mm/rmap: always do TTU_IGNORE_ACCESS

Since commit 369ea8242c0f ("mm/rmap: update to new mmu_notifier semantic
v2"), the code to check the secondary MMU's page table access bit is
broken for !(TTU_IGNORE_ACCESS) because the page is unmapped from the
secondary MMU's page table before the check.  More specifically for those
secondary MMUs which unmap the memory in
mmu_notifier_invalidate_range_start() like kvm.

However memory reclaim is the only user of !(TTU_IGNORE_ACCESS) or the
absence of TTU_IGNORE_ACCESS and it explicitly performs the page table
access check before trying to unmap the page.  So, at worst the reclaim
will miss accesses in a very short window if we remove page table access
check in unmapping code.

There is an unintented consequence of !(TTU_IGNORE_ACCESS) for the memcg
reclaim.  From memcg reclaim the page_referenced() only account the
accesses from the processes which are in the same memcg of the target page
but the unmapping code is considering accesses from all the processes, so,
decreasing the effectiveness of memcg reclaim.

The simplest solution is to always assume TTU_IGNORE_ACCESS in unmapping
code.

Link: https://lkml.kernel.org/r/20201104231928.1494083-1-shakeelb@google.com
Fixes: 369ea8242c0f ("mm/rmap: update to new mmu_notifier semantic v2")
Change-Id: If6b3d528bf5d76d2004817da96dfa430e78de42f
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[backport of the commit 013339df116c2ee0d796dd8bfb8f293a2030c063 from mainline]
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 988d176..c247109 100644 (file)
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -91,7 +91,6 @@ enum ttu_flags {
 
        TTU_SPLIT_HUGE_PMD      = 0x4,  /* split huge PMD if any */
        TTU_IGNORE_MLOCK        = 0x8,  /* ignore mlock */
-       TTU_IGNORE_ACCESS       = 0x10, /* don't age */
        TTU_IGNORE_HWPOISON     = 0x20, /* corrupted page is recoverable */
        TTU_BATCH_FLUSH         = 0x40, /* Batch TLB flushes where possible
                                         * and caller guarantees they will

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index da9040a..e3e4afc 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2434,7 +2434,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
 
 static void unmap_page(struct page *page)
 {
-       enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
+       enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK |
                TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
        bool unmap_success;
 

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 3151c87..58120d0 100644 (file)
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -965,7 +965,7 @@ EXPORT_SYMBOL_GPL(get_hwpoison_page);
 static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
                                  int flags, struct page **hpagep)
 {
-       enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS;
+       enum ttu_flags ttu = TTU_IGNORE_MLOCK;
        struct address_space *mapping;
        LIST_HEAD(tokill);
        bool unmap_success;

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c054945..ead6008 100644 (file)
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1340,7 +1340,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
                        if (WARN_ON(PageLRU(page)))
                                isolate_lru_page(page);
                        if (page_mapped(page))
-                               try_to_unmap(page, TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS);
+                               try_to_unmap(page, TTU_IGNORE_MLOCK);
                        continue;
                }
 

diff --git a/mm/migrate.c b/mm/migrate.c
index c4c313e..ffa3686 100644 (file)
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1107,8 +1107,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
                /* Establish migration ptes */
                VM_BUG_ON_PAGE(PageAnon(page) && !PageKsm(page) && !anon_vma,
                                page);
-               try_to_unmap(page,
-                       TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
+               try_to_unmap(page, TTU_MIGRATION|TTU_IGNORE_MLOCK);
                page_was_mapped = 1;
        }
 
@@ -1334,7 +1333,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 
        if (page_mapped(hpage)) {
                try_to_unmap(hpage,
-                       TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
+                       TTU_MIGRATION|TTU_IGNORE_MLOCK);
                page_was_mapped = 1;
        }
 
@@ -2551,7 +2550,7 @@ static void migrate_vma_prepare(struct migrate_vma *migrate)
  */
 static void migrate_vma_unmap(struct migrate_vma *migrate)
 {
-       int flags = TTU_MIGRATION | TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS;
+       int flags = TTU_MIGRATION | TTU_IGNORE_MLOCK;
        const unsigned long npages = migrate->npages;
        const unsigned long start = migrate->start;
        unsigned long addr, i, restore = 0;

diff --git a/mm/rmap.c b/mm/rmap.c
index 0c7b2a9..ced76b5 100644 (file)
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1488,15 +1488,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
                        goto discard;
                }
 
-               if (!(flags & TTU_IGNORE_ACCESS)) {
-                       if (ptep_clear_flush_young_notify(vma, address,
-                                               pvmw.pte)) {
-                               ret = false;
-                               page_vma_mapped_walk_done(&pvmw);
-                               break;
-                       }
-               }
-
                /* Nuke the page table entry. */
                flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
                if (should_defer_flush(mm, flags)) {

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 9fe201a..f76353f 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1084,7 +1084,6 @@ static void page_check_dirty_writeback(struct page *page,
 static unsigned long shrink_page_list(struct list_head *page_list,
                                      struct pglist_data *pgdat,
                                      struct scan_control *sc,
-                                     enum ttu_flags ttu_flags,
                                      struct reclaim_stat *stat,
                                      bool ignore_references)
 {
@@ -1310,7 +1309,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
                 * processes. Try to unmap it here.
                 */
                if (page_mapped(page)) {
-                       enum ttu_flags flags = ttu_flags | TTU_BATCH_FLUSH;
+                       enum ttu_flags flags = TTU_BATCH_FLUSH;
 
                        if (unlikely(PageTransHuge(page)))
                                flags |= TTU_SPLIT_HUGE_PMD;
@@ -1521,7 +1520,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
        }
 
        ret = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc,
-                       TTU_IGNORE_ACCESS, &dummy_stat, true);
+                               &dummy_stat, true);
        list_splice(&clean_pages, page_list);
        mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -ret);
        return ret;
@@ -1952,8 +1951,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
        if (nr_taken == 0)
                return 0;
 
-       nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, 0,
-                               &stat, false);
+       nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, &stat, false);
 
        spin_lock_irq(&pgdat->lru_lock);
 
@@ -2134,8 +2132,7 @@ unsigned long reclaim_pages(struct list_head *page_list)
 
                nr_reclaimed += shrink_page_list(&node_page_list,
                                                NODE_DATA(nid),
-                                               &sc, 0,
-                                               &dummy_stat, false);
+                                               &sc, &dummy_stat, false);
                while (!list_empty(&node_page_list)) {
                        page = lru_to_page(&node_page_list);
                        list_del(&page->lru);
@@ -2148,8 +2145,7 @@ unsigned long reclaim_pages(struct list_head *page_list)
        if (!list_empty(&node_page_list)) {
                nr_reclaimed += shrink_page_list(&node_page_list,
                                                NODE_DATA(nid),
-                                               &sc, 0,
-                                               &dummy_stat, false);
+                                               &sc, &dummy_stat, false);
                while (!list_empty(&node_page_list)) {
                        page = lru_to_page(&node_page_list);
                        list_del(&page->lru);