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: <1370964919-16187-9-git-send-email-kirill.shutemov@linux.intel.com>
Date:	Tue, 11 Jun 2013 18:35:19 +0300
From:	"Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
To:	Andrea Arcangeli <aarcange@...hat.com>,
	Andrew Morton <akpm@...ux-foundation.org>
Cc:	Al Viro <viro@...iv.linux.org.uk>, Hugh Dickins <hughd@...gle.com>,
	Wu Fengguang <fengguang.wu@...el.com>, Jan Kara <jack@...e.cz>,
	Mel Gorman <mgorman@...e.de>, linux-mm@...ck.org,
	Andi Kleen <ak@...ux.intel.com>,
	Matthew Wilcox <willy@...ux.intel.com>,
	"Kirill A. Shutemov" <kirill@...temov.name>,
	Hillf Danton <dhillf@...il.com>, Dave Hansen <dave@...1.net>,
	linux-fsdevel@...r.kernel.org, linux-kernel@...r.kernel.org,
	"Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
Subject: [PATCH 8/8] thp: consolidate code between handle_mm_fault() and do_huge_pmd_anonymous_page()

From: "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>

do_huge_pmd_anonymous_page() has copy-pasted piece of handle_mm_fault()
to handle fallback path.

Let's consolidate code back by introducing VM_FAULT_FALLBACK return
code.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@...ux.intel.com>
Acked-by: Hillf Danton <dhillf@...il.com>
---
 include/linux/huge_mm.h |    3 ---
 include/linux/mm.h      |    3 ++-
 mm/huge_memory.c        |   31 +++++--------------------------
 mm/memory.c             |    9 ++++++---
 4 files changed, 13 insertions(+), 33 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index cc276d2..1031229 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -95,9 +95,6 @@ extern int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 			  pmd_t *dst_pmd, pmd_t *src_pmd,
 			  struct vm_area_struct *vma,
 			  unsigned long addr, unsigned long end);
-extern int handle_pte_fault(struct mm_struct *mm,
-			    struct vm_area_struct *vma, unsigned long address,
-			    pte_t *pte, pmd_t *pmd, unsigned int flags);
 extern int split_huge_page_to_list(struct page *page, struct list_head *list);
 static inline int split_huge_page(struct page *page)
 {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 98c9256..487988d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -890,11 +890,12 @@ static inline int page_mapped(struct page *page)
 #define VM_FAULT_NOPAGE	0x0100	/* ->fault installed the pte, not return page */
 #define VM_FAULT_LOCKED	0x0200	/* ->fault locked the returned page */
 #define VM_FAULT_RETRY	0x0400	/* ->fault blocked, must retry */
+#define VM_FAULT_FALLBACK 0x0800	/* huge page fault failed, fall back to small */
 
 #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
 
 #define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \
-			 VM_FAULT_HWPOISON_LARGE)
+			 VM_FAULT_FALLBACK | VM_FAULT_HWPOISON_LARGE)
 
 /* Encode hstate index for a hwpoisoned large page */
 #define VM_FAULT_SET_HINDEX(x) ((x) << 12)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 01a267c..7f4ae96 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -788,10 +788,9 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	struct page *page;
 	unsigned long haddr = address & HPAGE_PMD_MASK;
-	pte_t *pte;
 
 	if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end)
-		goto out;
+		return VM_FAULT_FALLBACK;
 	if (unlikely(anon_vma_prepare(vma)))
 		return VM_FAULT_OOM;
 	if (unlikely(khugepaged_enter(vma)))
@@ -808,7 +807,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		if (unlikely(!zero_page)) {
 			pte_free(mm, pgtable);
 			count_vm_event(THP_FAULT_FALLBACK);
-			goto out;
+			return VM_FAULT_FALLBACK;
 		}
 		spin_lock(&mm->page_table_lock);
 		set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd,
@@ -824,40 +823,20 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			vma, haddr, numa_node_id(), 0);
 	if (unlikely(!page)) {
 		count_vm_event(THP_FAULT_FALLBACK);
-		goto out;
+		return VM_FAULT_FALLBACK;
 	}
 	count_vm_event(THP_FAULT_ALLOC);
 	if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
 		put_page(page);
-		goto out;
+		return VM_FAULT_FALLBACK;
 	}
 	if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page))) {
 		mem_cgroup_uncharge_page(page);
 		put_page(page);
-		goto out;
+		return VM_FAULT_FALLBACK;
 	}
 
 	return 0;
-out:
-	/*
-	 * Use __pte_alloc instead of pte_alloc_map, because we can't
-	 * run pte_offset_map on the pmd, if an huge pmd could
-	 * materialize from under us from a different thread.
-	 */
-	if (unlikely(pmd_none(*pmd)) &&
-	    unlikely(__pte_alloc(mm, vma, pmd, address)))
-		return VM_FAULT_OOM;
-	/* if an huge pmd materialized from under us just retry later */
-	if (unlikely(pmd_trans_huge(*pmd)))
-		return 0;
-	/*
-	 * A regular pmd is established and it can't morph into a huge pmd
-	 * from under us anymore at this point because we hold the mmap_sem
-	 * read mode and khugepaged takes it in write mode. So now it's
-	 * safe to run pte_offset_map().
-	 */
-	pte = pte_offset_map(pmd, address);
-	return handle_pte_fault(mm, vma, address, pte, pmd, flags);
 }
 
 int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
diff --git a/mm/memory.c b/mm/memory.c
index 27c4da8..e633b4c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3702,7 +3702,7 @@ static int do_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
  * but allow concurrent faults), and pte mapped but not yet locked.
  * We return with mmap_sem still held, but pte unmapped and unlocked.
  */
-int handle_pte_fault(struct mm_struct *mm,
+static int handle_pte_fault(struct mm_struct *mm,
 		     struct vm_area_struct *vma, unsigned long address,
 		     pte_t *pte, pmd_t *pmd, unsigned int flags)
 {
@@ -3789,9 +3789,12 @@ retry:
 	if (!pmd)
 		return VM_FAULT_OOM;
 	if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) {
+		int ret = VM_FAULT_FALLBACK;
 		if (!vma->vm_ops)
-			return do_huge_pmd_anonymous_page(mm, vma, address,
-							  pmd, flags);
+			ret = do_huge_pmd_anonymous_page(mm, vma, address,
+					pmd, flags);
+		if (!(ret & VM_FAULT_FALLBACK))
+			return ret;
 	} else {
 		pmd_t orig_pmd = *pmd;
 		int ret;
-- 
1.7.10.4

--
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/

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ