linux-kernel - [PATCH 05/64] mm,khugepaged: prepare passing of rangelock field to vm

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:   Mon,  5 Feb 2018 02:26:55 +0100
From:   Davidlohr Bueso <dbueso@...e.de>
To:     akpm@...ux-foundation.org, mingo@...nel.org
Cc:     peterz@...radead.org, ldufour@...ux.vnet.ibm.com, jack@...e.cz,
        mhocko@...nel.org, kirill.shutemov@...ux.intel.com,
        mawilcox@...rosoft.com, mgorman@...hsingularity.net,
        dave@...olabs.net, linux-mm@...ck.org,
        linux-kernel@...r.kernel.org, Davidlohr Bueso <dbueso@...e.de>
Subject: [PATCH 05/64] mm,khugepaged: prepare passing of rangelock field to vm_fault

From: Davidlohr Bueso <dave@...olabs.net>

When collapsing huge pages from swapin, a vm_fault structure is built
and passed to do_swap_page(). The new range field of the vm_fault
structure must be set correctly when dealing with range_lock.

We teach the main workhorse, khugepaged_scan_mm_slot(), to pass on
a full range lock.

Signed-off-by: Davidlohr Bueso <dbueso@...e.de>
---
 mm/khugepaged.c | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index b7e2268dfc9a..0b91ce730160 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -873,7 +873,8 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
 static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 					struct vm_area_struct *vma,
 					unsigned long address, pmd_t *pmd,
-					int referenced)
+					int referenced,
+					struct range_lock *mmrange)
 {
 	int swapped_in = 0, ret = 0;
 	struct vm_fault vmf = {
@@ -882,6 +883,7 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 		.flags = FAULT_FLAG_ALLOW_RETRY,
 		.pmd = pmd,
 		.pgoff = linear_page_index(vma, address),
+		.lockrange = mmrange,
 	};
 
 	/* we only decide to swapin, if there is enough young ptes */
@@ -926,9 +928,10 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 }
 
 static void collapse_huge_page(struct mm_struct *mm,
-				   unsigned long address,
-				   struct page **hpage,
-				   int node, int referenced)
+			       unsigned long address,
+			       struct page **hpage,
+			       int node, int referenced,
+			       struct range_lock *mmrange)
 {
 	pmd_t *pmd, _pmd;
 	pte_t *pte;
@@ -986,7 +989,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	 * If it fails, we release mmap_sem and jump out_nolock.
 	 * Continuing to collapse causes inconsistency.
 	 */
-	if (!__collapse_huge_page_swapin(mm, vma, address, pmd, referenced)) {
+	if (!__collapse_huge_page_swapin(mm, vma, address, pmd, referenced, mmrange)) {
 		mem_cgroup_cancel_charge(new_page, memcg, true);
 		up_read(&mm->mmap_sem);
 		goto out_nolock;
@@ -1093,7 +1096,8 @@ static void collapse_huge_page(struct mm_struct *mm,
 static int khugepaged_scan_pmd(struct mm_struct *mm,
 			       struct vm_area_struct *vma,
 			       unsigned long address,
-			       struct page **hpage)
+			       struct page **hpage,
+			       struct range_lock *mmrange)
 {
 	pmd_t *pmd;
 	pte_t *pte, *_pte;
@@ -1207,7 +1211,8 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 	if (ret) {
 		node = khugepaged_find_target_node();
 		/* collapse_huge_page will return with the mmap_sem released */
-		collapse_huge_page(mm, address, hpage, node, referenced);
+		collapse_huge_page(mm, address, hpage, node, referenced,
+				   mmrange);
 	}
 out:
 	trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced,
@@ -1658,6 +1663,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
 	struct mm_struct *mm;
 	struct vm_area_struct *vma;
 	int progress = 0;
+	DEFINE_RANGE_LOCK_FULL(mmrange);
 
 	VM_BUG_ON(!pages);
 	VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&khugepaged_mm_lock));
@@ -1731,7 +1737,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
 			} else {
 				ret = khugepaged_scan_pmd(mm, vma,
 						khugepaged_scan.address,
-						hpage);
+						hpage, &mmrange);
 			}
 			/* move to next address */
 			khugepaged_scan.address += HPAGE_PMD_SIZE;
-- 
2.13.6