Merging upstream version 6.7.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 117 insertions, 1 deletions

diff --git a/mm/ksm.c b/mm/ksm.c
index 981af9c72e..6a831009b4 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -56,6 +56,8 @@
 #define DO_NUMA(x)	do { } while (0)
 #endif
 
+typedef u8 rmap_age_t;
+
 /**
  * DOC: Overview
  *
@@ -193,6 +195,8 @@ struct ksm_stable_node {
  * @node: rb node of this rmap_item in the unstable tree
  * @head: pointer to stable_node heading this list in the stable tree
  * @hlist: link into hlist of rmap_items hanging off that stable_node
+ * @age: number of scan iterations since creation
+ * @remaining_skips: how many scans to skip
  */
 struct ksm_rmap_item {
 	struct ksm_rmap_item *rmap_list;
@@ -205,6 +209,8 @@ struct ksm_rmap_item {
 	struct mm_struct *mm;
 	unsigned long address;		/* + low bits used for flags below */
 	unsigned int oldchecksum;	/* when unstable */
+	rmap_age_t age;
+	rmap_age_t remaining_skips;
 	union {
 		struct rb_node node;	/* when node of unstable tree */
 		struct {		/* when listed from stable tree */
@@ -281,9 +287,16 @@ static unsigned int zero_checksum __read_mostly;
 /* Whether to merge empty (zeroed) pages with actual zero pages */
 static bool ksm_use_zero_pages __read_mostly;
 
+/* Skip pages that couldn't be de-duplicated previously */
+/* Default to true at least temporarily, for testing */
+static bool ksm_smart_scan = true;
+
 /* The number of zero pages which is placed by KSM */
 unsigned long ksm_zero_pages;
 
+/* The number of pages that have been skipped due to "smart scanning" */
+static unsigned long ksm_pages_skipped;
+
 #ifdef CONFIG_NUMA
 /* Zeroed when merging across nodes is not allowed */
 static unsigned int ksm_merge_across_nodes = 1;
@@ -455,7 +468,7 @@ static int break_ksm_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long nex
 			page = pfn_swap_entry_to_page(entry);
 	}
 	/* return 1 if the page is an normal ksm page or KSM-placed zero page */
-	ret = (page && PageKsm(page)) || is_ksm_zero_pte(*pte);
+	ret = (page && PageKsm(page)) || is_ksm_zero_pte(ptent);
 	pte_unmap_unlock(pte, ptl);
 	return ret;
 }
@@ -2305,6 +2318,74 @@ static struct ksm_rmap_item *get_next_rmap_item(struct ksm_mm_slot *mm_slot,
 	return rmap_item;
 }
 
+/*
+ * Calculate skip age for the ksm page age. The age determines how often
+ * de-duplicating has already been tried unsuccessfully. If the age is
+ * smaller, the scanning of this page is skipped for less scans.
+ *
+ * @age: rmap_item age of page
+ */
+static unsigned int skip_age(rmap_age_t age)
+{
+	if (age <= 3)
+		return 1;
+	if (age <= 5)
+		return 2;
+	if (age <= 8)
+		return 4;
+
+	return 8;
+}
+
+/*
+ * Determines if a page should be skipped for the current scan.
+ *
+ * @page: page to check
+ * @rmap_item: associated rmap_item of page
+ */
+static bool should_skip_rmap_item(struct page *page,
+				  struct ksm_rmap_item *rmap_item)
+{
+	rmap_age_t age;
+
+	if (!ksm_smart_scan)
+		return false;
+
+	/*
+	 * Never skip pages that are already KSM; pages cmp_and_merge_page()
+	 * will essentially ignore them, but we still have to process them
+	 * properly.
+	 */
+	if (PageKsm(page))
+		return false;
+
+	age = rmap_item->age;
+	if (age != U8_MAX)
+		rmap_item->age++;
+
+	/*
+	 * Smaller ages are not skipped, they need to get a chance to go
+	 * through the different phases of the KSM merging.
+	 */
+	if (age < 3)
+		return false;
+
+	/*
+	 * Are we still allowed to skip? If not, then don't skip it
+	 * and determine how much more often we are allowed to skip next.
+	 */
+	if (!rmap_item->remaining_skips) {
+		rmap_item->remaining_skips = skip_age(age);
+		return false;
+	}
+
+	/* Skip this page */
+	ksm_pages_skipped++;
+	rmap_item->remaining_skips--;
+	remove_rmap_item_from_tree(rmap_item);
+	return true;
+}
+
 static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page)
 {
 	struct mm_struct *mm;
@@ -2409,6 +2490,10 @@ next_mm:
 				if (rmap_item) {
 					ksm_scan.rmap_list =
 							&rmap_item->rmap_list;
+
+					if (should_skip_rmap_item(*page, rmap_item))
+						goto next_page;
+
 					ksm_scan.address += PAGE_SIZE;
 				} else
 					put_page(*page);
@@ -3383,6 +3468,13 @@ static ssize_t pages_volatile_show(struct kobject *kobj,
 }
 KSM_ATTR_RO(pages_volatile);
 
+static ssize_t pages_skipped_show(struct kobject *kobj,
+				  struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%lu\n", ksm_pages_skipped);
+}
+KSM_ATTR_RO(pages_skipped);
+
 static ssize_t ksm_zero_pages_show(struct kobject *kobj,
 				struct kobj_attribute *attr, char *buf)
 {
@@ -3449,6 +3541,28 @@ static ssize_t full_scans_show(struct kobject *kobj,
 }
 KSM_ATTR_RO(full_scans);
 
+static ssize_t smart_scan_show(struct kobject *kobj,
+			       struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%u\n", ksm_smart_scan);
+}
+
+static ssize_t smart_scan_store(struct kobject *kobj,
+				struct kobj_attribute *attr,
+				const char *buf, size_t count)
+{
+	int err;
+	bool value;
+
+	err = kstrtobool(buf, &value);
+	if (err)
+		return -EINVAL;
+
+	ksm_smart_scan = value;
+	return count;
+}
+KSM_ATTR(smart_scan);
+
 static struct attribute *ksm_attrs[] = {
 	&sleep_millisecs_attr.attr,
 	&pages_to_scan_attr.attr,
@@ -3458,6 +3572,7 @@ static struct attribute *ksm_attrs[] = {
 	&pages_sharing_attr.attr,
 	&pages_unshared_attr.attr,
 	&pages_volatile_attr.attr,
+	&pages_skipped_attr.attr,
 	&ksm_zero_pages_attr.attr,
 	&full_scans_attr.attr,
 #ifdef CONFIG_NUMA
@@ -3469,6 +3584,7 @@ static struct attribute *ksm_attrs[] = {
 	&stable_node_chains_prune_millisecs_attr.attr,
 	&use_zero_pages_attr.attr,
 	&general_profit_attr.attr,
+	&smart_scan_attr.attr,
 	NULL,
 };