mm: make optimistic check for swapin readahead

Introduce a new sysfs integer knob
/sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_swap which makes
optimistic check for swapin readahead to increase thp collapse rate. 
Before getting swapped out pages to memory, checks them and allows up to a
certain number.  It also prints out using tracepoints amount of unmapped
ptes.

Signed-off-by: Ebru Akagunduz <ebru.akagunduz@gmail.com>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Xie XiuQi <xiexiuqi@huawei.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/trace/events/huge_memory.h

@@ -29,7 +29,8 @@
 	EM( SCAN_SWAP_CACHE_PAGE,	"page_swap_cache")		\
 	EM( SCAN_DEL_PAGE_LRU,		"could_not_delete_page_from_lru")\
 	EM( SCAN_ALLOC_HUGE_PAGE_FAIL,	"alloc_huge_page_failed")	\
-	EMe( SCAN_CGROUP_CHARGE_FAIL,	"ccgroup_charge_failed")
+	EM( SCAN_CGROUP_CHARGE_FAIL,	"ccgroup_charge_failed")	\
+	EMe( SCAN_EXCEED_SWAP_PTE,	"exceed_swap_pte")
 
 #undef EM
 #undef EMe
@@ -46,9 +47,9 @@ SCAN_STATUS
 TRACE_EVENT(mm_khugepaged_scan_pmd,
 
 	TP_PROTO(struct mm_struct *mm, unsigned long pfn, bool writable,
-		 bool referenced, int none_or_zero, int status),
+		 bool referenced, int none_or_zero, int status, int unmapped),
 
-	TP_ARGS(mm, pfn, writable, referenced, none_or_zero, status),
+	TP_ARGS(mm, pfn, writable, referenced, none_or_zero, status, unmapped),
 
 	TP_STRUCT__entry(
 		__field(struct mm_struct *, mm)
@@ -57,6 +58,7 @@ TRACE_EVENT(mm_khugepaged_scan_pmd,
 		__field(bool, referenced)
 		__field(int, none_or_zero)
 		__field(int, status)
+		__field(int, unmapped)
 	),
 
 	TP_fast_assign(
@@ -66,15 +68,17 @@ TRACE_EVENT(mm_khugepaged_scan_pmd,
 		__entry->referenced = referenced;
 		__entry->none_or_zero = none_or_zero;
 		__entry->status = status;
+		__entry->unmapped = unmapped;
 	),
 
-	TP_printk("mm=%p, scan_pfn=0x%lx, writable=%d, referenced=%d, none_or_zero=%d, status=%s",
+	TP_printk("mm=%p, scan_pfn=0x%lx, writable=%d, referenced=%d, none_or_zero=%d, status=%s, unmapped=%d",
 		__entry->mm,
 		__entry->pfn,
 		__entry->writable,
 		__entry->referenced,
 		__entry->none_or_zero,
-		__print_symbolic(__entry->status, SCAN_STATUS))
+		__print_symbolic(__entry->status, SCAN_STATUS),
+		__entry->unmapped)
 );
 
 TRACE_EVENT(mm_collapse_huge_page,

mm/huge_memory.c

@@ -26,6 +26,7 @@
 #include <linux/hashtable.h>
 #include <linux/userfaultfd_k.h>
 #include <linux/page_idle.h>
+#include <linux/swapops.h>
 
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
@@ -52,7 +53,8 @@ enum scan_result {
 	SCAN_SWAP_CACHE_PAGE,
 	SCAN_DEL_PAGE_LRU,
 	SCAN_ALLOC_HUGE_PAGE_FAIL,
-	SCAN_CGROUP_CHARGE_FAIL
+	SCAN_CGROUP_CHARGE_FAIL,
+	SCAN_EXCEED_SWAP_PTE
 };
 
 #define CREATE_TRACE_POINTS
@@ -94,6 +96,7 @@ static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait);
  * fault.
  */
 static unsigned int khugepaged_max_ptes_none __read_mostly = HPAGE_PMD_NR-1;
+static unsigned int khugepaged_max_ptes_swap __read_mostly = HPAGE_PMD_NR/8;
 
 static int khugepaged(void *none);
 static int khugepaged_slab_init(void);
@@ -580,6 +583,33 @@ static struct kobj_attribute khugepaged_max_ptes_none_attr =
 	__ATTR(max_ptes_none, 0644, khugepaged_max_ptes_none_show,
 	       khugepaged_max_ptes_none_store);
 
+static ssize_t khugepaged_max_ptes_swap_show(struct kobject *kobj,
+					     struct kobj_attribute *attr,
+					     char *buf)
+{
+	return sprintf(buf, "%u\n", khugepaged_max_ptes_swap);
+}
+
+static ssize_t khugepaged_max_ptes_swap_store(struct kobject *kobj,
+					      struct kobj_attribute *attr,
+					      const char *buf, size_t count)
+{
+	int err;
+	unsigned long max_ptes_swap;
+
+	err  = kstrtoul(buf, 10, &max_ptes_swap);
+	if (err || max_ptes_swap > HPAGE_PMD_NR-1)
+		return -EINVAL;
+
+	khugepaged_max_ptes_swap = max_ptes_swap;
+
+	return count;
+}
+
+static struct kobj_attribute khugepaged_max_ptes_swap_attr =
+	__ATTR(max_ptes_swap, 0644, khugepaged_max_ptes_swap_show,
+	       khugepaged_max_ptes_swap_store);
+
 static struct attribute *khugepaged_attr[] = {
 	&khugepaged_defrag_attr.attr,
 	&khugepaged_max_ptes_none_attr.attr,
@@ -588,6 +618,7 @@ static struct attribute *khugepaged_attr[] = {
 	&full_scans_attr.attr,
 	&scan_sleep_millisecs_attr.attr,
 	&alloc_sleep_millisecs_attr.attr,
+	&khugepaged_max_ptes_swap_attr.attr,
 	NULL,
 };
 
@@ -2720,7 +2751,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 	struct page *page = NULL;
 	unsigned long _address;
 	spinlock_t *ptl;
-	int node = NUMA_NO_NODE;
+	int node = NUMA_NO_NODE, unmapped = 0;
 	bool writable = false, referenced = false;
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
@@ -2736,6 +2767,14 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 	for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR;
 	     _pte++, _address += PAGE_SIZE) {
 		pte_t pteval = *_pte;
+		if (is_swap_pte(pteval)) {
+			if (++unmapped <= khugepaged_max_ptes_swap) {
+				continue;
+			} else {
+				ret = SCAN_EXCEED_SWAP_PTE;
+				goto out_unmap;
+			}
+		}
 		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
 			if (!userfaultfd_armed(vma) &&
 			    ++none_or_zero <= khugepaged_max_ptes_none) {
@@ -2816,7 +2855,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 	}
 out:
 	trace_mm_khugepaged_scan_pmd(mm, page_to_pfn(page), writable, referenced,
-				     none_or_zero, result);
+				     none_or_zero, result, unmapped);
 	return ret;
 }