mm: memcg: enable memcg OOM killer only for user faults

[deliverable/linux.git] / mm / filemap.c

diff --git a/mm/filemap.c b/mm/filemap.c
index e607728db4a8f011ba80739a1f1cea17aff023bc..e3b6fc8c0b7b545c65dea56e9f2d8bdaaf3d1f69 100644 (file)
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1614,6 +1614,7 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
        struct inode *inode = mapping->host;
        pgoff_t offset = vmf->pgoff;
        struct page *page;
+       bool memcg_oom;
        pgoff_t size;
        int ret = 0;
 
@@ -1622,7 +1623,11 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
                return VM_FAULT_SIGBUS;
 
        /*
-        * Do we have something in the page cache already?
+        * Do we have something in the page cache already?  Either
+        * way, try readahead, but disable the memcg OOM killer for it
+        * as readahead is optional and no errors are propagated up
+        * the fault stack.  The OOM killer is enabled while trying to
+        * instantiate the faulting page individually below.
         */
        page = find_get_page(mapping, offset);
        if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) {
@@ -1630,10 +1635,14 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
                 * We found the page, so try async readahead before
                 * waiting for the lock.
                 */
+               memcg_oom = mem_cgroup_toggle_oom(false);
                do_async_mmap_readahead(vma, ra, file, page, offset);
+               mem_cgroup_toggle_oom(memcg_oom);
        } else if (!page) {
                /* No page in the page cache at all */
+               memcg_oom = mem_cgroup_toggle_oom(false);
                do_sync_mmap_readahead(vma, ra, file, offset);
+               mem_cgroup_toggle_oom(memcg_oom);
                count_vm_event(PGMAJFAULT);
                mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
                ret = VM_FAULT_MAJOR;