Skip to contentSkip to conversation

mm: thp: replace DEBUG_VM BUG with VM_WARN when unmap fails for split

PATCH In review Yang Shi 5 participants 6 messages May 26, 2021 – May 27, 2021

Subsystems (6)
lore
Share & tools
lore

Yang Shi

author
#0 lore raw

PATCH v4 1/2 mm: thp: replace DEBUG_VM BUG with VM_WARN when unmap fails for split

When debugging the bug reported by Wang Yugui [1], try_to_unmap() may fail, but the first VM_BUG_ON_PAGE() just checks page_mapcount() however it may miss the failure when head page is unmapped but other subpage is mapped. Then the second DEBUG_VM BUG() that check total mapcount would catch it. This may incur some confusion. And this is not a fatal issue, so consolidate the two DEBUG_VM checks into one VM_WARN_ON_ONCE_PAGE().

[1] https://lore.kernel.org/linux-mm/[email protected]/

---
v4: Updated the subject and commit log per Hugh.
Reordered the patches per Hugh.
v3: Incorporated the comments from Hugh. Keep Zi Yan's reviewed-by tag
since there is no fundamental change against v2.
v2: Removed dead code and updated the comment of try_to_unmap() per Zi
Yan.

 mm/huge_memory.c | 24 +++++++-----------------
 1 file changed, 7 insertions(+), 17 deletions(-)
mm/huge_memory.c +7 -17
index 19195fca1aee..8827f82c5302 100644
@@ -2336,15 +2336,15 @@ static void unmap_page(struct page *page)
 {
 	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK |
 		TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
-	bool unmap_success;
 
 	VM_BUG_ON_PAGE(!PageHead(page), page);
 
 	if (PageAnon(page))
 		ttu_flags |= TTU_SPLIT_FREEZE;
 
-	unmap_success = try_to_unmap(page, ttu_flags);
-	VM_BUG_ON_PAGE(!unmap_success, page);
+	try_to_unmap(page, ttu_flags);
+
+	VM_WARN_ON_ONCE_PAGE(page_mapped(page), page);
 }
 
 static void remap_page(struct page *page, unsigned int nr)
@@ -2655,7 +2655,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	struct deferred_split *ds_queue = get_deferred_split_queue(head);
 	struct anon_vma *anon_vma = NULL;
 	struct address_space *mapping = NULL;
-	int count, mapcount, extra_pins, ret;
+	int extra_pins, ret;
 	pgoff_t end;
 
 	VM_BUG_ON_PAGE(is_huge_zero_page(head), head);
@@ -2714,7 +2714,6 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	}
 
 	unmap_page(head);
-	VM_BUG_ON_PAGE(compound_mapcount(head), head);
 
 	/* block interrupt reentry in xa_lock and spinlock */
 	local_irq_disable();
@@ -2732,9 +2731,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 
 	/* Prevent deferred_split_scan() touching ->_refcount */
 	spin_lock(&ds_queue->split_queue_lock);
-	count = page_count(head);
-	mapcount = total_mapcount(head);
-	if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) {
+	if (page_ref_freeze(head, 1 + extra_pins)) {
 		if (!list_empty(page_deferred_list(head))) {
 			ds_queue->split_queue_len--;
 			list_del(page_deferred_list(head));
@@ -2754,16 +2751,9 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		__split_huge_page(page, list, end);
 		ret = 0;
 	} else {
-		if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
-			pr_alert("total_mapcount: %u, page_count(): %u\n",
-					mapcount, count);
-			if (PageTail(page))
-				dump_page(head, NULL);
-			dump_page(page, "total_mapcount(head) > 0");
-			BUG();
-		}
 		spin_unlock(&ds_queue->split_queue_lock);
-fail:		if (mapping)
+fail:
+		if (mapping)
 			xa_unlock(&mapping->i_pages);
 		local_irq_enable();
 		remap_page(head, thp_nr_pages(head));
Signature · 1 line
2.26.2
author
#1 lore raw

PATCH v4 2/2 mm: rmap: make try_to_unmap() void function

Currently try_to_unmap() return bool value by checking page_mapcount(), however this may return false positive since page_mapcount() doesn't check all subpages of compound page. The total_mapcount() could be used instead, but its cost is higher since it traverses all subpages.

Actually the most callers of try_to_unmap() don't care about the return value at all. So just need check if page is still mapped by page_mapped() when necessary. And page_mapped() does bail out early when it finds mapped subpage.

---
v4: Updated the comment of try_to_unmap() per Minchan.
Minor fix and patch reorder per Hugh. Collected ack tag from Hugh.

 include/linux/rmap.h |  2 +-
 mm/memory-failure.c  | 15 +++++++--------
 mm/rmap.c            |  7 +++----
 mm/vmscan.c          |  3 ++-
 4 files changed, 13 insertions(+), 14 deletions(-)
include/linux/rmap.h +1 -1
index def5c62c93b3..116cb193110a 100644
@@ -194,7 +194,7 @@ static inline void page_dup_rmap(struct page *page, bool compound)
 int page_referenced(struct page *, int is_locked,
 			struct mem_cgroup *memcg, unsigned long *vm_flags);
 
-bool try_to_unmap(struct page *, enum ttu_flags flags);
+void try_to_unmap(struct page *, enum ttu_flags flags);
 
 /* Avoid racy checks */
 #define PVMW_SYNC		(1 << 0)
mm/memory-failure.c +7 -8
index 9dcc9bcea731..07e462588df9 100644
@@ -1063,7 +1063,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	enum ttu_flags ttu = TTU_IGNORE_MLOCK;
 	struct address_space *mapping;
 	LIST_HEAD(tokill);
-	bool unmap_success = true;
+	bool unmap_success;
 	int kill = 1, forcekill;
 	struct page *hpage = *hpagep;
 	bool mlocked = PageMlocked(hpage);
@@ -1126,7 +1126,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
 		collect_procs(hpage, &tokill, flags & MF_ACTION_REQUIRED);
 
 	if (!PageHuge(hpage)) {
-		unmap_success = try_to_unmap(hpage, ttu);
+		try_to_unmap(hpage, ttu);
 	} else {
 		if (!PageAnon(hpage)) {
 			/*
@@ -1138,17 +1138,16 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn,
 			 */
 			mapping = hugetlb_page_mapping_lock_write(hpage);
 			if (mapping) {
-				unmap_success = try_to_unmap(hpage,
-						     ttu|TTU_RMAP_LOCKED);
+				try_to_unmap(hpage, ttu|TTU_RMAP_LOCKED);
 				i_mmap_unlock_write(mapping);
-			} else {
+			} else
 				pr_info("Memory failure: %#lx: could not lock mapping for mapped huge page\n", pfn);
-				unmap_success = false;
-			}
 		} else {
-			unmap_success = try_to_unmap(hpage, ttu);
+			try_to_unmap(hpage, ttu);
 		}
 	}
+
+	unmap_success = !page_mapped(hpage);
 	if (!unmap_success)
 		pr_err("Memory failure: %#lx: failed to unmap page (mapcount=%d)\n",
 		       pfn, page_mapcount(hpage));
mm/rmap.c +3 -4
index a35cbbbded0d..d4e0d89726b8 100644
@@ -1749,9 +1749,10 @@ static int page_not_mapped(struct page *page)
  * Tries to remove all the page table entries which are mapping this
  * page, used in the pageout path.  Caller must hold the page lock.
  *
- * If unmap is successful, return true. Otherwise, false.
+ * It is the callers' responsibility to check if the page is still
+ * mapped when needed.
  */
-bool try_to_unmap(struct page *page, enum ttu_flags flags)
+void try_to_unmap(struct page *page, enum ttu_flags flags)
 {
 	struct rmap_walk_control rwc = {
 		.rmap_one = try_to_unmap_one,
@@ -1776,8 +1777,6 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags)
 		rmap_walk_locked(page, &rwc);
 	else
 		rmap_walk(page, &rwc);
-
-	return !page_mapcount(page) ? true : false;
 }
 
 /**
mm/vmscan.c +2 -1
index f96d62159720..fa5052ace415 100644
@@ -1499,7 +1499,8 @@ static unsigned int shrink_page_list(struct list_head *page_list,
 			if (unlikely(PageTransHuge(page)))
 				flags |= TTU_SPLIT_HUGE_PMD;
 
-			if (!try_to_unmap(page, flags)) {
+			try_to_unmap(page, flags);
+			if (page_mapped(page)) {
 				stat->nr_unmap_fail += nr_pages;
 				if (!was_swapbacked && PageSwapBacked(page))
 					stat->nr_lazyfree_fail += nr_pages;
Signature · 1 line
2.26.2
Acked-by on v4 2/2
#2 lore raw

Re: [v4 PATCH 2/2] mm: rmap: make try_to_unmap() void function

Quoted 5 lines · Yang Shi

Currently try_to_unmap() return bool value by checking page_mapcount(), however this may return false positive since page_mapcount() doesn't check all subpages of compound page. The total_mapcount() could be used instead, but its cost is higher since it traverses all subpages.

Quoted 8 lines

Actually the most callers of try_to_unmap() don't care about the return value at all. So just need check if page is still mapped by page_mapped() when necessary. And page_mapped() does bail out early when it finds mapped subpage.

Thanks for the update, Yang Shi.

Reviewed-by on v4 2/2
#3 lore raw

Re: [v4 PATCH 2/2] mm: rmap: make try_to_unmap() void function

In reply to Yang Shi
Quoted 6 lines · Yang Shi

Currently try_to_unmap() return bool value by checking page_mapcount(), however this may return false positive since page_mapcount() doesn't check all subpages of compound page. The total_mapcount() could be used instead, but its cost is higher since it traverses all subpages.

Quoted 8 lines

Actually the most callers of try_to_unmap() don't care about the return value at all. So just need check if page is still mapped by page_mapped() when necessary. And page_mapped() does bail out early when it finds mapped subpage.

Acked-by on v4 1/2
#4 lore raw
In reply to Yang Shi
Quoted 11 lines · Yang Shi

When debugging the bug reported by Wang Yugui [1], try_to_unmap() may fail, but the first VM_BUG_ON_PAGE() just checks page_mapcount() however it may miss the failure when head page is unmapped but other subpage is mapped. Then the second DEBUG_VM BUG() that check total mapcount would catch it. This may incur some confusion. And this is not a fatal issue, so consolidate the two DEBUG_VM checks into one VM_WARN_ON_ONCE_PAGE().

[1] https://lore.kernel.org/linux-mm/[email protected]/

Thanks: and 2/2 already has my Ack, correct.

Quoted 85 lines

---
v4: Updated the subject and commit log per Hugh.
Reordered the patches per Hugh.
v3: Incorporated the comments from Hugh. Keep Zi Yan's reviewed-by tag
since there is no fundamental change against v2.
v2: Removed dead code and updated the comment of try_to_unmap() per Zi
Yan.

 mm/huge_memory.c | 24 +++++++-----------------
 1 file changed, 7 insertions(+), 17 deletions(-)
mm/huge_memory.c +7 -17
index 19195fca1aee..8827f82c5302 100644
@@ -2336,15 +2336,15 @@ static void unmap_page(struct page *page)
 {
 	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK |
 		TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
-	bool unmap_success;
 
 	VM_BUG_ON_PAGE(!PageHead(page), page);
 
 	if (PageAnon(page))
 		ttu_flags |= TTU_SPLIT_FREEZE;
 
-	unmap_success = try_to_unmap(page, ttu_flags);
-	VM_BUG_ON_PAGE(!unmap_success, page);
+	try_to_unmap(page, ttu_flags);
+
+	VM_WARN_ON_ONCE_PAGE(page_mapped(page), page);
 }
 
 static void remap_page(struct page *page, unsigned int nr)
@@ -2655,7 +2655,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	struct deferred_split *ds_queue = get_deferred_split_queue(head);
 	struct anon_vma *anon_vma = NULL;
 	struct address_space *mapping = NULL;
-	int count, mapcount, extra_pins, ret;
+	int extra_pins, ret;
 	pgoff_t end;
 
 	VM_BUG_ON_PAGE(is_huge_zero_page(head), head);
@@ -2714,7 +2714,6 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	}
 
 	unmap_page(head);
-	VM_BUG_ON_PAGE(compound_mapcount(head), head);
 
 	/* block interrupt reentry in xa_lock and spinlock */
 	local_irq_disable();
@@ -2732,9 +2731,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 
 	/* Prevent deferred_split_scan() touching ->_refcount */
 	spin_lock(&ds_queue->split_queue_lock);
-	count = page_count(head);
-	mapcount = total_mapcount(head);
-	if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) {
+	if (page_ref_freeze(head, 1 + extra_pins)) {
 		if (!list_empty(page_deferred_list(head))) {
 			ds_queue->split_queue_len--;
 			list_del(page_deferred_list(head));
@@ -2754,16 +2751,9 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		__split_huge_page(page, list, end);
 		ret = 0;
 	} else {
-		if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
-			pr_alert("total_mapcount: %u, page_count(): %u\n",
-					mapcount, count);
-			if (PageTail(page))
-				dump_page(head, NULL);
-			dump_page(page, "total_mapcount(head) > 0");
-			BUG();
-		}
 		spin_unlock(&ds_queue->split_queue_lock);
-fail:		if (mapping)
+fail:
+		if (mapping)
 			xa_unlock(&mapping->i_pages);
 		local_irq_enable();
 		remap_page(head, thp_nr_pages(head));
Signature · 1 line
2.26.2
Acked-by on v4 1/2
#5 lore raw
In reply to Yang Shi
Quoted 11 lines · Yang Shi

When debugging the bug reported by Wang Yugui [1], try_to_unmap() may fail, but the first VM_BUG_ON_PAGE() just checks page_mapcount() however it may miss the failure when head page is unmapped but other subpage is mapped. Then the second DEBUG_VM BUG() that check total mapcount would catch it. This may incur some confusion. And this is not a fatal issue, so consolidate the two DEBUG_VM checks into one VM_WARN_ON_ONCE_PAGE().

[1] https://lore.kernel.org/linux-mm/[email protected]/

For both patches:

Signature · 1 line
 Kirill A. Shutemov