmap(pmd_t pmd) +{ + return 0; +} +#endif + /* * FIXME: take this include out, include page-flags.h in * files which need it (119 of them) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index d93706013a55..82bed2bec3ed 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -995,7 +995,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, ret = -EAGAIN; pmd = *src_pmd; - if (unlikely(!pmd_trans_huge(pmd))) { + if (unlikely(!pmd_trans_huge(pmd) && !pmd_devmap(pmd))) { pte_free(dst_mm, pgtable); goto out_unlock; } @@ -1018,17 +1018,20 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, goto out_unlock; } - src_page = pmd_page(pmd); - VM_BUG_ON_PAGE(!PageHead(src_page), src_page); - get_page(src_page); - page_dup_rmap(src_page, true); - add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); + if (pmd_trans_huge(pmd)) { + /* thp accounting separate from pmd_devmap accounting */ + src_page = pmd_page(pmd); + VM_BUG_ON_PAGE(!PageHead(src_page), src_page); + get_page(src_page); + page_dup_rmap(src_page, true); + add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); + atomic_long_inc(&dst_mm->nr_ptes); + pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); + } pmdp_set_wrprotect(src_mm, addr, src_pmd); pmd = pmd_mkold(pmd_wrprotect(pmd)); - pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); set_pmd_at(dst_mm, addr, dst_pmd, pmd); - atomic_long_inc(&dst_mm->nr_ptes); ret = 0; out_unlock: @@ -1716,7 +1719,7 @@ bool __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, spinlock_t **ptl) { *ptl = pmd_lock(vma->vm_mm, pmd); - if (likely(pmd_trans_huge(*pmd))) + if (likely(pmd_trans_huge(*pmd) || pmd_devmap(*pmd))) return true; spin_unlock(*ptl); return false; @@ -2788,7 +2791,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, VM_BUG_ON(haddr & ~HPAGE_PMD_MASK); VM_BUG_ON_VMA(vma->vm_start > haddr, vma); VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma); - VM_BUG_ON(!pmd_trans_huge(*pmd)); + VM_BUG_ON(!pmd_trans_huge(*pmd) && !pmd_devmap(*pmd)); count_vm_event(THP_SPLIT_PMD); @@ -2901,14 +2904,15 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PMD_SIZE); ptl = pmd_lock(mm, pmd); - if (unlikely(!pmd_trans_huge(*pmd))) + if (pmd_trans_huge(*pmd)) { + page = pmd_page(*pmd); + if (PageMlocked(page)) + get_page(page); + else + page = NULL; + } else if (!pmd_devmap(*pmd)) goto out; - page = pmd_page(*pmd); __split_huge_pmd_locked(vma, pmd, haddr, false); - if (PageMlocked(page)) - get_page(page); - else - page = NULL; out: spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, haddr, haddr + HPAGE_PMD_SIZE); @@ -2938,7 +2942,7 @@ static void split_huge_pmd_address(struct vm_area_struct *vma, return; pmd = pmd_offset(pud, address); - if (!pmd_present(*pmd) || !pmd_trans_huge(*pmd)) + if (!pmd_present(*pmd) || (!pmd_trans_huge(*pmd) && !pmd_devmap(*pmd))) return; /* * Caller holds the mmap_sem write mode, so a huge pmd cannot diff --git a/mm/memory.c b/mm/memory.c index 552ae3d69435..ff17850a52d9 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -950,7 +950,7 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src src_pmd = pmd_offset(src_pud, addr); do { next = pmd_addr_end(addr, end); - if (pmd_trans_huge(*src_pmd)) { + if (pmd_trans_huge(*src_pmd) || pmd_devmap(*src_pmd)) { int err; VM_BUG_ON(next-addr != HPAGE_PMD_SIZE); err = copy_huge_pmd(dst_mm, src_mm, @@ -1177,7 +1177,7 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); - if (pmd_trans_huge(*pmd)) { + if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) { #ifdef CONFIG_DEBUG_VM if (!rwsem_is_locked(&tlb->mm->mmap_sem)) { @@ -3375,7 +3375,7 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, int ret; barrier(); - if (pmd_trans_huge(orig_pmd)) { + if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) { unsigned int dirty = flags & FAULT_FLAG_WRITE; if (pmd_protnone(orig_pmd)) @@ -3404,7 +3404,7 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, unlikely(__pte_alloc(mm, vma, pmd, address))) return VM_FAULT_OOM; /* if an huge pmd materialized from under us just retry later */ - if (unlikely(pmd_trans_huge(*pmd))) + if (unlikely(pmd_trans_huge(*pmd) || pmd_devmap(*pmd))) return 0; /* * A regular pmd is established and it can't morph into a huge pmd diff --git a/mm/mprotect.c b/mm/mprotect.c index 6047707085c1..8eb7bb40dc40 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -149,7 +149,8 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, unsigned long this_pages; next = pmd_addr_end(addr, end); - if (!pmd_trans_huge(*pmd) && pmd_none_or_clear_bad(pmd)) + if (!pmd_trans_huge(*pmd) && !pmd_devmap(*pmd) + && pmd_none_or_clear_bad(pmd)) continue; /* invoke the mmu notifier if the pmd is populated */ @@ -158,7 +159,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, mmu_notifier_invalidate_range_start(mm, mni_start, end); } - if (pmd_trans_huge(*pmd)) { + if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) split_huge_pmd(vma, pmd, addr); else { diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index c311a2ec6fea..9d4767698a1c 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -132,7 +132,7 @@ pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, { pmd_t pmd; VM_BUG_ON(address & ~HPAGE_PMD_MASK); - VM_BUG_ON(!pmd_trans_huge(*pmdp)); + VM_BUG_ON(!pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp)); pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return pmd; -- cgit v1.2.3 From 3565fce3a6597e91b8dee3e8e36ebf70f8b7ef9b Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 15 Jan 2016 16:56:55 -0800 Subject: mm, x86: get_user_pages() for dax mappings A dax mapping establishes a pte with _PAGE_DEVMAP set when the driver has established a devm_memremap_pages() mapping, i.e. when the pfn_t return from ->direct_access() has PFN_DEV and PFN_MAP set. Later, when encountering _PAGE_DEVMAP during a page table walk we lookup and pin a struct dev_pagemap instance to keep the result of pfn_to_page() valid until put_page(). Signed-off-by: Dan Williams Tested-by: Logan Gunthorpe Cc: Dave Hansen Cc: Mel Gorman Cc: Peter Zijlstra Cc: Andrea Arcangeli Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/pgtable.h | 7 ++++ arch/x86/mm/gup.c | 57 ++++++++++++++++++++++++++++++-- include/linux/huge_mm.h | 10 +++++- include/linux/mm.h | 59 +++++++++++++++++++++++---------- kernel/memremap.c | 12 +++++++ mm/gup.c | 30 +++++++++++++++-- mm/huge_memory.c | 75 +++++++++++++++++++++++++++++++++--------- mm/swap.c | 1 + 8 files changed, 212 insertions(+), 39 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 6a0ad82c8d0f..0687c4748b8f 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -479,6 +479,13 @@ static inline int pte_present(pte_t a) return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE); } +#ifdef __HAVE_ARCH_PTE_DEVMAP +static inline int pte_devmap(pte_t a) +{ + return (pte_flags(a) & _PAGE_DEVMAP) == _PAGE_DEVMAP; +} +#endif + #define pte_accessible pte_accessible static inline bool pte_accessible(struct mm_struct *mm, pte_t a) { diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index f8cb3e8ac250..6d5eb5900372 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -9,6 +9,7 @@ #include #include #include +#include #include @@ -63,6 +64,16 @@ retry: #endif } +static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages) +{ + while ((*nr) - nr_start) { + struct page *page = pages[--(*nr)]; + + ClearPageReferenced(page); + put_page(page); + } +} + /* * The performance critical leaf functions are made noinline otherwise gcc * inlines everything into a single function which results in too much @@ -71,7 +82,9 @@ retry: static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { + struct dev_pagemap *pgmap = NULL; unsigned long mask; + int nr_start = *nr; pte_t *ptep; mask = _PAGE_PRESENT|_PAGE_USER; @@ -89,13 +102,21 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, return 0; } - if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) { + page = pte_page(pte); + if (pte_devmap(pte)) { + pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); + if (unlikely(!pgmap)) { + undo_dev_pagemap(nr, nr_start, pages); + pte_unmap(ptep); + return 0; + } + } else if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) { pte_unmap(ptep); return 0; } VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - page = pte_page(pte); get_page(page); + put_dev_pagemap(pgmap); SetPageReferenced(page); pages[*nr] = page; (*nr)++; @@ -114,6 +135,32 @@ static inline void get_head_page_multiple(struct page *page, int nr) SetPageReferenced(page); } +static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr, + unsigned long end, struct page **pages, int *nr) +{ + int nr_start = *nr; + unsigned long pfn = pmd_pfn(pmd); + struct dev_pagemap *pgmap = NULL; + + pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT; + do { + struct page *page = pfn_to_page(pfn); + + pgmap = get_dev_pagemap(pfn, pgmap); + if (unlikely(!pgmap)) { + undo_dev_pagemap(nr, nr_start, pages); + return 0; + } + SetPageReferenced(page); + pages[*nr] = page; + get_page(page); + put_dev_pagemap(pgmap); + (*nr)++; + pfn++; + } while (addr += PAGE_SIZE, addr != end); + return 1; +} + static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { @@ -126,9 +173,13 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, mask |= _PAGE_RW; if ((pmd_flags(pmd) & mask) != mask) return 0; + + VM_BUG_ON(!pfn_valid(pmd_pfn(pmd))); + if (pmd_devmap(pmd)) + return __gup_device_huge_pmd(pmd, addr, end, pages, nr); + /* hugepages are never "special" */ VM_BUG_ON(pmd_flags(pmd) & _PAGE_SPECIAL); - VM_BUG_ON(!pfn_valid(pmd_pfn(pmd))); refs = 0; head = pmd_page(pmd); diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index d39fa60bd6bf..cfe81e10bd54 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -38,7 +38,6 @@ extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, int prot_numa); int vmf_insert_pfn_pmd(struct vm_area_struct *, unsigned long addr, pmd_t *, pfn_t pfn, bool write); - enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_FLAG, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, @@ -55,6 +54,9 @@ enum transparent_hugepage_flag { #define HPAGE_PMD_NR (1< #include #include +#include #include #include #include @@ -465,17 +466,6 @@ static inline int page_count(struct page *page) return atomic_read(&compound_head(page)->_count); } -static inline void get_page(struct page *page) -{ - page = compound_head(page); - /* - * Getting a normal page or the head of a compound page - * requires to already have an elevated page->_count. - */ - VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page); - atomic_inc(&page->_count); -} - static inline struct page *virt_to_head_page(const void *x) { struct page *page = virt_to_page(x); @@ -494,13 +484,6 @@ static inline void init_page_count(struct page *page) void __put_page(struct page *page); -static inline void put_page(struct page *page) -{ - page = compound_head(page); - if (put_page_testzero(page)) - __put_page(page); -} - void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); @@ -682,17 +665,50 @@ static inline enum zone_type page_zonenum(const struct page *page) } #ifdef CONFIG_ZONE_DEVICE +void get_zone_device_page(struct page *page); +void put_zone_device_page(struct page *page); static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } #else +static inline void get_zone_device_page(struct page *page) +{ +} +static inline void put_zone_device_page(struct page *page) +{ +} static inline bool is_zone_device_page(const struct page *page) { return false; } #endif +static inline void get_page(struct page *page) +{ + page = compound_head(page); + /* + * Getting a normal page or the head of a compound page + * requires to already have an elevated page->_count. + */ + VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page); + atomic_inc(&page->_count); + + if (unlikely(is_zone_device_page(page))) + get_zone_device_page(page); +} + +static inline void put_page(struct page *page) +{ + page = compound_head(page); + + if (put_page_testzero(page)) + __put_page(page); + + if (unlikely(is_zone_device_page(page))) + put_zone_device_page(page); +} + #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif @@ -1444,6 +1460,13 @@ static inline void sync_mm_rss(struct mm_struct *mm) } #endif +#ifndef __HAVE_ARCH_PTE_DEVMAP +static inline int pte_devmap(pte_t pte) +{ + return 0; +} +#endif + int vma_wants_writenotify(struct vm_area_struct *vma); extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, diff --git a/kernel/memremap.c b/kernel/memremap.c index 3eb8944265d5..e517a16cb426 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -169,6 +169,18 @@ struct page_map { struct vmem_altmap altmap; }; +void get_zone_device_page(struct page *page) +{ + percpu_ref_get(page->pgmap->ref); +} +EXPORT_SYMBOL(get_zone_device_page); + +void put_zone_device_page(struct page *page) +{ + put_dev_pagemap(page->pgmap); +} +EXPORT_SYMBOL(put_zone_device_page); + static void pgmap_radix_release(struct resource *res) { resource_size_t key; diff --git a/mm/gup.c b/mm/gup.c index e95b0cb6ed81..aa21c4b865a5 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -4,6 +4,7 @@ #include #include +#include #include #include #include @@ -62,6 +63,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, unsigned int flags) { struct mm_struct *mm = vma->vm_mm; + struct dev_pagemap *pgmap = NULL; struct page *page; spinlock_t *ptl; pte_t *ptep, pte; @@ -98,7 +100,17 @@ retry: } page = vm_normal_page(vma, address, pte); - if (unlikely(!page)) { + if (!page && pte_devmap(pte) && (flags & FOLL_GET)) { + /* + * Only return device mapping pages in the FOLL_GET case since + * they are only valid while holding the pgmap reference. + */ + pgmap = get_dev_pagemap(pte_pfn(pte), NULL); + if (pgmap) + page = pte_page(pte); + else + goto no_page; + } else if (unlikely(!page)) { if (flags & FOLL_DUMP) { /* Avoid special (like zero) pages in core dumps */ page = ERR_PTR(-EFAULT); @@ -129,8 +141,15 @@ retry: goto retry; } - if (flags & FOLL_GET) + if (flags & FOLL_GET) { get_page(page); + + /* drop the pgmap reference now that we hold the page */ + if (pgmap) { + put_dev_pagemap(pgmap); + pgmap = NULL; + } + } if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) @@ -237,6 +256,13 @@ struct page *follow_page_mask(struct vm_area_struct *vma, } if ((flags & FOLL_NUMA) && pmd_protnone(*pmd)) return no_page_table(vma, flags); + if (pmd_devmap(*pmd)) { + ptl = pmd_lock(mm, pmd); + page = follow_devmap_pmd(vma, address, pmd, flags); + spin_unlock(ptl); + if (page) + return page; + } if (likely(!pmd_trans_huge(*pmd))) return follow_page_pte(vma, address, pmd, flags); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 82bed2bec3ed..b2db98136af9 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include @@ -974,6 +975,63 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, return VM_FAULT_NOPAGE; } +static void touch_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd) +{ + pmd_t _pmd; + + /* + * We should set the dirty bit only for FOLL_WRITE but for now + * the dirty bit in the pmd is meaningless. And if the dirty + * bit will become meaningful and we'll only set it with + * FOLL_WRITE, an atomic set_bit will be required on the pmd to + * set the young bit, instead of the current set_pmd_at. + */ + _pmd = pmd_mkyoung(pmd_mkdirty(*pmd)); + if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK, + pmd, _pmd, 1)) + update_mmu_cache_pmd(vma, addr, pmd); +} + +struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, int flags) +{ + unsigned long pfn = pmd_pfn(*pmd); + struct mm_struct *mm = vma->vm_mm; + struct dev_pagemap *pgmap; + struct page *page; + + assert_spin_locked(pmd_lockptr(mm, pmd)); + + if (flags & FOLL_WRITE && !pmd_write(*pmd)) + return NULL; + + if (pmd_present(*pmd) && pmd_devmap(*pmd)) + /* pass */; + else + return NULL; + + if (flags & FOLL_TOUCH) + touch_pmd(vma, addr, pmd); + + /* + * device mapped pages can only be returned if the + * caller will manage the page reference count. + */ + if (!(flags & FOLL_GET)) + return ERR_PTR(-EEXIST); + + pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT; + pgmap = get_dev_pagemap(pfn, NULL); + if (!pgmap) + return ERR_PTR(-EFAULT); + page = pfn_to_page(pfn); + get_page(page); + put_dev_pagemap(pgmap); + + return page; +} + int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, struct vm_area_struct *vma) @@ -1331,21 +1389,8 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, page = pmd_page(*pmd); VM_BUG_ON_PAGE(!PageHead(page), page); - if (flags & FOLL_TOUCH) { - pmd_t _pmd; - /* - * We should set the dirty bit only for FOLL_WRITE but - * for now the dirty bit in the pmd is meaningless. - * And if the dirty bit will become meaningful and - * we'll only set it with FOLL_WRITE, an atomic - * set_bit will be required on the pmd to set the - * young bit, instead of the current set_pmd_at. - */ - _pmd = pmd_mkyoung(pmd_mkdirty(*pmd)); - if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK, - pmd, _pmd, 1)) - update_mmu_cache_pmd(vma, addr, pmd); - } + if (flags & FOLL_TOUCH) + touch_pmd(vma, addr, pmd); if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { /* * We don't mlock() pte-mapped THPs. This way we can avoid diff --git a/mm/swap.c b/mm/swap.c index 674e2c93da4e..09fe5e97714a 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From da48d094ce5d7c7dcdad9011648a81c42fd1c2ef Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 15 Jan 2016 16:58:07 -0800 Subject: Kconfig: remove HAVE_LATENCYTOP_SUPPORT As illustrated by commit a3afe70b83fd ("[S390] latencytop s390 support."), HAVE_LATENCYTOP_SUPPORT is defined by an architecture to advertise an implementation of save_stack_trace_tsk. However, as of 9212ddb5eada ("stacktrace: provide save_stack_trace_tsk() weak alias") a dummy implementation is provided if STACKTRACE=y. Given that LATENCYTOP already depends on STACKTRACE_SUPPORT and selects STACKTRACE, we can remove HAVE_LATENCYTOP_SUPPORT altogether. Signed-off-by: Will Deacon Acked-by: Heiko Carstens Cc: Vineet Gupta Cc: Russell King Cc: James Hogan Cc: Michal Simek Cc: Helge Deller Acked-by: Michael Ellerman Cc: "David S. Miller" Cc: Guan Xuetao Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arc/Kconfig | 3 --- arch/arm/Kconfig | 5 ----- arch/metag/Kconfig | 3 --- arch/microblaze/Kconfig | 3 --- arch/parisc/Kconfig | 3 --- arch/powerpc/Kconfig | 3 --- arch/s390/Kconfig | 3 --- arch/sh/Kconfig | 3 --- arch/sparc/Kconfig | 4 ---- arch/unicore32/Kconfig | 3 --- arch/x86/Kconfig | 3 --- lib/Kconfig.debug | 1 - 12 files changed, 37 deletions(-) (limited to 'arch/x86') diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 6312f607932f..76dde9db7934 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -73,9 +73,6 @@ config STACKTRACE_SUPPORT def_bool y select STACKTRACE -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config HAVE_ARCH_TRANSPARENT_HUGEPAGE def_bool y depends on ARC_MMU_V4 diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 4e489cc5c45e..6a889afa6a2c 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -168,11 +168,6 @@ config STACKTRACE_SUPPORT bool default y -config HAVE_LATENCYTOP_SUPPORT - bool - depends on !SMP - default y - config LOCKDEP_SUPPORT bool default y diff --git a/arch/metag/Kconfig b/arch/metag/Kconfig index 0b389a81c43a..a0fa88da3e31 100644 --- a/arch/metag/Kconfig +++ b/arch/metag/Kconfig @@ -36,9 +36,6 @@ config STACKTRACE_SUPPORT config LOCKDEP_SUPPORT def_bool y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config RWSEM_GENERIC_SPINLOCK def_bool y diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 0bce820428fc..5ecd0287a874 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -67,9 +67,6 @@ config STACKTRACE_SUPPORT config LOCKDEP_SUPPORT def_bool y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - source "init/Kconfig" source "kernel/Kconfig.freezer" diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 729f89163bc3..7c34cafdf301 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -79,9 +79,6 @@ config TIME_LOW_RES depends on SMP default y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - # unless you want to implement ACPI on PA-RISC ... ;-) config PM bool diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 7d5a8350f913..94f6c5089e0c 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -47,9 +47,6 @@ config STACKTRACE_SUPPORT bool default y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config TRACE_IRQFLAGS_SUPPORT bool default y diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 24490344c30f..dbeeb3a049f2 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -10,9 +10,6 @@ config LOCKDEP_SUPPORT config STACKTRACE_SUPPORT def_bool y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config RWSEM_GENERIC_SPINLOCK bool diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index d514df7e04dd..6c391a5d3e5c 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -130,9 +130,6 @@ config STACKTRACE_SUPPORT config LOCKDEP_SUPPORT def_bool y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config ARCH_HAS_ILOG2_U32 def_bool n diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 56442d2d7bbc..3203e42190dd 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -101,10 +101,6 @@ config LOCKDEP_SUPPORT bool default y if SPARC64 -config HAVE_LATENCYTOP_SUPPORT - bool - default y if SPARC64 - config ARCH_HIBERNATION_POSSIBLE def_bool y if SPARC64 diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig index 5dc4c0a43ccd..877342640b6e 100644 --- a/arch/unicore32/Kconfig +++ b/arch/unicore32/Kconfig @@ -34,9 +34,6 @@ config NO_IOPORT_MAP config STACKTRACE_SUPPORT def_bool y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config LOCKDEP_SUPPORT def_bool y diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 24f362bf3ec6..4a10ba9e95da 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -180,9 +180,6 @@ config LOCKDEP_SUPPORT config STACKTRACE_SUPPORT def_bool y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config MMU def_bool y diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 8fbdef1980a5..f75a33f29f6e 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1597,7 +1597,6 @@ config FAULT_INJECTION_STACKTRACE_FILTER config LATENCYTOP bool "Latency measuring infrastructure" - depends on HAVE_LATENCYTOP_SUPPORT depends on DEBUG_KERNEL depends on STACKTRACE_SUPPORT depends on PROC_FS -- cgit v1.2.3