Merge branch 'hwpoison' of git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux...

[karo-tx-linux.git] / mm / memory.c

diff --git a/mm/memory.c b/mm/memory.c
index 5c694f2b9c12d02d6a9ca129afb702d68237a9c9..987389a809e77accb1915dbd291d3e38b8dc1e60 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -108,7 +108,8 @@ static int __init disable_randmaps(char *s)
 }
 __setup("norandmaps", disable_randmaps);
 
-static unsigned long zero_pfn __read_mostly;
+unsigned long zero_pfn __read_mostly;
+unsigned long highest_memmap_pfn __read_mostly;
 
 /*
  * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init()
@@ -455,6 +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.
  *
@@ -512,7 +527,7 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
                        goto check_pfn;
                if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
                        return NULL;
-               if (pfn != zero_pfn)
+               if (!is_zero_pfn(pfn))
                        print_bad_pte(vma, addr, pte, NULL);
                return NULL;
        }
@@ -534,6 +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);
@@ -1161,7 +1178,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
        page = vm_normal_page(vma, address, pte);
        if (unlikely(!page)) {
                if ((flags & FOLL_DUMP) ||
-                   pte_pfn(pte) != zero_pfn)
+                   !is_zero_pfn(pte_pfn(pte)))
                        goto bad_page;
                page = pte_page(pte);
        }
@@ -1308,7 +1325,8 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                                if (ret & VM_FAULT_ERROR) {
                                        if (ret & VM_FAULT_OOM)
                                                return i ? i : -ENOMEM;
-                                       else if (ret & VM_FAULT_SIGBUS)
+                                       if (ret &
+                                           (VM_FAULT_HWPOISON|VM_FAULT_SIGBUS))
                                                return i ? i : -EFAULT;
                                        BUG();
                                }
@@ -1443,10 +1461,6 @@ struct page *get_dump_page(unsigned long addr)
        if (__get_user_pages(current, current->mm, addr, 1,
                        FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma) < 1)
                return NULL;
-       if (page == ZERO_PAGE(0)) {
-               page_cache_release(page);
-               return NULL;
-       }
        flush_cache_page(vma, addr, page_to_pfn(page));
        return page;
 }
@@ -1629,7 +1643,8 @@ 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;
@@ -2097,7 +2112,7 @@ gotten:
        if (unlikely(anon_vma_prepare(vma)))
                goto oom;
 
-       if (pte_pfn(orig_pte) == zero_pfn) {
+       if (is_zero_pfn(pte_pfn(orig_pte))) {
                new_page = alloc_zeroed_user_highpage_movable(vma, address);
                if (!new_page)
                        goto oom;
@@ -2545,8 +2560,15 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
                goto out;
 
        entry = pte_to_swp_entry(orig_pte);
-       if (is_migration_entry(entry)) {
-               migration_entry_wait(mm, pmd, address);
+       if (unlikely(non_swap_entry(entry))) {
+               if (is_migration_entry(entry)) {
+                       migration_entry_wait(mm, pmd, address);
+               } else if (is_hwpoison_entry(entry)) {
+                       ret = VM_FAULT_HWPOISON;
+               } else {
+                       print_bad_pte(vma, address, orig_pte, NULL);
+                       ret = VM_FAULT_OOM;
+               }
                goto out;
        }
        delayacct_set_flag(DELAYACCT_PF_SWAPIN);
@@ -2570,6 +2592,10 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
                /* Had to read the page from swap area: Major fault */
                ret = VM_FAULT_MAJOR;
                count_vm_event(PGMAJFAULT);
+       } else if (PageHWPoison(page)) {
+               ret = VM_FAULT_HWPOISON;
+               delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
+               goto out;
        }
 
        lock_page(page);
@@ -2658,8 +2684,9 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
        spinlock_t *ptl;
        pte_t entry;
 
-       if (HAVE_PTE_SPECIAL && !(flags & FAULT_FLAG_WRITE)) {
-               entry = pte_mkspecial(pfn_pte(zero_pfn, vma->vm_page_prot));
+       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))
@@ -2745,6 +2772,12 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
        if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))
                return ret;
 
+       if (unlikely(PageHWPoison(vmf.page))) {
+               if (ret & VM_FAULT_LOCKED)
+                       unlock_page(vmf.page);
+               return VM_FAULT_HWPOISON;
+       }
+
        /*
         * For consistency in subsequent calls, make the faulted page always
         * locked.