Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/gerg/m68knommu

[~andy/linux] / mm / memory.c

diff --git a/mm/memory.c b/mm/memory.c
index e5bfbe6b594cde7662df86d0b5386fe59abfbb86..22bfa7a47a0b613cf9c39ee6e7d24f7dc3c9cf77 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1511,6 +1511,7 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
                        unsigned long pfn)
 {
        int ret;
+       pgprot_t pgprot = vma->vm_page_prot;
        /*
         * Technically, architectures with pte_special can avoid all these
         * restrictions (same for remap_pfn_range).  However we would like
@@ -1525,10 +1526,10 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 
        if (addr < vma->vm_start || addr >= vma->vm_end)
                return -EFAULT;
-       if (track_pfn_vma_new(vma, vma->vm_page_prot, pfn, PAGE_SIZE))
+       if (track_pfn_vma_new(vma, &pgprot, pfn, PAGE_SIZE))
                return -EINVAL;
 
-       ret = insert_pfn(vma, addr, pfn, vma->vm_page_prot);
+       ret = insert_pfn(vma, addr, pfn, pgprot);
 
        if (ret)
                untrack_pfn_vma(vma, pfn, PAGE_SIZE);
@@ -1671,9 +1672,15 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 
        vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
 
-       err = track_pfn_vma_new(vma, prot, pfn, PAGE_ALIGN(size));
-       if (err)
+       err = track_pfn_vma_new(vma, &prot, pfn, PAGE_ALIGN(size));
+       if (err) {
+               /*
+                * To indicate that track_pfn related cleanup is not
+                * needed from higher level routine calling unmap_vmas
+                */
+               vma->vm_flags &= ~(VM_IO | VM_RESERVED | VM_PFNMAP);
                return -EINVAL;
+       }
 
        BUG_ON(addr >= end);
        pfn -= addr >> PAGE_SHIFT;
@@ -2457,22 +2464,23 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
         * while the page is counted on swap but not yet in mapcount i.e.
         * before page_add_anon_rmap() and swap_free(); try_to_free_swap()
         * must be called after the swap_free(), or it will never succeed.
-        * And mem_cgroup_commit_charge_swapin(), which uses the swp_entry
-        * in page->private, must be called before reuse_swap_page(),
-        * which may delete_from_swap_cache().
+        * Because delete_from_swap_page() may be called by reuse_swap_page(),
+        * mem_cgroup_commit_charge_swapin() may not be able to find swp_entry
+        * in page->private. In this case, a record in swap_cgroup  is silently
+        * discarded at swap_free().
         */
 
-       mem_cgroup_commit_charge_swapin(page, ptr);
        inc_mm_counter(mm, anon_rss);
        pte = mk_pte(page, vma->vm_page_prot);
        if (write_access && reuse_swap_page(page)) {
                pte = maybe_mkwrite(pte_mkdirty(pte), vma);
                write_access = 0;
        }
-
        flush_icache_page(vma, page);
        set_pte_at(mm, address, page_table, pte);
        page_add_anon_rmap(page, vma, address);
+       /* It's better to call commit-charge after rmap is established */
+       mem_cgroup_commit_charge_swapin(page, ptr);
 
        swap_free(entry);
        if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
@@ -3164,6 +3172,15 @@ void print_vma_addr(char *prefix, unsigned long ip)
 #ifdef CONFIG_PROVE_LOCKING
 void might_fault(void)
 {
+       /*
+        * Some code (nfs/sunrpc) uses socket ops on kernel memory while
+        * holding the mmap_sem, this is safe because kernel memory doesn't
+        * get paged out, therefore we'll never actually fault, and the
+        * below annotations will generate false positives.
+        */
+       if (segment_eq(get_fs(), KERNEL_DS))
+               return;
+
        might_sleep();
        /*
         * it would be nicer only to annotate paths which are not under