Merge branch 'work.mount' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

[thirdparty/kernel/stable.git] / fs / dax.c

diff --git a/fs/dax.c b/fs/dax.c
index 48132eca3761de2b4cdf7c6c75ab8efda8cf7a26..ca0671d55aa699df6723ffb897706b6579c68780 100644 (file)
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -246,18 +246,16 @@ static void wait_entry_unlocked(struct xa_state *xas, void *entry)
        ewait.wait.func = wake_exceptional_entry_func;
 
        wq = dax_entry_waitqueue(xas, entry, &ewait.key);
-       prepare_to_wait_exclusive(wq, &ewait.wait, TASK_UNINTERRUPTIBLE);
+       /*
+        * Unlike get_unlocked_entry() there is no guarantee that this
+        * path ever successfully retrieves an unlocked entry before an
+        * inode dies. Perform a non-exclusive wait in case this path
+        * never successfully performs its own wake up.
+        */
+       prepare_to_wait(wq, &ewait.wait, TASK_UNINTERRUPTIBLE);
        xas_unlock_irq(xas);
        schedule();
        finish_wait(wq, &ewait.wait);
-
-       /*
-        * Entry lock waits are exclusive. Wake up the next waiter since
-        * we aren't sure we will acquire the entry lock and thus wake
-        * the next waiter up on unlock.
-        */
-       if (waitqueue_active(wq))
-               __wake_up(wq, TASK_NORMAL, 1, &ewait.key);
 }
 
 static void put_unlocked_entry(struct xa_state *xas, void *entry)
@@ -779,7 +777,8 @@ static void dax_entry_mkclean(struct address_space *mapping, pgoff_t index,
 
        i_mmap_lock_read(mapping);
        vma_interval_tree_foreach(vma, &mapping->i_mmap, index, index) {
-               unsigned long address, start, end;
+               struct mmu_notifier_range range;
+               unsigned long address;
 
                cond_resched();
 
@@ -789,11 +788,12 @@ static void dax_entry_mkclean(struct address_space *mapping, pgoff_t index,
                address = pgoff_address(index, vma);
 
                /*
-                * Note because we provide start/end to follow_pte_pmd it will
+                * Note because we provide range to follow_pte_pmd it will
                 * call mmu_notifier_invalidate_range_start() on our behalf
                 * before taking any lock.
                 */
-               if (follow_pte_pmd(vma->vm_mm, address, &start, &end, &ptep, &pmdp, &ptl))
+               if (follow_pte_pmd(vma->vm_mm, address, &range,
+                                  &ptep, &pmdp, &ptl))
                        continue;
 
                /*
@@ -835,7 +835,7 @@ unlock_pte:
                        pte_unmap_unlock(ptep, ptl);
                }
 
-               mmu_notifier_invalidate_range_end(vma->vm_mm, start, end);
+               mmu_notifier_invalidate_range_end(&range);
        }
        i_mmap_unlock_read(mapping);
 }
@@ -843,9 +843,8 @@ unlock_pte:
 static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev,
                struct address_space *mapping, void *entry)
 {
-       unsigned long pfn;
+       unsigned long pfn, index, count;
        long ret = 0;
-       size_t size;
 
        /*
         * A page got tagged dirty in DAX mapping? Something is seriously
@@ -894,17 +893,18 @@ static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev,
        xas_unlock_irq(xas);
 
        /*
-        * Even if dax_writeback_mapping_range() was given a wbc->range_start
-        * in the middle of a PMD, the 'index' we are given will be aligned to
-        * the start index of the PMD, as will the pfn we pull from 'entry'.
+        * If dax_writeback_mapping_range() was given a wbc->range_start
+        * in the middle of a PMD, the 'index' we use needs to be
+        * aligned to the start of the PMD.
         * This allows us to flush for PMD_SIZE and not have to worry about
         * partial PMD writebacks.
         */
        pfn = dax_to_pfn(entry);
-       size = PAGE_SIZE << dax_entry_order(entry);
+       count = 1UL << dax_entry_order(entry);
+       index = xas->xa_index & ~(count - 1);
 
-       dax_entry_mkclean(mapping, xas->xa_index, pfn);
-       dax_flush(dax_dev, page_address(pfn_to_page(pfn)), size);
+       dax_entry_mkclean(mapping, index, pfn);
+       dax_flush(dax_dev, page_address(pfn_to_page(pfn)), count * PAGE_SIZE);
        /*
         * After we have flushed the cache, we can clear the dirty tag. There
         * cannot be new dirty data in the pfn after the flush has completed as
@@ -917,8 +917,7 @@ static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev,
        xas_clear_mark(xas, PAGECACHE_TAG_DIRTY);
        dax_wake_entry(xas, entry, false);
 
-       trace_dax_writeback_one(mapping->host, xas->xa_index,
-                       size >> PAGE_SHIFT);
+       trace_dax_writeback_one(mapping->host, index, count);
        return ret;
 
  put_unlocked:
@@ -1220,9 +1219,7 @@ static vm_fault_t dax_fault_return(int error)
 {
        if (error == 0)
                return VM_FAULT_NOPAGE;
-       if (error == -ENOMEM)
-               return VM_FAULT_OOM;
-       return VM_FAULT_SIGBUS;
+       return vmf_error(error);
 }
 
 /*