linux-kernel - [PATCH 1/2] hugetlbfs: handle pages higher order than MAX

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]

Message-Id: <1224771559-19363-2-git-send-email-apw@shadowen.org>
Date:	Thu, 23 Oct 2008 15:19:18 +0100
From:	Andy Whitcroft <apw@...dowen.org>
To:	Andrew Morton <akpm@...ux-foundation.org>
Cc:	linux-mm@...ck.org, linux-kernel@...r.kernel.org,
	Jon Tollefson <kniht@...ux.vnet.ibm.com>,
	Mel Gorman <mel@....ul.ie>,
	Nick Piggin <nickpiggin@...oo.com.au>,
	Christoph Lameter <cl@...ux-foundation.org>,
	Andy Whitcroft <apw@...dowen.org>
Subject: [PATCH 1/2] hugetlbfs: handle pages higher order than MAX_ORDER

When working with hugepages, hugetlbfs assumes that those hugepages
are smaller than MAX_ORDER.  Specifically it assumes that the mem_map
is contigious and uses that to optimise access to the elements of the
mem_map that represent the hugepage.  Gigantic pages (such as 16GB pages
on powerpc) by definition are of greater order than MAX_ORDER (larger
than MAX_ORDER_NR_PAGES in size).  This means that we can no longer make
use of the buddy alloctor guarentees for the contiguity of the mem_map,
which ensures that the mem_map is at least contigious for maximmally
aligned areas of MAX_ORDER_NR_PAGES pages.

This patch adds new mem_map accessors and iterator helpers which handle
any discontiguity at MAX_ORDER_NR_PAGES boundaries.  It then uses these
to implement gigantic page versions of copy_huge_page and clear_huge_page,
and to allow follow_hugetlb_page handle gigantic pages.

Signed-off-by: Andy Whitcroft <apw@...dowen.org>
---
 mm/hugetlb.c  |   37 ++++++++++++++++++++++++++++++++++++-
 mm/internal.h |   28 ++++++++++++++++++++++++++++
 2 files changed, 64 insertions(+), 1 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 67a7119..793f52e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -353,11 +353,26 @@ static int vma_has_reserves(struct vm_area_struct *vma)
 	return 0;
 }
 
+static void clear_gigantic_page(struct page *page,
+			unsigned long addr, unsigned long sz)
+{
+	int i;
+	struct page *p = page;
+
+	might_sleep();
+	for (i = 0; i < sz/PAGE_SIZE; i++, p = mem_map_next(p, page, i)) {
+		cond_resched();
+		clear_user_highpage(p, addr + i * PAGE_SIZE);
+	}
+}
 static void clear_huge_page(struct page *page,
 			unsigned long addr, unsigned long sz)
 {
 	int i;
 
+	if (unlikely(sz > MAX_ORDER_NR_PAGES))
+		return clear_gigantic_page(page, addr, sz);
+
 	might_sleep();
 	for (i = 0; i < sz/PAGE_SIZE; i++) {
 		cond_resched();
@@ -365,12 +380,32 @@ static void clear_huge_page(struct page *page,
 	}
 }
 
+static void copy_gigantic_page(struct page *dst, struct page *src,
+			   unsigned long addr, struct vm_area_struct *vma)
+{
+	int i;
+	struct hstate *h = hstate_vma(vma);
+	struct page *dst_base = dst;
+	struct page *src_base = src;
+	might_sleep();
+	for (i = 0; i < pages_per_huge_page(h); ) {
+		cond_resched();
+		copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma);
+
+		i++;
+		dst = mem_map_next(dst, dst_base, i);
+		src = mem_map_next(src, src_base, i);
+	}
+}
 static void copy_huge_page(struct page *dst, struct page *src,
 			   unsigned long addr, struct vm_area_struct *vma)
 {
 	int i;
 	struct hstate *h = hstate_vma(vma);
 
+	if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES))
+		return copy_gigantic_page(dst, src, addr, vma);
+
 	might_sleep();
 	for (i = 0; i < pages_per_huge_page(h); i++) {
 		cond_resched();
@@ -2103,7 +2138,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 same_page:
 		if (pages) {
 			get_page(page);
-			pages[i] = page + pfn_offset;
+			pages[i] = mem_map_offset(page, pfn_offset);
 		}
 
 		if (vmas)
diff --git a/mm/internal.h b/mm/internal.h
index 1f43f74..08b8dea 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -53,6 +53,34 @@ static inline unsigned long page_order(struct page *page)
 }
 
 /*
+ * Return the mem_map entry representing the 'offset' subpage within
+ * the maximally aligned gigantic page 'base'.  Handle any discontiguity
+ * in the mem_map at MAX_ORDER_NR_PAGES boundaries.
+ */
+static inline struct page *mem_map_offset(struct page *base, int offset)
+{
+	if (unlikely(offset >= MAX_ORDER_NR_PAGES))
+		return pfn_to_page(page_to_pfn(base) + offset);
+	return base + offset;
+}
+
+/*
+ * Iterator over all subpages withing the maximally aligned gigantic
+ * page 'base'.  Handle any discontiguity in the mem_map.
+ */
+static inline struct page *mem_map_next(struct page *iter,
+						struct page *base, int offset)
+{
+	if (unlikely((offset & (MAX_ORDER_NR_PAGES - 1)) == 0)) {
+		unsigned long pfn = page_to_pfn(base) + offset;
+		if (!pfn_valid(pfn))
+			return NULL;
+		return pfn_to_page(pfn);
+	}
+	return iter + 1;
+}
+
+/*
  * FLATMEM and DISCONTIGMEM configurations use alloc_bootmem_node,
  * so all functions starting at paging_init should be marked __init
  * in those cases. SPARSEMEM, however, allows for memory hotplug,
-- 
1.6.0.2.711.gf1ba4

--
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/