mm: thp: optimize memcg charge in khugepaged

We don't need to hold the mmmap_sem through mem_cgroup_newpage_charge(),
the mmap_sem is only hold for keeping the vma stable and we don't need the
vma stable anymore after we return from alloc_hugepage_vma().
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/huge_memory.c

@@ -1771,12 +1771,9 @@ static void collapse_huge_page(struct mm_struct *mm,
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
 #ifndef CONFIG_NUMA
+	up_read(&mm->mmap_sem);
 	VM_BUG_ON(!*hpage);
 	new_page = *hpage;
-	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
-		up_read(&mm->mmap_sem);
-		return;
-	}
 #else
 	VM_BUG_ON(*hpage);
 	/*
@@ -1791,22 +1788,26 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 */
 	new_page = alloc_hugepage_vma(khugepaged_defrag(), vma, address,
 				      node, __GFP_OTHER_NODE);
+
+	/*
+	 * After allocating the hugepage, release the mmap_sem read lock in
+	 * preparation for taking it in write mode.
+	 */
+	up_read(&mm->mmap_sem);
 	if (unlikely(!new_page)) {
-		up_read(&mm->mmap_sem);
 		count_vm_event(THP_COLLAPSE_ALLOC_FAILED);
 		*hpage = ERR_PTR(-ENOMEM);
 		return;
 	}
+#endif
+
 	count_vm_event(THP_COLLAPSE_ALLOC);
 	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
-		up_read(&mm->mmap_sem);
+#ifdef CONFIG_NUMA
 		put_page(new_page);
+#endif
 		return;
 	}
-#endif
-
-	/* after allocating the hugepage upgrade to mmap_sem write mode */
-	up_read(&mm->mmap_sem);
 
 	/*
 	 * Prevent all access to pagetables with the exception of