X-Git-Url: http://git.cascardo.info/?a=blobdiff_plain;f=mm%2Fhuge_memory.c;h=9ed58530f6957bef1e2e0fa166ed87085dcae523;hb=3fb54d7590a4a4d4cf99279c5c228bea788b9628;hp=b49ee126d4d1feb7a89a9c776edc89141c3351da;hpb=0422e5e0be4cce09ed6a095410efa7ee0f978607;p=cascardo%2Flinux.git

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b49ee126d4d1..9ed58530f695 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -89,6 +89,7 @@ static unsigned int khugepaged_full_scans;
 static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000;
 /* during fragmentation poll the hugepage allocator once every minute */
 static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000;
+static unsigned long khugepaged_sleep_expire;
 static struct task_struct *khugepaged_thread __read_mostly;
 static DEFINE_MUTEX(khugepaged_mutex);
 static DEFINE_SPINLOCK(khugepaged_mm_lock);
@@ -467,6 +468,7 @@ static ssize_t scan_sleep_millisecs_store(struct kobject *kobj,
 		return -EINVAL;
 
 	khugepaged_scan_sleep_millisecs = msecs;
+	khugepaged_sleep_expire = 0;
 	wake_up_interruptible(&khugepaged_wait);
 
 	return count;
@@ -494,6 +496,7 @@ static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj,
 		return -EINVAL;
 
 	khugepaged_alloc_sleep_millisecs = msecs;
+	khugepaged_sleep_expire = 0;
 	wake_up_interruptible(&khugepaged_wait);
 
 	return count;
@@ -764,10 +767,7 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
 
 static inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot)
 {
-	pmd_t entry;
-	entry = mk_pmd(page, prot);
-	entry = pmd_mkhuge(entry);
-	return entry;
+	return pmd_mkhuge(mk_pmd(page, prot));
 }
 
 static inline struct list_head *page_deferred_list(struct page *page)
@@ -1013,6 +1013,7 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 	insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write);
 	return VM_FAULT_NOPAGE;
 }
+EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
 
 static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
 		pmd_t *pmd)
@@ -1698,20 +1699,17 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	return 1;
 }
 
-bool move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
-		  unsigned long old_addr,
+bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 		  unsigned long new_addr, unsigned long old_end,
 		  pmd_t *old_pmd, pmd_t *new_pmd)
 {
 	spinlock_t *old_ptl, *new_ptl;
 	pmd_t pmd;
-
 	struct mm_struct *mm = vma->vm_mm;
 
 	if ((old_addr & ~HPAGE_PMD_MASK) ||
 	    (new_addr & ~HPAGE_PMD_MASK) ||
-	    old_end - old_addr < HPAGE_PMD_SIZE ||
-	    (new_vma->vm_flags & VM_NOHUGEPAGE))
+	    old_end - old_addr < HPAGE_PMD_SIZE)
 		return false;
 
 	/*
@@ -2797,15 +2795,25 @@ static void khugepaged_do_scan(void)
 		put_page(hpage);
 }
 
+static bool khugepaged_should_wakeup(void)
+{
+	return kthread_should_stop() ||
+	       time_after_eq(jiffies, khugepaged_sleep_expire);
+}
+
 static void khugepaged_wait_work(void)
 {
 	if (khugepaged_has_work()) {
-		if (!khugepaged_scan_sleep_millisecs)
+		const unsigned long scan_sleep_jiffies =
+			msecs_to_jiffies(khugepaged_scan_sleep_millisecs);
+
+		if (!scan_sleep_jiffies)
 			return;
 
+		khugepaged_sleep_expire = jiffies + scan_sleep_jiffies;
 		wait_event_freezable_timeout(khugepaged_wait,
-					     kthread_should_stop(),
-			msecs_to_jiffies(khugepaged_scan_sleep_millisecs));
+					     khugepaged_should_wakeup(),
+					     scan_sleep_jiffies);
 		return;
 	}
 
@@ -3029,8 +3037,10 @@ void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
 		return;
 
 	/*
-	 * Caller holds the mmap_sem write mode, so a huge pmd cannot
-	 * materialize from under us.
+	 * Caller holds the mmap_sem write mode or the anon_vma lock,
+	 * so a huge pmd cannot materialize from under us (khugepaged
+	 * holds both the mmap_sem write mode and the anon_vma lock
+	 * write mode).
 	 */
 	__split_huge_pmd(vma, pmd, address, freeze);
 }
@@ -3113,7 +3123,7 @@ static void __split_huge_page_tail(struct page *head, int tail,
 	VM_BUG_ON_PAGE(page_ref_count(page_tail) != 0, page_tail);
 
 	/*
-	 * tail_page->_count is zero and not changing from under us. But
+	 * tail_page->_refcount is zero and not changing from under us. But
 	 * get_page_unless_zero() may be running from under us on the
 	 * tail_page. If we used atomic_set() below instead of atomic_inc(), we
 	 * would then run atomic_set() concurrently with
@@ -3340,7 +3350,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	if (mlocked)
 		lru_add_drain();
 
-	/* Prevent deferred_split_scan() touching ->_count */
+	/* Prevent deferred_split_scan() touching ->_refcount */
 	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
 	count = page_count(head);
 	mapcount = total_mapcount(head);