1 files changed, 136 insertions, 76 deletions

diff --git a/mm/memory.c b/mm/memory.c
index e8f63d9961ea..b1443ac07c00 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -45,6 +45,7 @@
 #include <linux/swap.h>
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
+#include <linux/ksm.h>
 #include <linux/rmap.h>
 #include <linux/module.h>
 #include <linux/delayacct.h>
@@ -107,6 +108,18 @@ static int __init disable_randmaps(char *s)
 }
 __setup("norandmaps", disable_randmaps);
 
+unsigned long zero_pfn __read_mostly;
+unsigned long highest_memmap_pfn __read_mostly;
+
+/*
+ * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init()
+ */
+static int __init init_zero_pfn(void)
+{
+        zero_pfn = page_to_pfn(ZERO_PAGE(0));
+        return 0;
+}
+core_initcall(init_zero_pfn);
 
 /*
  * If a p?d_bad entry is found while walking page tables, report
@@ -443,6 +456,20 @@ static inline int is_cow_mapping(unsigned int flags)
         return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
 }
 
+#ifndef is_zero_pfn
+static inline int is_zero_pfn(unsigned long pfn)
+{
+        return pfn == zero_pfn;
+}
+#endif
+
+#ifndef my_zero_pfn
+static inline unsigned long my_zero_pfn(unsigned long addr)
+{
+        return zero_pfn;
+}
+#endif
+
 /*
  * vm_normal_page -- This function gets the "struct page" associated with a pte.
  *
@@ -498,7 +525,9 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
         if (HAVE_PTE_SPECIAL) {
                 if (likely(!pte_special(pte)))
                         goto check_pfn;
-                if (!(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)))
+                if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
+                        return NULL;
+                if (!is_zero_pfn(pfn))
                         print_bad_pte(vma, addr, pte, NULL);
                 return NULL;
         }
@@ -520,6 +549,8 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
                 }
         }
 
+        if (is_zero_pfn(pfn))
+                return NULL;
 check_pfn:
         if (unlikely(pfn > highest_memmap_pfn)) {
                 print_bad_pte(vma, addr, pte, NULL);
@@ -597,8 +628,8 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
         page = vm_normal_page(vma, addr, pte);
         if (page) {
                 get_page(page);
-                page_dup_rmap(page, vma, addr);
-                rss[!!PageAnon(page)]++;
+                page_dup_rmap(page);
+                rss[PageAnon(page)]++;
         }
 
 out_set_pte:
@@ -1143,9 +1174,14 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
                 goto no_page;
         if ((flags & FOLL_WRITE) && !pte_write(pte))
                 goto unlock;
+
         page = vm_normal_page(vma, address, pte);
-        if (unlikely(!page))
-                goto bad_page;
+        if (unlikely(!page)) {
+                if ((flags & FOLL_DUMP) ||
+                    !is_zero_pfn(pte_pfn(pte)))
+                        goto bad_page;
+                page = pte_page(pte);
+        }
 
         if (flags & FOLL_GET)
                 get_page(page);
@@ -1173,65 +1209,46 @@ no_page:
         pte_unmap_unlock(ptep, ptl);
         if (!pte_none(pte))
                 return page;
-        /* Fall through to ZERO_PAGE handling */
+
 no_page_table:
         /*
          * When core dumping an enormous anonymous area that nobody
-         * has touched so far, we don't want to allocate page tables.
+         * has touched so far, we don't want to allocate unnecessary pages or
+         * page tables.  Return error instead of NULL to skip handle_mm_fault,
+         * then get_dump_page() will return NULL to leave a hole in the dump.
+         * But we can only make this optimization where a hole would surely
+         * be zero-filled if handle_mm_fault() actually did handle it.
          */
-        if (flags & FOLL_ANON) {
-                page = ZERO_PAGE(0);
-                if (flags & FOLL_GET)
-                        get_page(page);
-                BUG_ON(flags & FOLL_WRITE);
-        }
+        if ((flags & FOLL_DUMP) &&
+            (!vma->vm_ops || !vma->vm_ops->fault))
+                return ERR_PTR(-EFAULT);
         return page;
 }
 
-/* Can we do the FOLL_ANON optimization? */
-static inline int use_zero_page(struct vm_area_struct *vma)
-{
-        /*
-         * We don't want to optimize FOLL_ANON for make_pages_present()
-         * when it tries to page in a VM_LOCKED region. As to VM_SHARED,
-         * we want to get the page from the page tables to make sure
-         * that we serialize and update with any other user of that
-         * mapping.
-         */
-        if (vma->vm_flags & (VM_LOCKED | VM_SHARED))
-                return 0;
-        /*
-         * And if we have a fault routine, it's not an anonymous region.
-         */
-        return !vma->vm_ops || !vma->vm_ops->fault;
-}
-
-
-
 int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-                     unsigned long start, int nr_pages, int flags,
+                     unsigned long start, int nr_pages, unsigned int gup_flags,
                      struct page **pages, struct vm_area_struct **vmas)
 {
         int i;
-        unsigned int vm_flags = 0;
-        int write = !!(flags & GUP_FLAGS_WRITE);
-        int force = !!(flags & GUP_FLAGS_FORCE);
-        int ignore = !!(flags & GUP_FLAGS_IGNORE_VMA_PERMISSIONS);
-        int ignore_sigkill = !!(flags & GUP_FLAGS_IGNORE_SIGKILL);
+        unsigned long vm_flags;
 
         if (nr_pages <= 0)
                 return 0;
+
+        VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));
+
         /* 
          * Require read or write permissions.
-         * If 'force' is set, we only require the "MAY" flags.
+         * If FOLL_FORCE is set, we only require the "MAY" flags.
          */
-        vm_flags  = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
-        vm_flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
+        vm_flags  = (gup_flags & FOLL_WRITE) ?
+                        (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
+        vm_flags &= (gup_flags & FOLL_FORCE) ?
+                        (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
         i = 0;
 
         do {
                 struct vm_area_struct *vma;
-                unsigned int foll_flags;
 
                 vma = find_extend_vma(mm, start);
                 if (!vma && in_gate_area(tsk, start)) {
@@ -1243,7 +1260,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                         pte_t *pte;
 
                         /* user gate pages are read-only */
-                        if (!ignore && write)
+                        if (gup_flags & FOLL_WRITE)
                                 return i ? : -EFAULT;
                         if (pg > TASK_SIZE)
                                 pgd = pgd_offset_k(pg);
@@ -1277,38 +1294,26 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 
                 if (!vma ||
                     (vma->vm_flags & (VM_IO | VM_PFNMAP)) ||
-                    (!ignore && !(vm_flags & vma->vm_flags)))
+                    !(vm_flags & vma->vm_flags))
                         return i ? : -EFAULT;
 
                 if (is_vm_hugetlb_page(vma)) {
                         i = follow_hugetlb_page(mm, vma, pages, vmas,
-                                                &start, &nr_pages, i, write);
+                                        &start, &nr_pages, i, gup_flags);
                         continue;
                 }
 
-                foll_flags = FOLL_TOUCH;
-                if (pages)
-                        foll_flags |= FOLL_GET;
-                if (!write && use_zero_page(vma))
-                        foll_flags |= FOLL_ANON;
-
                 do {
                         struct page *page;
+                        unsigned int foll_flags = gup_flags;
 
                         /*
                          * If we have a pending SIGKILL, don't keep faulting
-                         * pages and potentially allocating memory, unless
-                         * current is handling munlock--e.g., on exit. In
-                         * that case, we are not allocating memory.  Rather,
-                         * we're only unlocking already resident/mapped pages.
+                         * pages and potentially allocating memory.
                          */
-                        if (unlikely(!ignore_sigkill &&
-                                        fatal_signal_pending(current)))
+                        if (unlikely(fatal_signal_pending(current)))
                                 return i ? i : -ERESTARTSYS;
 
-                        if (write)
-                                foll_flags |= FOLL_WRITE;
-
                         cond_resched();
                         while (!(page = follow_page(vma, start, foll_flags))) {
                                 int ret;
@@ -1419,18 +1424,47 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                 unsigned long start, int nr_pages, int write, int force,
                 struct page **pages, struct vm_area_struct **vmas)
 {
-        int flags = 0;
+        int flags = FOLL_TOUCH;
 
+        if (pages)
+                flags |= FOLL_GET;
         if (write)
-                flags |= GUP_FLAGS_WRITE;
+                flags |= FOLL_WRITE;
         if (force)
-                flags |= GUP_FLAGS_FORCE;
+                flags |= FOLL_FORCE;
 
         return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas);
 }
-
 EXPORT_SYMBOL(get_user_pages);
 
+/**
+ * get_dump_page() - pin user page in memory while writing it to core dump
+ * @addr: user address
+ *
+ * Returns struct page pointer of user page pinned for dump,
+ * to be freed afterwards by page_cache_release() or put_page().
+ *
+ * Returns NULL on any kind of failure - a hole must then be inserted into
+ * the corefile, to preserve alignment with its headers; and also returns
+ * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found -
+ * allowing a hole to be left in the corefile to save diskspace.
+ *
+ * Called without mmap_sem, but after all other threads have been killed.
+ */
+#ifdef CONFIG_ELF_CORE
+struct page *get_dump_page(unsigned long addr)
+{
+        struct vm_area_struct *vma;
+        struct page *page;
+
+        if (__get_user_pages(current, current->mm, addr, 1,
+                        FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma) < 1)
+                return NULL;
+        flush_cache_page(vma, addr, page_to_pfn(page));
+        return page;
+}
+#endif /* CONFIG_ELF_CORE */
+
 pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr,
                         spinlock_t **ptl)
 {
@@ -1608,7 +1642,8 @@ int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
          * If we don't have pte special, then we have to use the pfn_valid()
          * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must*
          * refcount the page if pfn_valid is true (hence insert_page rather
-         * than insert_pfn).
+         * than insert_pfn).  If a zero_pfn were inserted into a VM_MIXEDMAP
+         * without pte special, it would there be refcounted as a normal page.
          */
         if (!HAVE_PTE_SPECIAL && pfn_valid(pfn)) {
                 struct page *page;
@@ -1974,7 +2009,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
          * Take out anonymous pages first, anonymous shared vmas are
          * not dirty accountable.
          */
-        if (PageAnon(old_page)) {
+        if (PageAnon(old_page) && !PageKsm(old_page)) {
                 if (!trylock_page(old_page)) {
                         page_cache_get(old_page);
                         pte_unmap_unlock(page_table, ptl);
@@ -2075,10 +2110,19 @@ gotten:
 
         if (unlikely(anon_vma_prepare(vma)))
                 goto oom;
-        VM_BUG_ON(old_page == ZERO_PAGE(0));
-        new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
-        if (!new_page)
-                goto oom;
+
+        if (is_zero_pfn(pte_pfn(orig_pte))) {
+                new_page = alloc_zeroed_user_highpage_movable(vma, address);
+                if (!new_page)
+                        goto oom;
+        } else {
+                new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
+                if (!new_page)
+                        goto oom;
+                cow_user_page(new_page, old_page, address, vma);
+        }
+        __SetPageUptodate(new_page);
+
         /*
          * Don't let another task, with possibly unlocked vma,
          * keep the mlocked page.
@@ -2088,8 +2132,6 @@ gotten:
                 clear_page_mlock(old_page);
                 unlock_page(old_page);
         }
-        cow_user_page(new_page, old_page, address, vma);
-        __SetPageUptodate(new_page);
 
         if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))
                 goto oom_free_new;
@@ -2115,9 +2157,14 @@ gotten:
                  * seen in the presence of one thread doing SMC and another
                  * thread doing COW.
                  */
-                ptep_clear_flush_notify(vma, address, page_table);
+                ptep_clear_flush(vma, address, page_table);
                 page_add_new_anon_rmap(new_page, vma, address);
-                set_pte_at(mm, address, page_table, entry);
+                /*
+                 * We call the notify macro here because, when using secondary
+                 * mmu page tables (such as kvm shadow page tables), we want the
+                 * new page to be mapped directly into the secondary page table.
+                 */
+                set_pte_at_notify(mm, address, page_table, entry);
                 update_mmu_cache(vma, address, entry);
                 if (old_page) {
                         /*
@@ -2625,6 +2672,16 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
         spinlock_t *ptl;
         pte_t entry;
 
+        if (!(flags & FAULT_FLAG_WRITE)) {
+                entry = pte_mkspecial(pfn_pte(my_zero_pfn(address),
+                                                vma->vm_page_prot));
+                ptl = pte_lockptr(mm, pmd);
+                spin_lock(ptl);
+                if (!pte_none(*page_table))
+                        goto unlock;
+                goto setpte;
+        }
+
         /* Allocate our own private page. */
         pte_unmap(page_table);
 
@@ -2639,13 +2696,16 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
                 goto oom_free_page;
 
         entry = mk_pte(page, vma->vm_page_prot);
-        entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+        if (vma->vm_flags & VM_WRITE)
+                entry = pte_mkwrite(pte_mkdirty(entry));
 
         page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
         if (!pte_none(*page_table))
                 goto release;
+
         inc_mm_counter(mm, anon_rss);
         page_add_new_anon_rmap(page, vma, address);
+setpte:
         set_pte_at(mm, address, page_table, entry);
 
         /* No need to invalidate - it was non-present before */