X-Git-Url: https://git.openpandora.org/cgi-bin/gitweb.cgi?p=pandora-kernel.git;a=blobdiff_plain;f=mm%2Fhuge_memory.c;h=d6e6cafdb2c9a74904853cd63f3220263526e7bc;hp=4298abaae153033caafe1f8ac641fdef1dee097e;hb=2ea6895123eb8604c1c0c153e2fcd1305fb96aca;hpb=e6f1227e8bc8a2ea2d76d09e19c89fa66c2f3a4c

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 4298abaae153..d6e6cafdb2c9 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -642,6 +642,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 		set_pmd_at(mm, haddr, pmd, entry);
 		prepare_pmd_huge_pte(pgtable, mm);
 		add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
+		mm->nr_ptes++;
 		spin_unlock(&mm->page_table_lock);
 	}
 
@@ -681,7 +682,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (haddr >= vma->vm_start && haddr + HPAGE_PMD_SIZE <= vma->vm_end) {
 		if (unlikely(anon_vma_prepare(vma)))
 			return VM_FAULT_OOM;
-		if (unlikely(khugepaged_enter(vma)))
+		if (unlikely(khugepaged_enter(vma, vma->vm_flags)))
 			return VM_FAULT_OOM;
 		page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
 					  vma, haddr, numa_node_id(), 0);
@@ -760,6 +761,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	pmd = pmd_mkold(pmd_wrprotect(pmd));
 	set_pmd_at(dst_mm, addr, dst_pmd, pmd);
 	prepare_pmd_huge_pte(pgtable, dst_mm);
+	dst_mm->nr_ptes++;
 
 	ret = 0;
 out_unlock:
@@ -858,7 +860,6 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 	}
 	kfree(pages);
 
-	mm->nr_ptes++;
 	smp_wmb(); /* make pte visible before pmd */
 	pmd_populate(mm, pmd, pgtable);
 	page_remove_rmap(page);
@@ -920,6 +921,8 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		count_vm_event(THP_FAULT_FALLBACK);
 		ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
 						   pmd, orig_pmd, page, haddr);
+		if (ret & VM_FAULT_OOM)
+			split_huge_page(page);
 		put_page(page);
 		goto out;
 	}
@@ -927,6 +930,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
 		put_page(new_page);
+		split_huge_page(page);
 		put_page(page);
 		ret |= VM_FAULT_OOM;
 		goto out;
@@ -960,6 +964,18 @@ out:
 	return ret;
 }
 
+/*
+ * FOLL_FORCE can write to even unwritable pmd's, but only
+ * after we've gone through a COW cycle and they are dirty.
+ */
+static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page,
+					unsigned int flags)
+{
+	return pmd_write(pmd) ||
+		((flags & FOLL_FORCE) && (flags & FOLL_COW) &&
+		 page && PageAnon(page));
+}
+
 struct page *follow_trans_huge_pmd(struct mm_struct *mm,
 				   unsigned long addr,
 				   pmd_t *pmd,
@@ -969,11 +985,12 @@ struct page *follow_trans_huge_pmd(struct mm_struct *mm,
 
 	assert_spin_locked(&mm->page_table_lock);
 
-	if (flags & FOLL_WRITE && !pmd_write(*pmd))
-		goto out;
-
 	page = pmd_page(*pmd);
 	VM_BUG_ON(!PageHead(page));
+
+	if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, page, flags))
+		return NULL;
+
 	if (flags & FOLL_TOUCH) {
 		pmd_t _pmd;
 		/*
@@ -1017,6 +1034,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			VM_BUG_ON(page_mapcount(page) < 0);
 			add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
 			VM_BUG_ON(!PageHead(page));
+			tlb->mm->nr_ptes--;
 			spin_unlock(&tlb->mm->page_table_lock);
 			tlb_remove_page(tlb, page);
 			pte_free(tlb->mm, pgtable);
@@ -1356,7 +1374,6 @@ static int __split_huge_page_map(struct page *page,
 			pte_unmap(pte);
 		}
 
-		mm->nr_ptes++;
 		smp_wmb(); /* make pte visible before pmd */
 		/*
 		 * Up to this point the pmd is present and huge and
@@ -1489,7 +1506,7 @@ int hugepage_madvise(struct vm_area_struct *vma,
 		 * register it here without waiting a page fault that
 		 * may not happen any time soon.
 		 */
-		if (unlikely(khugepaged_enter_vma_merge(vma)))
+		if (unlikely(khugepaged_enter_vma_merge(vma, *vm_flags)))
 			return -ENOMEM;
 		break;
 	case MADV_NOHUGEPAGE:
@@ -1621,7 +1638,8 @@ int __khugepaged_enter(struct mm_struct *mm)
 	return 0;
 }
 
-int khugepaged_enter_vma_merge(struct vm_area_struct *vma)
+int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
+			       unsigned long vm_flags)
 {
 	unsigned long hstart, hend;
 	if (!vma->anon_vma)
@@ -1630,18 +1648,18 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma)
 		 * page fault if needed.
 		 */
 		return 0;
-	if (vma->vm_ops)
+	if (vma->vm_ops || (vm_flags & VM_NO_THP))
 		/* khugepaged not yet working on file or special mappings */
 		return 0;
 	/*
 	 * If is_pfn_mapping() is true is_learn_pfn_mapping() must be
 	 * true too, verify it here.
 	 */
-	VM_BUG_ON(is_linear_pfn_mapping(vma) || vma->vm_flags & VM_NO_THP);
+	VM_BUG_ON(is_linear_pfn_mapping(vma));
 	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
 	hend = vma->vm_end & HPAGE_PMD_MASK;
 	if (hstart < hend)
-		return khugepaged_enter(vma);
+		return khugepaged_enter(vma, vm_flags);
 	return 0;
 }
 
@@ -1812,6 +1830,24 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
 	}
 }
 
+static bool hugepage_vma_check(struct vm_area_struct *vma)
+{
+	if ((!(vma->vm_flags & VM_HUGEPAGE) && !khugepaged_always()) ||
+	    (vma->vm_flags & VM_NOHUGEPAGE))
+		return false;
+
+	if (!vma->anon_vma || vma->vm_ops)
+		return false;
+	if (is_vma_temporary_stack(vma))
+		return false;
+	/*
+	 * If is_pfn_mapping() is true is_learn_pfn_mapping() must be
+	 * true too, verify it here.
+	 */
+	VM_BUG_ON(is_linear_pfn_mapping(vma));
+	return !(vma->vm_flags & VM_NO_THP);
+}
+
 static void collapse_huge_page(struct mm_struct *mm,
 			       unsigned long address,
 			       struct page **hpage,
@@ -1878,25 +1914,14 @@ static void collapse_huge_page(struct mm_struct *mm,
 		goto out;
 
 	vma = find_vma(mm, address);
+	if (!vma)
+		goto out;
 	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
 	hend = vma->vm_end & HPAGE_PMD_MASK;
 	if (address < hstart || address + HPAGE_PMD_SIZE > hend)
 		goto out;
-
-	if ((!(vma->vm_flags & VM_HUGEPAGE) && !khugepaged_always()) ||
-	    (vma->vm_flags & VM_NOHUGEPAGE))
-		goto out;
-
-	if (!vma->anon_vma || vma->vm_ops)
-		goto out;
-	if (is_vma_temporary_stack(vma))
+	if (!hugepage_vma_check(vma))
 		goto out;
-	/*
-	 * If is_pfn_mapping() is true is_learn_pfn_mapping() must be
-	 * true too, verify it here.
-	 */
-	VM_BUG_ON(is_linear_pfn_mapping(vma) || vma->vm_flags & VM_NO_THP);
-
 	pgd = pgd_offset(mm, address);
 	if (!pgd_present(*pgd))
 		goto out;
@@ -1933,7 +1958,12 @@ static void collapse_huge_page(struct mm_struct *mm,
 		pte_unmap(pte);
 		spin_lock(&mm->page_table_lock);
 		BUG_ON(!pmd_none(*pmd));
-		set_pmd_at(mm, address, pmd, _pmd);
+		/*
+		 * We can only use set_pmd_at when establishing
+		 * hugepmds and never for establishing regular pmds that
+		 * points to regular pagetables. Use pmd_populate for that
+		 */
+		pmd_populate(mm, pmd, pmd_pgtable(_pmd));
 		spin_unlock(&mm->page_table_lock);
 		anon_vma_unlock(vma->anon_vma);
 		goto out;
@@ -1969,7 +1999,6 @@ static void collapse_huge_page(struct mm_struct *mm,
 	set_pmd_at(mm, address, pmd, _pmd);
 	update_mmu_cache(vma, address, _pmd);
 	prepare_pmd_huge_pte(pgtable, mm);
-	mm->nr_ptes--;
 	spin_unlock(&mm->page_table_lock);
 
 #ifndef CONFIG_NUMA
@@ -2064,7 +2093,7 @@ static void collect_mm_slot(struct mm_slot *mm_slot)
 {
 	struct mm_struct *mm = mm_slot->mm;
 
-	VM_BUG_ON(!spin_is_locked(&khugepaged_mm_lock));
+	VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&khugepaged_mm_lock));
 
 	if (khugepaged_test_exit(mm)) {
 		/* free mm_slot */
@@ -2094,7 +2123,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
 	int progress = 0;
 
 	VM_BUG_ON(!pages);
-	VM_BUG_ON(!spin_is_locked(&khugepaged_mm_lock));
+	VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&khugepaged_mm_lock));
 
 	if (khugepaged_scan.mm_slot)
 		mm_slot = khugepaged_scan.mm_slot;
@@ -2122,25 +2151,11 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
 			progress++;
 			break;
 		}
-
-		if ((!(vma->vm_flags & VM_HUGEPAGE) &&
-		     !khugepaged_always()) ||
-		    (vma->vm_flags & VM_NOHUGEPAGE)) {
-		skip:
+		if (!hugepage_vma_check(vma)) {
+skip:
 			progress++;
 			continue;
 		}
-		if (!vma->anon_vma || vma->vm_ops)
-			goto skip;
-		if (is_vma_temporary_stack(vma))
-			goto skip;
-		/*
-		 * If is_pfn_mapping() is true is_learn_pfn_mapping()
-		 * must be true too, verify it here.
-		 */
-		VM_BUG_ON(is_linear_pfn_mapping(vma) ||
-			  vma->vm_flags & VM_NO_THP);
-
 		hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
 		hend = vma->vm_end & HPAGE_PMD_MASK;
 		if (hstart >= hend)
@@ -2259,12 +2274,8 @@ static void khugepaged_do_scan(struct page **hpage)
 
 static void khugepaged_alloc_sleep(void)
 {
-	DEFINE_WAIT(wait);
-	add_wait_queue(&khugepaged_wait, &wait);
-	schedule_timeout_interruptible(
-		msecs_to_jiffies(
-			khugepaged_alloc_sleep_millisecs));
-	remove_wait_queue(&khugepaged_wait, &wait);
+	wait_event_freezable_timeout(khugepaged_wait, false,
+			msecs_to_jiffies(khugepaged_alloc_sleep_millisecs));
 }
 
 #ifndef CONFIG_NUMA
@@ -2313,14 +2324,10 @@ static void khugepaged_loop(void)
 		if (unlikely(kthread_should_stop()))
 			break;
 		if (khugepaged_has_work()) {
-			DEFINE_WAIT(wait);
 			if (!khugepaged_scan_sleep_millisecs)
 				continue;
-			add_wait_queue(&khugepaged_wait, &wait);
-			schedule_timeout_interruptible(
-				msecs_to_jiffies(
-					khugepaged_scan_sleep_millisecs));
-			remove_wait_queue(&khugepaged_wait, &wait);
+			wait_event_freezable_timeout(khugepaged_wait, false,
+			    msecs_to_jiffies(khugepaged_scan_sleep_millisecs));
 		} else if (khugepaged_enabled())
 			wait_event_freezable(khugepaged_wait,
 					     khugepaged_wait_event());