1 files changed, 83 insertions, 29 deletions

diff --git a/mm/ksm.c b/mm/ksm.c
index 5b0894b45ee5..fc64874dc6f4 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -25,7 +25,7 @@
 #include <linux/pagemap.h>
 #include <linux/rmap.h>
 #include <linux/spinlock.h>
-#include <linux/jhash.h>
+#include <linux/xxhash.h>
 #include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/wait.h>
@@ -296,6 +296,7 @@ static unsigned long ksm_run = KSM_RUN_STOP;
 static void wait_while_offlining(void);
 
 static DECLARE_WAIT_QUEUE_HEAD(ksm_thread_wait);
+static DECLARE_WAIT_QUEUE_HEAD(ksm_iter_wait);
 static DEFINE_MUTEX(ksm_thread_mutex);
 static DEFINE_SPINLOCK(ksm_mmlist_lock);
 
@@ -597,7 +598,7 @@ static struct stable_node *alloc_stable_node_chain(struct stable_node *dup,
 		chain->chain_prune_time = jiffies;
 		chain->rmap_hlist_len = STABLE_NODE_CHAIN;
 #if defined (CONFIG_DEBUG_VM) && defined(CONFIG_NUMA)
-		chain->nid = -1; /* debug */
+		chain->nid = NUMA_NO_NODE; /* debug */
 #endif
 		ksm_stable_node_chains++;
 
@@ -666,6 +667,12 @@ static void remove_node_from_stable_tree(struct stable_node *stable_node)
 	free_stable_node(stable_node);
 }
 
+enum get_ksm_page_flags {
+	GET_KSM_PAGE_NOLOCK,
+	GET_KSM_PAGE_LOCK,
+	GET_KSM_PAGE_TRYLOCK
+};
+
 /*
  * get_ksm_page: checks if the page indicated by the stable node
  * is still its ksm page, despite having held no reference to it.
@@ -685,7 +692,8 @@ static void remove_node_from_stable_tree(struct stable_node *stable_node)
  * a page to put something that might look like our key in page->mapping.
  * is on its way to being freed; but it is an anomaly to bear in mind.
  */
-static struct page *get_ksm_page(struct stable_node *stable_node, bool lock_it)
+static struct page *get_ksm_page(struct stable_node *stable_node,
+				 enum get_ksm_page_flags flags)
 {
 	struct page *page;
 	void *expected_mapping;
@@ -705,8 +713,9 @@ again:
 	 * case this node is no longer referenced, and should be freed;
 	 * however, it might mean that the page is under page_ref_freeze().
 	 * The __remove_mapping() case is easy, again the node is now stale;
-	 * but if page is swapcache in migrate_page_move_mapping(), it might
-	 * still be our page, in which case it's essential to keep the node.
+	 * the same is in reuse_ksm_page() case; but if page is swapcache
+	 * in migrate_page_move_mapping(), it might still be our page,
+	 * in which case it's essential to keep the node.
 	 */
 	while (!get_page_unless_zero(page)) {
 		/*
@@ -727,8 +736,15 @@ again:
 		goto stale;
 	}
 
-	if (lock_it) {
+	if (flags == GET_KSM_PAGE_TRYLOCK) {
+		if (!trylock_page(page)) {
+			put_page(page);
+			return ERR_PTR(-EBUSY);
+		}
+	} else if (flags == GET_KSM_PAGE_LOCK)
 		lock_page(page);
+
+	if (flags != GET_KSM_PAGE_NOLOCK) {
 		if (READ_ONCE(page->mapping) != expected_mapping) {
 			unlock_page(page);
 			put_page(page);
@@ -762,7 +778,7 @@ static void remove_rmap_item_from_tree(struct rmap_item *rmap_item)
 		struct page *page;
 
 		stable_node = rmap_item->head;
-		page = get_ksm_page(stable_node, true);
+		page = get_ksm_page(stable_node, GET_KSM_PAGE_LOCK);
 		if (!page)
 			goto out;
 
@@ -862,7 +878,7 @@ static int remove_stable_node(struct stable_node *stable_node)
 	struct page *page;
 	int err;
 
-	page = get_ksm_page(stable_node, true);
+	page = get_ksm_page(stable_node, GET_KSM_PAGE_LOCK);
 	if (!page) {
 		/*
 		 * get_ksm_page did remove_node_from_stable_tree itself.
@@ -1009,7 +1025,7 @@ static u32 calc_checksum(struct page *page)
 {
 	u32 checksum;
 	void *addr = kmap_atomic(page);
-	checksum = jhash2(addr, PAGE_SIZE / 4, 17);
+	checksum = xxhash(addr, PAGE_SIZE, 0);
 	kunmap_atomic(addr);
 	return checksum;
 }
@@ -1042,8 +1058,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 	};
 	int swapped;
 	int err = -EFAULT;
-	unsigned long mmun_start;	/* For mmu_notifiers */
-	unsigned long mmun_end;		/* For mmu_notifiers */
+	struct mmu_notifier_range range;
 
 	pvmw.address = page_address_in_vma(page, vma);
 	if (pvmw.address == -EFAULT)
@@ -1051,9 +1066,9 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 
 	BUG_ON(PageTransCompound(page));
 
-	mmun_start = pvmw.address;
-	mmun_end   = pvmw.address + PAGE_SIZE;
-	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
+	mmu_notifier_range_init(&range, mm, pvmw.address,
+				pvmw.address + PAGE_SIZE);
+	mmu_notifier_invalidate_range_start(&range);
 
 	if (!page_vma_mapped_walk(&pvmw))
 		goto out_mn;
@@ -1105,7 +1120,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 out_unlock:
 	page_vma_mapped_walk_done(&pvmw);
 out_mn:
-	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
+	mmu_notifier_invalidate_range_end(&range);
 out:
 	return err;
 }
@@ -1129,8 +1144,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 	spinlock_t *ptl;
 	unsigned long addr;
 	int err = -EFAULT;
-	unsigned long mmun_start;	/* For mmu_notifiers */
-	unsigned long mmun_end;		/* For mmu_notifiers */
+	struct mmu_notifier_range range;
 
 	addr = page_address_in_vma(page, vma);
 	if (addr == -EFAULT)
@@ -1140,9 +1154,8 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 	if (!pmd)
 		goto out;
 
-	mmun_start = addr;
-	mmun_end   = addr + PAGE_SIZE;
-	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
+	mmu_notifier_range_init(&range, mm, addr, addr + PAGE_SIZE);
+	mmu_notifier_invalidate_range_start(&range);
 
 	ptep = pte_offset_map_lock(mm, pmd, addr, &ptl);
 	if (!pte_same(*ptep, orig_pte)) {
@@ -1188,7 +1201,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 	pte_unmap_unlock(ptep, ptl);
 	err = 0;
 out_mn:
-	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
+	mmu_notifier_invalidate_range_end(&range);
 out:
 	return err;
 }
@@ -1387,7 +1400,7 @@ static struct page *stable_node_dup(struct stable_node **_stable_node_dup,
 		 * stable_node parameter itself will be freed from
 		 * under us if it returns NULL.
 		 */
-		_tree_page = get_ksm_page(dup, false);
+		_tree_page = get_ksm_page(dup, GET_KSM_PAGE_NOLOCK);
 		if (!_tree_page)
 			continue;
 		nr += 1;
@@ -1510,7 +1523,7 @@ static struct page *__stable_node_chain(struct stable_node **_stable_node_dup,
 	if (!is_stable_node_chain(stable_node)) {
 		if (is_page_sharing_candidate(stable_node)) {
 			*_stable_node_dup = stable_node;
-			return get_ksm_page(stable_node, false);
+			return get_ksm_page(stable_node, GET_KSM_PAGE_NOLOCK);
 		}
 		/*
 		 * _stable_node_dup set to NULL means the stable_node
@@ -1615,7 +1628,8 @@ again:
 			 * wrprotected at all times. Any will work
 			 * fine to continue the walk.
 			 */
-			tree_page = get_ksm_page(stable_node_any, false);
+			tree_page = get_ksm_page(stable_node_any,
+						 GET_KSM_PAGE_NOLOCK);
 		}
 		VM_BUG_ON(!stable_node_dup ^ !!stable_node_any);
 		if (!tree_page) {
@@ -1675,7 +1689,12 @@ again:
 			 * It would be more elegant to return stable_node
 			 * than kpage, but that involves more changes.
 			 */
-			tree_page = get_ksm_page(stable_node_dup, true);
+			tree_page = get_ksm_page(stable_node_dup,
+						 GET_KSM_PAGE_TRYLOCK);
+
+			if (PTR_ERR(tree_page) == -EBUSY)
+				return ERR_PTR(-EBUSY);
+
 			if (unlikely(!tree_page))
 				/*
 				 * The tree may have been rebalanced,
@@ -1844,7 +1863,8 @@ again:
 			 * wrprotected at all times. Any will work
 			 * fine to continue the walk.
 			 */
-			tree_page = get_ksm_page(stable_node_any, false);
+			tree_page = get_ksm_page(stable_node_any,
+						 GET_KSM_PAGE_NOLOCK);
 		}
 		VM_BUG_ON(!stable_node_dup ^ !!stable_node_any);
 		if (!tree_page) {
@@ -2070,6 +2090,9 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item)
 	remove_rmap_item_from_tree(rmap_item);
 
 	if (kpage) {
+		if (PTR_ERR(kpage) == -EBUSY)
+			return;
+
 		err = try_to_merge_with_ksm_page(rmap_item, page, kpage);
 		if (!err) {
 			/*
@@ -2244,7 +2267,8 @@ static struct rmap_item *scan_get_next_rmap_item(struct page **page)
 
 			list_for_each_entry_safe(stable_node, next,
 						 &migrate_nodes, list) {
-				page = get_ksm_page(stable_node, false);
+				page = get_ksm_page(stable_node,
+						    GET_KSM_PAGE_NOLOCK);
 				if (page)
 					put_page(page);
 				cond_resched();
@@ -2391,6 +2415,8 @@ static int ksmd_should_run(void)
 
 static int ksm_scan_thread(void *nothing)
 {
+	unsigned int sleep_ms;
+
 	set_freezable();
 	set_user_nice(current, 5);
 
@@ -2404,8 +2430,10 @@ static int ksm_scan_thread(void *nothing)
 		try_to_freeze();
 
 		if (ksmd_should_run()) {
-			schedule_timeout_interruptible(
-				msecs_to_jiffies(ksm_thread_sleep_millisecs));
+			sleep_ms = READ_ONCE(ksm_thread_sleep_millisecs);
+			wait_event_interruptible_timeout(ksm_iter_wait,
+				sleep_ms != READ_ONCE(ksm_thread_sleep_millisecs),
+				msecs_to_jiffies(sleep_ms));
 		} else {
 			wait_event_freezable(ksm_thread_wait,
 				ksmd_should_run() || kthread_should_stop());
@@ -2640,6 +2668,31 @@ again:
 		goto again;
 }
 
+bool reuse_ksm_page(struct page *page,
+		    struct vm_area_struct *vma,
+		    unsigned long address)
+{
+#ifdef CONFIG_DEBUG_VM
+	if (WARN_ON(is_zero_pfn(page_to_pfn(page))) ||
+			WARN_ON(!page_mapped(page)) ||
+			WARN_ON(!PageLocked(page))) {
+		dump_page(page, "reuse_ksm_page");
+		return false;
+	}
+#endif
+
+	if (PageSwapCache(page) || !page_stable_node(page))
+		return false;
+	/* Prohibit parallel get_ksm_page() */
+	if (!page_ref_freeze(page, 1))
+		return false;
+
+	page_move_anon_rmap(page, vma);
+	page->index = linear_page_index(vma, address);
+	page_ref_unfreeze(page, 1);
+
+	return true;
+}
 #ifdef CONFIG_MIGRATION
 void ksm_migrate_page(struct page *newpage, struct page *oldpage)
 {
@@ -2824,6 +2877,7 @@ static ssize_t sleep_millisecs_store(struct kobject *kobj,
 		return -EINVAL;
 
 	ksm_thread_sleep_millisecs = msecs;
+	wake_up_interruptible(&ksm_iter_wait);
 
 	return count;
 }