1 files changed, 63 insertions, 44 deletions

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index f765475be359..f0d7e6483ba3 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -54,6 +54,9 @@ enum scan_result {
 #define CREATE_TRACE_POINTS
 #include <trace/events/huge_memory.h>
 
+static struct task_struct *khugepaged_thread __read_mostly;
+static DEFINE_MUTEX(khugepaged_mutex);
+
 /* default scan 8*512 pte (or vmas) every 30 second */
 static unsigned int khugepaged_pages_to_scan __read_mostly;
 static unsigned int khugepaged_pages_collapsed;
@@ -401,7 +404,7 @@ static void insert_to_mm_slots_hash(struct mm_struct *mm,
 
 static inline int khugepaged_test_exit(struct mm_struct *mm)
 {
-	return atomic_read(&mm->mm_users) == 0;
+	return atomic_read(&mm->mm_users) == 0 || !mmget_still_valid(mm);
 }
 
 static bool hugepage_vma_check(struct vm_area_struct *vma,
@@ -438,7 +441,7 @@ int __khugepaged_enter(struct mm_struct *mm)
 		return -ENOMEM;
 
 	/* __khugepaged_exit() must not run from under us */
-	VM_BUG_ON_MM(khugepaged_test_exit(mm), mm);
+	VM_BUG_ON_MM(atomic_read(&mm->mm_users) == 0, mm);
 	if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) {
 		free_mm_slot(mm_slot);
 		return 0;
@@ -832,6 +835,18 @@ static struct page *khugepaged_alloc_hugepage(bool *wait)
 
 static bool khugepaged_prealloc_page(struct page **hpage, bool *wait)
 {
+	/*
+	 * If the hpage allocated earlier was briefly exposed in page cache
+	 * before collapse_file() failed, it is possible that racing lookups
+	 * have not yet completed, and would then be unpleasantly surprised by
+	 * finding the hpage reused for the same mapping at a different offset.
+	 * Just release the previous allocation if there is any danger of that.
+	 */
+	if (*hpage && page_count(*hpage) > 1) {
+		put_page(*hpage);
+		*hpage = NULL;
+	}
+
 	if (!*hpage)
 		*hpage = khugepaged_alloc_hugepage(wait);
 
@@ -876,6 +891,9 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
 		return SCAN_ADDRESS_RANGE;
 	if (!hugepage_vma_check(vma, vma->vm_flags))
 		return SCAN_VMA_CHECK;
+	/* Anon VMA expected */
+	if (!vma->anon_vma || vma->vm_ops)
+		return SCAN_VMA_CHECK;
 	return 0;
 }
 
@@ -1016,9 +1034,6 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 * handled by the anon_vma lock + PG_lock.
 	 */
 	down_write(&mm->mmap_sem);
-	result = SCAN_ANY_PROCESS;
-	if (!mmget_still_valid(mm))
-		goto out;
 	result = hugepage_vma_revalidate(mm, address, &vma);
 	if (result)
 		goto out;
@@ -1291,7 +1306,7 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr)
 {
 	unsigned long haddr = addr & HPAGE_PMD_MASK;
 	struct vm_area_struct *vma = find_vma(mm, haddr);
-	struct page *hpage = NULL;
+	struct page *hpage;
 	pte_t *start_pte, *pte;
 	pmd_t *pmd, _pmd;
 	spinlock_t *ptl;
@@ -1311,9 +1326,17 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr)
 	if (!hugepage_vma_check(vma, vma->vm_flags | VM_HUGEPAGE))
 		return;
 
+	hpage = find_lock_page(vma->vm_file->f_mapping,
+			       linear_page_index(vma, haddr));
+	if (!hpage)
+		return;
+
+	if (!PageHead(hpage))
+		goto drop_hpage;
+
 	pmd = mm_find_pmd(mm, haddr);
 	if (!pmd)
-		return;
+		goto drop_hpage;
 
 	start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl);
 
@@ -1332,30 +1355,11 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr)
 
 		page = vm_normal_page(vma, addr, *pte);
 
-		if (!page || !PageCompound(page))
-			goto abort;
-
-		if (!hpage) {
-			hpage = compound_head(page);
-			/*
-			 * The mapping of the THP should not change.
-			 *
-			 * Note that uprobe, debugger, or MAP_PRIVATE may
-			 * change the page table, but the new page will
-			 * not pass PageCompound() check.
-			 */
-			if (WARN_ON(hpage->mapping != vma->vm_file->f_mapping))
-				goto abort;
-		}
-
 		/*
-		 * Confirm the page maps to the correct subpage.
-		 *
-		 * Note that uprobe, debugger, or MAP_PRIVATE may change
-		 * the page table, but the new page will not pass
-		 * PageCompound() check.
+		 * Note that uprobe, debugger, or MAP_PRIVATE may change the
+		 * page table, but the new page will not be a subpage of hpage.
 		 */
-		if (WARN_ON(hpage + i != page))
+		if (hpage + i != page)
 			goto abort;
 		count++;
 	}
@@ -1374,21 +1378,26 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr)
 	pte_unmap_unlock(start_pte, ptl);
 
 	/* step 3: set proper refcount and mm_counters. */
-	if (hpage) {
+	if (count) {
 		page_ref_sub(hpage, count);
 		add_mm_counter(vma->vm_mm, mm_counter_file(hpage), -count);
 	}
 
 	/* step 4: collapse pmd */
 	ptl = pmd_lock(vma->vm_mm, pmd);
-	_pmd = pmdp_collapse_flush(vma, addr, pmd);
+	_pmd = pmdp_collapse_flush(vma, haddr, pmd);
 	spin_unlock(ptl);
 	mm_dec_nr_ptes(mm);
 	pte_free(mm, pmd_pgtable(_pmd));
+
+drop_hpage:
+	unlock_page(hpage);
+	put_page(hpage);
 	return;
 
 abort:
 	pte_unmap_unlock(start_pte, ptl);
+	goto drop_hpage;
 }
 
 static int khugepaged_collapse_pte_mapped_thps(struct mm_slot *mm_slot)
@@ -1417,6 +1426,7 @@ out:
 static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 {
 	struct vm_area_struct *vma;
+	struct mm_struct *mm;
 	unsigned long addr;
 	pmd_t *pmd, _pmd;
 
@@ -1445,7 +1455,8 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 			continue;
 		if (vma->vm_end < addr + HPAGE_PMD_SIZE)
 			continue;
-		pmd = mm_find_pmd(vma->vm_mm, addr);
+		mm = vma->vm_mm;
+		pmd = mm_find_pmd(mm, addr);
 		if (!pmd)
 			continue;
 		/*
@@ -1455,17 +1466,19 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
 		 * mmap_sem while holding page lock. Fault path does it in
 		 * reverse order. Trylock is a way to avoid deadlock.
 		 */
-		if (down_write_trylock(&vma->vm_mm->mmap_sem)) {
-			spinlock_t *ptl = pmd_lock(vma->vm_mm, pmd);
-			/* assume page table is clear */
-			_pmd = pmdp_collapse_flush(vma, addr, pmd);
-			spin_unlock(ptl);
-			up_write(&vma->vm_mm->mmap_sem);
-			mm_dec_nr_ptes(vma->vm_mm);
-			pte_free(vma->vm_mm, pmd_pgtable(_pmd));
+		if (down_write_trylock(&mm->mmap_sem)) {
+			if (!khugepaged_test_exit(mm)) {
+				spinlock_t *ptl = pmd_lock(mm, pmd);
+				/* assume page table is clear */
+				_pmd = pmdp_collapse_flush(vma, addr, pmd);
+				spin_unlock(ptl);
+				mm_dec_nr_ptes(mm);
+				pte_free(mm, pmd_pgtable(_pmd));
+			}
+			up_write(&mm->mmap_sem);
 		} else {
 			/* Try again later */
-			khugepaged_add_pte_mapped_thp(vma->vm_mm, addr);
+			khugepaged_add_pte_mapped_thp(mm, addr);
 		}
 	}
 	i_mmap_unlock_write(mapping);
@@ -1594,7 +1607,7 @@ static void collapse_file(struct mm_struct *mm,
 				xas_unlock_irq(&xas);
 				page_cache_sync_readahead(mapping, &file->f_ra,
 							  file, index,
-							  PAGE_SIZE);
+							  end - index);
 				/* drain pagevecs to help isolate_lru_page() */
 				lru_add_drain();
 				page = find_lock_page(mapping, index);
@@ -2167,8 +2180,6 @@ static void set_recommended_min_free_kbytes(void)
 
 int start_stop_khugepaged(void)
 {
-	static struct task_struct *khugepaged_thread __read_mostly;
-	static DEFINE_MUTEX(khugepaged_mutex);
 	int err = 0;
 
 	mutex_lock(&khugepaged_mutex);
@@ -2195,3 +2206,11 @@ fail:
 	mutex_unlock(&khugepaged_mutex);
 	return err;
 }
+
+void khugepaged_min_free_kbytes_update(void)
+{
+	mutex_lock(&khugepaged_mutex);
+	if (khugepaged_enabled() && khugepaged_thread)
+		set_recommended_min_free_kbytes();
+	mutex_unlock(&khugepaged_mutex);
+}