From d281ee6145183594788ab6d5b55f8d144e69eace Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 15 Jan 2016 16:52:16 -0800 Subject: rmap: add argument to charge compound page We're going to allow mapping of individual 4k pages of THP compound page. It means we cannot rely on PageTransHuge() check to decide if map/unmap small page or THP. The patch adds new argument to rmap functions to indicate whether we want to operate on whole compound page or only the small page. [n-horiguchi@ah.jp.nec.com: fix mapcount mismatch in hugepage migration] 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: Steve Capper Cc: Johannes Weiner Cc: Michal Hocko Cc: Christoph Lameter Cc: David Rientjes Signed-off-by: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/events/uprobes.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index bb0669169716..060c7a0edfdf 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -175,7 +175,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, goto unlock; get_page(kpage); - page_add_new_anon_rmap(kpage, vma, addr); + page_add_new_anon_rmap(kpage, vma, addr, false); mem_cgroup_commit_charge(kpage, memcg, false); lru_cache_add_active_or_unevictable(kpage, vma); @@ -188,7 +188,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, ptep_clear_flush_notify(vma, addr, ptep); set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot)); - page_remove_rmap(page); + page_remove_rmap(page, false); if (!page_mapped(page)) try_to_free_swap(page); pte_unmap_unlock(ptep, ptl); -- cgit v1.2.3-59-g8ed1b From f627c2f53786b0445abca47f6aa84c96a1fffec2 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 15 Jan 2016 16:52:20 -0800 Subject: memcg: adjust to support new THP refcounting As with rmap, with new refcounting we cannot rely on PageTransHuge() to check if we need to charge size of huge page form the cgroup. We need to get information from caller to know whether it was mapped with PMD or PTE. We do uncharge when last reference on the page gone. At that point if we see PageTransHuge() it means we need to unchange whole huge page. The tricky part is partial unmap -- when we try to unmap part of huge page. We don't do a special handing of this situation, meaning we don't uncharge the part of huge page unless last user is gone or split_huge_page() is triggered. In case of cgroup memory pressure happens the partial unmapped page will be split through shrinker. This should be good enough. 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 --- include/linux/memcontrol.h | 16 +++++++----- kernel/events/uprobes.c | 7 +++--- mm/filemap.c | 8 +++--- mm/huge_memory.c | 32 +++++++++++++----------- mm/memcontrol.c | 62 +++++++++++++++++----------------------------- mm/memory.c | 28 ++++++++++----------- mm/shmem.c | 21 +++++++++------- mm/swapfile.c | 9 ++++--- mm/userfaultfd.c | 6 ++--- 9 files changed, 92 insertions(+), 97 deletions(-) (limited to 'kernel') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 2292468f2a30..189f04d4d2ec 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -280,10 +280,12 @@ static inline void mem_cgroup_events(struct mem_cgroup *memcg, bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg); int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp); + gfp_t gfp_mask, struct mem_cgroup **memcgp, + bool compound); void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare); -void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); + bool lrucare, bool compound); +void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, + bool compound); void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); @@ -515,7 +517,8 @@ static inline bool mem_cgroup_low(struct mem_cgroup *root, static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - struct mem_cgroup **memcgp) + struct mem_cgroup **memcgp, + bool compound) { *memcgp = NULL; return 0; @@ -523,12 +526,13 @@ static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, static inline void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare) + bool lrucare, bool compound) { } static inline void mem_cgroup_cancel_charge(struct page *page, - struct mem_cgroup *memcg) + struct mem_cgroup *memcg, + bool compound) { } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 060c7a0edfdf..0167679182c0 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -161,7 +161,8 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, const unsigned long mmun_end = addr + PAGE_SIZE; struct mem_cgroup *memcg; - err = mem_cgroup_try_charge(kpage, vma->vm_mm, GFP_KERNEL, &memcg); + err = mem_cgroup_try_charge(kpage, vma->vm_mm, GFP_KERNEL, &memcg, + false); if (err) return err; @@ -176,7 +177,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, get_page(kpage); page_add_new_anon_rmap(kpage, vma, addr, false); - mem_cgroup_commit_charge(kpage, memcg, false); + mem_cgroup_commit_charge(kpage, memcg, false, false); lru_cache_add_active_or_unevictable(kpage, vma); if (!PageAnon(page)) { @@ -199,7 +200,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, err = 0; unlock: - mem_cgroup_cancel_charge(kpage, memcg); + mem_cgroup_cancel_charge(kpage, memcg, false); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); unlock_page(page); return err; diff --git a/mm/filemap.c b/mm/filemap.c index ae652ded700c..a729345ed6ec 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -618,7 +618,7 @@ static int __add_to_page_cache_locked(struct page *page, if (!huge) { error = mem_cgroup_try_charge(page, current->mm, - gfp_mask, &memcg); + gfp_mask, &memcg, false); if (error) return error; } @@ -626,7 +626,7 @@ static int __add_to_page_cache_locked(struct page *page, error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM); if (error) { if (!huge) - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, false); return error; } @@ -645,7 +645,7 @@ static int __add_to_page_cache_locked(struct page *page, __inc_zone_page_state(page, NR_FILE_PAGES); spin_unlock_irq(&mapping->tree_lock); if (!huge) - mem_cgroup_commit_charge(page, memcg, false); + mem_cgroup_commit_charge(page, memcg, false, false); trace_mm_filemap_add_to_page_cache(page); return 0; err_insert: @@ -653,7 +653,7 @@ err_insert: /* Leave page->index set: truncation relies upon it */ spin_unlock_irq(&mapping->tree_lock); if (!huge) - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, false); page_cache_release(page); return error; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index b7669cfe9dc9..4211682f223b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -751,7 +751,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, VM_BUG_ON_PAGE(!PageCompound(page), page); - if (mem_cgroup_try_charge(page, mm, gfp, &memcg)) { + if (mem_cgroup_try_charge(page, mm, gfp, &memcg, true)) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -759,7 +759,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, pgtable = pte_alloc_one(mm, haddr); if (unlikely(!pgtable)) { - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, true); put_page(page); return VM_FAULT_OOM; } @@ -775,7 +775,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, ptl = pmd_lock(mm, pmd); if (unlikely(!pmd_none(*pmd))) { spin_unlock(ptl); - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, true); put_page(page); pte_free(mm, pgtable); } else { @@ -786,7 +786,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, int ret; spin_unlock(ptl); - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, true); put_page(page); pte_free(mm, pgtable); ret = handle_userfault(vma, address, flags, @@ -798,7 +798,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, entry = mk_huge_pmd(page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); page_add_new_anon_rmap(page, vma, haddr, true); - mem_cgroup_commit_charge(page, memcg, false); + mem_cgroup_commit_charge(page, memcg, false, true); lru_cache_add_active_or_unevictable(page, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, haddr, pmd, entry); @@ -1095,13 +1095,14 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, vma, address, page_to_nid(page)); if (unlikely(!pages[i] || mem_cgroup_try_charge(pages[i], mm, GFP_KERNEL, - &memcg))) { + &memcg, false))) { if (pages[i]) put_page(pages[i]); while (--i >= 0) { memcg = (void *)page_private(pages[i]); set_page_private(pages[i], 0); - mem_cgroup_cancel_charge(pages[i], memcg); + mem_cgroup_cancel_charge(pages[i], memcg, + false); put_page(pages[i]); } kfree(pages); @@ -1140,7 +1141,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, memcg = (void *)page_private(pages[i]); set_page_private(pages[i], 0); page_add_new_anon_rmap(pages[i], vma, haddr, false); - mem_cgroup_commit_charge(pages[i], memcg, false); + mem_cgroup_commit_charge(pages[i], memcg, false, false); lru_cache_add_active_or_unevictable(pages[i], vma); pte = pte_offset_map(&_pmd, haddr); VM_BUG_ON(!pte_none(*pte)); @@ -1168,7 +1169,7 @@ out_free_pages: for (i = 0; i < HPAGE_PMD_NR; i++) { memcg = (void *)page_private(pages[i]); set_page_private(pages[i], 0); - mem_cgroup_cancel_charge(pages[i], memcg); + mem_cgroup_cancel_charge(pages[i], memcg, false); put_page(pages[i]); } kfree(pages); @@ -1234,7 +1235,8 @@ alloc: goto out; } - if (unlikely(mem_cgroup_try_charge(new_page, mm, huge_gfp, &memcg))) { + if (unlikely(mem_cgroup_try_charge(new_page, mm, huge_gfp, &memcg, + true))) { put_page(new_page); if (page) { split_huge_page(page); @@ -1263,7 +1265,7 @@ alloc: put_user_huge_page(page); if (unlikely(!pmd_same(*pmd, orig_pmd))) { spin_unlock(ptl); - mem_cgroup_cancel_charge(new_page, memcg); + mem_cgroup_cancel_charge(new_page, memcg, true); put_page(new_page); goto out_mn; } else { @@ -1272,7 +1274,7 @@ alloc: entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); pmdp_huge_clear_flush_notify(vma, haddr, pmd); page_add_new_anon_rmap(new_page, vma, haddr, true); - mem_cgroup_commit_charge(new_page, memcg, false); + mem_cgroup_commit_charge(new_page, memcg, false, true); lru_cache_add_active_or_unevictable(new_page, vma); set_pmd_at(mm, haddr, pmd, entry); update_mmu_cache_pmd(vma, address, pmd); @@ -2583,7 +2585,7 @@ static void collapse_huge_page(struct mm_struct *mm, goto out_nolock; } - if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg))) { + if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out_nolock; } @@ -2683,7 +2685,7 @@ static void collapse_huge_page(struct mm_struct *mm, spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); page_add_new_anon_rmap(new_page, vma, address, true); - mem_cgroup_commit_charge(new_page, memcg, false); + mem_cgroup_commit_charge(new_page, memcg, false, true); lru_cache_add_active_or_unevictable(new_page, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); @@ -2703,7 +2705,7 @@ out_nolock: trace_mm_collapse_huge_page(mm, isolated, result); return; out: - mem_cgroup_cancel_charge(new_page, memcg); + mem_cgroup_cancel_charge(new_page, memcg, true); goto out_up_write; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 54eae4f19d80..311fd2b71bae 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -647,7 +647,7 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, struct page *page, - int nr_pages) + bool compound, int nr_pages) { /* * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is @@ -660,9 +660,11 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE], nr_pages); - if (PageTransHuge(page)) + if (compound) { + VM_BUG_ON_PAGE(!PageTransHuge(page), page); __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE], nr_pages); + } /* pagein of a big page is an event. So, ignore page size */ if (nr_pages > 0) @@ -4513,30 +4515,24 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, * from old cgroup. */ static int mem_cgroup_move_account(struct page *page, - unsigned int nr_pages, + bool compound, struct mem_cgroup *from, struct mem_cgroup *to) { unsigned long flags; + unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; int ret; bool anon; VM_BUG_ON(from == to); VM_BUG_ON_PAGE(PageLRU(page), page); - /* - * The page is isolated from LRU. So, collapse function - * will not handle this page. But page splitting can happen. - * Do this check under compound_page_lock(). The caller should - * hold it. - */ - ret = -EBUSY; - if (nr_pages > 1 && !PageTransHuge(page)) - goto out; + VM_BUG_ON(compound && !PageTransHuge(page)); /* * Prevent mem_cgroup_replace_page() from looking at * page->mem_cgroup of its source page while we change it. */ + ret = -EBUSY; if (!trylock_page(page)) goto out; @@ -4591,9 +4587,9 @@ static int mem_cgroup_move_account(struct page *page, ret = 0; local_irq_disable(); - mem_cgroup_charge_statistics(to, page, nr_pages); + mem_cgroup_charge_statistics(to, page, compound, nr_pages); memcg_check_events(to, page); - mem_cgroup_charge_statistics(from, page, -nr_pages); + mem_cgroup_charge_statistics(from, page, compound, -nr_pages); memcg_check_events(from, page); local_irq_enable(); out_unlock: @@ -4890,7 +4886,7 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, if (target_type == MC_TARGET_PAGE) { page = target.page; if (!isolate_lru_page(page)) { - if (!mem_cgroup_move_account(page, HPAGE_PMD_NR, + if (!mem_cgroup_move_account(page, true, mc.from, mc.to)) { mc.precharge -= HPAGE_PMD_NR; mc.moved_charge += HPAGE_PMD_NR; @@ -4919,7 +4915,8 @@ retry: page = target.page; if (isolate_lru_page(page)) goto put; - if (!mem_cgroup_move_account(page, 1, mc.from, mc.to)) { + if (!mem_cgroup_move_account(page, false, + mc.from, mc.to)) { mc.precharge--; /* we uncharge from mc.from later. */ mc.moved_charge++; @@ -5258,10 +5255,11 @@ bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg) * with mem_cgroup_cancel_charge() in case page instantiation fails. */ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp) + gfp_t gfp_mask, struct mem_cgroup **memcgp, + bool compound) { struct mem_cgroup *memcg = NULL; - unsigned int nr_pages = 1; + unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; int ret = 0; if (mem_cgroup_disabled()) @@ -5291,11 +5289,6 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, } } - if (PageTransHuge(page)) { - nr_pages <<= compound_order(page); - VM_BUG_ON_PAGE(!PageTransHuge(page), page); - } - if (!memcg) memcg = get_mem_cgroup_from_mm(mm); @@ -5324,9 +5317,9 @@ out: * Use mem_cgroup_cancel_charge() to cancel the transaction instead. */ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare) + bool lrucare, bool compound) { - unsigned int nr_pages = 1; + unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; VM_BUG_ON_PAGE(!page->mapping, page); VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page); @@ -5343,13 +5336,8 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, commit_charge(page, memcg, lrucare); - if (PageTransHuge(page)) { - nr_pages <<= compound_order(page); - VM_BUG_ON_PAGE(!PageTransHuge(page), page); - } - local_irq_disable(); - mem_cgroup_charge_statistics(memcg, page, nr_pages); + mem_cgroup_charge_statistics(memcg, page, compound, nr_pages); memcg_check_events(memcg, page); local_irq_enable(); @@ -5371,9 +5359,10 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, * * Cancel a charge transaction started by mem_cgroup_try_charge(). */ -void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg) +void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, + bool compound) { - unsigned int nr_pages = 1; + unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; if (mem_cgroup_disabled()) return; @@ -5385,11 +5374,6 @@ void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg) if (!memcg) return; - if (PageTransHuge(page)) { - nr_pages <<= compound_order(page); - VM_BUG_ON_PAGE(!PageTransHuge(page), page); - } - cancel_charge(memcg, nr_pages); } @@ -5750,7 +5734,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) * only synchronisation we have for udpating the per-CPU variables. */ VM_BUG_ON(!irqs_disabled()); - mem_cgroup_charge_statistics(memcg, page, -1); + mem_cgroup_charge_statistics(memcg, page, false, -1); memcg_check_events(memcg, page); } diff --git a/mm/memory.c b/mm/memory.c index f964d190ce83..a021c295e88d 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2087,7 +2087,7 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, cow_user_page(new_page, old_page, address, vma); } - if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg)) + if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false)) goto oom_free_new; __SetPageUptodate(new_page); @@ -2119,7 +2119,7 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, */ ptep_clear_flush_notify(vma, address, page_table); page_add_new_anon_rmap(new_page, vma, address, false); - mem_cgroup_commit_charge(new_page, memcg, false); + mem_cgroup_commit_charge(new_page, memcg, false, false); lru_cache_add_active_or_unevictable(new_page, vma); /* * We call the notify macro here because, when using secondary @@ -2158,7 +2158,7 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, new_page = old_page; page_copied = 1; } else { - mem_cgroup_cancel_charge(new_page, memcg); + mem_cgroup_cancel_charge(new_page, memcg, false); } if (new_page) @@ -2533,7 +2533,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, goto out_page; } - if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg)) { + if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg, false)) { ret = VM_FAULT_OOM; goto out_page; } @@ -2575,10 +2575,10 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, set_pte_at(mm, address, page_table, pte); if (page == swapcache) { do_page_add_anon_rmap(page, vma, address, exclusive); - mem_cgroup_commit_charge(page, memcg, true); + mem_cgroup_commit_charge(page, memcg, true, false); } else { /* ksm created a completely new copy */ page_add_new_anon_rmap(page, vma, address, false); - mem_cgroup_commit_charge(page, memcg, false); + mem_cgroup_commit_charge(page, memcg, false, false); lru_cache_add_active_or_unevictable(page, vma); } @@ -2613,7 +2613,7 @@ unlock: out: return ret; out_nomap: - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, false); pte_unmap_unlock(page_table, ptl); out_page: unlock_page(page); @@ -2707,7 +2707,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, if (!page) goto oom; - if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg)) + if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg, false)) goto oom_free_page; /* @@ -2728,7 +2728,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(page_table, ptl); - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, false); page_cache_release(page); return handle_userfault(vma, address, flags, VM_UFFD_MISSING); @@ -2736,7 +2736,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, inc_mm_counter_fast(mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, address, false); - mem_cgroup_commit_charge(page, memcg, false); + mem_cgroup_commit_charge(page, memcg, false, false); lru_cache_add_active_or_unevictable(page, vma); setpte: set_pte_at(mm, address, page_table, entry); @@ -2747,7 +2747,7 @@ unlock: pte_unmap_unlock(page_table, ptl); return 0; release: - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, false); page_cache_release(page); goto unlock; oom_free_page: @@ -3000,7 +3000,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (!new_page) return VM_FAULT_OOM; - if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg)) { + if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false)) { page_cache_release(new_page); return VM_FAULT_OOM; } @@ -3029,7 +3029,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, goto uncharge_out; } do_set_pte(vma, address, new_page, pte, true, true); - mem_cgroup_commit_charge(new_page, memcg, false); + mem_cgroup_commit_charge(new_page, memcg, false, false); lru_cache_add_active_or_unevictable(new_page, vma); pte_unmap_unlock(pte, ptl); if (fault_page) { @@ -3044,7 +3044,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, } return ret; uncharge_out: - mem_cgroup_cancel_charge(new_page, memcg); + mem_cgroup_cancel_charge(new_page, memcg, false); page_cache_release(new_page); return ret; } diff --git a/mm/shmem.c b/mm/shmem.c index d271932f9ef9..b98e1011858c 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -810,7 +810,8 @@ int shmem_unuse(swp_entry_t swap, struct page *page) * the shmem_swaplist_mutex which might hold up shmem_writepage(). * Charged back to the user (not to caller) when swap account is used. */ - error = mem_cgroup_try_charge(page, current->mm, GFP_KERNEL, &memcg); + error = mem_cgroup_try_charge(page, current->mm, GFP_KERNEL, &memcg, + false); if (error) goto out; /* No radix_tree_preload: swap entry keeps a place for page in tree */ @@ -833,9 +834,9 @@ int shmem_unuse(swp_entry_t swap, struct page *page) if (error) { if (error != -ENOMEM) error = 0; - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, false); } else - mem_cgroup_commit_charge(page, memcg, true); + mem_cgroup_commit_charge(page, memcg, true, false); out: unlock_page(page); page_cache_release(page); @@ -1218,7 +1219,8 @@ repeat: goto failed; } - error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg); + error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg, + false); if (!error) { error = shmem_add_to_page_cache(page, mapping, index, swp_to_radix_entry(swap)); @@ -1235,14 +1237,14 @@ repeat: * "repeat": reading a hole and writing should succeed. */ if (error) { - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, false); delete_from_swap_cache(page); } } if (error) goto failed; - mem_cgroup_commit_charge(page, memcg, true); + mem_cgroup_commit_charge(page, memcg, true, false); spin_lock(&info->lock); info->swapped--; @@ -1281,7 +1283,8 @@ repeat: if (sgp == SGP_WRITE) __SetPageReferenced(page); - error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg); + error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg, + false); if (error) goto decused; error = radix_tree_maybe_preload(gfp & GFP_RECLAIM_MASK); @@ -1291,10 +1294,10 @@ repeat: radix_tree_preload_end(); } if (error) { - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, false); goto decused; } - mem_cgroup_commit_charge(page, memcg, false); + mem_cgroup_commit_charge(page, memcg, false, false); lru_cache_add_anon(page); spin_lock(&info->lock); diff --git a/mm/swapfile.c b/mm/swapfile.c index 058e6f0162eb..efe26bb10adb 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1142,14 +1142,15 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, if (unlikely(!page)) return -ENOMEM; - if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg)) { + if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, + &memcg, false)) { ret = -ENOMEM; goto out_nolock; } pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!maybe_same_pte(*pte, swp_entry_to_pte(entry)))) { - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, false); ret = 0; goto out; } @@ -1161,10 +1162,10 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, pte_mkold(mk_pte(page, vma->vm_page_prot))); if (page == swapcache) { page_add_anon_rmap(page, vma, addr, false); - mem_cgroup_commit_charge(page, memcg, true); + mem_cgroup_commit_charge(page, memcg, true, false); } else { /* ksm created a completely new copy */ page_add_new_anon_rmap(page, vma, addr, false); - mem_cgroup_commit_charge(page, memcg, false); + mem_cgroup_commit_charge(page, memcg, false, false); lru_cache_add_active_or_unevictable(page, vma); } swap_free(entry); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index ae21a1f309c2..806b0c758c5b 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -63,7 +63,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, __SetPageUptodate(page); ret = -ENOMEM; - if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg)) + if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg, false)) goto out_release; _dst_pte = mk_pte(page, dst_vma->vm_page_prot); @@ -77,7 +77,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, inc_mm_counter(dst_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, dst_vma, dst_addr, false); - mem_cgroup_commit_charge(page, memcg, false); + mem_cgroup_commit_charge(page, memcg, false, false); lru_cache_add_active_or_unevictable(page, dst_vma); set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); @@ -91,7 +91,7 @@ out: return ret; out_release_uncharge_unlock: pte_unmap_unlock(dst_pte, ptl); - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, false); out_release: page_cache_release(page); goto out; -- cgit v1.2.3-59-g8ed1b From 14d27abd1d12a64c89df1ce8c00ef1403226db5a Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 15 Jan 2016 16:53:00 -0800 Subject: futex, thp: remove special case for THP in get_futex_key With new THP refcounting, we don't need tricks to stabilize huge page. If we've got reference to tail page, it can't split under us. This patch effectively reverts a5b338f2b0b1 ("thp: update futex compound knowledge"). Signed-off-by: Kirill A. Shutemov Tested-by: Sasha Levin Tested-by: Aneesh Kumar K.V Acked-by: Jerome Marchand 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 Tested-by: Artem Savkov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/futex.c | 63 +++++++++++++--------------------------------------------- 1 file changed, 14 insertions(+), 49 deletions(-) (limited to 'kernel') diff --git a/kernel/futex.c b/kernel/futex.c index 8a310e240cda..eed92a8a4c49 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -469,7 +469,8 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; - struct page *page, *page_head; + struct page *page; + struct address_space *mapping; int err, ro = 0; /* @@ -519,46 +520,9 @@ again: else err = 0; -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - page_head = page; - if (unlikely(PageTail(page))) { - put_page(page); - /* serialize against __split_huge_page_splitting() */ - local_irq_disable(); - if (likely(__get_user_pages_fast(address, 1, !ro, &page) == 1)) { - page_head = compound_head(page); - /* - * page_head is valid pointer but we must pin - * it before taking the PG_lock and/or - * PG_compound_lock. The moment we re-enable - * irqs __split_huge_page_splitting() can - * return and the head page can be freed from - * under us. We can't take the PG_lock and/or - * PG_compound_lock on a page that could be - * freed from under us. - */ - if (page != page_head) { - get_page(page_head); - put_page(page); - } - local_irq_enable(); - } else { - local_irq_enable(); - goto again; - } - } -#else - page_head = compound_head(page); - if (page != page_head) { - get_page(page_head); - put_page(page); - } -#endif - - lock_page(page_head); - + lock_page(page); /* - * If page_head->mapping is NULL, then it cannot be a PageAnon + * If page->mapping is NULL, then it cannot be a PageAnon * page; but it might be the ZERO_PAGE or in the gate area or * in a special mapping (all cases which we are happy to fail); * or it may have been a good file page when get_user_pages_fast @@ -570,12 +534,13 @@ again: * * The case we do have to guard against is when memory pressure made * shmem_writepage move it from filecache to swapcache beneath us: - * an unlikely race, but we do need to retry for page_head->mapping. + * an unlikely race, but we do need to retry for page->mapping. */ - if (!page_head->mapping) { - int shmem_swizzled = PageSwapCache(page_head); - unlock_page(page_head); - put_page(page_head); + mapping = compound_head(page)->mapping; + if (!mapping) { + int shmem_swizzled = PageSwapCache(page); + unlock_page(page); + put_page(page); if (shmem_swizzled) goto again; return -EFAULT; @@ -588,7 +553,7 @@ again: * it's a read-only handle, it's expected that futexes attach to * the object not the particular process. */ - if (PageAnon(page_head)) { + if (PageAnon(page)) { /* * A RO anonymous page will never change and thus doesn't make * sense for futex operations. @@ -603,15 +568,15 @@ again: key->private.address = address; } else { key->both.offset |= FUT_OFF_INODE; /* inode-based key */ - key->shared.inode = page_head->mapping->host; + key->shared.inode = mapping->host; key->shared.pgoff = basepage_index(page); } get_futex_key_refs(key); /* implies MB (B) */ out: - unlock_page(page_head); - put_page(page_head); + unlock_page(page); + put_page(page); return err; } -- cgit v1.2.3-59-g8ed1b From 34c0fd540e79fb49ef9ce864dae1058cca265780 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 15 Jan 2016 16:56:14 -0800 Subject: mm, dax, pmem: introduce pfn_t For the purpose of communicating the optional presence of a 'struct page' for the pfn returned from ->direct_access(), introduce a type that encapsulates a page-frame-number plus flags. These flags contain the historical "page_link" encoding for a scatterlist entry, but can also denote "device memory". Where "device memory" is a set of pfns that are not part of the kernel's linear mapping by default, but are accessed via the same memory controller as ram. The motivation for this new type is large capacity persistent memory that needs struct page entries in the 'memmap' to support 3rd party DMA (i.e. O_DIRECT I/O with a persistent memory source/target). However, we also need it in support of maintaining a list of mapped inodes which need to be unmapped at driver teardown or freeze_bdev() time. Signed-off-by: Dan Williams Cc: Christoph Hellwig Cc: Dave Hansen Cc: Ross Zwisler Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/sysdev/axonram.c | 9 +++--- drivers/block/brd.c | 7 +++-- drivers/nvdimm/pmem.c | 13 ++++++--- drivers/s390/block/dcssblk.c | 11 ++++--- fs/dax.c | 11 ++++--- include/linux/blkdev.h | 5 ++-- include/linux/pfn.h | 9 ++++++ include/linux/pfn_t.h | 67 +++++++++++++++++++++++++++++++++++++++++++ kernel/memremap.c | 7 +++++ 9 files changed, 116 insertions(+), 23 deletions(-) create mode 100644 include/linux/pfn_t.h (limited to 'kernel') diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c index c713b349d967..0d112b94d91d 100644 --- a/arch/powerpc/sysdev/axonram.c +++ b/arch/powerpc/sysdev/axonram.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include @@ -142,15 +143,13 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio) */ static long axon_ram_direct_access(struct block_device *device, sector_t sector, - void __pmem **kaddr, unsigned long *pfn) + void __pmem **kaddr, pfn_t *pfn) { struct axon_ram_bank *bank = device->bd_disk->private_data; loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT; - void *addr = (void *)(bank->ph_addr + offset); - - *kaddr = (void __pmem *)addr; - *pfn = virt_to_phys(addr) >> PAGE_SHIFT; + *kaddr = (void __pmem __force *) bank->io_addr + offset; + *pfn = phys_to_pfn_t(bank->ph_addr + offset, PFN_DEV); return bank->size - offset; } diff --git a/drivers/block/brd.c b/drivers/block/brd.c index a5880f4ab40e..cb27190e9f39 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -19,6 +19,9 @@ #include #include #include +#ifdef CONFIG_BLK_DEV_RAM_DAX +#include +#endif #include @@ -378,7 +381,7 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector, #ifdef CONFIG_BLK_DEV_RAM_DAX static long brd_direct_access(struct block_device *bdev, sector_t sector, - void __pmem **kaddr, unsigned long *pfn) + void __pmem **kaddr, pfn_t *pfn) { struct brd_device *brd = bdev->bd_disk->private_data; struct page *page; @@ -389,7 +392,7 @@ static long brd_direct_access(struct block_device *bdev, sector_t sector, if (!page) return -ENOSPC; *kaddr = (void __pmem *)page_address(page); - *pfn = page_to_pfn(page); + *pfn = page_to_pfn_t(page); return PAGE_SIZE; } diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index b493ff3fccb2..5def7f4ddbd2 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -40,6 +41,7 @@ struct pmem_device { phys_addr_t phys_addr; /* when non-zero this device is hosting a 'pfn' instance */ phys_addr_t data_offset; + unsigned long pfn_flags; void __pmem *virt_addr; size_t size; struct badblocks bb; @@ -135,13 +137,13 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector, } static long pmem_direct_access(struct block_device *bdev, sector_t sector, - void __pmem **kaddr, unsigned long *pfn) + void __pmem **kaddr, pfn_t *pfn) { struct pmem_device *pmem = bdev->bd_disk->private_data; resource_size_t offset = sector * 512 + pmem->data_offset; *kaddr = pmem->virt_addr + offset; - *pfn = (pmem->phys_addr + offset) >> PAGE_SHIFT; + *pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags); return pmem->size - offset; } @@ -174,9 +176,11 @@ static struct pmem_device *pmem_alloc(struct device *dev, return ERR_PTR(-EBUSY); } - if (pmem_should_map_pages(dev)) + pmem->pfn_flags = PFN_DEV; + if (pmem_should_map_pages(dev)) { pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, res); - else + pmem->pfn_flags |= PFN_MAP; + } else pmem->virt_addr = (void __pmem *) devm_memremap(dev, pmem->phys_addr, pmem->size, ARCH_MEMREMAP_PMEM); @@ -384,6 +388,7 @@ static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns) 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->pfn_flags |= PFN_MAP; if (IS_ERR(pmem->virt_addr)) { rc = PTR_ERR(pmem->virt_addr); goto err; diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 94a8f4ab57bc..ce7b70181740 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -30,7 +31,7 @@ static void dcssblk_release(struct gendisk *disk, fmode_t mode); static blk_qc_t dcssblk_make_request(struct request_queue *q, struct bio *bio); static long dcssblk_direct_access(struct block_device *bdev, sector_t secnum, - void __pmem **kaddr, unsigned long *pfn); + void __pmem **kaddr, pfn_t *pfn); static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0"; @@ -883,20 +884,18 @@ fail: static long dcssblk_direct_access (struct block_device *bdev, sector_t secnum, - void __pmem **kaddr, unsigned long *pfn) + void __pmem **kaddr, pfn_t *pfn) { struct dcssblk_dev_info *dev_info; unsigned long offset, dev_sz; - void *addr; dev_info = bdev->bd_disk->private_data; if (!dev_info) return -ENODEV; dev_sz = dev_info->end - dev_info->start; offset = secnum * 512; - addr = (void *) (dev_info->start + offset); - *pfn = virt_to_phys(addr) >> PAGE_SHIFT; - *kaddr = (void __pmem *) addr; + *kaddr = (void __pmem *) (dev_info->start + offset); + *pfn = __pfn_to_pfn_t(PFN_DOWN(dev_info->start + offset), PFN_DEV); return dev_sz - offset; } diff --git a/fs/dax.c b/fs/dax.c index 3220da70ee20..6b13d6cd9a9a 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -28,6 +28,7 @@ #include #include #include +#include #include static long dax_map_atomic(struct block_device *bdev, struct blk_dax_ctl *dax) @@ -362,7 +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, dax.pfn); + error = vm_insert_mixed(vma, vaddr, pfn_t_to_pfn(dax.pfn)); out: i_mmap_unlock_read(mapping); @@ -667,7 +668,8 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, result = VM_FAULT_SIGBUS; goto out; } - if ((length < PMD_SIZE) || (dax.pfn & PG_PMD_COLOUR)) { + if (length < PMD_SIZE + || (pfn_t_to_pfn(dax.pfn) & PG_PMD_COLOUR)) { dax_unmap_atomic(bdev, &dax); goto fallback; } @@ -676,7 +678,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, * TODO: teach vmf_insert_pfn_pmd() to support * 'pte_special' for pmds */ - if (pfn_valid(dax.pfn)) { + if (pfn_t_has_page(dax.pfn)) { dax_unmap_atomic(bdev, &dax); goto fallback; } @@ -690,7 +692,8 @@ 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, dax.pfn, write); + result |= vmf_insert_pfn_pmd(vma, address, pmd, + pfn_t_to_pfn(dax.pfn), write); } out: diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 88821fa26f19..bfb64d672e19 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -1628,7 +1629,7 @@ struct blk_dax_ctl { sector_t sector; void __pmem *addr; long size; - unsigned long pfn; + pfn_t pfn; }; struct block_device_operations { @@ -1638,7 +1639,7 @@ struct block_device_operations { int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); long (*direct_access)(struct block_device *, sector_t, void __pmem **, - unsigned long *pfn); + pfn_t *); unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); /* ->media_changed() is DEPRECATED, use ->check_events() instead */ diff --git a/include/linux/pfn.h b/include/linux/pfn.h index 97f3e88aead4..2d8e49711b63 100644 --- a/include/linux/pfn.h +++ b/include/linux/pfn.h @@ -3,6 +3,15 @@ #ifndef __ASSEMBLY__ #include + +/* + * pfn_t: encapsulates a page-frame number that is optionally backed + * by memmap (struct page). Whether a pfn_t has a 'struct page' + * backing is indicated by flags in the high bits of the value. + */ +typedef struct { + unsigned long val; +} pfn_t; #endif #define PFN_ALIGN(x) (((unsigned long)(x) + (PAGE_SIZE - 1)) & PAGE_MASK) diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h new file mode 100644 index 000000000000..c557a0e0b20c --- /dev/null +++ b/include/linux/pfn_t.h @@ -0,0 +1,67 @@ +#ifndef _LINUX_PFN_T_H_ +#define _LINUX_PFN_T_H_ +#include + +/* + * PFN_FLAGS_MASK - mask of all the possible valid pfn_t flags + * PFN_SG_CHAIN - pfn is a pointer to the next scatterlist entry + * PFN_SG_LAST - pfn references a page and is the last scatterlist entry + * PFN_DEV - pfn is not covered by system memmap by default + * PFN_MAP - pfn has a dynamic page mapping established by a device driver + */ +#define PFN_FLAGS_MASK (((unsigned long) ~PAGE_MASK) \ + << (BITS_PER_LONG - PAGE_SHIFT)) +#define PFN_SG_CHAIN (1UL << (BITS_PER_LONG - 1)) +#define PFN_SG_LAST (1UL << (BITS_PER_LONG - 2)) +#define PFN_DEV (1UL << (BITS_PER_LONG - 3)) +#define PFN_MAP (1UL << (BITS_PER_LONG - 4)) + +static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, unsigned long flags) +{ + pfn_t pfn_t = { .val = pfn | (flags & PFN_FLAGS_MASK), }; + + return pfn_t; +} + +/* a default pfn to pfn_t conversion assumes that @pfn is pfn_valid() */ +static inline pfn_t pfn_to_pfn_t(unsigned long pfn) +{ + return __pfn_to_pfn_t(pfn, 0); +} + +extern pfn_t phys_to_pfn_t(dma_addr_t addr, unsigned long flags); + +static inline bool pfn_t_has_page(pfn_t pfn) +{ + return (pfn.val & PFN_MAP) == PFN_MAP || (pfn.val & PFN_DEV) == 0; +} + +static inline unsigned long pfn_t_to_pfn(pfn_t pfn) +{ + return pfn.val & ~PFN_FLAGS_MASK; +} + +static inline struct page *pfn_t_to_page(pfn_t pfn) +{ + if (pfn_t_has_page(pfn)) + return pfn_to_page(pfn_t_to_pfn(pfn)); + return NULL; +} + +static inline dma_addr_t pfn_t_to_phys(pfn_t pfn) +{ + return PFN_PHYS(pfn_t_to_pfn(pfn)); +} + +static inline void *pfn_t_to_virt(pfn_t pfn) +{ + if (pfn_t_has_page(pfn)) + return __va(pfn_t_to_phys(pfn)); + return NULL; +} + +static inline pfn_t page_to_pfn_t(struct page *page) +{ + return pfn_to_pfn_t(page_to_pfn(page)); +} +#endif /* _LINUX_PFN_T_H_ */ diff --git a/kernel/memremap.c b/kernel/memremap.c index 7658d32c5c78..449cb6a5d9a1 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -12,6 +12,7 @@ */ #include #include +#include #include #include #include @@ -147,6 +148,12 @@ void devm_memunmap(struct device *dev, void *addr) } EXPORT_SYMBOL(devm_memunmap); +pfn_t phys_to_pfn_t(dma_addr_t addr, unsigned long flags) +{ + return __pfn_to_pfn_t(addr >> PAGE_SHIFT, flags); +} +EXPORT_SYMBOL(phys_to_pfn_t); + #ifdef CONFIG_ZONE_DEVICE struct page_map { struct resource res; -- cgit v1.2.3-59-g8ed1b From 9476df7d80dfc425b37bfecf1d89edf8ec81fcb6 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 15 Jan 2016 16:56:19 -0800 Subject: mm: introduce find_dev_pagemap() There are several scenarios where we need to retrieve and update metadata associated with a given devm_memremap_pages() mapping, and the only lookup key available is a pfn in the range: 1/ We want to augment vmemmap_populate() (called via arch_add_memory()) to allocate memmap storage from pre-allocated pages reserved by the device driver. At vmemmap_alloc_block_buf() time it grabs device pages rather than page allocator pages. This is in support of devm_memremap_pages() mappings where the memmap is too large to fit in main memory (i.e. large persistent memory devices). 2/ Taking a reference against the mapping when inserting device pages into the address_space radix of a given inode. This facilitates unmap_mapping_range() and truncate_inode_pages() operations when the driver is tearing down the mapping. 3/ get_user_pages() operations on ZONE_DEVICE memory require taking a reference against the mapping so that the driver teardown path can revoke and drain usage of device pages. Signed-off-by: Dan Williams Tested-by: Logan Gunthorpe Cc: Christoph Hellwig Cc: Dave Chinner Cc: Ross Zwisler Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/nvdimm/pmem.c | 2 +- include/linux/io.h | 15 --------- include/linux/memremap.h | 38 ++++++++++++++++++++++ kernel/memremap.c | 85 +++++++++++++++++++++++++++++++++++++++++++----- 4 files changed, 116 insertions(+), 24 deletions(-) create mode 100644 include/linux/memremap.h (limited to 'kernel') diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 5def7f4ddbd2..904629b97c4f 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -21,9 +21,9 @@ #include #include #include -#include #include #include +#include #include #include #include diff --git a/include/linux/io.h b/include/linux/io.h index de64c1e53612..fffd88d7f426 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -89,21 +89,6 @@ void devm_memunmap(struct device *dev, void *addr); void *__devm_memremap_pages(struct device *dev, struct resource *res); -#ifdef CONFIG_ZONE_DEVICE -void *devm_memremap_pages(struct device *dev, struct resource *res); -#else -static inline void *devm_memremap_pages(struct device *dev, struct resource *res) -{ - /* - * Fail attempts to call devm_memremap_pages() without - * ZONE_DEVICE support enabled, this requires callers to fall - * back to plain devm_memremap() based on config - */ - WARN_ON_ONCE(1); - return ERR_PTR(-ENXIO); -} -#endif - /* * Some systems do not have legacy ISA devices. * /dev/port is not a valid interface on these systems. diff --git a/include/linux/memremap.h b/include/linux/memremap.h new file mode 100644 index 000000000000..d90721c178bb --- /dev/null +++ b/include/linux/memremap.h @@ -0,0 +1,38 @@ +#ifndef _LINUX_MEMREMAP_H_ +#define _LINUX_MEMREMAP_H_ +#include + +struct resource; +struct device; +/** + * struct dev_pagemap - metadata for ZONE_DEVICE mappings + * @dev: host device of the mapping for debug + */ +struct dev_pagemap { + /* TODO: vmem_altmap and percpu_ref count */ + struct device *dev; +}; + +#ifdef CONFIG_ZONE_DEVICE +void *devm_memremap_pages(struct device *dev, struct resource *res); +struct dev_pagemap *find_dev_pagemap(resource_size_t phys); +#else +static inline void *devm_memremap_pages(struct device *dev, + struct resource *res) +{ + /* + * Fail attempts to call devm_memremap_pages() without + * ZONE_DEVICE support enabled, this requires callers to fall + * back to plain devm_memremap() based on config + */ + WARN_ON_ONCE(1); + return ERR_PTR(-ENXIO); +} + +static inline struct dev_pagemap *find_dev_pagemap(resource_size_t phys) +{ + return NULL; +} +#endif + +#endif /* _LINUX_MEMREMAP_H_ */ diff --git a/kernel/memremap.c b/kernel/memremap.c index 449cb6a5d9a1..61cfbf4d3054 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -10,6 +10,8 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * General Public License for more details. */ +#include +#include #include #include #include @@ -155,22 +157,57 @@ pfn_t phys_to_pfn_t(dma_addr_t addr, unsigned long flags) EXPORT_SYMBOL(phys_to_pfn_t); #ifdef CONFIG_ZONE_DEVICE +static DEFINE_MUTEX(pgmap_lock); +static RADIX_TREE(pgmap_radix, GFP_KERNEL); +#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1) +#define SECTION_SIZE (1UL << PA_SECTION_SHIFT) + struct page_map { struct resource res; + struct percpu_ref *ref; + struct dev_pagemap pgmap; }; -static void devm_memremap_pages_release(struct device *dev, void *res) +static void pgmap_radix_release(struct resource *res) +{ + resource_size_t key; + + mutex_lock(&pgmap_lock); + for (key = res->start; key <= res->end; key += SECTION_SIZE) + radix_tree_delete(&pgmap_radix, key >> PA_SECTION_SHIFT); + mutex_unlock(&pgmap_lock); +} + +static void devm_memremap_pages_release(struct device *dev, void *data) { - struct page_map *page_map = res; + struct page_map *page_map = data; + struct resource *res = &page_map->res; + resource_size_t align_start, align_size; + + pgmap_radix_release(res); /* pages are dead and unused, undo the arch mapping */ - arch_remove_memory(page_map->res.start, resource_size(&page_map->res)); + align_start = res->start & ~(SECTION_SIZE - 1); + align_size = ALIGN(resource_size(res), SECTION_SIZE); + arch_remove_memory(align_start, align_size); +} + +/* assumes rcu_read_lock() held at entry */ +struct dev_pagemap *find_dev_pagemap(resource_size_t phys) +{ + struct page_map *page_map; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + page_map = radix_tree_lookup(&pgmap_radix, phys >> PA_SECTION_SHIFT); + return page_map ? &page_map->pgmap : NULL; } void *devm_memremap_pages(struct device *dev, struct resource *res) { int is_ram = region_intersects(res->start, resource_size(res), "System RAM"); + resource_size_t key, align_start, align_size; struct page_map *page_map; int error, nid; @@ -190,18 +227,50 @@ void *devm_memremap_pages(struct device *dev, struct resource *res) memcpy(&page_map->res, res, sizeof(*res)); + page_map->pgmap.dev = dev; + mutex_lock(&pgmap_lock); + error = 0; + for (key = res->start; key <= res->end; key += SECTION_SIZE) { + struct dev_pagemap *dup; + + rcu_read_lock(); + dup = find_dev_pagemap(key); + rcu_read_unlock(); + if (dup) { + dev_err(dev, "%s: %pr collides with mapping for %s\n", + __func__, res, dev_name(dup->dev)); + error = -EBUSY; + break; + } + error = radix_tree_insert(&pgmap_radix, key >> PA_SECTION_SHIFT, + page_map); + if (error) { + dev_err(dev, "%s: failed: %d\n", __func__, error); + break; + } + } + mutex_unlock(&pgmap_lock); + if (error) + goto err_radix; + nid = dev_to_node(dev); if (nid < 0) nid = numa_mem_id(); - error = arch_add_memory(nid, res->start, resource_size(res), true); - if (error) { - devres_free(page_map); - return ERR_PTR(error); - } + align_start = res->start & ~(SECTION_SIZE - 1); + align_size = ALIGN(resource_size(res), SECTION_SIZE); + error = arch_add_memory(nid, align_start, align_size, true); + if (error) + goto err_add_memory; devres_add(dev, page_map); return __va(res->start); + + err_add_memory: + err_radix: + pgmap_radix_release(res); + devres_free(page_map); + return ERR_PTR(error); } EXPORT_SYMBOL(devm_memremap_pages); #endif /* CONFIG_ZONE_DEVICE */ -- cgit v1.2.3-59-g8ed1b 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 'kernel') 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 v1.2.3-59-g8ed1b From 5c2c2587b13235bf8b5c9027589f22eff68bdf49 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 15 Jan 2016 16:56:49 -0800 Subject: mm, dax, pmem: introduce {get|put}_dev_pagemap() for dax-gup get_dev_page() enables paths like get_user_pages() to pin a dynamically mapped pfn-range (devm_memremap_pages()) while the resulting struct page objects are in use. Unlike get_page() it may fail if the device is, or is in the process of being, disabled. While the initial lookup of the range may be an expensive list walk, the result is cached to speed up subsequent lookups which are likely to be in the same mapped range. devm_memremap_pages() now requires a reference counter to be specified at init time. For pmem this means moving request_queue allocation into pmem_alloc() so the existing queue usage counter can track "device pages". ZONE_DEVICE pages always have an elevated count and will never be on an lru reclaim list. That space in 'struct page' can be redirected for other uses, but for safety introduce a poison value that will always trip __list_add() to assert. This allows half of the struct list_head storage to be reclaimed with some assurance to back up the assumption that the page count never goes to zero and a list_add() is never attempted. Signed-off-by: Dan Williams Tested-by: Logan Gunthorpe Cc: Dave Hansen Cc: Matthew Wilcox Cc: Ross Zwisler Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/nvdimm/pmem.c | 6 ++++-- include/linux/list.h | 11 ++++++++++ include/linux/memremap.h | 49 ++++++++++++++++++++++++++++++++++++++++++-- include/linux/mm_types.h | 5 +++++ kernel/memremap.c | 53 ++++++++++++++++++++++++++++++++++++++++++++---- lib/list_debug.c | 9 ++++++++ 6 files changed, 125 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 328173d7e1ac..7edf31671dab 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -184,7 +184,7 @@ 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, - NULL); + &q->q_usage_counter, NULL); pmem->pfn_flags |= PFN_MAP; } else pmem->virt_addr = (void __pmem *) devm_memremap(dev, @@ -365,6 +365,7 @@ static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns) struct vmem_altmap *altmap; struct nd_pfn_sb *pfn_sb; struct pmem_device *pmem; + struct request_queue *q; phys_addr_t offset; int rc; struct vmem_altmap __altmap = { @@ -406,9 +407,10 @@ 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); + q = pmem->pmem_queue; devm_memunmap(dev, (void __force *) pmem->virt_addr); pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, &nsio->res, - altmap); + &q->q_usage_counter, altmap); pmem->pfn_flags |= PFN_MAP; if (IS_ERR(pmem->virt_addr)) { rc = PTR_ERR(pmem->virt_addr); diff --git a/include/linux/list.h b/include/linux/list.h index 5356f4d661a7..30cf4200ab40 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -113,6 +113,17 @@ extern void __list_del_entry(struct list_head *entry); extern void list_del(struct list_head *entry); #endif +#ifdef CONFIG_DEBUG_LIST +/* + * See devm_memremap_pages() which wants DEBUG_LIST=y to assert if one + * of the pages it allocates is ever passed to list_add() + */ +extern void list_force_poison(struct list_head *entry); +#else +/* fallback to the less strict LIST_POISON* definitions */ +#define list_force_poison list_del +#endif + /** * list_replace - replace old entry by new one * @old : the element to be replaced diff --git a/include/linux/memremap.h b/include/linux/memremap.h index aa3e82a80d7b..bcaa634139a9 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -1,6 +1,8 @@ #ifndef _LINUX_MEMREMAP_H_ #define _LINUX_MEMREMAP_H_ #include +#include +#include struct resource; struct device; @@ -36,21 +38,25 @@ static inline struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start) /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings * @altmap: pre-allocated/reserved memory for vmemmap allocations + * @res: physical address range covered by @ref + * @ref: reference count that pins the devm_memremap_pages() mapping * @dev: host device of the mapping for debug */ struct dev_pagemap { struct vmem_altmap *altmap; const struct resource *res; + struct percpu_ref *ref; struct device *dev; }; #ifdef CONFIG_ZONE_DEVICE void *devm_memremap_pages(struct device *dev, struct resource *res, - struct vmem_altmap *altmap); + struct percpu_ref *ref, 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 vmem_altmap *altmap) + struct resource *res, struct percpu_ref *ref, + struct vmem_altmap *altmap) { /* * Fail attempts to call devm_memremap_pages() without @@ -66,4 +72,43 @@ static inline struct dev_pagemap *find_dev_pagemap(resource_size_t phys) return NULL; } #endif + +/** + * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn + * @pfn: page frame number to lookup page_map + * @pgmap: optional known pgmap that already has a reference + * + * @pgmap allows the overhead of a lookup to be bypassed when @pfn lands in the + * same mapping. + */ +static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn, + struct dev_pagemap *pgmap) +{ + const struct resource *res = pgmap ? pgmap->res : NULL; + resource_size_t phys = PFN_PHYS(pfn); + + /* + * In the cached case we're already holding a live reference so + * we can simply do a blind increment + */ + if (res && phys >= res->start && phys <= res->end) { + percpu_ref_get(pgmap->ref); + return pgmap; + } + + /* fall back to slow path lookup */ + rcu_read_lock(); + pgmap = find_dev_pagemap(phys); + if (pgmap && !percpu_ref_tryget_live(pgmap->ref)) + pgmap = NULL; + rcu_read_unlock(); + + return pgmap; +} + +static inline void put_dev_pagemap(struct dev_pagemap *pgmap) +{ + if (pgmap) + percpu_ref_put(pgmap->ref); +} #endif /* _LINUX_MEMREMAP_H_ */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 2dd9c313a8c0..d3ebb9d21a53 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -116,6 +116,11 @@ struct page { * Can be used as a generic list * by the page owner. */ + struct dev_pagemap *pgmap; /* ZONE_DEVICE pages are never on an + * lru or handled by a slab + * allocator, this points to the + * hosting device page map. + */ struct { /* slub per cpu partial pages */ struct page *next; /* Next partial slab */ #ifdef CONFIG_64BIT diff --git a/kernel/memremap.c b/kernel/memremap.c index 562f6471fe90..3eb8944265d5 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -179,6 +179,29 @@ static void pgmap_radix_release(struct resource *res) mutex_unlock(&pgmap_lock); } +static unsigned long pfn_first(struct page_map *page_map) +{ + struct dev_pagemap *pgmap = &page_map->pgmap; + const struct resource *res = &page_map->res; + struct vmem_altmap *altmap = pgmap->altmap; + unsigned long pfn; + + pfn = res->start >> PAGE_SHIFT; + if (altmap) + pfn += vmem_altmap_offset(altmap); + return pfn; +} + +static unsigned long pfn_end(struct page_map *page_map) +{ + const struct resource *res = &page_map->res; + + return (res->start + resource_size(res)) >> PAGE_SHIFT; +} + +#define for_each_device_pfn(pfn, map) \ + for (pfn = pfn_first(map); pfn < pfn_end(map); pfn++) + static void devm_memremap_pages_release(struct device *dev, void *data) { struct page_map *page_map = data; @@ -186,6 +209,11 @@ static void devm_memremap_pages_release(struct device *dev, void *data) resource_size_t align_start, align_size; struct dev_pagemap *pgmap = &page_map->pgmap; + if (percpu_ref_tryget_live(pgmap->ref)) { + dev_WARN(dev, "%s: page mapping is still live!\n", __func__); + percpu_ref_put(pgmap->ref); + } + pgmap_radix_release(res); /* pages are dead and unused, undo the arch mapping */ @@ -211,20 +239,26 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys) * devm_memremap_pages - remap and provide memmap backing for the given resource * @dev: hosting device for @res * @res: "host memory" address range + * @ref: a live per-cpu reference count * @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. + * Notes: + * 1/ @ref must be 'live' on entry and 'dead' before devm_memunmap_pages() time + * (or devm release event). + * + * 2/ @res is expected to be 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) + struct percpu_ref *ref, 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; + unsigned long pfn; int error, nid; if (is_ram == REGION_MIXED) { @@ -242,6 +276,9 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, return ERR_PTR(-ENXIO); } + if (!ref) + return ERR_PTR(-EINVAL); + page_map = devres_alloc_node(devm_memremap_pages_release, sizeof(*page_map), GFP_KERNEL, dev_to_node(dev)); if (!page_map) @@ -255,6 +292,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, memcpy(&page_map->altmap, altmap, sizeof(*altmap)); pgmap->altmap = &page_map->altmap; } + pgmap->ref = ref; pgmap->res = &page_map->res; mutex_lock(&pgmap_lock); @@ -292,6 +330,13 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, if (error) goto err_add_memory; + for_each_device_pfn(pfn, page_map) { + struct page *page = pfn_to_page(pfn); + + /* ZONE_DEVICE pages must never appear on a slab lru */ + list_force_poison(&page->lru); + page->pgmap = pgmap; + } devres_add(dev, page_map); return __va(res->start); diff --git a/lib/list_debug.c b/lib/list_debug.c index 3859bf63561c..3345a089ef7b 100644 --- a/lib/list_debug.c +++ b/lib/list_debug.c @@ -12,6 +12,13 @@ #include #include +static struct list_head force_poison; +void list_force_poison(struct list_head *entry) +{ + entry->next = &force_poison; + entry->prev = &force_poison; +} + /* * Insert a new entry between two known consecutive entries. * @@ -23,6 +30,8 @@ void __list_add(struct list_head *new, struct list_head *prev, struct list_head *next) { + WARN(new->next == &force_poison || new->prev == &force_poison, + "list_add attempted on force-poisoned entry\n"); WARN(next->prev != prev, "list_add corruption. next->prev should be " "prev (%p), but was %p. (next=%p).\n", -- cgit v1.2.3-59-g8ed1b 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 'kernel') 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 v1.2.3-59-g8ed1b From 4a9e1cda274893eca7d178d7dc265503ccb9d87a Mon Sep 17 00:00:00 2001 From: Dominik Dingel Date: Fri, 15 Jan 2016 16:57:04 -0800 Subject: mm: bring in additional flag for fixup_user_fault to signal unlock During Jason's work with postcopy migration support for s390 a problem regarding gmap faults was discovered. The gmap code will call fixup_user_fault which will end up always in handle_mm_fault. Till now we never cared about retries, but as the userfaultfd code kind of relies on it. this needs some fix. This patchset does not take care of the futex code. I will now look closer at this. This patch (of 2): With the introduction of userfaultfd, kvm on s390 needs fixup_user_fault to pass in FAULT_FLAG_ALLOW_RETRY and give feedback if during the faulting we ever unlocked mmap_sem. This patch brings in the logic to handle retries as well as it cleans up the current documentation. fixup_user_fault was not having the same semantics as filemap_fault. It never indicated if a retry happened and so a caller wasn't able to handle that case. So we now changed the behaviour to always retry a locked mmap_sem. Signed-off-by: Dominik Dingel Reviewed-by: Andrea Arcangeli Cc: "Kirill A. Shutemov" Cc: Martin Schwidefsky Cc: Christian Borntraeger Cc: "Jason J. Herne" Cc: David Rientjes Cc: Eric B Munson Cc: Naoya Horiguchi Cc: Mel Gorman Cc: Heiko Carstens Cc: Dominik Dingel Cc: Paolo Bonzini Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/s390/mm/pgtable.c | 8 +++++--- include/linux/mm.h | 5 +++-- kernel/futex.c | 2 +- mm/gup.c | 30 +++++++++++++++++++++++++----- 4 files changed, 34 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 4e54492f463a..84bddda8d412 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -585,7 +585,7 @@ int gmap_fault(struct gmap *gmap, unsigned long gaddr, rc = vmaddr; goto out_up; } - if (fixup_user_fault(current, gmap->mm, vmaddr, fault_flags)) { + if (fixup_user_fault(current, gmap->mm, vmaddr, fault_flags, NULL)) { rc = -EFAULT; goto out_up; } @@ -727,7 +727,8 @@ int gmap_ipte_notify(struct gmap *gmap, unsigned long gaddr, unsigned long len) break; } /* Get the page mapped */ - if (fixup_user_fault(current, gmap->mm, addr, FAULT_FLAG_WRITE)) { + if (fixup_user_fault(current, gmap->mm, addr, FAULT_FLAG_WRITE, + NULL)) { rc = -EFAULT; break; } @@ -802,7 +803,8 @@ retry: if (!(pte_val(*ptep) & _PAGE_INVALID) && (pte_val(*ptep) & _PAGE_PROTECT)) { pte_unmap_unlock(ptep, ptl); - if (fixup_user_fault(current, mm, addr, FAULT_FLAG_WRITE)) { + if (fixup_user_fault(current, mm, addr, FAULT_FLAG_WRITE, + NULL)) { up_read(&mm->mmap_sem); return -EFAULT; } diff --git a/include/linux/mm.h b/include/linux/mm.h index 792f2469c142..1d6ec55d8b25 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1194,7 +1194,8 @@ int invalidate_inode_page(struct page *page); extern int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, - unsigned long address, unsigned int fault_flags); + unsigned long address, unsigned int fault_flags, + bool *unlocked); #else static inline int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, @@ -1206,7 +1207,7 @@ static inline int handle_mm_fault(struct mm_struct *mm, } static inline int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, unsigned long address, - unsigned int fault_flags) + unsigned int fault_flags, bool *unlocked) { /* should never happen if there's no MMU */ BUG(); diff --git a/kernel/futex.c b/kernel/futex.c index eed92a8a4c49..c6f514573b28 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -604,7 +604,7 @@ static int fault_in_user_writeable(u32 __user *uaddr) down_read(&mm->mmap_sem); ret = fixup_user_fault(current, mm, (unsigned long)uaddr, - FAULT_FLAG_WRITE); + FAULT_FLAG_WRITE, NULL); up_read(&mm->mmap_sem); return ret < 0 ? ret : 0; diff --git a/mm/gup.c b/mm/gup.c index aa21c4b865a5..b64a36175884 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -618,6 +618,8 @@ EXPORT_SYMBOL(__get_user_pages); * @mm: mm_struct of target mm * @address: user address * @fault_flags:flags to pass down to handle_mm_fault() + * @unlocked: did we unlock the mmap_sem while retrying, maybe NULL if caller + * does not allow retry * * This is meant to be called in the specific scenario where for locking reasons * we try to access user memory in atomic context (within a pagefault_disable() @@ -629,22 +631,28 @@ EXPORT_SYMBOL(__get_user_pages); * The main difference with get_user_pages() is that this function will * unconditionally call handle_mm_fault() which will in turn perform all the * necessary SW fixup of the dirty and young bits in the PTE, while - * handle_mm_fault() only guarantees to update these in the struct page. + * get_user_pages() only guarantees to update these in the struct page. * * This is important for some architectures where those bits also gate the * access permission to the page because they are maintained in software. On * such architectures, gup() will not be enough to make a subsequent access * succeed. * - * This has the same semantics wrt the @mm->mmap_sem as does filemap_fault(). + * This function will not return with an unlocked mmap_sem. So it has not the + * same semantics wrt the @mm->mmap_sem as does filemap_fault(). */ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, - unsigned long address, unsigned int fault_flags) + unsigned long address, unsigned int fault_flags, + bool *unlocked) { struct vm_area_struct *vma; vm_flags_t vm_flags; - int ret; + int ret, major = 0; + + if (unlocked) + fault_flags |= FAULT_FLAG_ALLOW_RETRY; +retry: vma = find_extend_vma(mm, address); if (!vma || address < vma->vm_start) return -EFAULT; @@ -654,6 +662,7 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, return -EFAULT; ret = handle_mm_fault(mm, vma, address, fault_flags); + major |= ret & VM_FAULT_MAJOR; if (ret & VM_FAULT_ERROR) { if (ret & VM_FAULT_OOM) return -ENOMEM; @@ -663,8 +672,19 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, return -EFAULT; BUG(); } + + if (ret & VM_FAULT_RETRY) { + down_read(&mm->mmap_sem); + if (!(fault_flags & FAULT_FLAG_TRIED)) { + *unlocked = true; + fault_flags &= ~FAULT_FLAG_ALLOW_RETRY; + fault_flags |= FAULT_FLAG_TRIED; + goto retry; + } + } + if (tsk) { - if (ret & VM_FAULT_MAJOR) + if (major) tsk->maj_flt++; else tsk->min_flt++; -- cgit v1.2.3-59-g8ed1b From b493c34309cb4aebc44272897067ebf54cb07271 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Fri, 15 Jan 2016 16:58:16 -0800 Subject: kernel/stop_machine.c: remove CONFIG_SMP dependencies stop_machine.o is only built if CONFIG_SMP=y, so this ifdef always evaluates to true. [akpm@linux-foundation.org: remove now-unneeded ifdef] Reported-by: Valentin Rothberg Cc: Chris Wilson Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/stop_machine.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'kernel') diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index edb6de4f5908..a467e6c28a3b 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -529,8 +529,6 @@ static int __init cpu_stop_init(void) } early_initcall(cpu_stop_init); -#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU) - static int __stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { struct multi_stop_data msdata = { @@ -628,5 +626,3 @@ int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, mutex_unlock(&stop_cpus_mutex); return ret ?: done.ret; } - -#endif /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ -- cgit v1.2.3-59-g8ed1b From 81cc26f2bd11ba4421a17a2d5cebe4bba206c239 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 15 Jan 2016 16:58:21 -0800 Subject: printk: only unregister boot consoles when necessary Boot consoles are typically replaced by proper consoles during the boot process. This can be problematic if the boot console data is part of the init section that is reclaimed late during boot. If the proper console does not register before this point in time, the boot console will need to be removed (so that the freed memory is not accessed), leaving the system without output for some time. There are various reasons why the proper console may not register early enough, such as deferred probe or the driver being a loadable module. If that happens, there is some amount of time where no console messages are visible to the user, which in turn can mean that they won't see crashes or other potentially useful information. To avoid this situation, only remove the boot console when it resides in the init section. Code exists to replace the boot console by the proper console when it is registered, keeping a seamless transition between the boot and proper consoles. Signed-off-by: Thierry Reding Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/printk/printk.c | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 2ce8826f1053..0c9f02506169 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -48,6 +48,7 @@ #include #include +#include #define CREATE_TRACE_POINTS #include @@ -2658,13 +2659,36 @@ int unregister_console(struct console *console) } EXPORT_SYMBOL(unregister_console); +/* + * Some boot consoles access data that is in the init section and which will + * be discarded after the initcalls have been run. To make sure that no code + * will access this data, unregister the boot consoles in a late initcall. + * + * If for some reason, such as deferred probe or the driver being a loadable + * module, the real console hasn't registered yet at this point, there will + * be a brief interval in which no messages are logged to the console, which + * makes it difficult to diagnose problems that occur during this time. + * + * To mitigate this problem somewhat, only unregister consoles whose memory + * intersects with the init section. Note that code exists elsewhere to get + * rid of the boot console as soon as the proper console shows up, so there + * won't be side-effects from postponing the removal. + */ static int __init printk_late_init(void) { struct console *con; for_each_console(con) { if (!keep_bootcon && con->flags & CON_BOOT) { - unregister_console(con); + /* + * Make sure to unregister boot consoles whose data + * resides in the init section before the init section + * is discarded. Boot consoles whose data will stick + * around will automatically be unregistered when the + * proper console replaces them. + */ + if (init_section_intersects(con, sizeof(*con))) + unregister_console(con); } } hotcpu_notifier(console_cpu_notify, 0); -- cgit v1.2.3-59-g8ed1b From 8d91f8b15361dfb438ab6eb3b319e2ded43458ff Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 15 Jan 2016 16:58:24 -0800 Subject: printk: do cond_resched() between lines while outputting to consoles @console_may_schedule tracks whether console_sem was acquired through lock or trylock. If the former, we're inside a sleepable context and console_conditional_schedule() performs cond_resched(). This allows console drivers which use console_lock for synchronization to yield while performing time-consuming operations such as scrolling. However, the actual console outputting is performed while holding irq-safe logbuf_lock, so console_unlock() clears @console_may_schedule before starting outputting lines. Also, only a few drivers call console_conditional_schedule() to begin with. This means that when a lot of lines need to be output by console_unlock(), for example on a console registration, the task doing console_unlock() may not yield for a long time on a non-preemptible kernel. If this happens with a slow console devices, for example a serial console, the outputting task may occupy the cpu for a very long time. Long enough to trigger softlockup and/or RCU stall warnings, which in turn pile more messages, sometimes enough to trigger the next cycle of warnings incapacitating the system. Fix it by making console_unlock() insert cond_resched() between lines if @console_may_schedule. Signed-off-by: Tejun Heo Reported-by: Calvin Owens Acked-by: Jan Kara Cc: Dave Jones Cc: Kyle McMartin Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/console.h | 1 + kernel/panic.c | 3 +-- kernel/printk/printk.c | 35 ++++++++++++++++++++++++++++++++++- 3 files changed, 36 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/include/linux/console.h b/include/linux/console.h index bd194343c346..ea731af2451e 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -150,6 +150,7 @@ extern int console_trylock(void); extern void console_unlock(void); extern void console_conditional_schedule(void); extern void console_unblank(void); +extern void console_flush_on_panic(void); extern struct tty_driver *console_device(int *); extern void console_stop(struct console *); extern void console_start(struct console *); diff --git a/kernel/panic.c b/kernel/panic.c index b333380c6bb2..d96469de72dc 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -180,8 +180,7 @@ void panic(const char *fmt, ...) * panic() is not being callled from OOPS. */ debug_locks_off(); - console_trylock(); - console_unlock(); + console_flush_on_panic(); if (!panic_blink) panic_blink = no_blink; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 0c9f02506169..08934a395c1a 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2234,13 +2234,24 @@ void console_unlock(void) static u64 seen_seq; unsigned long flags; bool wake_klogd = false; - bool retry; + bool do_cond_resched, retry; if (console_suspended) { up_console_sem(); return; } + /* + * Console drivers are called under logbuf_lock, so + * @console_may_schedule should be cleared before; however, we may + * end up dumping a lot of lines, for example, if called from + * console registration path, and should invoke cond_resched() + * between lines if allowable. Not doing so can cause a very long + * scheduling stall on a slow console leading to RCU stall and + * softlockup warnings which exacerbate the issue with more + * messages practically incapacitating the system. + */ + do_cond_resched = console_may_schedule; console_may_schedule = 0; /* flush buffered message fragment immediately to console */ @@ -2312,6 +2323,9 @@ skip: call_console_drivers(level, ext_text, ext_len, text, len); start_critical_timings(); local_irq_restore(flags); + + if (do_cond_resched) + cond_resched(); } console_locked = 0; @@ -2379,6 +2393,25 @@ void console_unblank(void) console_unlock(); } +/** + * console_flush_on_panic - flush console content on panic + * + * Immediately output all pending messages no matter what. + */ +void console_flush_on_panic(void) +{ + /* + * If someone else is holding the console lock, trylock will fail + * and may_schedule may be set. Ignore and proceed to unlock so + * that messages are flushed out. As this can be called from any + * context and we don't want to get preempted while flushing, + * ensure may_schedule is cleared. + */ + console_trylock(); + console_may_schedule = 0; + console_unlock(); +} + /* * Return the console tty driver structure and its associated index */ -- cgit v1.2.3-59-g8ed1b From 06b031de22d28ae76b2e5bfaf22c56a265a1e106 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Fri, 15 Jan 2016 16:59:23 -0800 Subject: printk: change recursion_bug type to bool `recursion_bug' is used as recursion_bug toggle, so make it `bool'. Signed-off-by: Sergey Senozhatsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/printk/printk.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 08934a395c1a..e79439134978 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1661,7 +1661,7 @@ asmlinkage int vprintk_emit(int facility, int level, const char *dict, size_t dictlen, const char *fmt, va_list args) { - static int recursion_bug; + static bool recursion_bug; static char textbuf[LOG_LINE_MAX]; char *text = textbuf; size_t text_len = 0; @@ -1697,7 +1697,7 @@ asmlinkage int vprintk_emit(int facility, int level, * it can be printed at the next appropriate moment: */ if (!oops_in_progress && !lockdep_recursing(current)) { - recursion_bug = 1; + recursion_bug = true; local_irq_restore(flags); return 0; } @@ -1712,7 +1712,7 @@ asmlinkage int vprintk_emit(int facility, int level, static const char recursion_msg[] = "BUG: recent printk recursion!"; - recursion_bug = 0; + recursion_bug = false; /* emit KERN_CRIT message */ printed_len += log_store(0, 2, LOG_PREFIX|LOG_NEWLINE, 0, NULL, 0, recursion_msg, -- cgit v1.2.3-59-g8ed1b