mm: take i_mmap_lock in unmap_mapping_range() for DAX

DAX is not so special: we need i_mmap_lock to protect mapping->i_mmap.

__dax_pmd_fault() uses unmap_mapping_range() shoot out zero page from
all mappings.  We need to drop i_mmap_lock there to avoid lock deadlock.

Re-aquiring the lock should be fine since we check i_size after the
point.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox <willy@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/dax.c b/fs/dax.c
index 9ef9b80..ed54efe 100644 (file)
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -554,6 +554,25 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
        if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE)
                goto fallback;
 
+       if (buffer_unwritten(&bh) || buffer_new(&bh)) {
+               int i;
+               for (i = 0; i < PTRS_PER_PMD; i++)
+                       clear_page(kaddr + i * PAGE_SIZE);
+               count_vm_event(PGMAJFAULT);
+               mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+               result |= VM_FAULT_MAJOR;
+       }
+
+       /*
+        * If we allocated new storage, make sure no process has any
+        * zero pages covering this hole
+        */
+       if (buffer_new(&bh)) {
+               i_mmap_unlock_write(mapping);
+               unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PMD_SIZE, 0);
+               i_mmap_lock_write(mapping);
+       }
+
        /*
         * If a truncate happened while we were allocating blocks, we may
         * leave blocks allocated to the file that are beyond EOF.  We can't
@@ -568,13 +587,6 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
        if ((pgoff | PG_PMD_COLOUR) >= size)
                goto fallback;
 
-       /*
-        * If we allocated new storage, make sure no process has any
-        * zero pages covering this hole
-        */
-       if (buffer_new(&bh))
-               unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PMD_SIZE, 0);
-
        if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) {
                spinlock_t *ptl;
                pmd_t entry;
@@ -605,15 +617,6 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
                if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR))
                        goto fallback;
 
-               if (buffer_unwritten(&bh) || buffer_new(&bh)) {
-                       int i;
-                       for (i = 0; i < PTRS_PER_PMD; i++)
-                               clear_page(kaddr + i * PAGE_SIZE);
-                       count_vm_event(PGMAJFAULT);
-                       mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
-                       result |= VM_FAULT_MAJOR;
-               }
-
                result |= vmf_insert_pfn_pmd(vma, address, pmd, pfn, write);
        }
 

diff --git a/mm/memory.c b/mm/memory.c
index 320c42e..ce8e983 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2426,17 +2426,10 @@ void unmap_mapping_range(struct address_space *mapping,
        if (details.last_index < details.first_index)
                details.last_index = ULONG_MAX;
 
-
-       /*
-        * DAX already holds i_mmap_lock to serialise file truncate vs
-        * page fault and page fault vs page fault.
-        */
-       if (!IS_DAX(mapping->host))
-               i_mmap_lock_write(mapping);
+       i_mmap_lock_write(mapping);
        if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap)))
                unmap_mapping_range_tree(&mapping->i_mmap, &details);
-       if (!IS_DAX(mapping->host))
-               i_mmap_unlock_write(mapping);
+       i_mmap_unlock_write(mapping);
 }
 EXPORT_SYMBOL(unmap_mapping_range);