mm: drop tail page refcounting

Tail page refcounting is utterly complicated and painful to support.

It uses ->_mapcount on tail pages to store how many times this page is
pinned.  get_page() bumps ->_mapcount on tail page in addition to
->_count on head.  This information is required by split_huge_page() to
be able to distribute pins from head of compound page to tails during
the split.

We will need ->_mapcount to account PTE mappings of subpages of the
compound page.  We eliminate need in current meaning of ->_mapcount in
tail pages by forbidding split entirely if the page is pinned.

The only user of tail page refcounting is THP which is marked BROKEN for
now.

Let's drop all this mess.  It makes get_page() and put_page() much
simpler.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Sasha Levin <sasha.levin@oracle.com>
Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Jerome Marchand <jmarchan@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 5 insertions, 36 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 016b70a..72fd53f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1038,37 +1038,6 @@ unlock:
 	spin_unlock(ptl);
 }
 
-/*
- * Save CONFIG_DEBUG_PAGEALLOC from faulting falsely on tail pages
- * during copy_user_huge_page()'s copy_page_rep(): in the case when
- * the source page gets split and a tail freed before copy completes.
- * Called under pmd_lock of checked pmd, so safe from splitting itself.
- */
-static void get_user_huge_page(struct page *page)
-{
-	if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) {
-		struct page *endpage = page + HPAGE_PMD_NR;
-
-		atomic_add(HPAGE_PMD_NR, &page->_count);
-		while (++page < endpage)
-			get_huge_page_tail(page);
-	} else {
-		get_page(page);
-	}
-}
-
-static void put_user_huge_page(struct page *page)
-{
-	if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) {
-		struct page *endpage = page + HPAGE_PMD_NR;
-
-		while (page < endpage)
-			put_page(page++);
-	} else {
-		put_page(page);
-	}
-}
-
 static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 					struct vm_area_struct *vma,
 					unsigned long address,
@@ -1221,7 +1190,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		ret |= VM_FAULT_WRITE;
 		goto out_unlock;
 	}
-	get_user_huge_page(page);
+	get_page(page);
 	spin_unlock(ptl);
 alloc:
 	if (transparent_hugepage_enabled(vma) &&
@@ -1242,7 +1211,7 @@ alloc:
 				split_huge_pmd(vma, pmd, address);
 				ret |= VM_FAULT_FALLBACK;
 			}
-			put_user_huge_page(page);
+			put_page(page);
 		}
 		count_vm_event(THP_FAULT_FALLBACK);
 		goto out;
@@ -1253,7 +1222,7 @@ alloc:
 		put_page(new_page);
 		if (page) {
 			split_huge_pmd(vma, pmd, address);
-			put_user_huge_page(page);
+			put_page(page);
 		} else
 			split_huge_pmd(vma, pmd, address);
 		ret |= VM_FAULT_FALLBACK;
@@ -1275,7 +1244,7 @@ alloc:
 
 	spin_lock(ptl);
 	if (page)
-		put_user_huge_page(page);
+		put_page(page);
 	if (unlikely(!pmd_same(*pmd, orig_pmd))) {
 		spin_unlock(ptl);
 		mem_cgroup_cancel_charge(new_page, memcg, true);
@@ -1360,7 +1329,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 	if (flags & FOLL_GET)
-		get_page_foll(page);
+		get_page(page);
 
 out:
 	return page;