linux-kernel - [RFC 2/3] mm: make optimistic check for swapin readahead

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Sun, 14 Jun 2015 18:04:42 +0300
From:	Ebru Akagunduz <ebru.akagunduz@...il.com>
To:	linux-mm@...ck.org
Cc:	akpm@...ux-foundation.org, kirill.shutemov@...ux.intel.com,
	n-horiguchi@...jp.nec.com, aarcange@...hat.com, riel@...hat.com,
	iamjoonsoo.kim@....com, xiexiuqi@...wei.com, gorcunov@...nvz.org,
	linux-kernel@...r.kernel.org, mgorman@...e.de, rientjes@...gle.com,
	vbabka@...e.cz, aneesh.kumar@...ux.vnet.ibm.com, hughd@...gle.com,
	hannes@...xchg.org, mhocko@...e.cz, boaz@...xistor.com,
	raindel@...lanox.com, Ebru Akagunduz <ebru.akagunduz@...il.com>
Subject: [RFC 2/3] mm: make optimistic check for swapin readahead

This patch 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@...il.com>
---
 include/trace/events/huge_memory.h | 11 +++++++----
 mm/huge_memory.c                   | 13 ++++++++++---
 2 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h
index 4b9049b..53c9f2e 100644
--- a/include/trace/events/huge_memory.h
+++ b/include/trace/events/huge_memory.h
@@ -9,9 +9,9 @@
 TRACE_EVENT(mm_khugepaged_scan_pmd,
 
 	TP_PROTO(struct mm_struct *mm, unsigned long vm_start, bool writable,
-		bool referenced, int none_or_zero, int collapse),
+		bool referenced, int none_or_zero, int collapse, int unmapped),
 
-	TP_ARGS(mm, vm_start, writable, referenced, none_or_zero, collapse),
+	TP_ARGS(mm, vm_start, writable, referenced, none_or_zero, collapse, unmapped),
 
 	TP_STRUCT__entry(
 		__field(struct mm_struct *, mm)
@@ -20,6 +20,7 @@ TRACE_EVENT(mm_khugepaged_scan_pmd,
 		__field(bool, referenced)
 		__field(int, none_or_zero)
 		__field(int, collapse)
+		__field(int, unmapped)
 	),
 
 	TP_fast_assign(
@@ -29,15 +30,17 @@ TRACE_EVENT(mm_khugepaged_scan_pmd,
 		__entry->referenced = referenced;
 		__entry->none_or_zero = none_or_zero;
 		__entry->collapse = collapse;
+		__entry->unmapped = unmapped;
 	),
 
-	TP_printk("mm=%p, vm_start=%04lx, writable=%d, referenced=%d, none_or_zero=%d, collapse=%d",
+	TP_printk("mm=%p, vm_start=%04lx, writable=%d, referenced=%d, none_or_zero=%d, collapse=%d, unmapped=%d",
 		__entry->mm,
 		__entry->vm_start,
 		__entry->writable,
 		__entry->referenced,
 		__entry->none_or_zero,
-		__entry->collapse)
+		__entry->collapse,
+		__entry->unmapped)
 );
 
 TRACE_EVENT(mm_collapse_huge_page,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9bb97fc..22bc0bf 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -24,6 +24,7 @@
 #include <linux/migrate.h>
 #include <linux/hashtable.h>
 #include <linux/userfaultfd_k.h>
+#include <linux/swapops.h>
 
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
@@ -2639,11 +2640,11 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 {
 	pmd_t *pmd;
 	pte_t *pte, *_pte;
-	int ret = 0, none_or_zero = 0;
+	int ret = 0, none_or_zero = 0, unmapped = 0;
 	struct page *page;
 	unsigned long _address;
 	spinlock_t *ptl;
-	int node = NUMA_NO_NODE;
+	int node = NUMA_NO_NODE, max_ptes_swap = HPAGE_PMD_NR/8;
 	bool writable = false, referenced = false;
 
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
@@ -2657,6 +2658,12 @@ 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 <= max_ptes_swap)
+				continue;
+			else
+				goto out_unmap;
+		}
 		if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) {
 			if (!userfaultfd_armed(vma) &&
 			    ++none_or_zero <= khugepaged_max_ptes_none)
@@ -2701,7 +2708,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 out_unmap:
 	pte_unmap_unlock(pte, ptl);
 	trace_mm_khugepaged_scan_pmd(mm, vma->vm_start, writable, referenced,
-				     none_or_zero, ret);
+				     none_or_zero, ret, unmapped);
 	if (ret) {
 		node = khugepaged_find_target_node();
 		/* collapse_huge_page will return with the mmap_sem released */
-- 
1.9.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/