[PATCH 00/16] Sanitize usage of ->flags and ->mapping for tail pages

[PATCH 00/16] Sanitize usage of ->flags and ->mapping for tail pages

[Kirill A. Shutemov]

Currently we take naive approach to page flags on compound -- we set the
flag on the page without consideration if the flag makes sense for tail
page or for compound page in general. This patchset try to sort this out
by defining per-flag policy on what need to be done if page-flag helper
operate on compound page.

The last patch in patchset also sanitize usege of page->mapping for tail
pages. We don't define meaning of page->mapping for tail pages. Currently
it's always NULL, which can be inconsistent with head page and potentially
lead to problems.

For now I catched one case of illigal usage of page flags or ->mapping:
sound subsystem allocates pages with __GFP_COMP and maps them with PTEs.
It leads to setting dirty bit on tail pages and access to tail_page's
->mapping. I don't see any bad behaviour caused by this, but worth fixing
anyway.

This patchset makes more sense if you take my THP refcounting into
account: we will see more compound pages mapped with PTEs and we need to
define behaviour of flags on compound pages to avoid bugs.

Kirill A. Shutemov (16):
  mm: consolidate all page-flags helpers in <linux/page-flags.h>
  page-flags: trivial cleanup for PageTrans* helpers
  page-flags: introduce page flags policies wrt compound pages
  page-flags: define PG_locked behavior on compound pages
  page-flags: define behavior of FS/IO-related flags on compound pages
  page-flags: define behavior of LRU-related flags on compound pages
  page-flags: define behavior SL*B-related flags on compound pages
  page-flags: define behavior of Xen-related flags on compound pages
  page-flags: define PG_reserved behavior on compound pages
  page-flags: define PG_swapbacked behavior on compound pages
  page-flags: define PG_swapcache behavior on compound pages
  page-flags: define PG_mlocked behavior on compound pages
  page-flags: define PG_uncached behavior on compound pages
  page-flags: define PG_uptodate behavior on compound pages
  page-flags: look on head page if the flag is encoded in page->mapping
  mm: sanitize page->mapping for tail pages

 fs/cifs/file.c             |   8 +-
 include/linux/hugetlb.h    |   7 -
 include/linux/ksm.h        |  17 ---
 include/linux/mm.h         | 122 +----------------
 include/linux/page-flags.h | 317 ++++++++++++++++++++++++++++++++++-----------
 include/linux/pagemap.h    |  25 ++--
 include/linux/poison.h     |   4 +
 mm/filemap.c               |  15 ++-
 mm/huge_memory.c           |   2 +-
 mm/ksm.c                   |   2 +-
 mm/memory-failure.c        |   2 +-
 mm/memory.c                |   2 +-
 mm/migrate.c               |   2 +-
 mm/page_alloc.c            |   7 +
 mm/shmem.c                 |   4 +-
 mm/slub.c                  |   2 +
 mm/swap_state.c            |   4 +-
 mm/util.c                  |   5 +-
 mm/vmscan.c                |   4 +-
 mm/zswap.c                 |   4 +-
 20 files changed, 294 insertions(+), 261 deletions(-)

-- 
2.1.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 01/16] mm: consolidate all page-flags helpers in <linux/page-flags.h>

[Kirill A. Shutemov]

We have page-flags helper function declarations/definitions spread over
several header files. Let's consolidate them in <linux/page-flags.h>.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 include/linux/hugetlb.h    |  7 ----
 include/linux/ksm.h        | 17 --------
 include/linux/mm.h         | 81 --------------------------------------
 include/linux/page-flags.h | 96 ++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 96 insertions(+), 105 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 7b5785032049..1a782733a420 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -41,8 +41,6 @@ extern int hugetlb_max_hstate __read_mostly;
 struct hugepage_subpool *hugepage_new_subpool(long nr_blocks);
 void hugepage_put_subpool(struct hugepage_subpool *spool);
 
-int PageHuge(struct page *page);
-
 void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
 int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
 int hugetlb_overcommit_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
@@ -109,11 +107,6 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 
 #else /* !CONFIG_HUGETLB_PAGE */
 
-static inline int PageHuge(struct page *page)
-{
-	return 0;
-}
-
 static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
 {
 }
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 3be6bb18562d..7ae216a39c9e 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -35,18 +35,6 @@ static inline void ksm_exit(struct mm_struct *mm)
 		__ksm_exit(mm);
 }
 
-/*
- * A KSM page is one of those write-protected "shared pages" or "merged pages"
- * which KSM maps into multiple mms, wherever identical anonymous page content
- * is found in VM_MERGEABLE vmas.  It's a PageAnon page, pointing not to any
- * anon_vma, but to that page's node of the stable tree.
- */
-static inline int PageKsm(struct page *page)
-{
-	return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) ==
-				(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM);
-}
-
 static inline struct stable_node *page_stable_node(struct page *page)
 {
 	return PageKsm(page) ? page_rmapping(page) : NULL;
@@ -87,11 +75,6 @@ static inline void ksm_exit(struct mm_struct *mm)
 {
 }
 
-static inline int PageKsm(struct page *page)
-{
-	return 0;
-}
-
 #ifdef CONFIG_MMU
 static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 		unsigned long end, int advice, unsigned long *vm_flags)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6571dd78e984..fb1fc38b01ce 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -494,15 +494,6 @@ static inline int page_count(struct page *page)
 	return atomic_read(&compound_head(page)->_count);
 }
 
-#ifdef CONFIG_HUGETLB_PAGE
-extern int PageHeadHuge(struct page *page_head);
-#else /* CONFIG_HUGETLB_PAGE */
-static inline int PageHeadHuge(struct page *page_head)
-{
-	return 0;
-}
-#endif /* CONFIG_HUGETLB_PAGE */
-
 static inline bool __compound_tail_refcounted(struct page *page)
 {
 	return !PageSlab(page) && !PageHeadHuge(page);
@@ -571,53 +562,6 @@ static inline void init_page_count(struct page *page)
 	atomic_set(&page->_count, 1);
 }
 
-/*
- * PageBuddy() indicate that the page is free and in the buddy system
- * (see mm/page_alloc.c).
- *
- * PAGE_BUDDY_MAPCOUNT_VALUE must be <= -2 but better not too close to
- * -2 so that an underflow of the page_mapcount() won't be mistaken
- * for a genuine PAGE_BUDDY_MAPCOUNT_VALUE. -128 can be created very
- * efficiently by most CPU architectures.
- */
-#define PAGE_BUDDY_MAPCOUNT_VALUE (-128)
-
-static inline int PageBuddy(struct page *page)
-{
-	return atomic_read(&page->_mapcount) == PAGE_BUDDY_MAPCOUNT_VALUE;
-}
-
-static inline void __SetPageBuddy(struct page *page)
-{
-	VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page);
-	atomic_set(&page->_mapcount, PAGE_BUDDY_MAPCOUNT_VALUE);
-}
-
-static inline void __ClearPageBuddy(struct page *page)
-{
-	VM_BUG_ON_PAGE(!PageBuddy(page), page);
-	atomic_set(&page->_mapcount, -1);
-}
-
-#define PAGE_BALLOON_MAPCOUNT_VALUE (-256)
-
-static inline int PageBalloon(struct page *page)
-{
-	return atomic_read(&page->_mapcount) == PAGE_BALLOON_MAPCOUNT_VALUE;
-}
-
-static inline void __SetPageBalloon(struct page *page)
-{
-	VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page);
-	atomic_set(&page->_mapcount, PAGE_BALLOON_MAPCOUNT_VALUE);
-}
-
-static inline void __ClearPageBalloon(struct page *page)
-{
-	VM_BUG_ON_PAGE(!PageBalloon(page), page);
-	atomic_set(&page->_mapcount, -1);
-}
-
 void put_page(struct page *page);
 void put_pages_list(struct list_head *pages);
 
@@ -1006,26 +950,6 @@ void page_address_init(void);
 #define page_address_init()  do { } while(0)
 #endif
 
-/*
- * On an anonymous page mapped into a user virtual memory area,
- * page->mapping points to its anon_vma, not to a struct address_space;
- * with the PAGE_MAPPING_ANON bit set to distinguish it.  See rmap.h.
- *
- * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled,
- * the PAGE_MAPPING_KSM bit may be set along with the PAGE_MAPPING_ANON bit;
- * and then page->mapping points, not to an anon_vma, but to a private
- * structure which KSM associates with that merged page.  See ksm.h.
- *
- * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is currently never used.
- *
- * Please note that, confusingly, "page_mapping" refers to the inode
- * address_space which maps the page from disk; whereas "page_mapped"
- * refers to user virtual address space into which the page is mapped.
- */
-#define PAGE_MAPPING_ANON	1
-#define PAGE_MAPPING_KSM	2
-#define PAGE_MAPPING_FLAGS	(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM)
-
 extern struct address_space *page_mapping(struct page *page);
 
 /* Neutral page->mapping pointer to address_space or anon_vma or other */
@@ -1045,11 +969,6 @@ struct address_space *page_file_mapping(struct page *page)
 	return page->mapping;
 }
 
-static inline int PageAnon(struct page *page)
-{
-	return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
-}
-
 /*
  * Return the pagecache index of the passed page.  Regular pagecache pages
  * use ->index whereas swapcache pages use ->private
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index c851ff92d5b3..84d10b65cec6 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -289,6 +289,47 @@ PAGEFLAG_FALSE(HWPoison)
 #define __PG_HWPOISON 0
 #endif
 
+/*
+ * On an anonymous page mapped into a user virtual memory area,
+ * page->mapping points to its anon_vma, not to a struct address_space;
+ * with the PAGE_MAPPING_ANON bit set to distinguish it.  See rmap.h.
+ *
+ * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled,
+ * the PAGE_MAPPING_KSM bit may be set along with the PAGE_MAPPING_ANON bit;
+ * and then page->mapping points, not to an anon_vma, but to a private
+ * structure which KSM associates with that merged page.  See ksm.h.
+ *
+ * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is currently never used.
+ *
+ * Please note that, confusingly, "page_mapping" refers to the inode
+ * address_space which maps the page from disk; whereas "page_mapped"
+ * refers to user virtual address space into which the page is mapped.
+ */
+#define PAGE_MAPPING_ANON	1
+#define PAGE_MAPPING_KSM	2
+#define PAGE_MAPPING_FLAGS	(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM)
+
+static inline int PageAnon(struct page *page)
+{
+	return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
+}
+
+#ifdef CONFIG_KSM
+/*
+ * A KSM page is one of those write-protected "shared pages" or "merged pages"
+ * which KSM maps into multiple mms, wherever identical anonymous page content
+ * is found in VM_MERGEABLE vmas.  It's a PageAnon page, pointing not to any
+ * anon_vma, but to that page's node of the stable tree.
+ */
+static inline int PageKsm(struct page *page)
+{
+	return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) ==
+				(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM);
+}
+#else
+TESTPAGEFLAG_FALSE(Ksm)
+#endif
+
 u64 stable_page_flags(struct page *page);
 
 static inline int PageUptodate(struct page *page)
@@ -426,6 +467,14 @@ static inline void ClearPageCompound(struct page *page)
 
 #endif /* !PAGEFLAGS_EXTENDED */
 
+#ifdef CONFIG_HUGETLB_PAGE
+int PageHuge(struct page *page);
+int PageHeadHuge(struct page *page);
+#else
+TESTPAGEFLAG_FALSE(Huge)
+TESTPAGEFLAG_FALSE(HeadHuge)
+#endif
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 /*
  * PageHuge() only returns true for hugetlbfs pages, but not for
@@ -480,6 +529,53 @@ static inline int PageTransTail(struct page *page)
 #endif
 
 /*
+ * PageBuddy() indicate that the page is free and in the buddy system
+ * (see mm/page_alloc.c).
+ *
+ * PAGE_BUDDY_MAPCOUNT_VALUE must be <= -2 but better not too close to
+ * -2 so that an underflow of the page_mapcount() won't be mistaken
+ * for a genuine PAGE_BUDDY_MAPCOUNT_VALUE. -128 can be created very
+ * efficiently by most CPU architectures.
+ */
+#define PAGE_BUDDY_MAPCOUNT_VALUE (-128)
+
+static inline int PageBuddy(struct page *page)
+{
+	return atomic_read(&page->_mapcount) == PAGE_BUDDY_MAPCOUNT_VALUE;
+}
+
+static inline void __SetPageBuddy(struct page *page)
+{
+	VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page);
+	atomic_set(&page->_mapcount, PAGE_BUDDY_MAPCOUNT_VALUE);
+}
+
+static inline void __ClearPageBuddy(struct page *page)
+{
+	VM_BUG_ON_PAGE(!PageBuddy(page), page);
+	atomic_set(&page->_mapcount, -1);
+}
+
+#define PAGE_BALLOON_MAPCOUNT_VALUE (-256)
+
+static inline int PageBalloon(struct page *page)
+{
+	return atomic_read(&page->_mapcount) == PAGE_BALLOON_MAPCOUNT_VALUE;
+}
+
+static inline void __SetPageBalloon(struct page *page)
+{
+	VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page);
+	atomic_set(&page->_mapcount, PAGE_BALLOON_MAPCOUNT_VALUE);
+}
+
+static inline void __ClearPageBalloon(struct page *page)
+{
+	VM_BUG_ON_PAGE(!PageBalloon(page), page);
+	atomic_set(&page->_mapcount, -1);
+}
+
+/*
  * If network-based swap is enabled, sl*b must keep track of whether pages
  * were allocated from pfmemalloc reserves.
  */
-- 
2.1.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 02/16] page-flags: trivial cleanup for PageTrans* helpers

[Kirill A. Shutemov]

Use TESTPAGEFLAG_FALSE() to get it a bit cleaner.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 include/linux/page-flags.h | 18 +++---------------
 1 file changed, 3 insertions(+), 15 deletions(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 84d10b65cec6..327aabd9792e 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -511,21 +511,9 @@ static inline int PageTransTail(struct page *page)
 }
 
 #else
-
-static inline int PageTransHuge(struct page *page)
-{
-	return 0;
-}
-
-static inline int PageTransCompound(struct page *page)
-{
-	return 0;
-}
-
-static inline int PageTransTail(struct page *page)
-{
-	return 0;
-}
+TESTPAGEFLAG_FALSE(TransHuge)
+TESTPAGEFLAG_FALSE(TransCompound)
+TESTPAGEFLAG_FALSE(TransTail)
 #endif
 
 /*
-- 
2.1.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 03/16] page-flags: introduce page flags policies wrt compound pages

[Kirill A. Shutemov]

This patch third argument to macros which create function definitions
for page flags. This arguments defines how page-flags helpers behave
on compound functions.

For now we define four policies:

 - ANY: the helper function operates on the page it gets, regardless if
   it's non-compound, head or tail.

 - HEAD: the helper function operates on the head page of the compound
   page if it gets tail page.

 - NO_TAIL: only head and non-compond pages are acceptable for this
   helper function.

 - NO_COMPOUND: only non-compound pages are acceptable for this helper
   function.

For now we use policy ANY for all helpers, which match current
behaviour.

We do not enforce the policy for TESTPAGEFLAG, because we have flags
checked for random pages all over the kernel. Noticeable exception to
this is PageTransHuge() which triggers VM_BUG_ON() for tail page.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 include/linux/mm.h         |  40 ---------
 include/linux/page-flags.h | 198 ++++++++++++++++++++++++++++++---------------
 2 files changed, 134 insertions(+), 104 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index fb1fc38b01ce..bcf37dacbee3 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -433,46 +433,6 @@ static inline void compound_unlock_irqrestore(struct page *page,
 #endif
 }
 
-static inline struct page *compound_head_by_tail(struct page *tail)
-{
-	struct page *head = tail->first_page;
-
-	/*
-	 * page->first_page may be a dangling pointer to an old
-	 * compound page, so recheck that it is still a tail
-	 * page before returning.
-	 */
-	smp_rmb();
-	if (likely(PageTail(tail)))
-		return head;
-	return tail;
-}
-
-/*
- * Since either compound page could be dismantled asynchronously in THP
- * or we access asynchronously arbitrary positioned struct page, there
- * would be tail flag race. To handle this race, we should call
- * smp_rmb() before checking tail flag. compound_head_by_tail() did it.
- */
-static inline struct page *compound_head(struct page *page)
-{
-	if (unlikely(PageTail(page)))
-		return compound_head_by_tail(page);
-	return page;
-}
-
-/*
- * If we access compound page synchronously such as access to
- * allocated page, there is no need to handle tail flag race, so we can
- * check tail flag directly without any synchronization primitive.
- */
-static inline struct page *compound_head_fast(struct page *page)
-{
-	if (unlikely(PageTail(page)))
-		return page->first_page;
-	return page;
-}
-
 /*
  * The atomic page->_mapcount, starts from -1: so that transitions
  * both from it and to it can be tracked, using atomic_inc_and_test
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 327aabd9792e..32ea62c0ad30 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -134,49 +134,68 @@ enum pageflags {
 
 #ifndef __GENERATING_BOUNDS_H
 
+/* Page flags policies wrt compound pages */
+#define ANY(page, enforce)	page
+#define HEAD(page, enforce)	compound_head(page)
+#define NO_TAIL(page, enforce) ({					\
+		if (enforce)						\
+			VM_BUG_ON_PAGE(PageTail(page), page);		\
+		else							\
+			page = compound_head(page);			\
+		page;})
+#define NO_COMPOUND(page, enforce) ({					\
+		if (enforce)						\
+			VM_BUG_ON_PAGE(PageCompound(page), page);	\
+		page;})
+
 /*
  * Macros to create function definitions for page flags
  */
-#define TESTPAGEFLAG(uname, lname)					\
-static inline int Page##uname(const struct page *page)			\
-			{ return test_bit(PG_##lname, &page->flags); }
+#define TESTPAGEFLAG(uname, lname, policy)				\
+static inline int Page##uname(struct page *page)			\
+	{ return test_bit(PG_##lname, &policy(page, 0)->flags); }
 
-#define SETPAGEFLAG(uname, lname)					\
+#define SETPAGEFLAG(uname, lname, policy)				\
 static inline void SetPage##uname(struct page *page)			\
-			{ set_bit(PG_##lname, &page->flags); }
+	{ set_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define CLEARPAGEFLAG(uname, lname)					\
+#define CLEARPAGEFLAG(uname, lname, policy)				\
 static inline void ClearPage##uname(struct page *page)			\
-			{ clear_bit(PG_##lname, &page->flags); }
+	{ clear_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define __SETPAGEFLAG(uname, lname)					\
+#define __SETPAGEFLAG(uname, lname, policy)				\
 static inline void __SetPage##uname(struct page *page)			\
-			{ __set_bit(PG_##lname, &page->flags); }
+	{ __set_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define __CLEARPAGEFLAG(uname, lname)					\
+#define __CLEARPAGEFLAG(uname, lname, policy)				\
 static inline void __ClearPage##uname(struct page *page)		\
-			{ __clear_bit(PG_##lname, &page->flags); }
+	{ __clear_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define TESTSETFLAG(uname, lname)					\
+#define TESTSETFLAG(uname, lname, policy)				\
 static inline int TestSetPage##uname(struct page *page)			\
-		{ return test_and_set_bit(PG_##lname, &page->flags); }
+	{ return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define TESTCLEARFLAG(uname, lname)					\
+#define TESTCLEARFLAG(uname, lname, policy)				\
 static inline int TestClearPage##uname(struct page *page)		\
-		{ return test_and_clear_bit(PG_##lname, &page->flags); }
+	{ return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define __TESTCLEARFLAG(uname, lname)					\
+#define __TESTCLEARFLAG(uname, lname, policy)				\
 static inline int __TestClearPage##uname(struct page *page)		\
-		{ return __test_and_clear_bit(PG_##lname, &page->flags); }
+	{ return __test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname)		\
-	SETPAGEFLAG(uname, lname) CLEARPAGEFLAG(uname, lname)
+#define PAGEFLAG(uname, lname, policy)					\
+	TESTPAGEFLAG(uname, lname, policy)				\
+	SETPAGEFLAG(uname, lname, policy)				\
+	CLEARPAGEFLAG(uname, lname, policy)
 
-#define __PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname)		\
-	__SETPAGEFLAG(uname, lname)  __CLEARPAGEFLAG(uname, lname)
+#define __PAGEFLAG(uname, lname, policy)				\
+	TESTPAGEFLAG(uname, lname, policy)				\
+	__SETPAGEFLAG(uname, lname, policy)				\
+	__CLEARPAGEFLAG(uname, lname, policy)
 
-#define TESTSCFLAG(uname, lname)					\
-	TESTSETFLAG(uname, lname) TESTCLEARFLAG(uname, lname)
+#define TESTSCFLAG(uname, lname, policy)				\
+	TESTSETFLAG(uname, lname, policy)				\
+	TESTCLEARFLAG(uname, lname, policy)
 
 #define TESTPAGEFLAG_FALSE(uname)					\
 static inline int Page##uname(const struct page *page) { return 0; }
@@ -205,47 +224,93 @@ static inline int __TestClearPage##uname(struct page *page) { return 0; }
 #define TESTSCFLAG_FALSE(uname)						\
 	TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname)
 
-struct page;	/* forward declaration */
-
-TESTPAGEFLAG(Locked, locked)
-PAGEFLAG(Error, error) TESTCLEARFLAG(Error, error)
-PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced)
-	__SETPAGEFLAG(Referenced, referenced)
-PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty)
-PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru)
-PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active)
-	TESTCLEARFLAG(Active, active)
-__PAGEFLAG(Slab, slab)
-PAGEFLAG(Checked, checked)		/* Used by some filesystems */
-PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned)	/* Xen */
-PAGEFLAG(SavePinned, savepinned);			/* Xen */
-PAGEFLAG(Foreign, foreign);				/* Xen */
-PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved)
-PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked)
-	__SETPAGEFLAG(SwapBacked, swapbacked)
-
-__PAGEFLAG(SlobFree, slob_free)
+/* Forward declarations */
+struct page;
+static inline int PageCompound(struct page *page);
+static inline int PageTail(struct page *page);
+
+static inline struct page *compound_head_by_tail(struct page *tail)
+{
+	struct page *head = tail->first_page;
+
+	/*
+	 * page->first_page may be a dangling pointer to an old
+	 * compound page, so recheck that it is still a tail
+	 * page before returning.
+	 */
+	smp_rmb();
+	if (likely(PageTail(tail)))
+		return head;
+	return tail;
+}
+
+/*
+ * Since either compound page could be dismantled asynchronously in THP
+ * or we access asynchronously arbitrary positioned struct page, there
+ * would be tail flag race. To handle this race, we should call
+ * smp_rmb() before checking tail flag. compound_head_by_tail() did it.
+ */
+static inline struct page *compound_head(struct page *page)
+{
+	if (unlikely(PageTail(page)))
+		return compound_head_by_tail(page);
+	return page;
+}
+
+/*
+ * If we access compound page synchronously such as access to
+ * allocated page, there is no need to handle tail flag race, so we can
+ * check tail flag directly without any synchronization primitive.
+ */
+static inline struct page *compound_head_fast(struct page *page)
+{
+	if (unlikely(PageTail(page)))
+		return page->first_page;
+	return page;
+}
+
+TESTPAGEFLAG(Locked, locked, ANY)
+PAGEFLAG(Error, error, ANY) TESTCLEARFLAG(Error, error, ANY)
+PAGEFLAG(Referenced, referenced, ANY) TESTCLEARFLAG(Referenced, referenced, ANY)
+	__SETPAGEFLAG(Referenced, referenced, ANY)
+PAGEFLAG(Dirty, dirty, ANY) TESTSCFLAG(Dirty, dirty, ANY)
+	__CLEARPAGEFLAG(Dirty, dirty, ANY)
+PAGEFLAG(LRU, lru, ANY) __CLEARPAGEFLAG(LRU, lru, ANY)
+PAGEFLAG(Active, active, ANY) __CLEARPAGEFLAG(Active, active, ANY)
+	TESTCLEARFLAG(Active, active, ANY)
+__PAGEFLAG(Slab, slab, ANY)
+PAGEFLAG(Checked, checked, ANY)		/* Used by some filesystems */
+PAGEFLAG(Pinned, pinned, ANY) TESTSCFLAG(Pinned, pinned, ANY)	/* Xen */
+PAGEFLAG(SavePinned, savepinned, ANY);			/* Xen */
+PAGEFLAG(Foreign, foreign, ANY);				/* Xen */
+PAGEFLAG(Reserved, reserved, ANY) __CLEARPAGEFLAG(Reserved, reserved, ANY)
+PAGEFLAG(SwapBacked, swapbacked, ANY)
+	__CLEARPAGEFLAG(SwapBacked, swapbacked, ANY)
+	__SETPAGEFLAG(SwapBacked, swapbacked, ANY)
+
+__PAGEFLAG(SlobFree, slob_free, ANY)
 
 /*
  * Private page markings that may be used by the filesystem that owns the page
  * for its own purposes.
  * - PG_private and PG_private_2 cause releasepage() and co to be invoked
  */
-PAGEFLAG(Private, private) __SETPAGEFLAG(Private, private)
-	__CLEARPAGEFLAG(Private, private)
-PAGEFLAG(Private2, private_2) TESTSCFLAG(Private2, private_2)
-PAGEFLAG(OwnerPriv1, owner_priv_1) TESTCLEARFLAG(OwnerPriv1, owner_priv_1)
+PAGEFLAG(Private, private, ANY) __SETPAGEFLAG(Private, private, ANY)
+	__CLEARPAGEFLAG(Private, private, ANY)
+PAGEFLAG(Private2, private_2, ANY) TESTSCFLAG(Private2, private_2, ANY)
+PAGEFLAG(OwnerPriv1, owner_priv_1, ANY)
+	TESTCLEARFLAG(OwnerPriv1, owner_priv_1, ANY)
 
 /*
  * Only test-and-set exist for PG_writeback.  The unconditional operators are
  * risky: they bypass page accounting.
  */
-TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback)
-PAGEFLAG(MappedToDisk, mappedtodisk)
+TESTPAGEFLAG(Writeback, writeback, ANY) TESTSCFLAG(Writeback, writeback, ANY)
+PAGEFLAG(MappedToDisk, mappedtodisk, ANY)
 
 /* PG_readahead is only used for reads; PG_reclaim is only for writes */
-PAGEFLAG(Reclaim, reclaim) TESTCLEARFLAG(Reclaim, reclaim)
-PAGEFLAG(Readahead, reclaim) TESTCLEARFLAG(Readahead, reclaim)
+PAGEFLAG(Reclaim, reclaim, ANY) TESTCLEARFLAG(Reclaim, reclaim, ANY)
+PAGEFLAG(Readahead, reclaim, ANY) TESTCLEARFLAG(Readahead, reclaim, ANY)
 
 #ifdef CONFIG_HIGHMEM
 /*
@@ -258,31 +323,32 @@ PAGEFLAG_FALSE(HighMem)
 #endif
 
 #ifdef CONFIG_SWAP
-PAGEFLAG(SwapCache, swapcache)
+PAGEFLAG(SwapCache, swapcache, ANY)
 #else
 PAGEFLAG_FALSE(SwapCache)
 #endif
 
-PAGEFLAG(Unevictable, unevictable) __CLEARPAGEFLAG(Unevictable, unevictable)
-	TESTCLEARFLAG(Unevictable, unevictable)
+PAGEFLAG(Unevictable, unevictable, ANY)
+	__CLEARPAGEFLAG(Unevictable, unevictable, ANY)
+	TESTCLEARFLAG(Unevictable, unevictable, ANY)
 
 #ifdef CONFIG_MMU
-PAGEFLAG(Mlocked, mlocked) __CLEARPAGEFLAG(Mlocked, mlocked)
-	TESTSCFLAG(Mlocked, mlocked) __TESTCLEARFLAG(Mlocked, mlocked)
+PAGEFLAG(Mlocked, mlocked, ANY) __CLEARPAGEFLAG(Mlocked, mlocked, ANY)
+	TESTSCFLAG(Mlocked, mlocked, ANY) __TESTCLEARFLAG(Mlocked, mlocked, ANY)
 #else
 PAGEFLAG_FALSE(Mlocked) __CLEARPAGEFLAG_NOOP(Mlocked)
 	TESTSCFLAG_FALSE(Mlocked) __TESTCLEARFLAG_FALSE(Mlocked)
 #endif
 
 #ifdef CONFIG_ARCH_USES_PG_UNCACHED
-PAGEFLAG(Uncached, uncached)
+PAGEFLAG(Uncached, uncached, ANY)
 #else
 PAGEFLAG_FALSE(Uncached)
 #endif
 
 #ifdef CONFIG_MEMORY_FAILURE
-PAGEFLAG(HWPoison, hwpoison)
-TESTSCFLAG(HWPoison, hwpoison)
+PAGEFLAG(HWPoison, hwpoison, ANY)
+TESTSCFLAG(HWPoison, hwpoison, ANY)
 #define __PG_HWPOISON (1UL << PG_hwpoison)
 #else
 PAGEFLAG_FALSE(HWPoison)
@@ -367,7 +433,7 @@ static inline void SetPageUptodate(struct page *page)
 	set_bit(PG_uptodate, &(page)->flags);
 }
 
-CLEARPAGEFLAG(Uptodate, uptodate)
+CLEARPAGEFLAG(Uptodate, uptodate, ANY)
 
 int test_clear_page_writeback(struct page *page);
 int __test_set_page_writeback(struct page *page, bool keep_write);
@@ -396,8 +462,8 @@ static inline void set_page_writeback_keepwrite(struct page *page)
  * and arch/powerpc/kvm/book3s_64_vio_hv.c which use it to detect huge pages
  * and avoid handling those in real mode.
  */
-__PAGEFLAG(Head, head) CLEARPAGEFLAG(Head, head)
-__PAGEFLAG(Tail, tail)
+__PAGEFLAG(Head, head, ANY) CLEARPAGEFLAG(Head, head, ANY)
+__PAGEFLAG(Tail, tail, ANY)
 
 static inline int PageCompound(struct page *page)
 {
@@ -421,8 +487,8 @@ static inline void ClearPageCompound(struct page *page)
  * because PageCompound is always set for compound pages and not for
  * pages on the LRU and/or pagecache.
  */
-TESTPAGEFLAG(Compound, compound)
-__SETPAGEFLAG(Head, compound)  __CLEARPAGEFLAG(Head, compound)
+TESTPAGEFLAG(Compound, compound, ANY)
+__SETPAGEFLAG(Head, compound, ANY)  __CLEARPAGEFLAG(Head, compound, ANY)
 
 /*
  * PG_reclaim is used in combination with PG_compound to mark the
@@ -636,6 +702,10 @@ static inline int page_has_private(struct page *page)
 	return !!(page->flags & PAGE_FLAGS_PRIVATE);
 }
 
+#undef ANY
+#undef HEAD
+#undef NO_TAIL
+#undef NO_COMPOUND
 #endif /* !__GENERATING_BOUNDS_H */
 
 #endif	/* PAGE_FLAGS_H */
-- 
2.1.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 04/16] page-flags: define PG_locked behavior on compound pages

[Kirill A. Shutemov]

lock_page() must operate on the whole compound page. It doesn't make
much sense to lock part of compound page. Change code to use head page's
PG_locked, if tail page is passed.

This patch also get rid of custom helprer functions --
__set_page_locked() and __clear_page_locked(). They replaced with
helpers generated by __SETPAGEFLAG/__CLEARPAGEFLAG. Tail pages to these
helper would trigger VM_BUG_ON().

SLUB uses PG_locked as a bit spin locked. IIUC, tail pages should never
appear there. VM_BUG_ON() is added to make sure that this assumption is
correct.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 fs/cifs/file.c             |  8 ++++----
 include/linux/page-flags.h |  2 +-
 include/linux/pagemap.h    | 25 ++++++++-----------------
 mm/filemap.c               | 15 +++++++++------
 mm/ksm.c                   |  2 +-
 mm/memory-failure.c        |  2 +-
 mm/migrate.c               |  2 +-
 mm/shmem.c                 |  4 ++--
 mm/slub.c                  |  2 ++
 mm/swap_state.c            |  4 ++--
 mm/vmscan.c                |  4 ++--
 mm/zswap.c                 |  4 ++--
 12 files changed, 35 insertions(+), 39 deletions(-)

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index ca30c391a894..b9fd85dfee9b 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3413,13 +3413,13 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
 	 * should have access to this page, we're safe to simply set
 	 * PG_locked without checking it first.
 	 */
-	__set_page_locked(page);
+	__SetPageLocked(page);
 	rc = add_to_page_cache_locked(page, mapping,
 				      page->index, GFP_KERNEL);
 
 	/* give up if we can't stick it in the cache */
 	if (rc) {
-		__clear_page_locked(page);
+		__ClearPageLocked(page);
 		return rc;
 	}
 
@@ -3440,10 +3440,10 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
 		if (*bytes + PAGE_CACHE_SIZE > rsize)
 			break;
 
-		__set_page_locked(page);
+		__SetPageLocked(page);
 		if (add_to_page_cache_locked(page, mapping, page->index,
 								GFP_KERNEL)) {
-			__clear_page_locked(page);
+			__ClearPageLocked(page);
 			break;
 		}
 		list_move_tail(&page->lru, tmplist);
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 32ea62c0ad30..10bdde20b14c 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -269,7 +269,7 @@ static inline struct page *compound_head_fast(struct page *page)
 	return page;
 }
 
-TESTPAGEFLAG(Locked, locked, ANY)
+__PAGEFLAG(Locked, locked, NO_TAIL)
 PAGEFLAG(Error, error, ANY) TESTCLEARFLAG(Error, error, ANY)
 PAGEFLAG(Referenced, referenced, ANY) TESTCLEARFLAG(Referenced, referenced, ANY)
 	__SETPAGEFLAG(Referenced, referenced, ANY)
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 4b3736f7065c..7c3790764795 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -426,18 +426,9 @@ extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
 				unsigned int flags);
 extern void unlock_page(struct page *page);
 
-static inline void __set_page_locked(struct page *page)
-{
-	__set_bit(PG_locked, &page->flags);
-}
-
-static inline void __clear_page_locked(struct page *page)
-{
-	__clear_bit(PG_locked, &page->flags);
-}
-
 static inline int trylock_page(struct page *page)
 {
+	page = compound_head(page);
 	return (likely(!test_and_set_bit_lock(PG_locked, &page->flags)));
 }
 
@@ -490,9 +481,9 @@ extern int wait_on_page_bit_killable_timeout(struct page *page,
 
 static inline int wait_on_page_locked_killable(struct page *page)
 {
-	if (PageLocked(page))
-		return wait_on_page_bit_killable(page, PG_locked);
-	return 0;
+	if (!PageLocked(page))
+		return 0;
+	return wait_on_page_bit_killable(compound_head(page), PG_locked);
 }
 
 extern wait_queue_head_t *page_waitqueue(struct page *page);
@@ -511,7 +502,7 @@ static inline void wake_up_page(struct page *page, int bit)
 static inline void wait_on_page_locked(struct page *page)
 {
 	if (PageLocked(page))
-		wait_on_page_bit(page, PG_locked);
+		wait_on_page_bit(compound_head(page), PG_locked);
 }
 
 /* 
@@ -656,17 +647,17 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask);
 
 /*
  * Like add_to_page_cache_locked, but used to add newly allocated pages:
- * the page is new, so we can just run __set_page_locked() against it.
+ * the page is new, so we can just run __SetPageLocked() against it.
  */
 static inline int add_to_page_cache(struct page *page,
 		struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask)
 {
 	int error;
 
-	__set_page_locked(page);
+	__SetPageLocked(page);
 	error = add_to_page_cache_locked(page, mapping, offset, gfp_mask);
 	if (unlikely(error))
-		__clear_page_locked(page);
+		__ClearPageLocked(page);
 	return error;
 }
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 12548d03c11d..467768d4263b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -615,11 +615,11 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 	void *shadow = NULL;
 	int ret;
 
-	__set_page_locked(page);
+	__SetPageLocked(page);
 	ret = __add_to_page_cache_locked(page, mapping, offset,
 					 gfp_mask, &shadow);
 	if (unlikely(ret))
-		__clear_page_locked(page);
+		__ClearPageLocked(page);
 	else {
 		/*
 		 * The page might have been evicted from cache only
@@ -742,6 +742,7 @@ EXPORT_SYMBOL_GPL(add_page_wait_queue);
  */
 void unlock_page(struct page *page)
 {
+	page = compound_head(page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	clear_bit_unlock(PG_locked, &page->flags);
 	smp_mb__after_atomic();
@@ -806,18 +807,20 @@ EXPORT_SYMBOL_GPL(page_endio);
  */
 void __lock_page(struct page *page)
 {
-	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
+	struct page *page_head = compound_head(page);
+	DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked);
 
-	__wait_on_bit_lock(page_waitqueue(page), &wait, bit_wait_io,
+	__wait_on_bit_lock(page_waitqueue(page_head), &wait, bit_wait_io,
 							TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(__lock_page);
 
 int __lock_page_killable(struct page *page)
 {
-	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
+	struct page *page_head = compound_head(page);
+	DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked);
 
-	return __wait_on_bit_lock(page_waitqueue(page), &wait,
+	return __wait_on_bit_lock(page_waitqueue(page_head), &wait,
 					bit_wait_io, TASK_KILLABLE);
 }
 EXPORT_SYMBOL_GPL(__lock_page_killable);
diff --git a/mm/ksm.c b/mm/ksm.c
index 4162dce2eb44..23138e99a531 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1884,7 +1884,7 @@ struct page *ksm_might_need_to_copy(struct page *page,
 
 		SetPageDirty(new_page);
 		__SetPageUptodate(new_page);
-		__set_page_locked(new_page);
+		__SetPageLocked(new_page);
 	}
 
 	return new_page;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index d487f8dc6d39..399eee44d13d 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1136,7 +1136,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	/*
 	 * We ignore non-LRU pages for good reasons.
 	 * - PG_locked is only well defined for LRU pages and a few others
-	 * - to avoid races with __set_page_locked()
+	 * - to avoid races with __SetPageLocked()
 	 * - to avoid races with __SetPageSlab*() (and more non-atomic ops)
 	 * The check (unnecessarily) ignores LRU pages being isolated and
 	 * walked by the page reclaim code, however that's not a big loss.
diff --git a/mm/migrate.c b/mm/migrate.c
index 6aa9a4222ea9..114602a68111 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1734,7 +1734,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 		flush_tlb_range(vma, mmun_start, mmun_end);
 
 	/* Prepare a page as a migration target */
-	__set_page_locked(new_page);
+	__SetPageLocked(new_page);
 	SetPageSwapBacked(new_page);
 
 	/* anon mapping, we can simply copy page->mapping to the new page: */
diff --git a/mm/shmem.c b/mm/shmem.c
index 80b360c7bcd1..2e2b943c8e62 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -981,7 +981,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 	copy_highpage(newpage, oldpage);
 	flush_dcache_page(newpage);
 
-	__set_page_locked(newpage);
+	__SetPageLocked(newpage);
 	SetPageUptodate(newpage);
 	SetPageSwapBacked(newpage);
 	set_page_private(newpage, swap_index);
@@ -1173,7 +1173,7 @@ repeat:
 		}
 
 		__SetPageSwapBacked(page);
-		__set_page_locked(page);
+		__SetPageLocked(page);
 		if (sgp == SGP_WRITE)
 			__SetPageReferenced(page);
 
diff --git a/mm/slub.c b/mm/slub.c
index 2584d4ff02eb..f33ae2b7a5e7 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -338,11 +338,13 @@ static inline int oo_objects(struct kmem_cache_order_objects x)
  */
 static __always_inline void slab_lock(struct page *page)
 {
+	VM_BUG_ON_PAGE(PageTail(page), page);
 	bit_spin_lock(PG_locked, &page->flags);
 }
 
 static __always_inline void slab_unlock(struct page *page)
 {
+	VM_BUG_ON_PAGE(PageTail(page), page);
 	__bit_spin_unlock(PG_locked, &page->flags);
 }
 
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 405923f77334..d1c4a25b4362 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -357,7 +357,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		}
 
 		/* May fail (-ENOMEM) if radix-tree node allocation failed. */
-		__set_page_locked(new_page);
+		__SetPageLocked(new_page);
 		SetPageSwapBacked(new_page);
 		err = __add_to_swap_cache(new_page, entry);
 		if (likely(!err)) {
@@ -371,7 +371,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		}
 		radix_tree_preload_end();
 		ClearPageSwapBacked(new_page);
-		__clear_page_locked(new_page);
+		__ClearPageLocked(new_page);
 		/*
 		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
 		 * clear SWAP_HAS_CACHE flag.
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 260c413d39cd..dc6cd51577a6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1062,7 +1062,7 @@ unmap:
 				VM_BUG_ON_PAGE(PageSwapCache(page), page);
 				if (!page_freeze_refs(page, 1))
 					goto keep_locked;
-				__clear_page_locked(page);
+				__ClearPageLocked(page);
 				count_vm_event(PGLAZYFREED);
 				goto free_it;
 			}
@@ -1174,7 +1174,7 @@ unmap:
 		 * we obviously don't have to worry about waking up a process
 		 * waiting on the page lock, because there are no references.
 		 */
-		__clear_page_locked(page);
+		__ClearPageLocked(page);
 free_it:
 		nr_reclaimed++;
 
diff --git a/mm/zswap.c b/mm/zswap.c
index 4249e82ff934..f8583f1fc938 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -490,7 +490,7 @@ static int zswap_get_swap_cache_page(swp_entry_t entry,
 		}
 
 		/* May fail (-ENOMEM) if radix-tree node allocation failed. */
-		__set_page_locked(new_page);
+		__SetPageLocked(new_page);
 		SetPageSwapBacked(new_page);
 		err = __add_to_swap_cache(new_page, entry);
 		if (likely(!err)) {
@@ -501,7 +501,7 @@ static int zswap_get_swap_cache_page(swp_entry_t entry,
 		}
 		radix_tree_preload_end();
 		ClearPageSwapBacked(new_page);
-		__clear_page_locked(new_page);
+		__ClearPageLocked(new_page);
 		/*
 		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
 		 * clear SWAP_HAS_CACHE flag.
-- 
2.1.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 05/16] page-flags: define behavior of FS/IO-related flags on compound pages

[Kirill A. Shutemov]

It seems we don't have compound page on FS/IO path currently. Use
NO_COMPOUND to catch if we have.

The odd expection is PG_dirty: sound uses compound pages and maps them
with PTEs. NO_COMPOUND triggers VM_BUG_ON() in set_page_dirty() on
handling shared fault. Let's use HEAD for PG_dirty.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 include/linux/page-flags.h | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 10bdde20b14c..df2493860821 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -270,16 +270,16 @@ static inline struct page *compound_head_fast(struct page *page)
 }
 
 __PAGEFLAG(Locked, locked, NO_TAIL)
-PAGEFLAG(Error, error, ANY) TESTCLEARFLAG(Error, error, ANY)
+PAGEFLAG(Error, error, NO_COMPOUND) TESTCLEARFLAG(Error, error, NO_COMPOUND)
 PAGEFLAG(Referenced, referenced, ANY) TESTCLEARFLAG(Referenced, referenced, ANY)
 	__SETPAGEFLAG(Referenced, referenced, ANY)
-PAGEFLAG(Dirty, dirty, ANY) TESTSCFLAG(Dirty, dirty, ANY)
-	__CLEARPAGEFLAG(Dirty, dirty, ANY)
+PAGEFLAG(Dirty, dirty, HEAD) TESTSCFLAG(Dirty, dirty, HEAD)
+	__CLEARPAGEFLAG(Dirty, dirty, HEAD)
 PAGEFLAG(LRU, lru, ANY) __CLEARPAGEFLAG(LRU, lru, ANY)
 PAGEFLAG(Active, active, ANY) __CLEARPAGEFLAG(Active, active, ANY)
 	TESTCLEARFLAG(Active, active, ANY)
 __PAGEFLAG(Slab, slab, ANY)
-PAGEFLAG(Checked, checked, ANY)		/* Used by some filesystems */
+PAGEFLAG(Checked, checked, NO_COMPOUND) /* Used by some filesystems */
 PAGEFLAG(Pinned, pinned, ANY) TESTSCFLAG(Pinned, pinned, ANY)	/* Xen */
 PAGEFLAG(SavePinned, savepinned, ANY);			/* Xen */
 PAGEFLAG(Foreign, foreign, ANY);				/* Xen */
@@ -305,12 +305,15 @@ PAGEFLAG(OwnerPriv1, owner_priv_1, ANY)
  * Only test-and-set exist for PG_writeback.  The unconditional operators are
  * risky: they bypass page accounting.
  */
-TESTPAGEFLAG(Writeback, writeback, ANY) TESTSCFLAG(Writeback, writeback, ANY)
-PAGEFLAG(MappedToDisk, mappedtodisk, ANY)
+TESTPAGEFLAG(Writeback, writeback, NO_COMPOUND)
+	TESTSCFLAG(Writeback, writeback, NO_COMPOUND)
+PAGEFLAG(MappedToDisk, mappedtodisk, NO_COMPOUND)
 
 /* PG_readahead is only used for reads; PG_reclaim is only for writes */
-PAGEFLAG(Reclaim, reclaim, ANY) TESTCLEARFLAG(Reclaim, reclaim, ANY)
-PAGEFLAG(Readahead, reclaim, ANY) TESTCLEARFLAG(Readahead, reclaim, ANY)
+PAGEFLAG(Reclaim, reclaim, NO_COMPOUND)
+	TESTCLEARFLAG(Reclaim, reclaim, NO_COMPOUND)
+PAGEFLAG(Readahead, reclaim, NO_COMPOUND)
+	TESTCLEARFLAG(Readahead, reclaim, NO_COMPOUND)
 
 #ifdef CONFIG_HIGHMEM
 /*
@@ -419,7 +422,7 @@ static inline int PageUptodate(struct page *page)
 static inline void __SetPageUptodate(struct page *page)
 {
 	smp_wmb();
-	__set_bit(PG_uptodate, &(page)->flags);
+	__set_bit(PG_uptodate, &page->flags);
 }
 
 static inline void SetPageUptodate(struct page *page)
@@ -430,7 +433,7 @@ static inline void SetPageUptodate(struct page *page)
 	 * uptodate are actually visible before PageUptodate becomes true.
 	 */
 	smp_wmb();
-	set_bit(PG_uptodate, &(page)->flags);
+	set_bit(PG_uptodate, &page->flags);
 }
 
 CLEARPAGEFLAG(Uptodate, uptodate, ANY)
-- 
2.1.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 06/16] page-flags: define behavior of LRU-related flags on compound pages

[Kirill A. Shutemov]

Only head pages are ever on LRU. Let's use HEAD policy to avoid any
confusion for all LRU-related flags.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 include/linux/page-flags.h | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index df2493860821..bdb0d0e226c4 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -271,13 +271,14 @@ static inline struct page *compound_head_fast(struct page *page)
 
 __PAGEFLAG(Locked, locked, NO_TAIL)
 PAGEFLAG(Error, error, NO_COMPOUND) TESTCLEARFLAG(Error, error, NO_COMPOUND)
-PAGEFLAG(Referenced, referenced, ANY) TESTCLEARFLAG(Referenced, referenced, ANY)
-	__SETPAGEFLAG(Referenced, referenced, ANY)
+PAGEFLAG(Referenced, referenced, HEAD)
+	TESTCLEARFLAG(Referenced, referenced, HEAD)
+	__SETPAGEFLAG(Referenced, referenced, HEAD)
 PAGEFLAG(Dirty, dirty, HEAD) TESTSCFLAG(Dirty, dirty, HEAD)
 	__CLEARPAGEFLAG(Dirty, dirty, HEAD)
-PAGEFLAG(LRU, lru, ANY) __CLEARPAGEFLAG(LRU, lru, ANY)
-PAGEFLAG(Active, active, ANY) __CLEARPAGEFLAG(Active, active, ANY)
-	TESTCLEARFLAG(Active, active, ANY)
+PAGEFLAG(LRU, lru, HEAD) __CLEARPAGEFLAG(LRU, lru, HEAD)
+PAGEFLAG(Active, active, HEAD) __CLEARPAGEFLAG(Active, active, HEAD)
+	TESTCLEARFLAG(Active, active, HEAD)
 __PAGEFLAG(Slab, slab, ANY)
 PAGEFLAG(Checked, checked, NO_COMPOUND) /* Used by some filesystems */
 PAGEFLAG(Pinned, pinned, ANY) TESTSCFLAG(Pinned, pinned, ANY)	/* Xen */
@@ -331,9 +332,9 @@ PAGEFLAG(SwapCache, swapcache, ANY)
 PAGEFLAG_FALSE(SwapCache)
 #endif
 
-PAGEFLAG(Unevictable, unevictable, ANY)
-	__CLEARPAGEFLAG(Unevictable, unevictable, ANY)
-	TESTCLEARFLAG(Unevictable, unevictable, ANY)
+PAGEFLAG(Unevictable, unevictable, HEAD)
+	__CLEARPAGEFLAG(Unevictable, unevictable, HEAD)
+	TESTCLEARFLAG(Unevictable, unevictable, HEAD)
 
 #ifdef CONFIG_MMU
 PAGEFLAG(Mlocked, mlocked, ANY) __CLEARPAGEFLAG(Mlocked, mlocked, ANY)
-- 
2.1.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 07/16] page-flags: define behavior SL*B-related flags on compound pages

[Kirill A. Shutemov]

SL*B uses compound pages and marks head pages with PG_slab.
__SetPageSlab() and __ClearPageSlab() are never called for tail pages.

The same situation with PG_slob_free in SLOB allocator.

NO_TAIL is appropriate for these flags.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 include/linux/page-flags.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index bdb0d0e226c4..d41c63b566b8 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -279,7 +279,8 @@ PAGEFLAG(Dirty, dirty, HEAD) TESTSCFLAG(Dirty, dirty, HEAD)
 PAGEFLAG(LRU, lru, HEAD) __CLEARPAGEFLAG(LRU, lru, HEAD)
 PAGEFLAG(Active, active, HEAD) __CLEARPAGEFLAG(Active, active, HEAD)
 	TESTCLEARFLAG(Active, active, HEAD)
-__PAGEFLAG(Slab, slab, ANY)
+__PAGEFLAG(Slab, slab, NO_TAIL)
+__PAGEFLAG(SlobFree, slob_free, NO_TAIL)
 PAGEFLAG(Checked, checked, NO_COMPOUND) /* Used by some filesystems */
 PAGEFLAG(Pinned, pinned, ANY) TESTSCFLAG(Pinned, pinned, ANY)	/* Xen */
 PAGEFLAG(SavePinned, savepinned, ANY);			/* Xen */
@@ -289,8 +290,6 @@ PAGEFLAG(SwapBacked, swapbacked, ANY)
 	__CLEARPAGEFLAG(SwapBacked, swapbacked, ANY)
 	__SETPAGEFLAG(SwapBacked, swapbacked, ANY)
 
-__PAGEFLAG(SlobFree, slob_free, ANY)
-
 /*
  * Private page markings that may be used by the filesystem that owns the page
  * for its own purposes.
-- 
2.1.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 08/16] page-flags: define behavior of Xen-related flags on compound pages

[Kirill A. Shutemov]

PG_pinned and PG_savepinned are about page table's pages which are never
compound.

I'm not so sure about PG_foreign, but it seems we shouldn't see compound
pages there too.

Let's use NO_COMPOUND for all of them.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 include/linux/page-flags.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index d41c63b566b8..19373c98d08a 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -282,9 +282,12 @@ PAGEFLAG(Active, active, HEAD) __CLEARPAGEFLAG(Active, active, HEAD)
 __PAGEFLAG(Slab, slab, NO_TAIL)
 __PAGEFLAG(SlobFree, slob_free, NO_TAIL)
 PAGEFLAG(Checked, checked, NO_COMPOUND) /* Used by some filesystems */
-PAGEFLAG(Pinned, pinned, ANY) TESTSCFLAG(Pinned, pinned, ANY)	/* Xen */
-PAGEFLAG(SavePinned, savepinned, ANY);			/* Xen */
-PAGEFLAG(Foreign, foreign, ANY);				/* Xen */
+
+/* Xen */
+PAGEFLAG(Pinned, pinned, NO_COMPOUND) TESTSCFLAG(Pinned, pinned, NO_COMPOUND)
+PAGEFLAG(SavePinned, savepinned, NO_COMPOUND)
+PAGEFLAG(Foreign, foreign, NO_COMPOUND)
+
 PAGEFLAG(Reserved, reserved, ANY) __CLEARPAGEFLAG(Reserved, reserved, ANY)
 PAGEFLAG(SwapBacked, swapbacked, ANY)
 	__CLEARPAGEFLAG(SwapBacked, swapbacked, ANY)
-- 
2.1.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 09/16] page-flags: define PG_reserved behavior on compound pages

[Kirill A. Shutemov]

As far as I can see there's no users of PG_reserved on compound pages.
Let's use NO_COMPOUND here.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 include/linux/page-flags.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 19373c98d08a..be691551896b 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -288,7 +288,8 @@ PAGEFLAG(Pinned, pinned, NO_COMPOUND) TESTSCFLAG(Pinned, pinned, NO_COMPOUND)
 PAGEFLAG(SavePinned, savepinned, NO_COMPOUND)
 PAGEFLAG(Foreign, foreign, NO_COMPOUND)
 
-PAGEFLAG(Reserved, reserved, ANY) __CLEARPAGEFLAG(Reserved, reserved, ANY)
+PAGEFLAG(Reserved, reserved, NO_COMPOUND)
+	__CLEARPAGEFLAG(Reserved, reserved, NO_COMPOUND)
 PAGEFLAG(SwapBacked, swapbacked, ANY)
 	__CLEARPAGEFLAG(SwapBacked, swapbacked, ANY)
 	__SETPAGEFLAG(SwapBacked, swapbacked, ANY)
-- 
2.1.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 10/16] page-flags: define PG_swapbacked behavior on compound pages

[Kirill A. Shutemov]

PG_swapbacked is used for transparent huge pages. For head pages only.
Let's use NO_TAIL policy.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 include/linux/page-flags.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index be691551896b..d1d08508984d 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -290,9 +290,9 @@ PAGEFLAG(Foreign, foreign, NO_COMPOUND)
 
 PAGEFLAG(Reserved, reserved, NO_COMPOUND)
 	__CLEARPAGEFLAG(Reserved, reserved, NO_COMPOUND)
-PAGEFLAG(SwapBacked, swapbacked, ANY)
-	__CLEARPAGEFLAG(SwapBacked, swapbacked, ANY)
-	__SETPAGEFLAG(SwapBacked, swapbacked, ANY)
+PAGEFLAG(SwapBacked, swapbacked, NO_TAIL)
+	__CLEARPAGEFLAG(SwapBacked, swapbacked, NO_TAIL)
+	__SETPAGEFLAG(SwapBacked, swapbacked, NO_TAIL)
 
 /*
  * Private page markings that may be used by the filesystem that owns the page
-- 
2.1.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 11/16] page-flags: define PG_swapcache behavior on compound pages

[Kirill A. Shutemov]

Swap cannot handle compound pages so far. Transparent huge pages are
split on the way to swap.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 include/linux/page-flags.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index d1d08508984d..9ea90bb8cb89 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -330,7 +330,7 @@ PAGEFLAG_FALSE(HighMem)
 #endif
 
 #ifdef CONFIG_SWAP
-PAGEFLAG(SwapCache, swapcache, ANY)
+PAGEFLAG(SwapCache, swapcache, NO_COMPOUND)
 #else
 PAGEFLAG_FALSE(SwapCache)
 #endif
-- 
2.1.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 12/16] page-flags: define PG_mlocked behavior on compound pages

[Kirill A. Shutemov]

Transparent huge pages can be mlocked -- whole compund page at once.
Something went wrong if we're trying to mlock() tail page.
Let's use NO_TAIL.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 include/linux/page-flags.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 9ea90bb8cb89..a1ecec3f505f 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -340,8 +340,9 @@ PAGEFLAG(Unevictable, unevictable, HEAD)
 	TESTCLEARFLAG(Unevictable, unevictable, HEAD)
 
 #ifdef CONFIG_MMU
-PAGEFLAG(Mlocked, mlocked, ANY) __CLEARPAGEFLAG(Mlocked, mlocked, ANY)
-	TESTSCFLAG(Mlocked, mlocked, ANY) __TESTCLEARFLAG(Mlocked, mlocked, ANY)
+PAGEFLAG(Mlocked, mlocked, NO_TAIL) __CLEARPAGEFLAG(Mlocked, mlocked, NO_TAIL)
+	TESTSCFLAG(Mlocked, mlocked, NO_TAIL)
+	__TESTCLEARFLAG(Mlocked, mlocked, NO_TAIL)
 #else
 PAGEFLAG_FALSE(Mlocked) __CLEARPAGEFLAG_NOOP(Mlocked)
 	TESTSCFLAG_FALSE(Mlocked) __TESTCLEARFLAG_FALSE(Mlocked)
-- 
2.1.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 13/16] page-flags: define PG_uncached behavior on compound pages

[Kirill A. Shutemov]

So far, only IA64 uses PG_uncached and only on non-compound pages.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 include/linux/page-flags.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index a1ecec3f505f..0b6921d2f2f3 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -349,7 +349,7 @@ PAGEFLAG_FALSE(Mlocked) __CLEARPAGEFLAG_NOOP(Mlocked)
 #endif
 
 #ifdef CONFIG_ARCH_USES_PG_UNCACHED
-PAGEFLAG(Uncached, uncached, ANY)
+PAGEFLAG(Uncached, uncached, NO_COMPOUND)
 #else
 PAGEFLAG_FALSE(Uncached)
 #endif
-- 
2.1.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 14/16] page-flags: define PG_uptodate behavior on compound pages

[Kirill A. Shutemov]

We use PG_uptodate on head pages on transparent huge page.
Let's use NO_TAIL.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 include/linux/page-flags.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 0b6921d2f2f3..55a69c40e4ae 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -408,8 +408,9 @@ u64 stable_page_flags(struct page *page);
 
 static inline int PageUptodate(struct page *page)
 {
-	int ret = test_bit(PG_uptodate, &(page)->flags);
-
+	int ret;
+	page = compound_head(page);
+	ret = test_bit(PG_uptodate, &(page)->flags);
 	/*
 	 * Must ensure that the data we read out of the page is loaded
 	 * _after_ we've loaded page->flags to check for PageUptodate.
@@ -426,12 +427,14 @@ static inline int PageUptodate(struct page *page)
 
 static inline void __SetPageUptodate(struct page *page)
 {
+	VM_BUG_ON_PAGE(PageTail(page), page);
 	smp_wmb();
 	__set_bit(PG_uptodate, &page->flags);
 }
 
 static inline void SetPageUptodate(struct page *page)
 {
+	VM_BUG_ON_PAGE(PageTail(page), page);
 	/*
 	 * Memory barrier must be issued before setting the PG_uptodate bit,
 	 * so that all previous stores issued in order to bring the page
@@ -441,7 +444,7 @@ static inline void SetPageUptodate(struct page *page)
 	set_bit(PG_uptodate, &page->flags);
 }
 
-CLEARPAGEFLAG(Uptodate, uptodate, ANY)
+CLEARPAGEFLAG(Uptodate, uptodate, NO_TAIL)
 
 int test_clear_page_writeback(struct page *page);
 int __test_set_page_writeback(struct page *page, bool keep_write);
-- 
2.1.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 15/16] page-flags: look on head page if the flag is encoded in page->mapping

[Kirill A. Shutemov]

PageAnon() and PageKsm() look on lower bits of page->mapping to check if
the page is Anon or KSM. page->mapping can be overloaded in tail pages.

Let's always look on head page to avoid false-positives.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 include/linux/page-flags.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 55a69c40e4ae..07fa2781df23 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -385,6 +385,7 @@ PAGEFLAG_FALSE(HWPoison)
 
 static inline int PageAnon(struct page *page)
 {
+	page = compound_head(page);
 	return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
 }
 
@@ -397,6 +398,7 @@ static inline int PageAnon(struct page *page)
  */
 static inline int PageKsm(struct page *page)
 {
+	page = compound_head(page);
 	return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) ==
 				(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM);
 }
-- 
2.1.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 16/16] mm: sanitize page->mapping for tail pages

[Kirill A. Shutemov]

We don't define meaning of page->mapping for tail pages. Currently it's
always NULL, which can be inconsistent with head page and potentially
lead to problems.

Let's poison the pointer to catch all illigal uses.

page_rmapping() and page_mapping() are changed to look on head page.

The only illigal use I've catched so far is __GPF_COMP pages from sound
subsystem, mapped with PTEs. do_shared_fault() is changed to use
page_rmapping() instead of direct access to fault_page->mapping.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 include/linux/mm.h     | 1 +
 include/linux/poison.h | 4 ++++
 mm/huge_memory.c       | 2 +-
 mm/memory.c            | 2 +-
 mm/page_alloc.c        | 7 +++++++
 mm/util.c              | 5 ++++-
 6 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index bcf37dacbee3..4a3a38522ab4 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -915,6 +915,7 @@ extern struct address_space *page_mapping(struct page *page);
 /* Neutral page->mapping pointer to address_space or anon_vma or other */
 static inline void *page_rmapping(struct page *page)
 {
+	page = compound_head(page);
 	return (void *)((unsigned long)page->mapping & ~PAGE_MAPPING_FLAGS);
 }
 
diff --git a/include/linux/poison.h b/include/linux/poison.h
index 2110a81c5e2a..7b2a7fcde6a3 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -32,6 +32,10 @@
 /********** mm/debug-pagealloc.c **********/
 #define PAGE_POISON 0xaa
 
+/********** mm/page_alloc.c ************/
+
+#define TAIL_MAPPING	((void *) 0x01014A11 + POISON_POINTER_DELTA)
+
 /********** mm/slab.c **********/
 /*
  * Magic nums for obj red zoning.
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 3412cc8a4bd4..54d90ed2d31b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1739,7 +1739,7 @@ static void __split_huge_page_refcount(struct page *page,
 		*/
 		page_tail->_mapcount = page->_mapcount;
 
-		BUG_ON(page_tail->mapping);
+		BUG_ON(page_tail->mapping != TAIL_MAPPING);
 		page_tail->mapping = page->mapping;
 
 		page_tail->index = page->index + i;
diff --git a/mm/memory.c b/mm/memory.c
index 5ec794f13f8a..a76f61aa88da 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3033,7 +3033,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * pinned by vma->vm_file's reference.  We rely on unlock_page()'s
 	 * release semantics to prevent the compiler from undoing this copying.
 	 */
-	mapping = fault_page->mapping;
+	mapping = page_rmapping(fault_page);
 	unlock_page(fault_page);
 	if ((dirtied || vma->vm_ops->page_mkwrite) && mapping) {
 		/*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1b849500640c..e73ecbbfa69f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -373,6 +373,7 @@ void prep_compound_page(struct page *page, unsigned long order)
 	for (i = 1; i < nr_pages; i++) {
 		struct page *p = page + i;
 		set_page_count(p, 0);
+		p->mapping = TAIL_MAPPING;
 		p->first_page = page;
 		/* Make sure p->first_page is always valid for PageTail() */
 		smp_wmb();
@@ -765,6 +766,12 @@ static void free_one_page(struct zone *zone,
 
 static int free_tail_pages_check(struct page *head_page, struct page *page)
 {
+	if (page->mapping != TAIL_MAPPING) {
+		bad_page(page, "corrupted mapping in tail page", 0);
+		page->mapping = NULL;
+		return 1;
+	}
+	page->mapping = NULL;
 	if (!IS_ENABLED(CONFIG_DEBUG_VM))
 		return 0;
 	if (unlikely(!PageTail(page))) {
diff --git a/mm/util.c b/mm/util.c
index d68339206100..769a7a2870af 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -357,7 +357,10 @@ EXPORT_SYMBOL(kvfree);
 
 struct address_space *page_mapping(struct page *page)
 {
-	struct address_space *mapping = page->mapping;
+	struct address_space *mapping;
+
+	page = compound_head(page);
+	mapping = page->mapping;
 
 	/* This happens if someone calls flush_dcache_page on slab page */
 	if (unlikely(PageSlab(page)))
-- 
2.1.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 05/16] page-flags: define behavior of FS/IO-related flags on compound pages

[Dave Hansen]

On 03/19/2015 10:08 AM, Kirill A. Shutemov wrote:
> The odd expection is PG_dirty: sound uses compound pages and maps them
> with PTEs. NO_COMPOUND triggers VM_BUG_ON() in set_page_dirty() on
> handling shared fault. Let's use HEAD for PG_dirty.

Can we get the sound guys to look at this, btw?  It seems like an odd
thing that we probably don't want to keep around, right?

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 05/16] page-flags: define behavior of FS/IO-related flags on compound pages

[Kirill A. Shutemov]

On Thu, Mar 19, 2015 at 11:29:52AM -0700, Dave Hansen wrote:
> On 03/19/2015 10:08 AM, Kirill A. Shutemov wrote:
> > The odd exception is PG_dirty: sound uses compound pages and maps them
> > with PTEs. NO_COMPOUND triggers VM_BUG_ON() in set_page_dirty() on
> > handling shared fault. Let's use HEAD for PG_dirty.
> 
> Can we get the sound guys to look at this, btw?  It seems like an odd
> thing that we probably don't want to keep around, right?

CC: +sound guys

I'm not sure what is right fix here. At the time adding __GFP_COMP was a
fix: see f3d48f0373c1.

Other odd part about __GFP_COMP here is that we have ->_mapcount in tail
pages to be used for both: mapcount of the individual page and for gup
pins. __compound_tail_refcounted() doesn't recognize that we don't need
tail page accounting for these pages.

Hugh, I tried to ask you about the situation several times (last time on
the summit). Any comments?

-- 
 Kirill A. Shutemov

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 03/16] page-flags: introduce page flags policies wrt compound pages

[Andrew Morton]

On Thu, 19 Mar 2015 19:08:09 +0200 "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> wrote:

> This patch third argument to macros which create function definitions
> for page flags. This arguments defines how page-flags helpers behave
> on compound functions.
> 
> For now we define four policies:
> 
>  - ANY: the helper function operates on the page it gets, regardless if
>    it's non-compound, head or tail.
> 
>  - HEAD: the helper function operates on the head page of the compound
>    page if it gets tail page.
> 
>  - NO_TAIL: only head and non-compond pages are acceptable for this
>    helper function.
> 
>  - NO_COMPOUND: only non-compound pages are acceptable for this helper
>    function.
> 
> For now we use policy ANY for all helpers, which match current
> behaviour.
> 
> We do not enforce the policy for TESTPAGEFLAG, because we have flags
> checked for random pages all over the kernel. Noticeable exception to
> this is PageTransHuge() which triggers VM_BUG_ON() for tail page.
> 
> +/* Page flags policies wrt compound pages */
> +#define ANY(page, enforce)	page
> +#define HEAD(page, enforce)	compound_head(page)
> +#define NO_TAIL(page, enforce) ({					\
> +#define NO_COMPOUND(page, enforce) ({					\
> ...
>
> +#undef ANY
> +#undef HEAD
> +#undef NO_TAIL
> +#undef NO_COMPOUND
>  #endif /* !__GENERATING_BOUNDS_H */

This is risky - there are existing definitions of ANY and HEAD, and
this code may go and undefine them.  This is improbable at present, as
those definitions are in .c, after all includes.  But still, it's not
good to chew off great hunks of the namespace like this.

So I think I'll prefix all these with "PF_", OK?

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 03/16] page-flags: introduce page flags policies wrt compound pages

[Kirill A. Shutemov]

On Fri, Mar 20, 2015 at 01:35:53PM -0700, Andrew Morton wrote:
> On Thu, 19 Mar 2015 19:08:09 +0200 "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> wrote:
> 
> > This patch third argument to macros which create function definitions
> > for page flags. This arguments defines how page-flags helpers behave
> > on compound functions.
> > 
> > For now we define four policies:
> > 
> >  - ANY: the helper function operates on the page it gets, regardless if
> >    it's non-compound, head or tail.
> > 
> >  - HEAD: the helper function operates on the head page of the compound
> >    page if it gets tail page.
> > 
> >  - NO_TAIL: only head and non-compond pages are acceptable for this
> >    helper function.
> > 
> >  - NO_COMPOUND: only non-compound pages are acceptable for this helper
> >    function.
> > 
> > For now we use policy ANY for all helpers, which match current
> > behaviour.
> > 
> > We do not enforce the policy for TESTPAGEFLAG, because we have flags
> > checked for random pages all over the kernel. Noticeable exception to
> > this is PageTransHuge() which triggers VM_BUG_ON() for tail page.
> > 
> > +/* Page flags policies wrt compound pages */
> > +#define ANY(page, enforce)	page
> > +#define HEAD(page, enforce)	compound_head(page)
> > +#define NO_TAIL(page, enforce) ({					\
> > +#define NO_COMPOUND(page, enforce) ({					\
> > ...
> >
> > +#undef ANY
> > +#undef HEAD
> > +#undef NO_TAIL
> > +#undef NO_COMPOUND
> >  #endif /* !__GENERATING_BOUNDS_H */
> 
> This is risky - there are existing definitions of ANY and HEAD, and
> this code may go and undefine them.  This is improbable at present, as
> those definitions are in .c, after all includes.  But still, it's not
> good to chew off great hunks of the namespace like this.
> 
> So I think I'll prefix all these with "PF_", OK?

Yeah. That's fine.

-- 
 Kirill A. Shutemov

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 05/16] page-flags: define behavior of FS/IO-related flags on compound pages

[Hugh Dickins]

On Thu, 19 Mar 2015, Kirill A. Shutemov wrote:
> On Thu, Mar 19, 2015 at 11:29:52AM -0700, Dave Hansen wrote:
> > On 03/19/2015 10:08 AM, Kirill A. Shutemov wrote:
> > > The odd exception is PG_dirty: sound uses compound pages and maps them
> > > with PTEs. NO_COMPOUND triggers VM_BUG_ON() in set_page_dirty() on
> > > handling shared fault. Let's use HEAD for PG_dirty.

It really depends on what you do with PageDirty of the head, when you
get to support 4k pagecache with subpages of a huge compound page.

HEAD will be fine, so long as PageDirty on the head means the whole
huge page must be written back.  I expect that's what you will choose;
but one could consider that if a huge page is only mapped read-only,
but a few subpages of it writable, then only the few need be written
back, in which case ANY would be more appropriate.  NO_COMPOUND is
certainly wrong.

But that does illustrate that I consider this patch series premature:
it belongs with your huge pagecache implementation.  You seem to be
"tidying up" and adding overhead to things that are fine as they are.

> > 
> > Can we get the sound guys to look at this, btw?  It seems like an odd
> > thing that we probably don't want to keep around, right?
> 
> CC: +sound guys

I don't think this is peculiar to sound at all: there are other users
of __GFP_COMP in the tree, aren't there?  And although some of them
might turn out not to need it any more, I expect most of them still
need it for the same reason they did originally.

> 
> I'm not sure what is right fix here. At the time adding __GFP_COMP was a
> fix: see f3d48f0373c1.

The only thing special about this one, was that I failed to add
__GFP_COMP at first.

The purpose of __GFP_COMP is to allow a >0-order page (originally, just
a hugetlb page: see 2.5.60) to be mapped into userspace, and parts of it
then subjected to get_user_pages (ptrace, futex, direct I/O, infiniband
etc), and now even munmap, without destroying the integrity of the
underlying >0-order page.

We don't bother with __GFP_COMP when a >0-order page cannot be mapped
into userspace (except through /dev/mem or suchlike); we add __GFP_COMP
when it might be, to get the right reference counting.

It's normal for set_page_dirty() to be called in the course of
get_user_pages(), and it's normal for set_page_dirty() to be called
when releasing the get_user_pages() references, and it's normal for
set_page_dirty() to be called when munmap'ing a pte_dirty().

> 
> Other odd part about __GFP_COMP here is that we have ->_mapcount in tail
> pages to be used for both: mapcount of the individual page and for gup
> pins. __compound_tail_refcounted() doesn't recognize that we don't need
> tail page accounting for these pages.

So page->_mapcount of the tails is being used for both their mapcount
and their reference count: that's certainly funny, and further reason
to pursue your aim of simplifying the way THPs are refcounted.  But
not responsible for any actual bug, I think?

> 
> Hugh, I tried to ask you about the situation several times (last time on
> the summit). Any comments?

I do remember we began a curtailed conversation about this at LSF/MM.
I do not remember you asking about it earlier: when was that?

Hugh

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 01/16] mm: consolidate all page-flags helpers in <linux/page-flags.h>

[Hugh Dickins]

On Thu, 19 Mar 2015, Kirill A. Shutemov wrote:

> We have page-flags helper function declarations/definitions spread over
> several header files. Let's consolidate them in <linux/page-flags.h>.
> 
> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>

Acked-by: Hugh Dickins <hughd@google.com>

I find this one helpful (assuming it builds fine everywhere).  I've
several times recently found myself wanting to use PageAnon tests at a low
level, and been frustrated by its positioning in linux/mm.h (see my 10/24).

> ---
>  include/linux/hugetlb.h    |  7 ----
>  include/linux/ksm.h        | 17 --------
>  include/linux/mm.h         | 81 --------------------------------------
>  include/linux/page-flags.h | 96 ++++++++++++++++++++++++++++++++++++++++++++++
>  4 files changed, 96 insertions(+), 105 deletions(-)
> 
> diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
> index 7b5785032049..1a782733a420 100644
> --- a/include/linux/hugetlb.h
> +++ b/include/linux/hugetlb.h
> @@ -41,8 +41,6 @@ extern int hugetlb_max_hstate __read_mostly;
>  struct hugepage_subpool *hugepage_new_subpool(long nr_blocks);
>  void hugepage_put_subpool(struct hugepage_subpool *spool);
>  
> -int PageHuge(struct page *page);
> -
>  void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
>  int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
>  int hugetlb_overcommit_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
> @@ -109,11 +107,6 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
>  
>  #else /* !CONFIG_HUGETLB_PAGE */
>  
> -static inline int PageHuge(struct page *page)
> -{
> -	return 0;
> -}
> -
>  static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
>  {
>  }
> diff --git a/include/linux/ksm.h b/include/linux/ksm.h
> index 3be6bb18562d..7ae216a39c9e 100644
> --- a/include/linux/ksm.h
> +++ b/include/linux/ksm.h
> @@ -35,18 +35,6 @@ static inline void ksm_exit(struct mm_struct *mm)
>  		__ksm_exit(mm);
>  }
>  
> -/*
> - * A KSM page is one of those write-protected "shared pages" or "merged pages"
> - * which KSM maps into multiple mms, wherever identical anonymous page content
> - * is found in VM_MERGEABLE vmas.  It's a PageAnon page, pointing not to any
> - * anon_vma, but to that page's node of the stable tree.
> - */
> -static inline int PageKsm(struct page *page)
> -{
> -	return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) ==
> -				(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM);
> -}
> -
>  static inline struct stable_node *page_stable_node(struct page *page)
>  {
>  	return PageKsm(page) ? page_rmapping(page) : NULL;
> @@ -87,11 +75,6 @@ static inline void ksm_exit(struct mm_struct *mm)
>  {
>  }
>  
> -static inline int PageKsm(struct page *page)
> -{
> -	return 0;
> -}
> -
>  #ifdef CONFIG_MMU
>  static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
>  		unsigned long end, int advice, unsigned long *vm_flags)
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 6571dd78e984..fb1fc38b01ce 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -494,15 +494,6 @@ static inline int page_count(struct page *page)
>  	return atomic_read(&compound_head(page)->_count);
>  }
>  
> -#ifdef CONFIG_HUGETLB_PAGE
> -extern int PageHeadHuge(struct page *page_head);
> -#else /* CONFIG_HUGETLB_PAGE */
> -static inline int PageHeadHuge(struct page *page_head)
> -{
> -	return 0;
> -}
> -#endif /* CONFIG_HUGETLB_PAGE */
> -
>  static inline bool __compound_tail_refcounted(struct page *page)
>  {
>  	return !PageSlab(page) && !PageHeadHuge(page);
> @@ -571,53 +562,6 @@ static inline void init_page_count(struct page *page)
>  	atomic_set(&page->_count, 1);
>  }
>  
> -/*
> - * PageBuddy() indicate that the page is free and in the buddy system
> - * (see mm/page_alloc.c).
> - *
> - * PAGE_BUDDY_MAPCOUNT_VALUE must be <= -2 but better not too close to
> - * -2 so that an underflow of the page_mapcount() won't be mistaken
> - * for a genuine PAGE_BUDDY_MAPCOUNT_VALUE. -128 can be created very
> - * efficiently by most CPU architectures.
> - */
> -#define PAGE_BUDDY_MAPCOUNT_VALUE (-128)
> -
> -static inline int PageBuddy(struct page *page)
> -{
> -	return atomic_read(&page->_mapcount) == PAGE_BUDDY_MAPCOUNT_VALUE;
> -}
> -
> -static inline void __SetPageBuddy(struct page *page)
> -{
> -	VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page);
> -	atomic_set(&page->_mapcount, PAGE_BUDDY_MAPCOUNT_VALUE);
> -}
> -
> -static inline void __ClearPageBuddy(struct page *page)
> -{
> -	VM_BUG_ON_PAGE(!PageBuddy(page), page);
> -	atomic_set(&page->_mapcount, -1);
> -}
> -
> -#define PAGE_BALLOON_MAPCOUNT_VALUE (-256)
> -
> -static inline int PageBalloon(struct page *page)
> -{
> -	return atomic_read(&page->_mapcount) == PAGE_BALLOON_MAPCOUNT_VALUE;
> -}
> -
> -static inline void __SetPageBalloon(struct page *page)
> -{
> -	VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page);
> -	atomic_set(&page->_mapcount, PAGE_BALLOON_MAPCOUNT_VALUE);
> -}
> -
> -static inline void __ClearPageBalloon(struct page *page)
> -{
> -	VM_BUG_ON_PAGE(!PageBalloon(page), page);
> -	atomic_set(&page->_mapcount, -1);
> -}
> -
>  void put_page(struct page *page);
>  void put_pages_list(struct list_head *pages);
>  
> @@ -1006,26 +950,6 @@ void page_address_init(void);
>  #define page_address_init()  do { } while(0)
>  #endif
>  
> -/*
> - * On an anonymous page mapped into a user virtual memory area,
> - * page->mapping points to its anon_vma, not to a struct address_space;
> - * with the PAGE_MAPPING_ANON bit set to distinguish it.  See rmap.h.
> - *
> - * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled,
> - * the PAGE_MAPPING_KSM bit may be set along with the PAGE_MAPPING_ANON bit;
> - * and then page->mapping points, not to an anon_vma, but to a private
> - * structure which KSM associates with that merged page.  See ksm.h.
> - *
> - * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is currently never used.
> - *
> - * Please note that, confusingly, "page_mapping" refers to the inode
> - * address_space which maps the page from disk; whereas "page_mapped"
> - * refers to user virtual address space into which the page is mapped.
> - */
> -#define PAGE_MAPPING_ANON	1
> -#define PAGE_MAPPING_KSM	2
> -#define PAGE_MAPPING_FLAGS	(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM)
> -
>  extern struct address_space *page_mapping(struct page *page);
>  
>  /* Neutral page->mapping pointer to address_space or anon_vma or other */
> @@ -1045,11 +969,6 @@ struct address_space *page_file_mapping(struct page *page)
>  	return page->mapping;
>  }
>  
> -static inline int PageAnon(struct page *page)
> -{
> -	return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
> -}
> -
>  /*
>   * Return the pagecache index of the passed page.  Regular pagecache pages
>   * use ->index whereas swapcache pages use ->private
> diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
> index c851ff92d5b3..84d10b65cec6 100644
> --- a/include/linux/page-flags.h
> +++ b/include/linux/page-flags.h
> @@ -289,6 +289,47 @@ PAGEFLAG_FALSE(HWPoison)
>  #define __PG_HWPOISON 0
>  #endif
>  
> +/*
> + * On an anonymous page mapped into a user virtual memory area,
> + * page->mapping points to its anon_vma, not to a struct address_space;
> + * with the PAGE_MAPPING_ANON bit set to distinguish it.  See rmap.h.
> + *
> + * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled,
> + * the PAGE_MAPPING_KSM bit may be set along with the PAGE_MAPPING_ANON bit;
> + * and then page->mapping points, not to an anon_vma, but to a private
> + * structure which KSM associates with that merged page.  See ksm.h.
> + *
> + * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is currently never used.
> + *
> + * Please note that, confusingly, "page_mapping" refers to the inode
> + * address_space which maps the page from disk; whereas "page_mapped"
> + * refers to user virtual address space into which the page is mapped.
> + */
> +#define PAGE_MAPPING_ANON	1
> +#define PAGE_MAPPING_KSM	2
> +#define PAGE_MAPPING_FLAGS	(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM)
> +
> +static inline int PageAnon(struct page *page)
> +{
> +	return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
> +}
> +
> +#ifdef CONFIG_KSM
> +/*
> + * A KSM page is one of those write-protected "shared pages" or "merged pages"
> + * which KSM maps into multiple mms, wherever identical anonymous page content
> + * is found in VM_MERGEABLE vmas.  It's a PageAnon page, pointing not to any
> + * anon_vma, but to that page's node of the stable tree.
> + */
> +static inline int PageKsm(struct page *page)
> +{
> +	return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) ==
> +				(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM);
> +}
> +#else
> +TESTPAGEFLAG_FALSE(Ksm)
> +#endif
> +
>  u64 stable_page_flags(struct page *page);
>  
>  static inline int PageUptodate(struct page *page)
> @@ -426,6 +467,14 @@ static inline void ClearPageCompound(struct page *page)
>  
>  #endif /* !PAGEFLAGS_EXTENDED */
>  
> +#ifdef CONFIG_HUGETLB_PAGE
> +int PageHuge(struct page *page);
> +int PageHeadHuge(struct page *page);
> +#else
> +TESTPAGEFLAG_FALSE(Huge)
> +TESTPAGEFLAG_FALSE(HeadHuge)
> +#endif
> +
>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>  /*
>   * PageHuge() only returns true for hugetlbfs pages, but not for
> @@ -480,6 +529,53 @@ static inline int PageTransTail(struct page *page)
>  #endif
>  
>  /*
> + * PageBuddy() indicate that the page is free and in the buddy system
> + * (see mm/page_alloc.c).
> + *
> + * PAGE_BUDDY_MAPCOUNT_VALUE must be <= -2 but better not too close to
> + * -2 so that an underflow of the page_mapcount() won't be mistaken
> + * for a genuine PAGE_BUDDY_MAPCOUNT_VALUE. -128 can be created very
> + * efficiently by most CPU architectures.
> + */
> +#define PAGE_BUDDY_MAPCOUNT_VALUE (-128)
> +
> +static inline int PageBuddy(struct page *page)
> +{
> +	return atomic_read(&page->_mapcount) == PAGE_BUDDY_MAPCOUNT_VALUE;
> +}
> +
> +static inline void __SetPageBuddy(struct page *page)
> +{
> +	VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page);
> +	atomic_set(&page->_mapcount, PAGE_BUDDY_MAPCOUNT_VALUE);
> +}
> +
> +static inline void __ClearPageBuddy(struct page *page)
> +{
> +	VM_BUG_ON_PAGE(!PageBuddy(page), page);
> +	atomic_set(&page->_mapcount, -1);
> +}
> +
> +#define PAGE_BALLOON_MAPCOUNT_VALUE (-256)
> +
> +static inline int PageBalloon(struct page *page)
> +{
> +	return atomic_read(&page->_mapcount) == PAGE_BALLOON_MAPCOUNT_VALUE;
> +}
> +
> +static inline void __SetPageBalloon(struct page *page)
> +{
> +	VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page);
> +	atomic_set(&page->_mapcount, PAGE_BALLOON_MAPCOUNT_VALUE);
> +}
> +
> +static inline void __ClearPageBalloon(struct page *page)
> +{
> +	VM_BUG_ON_PAGE(!PageBalloon(page), page);
> +	atomic_set(&page->_mapcount, -1);
> +}
> +
> +/*
>   * If network-based swap is enabled, sl*b must keep track of whether pages
>   * were allocated from pfmemalloc reserves.
>   */
> -- 
> 2.1.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 02/16] page-flags: trivial cleanup for PageTrans* helpers

[Hugh Dickins]

On Thu, 19 Mar 2015, Kirill A. Shutemov wrote:

> Use TESTPAGEFLAG_FALSE() to get it a bit cleaner.
> 
> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>

Yeah, this is okay too.

> ---
>  include/linux/page-flags.h | 18 +++---------------
>  1 file changed, 3 insertions(+), 15 deletions(-)
> 
> diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
> index 84d10b65cec6..327aabd9792e 100644
> --- a/include/linux/page-flags.h
> +++ b/include/linux/page-flags.h
> @@ -511,21 +511,9 @@ static inline int PageTransTail(struct page *page)
>  }
>  
>  #else
> -
> -static inline int PageTransHuge(struct page *page)
> -{
> -	return 0;
> -}
> -
> -static inline int PageTransCompound(struct page *page)
> -{
> -	return 0;
> -}
> -
> -static inline int PageTransTail(struct page *page)
> -{
> -	return 0;
> -}
> +TESTPAGEFLAG_FALSE(TransHuge)
> +TESTPAGEFLAG_FALSE(TransCompound)
> +TESTPAGEFLAG_FALSE(TransTail)
>  #endif
>  
>  /*
> -- 
> 2.1.4

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 00/16] Sanitize usage of ->flags and ->mapping for tail pages

[Hugh Dickins]

On Thu, 19 Mar 2015, Kirill A. Shutemov wrote:

> Currently we take naive approach to page flags on compound -- we set the
> flag on the page without consideration if the flag makes sense for tail
> page or for compound page in general. This patchset try to sort this out
> by defining per-flag policy on what need to be done if page-flag helper
> operate on compound page.
> 
> The last patch in patchset also sanitize usege of page->mapping for tail
> pages. We don't define meaning of page->mapping for tail pages. Currently
> it's always NULL, which can be inconsistent with head page and potentially
> lead to problems.
> 
> For now I catched one case of illigal usage of page flags or ->mapping:
> sound subsystem allocates pages with __GFP_COMP and maps them with PTEs.
> It leads to setting dirty bit on tail pages and access to tail_page's
> ->mapping. I don't see any bad behaviour caused by this, but worth fixing
> anyway.

But there's nothing to fix there.  We're more used to having page->mapping
set by filesystems, but it is normal for drivers to have pages with NULL
page->mapping mapped into userspace (and it's not accidental that they
appear !PageAnon); and subpages of compound pages mapped into userspace,
and set_page_dirty applied to them.

> 
> This patchset makes more sense if you take my THP refcounting into
> account: we will see more compound pages mapped with PTEs and we need to
> define behaviour of flags on compound pages to avoid bugs.

Yes, I quite understand that you want to clarify the usage of different
page flags to yourself, to help towards a policy of what to do with each
of them when subpages of a huge compound page are mapped into userspace;
but I don't see that we need this patchset in the kernel now, given that
it adds unnecessary overhead into several low-level inline functions.

I'm surprised that Andrew has fast-tracked it into his mmotm tree:
I don't think it's harmful beyond the overhead, but it seems premature:
let's wait until we get some benefit too?

Hugh

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 00/16] Sanitize usage of ->flags and ->mapping for tail pages

[Kirill A. Shutemov]

On Sun, Mar 22, 2015 at 05:28:47PM -0700, Hugh Dickins wrote:
> On Thu, 19 Mar 2015, Kirill A. Shutemov wrote:
> 
> > Currently we take naive approach to page flags on compound -- we set the
> > flag on the page without consideration if the flag makes sense for tail
> > page or for compound page in general. This patchset try to sort this out
> > by defining per-flag policy on what need to be done if page-flag helper
> > operate on compound page.
> > 
> > The last patch in patchset also sanitize usege of page->mapping for tail
> > pages. We don't define meaning of page->mapping for tail pages. Currently
> > it's always NULL, which can be inconsistent with head page and potentially
> > lead to problems.
> > 
> > For now I catched one case of illigal usage of page flags or ->mapping:
> > sound subsystem allocates pages with __GFP_COMP and maps them with PTEs.
> > It leads to setting dirty bit on tail pages and access to tail_page's
> > ->mapping. I don't see any bad behaviour caused by this, but worth fixing
> > anyway.
> 
> But there's nothing to fix there.  We're more used to having page->mapping
> set by filesystems, but it is normal for drivers to have pages with NULL
> page->mapping mapped into userspace (and it's not accidental that they
> appear !PageAnon); and subpages of compound pages mapped into userspace,
> and set_page_dirty applied to them.

Yes, it works until some sound driver decide it wants to use
page->mappging.

It's just pure luck that it happened to work in this particular case.

> > This patchset makes more sense if you take my THP refcounting into
> > account: we will see more compound pages mapped with PTEs and we need to
> > define behaviour of flags on compound pages to avoid bugs.
> 
> Yes, I quite understand that you want to clarify the usage of different
> page flags to yourself, to help towards a policy of what to do with each
> of them when subpages of a huge compound page are mapped into userspace;
> but I don't see that we need this patchset in the kernel now, given that
> it adds unnecessary overhead into several low-level inline functions.

We already have subpages of compound page mapped to userspace -- the sound
case.

And what overhead are you talking about?

Check for compound or head bit is practically free in most cases since you
are going to check other bits in the same cache line anyway. Probably a
bit more expensive if the flag is encoded in ->mapping or somewhere else.
(on 32-bit x86 ->mapping case is also free, since it's in the same cache
line as ->flags).

You only need to pay the expense if you hit tail page which is very rare
in current kernel. I think we can pay this cost for correctness.

We will shave some cost of compound_head() if/when my refcounting patchset
get merged: no need of barrier anymore.

-- 
 Kirill A. Shutemov

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 05/16] page-flags: define behavior of FS/IO-related flags on compound pages

[Kirill A. Shutemov]

On Sun, Mar 22, 2015 at 05:02:58PM -0700, Hugh Dickins wrote:
> On Thu, 19 Mar 2015, Kirill A. Shutemov wrote:
> > On Thu, Mar 19, 2015 at 11:29:52AM -0700, Dave Hansen wrote:
> > > On 03/19/2015 10:08 AM, Kirill A. Shutemov wrote:
> > > > The odd exception is PG_dirty: sound uses compound pages and maps them
> > > > with PTEs. NO_COMPOUND triggers VM_BUG_ON() in set_page_dirty() on
> > > > handling shared fault. Let's use HEAD for PG_dirty.
> 
> It really depends on what you do with PageDirty of the head, when you
> get to support 4k pagecache with subpages of a huge compound page.
> 
> HEAD will be fine, so long as PageDirty on the head means the whole
> huge page must be written back.  I expect that's what you will choose;
> but one could consider that if a huge page is only mapped read-only,
> but a few subpages of it writable, then only the few need be written
> back, in which case ANY would be more appropriate.  NO_COMPOUND is
> certainly wrong.
> 
> But that does illustrate that I consider this patch series premature:
> it belongs with your huge pagecache implementation.  You seem to be
> "tidying up" and adding overhead to things that are fine as they are.

I agree, it can be ANY too, since we don't use PG_dirty anywhere at the
moment. My first thought was that it's better to match PG_dirty behaviour
with LRU-related, but it's not necessary should be the case.

BTW, do we make any use of PG_dirty on pages with ->mapping == NULL?
Should we avoid dirtying them in the first place?

> > > Can we get the sound guys to look at this, btw?  It seems like an odd
> > > thing that we probably don't want to keep around, right?
> > 
> > CC: +sound guys
> 
> I don't think this is peculiar to sound at all: there are other users
> of __GFP_COMP in the tree, aren't there?  And although some of them
> might turn out not to need it any more, I expect most of them still
> need it for the same reason they did originally.

I haven't seen any other __GFP_COMP user which get it mapped to user-space
with PTEs. Do you? Probably I haven't just stepped on it.

... looking into code a bit more: at least one fb-drivers has compound
pages mapped with PTEs..

> > I'm not sure what is right fix here. At the time adding __GFP_COMP was a
> > fix: see f3d48f0373c1.
> 
> The only thing special about this one, was that I failed to add
> __GFP_COMP at first.
> 
> The purpose of __GFP_COMP is to allow a >0-order page (originally, just
> a hugetlb page: see 2.5.60) to be mapped into userspace, and parts of it
> then subjected to get_user_pages (ptrace, futex, direct I/O, infiniband
> etc), and now even munmap, without destroying the integrity of the
> underlying >0-order page.
> 
> We don't bother with __GFP_COMP when a >0-order page cannot be mapped
> into userspace (except through /dev/mem or suchlike); we add __GFP_COMP
> when it might be, to get the right reference counting.

Wouldn't non-compound >0-order page allocation + split_page() work too?

> It's normal for set_page_dirty() to be called in the course of
> get_user_pages(), and it's normal for set_page_dirty() to be called
> when releasing the get_user_pages() references, and it's normal for
> set_page_dirty() to be called when munmap'ing a pte_dirty().
> 
> > 
> > Other odd part about __GFP_COMP here is that we have ->_mapcount in tail
> > pages to be used for both: mapcount of the individual page and for gup
> > pins. __compound_tail_refcounted() doesn't recognize that we don't need
> > tail page accounting for these pages.
> 
> So page->_mapcount of the tails is being used for both their mapcount
> and their reference count: that's certainly funny, and further reason
> to pursue your aim of simplifying the way THPs are refcounted.  But
> not responsible for any actual bug, I think?

GUP pin would screw up page_mapcount() on these pages. It would affect
memory stats for the process and probably something else.

I think we can get __compound_tail_refcounted() ignore these pages by
checking if page->mapping is NULL.

> > Hugh, I tried to ask you about the situation several times (last time on
> > the summit). Any comments?
> 
> I do remember we began a curtailed conversation about this at LSF/MM.
> I do not remember you asking about it earlier: when was that?

http://lkml.kernel.org/g/20141217004734.GA23150@node.dhcp.inet.fi

-- 
 Kirill A. Shutemov

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 00/16] Sanitize usage of ->flags and ->mapping for tail pages

[Konstantin Khlebnikov]

On Thu, Mar 19, 2015 at 8:08 PM, Kirill A. Shutemov
<kirill.shutemov@linux.intel.com> wrote:
> Currently we take naive approach to page flags on compound -- we set the
> flag on the page without consideration if the flag makes sense for tail
> page or for compound page in general. This patchset try to sort this out
> by defining per-flag policy on what need to be done if page-flag helper
> operate on compound page.
>
> The last patch in patchset also sanitize usege of page->mapping for tail
> pages. We don't define meaning of page->mapping for tail pages. Currently
> it's always NULL, which can be inconsistent with head page and potentially
> lead to problems.
>
> For now I catched one case of illigal usage of page flags or ->mapping:
> sound subsystem allocates pages with __GFP_COMP and maps them with PTEs.
> It leads to setting dirty bit on tail pages and access to tail_page's
> ->mapping. I don't see any bad behaviour caused by this, but worth fixing
> anyway.

Do you mean call of set_page_dirty() from zap_pte_range() ?
I think this should be replaced with vma operation:
vma->vm_ops->set_page_dirty()

>
> This patchset makes more sense if you take my THP refcounting into
> account: we will see more compound pages mapped with PTEs and we need to
> define behaviour of flags on compound pages to avoid bugs.
>
> Kirill A. Shutemov (16):
>   mm: consolidate all page-flags helpers in <linux/page-flags.h>
>   page-flags: trivial cleanup for PageTrans* helpers
>   page-flags: introduce page flags policies wrt compound pages
>   page-flags: define PG_locked behavior on compound pages
>   page-flags: define behavior of FS/IO-related flags on compound pages
>   page-flags: define behavior of LRU-related flags on compound pages
>   page-flags: define behavior SL*B-related flags on compound pages
>   page-flags: define behavior of Xen-related flags on compound pages
>   page-flags: define PG_reserved behavior on compound pages
>   page-flags: define PG_swapbacked behavior on compound pages
>   page-flags: define PG_swapcache behavior on compound pages
>   page-flags: define PG_mlocked behavior on compound pages
>   page-flags: define PG_uncached behavior on compound pages
>   page-flags: define PG_uptodate behavior on compound pages
>   page-flags: look on head page if the flag is encoded in page->mapping
>   mm: sanitize page->mapping for tail pages
>
>  fs/cifs/file.c             |   8 +-
>  include/linux/hugetlb.h    |   7 -
>  include/linux/ksm.h        |  17 ---
>  include/linux/mm.h         | 122 +----------------
>  include/linux/page-flags.h | 317 ++++++++++++++++++++++++++++++++++-----------
>  include/linux/pagemap.h    |  25 ++--
>  include/linux/poison.h     |   4 +
>  mm/filemap.c               |  15 ++-
>  mm/huge_memory.c           |   2 +-
>  mm/ksm.c                   |   2 +-
>  mm/memory-failure.c        |   2 +-
>  mm/memory.c                |   2 +-
>  mm/migrate.c               |   2 +-
>  mm/page_alloc.c            |   7 +
>  mm/shmem.c                 |   4 +-
>  mm/slub.c                  |   2 +
>  mm/swap_state.c            |   4 +-
>  mm/util.c                  |   5 +-
>  mm/vmscan.c                |   4 +-
>  mm/zswap.c                 |   4 +-
>  20 files changed, 294 insertions(+), 261 deletions(-)
>
> --
> 2.1.4
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org.  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 00/16] Sanitize usage of ->flags and ->mapping for tail pages

[Kirill A. Shutemov]

On Tue, Mar 24, 2015 at 08:39:49PM +0300, Konstantin Khlebnikov wrote:
> On Thu, Mar 19, 2015 at 8:08 PM, Kirill A. Shutemov
> <kirill.shutemov@linux.intel.com> wrote:
> > Currently we take naive approach to page flags on compound -- we set the
> > flag on the page without consideration if the flag makes sense for tail
> > page or for compound page in general. This patchset try to sort this out
> > by defining per-flag policy on what need to be done if page-flag helper
> > operate on compound page.
> >
> > The last patch in patchset also sanitize usege of page->mapping for tail
> > pages. We don't define meaning of page->mapping for tail pages. Currently
> > it's always NULL, which can be inconsistent with head page and potentially
> > lead to problems.
> >
> > For now I catched one case of illigal usage of page flags or ->mapping:
> > sound subsystem allocates pages with __GFP_COMP and maps them with PTEs.
> > It leads to setting dirty bit on tail pages and access to tail_page's
> > ->mapping. I don't see any bad behaviour caused by this, but worth fixing
> > anyway.
> 
> Do you mean call of set_page_dirty() from zap_pte_range() ?

No. I trigger it earlier: set_page_dirty() from do_shared_fault().

> I think this should be replaced with vma operation:
> vma->vm_ops->set_page_dirty()

Does anybody know why would we want to dirtying pages with ->mapping ==
NULL?

I don't see a place where we can make any use of this. We probably could
avoid dirting such pages. Hm?

-- 
 Kirill A. Shutemov

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 05/16] page-flags: define behavior of FS/IO-related flags on compound pages

[Hugh Dickins]

On Mon, 23 Mar 2015, Kirill A. Shutemov wrote:
> On Sun, Mar 22, 2015 at 05:02:58PM -0700, Hugh Dickins wrote:
> > On Thu, 19 Mar 2015, Kirill A. Shutemov wrote:
> > > On Thu, Mar 19, 2015 at 11:29:52AM -0700, Dave Hansen wrote:
> > > > On 03/19/2015 10:08 AM, Kirill A. Shutemov wrote:
> > > > > The odd exception is PG_dirty: sound uses compound pages and maps them
> > > > > with PTEs. NO_COMPOUND triggers VM_BUG_ON() in set_page_dirty() on
> > > > > handling shared fault. Let's use HEAD for PG_dirty.
> > 
> > It really depends on what you do with PageDirty of the head, when you
> > get to support 4k pagecache with subpages of a huge compound page.
> > 
> > HEAD will be fine, so long as PageDirty on the head means the whole
> > huge page must be written back.  I expect that's what you will choose;
> > but one could consider that if a huge page is only mapped read-only,
> > but a few subpages of it writable, then only the few need be written
> > back, in which case ANY would be more appropriate.  NO_COMPOUND is
> > certainly wrong.
> > 
> > But that does illustrate that I consider this patch series premature:
> > it belongs with your huge pagecache implementation.  You seem to be
> > "tidying up" and adding overhead to things that are fine as they are.
> 
> I agree, it can be ANY too, since we don't use PG_dirty anywhere at the
> moment. My first thought was that it's better to match PG_dirty behaviour
> with LRU-related, but it's not necessary should be the case.

No, yes, we do treat Dirty differently from LRU.

> 
> BTW, do we make any use of PG_dirty on pages with ->mapping == NULL?

No use that I can recall; but I suppose it's possible there's some
driver which does make use of it (if so, then you should choose ANY).

> Should we avoid dirtying them in the first place?

I don't think so: to do so would add more branches in hot paths,
just to avoid a rare case which works fine without them; and
prevent a driver from using it, in the unlikely case that's so.

> 
> > > > Can we get the sound guys to look at this, btw?  It seems like an odd
> > > > thing that we probably don't want to keep around, right?
> > > 
> > > CC: +sound guys
> > 
> > I don't think this is peculiar to sound at all: there are other users
> > of __GFP_COMP in the tree, aren't there?  And although some of them
> > might turn out not to need it any more, I expect most of them still
> > need it for the same reason they did originally.
> 
> I haven't seen any other __GFP_COMP user which get it mapped to user-space
> with PTEs. Do you? Probably I haven't just stepped on it.

I don't know why a driver would use __GFP_COMP if it cannot get mapped
into user-space (except copy-and-paste from a driver that needed it to
a driver that did not): if there's no chance of mapping into userspace,
then an ordinary >0-order allocation is good enough, isn't it?

> 
> ... looking into code a bit more: at least one fb-drivers has compound
> pages mapped with PTEs..

Good, you've saved me from looking for them.  I would expect every
__GFP_COMP allocation to be mappable into user-space, with silly
exceptions.

> 
> > > I'm not sure what is right fix here. At the time adding __GFP_COMP was a
> > > fix: see f3d48f0373c1.
> > 
> > The only thing special about this one, was that I failed to add
> > __GFP_COMP at first.
> > 
> > The purpose of __GFP_COMP is to allow a >0-order page (originally, just
> > a hugetlb page: see 2.5.60) to be mapped into userspace, and parts of it
> > then subjected to get_user_pages (ptrace, futex, direct I/O, infiniband
> > etc), and now even munmap, without destroying the integrity of the
> > underlying >0-order page.
> > 
> > We don't bother with __GFP_COMP when a >0-order page cannot be mapped
> > into userspace (except through /dev/mem or suchlike); we add __GFP_COMP
> > when it might be, to get the right reference counting.
> 
> Wouldn't non-compound >0-order page allocation + split_page() work too?

That works very well for me in huge tmpfs, yes :)

But I think the typical __GFP_COMP-using driver wants one large
contiguous area that it holds as a single piece, without worrying
about the ref-counting implications of when it's mapped into
user-space, then partially unmapped, or accessed via get_user_pages.
It can't risk losing parts of its buffer at the whim of its users.

I expect you're right that drivers could be converted over to
manage their buffers differently, without __GFP_COMP.  But __GFP_COMP
existed already for hugetlbfs, and was easy for drivers to use safely:
the whole being held until the head is freed.  (And split_page() was
added later in history - I think so the surplus tail end of a high
order page could be freed immediately.)

> 
> > It's normal for set_page_dirty() to be called in the course of
> > get_user_pages(), and it's normal for set_page_dirty() to be called
> > when releasing the get_user_pages() references, and it's normal for
> > set_page_dirty() to be called when munmap'ing a pte_dirty().
> > 
> > > 
> > > Other odd part about __GFP_COMP here is that we have ->_mapcount in tail
> > > pages to be used for both: mapcount of the individual page and for gup
> > > pins. __compound_tail_refcounted() doesn't recognize that we don't need
> > > tail page accounting for these pages.
> > 
> > So page->_mapcount of the tails is being used for both their mapcount
> > and their reference count: that's certainly funny, and further reason
> > to pursue your aim of simplifying the way THPs are refcounted.  But
> > not responsible for any actual bug, I think?
> 
> GUP pin would screw up page_mapcount() on these pages. It would affect
> memory stats for the process and probably something else.

Yes, the GUP pin would increment page_mapcount() without an additional
mapping - but can only happen once the page has already been mapped,
so FILE_MAPPED stats unaffected?  I'm not sure; but surely it wouldn't
work as well when unmapped before unpinned, since the unmapping will
see "still mapped" and the unpinning won't do anything with FILE_MAPPED.

Unmapping before unpinning is an uncommon path; but it can't be ignored,
it is the path which demanded __GFP_COMP in the first place.

Looks like extending THP by-mapcount refcounting to other compound pages
was not such a good idea.  But since nobody has noticed, we may not need
a more urgent fix than your simplification of THP refcounting.

> 
> I think we can get __compound_tail_refcounted() ignore these pages by
> checking if page->mapping is NULL.

I forget what's in page->mapping on the THP tails.  Or do you mean
page->mapping of head?  It would be better not to rely on that, I'm
not certain that no driver could set page->mapping of compound head.
There's probably some field or flag on the tails that you could use;
but I don't know that it's needed in a hurry.

> 
> > > Hugh, I tried to ask you about the situation several times (last time on
> > > the summit). Any comments?
> > 
> > I do remember we began a curtailed conversation about this at LSF/MM.
> > I do not remember you asking about it earlier: when was that?
> 
> http://lkml.kernel.org/g/20141217004734.GA23150@node.dhcp.inet.fi

Hmm, curious: never reached me (and I should have seen that on linux-mm
even if not Cc'ed); unless I deleted it by accident, that's not unknown.

And in that you explain as I've said above, so you didn't really need
me anyway.

Hugh

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 00/16] Sanitize usage of ->flags and ->mapping for tail pages

[Hugh Dickins]

On Mon, 23 Mar 2015, Kirill A. Shutemov wrote:
> On Sun, Mar 22, 2015 at 05:28:47PM -0700, Hugh Dickins wrote:
> > On Thu, 19 Mar 2015, Kirill A. Shutemov wrote:
> > 
> > > Currently we take naive approach to page flags on compound -- we set the
> > > flag on the page without consideration if the flag makes sense for tail
> > > page or for compound page in general. This patchset try to sort this out
> > > by defining per-flag policy on what need to be done if page-flag helper
> > > operate on compound page.
> > > 
> > > The last patch in patchset also sanitize usege of page->mapping for tail
> > > pages. We don't define meaning of page->mapping for tail pages. Currently
> > > it's always NULL, which can be inconsistent with head page and potentially
> > > lead to problems.
> > > 
> > > For now I catched one case of illigal usage of page flags or ->mapping:
> > > sound subsystem allocates pages with __GFP_COMP and maps them with PTEs.
> > > It leads to setting dirty bit on tail pages and access to tail_page's
> > > ->mapping. I don't see any bad behaviour caused by this, but worth fixing
> > > anyway.
> > 
> > But there's nothing to fix there.  We're more used to having page->mapping
> > set by filesystems, but it is normal for drivers to have pages with NULL
> > page->mapping mapped into userspace (and it's not accidental that they
> > appear !PageAnon); and subpages of compound pages mapped into userspace,
> > and set_page_dirty applied to them.
> 
> Yes, it works until some sound driver decide it wants to use
> page->mappging.

(a) Why would it want to use page->mapping?
(b) What's the problem if it wants to use page->mapping?
(c) Or perhaps some __GFP_COMP driver does already use page->mapping?

The code works fine as is (er, modulo the fact that someone has tried
to use page_mapcount for two different things at the same time), and
has worked for years.

If new needs emerge, we can make suitable changes.  If your refcounting
rework needs a change here, fine, then just make these patches a part
of that set.  But please don't impose new rules for no reason.

> 
> It's just pure luck that it happened to work in this particular case.

We were lucky that it fitted together without needing extra code, yes.
But this didn't happen by accident, it was known and considered.

> 
> > > This patchset makes more sense if you take my THP refcounting into
> > > account: we will see more compound pages mapped with PTEs and we need to
> > > define behaviour of flags on compound pages to avoid bugs.
> > 
> > Yes, I quite understand that you want to clarify the usage of different
> > page flags to yourself, to help towards a policy of what to do with each
> > of them when subpages of a huge compound page are mapped into userspace;
> > but I don't see that we need this patchset in the kernel now, given that
> > it adds unnecessary overhead into several low-level inline functions.
> 
> We already have subpages of compound page mapped to userspace -- the sound
> case.
> 
> And what overhead are you talking about?
> 
> Check for compound or head bit is practically free in most cases since you
> are going to check other bits in the same cache line anyway. Probably a
> bit more expensive if the flag is encoded in ->mapping or somewhere else.
> (on 32-bit x86 ->mapping case is also free, since it's in the same cache
> line as ->flags).

Good that it's practically free on x86 (though your "practically"
suggests it's not quite free).  Then there's also the extra icache.

This is small stuff, I do agree (though small stuff concealed in
common inline functions we tend to think of as lightweight).

I care more about not adding unnecessary code,
and not fixing what's not broken.

> 
> You only need to pay the expense if you hit tail page which is very rare
> in current kernel. I think we can pay this cost for correctness.

But it's correct as is.

> 
> We will shave some cost of compound_head() if/when my refcounting patchset
> get merged: no need of barrier anymore.

And if these changes are necessary for that, sure, go ahead:
but as part of that work.

Hugh

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 05/16] page-flags: define behavior of FS/IO-related flags on compound pages

[Kirill A. Shutemov]

On Tue, Mar 24, 2015 at 03:54:00PM -0700, Hugh Dickins wrote:
> On Mon, 23 Mar 2015, Kirill A. Shutemov wrote:
> > Should we avoid dirtying them in the first place?
> 
> I don't think so: to do so would add more branches in hot paths,
> just to avoid a rare case which works fine without them; and
> prevent a driver from using it, in the unlikely case that's so.

It's branches vs. useless atomic oprations.

> > GUP pin would screw up page_mapcount() on these pages. It would affect
> > memory stats for the process and probably something else.
> 
> Yes, the GUP pin would increment page_mapcount() without an additional
> mapping - but can only happen once the page has already been mapped,
> so FILE_MAPPED stats unaffected?  I'm not sure; but surely it wouldn't
> work as well when unmapped before unpinned, since the unmapping will
> see "still mapped" and the unpinning won't do anything with FILE_MAPPED.
> 
> Unmapping before unpinning is an uncommon path; but it can't be ignored,
> it is the path which demanded __GFP_COMP in the first place.
> 
> Looks like extending THP by-mapcount refcounting to other compound pages
> was not such a good idea.  But since nobody has noticed, we may not need
> a more urgent fix than your simplification of THP refcounting.

I think PSS and /proc/kpagecount are broken by this.

> > I think we can get __compound_tail_refcounted() ignore these pages by
> > checking if page->mapping is NULL.
> 
> I forget what's in page->mapping on the THP tails.

NULL. We never set ->mapping on any tail pages. That's why I want outlaw
using that value: it's just doesn't match with head page ->mapping for
some of compound pages. And for others it matches just because nobody
touches it for any subpage.

> Or do you mean page->mapping of head?  It would be better not to rely on
> that, I'm not certain that no driver could set page->mapping of compound
> head.  There's probably some field or flag on the tails that you could
> use; but I don't know that it's needed in a hurry.

We only need tail refcounting for THP, so I think this should fix the issue:

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4a3a38522ab4..9ab432660adb 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -456,7 +456,7 @@ static inline int page_count(struct page *page)
 
 static inline bool __compound_tail_refcounted(struct page *page)
 {
-       return !PageSlab(page) && !PageHeadHuge(page);
+       return !PageSlab(page) && !PageHeadHuge(page) && PageAnon(page);
 }
 
 /*

-- 
 Kirill A. Shutemov

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 00/16] Sanitize usage of ->flags and ->mapping for tail pages

[Kirill A. Shutemov]

On Tue, Mar 24, 2015 at 04:42:48PM -0700, Hugh Dickins wrote:
> On Mon, 23 Mar 2015, Kirill A. Shutemov wrote:
> > Yes, it works until some sound driver decide it wants to use
> > page->mappging.
> 
> (a) Why would it want to use page->mapping?

No idea.

> (b) What's the problem if it wants to use page->mapping?

It would need to be initalized for all subpages to get core mm see correct
value. And this doesn't match with current ->mapping users of __GFP_COMP
page (THP and hugetlb) which initialize ->mapping only for head pages.

> (c) Or perhaps some __GFP_COMP driver does already use page->mapping?

I haven't found any.

> > It's just pure luck that it happened to work in this particular case.
> 
> We were lucky that it fitted together without needing extra code, yes.
> But this didn't happen by accident, it was known and considered.

I don't agree it was considered well enough.

> > You only need to pay the expense if you hit tail page which is very rare
> > in current kernel. I think we can pay this cost for correctness.
> 
> But it's correct as is.

See above.

> > 
> > We will shave some cost of compound_head() if/when my refcounting patchset
> > get merged: no need of barrier anymore.
> 
> And if these changes are necessary for that, sure, go ahead:
> but as part of that work.

I believe the patchset has value by its own. And having it merged makes my
life easier. But up to Andrew.

-- 
 Kirill A. Shutemov

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 05/16] page-flags: define behavior of FS/IO-related flags on compound pages

[Hugh Dickins]

On Wed, 25 Mar 2015, Kirill A. Shutemov wrote:
> 
> We only need tail refcounting for THP, so I think this should fix the issue:
> 
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 4a3a38522ab4..9ab432660adb 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -456,7 +456,7 @@ static inline int page_count(struct page *page)
>  
>  static inline bool __compound_tail_refcounted(struct page *page)
>  {
> -       return !PageSlab(page) && !PageHeadHuge(page);
> +       return !PageSlab(page) && !PageHeadHuge(page) && PageAnon(page);
>  }
>  
>  /*

Yes, that should be a good fix for the mapcount issue.
And no coincidence that it's just what I needed too,
when reusing the PG_compound_lock bit: see my 10/24
(which had to rearrange mm.h. not having your 1/16).

Hugh

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 04/16] page-flags: define PG_locked behavior on compound pages

[Mateusz Krawczuk]

Hi!

This patch breaks build of linux next since 2015-03-25 on arm using 
exynos_defconfig with arm-linux-gnueabi-linaro_4.7.4-2014.04, 
arm-linux-gnueabi-linaro_4.8.3-2014.04 and 
arm-linux-gnueabi-4.7.3-12ubuntu1(from ubuntu 14.04 lts). Compiler shows 
this error message:
mm/migrate.c: In function ?migrate_pages?:
mm/migrate.c:1148:1: internal compiler error: in push_minipool_fix, at 
config/arm/arm.c:13500
Please submit a full bug report,
with preprocessed source if appropriate.
See <file:///usr/share/doc/gcc-4.7/README.Bugs> for instructions.

It builds fine with arm-linux-gnueabi-linaro_4.9.1-2014.07.

Best Regards
Mateusz Krawczuk
Samsung R&D Institute Poland

  dniu 19.03.2015 o 18:08, Kirill A. Shutemov pisze:
> lock_page() must operate on the whole compound page. It doesn't make
> much sense to lock part of compound page. Change code to use head page's
> PG_locked, if tail page is passed.
>
> This patch also get rid of custom helprer functions --
> __set_page_locked() and __clear_page_locked(). They replaced with
> helpers generated by __SETPAGEFLAG/__CLEARPAGEFLAG. Tail pages to these
> helper would trigger VM_BUG_ON().
>
> SLUB uses PG_locked as a bit spin locked. IIUC, tail pages should never
> appear there. VM_BUG_ON() is added to make sure that this assumption is
> correct.
>
> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> ---
>   fs/cifs/file.c             |  8 ++++----
>   include/linux/page-flags.h |  2 +-
>   include/linux/pagemap.h    | 25 ++++++++-----------------
>   mm/filemap.c               | 15 +++++++++------
>   mm/ksm.c                   |  2 +-
>   mm/memory-failure.c        |  2 +-
>   mm/migrate.c               |  2 +-
>   mm/shmem.c                 |  4 ++--
>   mm/slub.c                  |  2 ++
>   mm/swap_state.c            |  4 ++--
>   mm/vmscan.c                |  4 ++--
>   mm/zswap.c                 |  4 ++--
>   12 files changed, 35 insertions(+), 39 deletions(-)
>
> diff --git a/fs/cifs/file.c b/fs/cifs/file.c
> index ca30c391a894..b9fd85dfee9b 100644
> --- a/fs/cifs/file.c
> +++ b/fs/cifs/file.c
> @@ -3413,13 +3413,13 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
>   	 * should have access to this page, we're safe to simply set
>   	 * PG_locked without checking it first.
>   	 */
> -	__set_page_locked(page);
> +	__SetPageLocked(page);
>   	rc = add_to_page_cache_locked(page, mapping,
>   				      page->index, GFP_KERNEL);
>
>   	/* give up if we can't stick it in the cache */
>   	if (rc) {
> -		__clear_page_locked(page);
> +		__ClearPageLocked(page);
>   		return rc;
>   	}
>
> @@ -3440,10 +3440,10 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
>   		if (*bytes + PAGE_CACHE_SIZE > rsize)
>   			break;
>
> -		__set_page_locked(page);
> +		__SetPageLocked(page);
>   		if (add_to_page_cache_locked(page, mapping, page->index,
>   								GFP_KERNEL)) {
> -			__clear_page_locked(page);
> +			__ClearPageLocked(page);
>   			break;
>   		}
>   		list_move_tail(&page->lru, tmplist);
> diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
> index 32ea62c0ad30..10bdde20b14c 100644
> --- a/include/linux/page-flags.h
> +++ b/include/linux/page-flags.h
> @@ -269,7 +269,7 @@ static inline struct page *compound_head_fast(struct page *page)
>   	return page;
>   }
>
> -TESTPAGEFLAG(Locked, locked, ANY)
> +__PAGEFLAG(Locked, locked, NO_TAIL)
>   PAGEFLAG(Error, error, ANY) TESTCLEARFLAG(Error, error, ANY)
>   PAGEFLAG(Referenced, referenced, ANY) TESTCLEARFLAG(Referenced, referenced, ANY)
>   	__SETPAGEFLAG(Referenced, referenced, ANY)
> diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
> index 4b3736f7065c..7c3790764795 100644
> --- a/include/linux/pagemap.h
> +++ b/include/linux/pagemap.h
> @@ -426,18 +426,9 @@ extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
>   				unsigned int flags);
>   extern void unlock_page(struct page *page);
>
> -static inline void __set_page_locked(struct page *page)
> -{
> -	__set_bit(PG_locked, &page->flags);
> -}
> -
> -static inline void __clear_page_locked(struct page *page)
> -{
> -	__clear_bit(PG_locked, &page->flags);
> -}
> -
>   static inline int trylock_page(struct page *page)
>   {
> +	page = compound_head(page);
>   	return (likely(!test_and_set_bit_lock(PG_locked, &page->flags)));
>   }
>
> @@ -490,9 +481,9 @@ extern int wait_on_page_bit_killable_timeout(struct page *page,
>
>   static inline int wait_on_page_locked_killable(struct page *page)
>   {
> -	if (PageLocked(page))
> -		return wait_on_page_bit_killable(page, PG_locked);
> -	return 0;
> +	if (!PageLocked(page))
> +		return 0;
> +	return wait_on_page_bit_killable(compound_head(page), PG_locked);
>   }
>
>   extern wait_queue_head_t *page_waitqueue(struct page *page);
> @@ -511,7 +502,7 @@ static inline void wake_up_page(struct page *page, int bit)
>   static inline void wait_on_page_locked(struct page *page)
>   {
>   	if (PageLocked(page))
> -		wait_on_page_bit(page, PG_locked);
> +		wait_on_page_bit(compound_head(page), PG_locked);
>   }
>
>   /*
> @@ -656,17 +647,17 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask);
>
>   /*
>    * Like add_to_page_cache_locked, but used to add newly allocated pages:
> - * the page is new, so we can just run __set_page_locked() against it.
> + * the page is new, so we can just run __SetPageLocked() against it.
>    */
>   static inline int add_to_page_cache(struct page *page,
>   		struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask)
>   {
>   	int error;
>
> -	__set_page_locked(page);
> +	__SetPageLocked(page);
>   	error = add_to_page_cache_locked(page, mapping, offset, gfp_mask);
>   	if (unlikely(error))
> -		__clear_page_locked(page);
> +		__ClearPageLocked(page);
>   	return error;
>   }
>
> diff --git a/mm/filemap.c b/mm/filemap.c
> index 12548d03c11d..467768d4263b 100644
> --- a/mm/filemap.c
> +++ b/mm/filemap.c
> @@ -615,11 +615,11 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
>   	void *shadow = NULL;
>   	int ret;
>
> -	__set_page_locked(page);
> +	__SetPageLocked(page);
>   	ret = __add_to_page_cache_locked(page, mapping, offset,
>   					 gfp_mask, &shadow);
>   	if (unlikely(ret))
> -		__clear_page_locked(page);
> +		__ClearPageLocked(page);
>   	else {
>   		/*
>   		 * The page might have been evicted from cache only
> @@ -742,6 +742,7 @@ EXPORT_SYMBOL_GPL(add_page_wait_queue);
>    */
>   void unlock_page(struct page *page)
>   {
> +	page = compound_head(page);
>   	VM_BUG_ON_PAGE(!PageLocked(page), page);
>   	clear_bit_unlock(PG_locked, &page->flags);
>   	smp_mb__after_atomic();
> @@ -806,18 +807,20 @@ EXPORT_SYMBOL_GPL(page_endio);
>    */
>   void __lock_page(struct page *page)
>   {
> -	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
> +	struct page *page_head = compound_head(page);
> +	DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked);
>
> -	__wait_on_bit_lock(page_waitqueue(page), &wait, bit_wait_io,
> +	__wait_on_bit_lock(page_waitqueue(page_head), &wait, bit_wait_io,
>   							TASK_UNINTERRUPTIBLE);
>   }
>   EXPORT_SYMBOL(__lock_page);
>
>   int __lock_page_killable(struct page *page)
>   {
> -	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
> +	struct page *page_head = compound_head(page);
> +	DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked);
>
> -	return __wait_on_bit_lock(page_waitqueue(page), &wait,
> +	return __wait_on_bit_lock(page_waitqueue(page_head), &wait,
>   					bit_wait_io, TASK_KILLABLE);
>   }
>   EXPORT_SYMBOL_GPL(__lock_page_killable);
> diff --git a/mm/ksm.c b/mm/ksm.c
> index 4162dce2eb44..23138e99a531 100644
> --- a/mm/ksm.c
> +++ b/mm/ksm.c
> @@ -1884,7 +1884,7 @@ struct page *ksm_might_need_to_copy(struct page *page,
>
>   		SetPageDirty(new_page);
>   		__SetPageUptodate(new_page);
> -		__set_page_locked(new_page);
> +		__SetPageLocked(new_page);
>   	}
>
>   	return new_page;
> diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> index d487f8dc6d39..399eee44d13d 100644
> --- a/mm/memory-failure.c
> +++ b/mm/memory-failure.c
> @@ -1136,7 +1136,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
>   	/*
>   	 * We ignore non-LRU pages for good reasons.
>   	 * - PG_locked is only well defined for LRU pages and a few others
> -	 * - to avoid races with __set_page_locked()
> +	 * - to avoid races with __SetPageLocked()
>   	 * - to avoid races with __SetPageSlab*() (and more non-atomic ops)
>   	 * The check (unnecessarily) ignores LRU pages being isolated and
>   	 * walked by the page reclaim code, however that's not a big loss.
> diff --git a/mm/migrate.c b/mm/migrate.c
> index 6aa9a4222ea9..114602a68111 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -1734,7 +1734,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
>   		flush_tlb_range(vma, mmun_start, mmun_end);
>
>   	/* Prepare a page as a migration target */
> -	__set_page_locked(new_page);
> +	__SetPageLocked(new_page);
>   	SetPageSwapBacked(new_page);
>
>   	/* anon mapping, we can simply copy page->mapping to the new page: */
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 80b360c7bcd1..2e2b943c8e62 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -981,7 +981,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
>   	copy_highpage(newpage, oldpage);
>   	flush_dcache_page(newpage);
>
> -	__set_page_locked(newpage);
> +	__SetPageLocked(newpage);
>   	SetPageUptodate(newpage);
>   	SetPageSwapBacked(newpage);
>   	set_page_private(newpage, swap_index);
> @@ -1173,7 +1173,7 @@ repeat:
>   		}
>
>   		__SetPageSwapBacked(page);
> -		__set_page_locked(page);
> +		__SetPageLocked(page);
>   		if (sgp == SGP_WRITE)
>   			__SetPageReferenced(page);
>
> diff --git a/mm/slub.c b/mm/slub.c
> index 2584d4ff02eb..f33ae2b7a5e7 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -338,11 +338,13 @@ static inline int oo_objects(struct kmem_cache_order_objects x)
>    */
>   static __always_inline void slab_lock(struct page *page)
>   {
> +	VM_BUG_ON_PAGE(PageTail(page), page);
>   	bit_spin_lock(PG_locked, &page->flags);
>   }
>
>   static __always_inline void slab_unlock(struct page *page)
>   {
> +	VM_BUG_ON_PAGE(PageTail(page), page);
>   	__bit_spin_unlock(PG_locked, &page->flags);
>   }
>
> diff --git a/mm/swap_state.c b/mm/swap_state.c
> index 405923f77334..d1c4a25b4362 100644
> --- a/mm/swap_state.c
> +++ b/mm/swap_state.c
> @@ -357,7 +357,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
>   		}
>
>   		/* May fail (-ENOMEM) if radix-tree node allocation failed. */
> -		__set_page_locked(new_page);
> +		__SetPageLocked(new_page);
>   		SetPageSwapBacked(new_page);
>   		err = __add_to_swap_cache(new_page, entry);
>   		if (likely(!err)) {
> @@ -371,7 +371,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
>   		}
>   		radix_tree_preload_end();
>   		ClearPageSwapBacked(new_page);
> -		__clear_page_locked(new_page);
> +		__ClearPageLocked(new_page);
>   		/*
>   		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
>   		 * clear SWAP_HAS_CACHE flag.
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 260c413d39cd..dc6cd51577a6 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -1062,7 +1062,7 @@ unmap:
>   				VM_BUG_ON_PAGE(PageSwapCache(page), page);
>   				if (!page_freeze_refs(page, 1))
>   					goto keep_locked;
> -				__clear_page_locked(page);
> +				__ClearPageLocked(page);
>   				count_vm_event(PGLAZYFREED);
>   				goto free_it;
>   			}
> @@ -1174,7 +1174,7 @@ unmap:
>   		 * we obviously don't have to worry about waking up a process
>   		 * waiting on the page lock, because there are no references.
>   		 */
> -		__clear_page_locked(page);
> +		__ClearPageLocked(page);
>   free_it:
>   		nr_reclaimed++;
>
> diff --git a/mm/zswap.c b/mm/zswap.c
> index 4249e82ff934..f8583f1fc938 100644
> --- a/mm/zswap.c
> +++ b/mm/zswap.c
> @@ -490,7 +490,7 @@ static int zswap_get_swap_cache_page(swp_entry_t entry,
>   		}
>
>   		/* May fail (-ENOMEM) if radix-tree node allocation failed. */
> -		__set_page_locked(new_page);
> +		__SetPageLocked(new_page);
>   		SetPageSwapBacked(new_page);
>   		err = __add_to_swap_cache(new_page, entry);
>   		if (likely(!err)) {
> @@ -501,7 +501,7 @@ static int zswap_get_swap_cache_page(swp_entry_t entry,
>   		}
>   		radix_tree_preload_end();
>   		ClearPageSwapBacked(new_page);
> -		__clear_page_locked(new_page);
> +		__ClearPageLocked(new_page);
>   		/*
>   		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
>   		 * clear SWAP_HAS_CACHE flag.
>


--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 04/16] page-flags: define PG_locked behavior on compound pages

[Mateusz Krawczuk]

Hi!

This patch breaks build of linux next since 2015-03-25 on arm using 
exynos_defconfig with arm-linux-gnueabi-linaro_4.7.4-2014.04, 
arm-linux-gnueabi-linaro_4.8.3-2014.04 and 
arm-linux-gnueabi-4.7.3-12ubuntu1(from ubuntu 14.04 lts). Compiler shows 
this error message:
mm/migrate.c: In function ?migrate_pages?:
mm/migrate.c:1148:1: internal compiler error: in push_minipool_fix, at 
config/arm/arm.c:13500
Please submit a full bug report,
with preprocessed source if appropriate.
See <file:///usr/share/doc/gcc-4.7/README.Bugs> for instructions.

It builds fine with arm-linux-gnueabi-linaro_4.9.1-2014.07.

Best Regards
Mateusz Krawczuk
Samsung R&D Institute Poland

  dniu 19.03.2015 o 18:08, Kirill A. Shutemov pisze:
> lock_page() must operate on the whole compound page. It doesn't make
> much sense to lock part of compound page. Change code to use head page's
> PG_locked, if tail page is passed.
>
> This patch also get rid of custom helprer functions --
> __set_page_locked() and __clear_page_locked(). They replaced with
> helpers generated by __SETPAGEFLAG/__CLEARPAGEFLAG. Tail pages to these
> helper would trigger VM_BUG_ON().
>
> SLUB uses PG_locked as a bit spin locked. IIUC, tail pages should never
> appear there. VM_BUG_ON() is added to make sure that this assumption is
> correct.
>
> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> ---
>   fs/cifs/file.c             |  8 ++++----
>   include/linux/page-flags.h |  2 +-
>   include/linux/pagemap.h    | 25 ++++++++-----------------
>   mm/filemap.c               | 15 +++++++++------
>   mm/ksm.c                   |  2 +-
>   mm/memory-failure.c        |  2 +-
>   mm/migrate.c               |  2 +-
>   mm/shmem.c                 |  4 ++--
>   mm/slub.c                  |  2 ++
>   mm/swap_state.c            |  4 ++--
>   mm/vmscan.c                |  4 ++--
>   mm/zswap.c                 |  4 ++--
>   12 files changed, 35 insertions(+), 39 deletions(-)
>
> diff --git a/fs/cifs/file.c b/fs/cifs/file.c
> index ca30c391a894..b9fd85dfee9b 100644
> --- a/fs/cifs/file.c
> +++ b/fs/cifs/file.c
> @@ -3413,13 +3413,13 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
>   	 * should have access to this page, we're safe to simply set
>   	 * PG_locked without checking it first.
>   	 */
> -	__set_page_locked(page);
> +	__SetPageLocked(page);
>   	rc = add_to_page_cache_locked(page, mapping,
>   				      page->index, GFP_KERNEL);
>
>   	/* give up if we can't stick it in the cache */
>   	if (rc) {
> -		__clear_page_locked(page);
> +		__ClearPageLocked(page);
>   		return rc;
>   	}
>
> @@ -3440,10 +3440,10 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
>   		if (*bytes + PAGE_CACHE_SIZE > rsize)
>   			break;
>
> -		__set_page_locked(page);
> +		__SetPageLocked(page);
>   		if (add_to_page_cache_locked(page, mapping, page->index,
>   								GFP_KERNEL)) {
> -			__clear_page_locked(page);
> +			__ClearPageLocked(page);
>   			break;
>   		}
>   		list_move_tail(&page->lru, tmplist);
> diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
> index 32ea62c0ad30..10bdde20b14c 100644
> --- a/include/linux/page-flags.h
> +++ b/include/linux/page-flags.h
> @@ -269,7 +269,7 @@ static inline struct page *compound_head_fast(struct page *page)
>   	return page;
>   }
>
> -TESTPAGEFLAG(Locked, locked, ANY)
> +__PAGEFLAG(Locked, locked, NO_TAIL)
>   PAGEFLAG(Error, error, ANY) TESTCLEARFLAG(Error, error, ANY)
>   PAGEFLAG(Referenced, referenced, ANY) TESTCLEARFLAG(Referenced, referenced, ANY)
>   	__SETPAGEFLAG(Referenced, referenced, ANY)
> diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
> index 4b3736f7065c..7c3790764795 100644
> --- a/include/linux/pagemap.h
> +++ b/include/linux/pagemap.h
> @@ -426,18 +426,9 @@ extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
>   				unsigned int flags);
>   extern void unlock_page(struct page *page);
>
> -static inline void __set_page_locked(struct page *page)
> -{
> -	__set_bit(PG_locked, &page->flags);
> -}
> -
> -static inline void __clear_page_locked(struct page *page)
> -{
> -	__clear_bit(PG_locked, &page->flags);
> -}
> -
>   static inline int trylock_page(struct page *page)
>   {
> +	page = compound_head(page);
>   	return (likely(!test_and_set_bit_lock(PG_locked, &page->flags)));
>   }
>
> @@ -490,9 +481,9 @@ extern int wait_on_page_bit_killable_timeout(struct page *page,
>
>   static inline int wait_on_page_locked_killable(struct page *page)
>   {
> -	if (PageLocked(page))
> -		return wait_on_page_bit_killable(page, PG_locked);
> -	return 0;
> +	if (!PageLocked(page))
> +		return 0;
> +	return wait_on_page_bit_killable(compound_head(page), PG_locked);
>   }
>
>   extern wait_queue_head_t *page_waitqueue(struct page *page);
> @@ -511,7 +502,7 @@ static inline void wake_up_page(struct page *page, int bit)
>   static inline void wait_on_page_locked(struct page *page)
>   {
>   	if (PageLocked(page))
> -		wait_on_page_bit(page, PG_locked);
> +		wait_on_page_bit(compound_head(page), PG_locked);
>   }
>
>   /*
> @@ -656,17 +647,17 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask);
>
>   /*
>    * Like add_to_page_cache_locked, but used to add newly allocated pages:
> - * the page is new, so we can just run __set_page_locked() against it.
> + * the page is new, so we can just run __SetPageLocked() against it.
>    */
>   static inline int add_to_page_cache(struct page *page,
>   		struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask)
>   {
>   	int error;
>
> -	__set_page_locked(page);
> +	__SetPageLocked(page);
>   	error = add_to_page_cache_locked(page, mapping, offset, gfp_mask);
>   	if (unlikely(error))
> -		__clear_page_locked(page);
> +		__ClearPageLocked(page);
>   	return error;
>   }
>
> diff --git a/mm/filemap.c b/mm/filemap.c
> index 12548d03c11d..467768d4263b 100644
> --- a/mm/filemap.c
> +++ b/mm/filemap.c
> @@ -615,11 +615,11 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
>   	void *shadow = NULL;
>   	int ret;
>
> -	__set_page_locked(page);
> +	__SetPageLocked(page);
>   	ret = __add_to_page_cache_locked(page, mapping, offset,
>   					 gfp_mask, &shadow);
>   	if (unlikely(ret))
> -		__clear_page_locked(page);
> +		__ClearPageLocked(page);
>   	else {
>   		/*
>   		 * The page might have been evicted from cache only
> @@ -742,6 +742,7 @@ EXPORT_SYMBOL_GPL(add_page_wait_queue);
>    */
>   void unlock_page(struct page *page)
>   {
> +	page = compound_head(page);
>   	VM_BUG_ON_PAGE(!PageLocked(page), page);
>   	clear_bit_unlock(PG_locked, &page->flags);
>   	smp_mb__after_atomic();
> @@ -806,18 +807,20 @@ EXPORT_SYMBOL_GPL(page_endio);
>    */
>   void __lock_page(struct page *page)
>   {
> -	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
> +	struct page *page_head = compound_head(page);
> +	DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked);
>
> -	__wait_on_bit_lock(page_waitqueue(page), &wait, bit_wait_io,
> +	__wait_on_bit_lock(page_waitqueue(page_head), &wait, bit_wait_io,
>   							TASK_UNINTERRUPTIBLE);
>   }
>   EXPORT_SYMBOL(__lock_page);
>
>   int __lock_page_killable(struct page *page)
>   {
> -	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
> +	struct page *page_head = compound_head(page);
> +	DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked);
>
> -	return __wait_on_bit_lock(page_waitqueue(page), &wait,
> +	return __wait_on_bit_lock(page_waitqueue(page_head), &wait,
>   					bit_wait_io, TASK_KILLABLE);
>   }
>   EXPORT_SYMBOL_GPL(__lock_page_killable);
> diff --git a/mm/ksm.c b/mm/ksm.c
> index 4162dce2eb44..23138e99a531 100644
> --- a/mm/ksm.c
> +++ b/mm/ksm.c
> @@ -1884,7 +1884,7 @@ struct page *ksm_might_need_to_copy(struct page *page,
>
>   		SetPageDirty(new_page);
>   		__SetPageUptodate(new_page);
> -		__set_page_locked(new_page);
> +		__SetPageLocked(new_page);
>   	}
>
>   	return new_page;
> diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> index d487f8dc6d39..399eee44d13d 100644
> --- a/mm/memory-failure.c
> +++ b/mm/memory-failure.c
> @@ -1136,7 +1136,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
>   	/*
>   	 * We ignore non-LRU pages for good reasons.
>   	 * - PG_locked is only well defined for LRU pages and a few others
> -	 * - to avoid races with __set_page_locked()
> +	 * - to avoid races with __SetPageLocked()
>   	 * - to avoid races with __SetPageSlab*() (and more non-atomic ops)
>   	 * The check (unnecessarily) ignores LRU pages being isolated and
>   	 * walked by the page reclaim code, however that's not a big loss.
> diff --git a/mm/migrate.c b/mm/migrate.c
> index 6aa9a4222ea9..114602a68111 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -1734,7 +1734,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
>   		flush_tlb_range(vma, mmun_start, mmun_end);
>
>   	/* Prepare a page as a migration target */
> -	__set_page_locked(new_page);
> +	__SetPageLocked(new_page);
>   	SetPageSwapBacked(new_page);
>
>   	/* anon mapping, we can simply copy page->mapping to the new page: */
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 80b360c7bcd1..2e2b943c8e62 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -981,7 +981,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
>   	copy_highpage(newpage, oldpage);
>   	flush_dcache_page(newpage);
>
> -	__set_page_locked(newpage);
> +	__SetPageLocked(newpage);
>   	SetPageUptodate(newpage);
>   	SetPageSwapBacked(newpage);
>   	set_page_private(newpage, swap_index);
> @@ -1173,7 +1173,7 @@ repeat:
>   		}
>
>   		__SetPageSwapBacked(page);
> -		__set_page_locked(page);
> +		__SetPageLocked(page);
>   		if (sgp == SGP_WRITE)
>   			__SetPageReferenced(page);
>
> diff --git a/mm/slub.c b/mm/slub.c
> index 2584d4ff02eb..f33ae2b7a5e7 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -338,11 +338,13 @@ static inline int oo_objects(struct kmem_cache_order_objects x)
>    */
>   static __always_inline void slab_lock(struct page *page)
>   {
> +	VM_BUG_ON_PAGE(PageTail(page), page);
>   	bit_spin_lock(PG_locked, &page->flags);
>   }
>
>   static __always_inline void slab_unlock(struct page *page)
>   {
> +	VM_BUG_ON_PAGE(PageTail(page), page);
>   	__bit_spin_unlock(PG_locked, &page->flags);
>   }
>
> diff --git a/mm/swap_state.c b/mm/swap_state.c
> index 405923f77334..d1c4a25b4362 100644
> --- a/mm/swap_state.c
> +++ b/mm/swap_state.c
> @@ -357,7 +357,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
>   		}
>
>   		/* May fail (-ENOMEM) if radix-tree node allocation failed. */
> -		__set_page_locked(new_page);
> +		__SetPageLocked(new_page);
>   		SetPageSwapBacked(new_page);
>   		err = __add_to_swap_cache(new_page, entry);
>   		if (likely(!err)) {
> @@ -371,7 +371,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
>   		}
>   		radix_tree_preload_end();
>   		ClearPageSwapBacked(new_page);
> -		__clear_page_locked(new_page);
> +		__ClearPageLocked(new_page);
>   		/*
>   		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
>   		 * clear SWAP_HAS_CACHE flag.
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 260c413d39cd..dc6cd51577a6 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -1062,7 +1062,7 @@ unmap:
>   				VM_BUG_ON_PAGE(PageSwapCache(page), page);
>   				if (!page_freeze_refs(page, 1))
>   					goto keep_locked;
> -				__clear_page_locked(page);
> +				__ClearPageLocked(page);
>   				count_vm_event(PGLAZYFREED);
>   				goto free_it;
>   			}
> @@ -1174,7 +1174,7 @@ unmap:
>   		 * we obviously don't have to worry about waking up a process
>   		 * waiting on the page lock, because there are no references.
>   		 */
> -		__clear_page_locked(page);
> +		__ClearPageLocked(page);
>   free_it:
>   		nr_reclaimed++;
>
> diff --git a/mm/zswap.c b/mm/zswap.c
> index 4249e82ff934..f8583f1fc938 100644
> --- a/mm/zswap.c
> +++ b/mm/zswap.c
> @@ -490,7 +490,7 @@ static int zswap_get_swap_cache_page(swp_entry_t entry,
>   		}
>
>   		/* May fail (-ENOMEM) if radix-tree node allocation failed. */
> -		__set_page_locked(new_page);
> +		__SetPageLocked(new_page);
>   		SetPageSwapBacked(new_page);
>   		err = __add_to_swap_cache(new_page, entry);
>   		if (likely(!err)) {
> @@ -501,7 +501,7 @@ static int zswap_get_swap_cache_page(swp_entry_t entry,
>   		}
>   		radix_tree_preload_end();
>   		ClearPageSwapBacked(new_page);
> -		__clear_page_locked(new_page);
> +		__ClearPageLocked(new_page);
>   		/*
>   		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
>   		 * clear SWAP_HAS_CACHE flag.
>

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 04/16] page-flags: define PG_locked behavior on compound pages

[Kirill A. Shutemov]

On Fri, Mar 27, 2015 at 04:13:08PM +0100, Mateusz Krawczuk wrote:
> Hi!
> 
> This patch breaks build of linux next since 2015-03-25 on arm using
> exynos_defconfig with arm-linux-gnueabi-linaro_4.7.4-2014.04,
> arm-linux-gnueabi-linaro_4.8.3-2014.04 and
> arm-linux-gnueabi-4.7.3-12ubuntu1(from ubuntu 14.04 lts). Compiler shows
> this error message:
> mm/migrate.c: In function a??migrate_pagesa??:
> mm/migrate.c:1148:1: internal compiler error: in push_minipool_fix, at
> config/arm/arm.c:13500
> Please submit a full bug report,
> with preprocessed source if appropriate.
> See <file:///usr/share/doc/gcc-4.7/README.Bugs> for instructions.
> 
> It builds fine with arm-linux-gnueabi-linaro_4.9.1-2014.07.

Obviously, you need to report bug against your compiler. It's not a kernel
bug.

-- 
 Kirill A. Shutemov

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 00/16] Sanitize usage of ->flags and ->mapping for tail pages

[Christoph Lameter]

On Thu, 19 Mar 2015, Kirill A. Shutemov wrote:

> Currently we take naive approach to page flags on compound -- we set the
> flag on the page without consideration if the flag makes sense for tail
> page or for compound page in general. This patchset try to sort this out
> by defining per-flag policy on what need to be done if page-flag helper
> operate on compound page.

Well we hand pointers to head pages around if handling compound pages.
References to tail pages are dicey and should only be used in a limited
way. At least that is true in the slab allocators and that was my
understanding in earlier years. Therefore it does not make sense
then check for tail pages.

> For now I catched one case of illigal usage of page flags or ->mapping:
> sound subsystem allocates pages with __GFP_COMP and maps them with PTEs.
> It leads to setting dirty bit on tail pages and access to tail_page's
> ->mapping. I don't see any bad behaviour caused by this, but worth fixing
> anyway.

Does this catch any errors?

> This patchset makes more sense if you take my THP refcounting into
> account: we will see more compound pages mapped with PTEs and we need to
> define behaviour of flags on compound pages to avoid bugs.

Ok that introduces the risk of pointers to tail pages becoming more of an
issue. But that does not affect non pagecache pages.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 04/16] page-flags: define PG_locked behavior on compound pages

[Christoph Lameter]

On Thu, 19 Mar 2015, Kirill A. Shutemov wrote:

> SLUB uses PG_locked as a bit spin locked. IIUC, tail pages should never
> appear there. VM_BUG_ON() is added to make sure that this assumption is
> correct.

Its really not worth checking that AFAICT. Tail page pointers are not
used.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 00/16] Sanitize usage of ->flags and ->mapping for tail pages

[Kirill A. Shutemov]

On Wed, Jul 15, 2015 at 03:20:01PM -0500, Christoph Lameter wrote:
> On Thu, 19 Mar 2015, Kirill A. Shutemov wrote:
> 
> > Currently we take naive approach to page flags on compound -- we set the
> > flag on the page without consideration if the flag makes sense for tail
> > page or for compound page in general. This patchset try to sort this out
> > by defining per-flag policy on what need to be done if page-flag helper
> > operate on compound page.
> 
> Well we hand pointers to head pages around if handling compound pages.
> References to tail pages are dicey and should only be used in a limited
> way. At least that is true in the slab allocators and that was my
> understanding in earlier years. Therefore it does not make sense
> then check for tail pages.

This is preparation patchset for THP refcounting rework. With new
refcounting sub-pages for THP can be mapped with PTEs, therefore we will
see tail pages returned from pte_page().

I've tried ad-hoc approach to page flags wrt tail pages on earlier (pre
LFS/MM) revisions of THP refcounting patchset. And IIRC, *you* pointed
that it would be nice to have more systematic approach.

And here's my attempt.

> > For now I catched one case of illigal usage of page flags or ->mapping:
> > sound subsystem allocates pages with __GFP_COMP and maps them with PTEs.
> > It leads to setting dirty bit on tail pages and access to tail_page's
> > ->mapping. I don't see any bad behaviour caused by this, but worth fixing
> > anyway.
> 
> Does this catch any errors?

It helped to catch BUG fixed by c761471b58e6 (mm: avoid tail page
refcounting on non-THP compound pages) and helped with work on
refcounting patchset.
 
> > This patchset makes more sense if you take my THP refcounting into
> > account: we will see more compound pages mapped with PTEs and we need to
> > define behaviour of flags on compound pages to avoid bugs.
> 
> Ok that introduces the risk of pointers to tail pages becoming more of an
> issue. But that does not affect non pagecache pages.

We don't have huge pages in pagecache yet. Refcounting patchset only
affects anon-THP. And makes compound pages suitable for pagecache.

We also have PTE-mapped compound pages -- in sound subsystem and some
drivers (framebuffer, etc.)

-- 
 Kirill A. Shutemov

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

page-flags behavior on compound pages: a worry

[Hugh Dickins]

Hi Kirill,

I had a nasty thought this morning.

Andrew had prodded me gently to re-examine my concerns with your
page-flags rework in mmotm.  I still dislike the bloat (my mm/built-in.o
text goes up from 478513 to 490183 bytes on a non-DEBUG_VM build); but I
was hoping to set that aside, to let us move forward.

But looking into the bloat led me to what seems a more serious issue
with it.  I'd tacked a little function on to the end of mm/filemap.c:

bool page_is_locked(struct page *page)
{
	return !!PageLocked(page);
}

which came out as:

0000000000003a60 <page_is_locked>:
    3a60:	48 8b 07             	mov    (%rdi),%rax
    3a63:	55                   	push   %rbp
    3a64:	48 89 e5             	mov    %rsp,%rbp

[instructions above same as without your patches; those below added by them]

    3a67:	f6 c4 80             	test   $0x80,%ah
    3a6a:	74 10                	je     3a7c <page_is_locked+0x1c>
    3a6c:	48 8b 47 30          	mov    0x30(%rdi),%rax
    3a70:	48 8b 17             	mov    (%rdi),%rdx
    3a73:	80 e6 80             	and    $0x80,%dh
    3a76:	48 0f 44 c7          	cmove  %rdi,%rax
    3a7a:	eb 03                	jmp    3a7f <page_is_locked+0x1f>
    3a7c:	48 89 f8             	mov    %rdi,%rax
    3a7f:	48 8b 00             	mov    (%rax),%rax

[instructions above added by your patches; those below same as before]

    3a82:	5d                   	pop    %rbp
    3a83:	83 e0 01             	and    $0x1,%eax
    3a86:	c3                   	retq   

The "and $0x80,%dh" looked superfluous at first, but of course it isn't:
it's from the smp_rmb() in David's 668f9abbd433 "mm: close PageTail race"
(a later commit refactors compound_head() but doesn't change the story).

And it's that race, or a worse race of that kind, that now worries me.
Relying on smp_wmb() and smp_rmb() may be all that was needed in the
case that David was fixing; and (I dare not look at them to audit!)
all uses of compound_head() in our current v4.2-rc tree may well be
safe, for this or that contingent reason in each place that it's used.

But there is no locking within compound_head(page) to make it safe
everywhere, yet your page-flags rework is changing a large number
of PageWhatever()s and SetPageWhatever()s and ClearPageWhatever()s
now to do a hidden compound_head(page) beneath the covers.

To be more specific: if preemption, or an interrupt, or entry to SMM
mode, or whatever, delays this thread somewhere in that compound_head()
sequence of instructions, how can we be sure that the "head" returned
by compound_head() is good?  We know the page was PageTail just before
looking up page->first_page, and we know it was PageTail just after,
but we don't know that it was PageTail throughout, and we don't know
whether page->first_page is even a good page pointer, or something
else from the private/ptl/slab_cache union.

Of course it would be very rare for it to go wrong; and most callsites
will obviously be safe for this or that reason; though, sadly, none of
them safe from holding a reference to the tail page in question, since
its count is frozen at 0 and cannot be grabbed by get_page_unless_zero.

But I don't see how it can be safe to rely on compound_head() inside
a general purpose page-flag function, that we're all accustomed to
think of as a simple bitop, that can be applied without great care.

Hugh

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: page-flags behavior on compound pages: a worry

[Kirill A. Shutemov]

On Wed, Aug 05, 2015 at 09:15:57PM -0700, Hugh Dickins wrote:
> Hi Kirill,
> 
> I had a nasty thought this morning.
 
Tough day.

I'm trying to wrap my head around this mail and not sure if I succeed
much. :-|

> Andrew had prodded me gently to re-examine my concerns with your
> page-flags rework in mmotm.  I still dislike the bloat (my mm/built-in.o
> text goes up from 478513 to 490183 bytes on a non-DEBUG_VM build); but I
> was hoping to set that aside, to let us move forward.
> 
> But looking into the bloat led me to what seems a more serious issue
> with it.  I'd tacked a little function on to the end of mm/filemap.c:
> 
> bool page_is_locked(struct page *page)
> {
> 	return !!PageLocked(page);
> }
> 
> which came out as:
> 
> 0000000000003a60 <page_is_locked>:
>     3a60:	48 8b 07             	mov    (%rdi),%rax
>     3a63:	55                   	push   %rbp
>     3a64:	48 89 e5             	mov    %rsp,%rbp
> 
> [instructions above same as without your patches; those below added by them]
> 
>     3a67:	f6 c4 80             	test   $0x80,%ah
>     3a6a:	74 10                	je     3a7c <page_is_locked+0x1c>
>     3a6c:	48 8b 47 30          	mov    0x30(%rdi),%rax
>     3a70:	48 8b 17             	mov    (%rdi),%rdx
>     3a73:	80 e6 80             	and    $0x80,%dh
>     3a76:	48 0f 44 c7          	cmove  %rdi,%rax
>     3a7a:	eb 03                	jmp    3a7f <page_is_locked+0x1f>
>     3a7c:	48 89 f8             	mov    %rdi,%rax
>     3a7f:	48 8b 00             	mov    (%rax),%rax
> 
> [instructions above added by your patches; those below same as before]
> 
>     3a82:	5d                   	pop    %rbp
>     3a83:	83 e0 01             	and    $0x1,%eax
>     3a86:	c3                   	retq   
> 
> The "and $0x80,%dh" looked superfluous at first, but of course it isn't:
> it's from the smp_rmb() in David's 668f9abbd433 "mm: close PageTail race"
> (a later commit refactors compound_head() but doesn't change the story).
> 
> And it's that race, or a worse race of that kind, that now worries me.
> Relying on smp_wmb() and smp_rmb() may be all that was needed in the
> case that David was fixing; and (I dare not look at them to audit!)
> all uses of compound_head() in our current v4.2-rc tree may well be
> safe, for this or that contingent reason in each place that it's used.
> 
> But there is no locking within compound_head(page) to make it safe
> everywhere, yet your page-flags rework is changing a large number
> of PageWhatever()s and SetPageWhatever()s and ClearPageWhatever()s
> now to do a hidden compound_head(page) beneath the covers.
> 
> To be more specific: if preemption, or an interrupt, or entry to SMM
> mode, or whatever, delays this thread somewhere in that compound_head()
> sequence of instructions, how can we be sure that the "head" returned
> by compound_head() is good?  We know the page was PageTail just before
> looking up page->first_page, and we know it was PageTail just after,
> but we don't know that it was PageTail throughout, and we don't know
> whether page->first_page is even a good page pointer, or something
> else from the private/ptl/slab_cache union.

That looks like a very valid worry to me. For current -mm tree.

But let's take my refcounting rework into picture.

One thing it simplifies is protection against splitting. Once you've got a
reference to a page, it cannot be split under you. It makes PageTail() and
->first_page stable for most callsites.

We can access the page's flags under ptl, without having reference the
page. And that's fine: ptl protects against splitting too.

Fast GUP also have a way to protect against split.

IIUC, the only potentially problematic callsites left are physical memory
scanners. This code requires audit. I'll do that.
 
Do I miss something else?

> Of course it would be very rare for it to go wrong; and most callsites
> will obviously be safe for this or that reason; though, sadly, none of
> them safe from holding a reference to the tail page in question, since
> its count is frozen at 0 and cannot be grabbed by get_page_unless_zero.

Do you mean that grabbing head page's ->_count is not enough to protect
against splitting and freeing tail page under you?

I know a patchset which solves this! ;)

> But I don't see how it can be safe to rely on compound_head() inside
> a general purpose page-flag function, that we're all accustomed to
> think of as a simple bitop, that can be applied without great care.
> 
> Hugh
> 
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org.  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

-- 
 Kirill A. Shutemov

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: page-flags behavior on compound pages: a worry

[Hugh Dickins]

On Thu, 6 Aug 2015, Kirill A. Shutemov wrote:
> On Wed, Aug 05, 2015 at 09:15:57PM -0700, Hugh Dickins wrote:
> > Hi Kirill,
> > 
> > I had a nasty thought this morning.
>  
> Tough day.
> 
> I'm trying to wrap my head around this mail and not sure if I succeed
> much. :-|

Sorry for not being clearer.

> > To be more specific: if preemption, or an interrupt, or entry to SMM
> > mode, or whatever, delays this thread somewhere in that compound_head()
> > sequence of instructions, how can we be sure that the "head" returned
> > by compound_head() is good?  We know the page was PageTail just before
> > looking up page->first_page, and we know it was PageTail just after,
> > but we don't know that it was PageTail throughout, and we don't know
> > whether page->first_page is even a good page pointer, or something
> > else from the private/ptl/slab_cache union.
> 
> That looks like a very valid worry to me. For current -mm tree.
> 
> But let's take my refcounting rework into picture.

Okay, let's do so.  I get very confused trying to think based on two
alternative schemes at the same time, so I'm happy to assume your
THP refcounting rework (which certainly has plenty to like in it
from the point of view of cleanup - though at present I think the
mlock splitting leaves it with a net regression in functionality).

That does say that this page-flags rework should not go to Linus
separately from your refcounting rework: I don't think the issues
here are ever likely to break someone's bisection, so it's fine for
the one series to precede the other, but any release should contain
both or neither.

> 
> One thing it simplifies is protection against splitting. Once you've got a
> reference to a page, it cannot be split under you. It makes PageTail() and
> ->first_page stable for most callsites.

Yes, but since you cannot acquire a reference to a tail page itself
(since it has count 0 throughout), don't you mean there that you
already hold a reference to the head?

In which case, why bother to make all the PageFlags operations on
tails redirect to the head: if the caller must hold a reference to
the head, then the caller should apply PageFlags to that head, with
no need for compound_head() redirection inside the operation, just a
VM_BUG_ON(PageTail).

Or so it seems from the outside: perhaps that becomes unworkable
somehow once you try to implement it.

> 
> We can access the page's flags under ptl, without having reference the
> page. And that's fine: ptl protects against splitting too.
> 
> Fast GUP also have a way to protect against split.

Yes and yes.  Perhaps it's those accesses under ptl which took you
in this compound_head-inside-PageFlags direction.  Fast GUP is easy
to do something special in, but there's probably a lot of scattered
PageFlags operations under ptl, which were tiresome to fiddle with
when you came to allow pte mappings of THP subpages.

> 
> IIUC, the only potentially problematic callsites left are physical memory
> scanners. This code requires audit. I'll do that.

Please.

>  
> Do I miss something else?

Probably not; but please check - and I'm afraid you've set things up
so that every use of a PageFlags operation needs to be thought about,
if only briefly.

It's certainly the physical approaches to a page (isolation, compaction,
formerly lumpy reclaim, are there others?  /proc things?) which have
always been very tricky to get right.

I think it was for those that David added the barriered double PageTail
checking.  I wonder if something extra special should be done just there,
in the physical scans; and the barriered double PageTail checking avoided
elsewhere, in the normal places that you reckon are safe already.

Mind you, shifting the unlikely PageTail handling out of line to a
called function would reduce the bloat considerably, then maybe it
wouldn't matter how complicated it gets for the general case.

> 
> > Of course it would be very rare for it to go wrong; and most callsites
> > will obviously be safe for this or that reason; though, sadly, none of
> > them safe from holding a reference to the tail page in question, since
> > its count is frozen at 0 and cannot be grabbed by get_page_unless_zero.
> 
> Do you mean that grabbing head page's ->_count is not enough to protect
> against splitting and freeing tail page under you?

No, I mean that if you know head already then why are you bothering with
tail; and if you only have tail, then locating head in all the cases where
the PageFlags operation might be called may be unsafe in a few of them.

And that it's not possible to acquire a reference to the tail page to
make this safe.  But I accept your point above, that the existence of
a pte in a locked page table amounts to a stable reference, even though
it does not contribute to that tail page's reference count.

> 
> I know a patchset which solves this! ;)

Oh, and I know a patchset which avoids these problems completely,
by not using compound pages at all ;)

Hugh

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: page-flags behavior on compound pages: a worry

[Christoph Lameter]

On Thu, 6 Aug 2015, Hugh Dickins wrote:

> > I know a patchset which solves this! ;)
>
> Oh, and I know a patchset which avoids these problems completely,
> by not using compound pages at all ;)

Another dumb idea: Stop the insanity of splitting pages on the fly?
Splitting pages should work like page migration: Lock everything down and
ensure no one is using the page and then do it. That way the compound pages
and its metadata are as stable as a regular page.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: page-flags behavior on compound pages: a worry

[Kirill A. Shutemov]

On Thu, Aug 06, 2015 at 12:24:22PM -0700, Hugh Dickins wrote:
> > I'm trying to wrap my head around this mail and not sure if I succeed
> > much. :-|
> 
> Sorry for not being clearer.

Not your fault.

The problem you've pointed to is on edge of my understanding of concurrency.

> On Thu, 6 Aug 2015, Kirill A. Shutemov wrote:
> > > To be more specific: if preemption, or an interrupt, or entry to SMM
> > > mode, or whatever, delays this thread somewhere in that compound_head()
> > > sequence of instructions, how can we be sure that the "head" returned
> > > by compound_head() is good?  We know the page was PageTail just before
> > > looking up page->first_page, and we know it was PageTail just after,
> > > but we don't know that it was PageTail throughout, and we don't know
> > > whether page->first_page is even a good page pointer, or something
> > > else from the private/ptl/slab_cache union.
> > 
> > That looks like a very valid worry to me. For current -mm tree.
> > 
> > But let's take my refcounting rework into picture.
> 
> Okay, let's do so.  I get very confused trying to think based on two
> alternative schemes at the same time, so I'm happy to assume your
> THP refcounting rework (which certainly has plenty to like in it
> from the point of view of cleanup - though at present I think the
> mlock splitting leaves it with a net regression in functionality).

The plan is to bring it a bit later. The refcounting patchset is huge
enough as it is.

> That does say that this page-flags rework should not go to Linus
> separately from your refcounting rework: I don't think the issues
> here are ever likely to break someone's bisection, so it's fine for
> the one series to precede the other, but any release should contain
> both or neither.

Agreed.

> > One thing it simplifies is protection against splitting. Once you've got a
> > reference to a page, it cannot be split under you. It makes PageTail() and
> > ->first_page stable for most callsites.
> 
> Yes, but since you cannot acquire a reference to a tail page itself
> (since it has count 0 throughout), don't you mean there that you
> already hold a reference to the head?
> 
> In which case, why bother to make all the PageFlags operations on
> tails redirect to the head: if the caller must hold a reference to
> the head, then the caller should apply PageFlags to that head, with
> no need for compound_head() redirection inside the operation, just a
> VM_BUG_ON(PageTail).

get_page() and put_page() hide the fact that refcounting is applied to
head page. And that's handy. Otherwise we would need drag pointers to two
pages on caller side, instead of one we have now.

The only special case is again get_page_unless_zero() users. They have to
deal with head vs. tail pages on their own. We have only few such places.
And it's manageable I believe.

> Or so it seems from the outside: perhaps that becomes unworkable
> somehow once you try to implement it.
> 
> > 
> > We can access the page's flags under ptl, without having reference the
> > page. And that's fine: ptl protects against splitting too.
> > 
> > Fast GUP also have a way to protect against split.
> 
> Yes and yes.  Perhaps it's those accesses under ptl which took you
> in this compound_head-inside-PageFlags direction.  Fast GUP is easy
> to do something special in, but there's probably a lot of scattered
> PageFlags operations under ptl, which were tiresome to fiddle with
> when you came to allow pte mappings of THP subpages.

Right.

> > IIUC, the only potentially problematic callsites left are physical memory
> > scanners. This code requires audit. I'll do that.
> 
> Please.

I'll bring some report on this next week.

> > Do I miss something else?
> 
> Probably not; but please check - and I'm afraid you've set things up
> so that every use of a PageFlags operation needs to be thought about,
> if only briefly.
> 
> It's certainly the physical approaches to a page (isolation, compaction,
> formerly lumpy reclaim, are there others?  /proc things?) which have
> always been very tricky to get right.

I didn't think about /proc as potential issue. Thanks.

> I think it was for those that David added the barriered double PageTail
> checking.  I wonder if something extra special should be done just there,
> in the physical scans; and the barriered double PageTail checking avoided
> elsewhere, in the normal places that you reckon are safe already.
> 
> Mind you, shifting the unlikely PageTail handling out of line to a
> called function would reduce the bloat considerably, then maybe it
> wouldn't matter how complicated it gets for the general case.

I'll try that.

> > > Of course it would be very rare for it to go wrong; and most callsites
> > > will obviously be safe for this or that reason; though, sadly, none of
> > > them safe from holding a reference to the tail page in question, since
> > > its count is frozen at 0 and cannot be grabbed by get_page_unless_zero.
> > 
> > Do you mean that grabbing head page's ->_count is not enough to protect
> > against splitting and freeing tail page under you?
> 
> No, I mean that if you know head already then why are you bothering with
> tail; and if you only have tail, then locating head in all the cases where
> the PageFlags operation might be called may be unsafe in a few of them.

See above.

> And that it's not possible to acquire a reference to the tail page to
> make this safe.  But I accept your point above, that the existence of
> a pte in a locked page table amounts to a stable reference, even though
> it does not contribute to that tail page's reference count.
> 
> > 
> > I know a patchset which solves this! ;)
> 
> Oh, and I know a patchset which avoids these problems completely,
> by not using compound pages at all ;)

BTW, I haven't heard anything about the patchset for a while.
What's the status?

Optimizing rmap operations in my patchset (see PG_double_map), I found
that it would be very tricky to expand team pages to anon-THP without
performance regression on rmap side due to amount of atomic ops it
requires.

Is there any clever approach to the issue?

Team pages are probably fine for file mappings due different performance
baseline. I'm less optimistic about anon-THP.

-- 
 Kirill A. Shutemov

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: page-flags behavior on compound pages: a worry

[Kirill A. Shutemov]

On Thu, Aug 06, 2015 at 03:45:31PM -0500, Christoph Lameter wrote:
> On Thu, 6 Aug 2015, Hugh Dickins wrote:
> 
> > > I know a patchset which solves this! ;)
> >
> > Oh, and I know a patchset which avoids these problems completely,
> > by not using compound pages at all ;)
> 
> Another dumb idea: Stop the insanity of splitting pages on the fly?
> Splitting pages should work like page migration: Lock everything down and
> ensure no one is using the page and then do it. That way the compound pages
> and its metadata are as stable as a regular page.
 
That's what I do in refcounting patchset.

-- 
 Kirill A. Shutemov

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: page-flags behavior on compound pages: a worry

[Christoph Lameter]

On Fri, 7 Aug 2015, Kirill A. Shutemov wrote:

> On Thu, Aug 06, 2015 at 03:45:31PM -0500, Christoph Lameter wrote:
> > On Thu, 6 Aug 2015, Hugh Dickins wrote:
> >
> > > > I know a patchset which solves this! ;)
> > >
> > > Oh, and I know a patchset which avoids these problems completely,
> > > by not using compound pages at all ;)
> >
> > Another dumb idea: Stop the insanity of splitting pages on the fly?
> > Splitting pages should work like page migration: Lock everything down and
> > ensure no one is using the page and then do it. That way the compound pages
> > and its metadata are as stable as a regular page.
>
> That's what I do in refcounting patchset.

Looks like you make refcounting easier and avoid splitting in some cases
maybe only splitting the pmd. But the fundamental issue still remains.
Complexity is high since individual pages of a compound can be mapped and
unmapped in multiple processes.

The compound would need to be always treated as a single order N entity
in order to really get things simplified and make code cleaner.

Either all pages are mapped or none. Otherwise you have to manage the
a schizoprenic view of pages. Sometimes an order N size entity is
managed and sometimes a base page size page which is a fraction of the
whole. Such a view of a memory object is pretty difficult to manage.






--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: page-flags behavior on compound pages: a worry

[Kirill A. Shutemov]

On Fri, Aug 07, 2015 at 10:28:49AM -0500, Christoph Lameter wrote:
> On Fri, 7 Aug 2015, Kirill A. Shutemov wrote:
> 
> > On Thu, Aug 06, 2015 at 03:45:31PM -0500, Christoph Lameter wrote:
> > > On Thu, 6 Aug 2015, Hugh Dickins wrote:
> > >
> > > > > I know a patchset which solves this! ;)
> > > >
> > > > Oh, and I know a patchset which avoids these problems completely,
> > > > by not using compound pages at all ;)
> > >
> > > Another dumb idea: Stop the insanity of splitting pages on the fly?
> > > Splitting pages should work like page migration: Lock everything down and
> > > ensure no one is using the page and then do it. That way the compound pages
> > > and its metadata are as stable as a regular page.
> >
> > That's what I do in refcounting patchset.
> 
> Looks like you make refcounting easier and avoid splitting in some cases
> maybe only splitting the pmd. But the fundamental issue still remains.
> Complexity is high since individual pages of a compound can be mapped and
> unmapped in multiple processes.
> 
> The compound would need to be always treated as a single order N entity
> in order to really get things simplified and make code cleaner.
> 
> Either all pages are mapped or none. Otherwise you have to manage the
> a schizoprenic view of pages. Sometimes an order N size entity is
> managed and sometimes a base page size page which is a fraction of the
> whole. Such a view of a memory object is pretty difficult to manage.

I don't see anything actionable here. Your wish list doesn't cope with
reality. Compound pages are mapped with PTEs for almost ten years and I
don't see why we should stop the practice.

-- 
 Kirill A. Shutemov

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: page-flags behavior on compound pages: a worry

[Christoph Lameter]

On Mon, 10 Aug 2015, Kirill A. Shutemov wrote:

> I don't see anything actionable here. Your wish list doesn't cope with
> reality. Compound pages are mapped with PTEs for almost ten years and I
> don't see why we should stop the practice.

Well they have to if they are smaller than huge pages. Treating each PTE
as each having their own state instead of having the whole compound mapped
completely causes the problem. Refcounting in tail pages is not necessary
if the whole compound is either mapped or not mapped at all by a process.
Refcounting in tail pages is only necessary if you allow 4k slices to be
mapped.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: page-flags behavior on compound pages: a worry

[Kirill A. Shutemov]

On Thu, Aug 06, 2015 at 12:24:22PM -0700, Hugh Dickins wrote:
> > IIUC, the only potentially problematic callsites left are physical memory
> > scanners. This code requires audit. I'll do that.
> 
> Please.

I haven't finished the exercise yet. But here's an issue I believe present
in current *Linus* tree:

Re: page-flags behavior on compound pages: a worry

[Vlastimil Babka]

On 08/12/2015 04:35 PM, Kirill A. Shutemov wrote:
> On Thu, Aug 06, 2015 at 12:24:22PM -0700, Hugh Dickins wrote:
>>> IIUC, the only potentially problematic callsites left are physical memory
>>> scanners. This code requires audit. I'll do that.
>>
>> Please.
>
> I haven't finished the exercise yet. But here's an issue I believe present
> in current *Linus* tree:
>
>  From e78eec7d7a8c4cba8b5952a997973f7741e704f4 Mon Sep 17 00:00:00 2001
> From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
> Date: Wed, 12 Aug 2015 17:09:16 +0300
> Subject: [PATCH] mm: fix potential race in isolate_migratepages_block()
>
> Hugh has pointed that compound_head() call can be unsafe in some context.
> There's one example:
>
> 	CPU0					CPU1
>
> isolate_migratepages_block()
>    page_count()
>      compound_head()
>        !!PageTail() == true
> 					put_page()
> 					  tail->first_page = NULL
>        head = tail->first_page
> 					alloc_pages(__GFP_COMP)
> 					   prep_compound_page()
> 					     tail->first_page = head
> 					     __SetPageTail(p);
>        !!PageTail() == true
>      <head == NULL dereferencing>
>
> The race is pure theoretical. I don't it's possible to trigger it in
> practice. But who knows.

It's even less probable thanks to the fact that before this check we 
determined it's a PageLRU (and thus !PageTail).

>
> This can be fixed by avoiding compound_head() in unsafe context.

This is OK because if page becomes tail and we read zero page count, 
it's not fatal.

> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>

Fixes: 119d6d59dc ("mm, compaction: avoid isolating pinned pages")

Potentially stable 3.15+ if theoretical races qualify. They don't per 
stable rules, but we seem to be bending that a lot anyway.

> Cc: Hugh Dickins <hughd@google.com>
> Cc: David Rientjes <rientjes@google.com>
> Cc: Vlastimil Babka <vbabka@suse.cz>

Acked-by: Vlastimil Babka <vbabka@suse.cz>

> ---
>   mm/compaction.c | 2 +-
>   1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/mm/compaction.c b/mm/compaction.c
> index 86f04e556f96..bec727b700d3 100644
> --- a/mm/compaction.c
> +++ b/mm/compaction.c
> @@ -787,7 +787,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
>   		 * admittedly racy check.
>   		 */
>   		if (!page_mapping(page) &&
> -		    page_count(page) > page_mapcount(page))
> +		    atomic_read(&page->_count) > page_mapcount(page))
>   			continue;
>
>   		/* If we already hold the lock, we can skip some rechecking */
>

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: page-flags behavior on compound pages: a worry

[Andrew Morton]

On Wed, 12 Aug 2015 17:35:09 +0300 "Kirill A. Shutemov" <kirill@shutemov.name> wrote:

> On Thu, Aug 06, 2015 at 12:24:22PM -0700, Hugh Dickins wrote:
> > > IIUC, the only potentially problematic callsites left are physical memory
> > > scanners. This code requires audit. I'll do that.
> > 
> > Please.
> 
> I haven't finished the exercise yet. But here's an issue I believe present
> in current *Linus* tree:
> 
> >From e78eec7d7a8c4cba8b5952a997973f7741e704f4 Mon Sep 17 00:00:00 2001
> From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
> Date: Wed, 12 Aug 2015 17:09:16 +0300
> Subject: [PATCH] mm: fix potential race in isolate_migratepages_block()
> 
> Hugh has pointed that compound_head() call can be unsafe in some context.
> There's one example:
> 
> 	CPU0					CPU1
> 
> isolate_migratepages_block()
>   page_count()
>     compound_head()
>       !!PageTail() == true
> 					put_page()
> 					  tail->first_page = NULL
>       head = tail->first_page
> 					alloc_pages(__GFP_COMP)
> 					   prep_compound_page()
> 					     tail->first_page = head
> 					     __SetPageTail(p);
>       !!PageTail() == true
>     <head == NULL dereferencing>
> 
> The race is pure theoretical. I don't it's possible to trigger it in
> practice. But who knows.
> 
> This can be fixed by avoiding compound_head() in unsafe context.

This is nuts :( page_count() should Just Work without us having to
worry about bizarre races against splitting.  Sigh.

> --- a/mm/compaction.c
> +++ b/mm/compaction.c
> @@ -787,7 +787,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
>  		 * admittedly racy check.
>  		 */
>  		if (!page_mapping(page) &&
> -		    page_count(page) > page_mapcount(page))
> +		    atomic_read(&page->_count) > page_mapcount(page))
>  			continue;

If we're going to do this sort of thing, can we please do it in a more
transparent manner?  Let's not sprinkle unexplained and
incomprehensible direct accesses to ->_count all over the place.

Create a formal function to do this, with an appropriate name and with
documentation which fully explains what's going on.  Then use that
here, and in has_unmovable_pages() (at least).

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: page-flags behavior on compound pages: a worry

[Kirill A. Shutemov]

On Wed, Aug 12, 2015 at 02:16:44PM -0700, Andrew Morton wrote:
> On Wed, 12 Aug 2015 17:35:09 +0300 "Kirill A. Shutemov" <kirill@shutemov.name> wrote:
> 
> > On Thu, Aug 06, 2015 at 12:24:22PM -0700, Hugh Dickins wrote:
> > > > IIUC, the only potentially problematic callsites left are physical memory
> > > > scanners. This code requires audit. I'll do that.
> > > 
> > > Please.
> > 
> > I haven't finished the exercise yet. But here's an issue I believe present
> > in current *Linus* tree:
> > 
> > >From e78eec7d7a8c4cba8b5952a997973f7741e704f4 Mon Sep 17 00:00:00 2001
> > From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
> > Date: Wed, 12 Aug 2015 17:09:16 +0300
> > Subject: [PATCH] mm: fix potential race in isolate_migratepages_block()
> > 
> > Hugh has pointed that compound_head() call can be unsafe in some context.
> > There's one example:
> > 
> > 	CPU0					CPU1
> > 
> > isolate_migratepages_block()
> >   page_count()
> >     compound_head()
> >       !!PageTail() == true
> > 					put_page()
> > 					  tail->first_page = NULL
> >       head = tail->first_page
> > 					alloc_pages(__GFP_COMP)
> > 					   prep_compound_page()
> > 					     tail->first_page = head
> > 					     __SetPageTail(p);
> >       !!PageTail() == true
> >     <head == NULL dereferencing>
> > 
> > The race is pure theoretical. I don't it's possible to trigger it in
> > practice. But who knows.
> > 
> > This can be fixed by avoiding compound_head() in unsafe context.
> 
> This is nuts :( page_count() should Just Work without us having to
> worry about bizarre races against splitting.  Sigh.

Split is not involved. And this race is present even for THP=n. :(

> 
> > --- a/mm/compaction.c
> > +++ b/mm/compaction.c
> > @@ -787,7 +787,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
> >  		 * admittedly racy check.
> >  		 */
> >  		if (!page_mapping(page) &&
> > -		    page_count(page) > page_mapcount(page))
> > +		    atomic_read(&page->_count) > page_mapcount(page))
> >  			continue;
> 
> If we're going to do this sort of thing, can we please do it in a more
> transparent manner?  Let's not sprinkle unexplained and
> incomprehensible direct accesses to ->_count all over the place.
> 
> Create a formal function to do this, with an appropriate name and with
> documentation which fully explains what's going on.  Then use that
> here, and in has_unmovable_pages() (at least).

All this situation is ugly. I'm thinking on more general solution for
PageTail() vs. ->first_page race.

We would be able to avoid the race in first place if we encode PageTail()
and position of head page within the same word in struct page. This way we
update both thing in one shot without possibility of race.

Details get tricky.

I'm going to try tomorrow something like this: encode the position of head
as offset from the tail page and store it as negative number in the union
with ->mapping and ->s_mem. PageTail() can be implemented as check value
of the field to be in range -1..-MAX_ORDER_NR_PAGES. 

I'm not sure at all if it's going to work, especially looking on
ridiculously high CONFIG_FORCE_MAX_ZONEORDER some architectures allow.

We could also try to encode page order instead (again as negative number)
and calculate head page position based on alignment...

Any other ideas are welcome.

-- 
 Kirill A. Shutemov

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: page-flags behavior on compound pages: a worry

[Hugh Dickins]

On Thu, 13 Aug 2015, Kirill A. Shutemov wrote:
> 
> All this situation is ugly. I'm thinking on more general solution for
> PageTail() vs. ->first_page race.
> 
> We would be able to avoid the race in first place if we encode PageTail()
> and position of head page within the same word in struct page. This way we
> update both thing in one shot without possibility of race.
> 
> Details get tricky.
> 
> I'm going to try tomorrow something like this: encode the position of head
> as offset from the tail page and store it as negative number in the union
> with ->mapping and ->s_mem. PageTail() can be implemented as check value
> of the field to be in range -1..-MAX_ORDER_NR_PAGES. 
> 
> I'm not sure at all if it's going to work, especially looking on
> ridiculously high CONFIG_FORCE_MAX_ZONEORDER some architectures allow.
> 
> We could also try to encode page order instead (again as negative number)
> and calculate head page position based on alignment...
> 
> Any other ideas are welcome.

Good luck, I've not given it any thought, but hope it works out:
my reasoning was the same when I put the PageAnon bit into
page->mapping instead of page->flags.

Something to beware of though: although exceedingly unlikely to be a
problem, page->mapping always contained a pointer to or into a relevant
structure, or else something that could not possibly be a kernel pointer,
when I was working on KSM swapping: see comment above get_ksm_page() in
mm/ksm.c.  It is best to keep page->mapping for pointers if possible
(and probably avoid having the PageAnon bit set unless really Anon).

I've only just read your mail, and I'm too slow a thinker to have
worked through your isolate_migratepages_block() race yet.  But, given
the timing, cannot resist sending you a code fragment I wrote earlier
today for our v3.11-based kernel: which still has compound_trans_order(),
which we had been using in a similar racy physical scan.

I'm not for a moment suggesting that this fragment is relevant to your
race; but it is something amusing to consider when you're thinking of
such races.  Credit to Greg Thelen for thinking of the prep_compound_page()
end of it, when I'd been focussed on the __split_huge_page_refcount() end.

	/*
	 * It is not safe to use compound_lock (inside compound_trans_order)
	 * until we have a reference on the page (okay, done above) and have
	 * then seen PageLRU on it (just below): because mm/huge_memory.c uses
	 * the non-atomic __SetPageUptodate on a freshly allocated THPage in
	 * several places, believing it to be invisible to the outside world,
	 * but liable to race and leave PG_compound_lock set when cleared here.
	 */
	nr_pages = 1;
	if (PageHead(page)) {
		/*
		 * smp_rmb() against the smp_wmb() in the first iteration of
		 * prep_compound_page(), so that the PageTail test ensures
		 * that compound_order(page) is now correctly readable.
		 */
		smp_rmb();
		if (PageTail(page + 1)) {
			nr_pages = 1 << compound_order(page);
			/*
			 * Then smp_rmb() against smp_wmb() in last iteration of
			 * __split_huge_page_refcount(), to ensure that has not
			 * yet written something else into page[1].lru.prev.
			 */
			smp_rmb();
			if (!PageTail(page + 1))
				nr_pages = 1;
		}
	}

Hugh

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: page-flags behavior on compound pages: a worry

[Hugh Dickins]

On Fri, 7 Aug 2015, Kirill A. Shutemov wrote:
> On Thu, Aug 06, 2015 at 12:24:22PM -0700, Hugh Dickins wrote:
> > 
> > Oh, and I know a patchset which avoids these problems completely,
> > by not using compound pages at all ;)
> 
> BTW, I haven't heard anything about the patchset for a while.
> What's the status?

It's gone well, and being put into wider use here.  But I'm not
one for monthly updates of large patchsets myself, always too much
to do; and nobody else seemed anxious to have it yet, back in March.

As I said at the time of posting huge tmpfs against v3.19, it was
fully working (and little changed since), but once memory pressure
had disbanded a team to swap it out, there was nothing to put it
together again later, to restore the original hugepage performance.

I couldn't imagine people putting it into real use while that remained
the case, so spent the next months adding "huge tmpfs recovery" -
considered hooking into khugepaged, but settled on work item queued
from fault.

Which has worked out well, except that I had to rush it in before
I went on vacation in June, then spent last month fixing all the
concurrent hole-punching bugs Andres found with his fuzzing while
I was away.  Busy time, stable now; but I do want to reconsider a
few rushed decisions before offering the rebased and extended set.

And there's three pieces of the work not begun:

The page-table allocation delay in mm/memory.c had been great for
the first posting, but not good enough for recovery (replacing ptes
by pmd): for the moment I skate around that by guarding with mmap_sem,
but mmap_sem usually ends up regrettable, and shouldn't be necessary -
there's just a lot of scattered walks to work through, adjusting them
to racy replacement of ptes by pmd.  Maybe I can get away without
doing this for now, we seem to be working well enough without it.

And I suspect that my queueing a recovery work item from fault
is over eager, needs some stats and knobs to tune it down.  Though
not surfaced as a problem yet; and I don't think we could live with
the opposite extreme, of khugepaged lumbering its way around the vmas.

But the one I think I shall have to do something better about before
posting, is NUMA.  For a confluence of reasons, that rule out swapin
readahead for now, it's not a serious issue for us as yet.  But swapin
readahead and NUMA have always been a joke in tmpfs, and I'll be
amplifying that joke with my current NUMA placement in recovery.
Unfortunately, there's a lot of opportunity to make silly mistakes
when trying to get NUMA right: I doubt I can get it right, but do
need to get it a little less wrong before letting others take over.

> 
> Optimizing rmap operations in my patchset (see PG_double_map), I found
> that it would be very tricky to expand team pages to anon-THP without
> performance regression on rmap side due to amount of atomic ops it
> requires.

Thanks for thinking of it: I've been too busy with the recovery
to put more thought into extending teams to anon THP, though I'd
certainly like to try that once the huge tmpfs end is "complete".

Yes, there's not a doubt that starting from compound pages is more
rigid but should involve much less repetition; whereas starting from
the other end with a team of ordinary 4k pages, more flexible but a
lot of wasted effort.  I can't predict where we shall meet.

> 
> Is there any clever approach to the issue?

I'd been hoping that I could implement first, and then optimize away
the unnecessary; but you're right that it's easier to live with that
in the pagecache case, whereas with anon THP it would be a regression.

Hugh

> 
> Team pages are probably fine for file mappings due different performance
> baseline. I'm less optimistic about anon-THP.
> 
> -- 
>  Kirill A. Shutemov

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 09/16] page-flags: define PG_reserved behavior on compound pages

[Chris Wilson]

Quoting Kirill A. Shutemov (2015-03-19 17:08:15)
> As far as I can see there's no users of PG_reserved on compound pages.
> Let's use NO_COMPOUND here.

Much later than you would ever expect, but we just had a user update an
ancient device and trip over this.
https://gitlab.freedesktop.org/drm/intel/issues/1027

In drm_pci_alloc() we allocate a high-order page (for it to be physically
contiguous) and mark each page as Reserved.

        dmah->vaddr = dma_alloc_coherent(&dev->pdev->dev, size,
                                         &dmah->busaddr,
                                         GFP_KERNEL | __GFP_COMP);

        /* XXX - Is virt_to_page() legal for consistent mem? */
        /* Reserve */
        for (addr = (unsigned long)dmah->vaddr, sz = size;
             sz > 0; addr += PAGE_SIZE, sz -= PAGE_SIZE) {
                SetPageReserved(virt_to_page((void *)addr));
        }

It's been doing that since

commit ddf19b973be5a96d77c8467f657fe5bd7d126e0f
Author: Dave Airlie <airlied@linux.ie>
Date:   Sun Mar 19 18:56:12 2006 +1100

    drm: fixup PCI DMA support

I haven't found anything to say if we are meant to be reserving the
pages or not. So I bring it to your attention, asking for help.

Thanks,
-Chris

Re: [PATCH 09/16] page-flags: define PG_reserved behavior on compound pages

[Kirill A. Shutemov]

On Fri, Jan 31, 2020 at 03:24:12PM +0000, Chris Wilson wrote:
> Quoting Kirill A. Shutemov (2015-03-19 17:08:15)
> > As far as I can see there's no users of PG_reserved on compound pages.
> > Let's use NO_COMPOUND here.
> 
> Much later than you would ever expect, but we just had a user update an
> ancient device and trip over this.
> https://gitlab.freedesktop.org/drm/intel/issues/1027
> 
> In drm_pci_alloc() we allocate a high-order page (for it to be physically
> contiguous) and mark each page as Reserved.
> 
>         dmah->vaddr = dma_alloc_coherent(&dev->pdev->dev, size,
>                                          &dmah->busaddr,
>                                          GFP_KERNEL | __GFP_COMP);
> 
>         /* XXX - Is virt_to_page() legal for consistent mem? */
>         /* Reserve */
>         for (addr = (unsigned long)dmah->vaddr, sz = size;
>              sz > 0; addr += PAGE_SIZE, sz -= PAGE_SIZE) {
>                 SetPageReserved(virt_to_page((void *)addr));
>         }
> 
> It's been doing that since
> 
> commit ddf19b973be5a96d77c8467f657fe5bd7d126e0f
> Author: Dave Airlie <airlied@linux.ie>
> Date:   Sun Mar 19 18:56:12 2006 +1100
> 
>     drm: fixup PCI DMA support
> 
> I haven't found anything to say if we are meant to be reserving the
> pages or not. So I bring it to your attention, asking for help.

I don't see a real reason for these pages to be reserved. But I might be
wrong here.

I tried to look around: other users (infiniband/ethernet) of
dma_alloc_coherent(__GFP_COMP) don't mess with PG_reserved.

Could you try to drop it from DRM?

-- 
 Kirill A. Shutemov

Re: [PATCH 09/16] page-flags: define PG_reserved behavior on compound pages

[Chris Wilson]

Quoting Kirill A. Shutemov (2020-02-03 15:18:44)
> On Fri, Jan 31, 2020 at 03:24:12PM +0000, Chris Wilson wrote:
> > Quoting Kirill A. Shutemov (2015-03-19 17:08:15)
> > > As far as I can see there's no users of PG_reserved on compound pages.
> > > Let's use NO_COMPOUND here.
> > 
> > Much later than you would ever expect, but we just had a user update an
> > ancient device and trip over this.
> > https://gitlab.freedesktop.org/drm/intel/issues/1027
> > 
> > In drm_pci_alloc() we allocate a high-order page (for it to be physically
> > contiguous) and mark each page as Reserved.
> > 
> >         dmah->vaddr = dma_alloc_coherent(&dev->pdev->dev, size,
> >                                          &dmah->busaddr,
> >                                          GFP_KERNEL | __GFP_COMP);
> > 
> >         /* XXX - Is virt_to_page() legal for consistent mem? */
> >         /* Reserve */
> >         for (addr = (unsigned long)dmah->vaddr, sz = size;
> >              sz > 0; addr += PAGE_SIZE, sz -= PAGE_SIZE) {
> >                 SetPageReserved(virt_to_page((void *)addr));
> >         }
> > 
> > It's been doing that since
> > 
> > commit ddf19b973be5a96d77c8467f657fe5bd7d126e0f
> > Author: Dave Airlie <airlied@linux.ie>
> > Date:   Sun Mar 19 18:56:12 2006 +1100
> > 
> >     drm: fixup PCI DMA support
> > 
> > I haven't found anything to say if we are meant to be reserving the
> > pages or not. So I bring it to your attention, asking for help.
> 
> I don't see a real reason for these pages to be reserved. But I might be
> wrong here.
> 
> I tried to look around: other users (infiniband/ethernet) of
> dma_alloc_coherent(__GFP_COMP) don't mess with PG_reserved.
> 
> Could you try to drop it from DRM?

That is the current plan. So long as there is nothing magical about
either the __GFP_COMP or SetPageReserved, we should be able to drop them
without any functional change. Only 2 very old bits of HW (r128, ancient
i915) depend on this routine, and i915 seems, touch wood, quite happy
with a plain dma_alloc_coherent().
-Chris

Re: [PATCH 09/16] page-flags: define PG_reserved behavior on compound pages

[David Hildenbrand]

On 03.02.20 16:24, Chris Wilson wrote:
> Quoting Kirill A. Shutemov (2020-02-03 15:18:44)
>> On Fri, Jan 31, 2020 at 03:24:12PM +0000, Chris Wilson wrote:
>>> Quoting Kirill A. Shutemov (2015-03-19 17:08:15)
>>>> As far as I can see there's no users of PG_reserved on compound pages.
>>>> Let's use NO_COMPOUND here.
>>>
>>> Much later than you would ever expect, but we just had a user update an
>>> ancient device and trip over this.
>>> https://gitlab.freedesktop.org/drm/intel/issues/1027
>>>
>>> In drm_pci_alloc() we allocate a high-order page (for it to be physically
>>> contiguous) and mark each page as Reserved.
>>>
>>>         dmah->vaddr = dma_alloc_coherent(&dev->pdev->dev, size,
>>>                                          &dmah->busaddr,
>>>                                          GFP_KERNEL | __GFP_COMP);
>>>
>>>         /* XXX - Is virt_to_page() legal for consistent mem? */
>>>         /* Reserve */
>>>         for (addr = (unsigned long)dmah->vaddr, sz = size;
>>>              sz > 0; addr += PAGE_SIZE, sz -= PAGE_SIZE) {
>>>                 SetPageReserved(virt_to_page((void *)addr));
>>>         }
>>>
>>> It's been doing that since
>>>
>>> commit ddf19b973be5a96d77c8467f657fe5bd7d126e0f
>>> Author: Dave Airlie <airlied@linux.ie>
>>> Date:   Sun Mar 19 18:56:12 2006 +1100
>>>
>>>     drm: fixup PCI DMA support
>>>
>>> I haven't found anything to say if we are meant to be reserving the
>>> pages or not. So I bring it to your attention, asking for help.
>>
>> I don't see a real reason for these pages to be reserved. But I might be
>> wrong here.
>>
>> I tried to look around: other users (infiniband/ethernet) of
>> dma_alloc_coherent(__GFP_COMP) don't mess with PG_reserved.
>>
>> Could you try to drop it from DRM?
> 
> That is the current plan. So long as there is nothing magical about
> either the __GFP_COMP or SetPageReserved, we should be able to drop them
> without any functional change. Only 2 very old bits of HW (r128, ancient
> i915) depend on this routine, and i915 seems, touch wood, quite happy
> with a plain dma_alloc_coherent().

I documented a while ago in include/linux/page-flags.h

"
Pages marked as PG_reserved include:
[...]
MMIO/DMA pages. Some architectures don't allow to ioremap pages that are
not marked PG_reserved (as they might be in use by somebody else who
does not respect the caching strategy).
"

I also removed a bunch of users back then (and even had a patch to
remove this code here), but for this code I think I came to the
conclusion that it might be relevant for some archs.

git grep -o PageReserved | grep ioremap
arch/mips/mm/ioremap.c:PageReserved
arch/nios2/mm/ioremap.c:PageReserved
arch/parisc/mm/ioremap.c:PageReserved
arch/x86/mm/ioremap.c:PageReserved

It would be good to clarify if this here is actually needed (and in
addition the same pattern in other driver/ paths) and eventually update
the documentation.

-- 
Thanks,

David / dhildenb

Re: [PATCH 09/16] page-flags: define PG_reserved behavior on compound pages

[Christoph Hellwig]

On Mon, Feb 03, 2020 at 06:18:44PM +0300, Kirill A. Shutemov wrote:
> > Much later than you would ever expect, but we just had a user update an
> > ancient device and trip over this.
> > https://gitlab.freedesktop.org/drm/intel/issues/1027
> > 
> > In drm_pci_alloc() we allocate a high-order page (for it to be physically
> > contiguous) and mark each page as Reserved.
> > 
> >         dmah->vaddr = dma_alloc_coherent(&dev->pdev->dev, size,
> >                                          &dmah->busaddr,
> >                                          GFP_KERNEL | __GFP_COMP);
> > 
> >         /* XXX - Is virt_to_page() legal for consistent mem? */
> >         /* Reserve */
> >         for (addr = (unsigned long)dmah->vaddr, sz = size;
> >              sz > 0; addr += PAGE_SIZE, sz -= PAGE_SIZE) {
> >                 SetPageReserved(virt_to_page((void *)addr));
> >         }
> > 
> > It's been doing that since

This code is completely and utterly broken.  Drivers were never allowed
to call virt_to_page() on the memory returned from dma_alloc_coherent
(or pci_alloc_consistent before that), as many implementations return
virtual addresses that are not in the kernel mapping.  So this code
needs to go away and not papered over.

Re: [PATCH 03/16] page-flags: introduce page flags policies wrt compound pages

[Kirill A. Shutemov]

On Mon, Sep 28, 2015 at 02:48:12PM +0300, Konstantin Khlebnikov wrote:
> On 28.09.2015 14:03, Kirill A. Shutemov wrote:
> >On Mon, Sep 28, 2015 at 01:02:19PM +0300, Konstantin Khlebnikov wrote:
> >>On 25.09.2015 22:13, Kirill A. Shutemov wrote:
> >>>On Fri, Sep 25, 2015 at 03:29:17PM +0300, Konstantin Khlebnikov wrote:
> >>>>On 24.09.2015 17:50, Kirill A. Shutemov wrote:
> >>>>>This patch adds a third argument to macros which create function
> >>>>>definitions for page flags.  This argument defines how page-flags helpers
> >>>>>behave on compound functions.
> >>>>>
> >>>>>For now we define four policies:
> >>>>>
> >>>>>- PF_ANY: the helper function operates on the page it gets, regardless
> >>>>>   if it's non-compound, head or tail.
> >>>>>
> >>>>>- PF_HEAD: the helper function operates on the head page of the compound
> >>>>>   page if it gets tail page.
> >>>>>
> >>>>>- PF_NO_TAIL: only head and non-compond pages are acceptable for this
> >>>>>   helper function.
> >>>>>
> >>>>>- PF_NO_COMPOUND: only non-compound pages are acceptable for this helper
> >>>>>   function.
> >>>>>
> >>>>>For now we use policy PF_ANY for all helpers, which matches current
> >>>>>behaviour.
> >>>>>
> >>>>>We do not enforce the policy for TESTPAGEFLAG, because we have flags
> >>>>>checked for random pages all over the kernel.  Noticeable exception to
> >>>>>this is PageTransHuge() which triggers VM_BUG_ON() for tail page.
> >>>>>
> >>>>>Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> >>>>>---
> >>>>>  include/linux/page-flags.h | 154 ++++++++++++++++++++++++++-------------------
> >>>>>  1 file changed, 90 insertions(+), 64 deletions(-)
> >>>>>
> >>>>>diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
> >>>>>index 713d3f2c2468..1b3babe5ff69 100644
> >>>>>--- a/include/linux/page-flags.h
> >>>>>+++ b/include/linux/page-flags.h
> >>>>>@@ -154,49 +154,68 @@ static inline int PageCompound(struct page *page)
> >>>>>  	return test_bit(PG_head, &page->flags) || PageTail(page);
> >>>>>  }
> >>>>>
> >>>>>+/* Page flags policies wrt compound pages */
> >>>>>+#define PF_ANY(page, enforce)	page
> >>>>>+#define PF_HEAD(page, enforce)	compound_head(page)
> >>>>>+#define PF_NO_TAIL(page, enforce) ({					\
> >>>>>+		if (enforce)						\
> >>>>>+			VM_BUG_ON_PAGE(PageTail(page), page);		\
> >>>>>+		else							\
> >>>>>+			page = compound_head(page);			\
> >>>>>+		page;})
> >>>>>+#define PF_NO_COMPOUND(page, enforce) ({					\
> >>>>>+		if (enforce)						\
> >>>>>+			VM_BUG_ON_PAGE(PageCompound(page), page);	\
> >>>>
> >>>>Linux next-20150925 crashes here (at least in lkvm)
> >>>>if CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
> >>>
> >>>Hm. I don't see the crash in qemu. Could you share your config?
> >>
> >>see in attachment
> >
> >Still don't see it. Have you tried patch from my previous mail?
> >
> 
> Just checked: patch fixes oops.
> 
> 
> This part of 7e18adb4f80bea90d30b62158694d97c31f71d37
> (mm: meminit: initialise remaining struct pages in parallel with kswapd)
> is unclear:
> 
> +#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
> +static void init_reserved_page(unsigned long pfn)
> +{
> +       pg_data_t *pgdat;
> +       int nid, zid;
> +
> +       if (!early_page_uninitialised(pfn))
> +               return;
> +
> +       nid = early_pfn_to_nid(pfn);
> +       pgdat = NODE_DATA(nid);
> +
> +       for (zid = 0; zid < MAX_NR_ZONES; zid++) {
> +               struct zone *zone = &pgdat->node_zones[zid];
> +
> +               if (pfn >= zone->zone_start_pfn && pfn < zone_end_pfn(zone))
> +                       break;
> +       }
> +       __init_single_pfn(pfn, zid, nid);
> +}
> +#else
> +static inline void init_reserved_page(unsigned long pfn)
> +{
> +}
> +#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
> +
>  /*
>   * Initialised pages do not have PageReserved set. This function is
>   * called for each range allocated by the bootmem allocator and
>   * marks the pages PageReserved. The remaining valid pages are later
>   * sent to the buddy page allocator.
>   */
> -void reserve_bootmem_region(unsigned long start, unsigned long end)
> +void __meminit reserve_bootmem_region(unsigned long start, unsigned long
> end)
>  {
>         unsigned long start_pfn = PFN_DOWN(start);
>         unsigned long end_pfn = PFN_UP(end);
> 
> -       for (; start_pfn < end_pfn; start_pfn++)
> -               if (pfn_valid(start_pfn))
> -                       SetPageReserved(pfn_to_page(start_pfn));
> +       for (; start_pfn < end_pfn; start_pfn++) {
> +               if (pfn_valid(start_pfn)) {
> +                       struct page *page = pfn_to_page(start_pfn);
> +
> +                       init_reserved_page(start_pfn);
> +                       SetPageReserved(page);
> +               }
> +       }
>  }
> 
> We leave struct page uninitialized but call SetPageReserved for it.

__init_single_pfn() initializes the page.

I guess the problem is false-negative reply from
early_page_uninitialised(). No idea why it could happen.

Mel?

-- 
 Kirill A. Shutemov

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 03/16] page-flags: introduce page flags policies wrt compound pages

[Konstantin Khlebnikov]

On 28.09.2015 14:03, Kirill A. Shutemov wrote:
> On Mon, Sep 28, 2015 at 01:02:19PM +0300, Konstantin Khlebnikov wrote:
>> On 25.09.2015 22:13, Kirill A. Shutemov wrote:
>>> On Fri, Sep 25, 2015 at 03:29:17PM +0300, Konstantin Khlebnikov wrote:
>>>> On 24.09.2015 17:50, Kirill A. Shutemov wrote:
>>>>> This patch adds a third argument to macros which create function
>>>>> definitions for page flags.  This argument defines how page-flags helpers
>>>>> behave on compound functions.
>>>>>
>>>>> For now we define four policies:
>>>>>
>>>>> - PF_ANY: the helper function operates on the page it gets, regardless
>>>>>    if it's non-compound, head or tail.
>>>>>
>>>>> - PF_HEAD: the helper function operates on the head page of the compound
>>>>>    page if it gets tail page.
>>>>>
>>>>> - PF_NO_TAIL: only head and non-compond pages are acceptable for this
>>>>>    helper function.
>>>>>
>>>>> - PF_NO_COMPOUND: only non-compound pages are acceptable for this helper
>>>>>    function.
>>>>>
>>>>> For now we use policy PF_ANY for all helpers, which matches current
>>>>> behaviour.
>>>>>
>>>>> We do not enforce the policy for TESTPAGEFLAG, because we have flags
>>>>> checked for random pages all over the kernel.  Noticeable exception to
>>>>> this is PageTransHuge() which triggers VM_BUG_ON() for tail page.
>>>>>
>>>>> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
>>>>> ---
>>>>>   include/linux/page-flags.h | 154 ++++++++++++++++++++++++++-------------------
>>>>>   1 file changed, 90 insertions(+), 64 deletions(-)
>>>>>
>>>>> diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
>>>>> index 713d3f2c2468..1b3babe5ff69 100644
>>>>> --- a/include/linux/page-flags.h
>>>>> +++ b/include/linux/page-flags.h
>>>>> @@ -154,49 +154,68 @@ static inline int PageCompound(struct page *page)
>>>>>   	return test_bit(PG_head, &page->flags) || PageTail(page);
>>>>>   }
>>>>>
>>>>> +/* Page flags policies wrt compound pages */
>>>>> +#define PF_ANY(page, enforce)	page
>>>>> +#define PF_HEAD(page, enforce)	compound_head(page)
>>>>> +#define PF_NO_TAIL(page, enforce) ({					\
>>>>> +		if (enforce)						\
>>>>> +			VM_BUG_ON_PAGE(PageTail(page), page);		\
>>>>> +		else							\
>>>>> +			page = compound_head(page);			\
>>>>> +		page;})
>>>>> +#define PF_NO_COMPOUND(page, enforce) ({					\
>>>>> +		if (enforce)						\
>>>>> +			VM_BUG_ON_PAGE(PageCompound(page), page);	\
>>>>
>>>> Linux next-20150925 crashes here (at least in lkvm)
>>>> if CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
>>>
>>> Hm. I don't see the crash in qemu. Could you share your config?
>>
>> see in attachment
>
> Still don't see it. Have you tried patch from my previous mail?
>

Just checked: patch fixes oops.


This part of 7e18adb4f80bea90d30b62158694d97c31f71d37
(mm: meminit: initialise remaining struct pages in parallel with kswapd)
is unclear:

+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+static void init_reserved_page(unsigned long pfn)
+{
+       pg_data_t *pgdat;
+       int nid, zid;
+
+       if (!early_page_uninitialised(pfn))
+               return;
+
+       nid = early_pfn_to_nid(pfn);
+       pgdat = NODE_DATA(nid);
+
+       for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+               struct zone *zone = &pgdat->node_zones[zid];
+
+               if (pfn >= zone->zone_start_pfn && pfn < zone_end_pfn(zone))
+                       break;
+       }
+       __init_single_pfn(pfn, zid, nid);
+}
+#else
+static inline void init_reserved_page(unsigned long pfn)
+{
+}
+#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
+
  /*
   * Initialised pages do not have PageReserved set. This function is
   * called for each range allocated by the bootmem allocator and
   * marks the pages PageReserved. The remaining valid pages are later
   * sent to the buddy page allocator.
   */
-void reserve_bootmem_region(unsigned long start, unsigned long end)
+void __meminit reserve_bootmem_region(unsigned long start, unsigned 
long end)
  {
         unsigned long start_pfn = PFN_DOWN(start);
         unsigned long end_pfn = PFN_UP(end);

-       for (; start_pfn < end_pfn; start_pfn++)
-               if (pfn_valid(start_pfn))
-                       SetPageReserved(pfn_to_page(start_pfn));
+       for (; start_pfn < end_pfn; start_pfn++) {
+               if (pfn_valid(start_pfn)) {
+                       struct page *page = pfn_to_page(start_pfn);
+
+                       init_reserved_page(start_pfn);
+                       SetPageReserved(page);
+               }
+       }
  }

We leave struct page uninitialized but call SetPageReserved for it.

-- 
Konstantin

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 03/16] page-flags: introduce page flags policies wrt compound pages

[Kirill A. Shutemov]

On Mon, Sep 28, 2015 at 01:02:19PM +0300, Konstantin Khlebnikov wrote:
> On 25.09.2015 22:13, Kirill A. Shutemov wrote:
> >On Fri, Sep 25, 2015 at 03:29:17PM +0300, Konstantin Khlebnikov wrote:
> >>On 24.09.2015 17:50, Kirill A. Shutemov wrote:
> >>>This patch adds a third argument to macros which create function
> >>>definitions for page flags.  This argument defines how page-flags helpers
> >>>behave on compound functions.
> >>>
> >>>For now we define four policies:
> >>>
> >>>- PF_ANY: the helper function operates on the page it gets, regardless
> >>>   if it's non-compound, head or tail.
> >>>
> >>>- PF_HEAD: the helper function operates on the head page of the compound
> >>>   page if it gets tail page.
> >>>
> >>>- PF_NO_TAIL: only head and non-compond pages are acceptable for this
> >>>   helper function.
> >>>
> >>>- PF_NO_COMPOUND: only non-compound pages are acceptable for this helper
> >>>   function.
> >>>
> >>>For now we use policy PF_ANY for all helpers, which matches current
> >>>behaviour.
> >>>
> >>>We do not enforce the policy for TESTPAGEFLAG, because we have flags
> >>>checked for random pages all over the kernel.  Noticeable exception to
> >>>this is PageTransHuge() which triggers VM_BUG_ON() for tail page.
> >>>
> >>>Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> >>>---
> >>>  include/linux/page-flags.h | 154 ++++++++++++++++++++++++++-------------------
> >>>  1 file changed, 90 insertions(+), 64 deletions(-)
> >>>
> >>>diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
> >>>index 713d3f2c2468..1b3babe5ff69 100644
> >>>--- a/include/linux/page-flags.h
> >>>+++ b/include/linux/page-flags.h
> >>>@@ -154,49 +154,68 @@ static inline int PageCompound(struct page *page)
> >>>  	return test_bit(PG_head, &page->flags) || PageTail(page);
> >>>  }
> >>>
> >>>+/* Page flags policies wrt compound pages */
> >>>+#define PF_ANY(page, enforce)	page
> >>>+#define PF_HEAD(page, enforce)	compound_head(page)
> >>>+#define PF_NO_TAIL(page, enforce) ({					\
> >>>+		if (enforce)						\
> >>>+			VM_BUG_ON_PAGE(PageTail(page), page);		\
> >>>+		else							\
> >>>+			page = compound_head(page);			\
> >>>+		page;})
> >>>+#define PF_NO_COMPOUND(page, enforce) ({					\
> >>>+		if (enforce)						\
> >>>+			VM_BUG_ON_PAGE(PageCompound(page), page);	\
> >>
> >>Linux next-20150925 crashes here (at least in lkvm)
> >>if CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
> >
> >Hm. I don't see the crash in qemu. Could you share your config?
> 
> see in attachment

Still don't see it. Have you tried patch from my previous mail?

-- 
 Kirill A. Shutemov

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 03/16] page-flags: introduce page flags policies wrt compound pages

[Konstantin Khlebnikov]

[-- Attachment #1: Type: text/plain, Size: 6462 bytes --]

On 25.09.2015 22:13, Kirill A. Shutemov wrote:
> On Fri, Sep 25, 2015 at 03:29:17PM +0300, Konstantin Khlebnikov wrote:
>> On 24.09.2015 17:50, Kirill A. Shutemov wrote:
>>> This patch adds a third argument to macros which create function
>>> definitions for page flags.  This argument defines how page-flags helpers
>>> behave on compound functions.
>>>
>>> For now we define four policies:
>>>
>>> - PF_ANY: the helper function operates on the page it gets, regardless
>>>    if it's non-compound, head or tail.
>>>
>>> - PF_HEAD: the helper function operates on the head page of the compound
>>>    page if it gets tail page.
>>>
>>> - PF_NO_TAIL: only head and non-compond pages are acceptable for this
>>>    helper function.
>>>
>>> - PF_NO_COMPOUND: only non-compound pages are acceptable for this helper
>>>    function.
>>>
>>> For now we use policy PF_ANY for all helpers, which matches current
>>> behaviour.
>>>
>>> We do not enforce the policy for TESTPAGEFLAG, because we have flags
>>> checked for random pages all over the kernel.  Noticeable exception to
>>> this is PageTransHuge() which triggers VM_BUG_ON() for tail page.
>>>
>>> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
>>> ---
>>>   include/linux/page-flags.h | 154 ++++++++++++++++++++++++++-------------------
>>>   1 file changed, 90 insertions(+), 64 deletions(-)
>>>
>>> diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
>>> index 713d3f2c2468..1b3babe5ff69 100644
>>> --- a/include/linux/page-flags.h
>>> +++ b/include/linux/page-flags.h
>>> @@ -154,49 +154,68 @@ static inline int PageCompound(struct page *page)
>>>   	return test_bit(PG_head, &page->flags) || PageTail(page);
>>>   }
>>>
>>> +/* Page flags policies wrt compound pages */
>>> +#define PF_ANY(page, enforce)	page
>>> +#define PF_HEAD(page, enforce)	compound_head(page)
>>> +#define PF_NO_TAIL(page, enforce) ({					\
>>> +		if (enforce)						\
>>> +			VM_BUG_ON_PAGE(PageTail(page), page);		\
>>> +		else							\
>>> +			page = compound_head(page);			\
>>> +		page;})
>>> +#define PF_NO_COMPOUND(page, enforce) ({					\
>>> +		if (enforce)						\
>>> +			VM_BUG_ON_PAGE(PageCompound(page), page);	\
>>
>> Linux next-20150925 crashes here (at least in lkvm)
>> if CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
>
> Hm. I don't see the crash in qemu. Could you share your config?

see in attachment

>
>> [    0.000000] Kernel command line: noapic noacpi pci=conf1 reboot=k panic=1
>> i8042.direct=1 i8042.dumbkbd=1 i8042.nopnp=1 console=ttyS0
>> earlyprintk=serial i8042.noaux=1  root=/dev/root rw
>> rootflags=rw,trans=virtio,version=9p2000.L rootfstype=9p init=/virt/init
>> ip=dhcp
>> [    0.000000] PID hash table entries: 2048 (order: 2, 16384 bytes)
>> [    0.000000] BUG: unable to handle kernel NULL pointer dereference at
>> 000000000000000c
>> [    0.000000] IP: [<ffffffff811aaafb>] dump_page_badflags+0x2b/0xe0
>> [    0.000000] PGD 0
>> [    0.000000] Oops: 0000 [#1] SMP
>> [    0.000000] Modules linked in:
>> [    0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted
>> 4.3.0-rc2-next-20150925+ #2
>> [    0.000000] task: ffffffff81c12580 ti: ffffffff81c00000 task.ti:
>> ffffffff81c00000
>> [    0.000000] RIP: 0010:[<ffffffff811aaafb>]  [<ffffffff811aaafb>]
>> dump_page_badflags+0x2b/0xe0
>> [    0.000000] RSP: 0000:ffffffff81c03ea8  EFLAGS: 00010002
>> [    0.000000] RAX: 000000000000000c RBX: ffffea00006dfd40 RCX:
>> 0000000000000100
>> [    0.000000] RDX: 0000000000000001 RSI: ffffffff81a4aeb8 RDI:
>> ffffea00006dfd40
>> [    0.000000] RBP: ffffffff81c03ec0 R08: 0000000000000000 R09:
>> 0000000000000000
>> [    0.000000] R10: 0000000000000001 R11: 0000000000000000 R12:
>> 0000000000000000
>> [    0.000000] R13: 000000000001b7f7 R14: ffffffff81fe50c0 R15:
>> ffffffff81c03fb0
>> [    0.000000] FS:  0000000000000000(0000) GS:ffff88001a400000(0000)
>> knlGS:0000000000000000
>> [    0.000000] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
>> [    0.000000] CR2: 000000000000000c CR3: 0000000001c0b000 CR4:
>> 00000000000406b0
>> [    0.000000] DR0: 0000000000000000 DR1: 0000000000000000 DR2:
>> 0000000000000000
>> [    0.000000] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7:
>> 0000000000000400
>> [    0.000000] Stack:
>> [    0.000000]  000000000001b7f5 ffffea00006dfd40 000000000001b7f7
>> ffffffff81c03ed0
>> [    0.000000]  ffffffff811aabc0 ffffffff81c03ef8 ffffffff81785eda
>> ffffffff81c03f10
>> [    0.000000]  0000000000000040 ffffffff81fd99c0 ffffffff81c03f30
>> ffffffff81f66600
>> [    0.000000] Call Trace:
>> [    0.000000]  [<ffffffff811aabc0>] dump_page+0x10/0x20
>> [    0.000000]  [<ffffffff81785eda>] reserve_bootmem_region+0xd9/0xe2
>> [    0.000000]  [<ffffffff81f66600>] free_all_bootmem+0x4b/0x11a
>> [    0.000000]  [<ffffffff81f5428d>] mem_init+0x6a/0x9d
>> [    0.000000]  [<ffffffff81f37d48>] start_kernel+0x214/0x46a
>> [    0.000000]  [<ffffffff81f37120>] ? early_idt_handler_array+0x120/0x120
>> [    0.000000]  [<ffffffff81f374d7>] x86_64_start_reservations+0x2a/0x2c
>> [    0.000000]  [<ffffffff81f3760f>] x86_64_start_kernel+0x136/0x145
>> [    0.000000] Code: e8 3b 7b 5e 00 55 48 89 e5 41 55 41 54 49 89 d4 53 48
>> 8b 57 20 48 89 fb 4c 8b 4f 10 4c 8b 47 08 48 8d 42 ff 83 e2 01 48 0f 44 c7
>> <48> 8b 00 a8 80 75 4b 8b 4f 18 8b 57 1c 49 89 f5 31 c0 48 89 fe
>> [    0.000000] RIP  [<ffffffff811aaafb>] dump_page_badflags+0x2b/0xe0
>> [    0.000000]  RSP <ffffffff81c03ea8>
>> [    0.000000] CR2: 000000000000000c
>> [    0.000000] ---[ end trace cb88537fdc8fa200 ]---
>
> Could you try this:
>
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 9bcfd70b1eb8..eff685f83879 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -929,8 +929,6 @@ static void init_reserved_page(unsigned long pfn)
>   #else
>   static inline void init_reserved_page(unsigned long pfn)
>   {
> -       /* Avoid false-positive PageTail() */
> -       INIT_LIST_HEAD(&pfn_to_page(pfn)->lru);
>   }
>   #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
>
> @@ -950,6 +948,10 @@ void __meminit reserve_bootmem_region(unsigned long start, unsigned long end)
>                          struct page *page = pfn_to_page(start_pfn);
>
>                          init_reserved_page(start_pfn);
> +
> +                       /* Avoid false-positive PageTail() */
> +                       INIT_LIST_HEAD(&pfn_to_page(pfn)->lru);
> +
>                          SetPageReserved(page);
>                  }
>          }
>


-- 
Konstantin

[-- Attachment #2: .config --]
[-- Type: text/plain, Size: 103542 bytes --]

#
# Automatically generated file; DO NOT EDIT.
# Linux/x86 4.3.0-rc2 Kernel Configuration
#
CONFIG_64BIT=y
CONFIG_X86_64=y
CONFIG_X86=y
CONFIG_INSTRUCTION_DECODER=y
CONFIG_PERF_EVENTS_INTEL_UNCORE=y
CONFIG_OUTPUT_FORMAT="elf64-x86-64"
CONFIG_ARCH_DEFCONFIG="arch/x86/configs/x86_64_defconfig"
CONFIG_LOCKDEP_SUPPORT=y
CONFIG_STACKTRACE_SUPPORT=y
CONFIG_HAVE_LATENCYTOP_SUPPORT=y
CONFIG_MMU=y
CONFIG_NEED_DMA_MAP_STATE=y
CONFIG_NEED_SG_DMA_LENGTH=y
CONFIG_GENERIC_ISA_DMA=y
CONFIG_GENERIC_BUG=y
CONFIG_GENERIC_BUG_RELATIVE_POINTERS=y
CONFIG_GENERIC_HWEIGHT=y
CONFIG_ARCH_MAY_HAVE_PC_FDC=y
CONFIG_RWSEM_XCHGADD_ALGORITHM=y
CONFIG_GENERIC_CALIBRATE_DELAY=y
CONFIG_ARCH_HAS_CPU_RELAX=y
CONFIG_ARCH_HAS_CACHE_LINE_SIZE=y
CONFIG_HAVE_SETUP_PER_CPU_AREA=y
CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK=y
CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK=y
CONFIG_ARCH_HIBERNATION_POSSIBLE=y
CONFIG_ARCH_SUSPEND_POSSIBLE=y
CONFIG_ARCH_WANT_HUGE_PMD_SHARE=y
CONFIG_ARCH_WANT_GENERAL_HUGETLB=y
CONFIG_ZONE_DMA32=y
CONFIG_AUDIT_ARCH=y
CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING=y
CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y
CONFIG_HAVE_INTEL_TXT=y
CONFIG_X86_64_SMP=y
CONFIG_ARCH_HWEIGHT_CFLAGS="-fcall-saved-rdi -fcall-saved-rsi -fcall-saved-rdx -fcall-saved-rcx -fcall-saved-r8 -fcall-saved-r9 -fcall-saved-r10 -fcall-saved-r11"
CONFIG_ARCH_SUPPORTS_UPROBES=y
CONFIG_FIX_EARLYCON_MEM=y
CONFIG_PGTABLE_LEVELS=4
CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
CONFIG_IRQ_WORK=y
CONFIG_BUILDTIME_EXTABLE_SORT=y

#
# General setup
#
CONFIG_INIT_ENV_ARG_LIMIT=32
CONFIG_CROSS_COMPILE=""
# CONFIG_COMPILE_TEST is not set
CONFIG_LOCALVERSION=""
# CONFIG_LOCALVERSION_AUTO is not set
CONFIG_HAVE_KERNEL_GZIP=y
CONFIG_HAVE_KERNEL_BZIP2=y
CONFIG_HAVE_KERNEL_LZMA=y
CONFIG_HAVE_KERNEL_XZ=y
CONFIG_HAVE_KERNEL_LZO=y
CONFIG_HAVE_KERNEL_LZ4=y
CONFIG_KERNEL_GZIP=y
# CONFIG_KERNEL_BZIP2 is not set
# CONFIG_KERNEL_LZMA is not set
# CONFIG_KERNEL_XZ is not set
# CONFIG_KERNEL_LZO is not set
# CONFIG_KERNEL_LZ4 is not set
CONFIG_DEFAULT_HOSTNAME="(none)"
CONFIG_SWAP=y
CONFIG_SYSVIPC=y
CONFIG_SYSVIPC_SYSCTL=y
CONFIG_POSIX_MQUEUE=y
CONFIG_POSIX_MQUEUE_SYSCTL=y
# CONFIG_KDBUS is not set
CONFIG_CROSS_MEMORY_ATTACH=y
CONFIG_FHANDLE=y
CONFIG_USELIB=y
CONFIG_AUDIT=y
CONFIG_HAVE_ARCH_AUDITSYSCALL=y
CONFIG_AUDITSYSCALL=y
CONFIG_AUDIT_WATCH=y
CONFIG_AUDIT_TREE=y

#
# IRQ subsystem
#
CONFIG_GENERIC_IRQ_PROBE=y
CONFIG_GENERIC_IRQ_SHOW=y
CONFIG_GENERIC_PENDING_IRQ=y
CONFIG_IRQ_DOMAIN=y
CONFIG_IRQ_DOMAIN_HIERARCHY=y
CONFIG_GENERIC_MSI_IRQ=y
CONFIG_GENERIC_MSI_IRQ_DOMAIN=y
# CONFIG_IRQ_DOMAIN_DEBUG is not set
CONFIG_IRQ_FORCED_THREADING=y
CONFIG_SPARSE_IRQ=y
CONFIG_CLOCKSOURCE_WATCHDOG=y
CONFIG_ARCH_CLOCKSOURCE_DATA=y
CONFIG_CLOCKSOURCE_VALIDATE_LAST_CYCLE=y
CONFIG_GENERIC_TIME_VSYSCALL=y
CONFIG_GENERIC_CLOCKEVENTS=y
CONFIG_GENERIC_CLOCKEVENTS_BROADCAST=y
CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST=y
CONFIG_GENERIC_CMOS_UPDATE=y

#
# Timers subsystem
#
CONFIG_TICK_ONESHOT=y
CONFIG_NO_HZ_COMMON=y
# CONFIG_HZ_PERIODIC is not set
CONFIG_NO_HZ_IDLE=y
# CONFIG_NO_HZ_FULL is not set
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y

#
# CPU/Task time and stats accounting
#
CONFIG_TICK_CPU_ACCOUNTING=y
# CONFIG_VIRT_CPU_ACCOUNTING_GEN is not set
# CONFIG_IRQ_TIME_ACCOUNTING is not set
CONFIG_BSD_PROCESS_ACCT=y
# CONFIG_BSD_PROCESS_ACCT_V3 is not set
CONFIG_TASKSTATS=y
CONFIG_TASK_DELAY_ACCT=y
CONFIG_TASK_XACCT=y
CONFIG_TASK_IO_ACCOUNTING=y

#
# RCU Subsystem
#
CONFIG_TREE_RCU=y
# CONFIG_RCU_EXPERT is not set
CONFIG_SRCU=y
# CONFIG_TASKS_RCU is not set
CONFIG_RCU_STALL_COMMON=y
# CONFIG_TREE_RCU_TRACE is not set
# CONFIG_RCU_EXPEDITE_BOOT is not set
# CONFIG_BUILD_BIN2C is not set
# CONFIG_IKCONFIG is not set
CONFIG_LOG_BUF_SHIFT=18
CONFIG_LOG_CPU_MAX_BUF_SHIFT=12
CONFIG_HAVE_UNSTABLE_SCHED_CLOCK=y
CONFIG_ARCH_SUPPORTS_NUMA_BALANCING=y
CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH=y
CONFIG_ARCH_SUPPORTS_INT128=y
# CONFIG_NUMA_BALANCING is not set
CONFIG_CGROUPS=y
# CONFIG_CGROUP_DEBUG is not set
CONFIG_CGROUP_FREEZER=y
CONFIG_CGROUP_PIDS=y
CONFIG_CGROUP_DEVICE=y
CONFIG_CPUSETS=y
CONFIG_PROC_PID_CPUSET=y
CONFIG_CGROUP_CPUACCT=y
CONFIG_PAGE_COUNTER=y
CONFIG_MEMCG=y
# CONFIG_MEMCG_SWAP is not set
# CONFIG_MEMCG_KMEM is not set
# CONFIG_CGROUP_HUGETLB is not set
# CONFIG_CGROUP_PERF is not set
CONFIG_CGROUP_SCHED=y
CONFIG_FAIR_GROUP_SCHED=y
# CONFIG_CFS_BANDWIDTH is not set
# CONFIG_RT_GROUP_SCHED is not set
CONFIG_BLK_CGROUP=y
# CONFIG_DEBUG_BLK_CGROUP is not set
CONFIG_CGROUP_WRITEBACK=y
CONFIG_CHECKPOINT_RESTORE=y
CONFIG_NAMESPACES=y
CONFIG_UTS_NS=y
CONFIG_IPC_NS=y
CONFIG_USER_NS=y
CONFIG_PID_NS=y
CONFIG_NET_NS=y
# CONFIG_SCHED_AUTOGROUP is not set
# CONFIG_SYSFS_DEPRECATED is not set
CONFIG_RELAY=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_INITRAMFS_SOURCE=""
CONFIG_RD_GZIP=y
CONFIG_RD_BZIP2=y
CONFIG_RD_LZMA=y
CONFIG_RD_XZ=y
CONFIG_RD_LZO=y
CONFIG_RD_LZ4=y
# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
# CONFIG_LTO_MENU is not set
CONFIG_SYSCTL=y
CONFIG_ANON_INODES=y
CONFIG_HAVE_UID16=y
CONFIG_SYSCTL_EXCEPTION_TRACE=y
CONFIG_HAVE_PCSPKR_PLATFORM=y
CONFIG_BPF=y
CONFIG_EXPERT=y
CONFIG_UID16=y
CONFIG_MULTIUSER=y
CONFIG_SGETMASK_SYSCALL=y
CONFIG_SYSFS_SYSCALL=y
# CONFIG_SYSCTL_SYSCALL is not set
CONFIG_KALLSYMS=y
# CONFIG_KALLSYMS_ALL is not set
CONFIG_PRINTK=y
CONFIG_BUG=y
CONFIG_ELF_CORE=y
CONFIG_PCSPKR_PLATFORM=y
CONFIG_BASE_FULL=y
CONFIG_FUTEX=y
CONFIG_EPOLL=y
CONFIG_SIGNALFD=y
CONFIG_TIMERFD=y
CONFIG_EVENTFD=y
# CONFIG_BPF_SYSCALL is not set
CONFIG_SHMEM=y
CONFIG_AIO=y
CONFIG_ADVISE_SYSCALLS=y
# CONFIG_USERFAULTFD is not set
CONFIG_PCI_QUIRKS=y
CONFIG_MEMBARRIER=y
# CONFIG_EMBEDDED is not set
CONFIG_HAVE_PERF_EVENTS=y

#
# Kernel Performance Events And Counters
#
CONFIG_PERF_EVENTS=y
# CONFIG_DEBUG_PERF_USE_VMALLOC is not set
CONFIG_VM_EVENT_COUNTERS=y
CONFIG_SLUB_DEBUG=y
# CONFIG_COMPAT_BRK is not set
# CONFIG_SLAB is not set
CONFIG_SLUB=y
# CONFIG_SLOB is not set
CONFIG_SLUB_CPU_PARTIAL=y
# CONFIG_SYSTEM_DATA_VERIFICATION is not set
CONFIG_PROFILING=y
CONFIG_TRACEPOINTS=y
CONFIG_KEXEC_CORE=y
# CONFIG_OPROFILE is not set
CONFIG_HAVE_OPROFILE=y
CONFIG_OPROFILE_NMI_TIMER=y
CONFIG_KPROBES=y
CONFIG_JUMP_LABEL=y
# CONFIG_STATIC_KEYS_SELFTEST is not set
CONFIG_OPTPROBES=y
# CONFIG_UPROBES is not set
# CONFIG_HAVE_64BIT_ALIGNED_ACCESS is not set
CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y
CONFIG_ARCH_USE_BUILTIN_BSWAP=y
CONFIG_KRETPROBES=y
CONFIG_HAVE_IOREMAP_PROT=y
CONFIG_HAVE_KPROBES=y
CONFIG_HAVE_KRETPROBES=y
CONFIG_HAVE_OPTPROBES=y
CONFIG_HAVE_KPROBES_ON_FTRACE=y
CONFIG_HAVE_ARCH_TRACEHOOK=y
CONFIG_HAVE_DMA_ATTRS=y
CONFIG_HAVE_DMA_CONTIGUOUS=y
CONFIG_GENERIC_SMP_IDLE_THREAD=y
CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT=y
CONFIG_HAVE_REGS_AND_STACK_ACCESS_API=y
CONFIG_HAVE_DMA_API_DEBUG=y
CONFIG_HAVE_HW_BREAKPOINT=y
CONFIG_HAVE_MIXED_BREAKPOINTS_REGS=y
CONFIG_HAVE_USER_RETURN_NOTIFIER=y
CONFIG_HAVE_PERF_EVENTS_NMI=y
CONFIG_HAVE_PERF_REGS=y
CONFIG_HAVE_PERF_USER_STACK_DUMP=y
CONFIG_HAVE_ARCH_JUMP_LABEL=y
CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG=y
CONFIG_HAVE_ALIGNED_STRUCT_PAGE=y
CONFIG_HAVE_CMPXCHG_LOCAL=y
CONFIG_HAVE_CMPXCHG_DOUBLE=y
CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION=y
CONFIG_ARCH_WANT_OLD_COMPAT_IPC=y
CONFIG_HAVE_ARCH_SECCOMP_FILTER=y
CONFIG_SECCOMP_FILTER=y
CONFIG_HAVE_CC_STACKPROTECTOR=y
# CONFIG_CC_STACKPROTECTOR is not set
CONFIG_CC_STACKPROTECTOR_NONE=y
# CONFIG_CC_STACKPROTECTOR_REGULAR is not set
# CONFIG_CC_STACKPROTECTOR_STRONG is not set
CONFIG_HAVE_CONTEXT_TRACKING=y
CONFIG_HAVE_VIRT_CPU_ACCOUNTING_GEN=y
CONFIG_HAVE_IRQ_TIME_ACCOUNTING=y
CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE=y
CONFIG_HAVE_ARCH_HUGE_VMAP=y
CONFIG_HAVE_ARCH_SOFT_DIRTY=y
CONFIG_MODULES_USE_ELF_RELA=y
CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK=y
CONFIG_ARCH_HAS_ELF_RANDOMIZE=y
CONFIG_HAVE_COPY_THREAD_TLS=y
CONFIG_OLD_SIGSUSPEND3=y
CONFIG_COMPAT_OLD_SIGACTION=y

#
# GCOV-based kernel profiling
#
# CONFIG_GCOV_KERNEL is not set
CONFIG_ARCH_HAS_GCOV_PROFILE_ALL=y
# CONFIG_HAVE_GENERIC_DMA_COHERENT is not set
CONFIG_SLABINFO=y
CONFIG_RT_MUTEXES=y
CONFIG_BASE_SMALL=0
CONFIG_MODULES=y
# CONFIG_MODULE_FORCE_LOAD is not set
CONFIG_MODULE_UNLOAD=y
CONFIG_MODULE_FORCE_UNLOAD=y
# CONFIG_MODVERSIONS is not set
# CONFIG_MODULE_SRCVERSION_ALL is not set
# CONFIG_MODULE_SIG is not set
# CONFIG_MODULE_COMPRESS is not set
CONFIG_MODULES_TREE_LOOKUP=y
CONFIG_STOP_MACHINE=y
CONFIG_BLOCK=y
CONFIG_BLK_DEV_BSG=y
# CONFIG_BLK_DEV_BSGLIB is not set
# CONFIG_BLK_DEV_INTEGRITY is not set
CONFIG_BLK_DEV_THROTTLING=y
# CONFIG_BLK_CMDLINE_PARSER is not set

#
# Partition Types
#
CONFIG_PARTITION_ADVANCED=y
# CONFIG_ACORN_PARTITION is not set
# CONFIG_AIX_PARTITION is not set
CONFIG_OSF_PARTITION=y
CONFIG_AMIGA_PARTITION=y
# CONFIG_ATARI_PARTITION is not set
CONFIG_MAC_PARTITION=y
CONFIG_MSDOS_PARTITION=y
CONFIG_BSD_DISKLABEL=y
CONFIG_MINIX_SUBPARTITION=y
CONFIG_SOLARIS_X86_PARTITION=y
CONFIG_UNIXWARE_DISKLABEL=y
# CONFIG_LDM_PARTITION is not set
CONFIG_SGI_PARTITION=y
# CONFIG_ULTRIX_PARTITION is not set
CONFIG_SUN_PARTITION=y
CONFIG_KARMA_PARTITION=y
CONFIG_EFI_PARTITION=y
# CONFIG_SYSV68_PARTITION is not set
# CONFIG_CMDLINE_PARTITION is not set
CONFIG_BLOCK_COMPAT=y

#
# IO Schedulers
#
CONFIG_IOSCHED_NOOP=y
CONFIG_IOSCHED_DEADLINE=y
CONFIG_IOSCHED_CFQ=y
CONFIG_CFQ_GROUP_IOSCHED=y
# CONFIG_DEFAULT_DEADLINE is not set
CONFIG_DEFAULT_CFQ=y
# CONFIG_DEFAULT_NOOP is not set
CONFIG_DEFAULT_IOSCHED="cfq"
CONFIG_INLINE_SPIN_UNLOCK_IRQ=y
CONFIG_INLINE_READ_UNLOCK=y
CONFIG_INLINE_READ_UNLOCK_IRQ=y
CONFIG_INLINE_WRITE_UNLOCK=y
CONFIG_INLINE_WRITE_UNLOCK_IRQ=y
CONFIG_ARCH_SUPPORTS_ATOMIC_RMW=y
CONFIG_MUTEX_SPIN_ON_OWNER=y
CONFIG_RWSEM_SPIN_ON_OWNER=y
CONFIG_LOCK_SPIN_ON_OWNER=y
CONFIG_ARCH_USE_QUEUED_SPINLOCKS=y
CONFIG_QUEUED_SPINLOCKS=y
CONFIG_ARCH_USE_QUEUED_RWLOCKS=y
CONFIG_QUEUED_RWLOCKS=y
CONFIG_FREEZER=y

#
# Processor type and features
#
CONFIG_ZONE_DMA=y
CONFIG_SMP=y
CONFIG_X86_FEATURE_NAMES=y
# CONFIG_X86_X2APIC is not set
CONFIG_X86_MPPARSE=y
CONFIG_X86_EXTENDED_PLATFORM=y
# CONFIG_X86_VSMP is not set
# CONFIG_X86_GOLDFISH is not set
# CONFIG_X86_INTEL_LPSS is not set
# CONFIG_X86_AMD_PLATFORM_DEVICE is not set
# CONFIG_IOSF_MBI is not set
CONFIG_X86_SUPPORTS_MEMORY_FAILURE=y
CONFIG_SCHED_OMIT_FRAME_POINTER=y
CONFIG_HYPERVISOR_GUEST=y
CONFIG_PARAVIRT=y
# CONFIG_PARAVIRT_DEBUG is not set
# CONFIG_PARAVIRT_SPINLOCKS is not set
# CONFIG_XEN is not set
CONFIG_KVM_GUEST=y
# CONFIG_KVM_DEBUG_FS is not set
# CONFIG_PARAVIRT_TIME_ACCOUNTING is not set
CONFIG_PARAVIRT_CLOCK=y
CONFIG_NO_BOOTMEM=y
# CONFIG_MK8 is not set
# CONFIG_MPSC is not set
# CONFIG_MCORE2 is not set
# CONFIG_MATOM is not set
CONFIG_GENERIC_CPU=y
CONFIG_X86_INTERNODE_CACHE_SHIFT=6
CONFIG_X86_L1_CACHE_SHIFT=6
CONFIG_X86_TSC=y
CONFIG_X86_CMPXCHG64=y
CONFIG_X86_CMOV=y
CONFIG_X86_MINIMUM_CPU_FAMILY=64
CONFIG_X86_DEBUGCTLMSR=y
# CONFIG_PROCESSOR_SELECT is not set
CONFIG_CPU_SUP_INTEL=y
CONFIG_CPU_SUP_AMD=y
CONFIG_CPU_SUP_CENTAUR=y
CONFIG_HPET_TIMER=y
CONFIG_HPET_EMULATE_RTC=y
CONFIG_DMI=y
# CONFIG_GART_IOMMU is not set
CONFIG_CALGARY_IOMMU=y
CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT=y
CONFIG_SWIOTLB=y
CONFIG_IOMMU_HELPER=y
# CONFIG_MAXSMP is not set
CONFIG_NR_CPUS=64
CONFIG_SCHED_SMT=y
CONFIG_SCHED_MC=y
# CONFIG_PREEMPT_NONE is not set
CONFIG_PREEMPT_VOLUNTARY=y
# CONFIG_PREEMPT is not set
CONFIG_X86_LOCAL_APIC=y
CONFIG_X86_IO_APIC=y
CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y
CONFIG_X86_MCE=y
CONFIG_X86_MCE_INTEL=y
CONFIG_X86_MCE_AMD=y
CONFIG_X86_MCE_THRESHOLD=y
# CONFIG_X86_MCE_INJECT is not set
CONFIG_X86_THERMAL_VECTOR=y
# CONFIG_VM86 is not set
CONFIG_X86_16BIT=y
CONFIG_X86_ESPFIX64=y
CONFIG_X86_VSYSCALL_EMULATION=y
# CONFIG_I8K is not set
CONFIG_MICROCODE=y
CONFIG_MICROCODE_INTEL=y
CONFIG_MICROCODE_AMD=y
CONFIG_MICROCODE_OLD_INTERFACE=y
CONFIG_MICROCODE_INTEL_EARLY=y
CONFIG_MICROCODE_AMD_EARLY=y
CONFIG_MICROCODE_EARLY=y
CONFIG_X86_MSR=y
CONFIG_X86_CPUID=y
CONFIG_ARCH_PHYS_ADDR_T_64BIT=y
CONFIG_ARCH_DMA_ADDR_T_64BIT=y
CONFIG_X86_DIRECT_GBPAGES=y
CONFIG_NUMA=y
CONFIG_AMD_NUMA=y
CONFIG_X86_64_ACPI_NUMA=y
CONFIG_NODES_SPAN_OTHER_NODES=y
# CONFIG_NUMA_EMU is not set
CONFIG_NODES_SHIFT=6
CONFIG_ARCH_SPARSEMEM_ENABLE=y
CONFIG_ARCH_SPARSEMEM_DEFAULT=y
CONFIG_ARCH_SELECT_MEMORY_MODEL=y
# CONFIG_ARCH_MEMORY_PROBE is not set
CONFIG_ARCH_PROC_KCORE_TEXT=y
CONFIG_ILLEGAL_POINTER_VALUE=0xdead000000000000
CONFIG_SELECT_MEMORY_MODEL=y
CONFIG_SPARSEMEM_MANUAL=y
CONFIG_SPARSEMEM=y
CONFIG_NEED_MULTIPLE_NODES=y
CONFIG_HAVE_MEMORY_PRESENT=y
CONFIG_SPARSEMEM_EXTREME=y
CONFIG_SPARSEMEM_VMEMMAP_ENABLE=y
CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER=y
CONFIG_SPARSEMEM_VMEMMAP=y
CONFIG_HAVE_MEMBLOCK=y
CONFIG_HAVE_MEMBLOCK_NODE_MAP=y
CONFIG_ARCH_DISCARD_MEMBLOCK=y
CONFIG_MEMORY_ISOLATION=y
# CONFIG_MOVABLE_NODE is not set
CONFIG_HAVE_BOOTMEM_INFO_NODE=y
CONFIG_MEMORY_HOTPLUG=y
CONFIG_MEMORY_HOTPLUG_SPARSE=y
CONFIG_MEMORY_HOTREMOVE=y
CONFIG_SPLIT_PTLOCK_CPUS=4
CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK=y
CONFIG_COMPACTION=y
CONFIG_MIGRATION=y
CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION=y
CONFIG_PHYS_ADDR_T_64BIT=y
CONFIG_ZONE_DMA_FLAG=1
CONFIG_BOUNCE=y
CONFIG_VIRT_TO_BUS=y
# CONFIG_KSM is not set
CONFIG_DEFAULT_MMAP_MIN_ADDR=4096
CONFIG_ARCH_SUPPORTS_MEMORY_FAILURE=y
# CONFIG_MEMORY_FAILURE is not set
# CONFIG_TRANSPARENT_HUGEPAGE is not set
# CONFIG_CLEANCACHE is not set
# CONFIG_FRONTSWAP is not set
# CONFIG_CMA is not set
# CONFIG_MEM_SOFT_DIRTY is not set
# CONFIG_ZPOOL is not set
# CONFIG_ZBUD is not set
# CONFIG_ZSMALLOC is not set
CONFIG_GENERIC_EARLY_IOREMAP=y
CONFIG_ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT=y
CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
# CONFIG_IDLE_PAGE_TRACKING is not set
# CONFIG_X86_PMEM_LEGACY is not set
CONFIG_X86_CHECK_BIOS_CORRUPTION=y
CONFIG_X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK=y
CONFIG_X86_RESERVE_LOW=64
CONFIG_MTRR=y
# CONFIG_MTRR_SANITIZER is not set
CONFIG_X86_PAT=y
CONFIG_ARCH_USES_PG_UNCACHED=y
CONFIG_ARCH_RANDOM=y
CONFIG_X86_SMAP=y
# CONFIG_X86_INTEL_MPX is not set
CONFIG_EFI=y
# CONFIG_EFI_STUB is not set
CONFIG_SECCOMP=y
# CONFIG_HZ_100 is not set
# CONFIG_HZ_250 is not set
# CONFIG_HZ_300 is not set
CONFIG_HZ_1000=y
CONFIG_HZ=1000
CONFIG_SCHED_HRTICK=y
CONFIG_KEXEC=y
# CONFIG_KEXEC_FILE is not set
CONFIG_CRASH_DUMP=y
# CONFIG_KEXEC_JUMP is not set
CONFIG_PHYSICAL_START=0x1000000
CONFIG_RELOCATABLE=y
# CONFIG_RANDOMIZE_BASE is not set
CONFIG_PHYSICAL_ALIGN=0x200000
CONFIG_HOTPLUG_CPU=y
# CONFIG_BOOTPARAM_HOTPLUG_CPU0 is not set
# CONFIG_DEBUG_HOTPLUG_CPU0 is not set
# CONFIG_COMPAT_VDSO is not set
# CONFIG_LEGACY_VSYSCALL_NATIVE is not set
CONFIG_LEGACY_VSYSCALL_EMULATE=y
# CONFIG_LEGACY_VSYSCALL_NONE is not set
# CONFIG_CMDLINE_BOOL is not set
CONFIG_MODIFY_LDT_SYSCALL=y
CONFIG_HAVE_LIVEPATCH=y
CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE=y
CONFIG_USE_PERCPU_NUMA_NODE_ID=y
CONFIG_HAVE_MEMORYLESS_NODES=y

#
# Power management and ACPI options
#
CONFIG_ARCH_HIBERNATION_HEADER=y
CONFIG_SUSPEND=y
CONFIG_SUSPEND_FREEZER=y
# CONFIG_SUSPEND_SKIP_SYNC is not set
CONFIG_HIBERNATE_CALLBACKS=y
CONFIG_HIBERNATION=y
CONFIG_PM_STD_PARTITION=""
CONFIG_PM_SLEEP=y
CONFIG_PM_SLEEP_SMP=y
# CONFIG_PM_AUTOSLEEP is not set
# CONFIG_PM_WAKELOCKS is not set
CONFIG_PM=y
CONFIG_PM_DEBUG=y
# CONFIG_PM_ADVANCED_DEBUG is not set
# CONFIG_PM_TEST_SUSPEND is not set
CONFIG_PM_SLEEP_DEBUG=y
CONFIG_PM_TRACE=y
CONFIG_PM_TRACE_RTC=y
# CONFIG_WQ_POWER_EFFICIENT_DEFAULT is not set
CONFIG_ACPI=y
CONFIG_ACPI_LEGACY_TABLES_LOOKUP=y
CONFIG_ARCH_MIGHT_HAVE_ACPI_PDC=y
CONFIG_ACPI_SYSTEM_POWER_STATES_SUPPORT=y
CONFIG_ACPI_SLEEP=y
# CONFIG_ACPI_PROCFS_POWER is not set
CONFIG_ACPI_REV_OVERRIDE_POSSIBLE=y
# CONFIG_ACPI_EC_DEBUGFS is not set
CONFIG_ACPI_AC=y
CONFIG_ACPI_BATTERY=y
CONFIG_ACPI_BUTTON=y
CONFIG_ACPI_VIDEO=y
CONFIG_ACPI_FAN=y
CONFIG_ACPI_DOCK=y
CONFIG_ACPI_CPU_FREQ_PSS=y
CONFIG_ACPI_PROCESSOR_IDLE=y
CONFIG_ACPI_PROCESSOR=y
CONFIG_ACPI_HOTPLUG_CPU=y
# CONFIG_ACPI_PROCESSOR_AGGREGATOR is not set
CONFIG_ACPI_THERMAL=y
CONFIG_ACPI_NUMA=y
# CONFIG_ACPI_CUSTOM_DSDT is not set
# CONFIG_ACPI_INITRD_TABLE_OVERRIDE is not set
# CONFIG_ACPI_DEBUG is not set
# CONFIG_ACPI_PCI_SLOT is not set
CONFIG_X86_PM_TIMER=y
CONFIG_ACPI_CONTAINER=y
CONFIG_ACPI_HOTPLUG_MEMORY=y
CONFIG_ACPI_HOTPLUG_IOAPIC=y
# CONFIG_ACPI_SBS is not set
# CONFIG_ACPI_HED is not set
# CONFIG_ACPI_CUSTOM_METHOD is not set
# CONFIG_ACPI_BGRT is not set
# CONFIG_ACPI_REDUCED_HARDWARE_ONLY is not set
# CONFIG_ACPI_NFIT is not set
CONFIG_HAVE_ACPI_APEI=y
CONFIG_HAVE_ACPI_APEI_NMI=y
# CONFIG_ACPI_APEI is not set
# CONFIG_ACPI_EXTLOG is not set
# CONFIG_PMIC_OPREGION is not set
# CONFIG_SFI is not set

#
# CPU Frequency scaling
#
CONFIG_CPU_FREQ=y
CONFIG_CPU_FREQ_GOV_COMMON=y
# CONFIG_CPU_FREQ_STAT is not set
# CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE is not set
# CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE is not set
CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y
# CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND is not set
# CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE is not set
CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
# CONFIG_CPU_FREQ_GOV_POWERSAVE is not set
CONFIG_CPU_FREQ_GOV_USERSPACE=y
CONFIG_CPU_FREQ_GOV_ONDEMAND=y
# CONFIG_CPU_FREQ_GOV_CONSERVATIVE is not set

#
# CPU frequency scaling drivers
#
# CONFIG_X86_INTEL_PSTATE is not set
# CONFIG_X86_PCC_CPUFREQ is not set
CONFIG_X86_ACPI_CPUFREQ=y
CONFIG_X86_ACPI_CPUFREQ_CPB=y
# CONFIG_X86_POWERNOW_K8 is not set
# CONFIG_X86_AMD_FREQ_SENSITIVITY is not set
# CONFIG_X86_SPEEDSTEP_CENTRINO is not set
# CONFIG_X86_P4_CLOCKMOD is not set

#
# shared options
#
# CONFIG_X86_SPEEDSTEP_LIB is not set

#
# CPU Idle
#
CONFIG_CPU_IDLE=y
CONFIG_CPU_IDLE_GOV_LADDER=y
CONFIG_CPU_IDLE_GOV_MENU=y
# CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED is not set
# CONFIG_INTEL_IDLE is not set

#
# Memory power savings
#
# CONFIG_I7300_IDLE is not set

#
# Bus options (PCI etc.)
#
CONFIG_PCI=y
CONFIG_PCI_DIRECT=y
CONFIG_PCI_MMCONFIG=y
CONFIG_PCI_DOMAINS=y
# CONFIG_PCI_CNB20LE_QUIRK is not set
CONFIG_PCIEPORTBUS=y
# CONFIG_HOTPLUG_PCI_PCIE is not set
CONFIG_PCIEAER=y
# CONFIG_PCIE_ECRC is not set
# CONFIG_PCIEAER_INJECT is not set
CONFIG_PCIEASPM=y
# CONFIG_PCIEASPM_DEBUG is not set
CONFIG_PCIEASPM_DEFAULT=y
# CONFIG_PCIEASPM_POWERSAVE is not set
# CONFIG_PCIEASPM_PERFORMANCE is not set
CONFIG_PCIE_PME=y
CONFIG_PCI_BUS_ADDR_T_64BIT=y
CONFIG_PCI_MSI=y
CONFIG_PCI_MSI_IRQ_DOMAIN=y
# CONFIG_PCI_DEBUG is not set
# CONFIG_PCI_REALLOC_ENABLE_AUTO is not set
# CONFIG_PCI_STUB is not set
CONFIG_HT_IRQ=y
CONFIG_PCI_ATS=y
# CONFIG_PCI_IOV is not set
CONFIG_PCI_PRI=y
CONFIG_PCI_PASID=y
CONFIG_PCI_LABEL=y

#
# PCI host controller drivers
#
CONFIG_ISA_DMA_API=y
CONFIG_AMD_NB=y
CONFIG_PCCARD=y
CONFIG_PCMCIA=y
CONFIG_PCMCIA_LOAD_CIS=y
CONFIG_CARDBUS=y

#
# PC-card bridges
#
CONFIG_YENTA=y
CONFIG_YENTA_O2=y
CONFIG_YENTA_RICOH=y
CONFIG_YENTA_TI=y
CONFIG_YENTA_ENE_TUNE=y
CONFIG_YENTA_TOSHIBA=y
# CONFIG_PD6729 is not set
# CONFIG_I82092 is not set
CONFIG_PCCARD_NONSTATIC=y
CONFIG_HOTPLUG_PCI=y
# CONFIG_HOTPLUG_PCI_ACPI is not set
# CONFIG_HOTPLUG_PCI_CPCI is not set
# CONFIG_HOTPLUG_PCI_SHPC is not set
# CONFIG_RAPIDIO is not set
# CONFIG_X86_SYSFB is not set

#
# Executable file formats / Emulations
#
CONFIG_BINFMT_ELF=y
CONFIG_COMPAT_BINFMT_ELF=y
CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS=y
CONFIG_BINFMT_SCRIPT=y
# CONFIG_HAVE_AOUT is not set
CONFIG_BINFMT_MISC=y
CONFIG_COREDUMP=y
CONFIG_IA32_EMULATION=y
# CONFIG_IA32_AOUT is not set
# CONFIG_X86_X32 is not set
CONFIG_COMPAT=y
CONFIG_COMPAT_FOR_U64_ALIGNMENT=y
CONFIG_SYSVIPC_COMPAT=y
CONFIG_KEYS_COMPAT=y
CONFIG_X86_DEV_DMA_OPS=y
CONFIG_PMC_ATOM=y
CONFIG_NET=y
CONFIG_NET_INGRESS=y

#
# Networking options
#
CONFIG_PACKET=y
# CONFIG_PACKET_DIAG is not set
CONFIG_UNIX=y
# CONFIG_UNIX_DIAG is not set
CONFIG_XFRM=y
CONFIG_XFRM_ALGO=y
CONFIG_XFRM_USER=y
# CONFIG_XFRM_SUB_POLICY is not set
# CONFIG_XFRM_MIGRATE is not set
# CONFIG_XFRM_STATISTICS is not set
# CONFIG_NET_KEY is not set
CONFIG_INET=y
CONFIG_IP_MULTICAST=y
CONFIG_IP_ADVANCED_ROUTER=y
# CONFIG_IP_FIB_TRIE_STATS is not set
CONFIG_IP_MULTIPLE_TABLES=y
CONFIG_IP_ROUTE_MULTIPATH=y
CONFIG_IP_ROUTE_VERBOSE=y
CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_IP_PNP_BOOTP=y
CONFIG_IP_PNP_RARP=y
# CONFIG_NET_IPIP is not set
# CONFIG_NET_IPGRE_DEMUX is not set
CONFIG_NET_IP_TUNNEL=y
CONFIG_IP_MROUTE=y
# CONFIG_IP_MROUTE_MULTIPLE_TABLES is not set
CONFIG_IP_PIMSM_V1=y
CONFIG_IP_PIMSM_V2=y
CONFIG_SYN_COOKIES=y
# CONFIG_NET_UDP_TUNNEL is not set
# CONFIG_NET_FOU is not set
# CONFIG_NET_FOU_IP_TUNNELS is not set
# CONFIG_INET_AH is not set
# CONFIG_INET_ESP is not set
# CONFIG_INET_IPCOMP is not set
# CONFIG_INET_XFRM_TUNNEL is not set
CONFIG_INET_TUNNEL=y
# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
# CONFIG_INET_XFRM_MODE_TUNNEL is not set
# CONFIG_INET_XFRM_MODE_BEET is not set
CONFIG_INET_LRO=y
# CONFIG_INET_DIAG is not set
CONFIG_TCP_CONG_ADVANCED=y
# CONFIG_TCP_CONG_BIC is not set
CONFIG_TCP_CONG_CUBIC=y
# CONFIG_TCP_CONG_WESTWOOD is not set
# CONFIG_TCP_CONG_HTCP is not set
# CONFIG_TCP_CONG_HSTCP is not set
# CONFIG_TCP_CONG_HYBLA is not set
# CONFIG_TCP_CONG_VEGAS is not set
# CONFIG_TCP_CONG_SCALABLE is not set
# CONFIG_TCP_CONG_LP is not set
# CONFIG_TCP_CONG_VENO is not set
# CONFIG_TCP_CONG_YEAH is not set
# CONFIG_TCP_CONG_ILLINOIS is not set
# CONFIG_TCP_CONG_DCTCP is not set
# CONFIG_TCP_CONG_CDG is not set
CONFIG_DEFAULT_CUBIC=y
# CONFIG_DEFAULT_RENO is not set
CONFIG_DEFAULT_TCP_CONG="cubic"
CONFIG_TCP_MD5SIG=y
CONFIG_IPV6=y
# CONFIG_IPV6_ROUTER_PREF is not set
# CONFIG_IPV6_OPTIMISTIC_DAD is not set
CONFIG_INET6_AH=y
CONFIG_INET6_ESP=y
# CONFIG_INET6_IPCOMP is not set
# CONFIG_IPV6_MIP6 is not set
# CONFIG_IPV6_ILA is not set
# CONFIG_INET6_XFRM_TUNNEL is not set
# CONFIG_INET6_TUNNEL is not set
CONFIG_INET6_XFRM_MODE_TRANSPORT=y
CONFIG_INET6_XFRM_MODE_TUNNEL=y
CONFIG_INET6_XFRM_MODE_BEET=y
# CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION is not set
# CONFIG_IPV6_VTI is not set
CONFIG_IPV6_SIT=y
# CONFIG_IPV6_SIT_6RD is not set
CONFIG_IPV6_NDISC_NODETYPE=y
# CONFIG_IPV6_TUNNEL is not set
# CONFIG_IPV6_GRE is not set
# CONFIG_IPV6_MULTIPLE_TABLES is not set
# CONFIG_IPV6_MROUTE is not set
CONFIG_NETLABEL=y
CONFIG_NETWORK_SECMARK=y
CONFIG_NET_PTP_CLASSIFY=y
# CONFIG_NETWORK_PHY_TIMESTAMPING is not set
CONFIG_NETFILTER=y
# CONFIG_NETFILTER_DEBUG is not set
# CONFIG_NETFILTER_ADVANCED is not set

#
# Core Netfilter Configuration
#
CONFIG_NETFILTER_INGRESS=y
CONFIG_NETFILTER_NETLINK=y
CONFIG_NETFILTER_NETLINK_LOG=y
CONFIG_NF_CONNTRACK=y
CONFIG_NF_LOG_COMMON=m
CONFIG_NF_CONNTRACK_SECMARK=y
CONFIG_NF_CONNTRACK_PROCFS=y
CONFIG_NF_CONNTRACK_FTP=y
CONFIG_NF_CONNTRACK_IRC=y
# CONFIG_NF_CONNTRACK_NETBIOS_NS is not set
CONFIG_NF_CONNTRACK_SIP=y
CONFIG_NF_CT_NETLINK=y
CONFIG_NF_NAT=m
CONFIG_NF_NAT_NEEDED=y
# CONFIG_NF_NAT_AMANDA is not set
CONFIG_NF_NAT_FTP=m
CONFIG_NF_NAT_IRC=m
CONFIG_NF_NAT_SIP=m
# CONFIG_NF_NAT_TFTP is not set
# CONFIG_NF_NAT_REDIRECT is not set
# CONFIG_NF_TABLES is not set
CONFIG_NETFILTER_XTABLES=y

#
# Xtables combined modules
#
CONFIG_NETFILTER_XT_MARK=m

#
# Xtables targets
#
CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
CONFIG_NETFILTER_XT_TARGET_LOG=m
CONFIG_NETFILTER_XT_NAT=m
# CONFIG_NETFILTER_XT_TARGET_NETMAP is not set
CONFIG_NETFILTER_XT_TARGET_NFLOG=y
# CONFIG_NETFILTER_XT_TARGET_REDIRECT is not set
CONFIG_NETFILTER_XT_TARGET_SECMARK=y
CONFIG_NETFILTER_XT_TARGET_TCPMSS=y

#
# Xtables matches
#
CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m
CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
CONFIG_NETFILTER_XT_MATCH_POLICY=y
CONFIG_NETFILTER_XT_MATCH_STATE=y
# CONFIG_IP_SET is not set
# CONFIG_IP_VS is not set

#
# IP: Netfilter Configuration
#
CONFIG_NF_DEFRAG_IPV4=y
CONFIG_NF_CONNTRACK_IPV4=y
CONFIG_NF_CONNTRACK_PROC_COMPAT=y
# CONFIG_NF_DUP_IPV4 is not set
CONFIG_NF_LOG_ARP=m
CONFIG_NF_LOG_IPV4=m
CONFIG_NF_REJECT_IPV4=y
CONFIG_NF_NAT_IPV4=m
CONFIG_NF_NAT_MASQUERADE_IPV4=m
# CONFIG_NF_NAT_PPTP is not set
# CONFIG_NF_NAT_H323 is not set
CONFIG_IP_NF_IPTABLES=y
CONFIG_IP_NF_FILTER=y
CONFIG_IP_NF_TARGET_REJECT=y
CONFIG_IP_NF_NAT=m
CONFIG_IP_NF_TARGET_MASQUERADE=m
CONFIG_IP_NF_MANGLE=y
# CONFIG_IP_NF_RAW is not set

#
# IPv6: Netfilter Configuration
#
CONFIG_NF_DEFRAG_IPV6=y
CONFIG_NF_CONNTRACK_IPV6=y
# CONFIG_NF_DUP_IPV6 is not set
CONFIG_NF_REJECT_IPV6=y
CONFIG_NF_LOG_IPV6=m
CONFIG_IP6_NF_IPTABLES=y
CONFIG_IP6_NF_MATCH_IPV6HEADER=y
CONFIG_IP6_NF_FILTER=y
CONFIG_IP6_NF_TARGET_REJECT=y
CONFIG_IP6_NF_MANGLE=y
# CONFIG_IP6_NF_RAW is not set
# CONFIG_IP_DCCP is not set
# CONFIG_IP_SCTP is not set
# CONFIG_RDS is not set
# CONFIG_TIPC is not set
# CONFIG_ATM is not set
# CONFIG_L2TP is not set
# CONFIG_BRIDGE is not set
CONFIG_HAVE_NET_DSA=y
# CONFIG_VLAN_8021Q is not set
# CONFIG_DECNET is not set
# CONFIG_LLC2 is not set
# CONFIG_IPX is not set
# CONFIG_ATALK is not set
# CONFIG_X25 is not set
# CONFIG_LAPB is not set
# CONFIG_PHONET is not set
# CONFIG_6LOWPAN is not set
# CONFIG_IEEE802154 is not set
CONFIG_NET_SCHED=y

#
# Queueing/Scheduling
#
# CONFIG_NET_SCH_CBQ is not set
CONFIG_NET_SCH_HTB=m
# CONFIG_NET_SCH_HFSC is not set
# CONFIG_NET_SCH_PRIO is not set
# CONFIG_NET_SCH_MULTIQ is not set
# CONFIG_NET_SCH_RED is not set
# CONFIG_NET_SCH_SFB is not set
# CONFIG_NET_SCH_SFQ is not set
# CONFIG_NET_SCH_TEQL is not set
# CONFIG_NET_SCH_TBF is not set
# CONFIG_NET_SCH_GRED is not set
# CONFIG_NET_SCH_DSMARK is not set
# CONFIG_NET_SCH_NETEM is not set
# CONFIG_NET_SCH_DRR is not set
# CONFIG_NET_SCH_MQPRIO is not set
# CONFIG_NET_SCH_CHOKE is not set
# CONFIG_NET_SCH_QFQ is not set
# CONFIG_NET_SCH_CODEL is not set
# CONFIG_NET_SCH_FQ_CODEL is not set
# CONFIG_NET_SCH_FQ is not set
# CONFIG_NET_SCH_HHF is not set
# CONFIG_NET_SCH_PIE is not set
# CONFIG_NET_SCH_INGRESS is not set
# CONFIG_NET_SCH_PLUG is not set

#
# Classification
#
CONFIG_NET_CLS=y
# CONFIG_NET_CLS_BASIC is not set
# CONFIG_NET_CLS_TCINDEX is not set
# CONFIG_NET_CLS_ROUTE4 is not set
# CONFIG_NET_CLS_FW is not set
# CONFIG_NET_CLS_U32 is not set
# CONFIG_NET_CLS_RSVP is not set
# CONFIG_NET_CLS_RSVP6 is not set
# CONFIG_NET_CLS_FLOW is not set
CONFIG_NET_CLS_CGROUP=y
# CONFIG_NET_CLS_BPF is not set
# CONFIG_NET_CLS_FLOWER is not set
CONFIG_NET_EMATCH=y
CONFIG_NET_EMATCH_STACK=32
# CONFIG_NET_EMATCH_CMP is not set
# CONFIG_NET_EMATCH_NBYTE is not set
# CONFIG_NET_EMATCH_U32 is not set
# CONFIG_NET_EMATCH_META is not set
# CONFIG_NET_EMATCH_TEXT is not set
CONFIG_NET_CLS_ACT=y
# CONFIG_NET_ACT_POLICE is not set
# CONFIG_NET_ACT_GACT is not set
# CONFIG_NET_ACT_MIRRED is not set
# CONFIG_NET_ACT_IPT is not set
# CONFIG_NET_ACT_NAT is not set
# CONFIG_NET_ACT_PEDIT is not set
# CONFIG_NET_ACT_SIMP is not set
# CONFIG_NET_ACT_SKBEDIT is not set
# CONFIG_NET_ACT_CSUM is not set
# CONFIG_NET_ACT_VLAN is not set
# CONFIG_NET_ACT_BPF is not set
CONFIG_NET_SCH_FIFO=y
# CONFIG_DCB is not set
CONFIG_DNS_RESOLVER=y
# CONFIG_BATMAN_ADV is not set
# CONFIG_OPENVSWITCH is not set
# CONFIG_VSOCKETS is not set
# CONFIG_NETLINK_MMAP is not set
# CONFIG_NETLINK_DIAG is not set
# CONFIG_MPLS is not set
# CONFIG_HSR is not set
# CONFIG_NET_SWITCHDEV is not set
CONFIG_RPS=y
CONFIG_RFS_ACCEL=y
CONFIG_XPS=y
CONFIG_CGROUP_NET_PRIO=y
CONFIG_CGROUP_NET_CLASSID=y
CONFIG_NET_RX_BUSY_POLL=y
CONFIG_BQL=y
# CONFIG_BPF_JIT is not set
CONFIG_NET_FLOW_LIMIT=y

#
# Network testing
#
# CONFIG_NET_PKTGEN is not set
# CONFIG_NET_TCPPROBE is not set
# CONFIG_NET_DROP_MONITOR is not set
CONFIG_HAMRADIO=y

#
# Packet Radio protocols
#
# CONFIG_AX25 is not set
# CONFIG_CAN is not set
# CONFIG_IRDA is not set
# CONFIG_BT is not set
# CONFIG_AF_RXRPC is not set
CONFIG_FIB_RULES=y
CONFIG_WIRELESS=y
CONFIG_CFG80211=y
# CONFIG_NL80211_TESTMODE is not set
# CONFIG_CFG80211_DEVELOPER_WARNINGS is not set
# CONFIG_CFG80211_REG_DEBUG is not set
# CONFIG_CFG80211_CERTIFICATION_ONUS is not set
CONFIG_CFG80211_DEFAULT_PS=y
# CONFIG_CFG80211_DEBUGFS is not set
# CONFIG_CFG80211_INTERNAL_REGDB is not set
# CONFIG_CFG80211_WEXT is not set
# CONFIG_LIB80211 is not set
CONFIG_MAC80211=y
CONFIG_MAC80211_HAS_RC=y
CONFIG_MAC80211_RC_MINSTREL=y
CONFIG_MAC80211_RC_MINSTREL_HT=y
# CONFIG_MAC80211_RC_MINSTREL_VHT is not set
CONFIG_MAC80211_RC_DEFAULT_MINSTREL=y
CONFIG_MAC80211_RC_DEFAULT="minstrel_ht"
# CONFIG_MAC80211_MESH is not set
CONFIG_MAC80211_LEDS=y
# CONFIG_MAC80211_DEBUGFS is not set
# CONFIG_MAC80211_MESSAGE_TRACING is not set
# CONFIG_MAC80211_DEBUG_MENU is not set
CONFIG_MAC80211_STA_HASH_MAX_SIZE=0
# CONFIG_WIMAX is not set
CONFIG_RFKILL=y
CONFIG_RFKILL_LEDS=y
CONFIG_RFKILL_INPUT=y
CONFIG_NET_9P=y
CONFIG_NET_9P_VIRTIO=y
# CONFIG_NET_9P_DEBUG is not set
# CONFIG_CAIF is not set
# CONFIG_CEPH_LIB is not set
# CONFIG_NFC is not set
# CONFIG_LWTUNNEL is not set
CONFIG_HAVE_BPF_JIT=y

#
# Device Drivers
#

#
# Generic Driver Options
#
CONFIG_UEVENT_HELPER=y
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
CONFIG_STANDALONE=y
CONFIG_PREVENT_FIRMWARE_BUILD=y
CONFIG_FW_LOADER=y
CONFIG_FIRMWARE_IN_KERNEL=y
CONFIG_EXTRA_FIRMWARE=""
# CONFIG_FW_LOADER_USER_HELPER_FALLBACK is not set
CONFIG_ALLOW_DEV_COREDUMP=y
# CONFIG_DEBUG_DRIVER is not set
CONFIG_DEBUG_DEVRES=y
# CONFIG_SYS_HYPERVISOR is not set
# CONFIG_GENERIC_CPU_DEVICES is not set
CONFIG_GENERIC_CPU_AUTOPROBE=y
CONFIG_REGMAP=y
CONFIG_DMA_SHARED_BUFFER=y
# CONFIG_FENCE_TRACE is not set

#
# Bus devices
#
CONFIG_CONNECTOR=y
CONFIG_PROC_EVENTS=y
# CONFIG_MTD is not set
# CONFIG_OF is not set
CONFIG_ARCH_MIGHT_HAVE_PC_PARPORT=y
# CONFIG_PARPORT is not set
CONFIG_PNP=y
CONFIG_PNP_DEBUG_MESSAGES=y

#
# Protocols
#
CONFIG_PNPACPI=y
CONFIG_BLK_DEV=y
# CONFIG_BLK_DEV_NULL_BLK is not set
# CONFIG_BLK_DEV_FD is not set
# CONFIG_BLK_DEV_PCIESSD_MTIP32XX is not set
# CONFIG_BLK_CPQ_CISS_DA is not set
# CONFIG_BLK_DEV_DAC960 is not set
# CONFIG_BLK_DEV_UMEM is not set
# CONFIG_BLK_DEV_COW_COMMON is not set
CONFIG_BLK_DEV_LOOP=y
CONFIG_BLK_DEV_LOOP_MIN_COUNT=8
# CONFIG_BLK_DEV_CRYPTOLOOP is not set
# CONFIG_BLK_DEV_DRBD is not set
# CONFIG_BLK_DEV_NBD is not set
# CONFIG_BLK_DEV_NVME is not set
# CONFIG_BLK_DEV_SKD is not set
# CONFIG_BLK_DEV_SX8 is not set
# CONFIG_BLK_DEV_RAM is not set
# CONFIG_CDROM_PKTCDVD is not set
# CONFIG_ATA_OVER_ETH is not set
CONFIG_VIRTIO_BLK=y
# CONFIG_BLK_DEV_HD is not set
# CONFIG_BLK_DEV_RBD is not set
# CONFIG_BLK_DEV_RSXX is not set

#
# Misc devices
#
# CONFIG_SENSORS_LIS3LV02D is not set
# CONFIG_AD525X_DPOT is not set
# CONFIG_DUMMY_IRQ is not set
# CONFIG_IBM_ASM is not set
# CONFIG_PHANTOM is not set
# CONFIG_SGI_IOC4 is not set
# CONFIG_TIFM_CORE is not set
# CONFIG_ICS932S401 is not set
# CONFIG_ENCLOSURE_SERVICES is not set
# CONFIG_HP_ILO is not set
# CONFIG_APDS9802ALS is not set
# CONFIG_ISL29003 is not set
# CONFIG_ISL29020 is not set
# CONFIG_SENSORS_TSL2550 is not set
# CONFIG_SENSORS_BH1780 is not set
# CONFIG_SENSORS_BH1770 is not set
# CONFIG_SENSORS_APDS990X is not set
# CONFIG_HMC6352 is not set
# CONFIG_DS1682 is not set
# CONFIG_VMWARE_BALLOON is not set
# CONFIG_BMP085_I2C is not set
# CONFIG_USB_SWITCH_FSA9480 is not set
# CONFIG_SRAM is not set
# CONFIG_C2PORT is not set

#
# EEPROM support
#
# CONFIG_EEPROM_AT24 is not set
# CONFIG_EEPROM_LEGACY is not set
# CONFIG_EEPROM_MAX6875 is not set
# CONFIG_EEPROM_93CX6 is not set
# CONFIG_CB710_CORE is not set

#
# Texas Instruments shared transport line discipline
#
# CONFIG_SENSORS_LIS3_I2C is not set

#
# Altera FPGA firmware download module
#
# CONFIG_ALTERA_STAPL is not set
# CONFIG_VMWARE_VMCI is not set

#
# Intel MIC Bus Driver
#
# CONFIG_INTEL_MIC_BUS is not set

#
# SCIF Bus Driver
#
# CONFIG_SCIF_BUS is not set

#
# Intel MIC Host Driver
#

#
# Intel MIC Card Driver
#

#
# SCIF Driver
#
# CONFIG_GENWQE is not set
# CONFIG_ECHO is not set
# CONFIG_CXL_BASE is not set
# CONFIG_CXL_KERNEL_API is not set
# CONFIG_CXL_EEH is not set
CONFIG_HAVE_IDE=y
# CONFIG_IDE is not set

#
# SCSI device support
#
CONFIG_SCSI_MOD=y
# CONFIG_RAID_ATTRS is not set
CONFIG_SCSI=y
CONFIG_SCSI_DMA=y
# CONFIG_SCSI_NETLINK is not set
# CONFIG_SCSI_MQ_DEFAULT is not set
CONFIG_SCSI_PROC_FS=y

#
# SCSI support type (disk, tape, CD-ROM)
#
CONFIG_BLK_DEV_SD=y
# CONFIG_CHR_DEV_ST is not set
# CONFIG_CHR_DEV_OSST is not set
CONFIG_BLK_DEV_SR=y
CONFIG_BLK_DEV_SR_VENDOR=y
CONFIG_CHR_DEV_SG=y
# CONFIG_CHR_DEV_SCH is not set
CONFIG_SCSI_CONSTANTS=y
# CONFIG_SCSI_LOGGING is not set
# CONFIG_SCSI_SCAN_ASYNC is not set

#
# SCSI Transports
#
CONFIG_SCSI_SPI_ATTRS=y
# CONFIG_SCSI_FC_ATTRS is not set
# CONFIG_SCSI_ISCSI_ATTRS is not set
# CONFIG_SCSI_SAS_ATTRS is not set
# CONFIG_SCSI_SAS_LIBSAS is not set
# CONFIG_SCSI_SRP_ATTRS is not set
# CONFIG_SCSI_LOWLEVEL is not set
# CONFIG_SCSI_LOWLEVEL_PCMCIA is not set
# CONFIG_SCSI_DH is not set
# CONFIG_SCSI_OSD_INITIATOR is not set
CONFIG_ATA=y
# CONFIG_ATA_NONSTANDARD is not set
CONFIG_ATA_VERBOSE_ERROR=y
CONFIG_ATA_ACPI=y
# CONFIG_SATA_ZPODD is not set
CONFIG_SATA_PMP=y

#
# Controllers with non-SFF native interface
#
CONFIG_SATA_AHCI=y
# CONFIG_SATA_AHCI_PLATFORM is not set
# CONFIG_SATA_INIC162X is not set
# CONFIG_SATA_ACARD_AHCI is not set
# CONFIG_SATA_SIL24 is not set
CONFIG_ATA_SFF=y

#
# SFF controllers with custom DMA interface
#
# CONFIG_PDC_ADMA is not set
# CONFIG_SATA_QSTOR is not set
# CONFIG_SATA_SX4 is not set
CONFIG_ATA_BMDMA=y

#
# SATA SFF controllers with BMDMA
#
CONFIG_ATA_PIIX=y
# CONFIG_SATA_MV is not set
# CONFIG_SATA_NV is not set
# CONFIG_SATA_PROMISE is not set
# CONFIG_SATA_SIL is not set
# CONFIG_SATA_SIS is not set
# CONFIG_SATA_SVW is not set
# CONFIG_SATA_ULI is not set
# CONFIG_SATA_VIA is not set
# CONFIG_SATA_VITESSE is not set

#
# PATA SFF controllers with BMDMA
#
# CONFIG_PATA_ALI is not set
CONFIG_PATA_AMD=y
# CONFIG_PATA_ARTOP is not set
# CONFIG_PATA_ATIIXP is not set
# CONFIG_PATA_ATP867X is not set
# CONFIG_PATA_CMD64X is not set
# CONFIG_PATA_CYPRESS is not set
# CONFIG_PATA_EFAR is not set
# CONFIG_PATA_HPT366 is not set
# CONFIG_PATA_HPT37X is not set
# CONFIG_PATA_HPT3X2N is not set
# CONFIG_PATA_HPT3X3 is not set
# CONFIG_PATA_IT8213 is not set
# CONFIG_PATA_IT821X is not set
# CONFIG_PATA_JMICRON is not set
# CONFIG_PATA_MARVELL is not set
# CONFIG_PATA_NETCELL is not set
# CONFIG_PATA_NINJA32 is not set
# CONFIG_PATA_NS87415 is not set
CONFIG_PATA_OLDPIIX=y
# CONFIG_PATA_OPTIDMA is not set
# CONFIG_PATA_PDC2027X is not set
# CONFIG_PATA_PDC_OLD is not set
# CONFIG_PATA_RADISYS is not set
# CONFIG_PATA_RDC is not set
CONFIG_PATA_SCH=y
# CONFIG_PATA_SERVERWORKS is not set
# CONFIG_PATA_SIL680 is not set
# CONFIG_PATA_SIS is not set
# CONFIG_PATA_TOSHIBA is not set
# CONFIG_PATA_TRIFLEX is not set
# CONFIG_PATA_VIA is not set
# CONFIG_PATA_WINBOND is not set

#
# PIO-only SFF controllers
#
# CONFIG_PATA_CMD640_PCI is not set
# CONFIG_PATA_MPIIX is not set
# CONFIG_PATA_NS87410 is not set
# CONFIG_PATA_OPTI is not set
# CONFIG_PATA_PCMCIA is not set
# CONFIG_PATA_PLATFORM is not set
# CONFIG_PATA_RZ1000 is not set

#
# Generic fallback / legacy drivers
#
# CONFIG_PATA_ACPI is not set
# CONFIG_ATA_GENERIC is not set
# CONFIG_PATA_LEGACY is not set
CONFIG_MD=y
CONFIG_BLK_DEV_MD=y
CONFIG_MD_AUTODETECT=y
# CONFIG_MD_LINEAR is not set
# CONFIG_MD_RAID0 is not set
# CONFIG_MD_RAID1 is not set
# CONFIG_MD_RAID10 is not set
# CONFIG_MD_RAID456 is not set
# CONFIG_MD_MULTIPATH is not set
# CONFIG_MD_FAULTY is not set
# CONFIG_BCACHE is not set
CONFIG_BLK_DEV_DM_BUILTIN=y
CONFIG_BLK_DEV_DM=y
# CONFIG_DM_MQ_DEFAULT is not set
# CONFIG_DM_DEBUG is not set
# CONFIG_DM_CRYPT is not set
# CONFIG_DM_SNAPSHOT is not set
# CONFIG_DM_THIN_PROVISIONING is not set
# CONFIG_DM_CACHE is not set
# CONFIG_DM_ERA is not set
CONFIG_DM_MIRROR=y
# CONFIG_DM_LOG_USERSPACE is not set
# CONFIG_DM_RAID is not set
CONFIG_DM_ZERO=y
# CONFIG_DM_MULTIPATH is not set
# CONFIG_DM_DELAY is not set
# CONFIG_DM_UEVENT is not set
# CONFIG_DM_FLAKEY is not set
# CONFIG_DM_VERITY is not set
# CONFIG_DM_SWITCH is not set
# CONFIG_DM_LOG_WRITES is not set
# CONFIG_TARGET_CORE is not set
# CONFIG_FUSION is not set

#
# IEEE 1394 (FireWire) support
#
# CONFIG_FIREWIRE is not set
# CONFIG_FIREWIRE_NOSY is not set
CONFIG_MACINTOSH_DRIVERS=y
CONFIG_MAC_EMUMOUSEBTN=y
CONFIG_NETDEVICES=y
CONFIG_MII=y
CONFIG_NET_CORE=y
# CONFIG_BONDING is not set
# CONFIG_DUMMY is not set
# CONFIG_EQUALIZER is not set
# CONFIG_NET_FC is not set
# CONFIG_IFB is not set
# CONFIG_NET_TEAM is not set
# CONFIG_MACVLAN is not set
# CONFIG_IPVLAN is not set
# CONFIG_VXLAN is not set
CONFIG_NETCONSOLE=y
CONFIG_NETPOLL=y
CONFIG_NET_POLL_CONTROLLER=y
# CONFIG_TUN is not set
# CONFIG_TUN_VNET_CROSS_LE is not set
# CONFIG_VETH is not set
CONFIG_VIRTIO_NET=y
# CONFIG_NLMON is not set
# CONFIG_ARCNET is not set

#
# CAIF transport drivers
#
# CONFIG_VHOST_NET is not set
# CONFIG_VHOST_CROSS_ENDIAN_LEGACY is not set

#
# Distributed Switch Architecture drivers
#
# CONFIG_NET_DSA_MV88E6XXX is not set
# CONFIG_NET_DSA_MV88E6XXX_NEED_PPU is not set
CONFIG_ETHERNET=y
CONFIG_NET_VENDOR_3COM=y
# CONFIG_PCMCIA_3C574 is not set
# CONFIG_PCMCIA_3C589 is not set
# CONFIG_VORTEX is not set
# CONFIG_TYPHOON is not set
CONFIG_NET_VENDOR_ADAPTEC=y
# CONFIG_ADAPTEC_STARFIRE is not set
CONFIG_NET_VENDOR_AGERE=y
# CONFIG_ET131X is not set
CONFIG_NET_VENDOR_ALTEON=y
# CONFIG_ACENIC is not set
# CONFIG_ALTERA_TSE is not set
CONFIG_NET_VENDOR_AMD=y
# CONFIG_AMD8111_ETH is not set
# CONFIG_PCNET32 is not set
# CONFIG_PCMCIA_NMCLAN is not set
CONFIG_NET_VENDOR_ARC=y
CONFIG_NET_VENDOR_ATHEROS=y
# CONFIG_ATL2 is not set
# CONFIG_ATL1 is not set
# CONFIG_ATL1E is not set
# CONFIG_ATL1C is not set
# CONFIG_ALX is not set
CONFIG_NET_CADENCE=y
# CONFIG_MACB is not set
CONFIG_NET_VENDOR_BROADCOM=y
# CONFIG_B44 is not set
# CONFIG_BCMGENET is not set
# CONFIG_BNX2 is not set
# CONFIG_CNIC is not set
CONFIG_TIGON3=y
# CONFIG_BNX2X is not set
CONFIG_NET_VENDOR_BROCADE=y
# CONFIG_BNA is not set
CONFIG_NET_VENDOR_CAVIUM=y
# CONFIG_THUNDER_NIC_PF is not set
# CONFIG_THUNDER_NIC_VF is not set
# CONFIG_THUNDER_NIC_BGX is not set
# CONFIG_LIQUIDIO is not set
CONFIG_NET_VENDOR_CHELSIO=y
# CONFIG_CHELSIO_T1 is not set
# CONFIG_CHELSIO_T3 is not set
# CONFIG_CHELSIO_T4 is not set
# CONFIG_CHELSIO_T4VF is not set
CONFIG_NET_VENDOR_CISCO=y
# CONFIG_ENIC is not set
# CONFIG_CX_ECAT is not set
# CONFIG_DNET is not set
CONFIG_NET_VENDOR_DEC=y
CONFIG_NET_TULIP=y
# CONFIG_DE2104X is not set
# CONFIG_TULIP is not set
# CONFIG_DE4X5 is not set
# CONFIG_WINBOND_840 is not set
# CONFIG_DM9102 is not set
# CONFIG_ULI526X is not set
# CONFIG_PCMCIA_XIRCOM is not set
CONFIG_NET_VENDOR_DLINK=y
# CONFIG_DL2K is not set
# CONFIG_SUNDANCE is not set
CONFIG_NET_VENDOR_EMULEX=y
# CONFIG_BE2NET is not set
CONFIG_NET_VENDOR_EZCHIP=y
CONFIG_NET_VENDOR_EXAR=y
# CONFIG_S2IO is not set
# CONFIG_VXGE is not set
CONFIG_NET_VENDOR_FUJITSU=y
# CONFIG_PCMCIA_FMVJ18X is not set
CONFIG_NET_VENDOR_HP=y
# CONFIG_HP100 is not set
CONFIG_NET_VENDOR_INTEL=y
CONFIG_E100=y
CONFIG_E1000=y
# CONFIG_E1000E is not set
# CONFIG_IGB is not set
# CONFIG_IGBVF is not set
# CONFIG_IXGB is not set
# CONFIG_IXGBE is not set
# CONFIG_IXGBEVF is not set
# CONFIG_I40E is not set
# CONFIG_I40EVF is not set
# CONFIG_FM10K is not set
CONFIG_NET_VENDOR_I825XX=y
# CONFIG_IP1000 is not set
# CONFIG_JME is not set
CONFIG_NET_VENDOR_MARVELL=y
# CONFIG_MVMDIO is not set
# CONFIG_SKGE is not set
CONFIG_SKY2=y
# CONFIG_SKY2_DEBUG is not set
CONFIG_NET_VENDOR_MELLANOX=y
# CONFIG_MLX4_EN is not set
# CONFIG_MLX4_CORE is not set
# CONFIG_MLX5_CORE is not set
# CONFIG_MLXSW_CORE is not set
CONFIG_NET_VENDOR_MICREL=y
# CONFIG_KS8851_MLL is not set
# CONFIG_KSZ884X_PCI is not set
CONFIG_NET_VENDOR_MYRI=y
# CONFIG_MYRI10GE is not set
# CONFIG_FEALNX is not set
CONFIG_NET_VENDOR_NATSEMI=y
# CONFIG_NATSEMI is not set
# CONFIG_NS83820 is not set
CONFIG_NET_VENDOR_8390=y
# CONFIG_PCMCIA_AXNET is not set
# CONFIG_NE2K_PCI is not set
# CONFIG_PCMCIA_PCNET is not set
CONFIG_NET_VENDOR_NVIDIA=y
CONFIG_FORCEDETH=y
CONFIG_NET_VENDOR_OKI=y
# CONFIG_ETHOC is not set
CONFIG_NET_PACKET_ENGINE=y
# CONFIG_HAMACHI is not set
# CONFIG_YELLOWFIN is not set
CONFIG_NET_VENDOR_QLOGIC=y
# CONFIG_QLA3XXX is not set
# CONFIG_QLCNIC is not set
# CONFIG_QLGE is not set
# CONFIG_NETXEN_NIC is not set
CONFIG_NET_VENDOR_QUALCOMM=y
CONFIG_NET_VENDOR_REALTEK=y
# CONFIG_8139CP is not set
CONFIG_8139TOO=y
CONFIG_8139TOO_PIO=y
# CONFIG_8139TOO_TUNE_TWISTER is not set
# CONFIG_8139TOO_8129 is not set
# CONFIG_8139_OLD_RX_RESET is not set
# CONFIG_R8169 is not set
CONFIG_NET_VENDOR_RENESAS=y
CONFIG_NET_VENDOR_RDC=y
# CONFIG_R6040 is not set
CONFIG_NET_VENDOR_ROCKER=y
CONFIG_NET_VENDOR_SAMSUNG=y
# CONFIG_SXGBE_ETH is not set
CONFIG_NET_VENDOR_SEEQ=y
CONFIG_NET_VENDOR_SILAN=y
# CONFIG_SC92031 is not set
CONFIG_NET_VENDOR_SIS=y
# CONFIG_SIS900 is not set
# CONFIG_SIS190 is not set
# CONFIG_SFC is not set
CONFIG_NET_VENDOR_SMSC=y
# CONFIG_PCMCIA_SMC91C92 is not set
# CONFIG_EPIC100 is not set
# CONFIG_SMSC911X is not set
# CONFIG_SMSC9420 is not set
CONFIG_NET_VENDOR_STMICRO=y
# CONFIG_STMMAC_ETH is not set
CONFIG_NET_VENDOR_SUN=y
# CONFIG_HAPPYMEAL is not set
# CONFIG_SUNGEM is not set
# CONFIG_CASSINI is not set
# CONFIG_NIU is not set
CONFIG_NET_VENDOR_SYNOPSYS=y
CONFIG_NET_VENDOR_TEHUTI=y
# CONFIG_TEHUTI is not set
CONFIG_NET_VENDOR_TI=y
# CONFIG_TI_CPSW_ALE is not set
# CONFIG_TLAN is not set
CONFIG_NET_VENDOR_VIA=y
# CONFIG_VIA_RHINE is not set
# CONFIG_VIA_VELOCITY is not set
CONFIG_NET_VENDOR_WIZNET=y
# CONFIG_WIZNET_W5100 is not set
# CONFIG_WIZNET_W5300 is not set
CONFIG_NET_VENDOR_XIRCOM=y
# CONFIG_PCMCIA_XIRC2PS is not set
CONFIG_FDDI=y
# CONFIG_DEFXX is not set
# CONFIG_SKFP is not set
# CONFIG_HIPPI is not set
# CONFIG_NET_SB1000 is not set
CONFIG_PHYLIB=y

#
# MII PHY device drivers
#
# CONFIG_AQUANTIA_PHY is not set
# CONFIG_AT803X_PHY is not set
# CONFIG_AMD_PHY is not set
# CONFIG_MARVELL_PHY is not set
# CONFIG_DAVICOM_PHY is not set
# CONFIG_QSEMI_PHY is not set
# CONFIG_LXT_PHY is not set
# CONFIG_CICADA_PHY is not set
# CONFIG_VITESSE_PHY is not set
# CONFIG_TERANETICS_PHY is not set
# CONFIG_SMSC_PHY is not set
# CONFIG_BROADCOM_PHY is not set
# CONFIG_BCM7XXX_PHY is not set
# CONFIG_BCM87XX_PHY is not set
# CONFIG_ICPLUS_PHY is not set
# CONFIG_REALTEK_PHY is not set
# CONFIG_NATIONAL_PHY is not set
# CONFIG_STE10XP is not set
# CONFIG_LSI_ET1011C_PHY is not set
# CONFIG_MICREL_PHY is not set
# CONFIG_DP83867_PHY is not set
# CONFIG_MICROCHIP_PHY is not set
# CONFIG_FIXED_PHY is not set
# CONFIG_MDIO_BITBANG is not set
# CONFIG_MDIO_OCTEON is not set
# CONFIG_MDIO_BCM_UNIMAC is not set
# CONFIG_PPP is not set
# CONFIG_SLIP is not set
CONFIG_USB_NET_DRIVERS=y
# CONFIG_USB_CATC is not set
# CONFIG_USB_KAWETH is not set
# CONFIG_USB_PEGASUS is not set
# CONFIG_USB_RTL8150 is not set
# CONFIG_USB_RTL8152 is not set
# CONFIG_USB_LAN78XX is not set
# CONFIG_USB_USBNET is not set
# CONFIG_USB_HSO is not set
# CONFIG_USB_IPHETH is not set
CONFIG_WLAN=y
# CONFIG_PCMCIA_RAYCS is not set
# CONFIG_LIBERTAS_THINFIRM is not set
# CONFIG_AIRO is not set
# CONFIG_ATMEL is not set
# CONFIG_AT76C50X_USB is not set
# CONFIG_AIRO_CS is not set
# CONFIG_PCMCIA_WL3501 is not set
# CONFIG_PRISM54 is not set
# CONFIG_USB_ZD1201 is not set
# CONFIG_USB_NET_RNDIS_WLAN is not set
# CONFIG_RTL8180 is not set
# CONFIG_RTL8187 is not set
# CONFIG_ADM8211 is not set
# CONFIG_MAC80211_HWSIM is not set
# CONFIG_MWL8K is not set
# CONFIG_ATH_CARDS is not set
# CONFIG_B43 is not set
# CONFIG_B43LEGACY is not set
# CONFIG_BRCMSMAC is not set
# CONFIG_BRCMFMAC is not set
# CONFIG_HOSTAP is not set
# CONFIG_IPW2100 is not set
# CONFIG_IPW2200 is not set
# CONFIG_IWLWIFI is not set
# CONFIG_IWL4965 is not set
# CONFIG_IWL3945 is not set
# CONFIG_LIBERTAS is not set
# CONFIG_HERMES is not set
# CONFIG_P54_COMMON is not set
# CONFIG_RT2X00 is not set
# CONFIG_WL_MEDIATEK is not set
CONFIG_RTL_CARDS=y
# CONFIG_RTL8192CE is not set
# CONFIG_RTL8192SE is not set
# CONFIG_RTL8192DE is not set
# CONFIG_RTL8723AE is not set
# CONFIG_RTL8723BE is not set
# CONFIG_RTL8188EE is not set
# CONFIG_RTL8192EE is not set
# CONFIG_RTL8821AE is not set
# CONFIG_RTL8192CU is not set
# CONFIG_WL_TI is not set
# CONFIG_ZD1211RW is not set
# CONFIG_MWIFIEX is not set
# CONFIG_CW1200 is not set
# CONFIG_RSI_91X is not set

#
# Enable WiMAX (Networking options) to see the WiMAX drivers
#
# CONFIG_WAN is not set
# CONFIG_VMXNET3 is not set
# CONFIG_FUJITSU_ES is not set
# CONFIG_ISDN is not set

#
# Input device support
#
CONFIG_INPUT=y
CONFIG_INPUT_LEDS=y
CONFIG_INPUT_FF_MEMLESS=y
CONFIG_INPUT_POLLDEV=y
CONFIG_INPUT_SPARSEKMAP=y
# CONFIG_INPUT_MATRIXKMAP is not set

#
# Userland interfaces
#
CONFIG_INPUT_MOUSEDEV=y
# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
# CONFIG_INPUT_JOYDEV is not set
CONFIG_INPUT_EVDEV=y
# CONFIG_INPUT_EVBUG is not set

#
# Input Device Drivers
#
CONFIG_INPUT_KEYBOARD=y
# CONFIG_KEYBOARD_ADP5588 is not set
# CONFIG_KEYBOARD_ADP5589 is not set
CONFIG_KEYBOARD_ATKBD=y
# CONFIG_KEYBOARD_QT1070 is not set
# CONFIG_KEYBOARD_QT2160 is not set
# CONFIG_KEYBOARD_LKKBD is not set
# CONFIG_KEYBOARD_TCA6416 is not set
# CONFIG_KEYBOARD_TCA8418 is not set
# CONFIG_KEYBOARD_LM8323 is not set
# CONFIG_KEYBOARD_LM8333 is not set
# CONFIG_KEYBOARD_MAX7359 is not set
# CONFIG_KEYBOARD_MCS is not set
# CONFIG_KEYBOARD_MPR121 is not set
# CONFIG_KEYBOARD_NEWTON is not set
# CONFIG_KEYBOARD_OPENCORES is not set
# CONFIG_KEYBOARD_STOWAWAY is not set
# CONFIG_KEYBOARD_SUNKBD is not set
# CONFIG_KEYBOARD_XTKBD is not set
CONFIG_INPUT_MOUSE=y
CONFIG_MOUSE_PS2=y
CONFIG_MOUSE_PS2_ALPS=y
CONFIG_MOUSE_PS2_LOGIPS2PP=y
CONFIG_MOUSE_PS2_SYNAPTICS=y
CONFIG_MOUSE_PS2_CYPRESS=y
CONFIG_MOUSE_PS2_LIFEBOOK=y
CONFIG_MOUSE_PS2_TRACKPOINT=y
# CONFIG_MOUSE_PS2_ELANTECH is not set
# CONFIG_MOUSE_PS2_SENTELIC is not set
# CONFIG_MOUSE_PS2_TOUCHKIT is not set
CONFIG_MOUSE_PS2_FOCALTECH=y
# CONFIG_MOUSE_PS2_VMMOUSE is not set
# CONFIG_MOUSE_SERIAL is not set
# CONFIG_MOUSE_APPLETOUCH is not set
# CONFIG_MOUSE_BCM5974 is not set
# CONFIG_MOUSE_CYAPA is not set
# CONFIG_MOUSE_ELAN_I2C is not set
# CONFIG_MOUSE_VSXXXAA is not set
# CONFIG_MOUSE_SYNAPTICS_I2C is not set
# CONFIG_MOUSE_SYNAPTICS_USB is not set
CONFIG_INPUT_JOYSTICK=y
# CONFIG_JOYSTICK_ANALOG is not set
# CONFIG_JOYSTICK_A3D is not set
# CONFIG_JOYSTICK_ADI is not set
# CONFIG_JOYSTICK_COBRA is not set
# CONFIG_JOYSTICK_GF2K is not set
# CONFIG_JOYSTICK_GRIP is not set
# CONFIG_JOYSTICK_GRIP_MP is not set
# CONFIG_JOYSTICK_GUILLEMOT is not set
# CONFIG_JOYSTICK_INTERACT is not set
# CONFIG_JOYSTICK_SIDEWINDER is not set
# CONFIG_JOYSTICK_TMDC is not set
# CONFIG_JOYSTICK_IFORCE is not set
# CONFIG_JOYSTICK_WARRIOR is not set
# CONFIG_JOYSTICK_MAGELLAN is not set
# CONFIG_JOYSTICK_SPACEORB is not set
# CONFIG_JOYSTICK_SPACEBALL is not set
# CONFIG_JOYSTICK_STINGER is not set
# CONFIG_JOYSTICK_TWIDJOY is not set
# CONFIG_JOYSTICK_ZHENHUA is not set
# CONFIG_JOYSTICK_AS5011 is not set
# CONFIG_JOYSTICK_JOYDUMP is not set
# CONFIG_JOYSTICK_XPAD is not set
CONFIG_INPUT_TABLET=y
# CONFIG_TABLET_USB_ACECAD is not set
# CONFIG_TABLET_USB_AIPTEK is not set
# CONFIG_TABLET_USB_GTCO is not set
# CONFIG_TABLET_USB_HANWANG is not set
# CONFIG_TABLET_USB_KBTAB is not set
# CONFIG_TABLET_SERIAL_WACOM4 is not set
CONFIG_INPUT_TOUCHSCREEN=y
CONFIG_TOUCHSCREEN_PROPERTIES=y
# CONFIG_TOUCHSCREEN_AD7879 is not set
# CONFIG_TOUCHSCREEN_ATMEL_MXT is not set
# CONFIG_TOUCHSCREEN_BU21013 is not set
# CONFIG_TOUCHSCREEN_CYTTSP_CORE is not set
# CONFIG_TOUCHSCREEN_CYTTSP4_CORE is not set
# CONFIG_TOUCHSCREEN_DYNAPRO is not set
# CONFIG_TOUCHSCREEN_HAMPSHIRE is not set
# CONFIG_TOUCHSCREEN_EETI is not set
# CONFIG_TOUCHSCREEN_FUJITSU is not set
# CONFIG_TOUCHSCREEN_GOODIX is not set
# CONFIG_TOUCHSCREEN_ILI210X is not set
# CONFIG_TOUCHSCREEN_GUNZE is not set
# CONFIG_TOUCHSCREEN_ELAN is not set
# CONFIG_TOUCHSCREEN_ELO is not set
# CONFIG_TOUCHSCREEN_WACOM_W8001 is not set
# CONFIG_TOUCHSCREEN_WACOM_I2C is not set
# CONFIG_TOUCHSCREEN_MAX11801 is not set
# CONFIG_TOUCHSCREEN_MCS5000 is not set
# CONFIG_TOUCHSCREEN_MMS114 is not set
# CONFIG_TOUCHSCREEN_MTOUCH is not set
# CONFIG_TOUCHSCREEN_INEXIO is not set
# CONFIG_TOUCHSCREEN_MK712 is not set
# CONFIG_TOUCHSCREEN_PENMOUNT is not set
# CONFIG_TOUCHSCREEN_EDT_FT5X06 is not set
# CONFIG_TOUCHSCREEN_TOUCHRIGHT is not set
# CONFIG_TOUCHSCREEN_TOUCHWIN is not set
# CONFIG_TOUCHSCREEN_PIXCIR is not set
# CONFIG_TOUCHSCREEN_WDT87XX_I2C is not set
# CONFIG_TOUCHSCREEN_USB_COMPOSITE is not set
# CONFIG_TOUCHSCREEN_TOUCHIT213 is not set
# CONFIG_TOUCHSCREEN_TSC_SERIO is not set
# CONFIG_TOUCHSCREEN_TSC2007 is not set
# CONFIG_TOUCHSCREEN_ST1232 is not set
# CONFIG_TOUCHSCREEN_SX8654 is not set
# CONFIG_TOUCHSCREEN_TPS6507X is not set
CONFIG_INPUT_MISC=y
# CONFIG_INPUT_AD714X is not set
# CONFIG_INPUT_BMA150 is not set
# CONFIG_INPUT_E3X0_BUTTON is not set
# CONFIG_INPUT_PCSPKR is not set
# CONFIG_INPUT_MMA8450 is not set
# CONFIG_INPUT_MPU3050 is not set
# CONFIG_INPUT_APANEL is not set
# CONFIG_INPUT_ATLAS_BTNS is not set
# CONFIG_INPUT_ATI_REMOTE2 is not set
# CONFIG_INPUT_KEYSPAN_REMOTE is not set
# CONFIG_INPUT_KXTJ9 is not set
# CONFIG_INPUT_POWERMATE is not set
# CONFIG_INPUT_YEALINK is not set
# CONFIG_INPUT_CM109 is not set
# CONFIG_INPUT_UINPUT is not set
# CONFIG_INPUT_PCF8574 is not set
# CONFIG_INPUT_ADXL34X is not set
# CONFIG_INPUT_IMS_PCU is not set
# CONFIG_INPUT_CMA3000 is not set
# CONFIG_INPUT_IDEAPAD_SLIDEBAR is not set
# CONFIG_INPUT_DRV2665_HAPTICS is not set
# CONFIG_INPUT_DRV2667_HAPTICS is not set

#
# Hardware I/O ports
#
CONFIG_SERIO=y
CONFIG_ARCH_MIGHT_HAVE_PC_SERIO=y
CONFIG_SERIO_I8042=y
CONFIG_SERIO_SERPORT=y
# CONFIG_SERIO_CT82C710 is not set
# CONFIG_SERIO_PCIPS2 is not set
CONFIG_SERIO_LIBPS2=y
# CONFIG_SERIO_RAW is not set
# CONFIG_SERIO_ALTERA_PS2 is not set
# CONFIG_SERIO_PS2MULT is not set
# CONFIG_SERIO_ARC_PS2 is not set
# CONFIG_GAMEPORT is not set

#
# Character devices
#
CONFIG_TTY=y
CONFIG_VT=y
CONFIG_CONSOLE_TRANSLATIONS=y
CONFIG_VT_CONSOLE=y
CONFIG_VT_CONSOLE_SLEEP=y
CONFIG_HW_CONSOLE=y
CONFIG_VT_HW_CONSOLE_BINDING=y
CONFIG_UNIX98_PTYS=y
# CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set
# CONFIG_LEGACY_PTYS is not set
CONFIG_SERIAL_NONSTANDARD=y
# CONFIG_ROCKETPORT is not set
# CONFIG_CYCLADES is not set
# CONFIG_MOXA_INTELLIO is not set
# CONFIG_MOXA_SMARTIO is not set
# CONFIG_SYNCLINK is not set
# CONFIG_SYNCLINKMP is not set
# CONFIG_SYNCLINK_GT is not set
# CONFIG_NOZOMI is not set
# CONFIG_ISI is not set
# CONFIG_N_HDLC is not set
# CONFIG_N_GSM is not set
# CONFIG_TRACE_SINK is not set
CONFIG_DEVMEM=y
CONFIG_DEVKMEM=y

#
# Serial drivers
#
CONFIG_SERIAL_EARLYCON=y
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_DEPRECATED_OPTIONS=y
CONFIG_SERIAL_8250_PNP=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_SERIAL_8250_DMA=y
CONFIG_SERIAL_8250_PCI=y
# CONFIG_SERIAL_8250_CS is not set
CONFIG_SERIAL_8250_NR_UARTS=32
CONFIG_SERIAL_8250_RUNTIME_UARTS=4
CONFIG_SERIAL_8250_EXTENDED=y
CONFIG_SERIAL_8250_MANY_PORTS=y
CONFIG_SERIAL_8250_SHARE_IRQ=y
CONFIG_SERIAL_8250_DETECT_IRQ=y
CONFIG_SERIAL_8250_RSA=y
# CONFIG_SERIAL_8250_DW is not set
# CONFIG_SERIAL_8250_FINTEK is not set

#
# Non-8250 serial port support
#
# CONFIG_SERIAL_UARTLITE is not set
CONFIG_SERIAL_CORE=y
CONFIG_SERIAL_CORE_CONSOLE=y
# CONFIG_SERIAL_JSM is not set
# CONFIG_SERIAL_SCCNXP is not set
# CONFIG_SERIAL_SC16IS7XX is not set
# CONFIG_SERIAL_ALTERA_JTAGUART is not set
# CONFIG_SERIAL_ALTERA_UART is not set
# CONFIG_SERIAL_ARC is not set
# CONFIG_SERIAL_RP2 is not set
# CONFIG_SERIAL_FSL_LPUART is not set
# CONFIG_TTY_PRINTK is not set
CONFIG_HVC_DRIVER=y
CONFIG_VIRTIO_CONSOLE=y
# CONFIG_IPMI_HANDLER is not set
CONFIG_HW_RANDOM=y
# CONFIG_HW_RANDOM_TIMERIOMEM is not set
# CONFIG_HW_RANDOM_INTEL is not set
# CONFIG_HW_RANDOM_AMD is not set
CONFIG_HW_RANDOM_VIA=y
# CONFIG_HW_RANDOM_VIRTIO is not set
CONFIG_NVRAM=y
# CONFIG_R3964 is not set
# CONFIG_APPLICOM is not set

#
# PCMCIA character devices
#
# CONFIG_SYNCLINK_CS is not set
# CONFIG_CARDMAN_4000 is not set
# CONFIG_CARDMAN_4040 is not set
# CONFIG_IPWIRELESS is not set
# CONFIG_MWAVE is not set
# CONFIG_RAW_DRIVER is not set
CONFIG_HPET=y
# CONFIG_HPET_MMAP is not set
# CONFIG_HANGCHECK_TIMER is not set
# CONFIG_TCG_TPM is not set
# CONFIG_TELCLOCK is not set
CONFIG_DEVPORT=y
# CONFIG_XILLYBUS is not set

#
# I2C support
#
CONFIG_I2C=y
CONFIG_ACPI_I2C_OPREGION=y
CONFIG_I2C_BOARDINFO=y
CONFIG_I2C_COMPAT=y
# CONFIG_I2C_CHARDEV is not set
# CONFIG_I2C_MUX is not set
CONFIG_I2C_HELPER_AUTO=y
CONFIG_I2C_ALGOBIT=y

#
# I2C Hardware Bus support
#

#
# PC SMBus host controller drivers
#
# CONFIG_I2C_ALI1535 is not set
# CONFIG_I2C_ALI1563 is not set
# CONFIG_I2C_ALI15X3 is not set
# CONFIG_I2C_AMD756 is not set
# CONFIG_I2C_AMD8111 is not set
CONFIG_I2C_I801=y
# CONFIG_I2C_ISCH is not set
# CONFIG_I2C_ISMT is not set
# CONFIG_I2C_PIIX4 is not set
# CONFIG_I2C_NFORCE2 is not set
# CONFIG_I2C_SIS5595 is not set
# CONFIG_I2C_SIS630 is not set
# CONFIG_I2C_SIS96X is not set
# CONFIG_I2C_VIA is not set
# CONFIG_I2C_VIAPRO is not set

#
# ACPI drivers
#
# CONFIG_I2C_SCMI is not set

#
# I2C system bus drivers (mostly embedded / system-on-chip)
#
# CONFIG_I2C_DESIGNWARE_PCI is not set
# CONFIG_I2C_OCORES is not set
# CONFIG_I2C_PCA_PLATFORM is not set
# CONFIG_I2C_PXA_PCI is not set
# CONFIG_I2C_SIMTEC is not set
# CONFIG_I2C_XILINX is not set

#
# External I2C/SMBus adapter drivers
#
# CONFIG_I2C_DIOLAN_U2C is not set
# CONFIG_I2C_PARPORT_LIGHT is not set
# CONFIG_I2C_ROBOTFUZZ_OSIF is not set
# CONFIG_I2C_TAOS_EVM is not set
# CONFIG_I2C_TINY_USB is not set

#
# Other I2C/SMBus bus drivers
#
# CONFIG_I2C_STUB is not set
# CONFIG_I2C_SLAVE is not set
# CONFIG_I2C_DEBUG_CORE is not set
# CONFIG_I2C_DEBUG_ALGO is not set
# CONFIG_I2C_DEBUG_BUS is not set
# CONFIG_SPI is not set
# CONFIG_SPMI is not set
# CONFIG_HSI is not set

#
# PPS support
#
CONFIG_PPS=y
# CONFIG_PPS_DEBUG is not set

#
# PPS clients support
#
# CONFIG_PPS_CLIENT_KTIMER is not set
# CONFIG_PPS_CLIENT_LDISC is not set
# CONFIG_PPS_CLIENT_GPIO is not set

#
# PPS generators support
#

#
# PTP clock support
#
CONFIG_PTP_1588_CLOCK=y

#
# Enable PHYLIB and NETWORK_PHY_TIMESTAMPING to see the additional clocks.
#
CONFIG_ARCH_WANT_OPTIONAL_GPIOLIB=y
# CONFIG_GPIOLIB is not set
# CONFIG_W1 is not set
CONFIG_POWER_SUPPLY=y
# CONFIG_POWER_SUPPLY_DEBUG is not set
# CONFIG_PDA_POWER is not set
# CONFIG_TEST_POWER is not set
# CONFIG_BATTERY_DS2780 is not set
# CONFIG_BATTERY_DS2781 is not set
# CONFIG_BATTERY_DS2782 is not set
# CONFIG_BATTERY_SBS is not set
# CONFIG_BATTERY_BQ27XXX is not set
# CONFIG_BATTERY_MAX17040 is not set
# CONFIG_BATTERY_MAX17042 is not set
# CONFIG_CHARGER_MAX8903 is not set
# CONFIG_CHARGER_LP8727 is not set
# CONFIG_CHARGER_BQ2415X is not set
# CONFIG_CHARGER_SMB347 is not set
# CONFIG_BATTERY_GAUGE_LTC2941 is not set
# CONFIG_POWER_RESET is not set
# CONFIG_POWER_AVS is not set
CONFIG_HWMON=y
# CONFIG_HWMON_VID is not set
# CONFIG_HWMON_DEBUG_CHIP is not set

#
# Native drivers
#
# CONFIG_SENSORS_ABITUGURU is not set
# CONFIG_SENSORS_ABITUGURU3 is not set
# CONFIG_SENSORS_AD7414 is not set
# CONFIG_SENSORS_AD7418 is not set
# CONFIG_SENSORS_ADM1021 is not set
# CONFIG_SENSORS_ADM1025 is not set
# CONFIG_SENSORS_ADM1026 is not set
# CONFIG_SENSORS_ADM1029 is not set
# CONFIG_SENSORS_ADM1031 is not set
# CONFIG_SENSORS_ADM9240 is not set
# CONFIG_SENSORS_ADT7410 is not set
# CONFIG_SENSORS_ADT7411 is not set
# CONFIG_SENSORS_ADT7462 is not set
# CONFIG_SENSORS_ADT7470 is not set
# CONFIG_SENSORS_ADT7475 is not set
# CONFIG_SENSORS_ASC7621 is not set
# CONFIG_SENSORS_K8TEMP is not set
# CONFIG_SENSORS_K10TEMP is not set
# CONFIG_SENSORS_FAM15H_POWER is not set
# CONFIG_SENSORS_APPLESMC is not set
# CONFIG_SENSORS_ASB100 is not set
# CONFIG_SENSORS_ATXP1 is not set
# CONFIG_SENSORS_DS620 is not set
# CONFIG_SENSORS_DS1621 is not set
# CONFIG_SENSORS_DELL_SMM is not set
# CONFIG_SENSORS_I5K_AMB is not set
# CONFIG_SENSORS_F71805F is not set
# CONFIG_SENSORS_F71882FG is not set
# CONFIG_SENSORS_F75375S is not set
# CONFIG_SENSORS_FSCHMD is not set
# CONFIG_SENSORS_GL518SM is not set
# CONFIG_SENSORS_GL520SM is not set
# CONFIG_SENSORS_G760A is not set
# CONFIG_SENSORS_G762 is not set
# CONFIG_SENSORS_HIH6130 is not set
# CONFIG_SENSORS_I5500 is not set
# CONFIG_SENSORS_CORETEMP is not set
# CONFIG_SENSORS_IT87 is not set
# CONFIG_SENSORS_JC42 is not set
# CONFIG_SENSORS_POWR1220 is not set
# CONFIG_SENSORS_LINEAGE is not set
# CONFIG_SENSORS_LTC2945 is not set
# CONFIG_SENSORS_LTC4151 is not set
# CONFIG_SENSORS_LTC4215 is not set
# CONFIG_SENSORS_LTC4222 is not set
# CONFIG_SENSORS_LTC4245 is not set
# CONFIG_SENSORS_LTC4260 is not set
# CONFIG_SENSORS_LTC4261 is not set
# CONFIG_SENSORS_MAX16065 is not set
# CONFIG_SENSORS_MAX1619 is not set
# CONFIG_SENSORS_MAX1668 is not set
# CONFIG_SENSORS_MAX197 is not set
# CONFIG_SENSORS_MAX6639 is not set
# CONFIG_SENSORS_MAX6642 is not set
# CONFIG_SENSORS_MAX6650 is not set
# CONFIG_SENSORS_MAX6697 is not set
# CONFIG_SENSORS_MAX31790 is not set
# CONFIG_SENSORS_HTU21 is not set
# CONFIG_SENSORS_MCP3021 is not set
# CONFIG_SENSORS_LM63 is not set
# CONFIG_SENSORS_LM73 is not set
# CONFIG_SENSORS_LM75 is not set
# CONFIG_SENSORS_LM77 is not set
# CONFIG_SENSORS_LM78 is not set
# CONFIG_SENSORS_LM80 is not set
# CONFIG_SENSORS_LM83 is not set
# CONFIG_SENSORS_LM85 is not set
# CONFIG_SENSORS_LM87 is not set
# CONFIG_SENSORS_LM90 is not set
# CONFIG_SENSORS_LM92 is not set
# CONFIG_SENSORS_LM93 is not set
# CONFIG_SENSORS_LM95234 is not set
# CONFIG_SENSORS_LM95241 is not set
# CONFIG_SENSORS_LM95245 is not set
# CONFIG_SENSORS_PC87360 is not set
# CONFIG_SENSORS_PC87427 is not set
# CONFIG_SENSORS_NTC_THERMISTOR is not set
# CONFIG_SENSORS_NCT6683 is not set
# CONFIG_SENSORS_NCT6775 is not set
# CONFIG_SENSORS_NCT7802 is not set
# CONFIG_SENSORS_NCT7904 is not set
# CONFIG_SENSORS_PCF8591 is not set
# CONFIG_PMBUS is not set
# CONFIG_SENSORS_SHT21 is not set
# CONFIG_SENSORS_SHTC1 is not set
# CONFIG_SENSORS_SIS5595 is not set
# CONFIG_SENSORS_DME1737 is not set
# CONFIG_SENSORS_EMC1403 is not set
# CONFIG_SENSORS_EMC2103 is not set
# CONFIG_SENSORS_EMC6W201 is not set
# CONFIG_SENSORS_SMSC47M1 is not set
# CONFIG_SENSORS_SMSC47M192 is not set
# CONFIG_SENSORS_SMSC47B397 is not set
# CONFIG_SENSORS_SCH56XX_COMMON is not set
# CONFIG_SENSORS_SCH5627 is not set
# CONFIG_SENSORS_SCH5636 is not set
# CONFIG_SENSORS_SMM665 is not set
# CONFIG_SENSORS_ADC128D818 is not set
# CONFIG_SENSORS_ADS1015 is not set
# CONFIG_SENSORS_ADS7828 is not set
# CONFIG_SENSORS_AMC6821 is not set
# CONFIG_SENSORS_INA209 is not set
# CONFIG_SENSORS_INA2XX is not set
# CONFIG_SENSORS_TC74 is not set
# CONFIG_SENSORS_THMC50 is not set
# CONFIG_SENSORS_TMP102 is not set
# CONFIG_SENSORS_TMP103 is not set
# CONFIG_SENSORS_TMP401 is not set
# CONFIG_SENSORS_TMP421 is not set
# CONFIG_SENSORS_VIA_CPUTEMP is not set
# CONFIG_SENSORS_VIA686A is not set
# CONFIG_SENSORS_VT1211 is not set
# CONFIG_SENSORS_VT8231 is not set
# CONFIG_SENSORS_W83781D is not set
# CONFIG_SENSORS_W83791D is not set
# CONFIG_SENSORS_W83792D is not set
# CONFIG_SENSORS_W83793 is not set
# CONFIG_SENSORS_W83795 is not set
# CONFIG_SENSORS_W83L785TS is not set
# CONFIG_SENSORS_W83L786NG is not set
# CONFIG_SENSORS_W83627HF is not set
# CONFIG_SENSORS_W83627EHF is not set

#
# ACPI drivers
#
# CONFIG_SENSORS_ACPI_POWER is not set
# CONFIG_SENSORS_ATK0110 is not set
CONFIG_THERMAL=y
CONFIG_THERMAL_HWMON=y
# CONFIG_THERMAL_WRITABLE_TRIPS is not set
CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE=y
# CONFIG_THERMAL_DEFAULT_GOV_FAIR_SHARE is not set
# CONFIG_THERMAL_DEFAULT_GOV_USER_SPACE is not set
# CONFIG_THERMAL_DEFAULT_GOV_POWER_ALLOCATOR is not set
# CONFIG_THERMAL_GOV_FAIR_SHARE is not set
CONFIG_THERMAL_GOV_STEP_WISE=y
# CONFIG_THERMAL_GOV_BANG_BANG is not set
CONFIG_THERMAL_GOV_USER_SPACE=y
# CONFIG_THERMAL_GOV_POWER_ALLOCATOR is not set
# CONFIG_THERMAL_EMULATION is not set
# CONFIG_INTEL_POWERCLAMP is not set
CONFIG_X86_PKG_TEMP_THERMAL=m
# CONFIG_INTEL_SOC_DTS_THERMAL is not set
# CONFIG_INT340X_THERMAL is not set
# CONFIG_INTEL_PCH_THERMAL is not set
CONFIG_WATCHDOG=y
# CONFIG_WATCHDOG_CORE is not set
# CONFIG_WATCHDOG_NOWAYOUT is not set

#
# Watchdog Device Drivers
#
# CONFIG_SOFT_WATCHDOG is not set
# CONFIG_XILINX_WATCHDOG is not set
# CONFIG_CADENCE_WATCHDOG is not set
# CONFIG_DW_WATCHDOG is not set
# CONFIG_MAX63XX_WATCHDOG is not set
# CONFIG_ACQUIRE_WDT is not set
# CONFIG_ADVANTECH_WDT is not set
# CONFIG_ALIM1535_WDT is not set
# CONFIG_ALIM7101_WDT is not set
# CONFIG_F71808E_WDT is not set
# CONFIG_SP5100_TCO is not set
# CONFIG_SBC_FITPC2_WATCHDOG is not set
# CONFIG_EUROTECH_WDT is not set
# CONFIG_IB700_WDT is not set
# CONFIG_IBMASR is not set
# CONFIG_WAFER_WDT is not set
# CONFIG_I6300ESB_WDT is not set
# CONFIG_IE6XX_WDT is not set
# CONFIG_ITCO_WDT is not set
# CONFIG_IT8712F_WDT is not set
# CONFIG_IT87_WDT is not set
# CONFIG_HP_WATCHDOG is not set
# CONFIG_SC1200_WDT is not set
# CONFIG_PC87413_WDT is not set
# CONFIG_NV_TCO is not set
# CONFIG_60XX_WDT is not set
# CONFIG_CPU5_WDT is not set
# CONFIG_SMSC_SCH311X_WDT is not set
# CONFIG_SMSC37B787_WDT is not set
# CONFIG_VIA_WDT is not set
# CONFIG_W83627HF_WDT is not set
# CONFIG_W83877F_WDT is not set
# CONFIG_W83977F_WDT is not set
# CONFIG_MACHZ_WDT is not set
# CONFIG_SBC_EPX_C3_WATCHDOG is not set

#
# PCI-based Watchdog Cards
#
# CONFIG_PCIPCWATCHDOG is not set
# CONFIG_WDTPCI is not set

#
# USB-based Watchdog Cards
#
# CONFIG_USBPCWATCHDOG is not set
CONFIG_SSB_POSSIBLE=y

#
# Sonics Silicon Backplane
#
# CONFIG_SSB is not set
CONFIG_BCMA_POSSIBLE=y

#
# Broadcom specific AMBA
#
# CONFIG_BCMA is not set

#
# Multifunction device drivers
#
# CONFIG_MFD_CORE is not set
# CONFIG_MFD_AS3711 is not set
# CONFIG_PMIC_ADP5520 is not set
# CONFIG_MFD_BCM590XX is not set
# CONFIG_MFD_AXP20X is not set
# CONFIG_MFD_CROS_EC is not set
# CONFIG_PMIC_DA903X is not set
# CONFIG_MFD_DA9052_I2C is not set
# CONFIG_MFD_DA9055 is not set
# CONFIG_MFD_DA9062 is not set
# CONFIG_MFD_DA9063 is not set
# CONFIG_MFD_DA9150 is not set
# CONFIG_MFD_DLN2 is not set
# CONFIG_MFD_MC13XXX_I2C is not set
# CONFIG_HTC_PASIC3 is not set
# CONFIG_LPC_ICH is not set
# CONFIG_LPC_SCH is not set
# CONFIG_MFD_INTEL_LPSS_ACPI is not set
# CONFIG_MFD_INTEL_LPSS_PCI is not set
# CONFIG_MFD_JANZ_CMODIO is not set
# CONFIG_MFD_KEMPLD is not set
# CONFIG_MFD_88PM800 is not set
# CONFIG_MFD_88PM805 is not set
# CONFIG_MFD_88PM860X is not set
# CONFIG_MFD_MAX14577 is not set
# CONFIG_MFD_MAX77693 is not set
# CONFIG_MFD_MAX77843 is not set
# CONFIG_MFD_MAX8907 is not set
# CONFIG_MFD_MAX8925 is not set
# CONFIG_MFD_MAX8997 is not set
# CONFIG_MFD_MAX8998 is not set
# CONFIG_MFD_MT6397 is not set
# CONFIG_MFD_MENF21BMC is not set
# CONFIG_MFD_VIPERBOARD is not set
# CONFIG_MFD_RETU is not set
# CONFIG_MFD_PCF50633 is not set
# CONFIG_MFD_RDC321X is not set
# CONFIG_MFD_RTSX_PCI is not set
# CONFIG_MFD_RT5033 is not set
# CONFIG_MFD_RTSX_USB is not set
# CONFIG_MFD_RC5T583 is not set
# CONFIG_MFD_RN5T618 is not set
# CONFIG_MFD_SEC_CORE is not set
# CONFIG_MFD_SI476X_CORE is not set
# CONFIG_MFD_SM501 is not set
# CONFIG_MFD_SKY81452 is not set
# CONFIG_MFD_SMSC is not set
# CONFIG_ABX500_CORE is not set
# CONFIG_MFD_SYSCON is not set
# CONFIG_MFD_TI_AM335X_TSCADC is not set
# CONFIG_MFD_LP3943 is not set
# CONFIG_MFD_LP8788 is not set
# CONFIG_MFD_PALMAS is not set
# CONFIG_TPS6105X is not set
# CONFIG_TPS6507X is not set
# CONFIG_MFD_TPS65090 is not set
# CONFIG_MFD_TPS65217 is not set
# CONFIG_MFD_TPS65218 is not set
# CONFIG_MFD_TPS6586X is not set
# CONFIG_MFD_TPS80031 is not set
# CONFIG_TWL4030_CORE is not set
# CONFIG_TWL6040_CORE is not set
# CONFIG_MFD_WL1273_CORE is not set
# CONFIG_MFD_LM3533 is not set
# CONFIG_MFD_TMIO is not set
# CONFIG_MFD_VX855 is not set
# CONFIG_MFD_ARIZONA_I2C is not set
# CONFIG_MFD_WM8400 is not set
# CONFIG_MFD_WM831X_I2C is not set
# CONFIG_MFD_WM8350_I2C is not set
# CONFIG_MFD_WM8994 is not set
# CONFIG_REGULATOR is not set
# CONFIG_MEDIA_SUPPORT is not set

#
# Graphics support
#
CONFIG_AGP=y
CONFIG_AGP_AMD64=y
CONFIG_AGP_INTEL=y
# CONFIG_AGP_SIS is not set
# CONFIG_AGP_VIA is not set
CONFIG_INTEL_GTT=y
CONFIG_VGA_ARB=y
CONFIG_VGA_ARB_MAX_GPUS=16
# CONFIG_VGA_SWITCHEROO is not set
CONFIG_DRM=y
CONFIG_DRM_MIPI_DSI=y
CONFIG_DRM_KMS_HELPER=y
CONFIG_DRM_KMS_FB_HELPER=y
CONFIG_DRM_FBDEV_EMULATION=y
# CONFIG_DRM_LOAD_EDID_FIRMWARE is not set

#
# I2C encoder or helper chips
#
# CONFIG_DRM_I2C_ADV7511 is not set
# CONFIG_DRM_I2C_CH7006 is not set
# CONFIG_DRM_I2C_SIL164 is not set
# CONFIG_DRM_I2C_NXP_TDA998X is not set
# CONFIG_DRM_TDFX is not set
# CONFIG_DRM_R128 is not set
# CONFIG_DRM_RADEON is not set
# CONFIG_DRM_AMDGPU is not set
# CONFIG_DRM_NOUVEAU is not set
# CONFIG_DRM_I810 is not set
CONFIG_DRM_I915=y
# CONFIG_DRM_I915_PRELIMINARY_HW_SUPPORT is not set
# CONFIG_DRM_MGA is not set
# CONFIG_DRM_SIS is not set
# CONFIG_DRM_VIA is not set
# CONFIG_DRM_SAVAGE is not set
# CONFIG_DRM_VGEM is not set
# CONFIG_DRM_VMWGFX is not set
# CONFIG_DRM_GMA500 is not set
# CONFIG_DRM_UDL is not set
# CONFIG_DRM_AST is not set
# CONFIG_DRM_MGAG200 is not set
# CONFIG_DRM_CIRRUS_QEMU is not set
# CONFIG_DRM_QXL is not set
# CONFIG_DRM_BOCHS is not set
# CONFIG_DRM_VIRTIO_GPU is not set
CONFIG_DRM_PANEL=y

#
# Display Panels
#
CONFIG_DRM_BRIDGE=y

#
# Display Interface Bridges
#

#
# Frame buffer Devices
#
CONFIG_FB=y
# CONFIG_FIRMWARE_EDID is not set
CONFIG_FB_CMDLINE=y
# CONFIG_FB_DDC is not set
# CONFIG_FB_BOOT_VESA_SUPPORT is not set
CONFIG_FB_CFB_FILLRECT=y
CONFIG_FB_CFB_COPYAREA=y
CONFIG_FB_CFB_IMAGEBLIT=y
# CONFIG_FB_CFB_REV_PIXELS_IN_BYTE is not set
CONFIG_FB_SYS_FILLRECT=y
CONFIG_FB_SYS_COPYAREA=y
CONFIG_FB_SYS_IMAGEBLIT=y
# CONFIG_FB_FOREIGN_ENDIAN is not set
CONFIG_FB_SYS_FOPS=y
# CONFIG_FB_SVGALIB is not set
# CONFIG_FB_MACMODES is not set
# CONFIG_FB_BACKLIGHT is not set
CONFIG_FB_MODE_HELPERS=y
CONFIG_FB_TILEBLITTING=y

#
# Frame buffer hardware drivers
#
# CONFIG_FB_CIRRUS is not set
# CONFIG_FB_PM2 is not set
# CONFIG_FB_CYBER2000 is not set
# CONFIG_FB_ARC is not set
# CONFIG_FB_ASILIANT is not set
# CONFIG_FB_IMSTT is not set
# CONFIG_FB_VGA16 is not set
# CONFIG_FB_UVESA is not set
# CONFIG_FB_VESA is not set
CONFIG_FB_EFI=y
# CONFIG_FB_N411 is not set
# CONFIG_FB_HGA is not set
# CONFIG_FB_OPENCORES is not set
# CONFIG_FB_S1D13XXX is not set
# CONFIG_FB_NVIDIA is not set
# CONFIG_FB_RIVA is not set
# CONFIG_FB_I740 is not set
# CONFIG_FB_LE80578 is not set
# CONFIG_FB_MATROX is not set
# CONFIG_FB_RADEON is not set
# CONFIG_FB_ATY128 is not set
# CONFIG_FB_ATY is not set
# CONFIG_FB_S3 is not set
# CONFIG_FB_SAVAGE is not set
# CONFIG_FB_SIS is not set
# CONFIG_FB_NEOMAGIC is not set
# CONFIG_FB_KYRO is not set
# CONFIG_FB_3DFX is not set
# CONFIG_FB_VOODOO1 is not set
# CONFIG_FB_VT8623 is not set
# CONFIG_FB_TRIDENT is not set
# CONFIG_FB_ARK is not set
# CONFIG_FB_PM3 is not set
# CONFIG_FB_CARMINE is not set
# CONFIG_FB_SMSCUFX is not set
# CONFIG_FB_UDL is not set
# CONFIG_FB_VIRTUAL is not set
# CONFIG_FB_METRONOME is not set
# CONFIG_FB_MB862XX is not set
# CONFIG_FB_BROADSHEET is not set
# CONFIG_FB_AUO_K190X is not set
# CONFIG_FB_SIMPLE is not set
# CONFIG_FB_SM712 is not set
CONFIG_BACKLIGHT_LCD_SUPPORT=y
# CONFIG_LCD_CLASS_DEVICE is not set
CONFIG_BACKLIGHT_CLASS_DEVICE=y
CONFIG_BACKLIGHT_GENERIC=y
# CONFIG_BACKLIGHT_APPLE is not set
# CONFIG_BACKLIGHT_PM8941_WLED is not set
# CONFIG_BACKLIGHT_SAHARA is not set
# CONFIG_BACKLIGHT_ADP8860 is not set
# CONFIG_BACKLIGHT_ADP8870 is not set
# CONFIG_BACKLIGHT_LM3639 is not set
# CONFIG_BACKLIGHT_LV5207LP is not set
# CONFIG_BACKLIGHT_BD6107 is not set
# CONFIG_VGASTATE is not set
CONFIG_HDMI=y

#
# Console display driver support
#
CONFIG_VGA_CONSOLE=y
CONFIG_VGACON_SOFT_SCROLLBACK=y
CONFIG_VGACON_SOFT_SCROLLBACK_SIZE=64
CONFIG_DUMMY_CONSOLE=y
CONFIG_DUMMY_CONSOLE_COLUMNS=80
CONFIG_DUMMY_CONSOLE_ROWS=25
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
# CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set
CONFIG_LOGO=y
# CONFIG_LOGO_LINUX_MONO is not set
# CONFIG_LOGO_LINUX_VGA16 is not set
CONFIG_LOGO_LINUX_CLUT224=y
CONFIG_SOUND=y
CONFIG_SOUND_OSS_CORE=y
CONFIG_SOUND_OSS_CORE_PRECLAIM=y
CONFIG_SND=y
CONFIG_SND_TIMER=y
CONFIG_SND_PCM=y
CONFIG_SND_HWDEP=y
CONFIG_SND_JACK=y
CONFIG_SND_SEQUENCER=y
CONFIG_SND_SEQ_DUMMY=y
CONFIG_SND_OSSEMUL=y
CONFIG_SND_MIXER_OSS=y
CONFIG_SND_PCM_OSS=y
CONFIG_SND_PCM_OSS_PLUGINS=y
CONFIG_SND_SEQUENCER_OSS=y
CONFIG_SND_HRTIMER=y
CONFIG_SND_SEQ_HRTIMER_DEFAULT=y
# CONFIG_SND_DYNAMIC_MINORS is not set
CONFIG_SND_SUPPORT_OLD_API=y
CONFIG_SND_PROC_FS=y
CONFIG_SND_VERBOSE_PROCFS=y
# CONFIG_SND_VERBOSE_PRINTK is not set
# CONFIG_SND_DEBUG is not set
CONFIG_SND_VMASTER=y
CONFIG_SND_DMA_SGBUF=y
# CONFIG_SND_RAWMIDI_SEQ is not set
# CONFIG_SND_OPL3_LIB_SEQ is not set
# CONFIG_SND_OPL4_LIB_SEQ is not set
# CONFIG_SND_SBAWE_SEQ is not set
# CONFIG_SND_EMU10K1_SEQ is not set
CONFIG_SND_DRIVERS=y
# CONFIG_SND_PCSP is not set
# CONFIG_SND_DUMMY is not set
# CONFIG_SND_ALOOP is not set
# CONFIG_SND_VIRMIDI is not set
# CONFIG_SND_MTPAV is not set
# CONFIG_SND_SERIAL_U16550 is not set
# CONFIG_SND_MPU401 is not set
CONFIG_SND_PCI=y
# CONFIG_SND_AD1889 is not set
# CONFIG_SND_ALS300 is not set
# CONFIG_SND_ALS4000 is not set
# CONFIG_SND_ALI5451 is not set
# CONFIG_SND_ASIHPI is not set
# CONFIG_SND_ATIIXP is not set
# CONFIG_SND_ATIIXP_MODEM is not set
# CONFIG_SND_AU8810 is not set
# CONFIG_SND_AU8820 is not set
# CONFIG_SND_AU8830 is not set
# CONFIG_SND_AW2 is not set
# CONFIG_SND_AZT3328 is not set
# CONFIG_SND_BT87X is not set
# CONFIG_SND_CA0106 is not set
# CONFIG_SND_CMIPCI is not set
# CONFIG_SND_OXYGEN is not set
# CONFIG_SND_CS4281 is not set
# CONFIG_SND_CS46XX is not set
# CONFIG_SND_CTXFI is not set
# CONFIG_SND_DARLA20 is not set
# CONFIG_SND_GINA20 is not set
# CONFIG_SND_LAYLA20 is not set
# CONFIG_SND_DARLA24 is not set
# CONFIG_SND_GINA24 is not set
# CONFIG_SND_LAYLA24 is not set
# CONFIG_SND_MONA is not set
# CONFIG_SND_MIA is not set
# CONFIG_SND_ECHO3G is not set
# CONFIG_SND_INDIGO is not set
# CONFIG_SND_INDIGOIO is not set
# CONFIG_SND_INDIGODJ is not set
# CONFIG_SND_INDIGOIOX is not set
# CONFIG_SND_INDIGODJX is not set
# CONFIG_SND_EMU10K1 is not set
# CONFIG_SND_EMU10K1X is not set
# CONFIG_SND_ENS1370 is not set
# CONFIG_SND_ENS1371 is not set
# CONFIG_SND_ES1938 is not set
# CONFIG_SND_ES1968 is not set
# CONFIG_SND_FM801 is not set
# CONFIG_SND_HDSP is not set
# CONFIG_SND_HDSPM is not set
# CONFIG_SND_ICE1712 is not set
# CONFIG_SND_ICE1724 is not set
# CONFIG_SND_INTEL8X0 is not set
# CONFIG_SND_INTEL8X0M is not set
# CONFIG_SND_KORG1212 is not set
# CONFIG_SND_LOLA is not set
# CONFIG_SND_LX6464ES is not set
# CONFIG_SND_MAESTRO3 is not set
# CONFIG_SND_MIXART is not set
# CONFIG_SND_NM256 is not set
# CONFIG_SND_PCXHR is not set
# CONFIG_SND_RIPTIDE is not set
# CONFIG_SND_RME32 is not set
# CONFIG_SND_RME96 is not set
# CONFIG_SND_RME9652 is not set
# CONFIG_SND_SE6X is not set
# CONFIG_SND_SONICVIBES is not set
# CONFIG_SND_TRIDENT is not set
# CONFIG_SND_VIA82XX is not set
# CONFIG_SND_VIA82XX_MODEM is not set
# CONFIG_SND_VIRTUOSO is not set
# CONFIG_SND_VX222 is not set
# CONFIG_SND_YMFPCI is not set

#
# HD-Audio
#
CONFIG_SND_HDA=y
CONFIG_SND_HDA_INTEL=y
CONFIG_SND_HDA_HWDEP=y
# CONFIG_SND_HDA_RECONFIG is not set
# CONFIG_SND_HDA_INPUT_BEEP is not set
# CONFIG_SND_HDA_PATCH_LOADER is not set
# CONFIG_SND_HDA_CODEC_REALTEK is not set
# CONFIG_SND_HDA_CODEC_ANALOG is not set
# CONFIG_SND_HDA_CODEC_SIGMATEL is not set
# CONFIG_SND_HDA_CODEC_VIA is not set
# CONFIG_SND_HDA_CODEC_HDMI is not set
# CONFIG_SND_HDA_CODEC_CIRRUS is not set
# CONFIG_SND_HDA_CODEC_CONEXANT is not set
# CONFIG_SND_HDA_CODEC_CA0110 is not set
# CONFIG_SND_HDA_CODEC_CA0132 is not set
# CONFIG_SND_HDA_CODEC_CMEDIA is not set
# CONFIG_SND_HDA_CODEC_SI3054 is not set
# CONFIG_SND_HDA_GENERIC is not set
CONFIG_SND_HDA_POWER_SAVE_DEFAULT=0
CONFIG_SND_HDA_CORE=y
CONFIG_SND_HDA_I915=y
CONFIG_SND_HDA_PREALLOC_SIZE=64
CONFIG_SND_USB=y
# CONFIG_SND_USB_AUDIO is not set
# CONFIG_SND_USB_UA101 is not set
# CONFIG_SND_USB_USX2Y is not set
# CONFIG_SND_USB_CAIAQ is not set
# CONFIG_SND_USB_US122L is not set
# CONFIG_SND_USB_6FIRE is not set
# CONFIG_SND_USB_HIFACE is not set
# CONFIG_SND_BCD2000 is not set
# CONFIG_SND_USB_POD is not set
# CONFIG_SND_USB_PODHD is not set
# CONFIG_SND_USB_TONEPORT is not set
# CONFIG_SND_USB_VARIAX is not set
CONFIG_SND_PCMCIA=y
# CONFIG_SND_VXPOCKET is not set
# CONFIG_SND_PDAUDIOCF is not set
# CONFIG_SND_SOC is not set
# CONFIG_SOUND_PRIME is not set

#
# HID support
#
CONFIG_HID=y
# CONFIG_HID_BATTERY_STRENGTH is not set
CONFIG_HIDRAW=y
# CONFIG_UHID is not set
CONFIG_HID_GENERIC=y

#
# Special HID drivers
#
CONFIG_HID_A4TECH=y
# CONFIG_HID_ACRUX is not set
CONFIG_HID_APPLE=y
# CONFIG_HID_APPLEIR is not set
# CONFIG_HID_AUREAL is not set
CONFIG_HID_BELKIN=y
# CONFIG_HID_BETOP_FF is not set
CONFIG_HID_CHERRY=y
CONFIG_HID_CHICONY=y
# CONFIG_HID_PRODIKEYS is not set
CONFIG_HID_CYPRESS=y
# CONFIG_HID_DRAGONRISE is not set
# CONFIG_HID_EMS_FF is not set
# CONFIG_HID_ELECOM is not set
# CONFIG_HID_ELO is not set
CONFIG_HID_EZKEY=y
# CONFIG_HID_GEMBIRD is not set
# CONFIG_HID_HOLTEK is not set
# CONFIG_HID_GT683R is not set
# CONFIG_HID_KEYTOUCH is not set
# CONFIG_HID_KYE is not set
# CONFIG_HID_UCLOGIC is not set
# CONFIG_HID_WALTOP is not set
CONFIG_HID_GYRATION=y
# CONFIG_HID_ICADE is not set
# CONFIG_HID_TWINHAN is not set
CONFIG_HID_KENSINGTON=y
# CONFIG_HID_LCPOWER is not set
# CONFIG_HID_LENOVO is not set
CONFIG_HID_LOGITECH=y
# CONFIG_HID_LOGITECH_DJ is not set
# CONFIG_HID_LOGITECH_HIDPP is not set
CONFIG_LOGITECH_FF=y
# CONFIG_LOGIRUMBLEPAD2_FF is not set
# CONFIG_LOGIG940_FF is not set
CONFIG_LOGIWHEELS_FF=y
# CONFIG_HID_MAGICMOUSE is not set
CONFIG_HID_MICROSOFT=y
CONFIG_HID_MONTEREY=y
# CONFIG_HID_MULTITOUCH is not set
CONFIG_HID_NTRIG=y
# CONFIG_HID_ORTEK is not set
CONFIG_HID_PANTHERLORD=y
CONFIG_PANTHERLORD_FF=y
# CONFIG_HID_PENMOUNT is not set
CONFIG_HID_PETALYNX=y
# CONFIG_HID_PICOLCD is not set
# CONFIG_HID_PLANTRONICS is not set
# CONFIG_HID_PRIMAX is not set
# CONFIG_HID_ROCCAT is not set
# CONFIG_HID_SAITEK is not set
CONFIG_HID_SAMSUNG=y
CONFIG_HID_SONY=y
# CONFIG_SONY_FF is not set
# CONFIG_HID_SPEEDLINK is not set
# CONFIG_HID_STEELSERIES is not set
CONFIG_HID_SUNPLUS=y
# CONFIG_HID_RMI is not set
# CONFIG_HID_GREENASIA is not set
# CONFIG_HID_SMARTJOYPLUS is not set
# CONFIG_HID_TIVO is not set
CONFIG_HID_TOPSEED=y
# CONFIG_HID_THINGM is not set
# CONFIG_HID_THRUSTMASTER is not set
# CONFIG_HID_WACOM is not set
# CONFIG_HID_WIIMOTE is not set
# CONFIG_HID_XINMO is not set
# CONFIG_HID_ZEROPLUS is not set
# CONFIG_HID_ZYDACRON is not set
# CONFIG_HID_SENSOR_HUB is not set

#
# USB HID support
#
CONFIG_USB_HID=y
CONFIG_HID_PID=y
CONFIG_USB_HIDDEV=y

#
# I2C HID support
#
# CONFIG_I2C_HID is not set
CONFIG_USB_OHCI_LITTLE_ENDIAN=y
CONFIG_USB_SUPPORT=y
CONFIG_USB_COMMON=y
CONFIG_USB_ARCH_HAS_HCD=y
CONFIG_USB=y
CONFIG_USB_ANNOUNCE_NEW_DEVICES=y

#
# Miscellaneous USB options
#
CONFIG_USB_DEFAULT_PERSIST=y
# CONFIG_USB_DYNAMIC_MINORS is not set
# CONFIG_USB_OTG is not set
# CONFIG_USB_OTG_WHITELIST is not set
# CONFIG_USB_OTG_BLACKLIST_HUB is not set
# CONFIG_USB_OTG_FSM is not set
# CONFIG_USB_ULPI_BUS is not set
CONFIG_USB_MON=y
# CONFIG_USB_WUSB_CBAF is not set

#
# USB Host Controller Drivers
#
# CONFIG_USB_C67X00_HCD is not set
# CONFIG_USB_XHCI_HCD is not set
CONFIG_USB_EHCI_HCD=y
# CONFIG_USB_EHCI_ROOT_HUB_TT is not set
CONFIG_USB_EHCI_TT_NEWSCHED=y
CONFIG_USB_EHCI_PCI=y
# CONFIG_USB_EHCI_HCD_PLATFORM is not set
# CONFIG_USB_OXU210HP_HCD is not set
# CONFIG_USB_ISP116X_HCD is not set
# CONFIG_USB_ISP1362_HCD is not set
# CONFIG_USB_FUSBH200_HCD is not set
# CONFIG_USB_FOTG210_HCD is not set
CONFIG_USB_OHCI_HCD=y
CONFIG_USB_OHCI_HCD_PCI=y
# CONFIG_USB_OHCI_HCD_PLATFORM is not set
CONFIG_USB_UHCI_HCD=y
# CONFIG_USB_SL811_HCD is not set
# CONFIG_USB_R8A66597_HCD is not set
# CONFIG_USB_HCD_TEST_MODE is not set

#
# USB Device Class drivers
#
# CONFIG_USB_ACM is not set
CONFIG_USB_PRINTER=y
# CONFIG_USB_WDM is not set
# CONFIG_USB_TMC is not set

#
# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may
#

#
# also be needed; see USB_STORAGE Help for more info
#
CONFIG_USB_STORAGE=y
# CONFIG_USB_STORAGE_DEBUG is not set
# CONFIG_USB_STORAGE_REALTEK is not set
# CONFIG_USB_STORAGE_DATAFAB is not set
# CONFIG_USB_STORAGE_FREECOM is not set
# CONFIG_USB_STORAGE_ISD200 is not set
# CONFIG_USB_STORAGE_USBAT is not set
# CONFIG_USB_STORAGE_SDDR09 is not set
# CONFIG_USB_STORAGE_SDDR55 is not set
# CONFIG_USB_STORAGE_JUMPSHOT is not set
# CONFIG_USB_STORAGE_ALAUDA is not set
# CONFIG_USB_STORAGE_ONETOUCH is not set
# CONFIG_USB_STORAGE_KARMA is not set
# CONFIG_USB_STORAGE_CYPRESS_ATACB is not set
# CONFIG_USB_STORAGE_ENE_UB6250 is not set
# CONFIG_USB_UAS is not set

#
# USB Imaging devices
#
# CONFIG_USB_MDC800 is not set
# CONFIG_USB_MICROTEK is not set
# CONFIG_USBIP_CORE is not set
# CONFIG_USB_MUSB_HDRC is not set
# CONFIG_USB_DWC3 is not set
# CONFIG_USB_DWC2 is not set
# CONFIG_USB_CHIPIDEA is not set
# CONFIG_USB_ISP1760 is not set

#
# USB port drivers
#
# CONFIG_USB_SERIAL is not set

#
# USB Miscellaneous drivers
#
# CONFIG_USB_EMI62 is not set
# CONFIG_USB_EMI26 is not set
# CONFIG_USB_ADUTUX is not set
# CONFIG_USB_SEVSEG is not set
# CONFIG_USB_RIO500 is not set
# CONFIG_USB_LEGOTOWER is not set
# CONFIG_USB_LCD is not set
# CONFIG_USB_LED is not set
# CONFIG_USB_CYPRESS_CY7C63 is not set
# CONFIG_USB_CYTHERM is not set
# CONFIG_USB_IDMOUSE is not set
# CONFIG_USB_FTDI_ELAN is not set
# CONFIG_USB_APPLEDISPLAY is not set
# CONFIG_USB_SISUSBVGA is not set
# CONFIG_USB_LD is not set
# CONFIG_USB_TRANCEVIBRATOR is not set
# CONFIG_USB_IOWARRIOR is not set
# CONFIG_USB_TEST is not set
# CONFIG_USB_EHSET_TEST_FIXTURE is not set
# CONFIG_USB_ISIGHTFW is not set
# CONFIG_USB_YUREX is not set
# CONFIG_USB_EZUSB_FX2 is not set
# CONFIG_USB_HSIC_USB3503 is not set
# CONFIG_USB_LINK_LAYER_TEST is not set
# CONFIG_USB_CHAOSKEY is not set

#
# USB Physical Layer drivers
#
# CONFIG_USB_PHY is not set
# CONFIG_NOP_USB_XCEIV is not set
# CONFIG_USB_ISP1301 is not set
# CONFIG_USB_GADGET is not set
# CONFIG_USB_LED_TRIG is not set
# CONFIG_UWB is not set
# CONFIG_MMC is not set
# CONFIG_MEMSTICK is not set
CONFIG_NEW_LEDS=y
CONFIG_LEDS_CLASS=y
# CONFIG_LEDS_CLASS_FLASH is not set

#
# LED drivers
#
# CONFIG_LEDS_LM3530 is not set
# CONFIG_LEDS_LM3642 is not set
# CONFIG_LEDS_PCA9532 is not set
# CONFIG_LEDS_LP3944 is not set
# CONFIG_LEDS_LP5521 is not set
# CONFIG_LEDS_LP5523 is not set
# CONFIG_LEDS_LP5562 is not set
# CONFIG_LEDS_LP8501 is not set
# CONFIG_LEDS_LP8860 is not set
# CONFIG_LEDS_CLEVO_MAIL is not set
# CONFIG_LEDS_PCA955X is not set
# CONFIG_LEDS_PCA963X is not set
# CONFIG_LEDS_BD2802 is not set
# CONFIG_LEDS_INTEL_SS4200 is not set
# CONFIG_LEDS_TCA6507 is not set
# CONFIG_LEDS_TLC591XX is not set
# CONFIG_LEDS_LM355x is not set

#
# LED driver for blink(1) USB RGB LED is under Special HID drivers (HID_THINGM)
#
# CONFIG_LEDS_BLINKM is not set

#
# LED Triggers
#
CONFIG_LEDS_TRIGGERS=y
# CONFIG_LEDS_TRIGGER_TIMER is not set
# CONFIG_LEDS_TRIGGER_ONESHOT is not set
# CONFIG_LEDS_TRIGGER_HEARTBEAT is not set
# CONFIG_LEDS_TRIGGER_BACKLIGHT is not set
# CONFIG_LEDS_TRIGGER_CPU is not set
# CONFIG_LEDS_TRIGGER_DEFAULT_ON is not set

#
# iptables trigger is under Netfilter config (LED target)
#
# CONFIG_LEDS_TRIGGER_TRANSIENT is not set
# CONFIG_LEDS_TRIGGER_CAMERA is not set
# CONFIG_ACCESSIBILITY is not set
# CONFIG_INFINIBAND is not set
CONFIG_EDAC_ATOMIC_SCRUB=y
CONFIG_EDAC_SUPPORT=y
CONFIG_EDAC=y
CONFIG_EDAC_LEGACY_SYSFS=y
# CONFIG_EDAC_DEBUG is not set
CONFIG_EDAC_DECODE_MCE=y
# CONFIG_EDAC_MM_EDAC is not set
CONFIG_RTC_LIB=y
CONFIG_RTC_CLASS=y
# CONFIG_RTC_HCTOSYS is not set
CONFIG_RTC_SYSTOHC=y
CONFIG_RTC_SYSTOHC_DEVICE="rtc0"
# CONFIG_RTC_DEBUG is not set

#
# RTC interfaces
#
CONFIG_RTC_INTF_SYSFS=y
CONFIG_RTC_INTF_PROC=y
CONFIG_RTC_INTF_DEV=y
# CONFIG_RTC_INTF_DEV_UIE_EMUL is not set
# CONFIG_RTC_DRV_TEST is not set

#
# I2C RTC drivers
#
# CONFIG_RTC_DRV_ABB5ZES3 is not set
# CONFIG_RTC_DRV_ABX80X is not set
# CONFIG_RTC_DRV_DS1307 is not set
# CONFIG_RTC_DRV_DS1374 is not set
# CONFIG_RTC_DRV_DS1672 is not set
# CONFIG_RTC_DRV_DS3232 is not set
# CONFIG_RTC_DRV_MAX6900 is not set
# CONFIG_RTC_DRV_RS5C372 is not set
# CONFIG_RTC_DRV_ISL1208 is not set
# CONFIG_RTC_DRV_ISL12022 is not set
# CONFIG_RTC_DRV_ISL12057 is not set
# CONFIG_RTC_DRV_X1205 is not set
# CONFIG_RTC_DRV_PCF2127 is not set
# CONFIG_RTC_DRV_PCF8523 is not set
# CONFIG_RTC_DRV_PCF8563 is not set
# CONFIG_RTC_DRV_PCF85063 is not set
# CONFIG_RTC_DRV_PCF8583 is not set
# CONFIG_RTC_DRV_M41T80 is not set
# CONFIG_RTC_DRV_BQ32K is not set
# CONFIG_RTC_DRV_S35390A is not set
# CONFIG_RTC_DRV_FM3130 is not set
# CONFIG_RTC_DRV_RX8581 is not set
# CONFIG_RTC_DRV_RX8025 is not set
# CONFIG_RTC_DRV_EM3027 is not set
# CONFIG_RTC_DRV_RV3029C2 is not set

#
# SPI RTC drivers
#

#
# Platform RTC drivers
#
CONFIG_RTC_DRV_CMOS=y
# CONFIG_RTC_DRV_DS1286 is not set
# CONFIG_RTC_DRV_DS1511 is not set
# CONFIG_RTC_DRV_DS1553 is not set
# CONFIG_RTC_DRV_DS1685_FAMILY is not set
# CONFIG_RTC_DRV_DS1742 is not set
# CONFIG_RTC_DRV_DS2404 is not set
# CONFIG_RTC_DRV_STK17TA8 is not set
# CONFIG_RTC_DRV_M48T86 is not set
# CONFIG_RTC_DRV_M48T35 is not set
# CONFIG_RTC_DRV_M48T59 is not set
# CONFIG_RTC_DRV_MSM6242 is not set
# CONFIG_RTC_DRV_BQ4802 is not set
# CONFIG_RTC_DRV_RP5C01 is not set
# CONFIG_RTC_DRV_V3020 is not set

#
# on-CPU RTC drivers
#

#
# HID Sensor RTC drivers
#
# CONFIG_RTC_DRV_HID_SENSOR_TIME is not set
CONFIG_DMADEVICES=y
# CONFIG_DMADEVICES_DEBUG is not set

#
# DMA Devices
#
CONFIG_DMA_ACPI=y
# CONFIG_IDMA64 is not set
# CONFIG_INTEL_IOATDMA is not set
# CONFIG_DW_DMAC is not set
# CONFIG_DW_DMAC_PCI is not set
# CONFIG_HSU_DMA_PCI is not set
# CONFIG_AUXDISPLAY is not set
# CONFIG_UIO is not set
# CONFIG_VFIO is not set
# CONFIG_VIRT_DRIVERS is not set
CONFIG_VIRTIO=y

#
# Virtio drivers
#
CONFIG_VIRTIO_PCI=y
CONFIG_VIRTIO_PCI_LEGACY=y
# CONFIG_VIRTIO_BALLOON is not set
# CONFIG_VIRTIO_INPUT is not set
# CONFIG_VIRTIO_MMIO is not set

#
# Microsoft Hyper-V guest support
#
# CONFIG_HYPERV is not set
# CONFIG_STAGING is not set
CONFIG_X86_PLATFORM_DEVICES=y
# CONFIG_ACERHDF is not set
# CONFIG_ASUS_LAPTOP is not set
# CONFIG_DELL_SMO8800 is not set
# CONFIG_DELL_RBTN is not set
# CONFIG_FUJITSU_LAPTOP is not set
# CONFIG_FUJITSU_TABLET is not set
# CONFIG_AMILO_RFKILL is not set
# CONFIG_HP_ACCEL is not set
# CONFIG_HP_WIRELESS is not set
# CONFIG_MSI_LAPTOP is not set
# CONFIG_PANASONIC_LAPTOP is not set
# CONFIG_COMPAL_LAPTOP is not set
# CONFIG_SONY_LAPTOP is not set
# CONFIG_IDEAPAD_LAPTOP is not set
# CONFIG_THINKPAD_ACPI is not set
# CONFIG_SENSORS_HDAPS is not set
# CONFIG_INTEL_MENLOW is not set
CONFIG_EEEPC_LAPTOP=y
# CONFIG_ACPI_WMI is not set
# CONFIG_TOPSTAR_LAPTOP is not set
# CONFIG_TOSHIBA_BT_RFKILL is not set
# CONFIG_TOSHIBA_HAPS is not set
# CONFIG_ACPI_CMPC is not set
# CONFIG_INTEL_IPS is not set
# CONFIG_IBM_RTL is not set
# CONFIG_SAMSUNG_LAPTOP is not set
# CONFIG_INTEL_OAKTRAIL is not set
# CONFIG_SAMSUNG_Q10 is not set
# CONFIG_APPLE_GMUX is not set
# CONFIG_INTEL_RST is not set
# CONFIG_INTEL_SMARTCONNECT is not set
# CONFIG_PVPANIC is not set
# CONFIG_INTEL_PMC_IPC is not set
# CONFIG_SURFACE_PRO3_BUTTON is not set
# CONFIG_CHROME_PLATFORMS is not set

#
# Hardware Spinlock drivers
#

#
# Clock Source drivers
#
CONFIG_CLKEVT_I8253=y
CONFIG_I8253_LOCK=y
CONFIG_CLKBLD_I8253=y
# CONFIG_ATMEL_PIT is not set
# CONFIG_SH_TIMER_CMT is not set
# CONFIG_SH_TIMER_MTU2 is not set
# CONFIG_SH_TIMER_TMU is not set
# CONFIG_EM_TIMER_STI is not set
# CONFIG_MAILBOX is not set
CONFIG_IOMMU_API=y
CONFIG_IOMMU_SUPPORT=y

#
# Generic IOMMU Pagetable Support
#
CONFIG_IOMMU_IOVA=y
CONFIG_AMD_IOMMU=y
CONFIG_AMD_IOMMU_STATS=y
# CONFIG_AMD_IOMMU_V2 is not set
CONFIG_DMAR_TABLE=y
CONFIG_INTEL_IOMMU=y
# CONFIG_INTEL_IOMMU_SVM is not set
# CONFIG_INTEL_IOMMU_DEFAULT_ON is not set
CONFIG_INTEL_IOMMU_FLOPPY_WA=y
# CONFIG_IRQ_REMAP is not set

#
# Remoteproc drivers
#
# CONFIG_STE_MODEM_RPROC is not set

#
# Rpmsg drivers
#

#
# SOC (System On Chip) specific Drivers
#
# CONFIG_SUNXI_SRAM is not set
# CONFIG_SOC_TI is not set
# CONFIG_PM_DEVFREQ is not set
# CONFIG_EXTCON is not set
# CONFIG_MEMORY is not set
# CONFIG_IIO is not set
# CONFIG_NTB is not set
# CONFIG_VME_BUS is not set
# CONFIG_PWM is not set
# CONFIG_IPACK_BUS is not set
# CONFIG_RESET_CONTROLLER is not set
# CONFIG_FMC is not set

#
# PHY Subsystem
#
# CONFIG_GENERIC_PHY is not set
# CONFIG_PHY_PXA_28NM_HSIC is not set
# CONFIG_PHY_PXA_28NM_USB2 is not set
# CONFIG_BCM_KONA_USB2_PHY is not set
# CONFIG_POWERCAP is not set
# CONFIG_MCB is not set

#
# Performance monitor support
#
CONFIG_RAS=y
# CONFIG_AMD_MCE_INJ is not set
# CONFIG_THUNDERBOLT is not set

#
# Android
#
# CONFIG_ANDROID is not set
# CONFIG_LIBNVDIMM is not set
# CONFIG_NVMEM is not set

#
# Firmware Drivers
#
# CONFIG_EDD is not set
CONFIG_FIRMWARE_MEMMAP=y
# CONFIG_DELL_RBU is not set
# CONFIG_DCDBAS is not set
CONFIG_DMIID=y
# CONFIG_DMI_SYSFS is not set
CONFIG_DMI_SCAN_MACHINE_NON_EFI_FALLBACK=y
# CONFIG_ISCSI_IBFT_FIND is not set
# CONFIG_GOOGLE_FIRMWARE is not set

#
# EFI (Extensible Firmware Interface) Support
#
CONFIG_EFI_VARS=y
CONFIG_EFI_ESRT=y
CONFIG_EFI_RUNTIME_MAP=y
CONFIG_EFI_RUNTIME_WRAPPERS=y

#
# File systems
#
CONFIG_DCACHE_WORD_ACCESS=y
# CONFIG_EXT2_FS is not set
# CONFIG_EXT3_FS is not set
CONFIG_EXT4_FS=y
CONFIG_EXT4_USE_FOR_EXT2=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_EXT4_FS_SECURITY=y
# CONFIG_EXT4_ENCRYPTION is not set
# CONFIG_EXT4_DEBUG is not set
CONFIG_JBD2=y
# CONFIG_JBD2_DEBUG is not set
CONFIG_FS_MBCACHE=y
# CONFIG_REISERFS_FS is not set
# CONFIG_JFS_FS is not set
# CONFIG_XFS_FS is not set
# CONFIG_GFS2_FS is not set
# CONFIG_BTRFS_FS is not set
# CONFIG_NILFS2_FS is not set
# CONFIG_F2FS_FS is not set
# CONFIG_FS_DAX is not set
CONFIG_FS_POSIX_ACL=y
CONFIG_EXPORTFS=y
CONFIG_FILE_LOCKING=y
CONFIG_FSNOTIFY=y
CONFIG_DNOTIFY=y
CONFIG_INOTIFY_USER=y
# CONFIG_FANOTIFY is not set
CONFIG_QUOTA=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
# CONFIG_PRINT_QUOTA_WARNING is not set
# CONFIG_QUOTA_DEBUG is not set
CONFIG_QUOTA_TREE=y
# CONFIG_QFMT_V1 is not set
CONFIG_QFMT_V2=y
CONFIG_QUOTACTL=y
CONFIG_QUOTACTL_COMPAT=y
CONFIG_AUTOFS4_FS=y
# CONFIG_FUSE_FS is not set
# CONFIG_OVERLAY_FS is not set

#
# Caches
#
# CONFIG_FSCACHE is not set

#
# CD-ROM/DVD Filesystems
#
CONFIG_ISO9660_FS=y
CONFIG_JOLIET=y
CONFIG_ZISOFS=y
# CONFIG_UDF_FS is not set

#
# DOS/FAT/NT Filesystems
#
CONFIG_FAT_FS=y
CONFIG_MSDOS_FS=y
CONFIG_VFAT_FS=y
CONFIG_FAT_DEFAULT_CODEPAGE=437
CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
# CONFIG_NTFS_FS is not set

#
# Pseudo filesystems
#
CONFIG_PROC_FS=y
CONFIG_PROC_KCORE=y
CONFIG_PROC_VMCORE=y
CONFIG_PROC_SYSCTL=y
CONFIG_PROC_PAGE_MONITOR=y
CONFIG_PROC_CHILDREN=y
CONFIG_KERNFS=y
CONFIG_SYSFS=y
CONFIG_TMPFS=y
CONFIG_TMPFS_POSIX_ACL=y
CONFIG_TMPFS_XATTR=y
CONFIG_HUGETLBFS=y
CONFIG_HUGETLB_PAGE=y
# CONFIG_CONFIGFS_FS is not set
CONFIG_EFIVAR_FS=m
CONFIG_MISC_FILESYSTEMS=y
# CONFIG_ORANGEFS_FS is not set
# CONFIG_ADFS_FS is not set
# CONFIG_AFFS_FS is not set
# CONFIG_ECRYPT_FS is not set
# CONFIG_HFS_FS is not set
# CONFIG_HFSPLUS_FS is not set
# CONFIG_BEFS_FS is not set
# CONFIG_BFS_FS is not set
# CONFIG_EFS_FS is not set
# CONFIG_LOGFS is not set
# CONFIG_CRAMFS is not set
# CONFIG_SQUASHFS is not set
# CONFIG_VXFS_FS is not set
# CONFIG_MINIX_FS is not set
# CONFIG_OMFS_FS is not set
# CONFIG_HPFS_FS is not set
# CONFIG_QNX4FS_FS is not set
# CONFIG_QNX6FS_FS is not set
# CONFIG_ROMFS_FS is not set
# CONFIG_PSTORE is not set
# CONFIG_SYSV_FS is not set
# CONFIG_UFS_FS is not set
CONFIG_NETWORK_FILESYSTEMS=y
CONFIG_NFS_FS=y
CONFIG_NFS_V2=y
CONFIG_NFS_V3=y
CONFIG_NFS_V3_ACL=y
CONFIG_NFS_V4=y
# CONFIG_NFS_SWAP is not set
# CONFIG_NFS_V4_1 is not set
CONFIG_ROOT_NFS=y
# CONFIG_NFS_USE_LEGACY_DNS is not set
CONFIG_NFS_USE_KERNEL_DNS=y
# CONFIG_NFSD is not set
CONFIG_GRACE_PERIOD=y
CONFIG_LOCKD=y
CONFIG_LOCKD_V4=y
CONFIG_NFS_ACL_SUPPORT=y
CONFIG_NFS_COMMON=y
CONFIG_SUNRPC=y
CONFIG_SUNRPC_GSS=y
# CONFIG_SUNRPC_DEBUG is not set
# CONFIG_CEPH_FS is not set
# CONFIG_CIFS is not set
# CONFIG_NCP_FS is not set
# CONFIG_CODA_FS is not set
# CONFIG_AFS_FS is not set
CONFIG_9P_FS=y
# CONFIG_9P_FS_POSIX_ACL is not set
# CONFIG_9P_FS_SECURITY is not set
CONFIG_NLS=y
CONFIG_NLS_DEFAULT="utf8"
CONFIG_NLS_CODEPAGE_437=y
# CONFIG_NLS_CODEPAGE_737 is not set
# CONFIG_NLS_CODEPAGE_775 is not set
# CONFIG_NLS_CODEPAGE_850 is not set
# CONFIG_NLS_CODEPAGE_852 is not set
# CONFIG_NLS_CODEPAGE_855 is not set
# CONFIG_NLS_CODEPAGE_857 is not set
# CONFIG_NLS_CODEPAGE_860 is not set
# CONFIG_NLS_CODEPAGE_861 is not set
# CONFIG_NLS_CODEPAGE_862 is not set
# CONFIG_NLS_CODEPAGE_863 is not set
# CONFIG_NLS_CODEPAGE_864 is not set
# CONFIG_NLS_CODEPAGE_865 is not set
# CONFIG_NLS_CODEPAGE_866 is not set
# CONFIG_NLS_CODEPAGE_869 is not set
# CONFIG_NLS_CODEPAGE_936 is not set
# CONFIG_NLS_CODEPAGE_950 is not set
# CONFIG_NLS_CODEPAGE_932 is not set
# CONFIG_NLS_CODEPAGE_949 is not set
# CONFIG_NLS_CODEPAGE_874 is not set
# CONFIG_NLS_ISO8859_8 is not set
# CONFIG_NLS_CODEPAGE_1250 is not set
# CONFIG_NLS_CODEPAGE_1251 is not set
CONFIG_NLS_ASCII=y
CONFIG_NLS_ISO8859_1=y
# CONFIG_NLS_ISO8859_2 is not set
# CONFIG_NLS_ISO8859_3 is not set
# CONFIG_NLS_ISO8859_4 is not set
# CONFIG_NLS_ISO8859_5 is not set
# CONFIG_NLS_ISO8859_6 is not set
# CONFIG_NLS_ISO8859_7 is not set
# CONFIG_NLS_ISO8859_9 is not set
# CONFIG_NLS_ISO8859_13 is not set
# CONFIG_NLS_ISO8859_14 is not set
# CONFIG_NLS_ISO8859_15 is not set
# CONFIG_NLS_KOI8_R is not set
# CONFIG_NLS_KOI8_U is not set
# CONFIG_NLS_MAC_ROMAN is not set
# CONFIG_NLS_MAC_CELTIC is not set
# CONFIG_NLS_MAC_CENTEURO is not set
# CONFIG_NLS_MAC_CROATIAN is not set
# CONFIG_NLS_MAC_CYRILLIC is not set
# CONFIG_NLS_MAC_GAELIC is not set
# CONFIG_NLS_MAC_GREEK is not set
# CONFIG_NLS_MAC_ICELAND is not set
# CONFIG_NLS_MAC_INUIT is not set
# CONFIG_NLS_MAC_ROMANIAN is not set
# CONFIG_NLS_MAC_TURKISH is not set
CONFIG_NLS_UTF8=y

#
# Kernel hacking
#
CONFIG_TRACE_IRQFLAGS_SUPPORT=y

#
# printk and dmesg options
#
CONFIG_PRINTK_TIME=y
CONFIG_MESSAGE_LOGLEVEL_DEFAULT=4
# CONFIG_BOOT_PRINTK_DELAY is not set
# CONFIG_DYNAMIC_DEBUG is not set

#
# Compile-time checks and compiler options
#
# CONFIG_DEBUG_INFO is not set
# CONFIG_ENABLE_WARN_DEPRECATED is not set
CONFIG_ENABLE_MUST_CHECK=y
CONFIG_FRAME_WARN=2048
# CONFIG_STRIP_ASM_SYMS is not set
# CONFIG_READABLE_ASM is not set
# CONFIG_UNUSED_SYMBOLS is not set
# CONFIG_PAGE_OWNER is not set
CONFIG_DEBUG_FS=y
# CONFIG_HEADERS_CHECK is not set
# CONFIG_DEBUG_SECTION_MISMATCH is not set
CONFIG_ARCH_WANT_FRAME_POINTERS=y
CONFIG_FRAME_POINTER=y
# CONFIG_DEBUG_FORCE_WEAK_PER_CPU is not set
CONFIG_MAGIC_SYSRQ=y
CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE=0x1
CONFIG_DEBUG_KERNEL=y

#
# Memory Debugging
#
# CONFIG_PAGE_EXTENSION is not set
# CONFIG_DEBUG_PAGEALLOC is not set
# CONFIG_DEBUG_OBJECTS is not set
# CONFIG_SLUB_DEBUG_ON is not set
# CONFIG_SLUB_STATS is not set
CONFIG_HAVE_DEBUG_KMEMLEAK=y
# CONFIG_DEBUG_KMEMLEAK is not set
CONFIG_DEBUG_STACK_USAGE=y
CONFIG_DEBUG_VM=y
# CONFIG_DEBUG_VM_VMACACHE is not set
# CONFIG_DEBUG_VM_RB is not set
# CONFIG_DEBUG_VIRTUAL is not set
CONFIG_DEBUG_MEMORY_INIT=y
# CONFIG_DEBUG_PER_CPU_MAPS is not set
CONFIG_HAVE_DEBUG_STACKOVERFLOW=y
CONFIG_DEBUG_STACKOVERFLOW=y
CONFIG_HAVE_ARCH_KMEMCHECK=y
# CONFIG_KMEMCHECK is not set
CONFIG_HAVE_ARCH_KASAN=y
# CONFIG_KASAN is not set
# CONFIG_DEBUG_SHIRQ is not set

#
# Debug Lockups and Hangs
#
# CONFIG_LOCKUP_DETECTOR is not set
# CONFIG_DETECT_HUNG_TASK is not set
# CONFIG_PANIC_ON_OOPS is not set
CONFIG_PANIC_ON_OOPS_VALUE=0
CONFIG_PANIC_TIMEOUT=0
# CONFIG_SCHED_DEBUG is not set
CONFIG_SCHED_INFO=y
CONFIG_SCHEDSTATS=y
# CONFIG_SCHED_STACK_END_CHECK is not set
# CONFIG_DEBUG_TIMEKEEPING is not set
CONFIG_TIMER_STATS=y

#
# Lock Debugging (spinlocks, mutexes, etc...)
#
# CONFIG_DEBUG_RT_MUTEXES is not set
# CONFIG_DEBUG_SPINLOCK is not set
# CONFIG_DEBUG_MUTEXES is not set
# CONFIG_DEBUG_WW_MUTEX_SLOWPATH is not set
# CONFIG_DEBUG_LOCK_ALLOC is not set
# CONFIG_PROVE_LOCKING is not set
# CONFIG_LOCK_STAT is not set
# CONFIG_DEBUG_ATOMIC_SLEEP is not set
# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
# CONFIG_LOCK_TORTURE_TEST is not set
CONFIG_STACKTRACE=y
# CONFIG_DEBUG_KOBJECT is not set
CONFIG_DEBUG_BUGVERBOSE=y
# CONFIG_DEBUG_LIST is not set
# CONFIG_DEBUG_PI_LIST is not set
# CONFIG_DEBUG_SG is not set
# CONFIG_DEBUG_NOTIFIERS is not set
# CONFIG_DEBUG_CREDENTIALS is not set

#
# RCU Debugging
#
# CONFIG_PROVE_RCU is not set
# CONFIG_SPARSE_RCU_POINTER is not set
# CONFIG_TORTURE_TEST is not set
# CONFIG_RCU_TORTURE_TEST is not set
CONFIG_RCU_CPU_STALL_TIMEOUT=21
# CONFIG_RCU_TRACE is not set
# CONFIG_RCU_EQS_DEBUG is not set
# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set
# CONFIG_NOTIFIER_ERROR_INJECTION is not set
# CONFIG_FAULT_INJECTION is not set
# CONFIG_LATENCYTOP is not set
CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS=y
# CONFIG_DEBUG_STRICT_USER_COPY_CHECKS is not set
CONFIG_USER_STACKTRACE_SUPPORT=y
CONFIG_NOP_TRACER=y
CONFIG_HAVE_FUNCTION_TRACER=y
CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y
CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST=y
CONFIG_HAVE_DYNAMIC_FTRACE=y
CONFIG_HAVE_DYNAMIC_FTRACE_WITH_REGS=y
CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
CONFIG_HAVE_SYSCALL_TRACEPOINTS=y
CONFIG_HAVE_FENTRY=y
CONFIG_HAVE_C_RECORDMCOUNT=y
CONFIG_TRACE_CLOCK=y
CONFIG_RING_BUFFER=y
CONFIG_EVENT_TRACING=y
CONFIG_CONTEXT_SWITCH_TRACER=y
CONFIG_TRACING=y
CONFIG_GENERIC_TRACER=y
CONFIG_TRACING_SUPPORT=y
CONFIG_FTRACE=y
# CONFIG_FUNCTION_TRACER is not set
# CONFIG_IRQSOFF_TRACER is not set
# CONFIG_SCHED_TRACER is not set
# CONFIG_FTRACE_SYSCALLS is not set
# CONFIG_TRACER_SNAPSHOT is not set
CONFIG_BRANCH_PROFILE_NONE=y
# CONFIG_PROFILE_ANNOTATED_BRANCHES is not set
# CONFIG_PROFILE_ALL_BRANCHES is not set
# CONFIG_STACK_TRACER is not set
CONFIG_BLK_DEV_IO_TRACE=y
CONFIG_KPROBE_EVENT=y
# CONFIG_UPROBE_EVENT is not set
CONFIG_PROBE_EVENTS=y
# CONFIG_FTRACE_STARTUP_TEST is not set
# CONFIG_MMIOTRACE is not set
# CONFIG_TRACEPOINT_BENCHMARK is not set
# CONFIG_RING_BUFFER_BENCHMARK is not set
# CONFIG_RING_BUFFER_STARTUP_TEST is not set
# CONFIG_TRACE_ENUM_MAP_FILE is not set

#
# Runtime Testing
#
# CONFIG_LKDTM is not set
# CONFIG_TEST_LIST_SORT is not set
# CONFIG_KPROBES_SANITY_TEST is not set
# CONFIG_BACKTRACE_SELF_TEST is not set
# CONFIG_RBTREE_TEST is not set
# CONFIG_INTERVAL_TREE_TEST is not set
# CONFIG_PERCPU_TEST is not set
# CONFIG_ATOMIC64_SELFTEST is not set
# CONFIG_TEST_HEXDUMP is not set
# CONFIG_TEST_STRING_HELPERS is not set
# CONFIG_TEST_KSTRTOX is not set
# CONFIG_TEST_RHASHTABLE is not set
CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
# CONFIG_DMA_API_DEBUG is not set
# CONFIG_TEST_LKM is not set
# CONFIG_TEST_USER_COPY is not set
# CONFIG_TEST_BPF is not set
# CONFIG_TEST_FIRMWARE is not set
# CONFIG_TEST_UDELAY is not set
# CONFIG_MEMTEST is not set
# CONFIG_TEST_STATIC_KEYS is not set
# CONFIG_SAMPLES is not set
CONFIG_HAVE_ARCH_KGDB=y
# CONFIG_KGDB is not set
# CONFIG_STRICT_DEVMEM is not set
CONFIG_X86_VERBOSE_BOOTUP=y
CONFIG_EARLY_PRINTK=y
CONFIG_EARLY_PRINTK_DBGP=y
# CONFIG_EARLY_PRINTK_EFI is not set
# CONFIG_X86_PTDUMP is not set
CONFIG_DEBUG_RODATA=y
# CONFIG_DEBUG_RODATA_TEST is not set
# CONFIG_DEBUG_SET_MODULE_RONX is not set
# CONFIG_DEBUG_NX_TEST is not set
CONFIG_DOUBLEFAULT=y
# CONFIG_DEBUG_TLBFLUSH is not set
# CONFIG_IOMMU_STRESS is not set
CONFIG_HAVE_MMIOTRACE_SUPPORT=y
# CONFIG_X86_DECODER_SELFTEST is not set
CONFIG_IO_DELAY_TYPE_0X80=0
CONFIG_IO_DELAY_TYPE_0XED=1
CONFIG_IO_DELAY_TYPE_UDELAY=2
CONFIG_IO_DELAY_TYPE_NONE=3
CONFIG_IO_DELAY_0X80=y
# CONFIG_IO_DELAY_0XED is not set
# CONFIG_IO_DELAY_UDELAY is not set
# CONFIG_IO_DELAY_NONE is not set
CONFIG_DEFAULT_IO_DELAY_TYPE=0
CONFIG_DEBUG_BOOT_PARAMS=y
# CONFIG_CPA_DEBUG is not set
CONFIG_OPTIMIZE_INLINING=y
# CONFIG_DEBUG_ENTRY is not set
# CONFIG_DEBUG_NMI_SELFTEST is not set
# CONFIG_X86_DEBUG_STATIC_CPU_HAS is not set
CONFIG_X86_DEBUG_FPU=y
# CONFIG_PUNIT_ATOM_DEBUG is not set

#
# Security options
#
CONFIG_KEYS=y
# CONFIG_PERSISTENT_KEYRINGS is not set
# CONFIG_BIG_KEYS is not set
# CONFIG_ENCRYPTED_KEYS is not set
# CONFIG_SECURITY_DMESG_RESTRICT is not set
CONFIG_SECURITY=y
# CONFIG_SECURITYFS is not set
CONFIG_SECURITY_NETWORK=y
# CONFIG_SECURITY_NETWORK_XFRM is not set
# CONFIG_SECURITY_PATH is not set
# CONFIG_INTEL_TXT is not set
CONFIG_LSM_MMAP_MIN_ADDR=65536
CONFIG_SECURITY_SELINUX=y
CONFIG_SECURITY_SELINUX_BOOTPARAM=y
CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=1
CONFIG_SECURITY_SELINUX_DISABLE=y
CONFIG_SECURITY_SELINUX_DEVELOP=y
CONFIG_SECURITY_SELINUX_AVC_STATS=y
CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=0
# CONFIG_SECURITY_SELINUX_POLICYDB_VERSION_MAX is not set
# CONFIG_SECURITY_SMACK is not set
# CONFIG_SECURITY_TOMOYO is not set
# CONFIG_SECURITY_APPARMOR is not set
# CONFIG_SECURITY_YAMA is not set
CONFIG_INTEGRITY=y
# CONFIG_INTEGRITY_SIGNATURE is not set
CONFIG_INTEGRITY_AUDIT=y
# CONFIG_IMA is not set
# CONFIG_EVM is not set
CONFIG_DEFAULT_SECURITY_SELINUX=y
# CONFIG_DEFAULT_SECURITY_DAC is not set
CONFIG_DEFAULT_SECURITY="selinux"
CONFIG_CRYPTO=y

#
# Crypto core or helper
#
CONFIG_CRYPTO_ALGAPI=y
CONFIG_CRYPTO_ALGAPI2=y
CONFIG_CRYPTO_AEAD=y
CONFIG_CRYPTO_AEAD2=y
CONFIG_CRYPTO_BLKCIPHER=y
CONFIG_CRYPTO_BLKCIPHER2=y
CONFIG_CRYPTO_HASH=y
CONFIG_CRYPTO_HASH2=y
CONFIG_CRYPTO_RNG=y
CONFIG_CRYPTO_RNG2=y
CONFIG_CRYPTO_RNG_DEFAULT=y
CONFIG_CRYPTO_PCOMP2=y
CONFIG_CRYPTO_AKCIPHER2=y
# CONFIG_CRYPTO_RSA is not set
CONFIG_CRYPTO_MANAGER=y
CONFIG_CRYPTO_MANAGER2=y
# CONFIG_CRYPTO_USER is not set
CONFIG_CRYPTO_MANAGER_DISABLE_TESTS=y
CONFIG_CRYPTO_GF128MUL=y
CONFIG_CRYPTO_NULL=y
CONFIG_CRYPTO_NULL2=y
# CONFIG_CRYPTO_PCRYPT is not set
CONFIG_CRYPTO_WORKQUEUE=y
# CONFIG_CRYPTO_CRYPTD is not set
# CONFIG_CRYPTO_MCRYPTD is not set
CONFIG_CRYPTO_AUTHENC=y
# CONFIG_CRYPTO_TEST is not set

#
# Authenticated Encryption with Associated Data
#
CONFIG_CRYPTO_CCM=y
CONFIG_CRYPTO_GCM=y
# CONFIG_CRYPTO_CHACHA20POLY1305 is not set
CONFIG_CRYPTO_SEQIV=y
CONFIG_CRYPTO_ECHAINIV=m

#
# Block modes
#
CONFIG_CRYPTO_CBC=y
CONFIG_CRYPTO_CTR=y
# CONFIG_CRYPTO_CTS is not set
# CONFIG_CRYPTO_ECB is not set
# CONFIG_CRYPTO_LRW is not set
# CONFIG_CRYPTO_PCBC is not set
# CONFIG_CRYPTO_XTS is not set

#
# Hash modes
#
# CONFIG_CRYPTO_CMAC is not set
CONFIG_CRYPTO_HMAC=y
# CONFIG_CRYPTO_XCBC is not set
# CONFIG_CRYPTO_VMAC is not set

#
# Digest
#
CONFIG_CRYPTO_CRC32C=y
# CONFIG_CRYPTO_CRC32C_INTEL is not set
# CONFIG_CRYPTO_CRC32 is not set
# CONFIG_CRYPTO_CRC32_PCLMUL is not set
# CONFIG_CRYPTO_CRCT10DIF is not set
CONFIG_CRYPTO_GHASH=y
# CONFIG_CRYPTO_POLY1305 is not set
# CONFIG_CRYPTO_POLY1305_X86_64 is not set
# CONFIG_CRYPTO_MD4 is not set
CONFIG_CRYPTO_MD5=y
# CONFIG_CRYPTO_MICHAEL_MIC is not set
# CONFIG_CRYPTO_RMD128 is not set
# CONFIG_CRYPTO_RMD160 is not set
# CONFIG_CRYPTO_RMD256 is not set
# CONFIG_CRYPTO_RMD320 is not set
CONFIG_CRYPTO_SHA1=y
# CONFIG_CRYPTO_SHA1_SSSE3 is not set
# CONFIG_CRYPTO_SHA256_SSSE3 is not set
# CONFIG_CRYPTO_SHA512_SSSE3 is not set
# CONFIG_CRYPTO_SHA1_MB is not set
CONFIG_CRYPTO_SHA256=y
# CONFIG_CRYPTO_SHA512 is not set
# CONFIG_CRYPTO_TGR192 is not set
# CONFIG_CRYPTO_WP512 is not set
# CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL is not set

#
# Ciphers
#
CONFIG_CRYPTO_AES=y
# CONFIG_CRYPTO_AES_X86_64 is not set
# CONFIG_CRYPTO_AES_NI_INTEL is not set
# CONFIG_CRYPTO_ANUBIS is not set
CONFIG_CRYPTO_ARC4=y
# CONFIG_CRYPTO_BLOWFISH is not set
# CONFIG_CRYPTO_BLOWFISH_X86_64 is not set
# CONFIG_CRYPTO_CAMELLIA is not set
# CONFIG_CRYPTO_CAMELLIA_X86_64 is not set
# CONFIG_CRYPTO_CAMELLIA_AESNI_AVX_X86_64 is not set
# CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64 is not set
# CONFIG_CRYPTO_CAST5 is not set
# CONFIG_CRYPTO_CAST5_AVX_X86_64 is not set
# CONFIG_CRYPTO_CAST6 is not set
# CONFIG_CRYPTO_CAST6_AVX_X86_64 is not set
CONFIG_CRYPTO_DES=y
# CONFIG_CRYPTO_DES3_EDE_X86_64 is not set
# CONFIG_CRYPTO_FCRYPT is not set
# CONFIG_CRYPTO_KHAZAD is not set
# CONFIG_CRYPTO_SALSA20 is not set
# CONFIG_CRYPTO_SALSA20_X86_64 is not set
# CONFIG_CRYPTO_CHACHA20 is not set
# CONFIG_CRYPTO_CHACHA20_X86_64 is not set
# CONFIG_CRYPTO_SEED is not set
# CONFIG_CRYPTO_SERPENT is not set
# CONFIG_CRYPTO_SERPENT_SSE2_X86_64 is not set
# CONFIG_CRYPTO_SERPENT_AVX_X86_64 is not set
# CONFIG_CRYPTO_SERPENT_AVX2_X86_64 is not set
# CONFIG_CRYPTO_TEA is not set
# CONFIG_CRYPTO_TWOFISH is not set
# CONFIG_CRYPTO_TWOFISH_X86_64 is not set
# CONFIG_CRYPTO_TWOFISH_X86_64_3WAY is not set
# CONFIG_CRYPTO_TWOFISH_AVX_X86_64 is not set

#
# Compression
#
# CONFIG_CRYPTO_DEFLATE is not set
# CONFIG_CRYPTO_ZLIB is not set
# CONFIG_CRYPTO_LZO is not set
# CONFIG_CRYPTO_842 is not set
# CONFIG_CRYPTO_LZ4 is not set
# CONFIG_CRYPTO_LZ4HC is not set

#
# Random Number Generation
#
# CONFIG_CRYPTO_ANSI_CPRNG is not set
CONFIG_CRYPTO_DRBG_MENU=y
CONFIG_CRYPTO_DRBG_HMAC=y
# CONFIG_CRYPTO_DRBG_HASH is not set
# CONFIG_CRYPTO_DRBG_CTR is not set
CONFIG_CRYPTO_DRBG=y
CONFIG_CRYPTO_JITTERENTROPY=y
# CONFIG_CRYPTO_USER_API_HASH is not set
# CONFIG_CRYPTO_USER_API_SKCIPHER is not set
# CONFIG_CRYPTO_USER_API_RNG is not set
# CONFIG_CRYPTO_USER_API_AEAD is not set
CONFIG_CRYPTO_HW=y
# CONFIG_CRYPTO_DEV_PADLOCK is not set
# CONFIG_CRYPTO_DEV_CCP is not set
# CONFIG_CRYPTO_DEV_QAT_DH895xCC is not set
# CONFIG_CRYPTO_DEV_QAT_DH895xCCVF is not set
# CONFIG_ASYMMETRIC_KEY_TYPE is not set

#
# Certificates for signature checking
#
# CONFIG_SYSTEM_TRUSTED_KEYRING is not set
CONFIG_HAVE_KVM=y
CONFIG_KVM_COMPAT=y
CONFIG_VIRTUALIZATION=y
# CONFIG_KVM is not set
CONFIG_BINARY_PRINTF=y

#
# Library routines
#
CONFIG_BITREVERSE=y
# CONFIG_HAVE_ARCH_BITREVERSE is not set
CONFIG_RATIONAL=y
CONFIG_GENERIC_STRNCPY_FROM_USER=y
CONFIG_GENERIC_STRNLEN_USER=y
CONFIG_GENERIC_NET_UTILS=y
CONFIG_GENERIC_FIND_FIRST_BIT=y
CONFIG_GENERIC_PCI_IOMAP=y
CONFIG_GENERIC_IOMAP=y
CONFIG_GENERIC_IO=y
CONFIG_ARCH_USE_CMPXCHG_LOCKREF=y
CONFIG_ARCH_HAS_FAST_MULTIPLIER=y
# CONFIG_CRC_CCITT is not set
CONFIG_CRC16=y
# CONFIG_CRC_T10DIF is not set
# CONFIG_CRC_ITU_T is not set
CONFIG_CRC32=y
# CONFIG_CRC32_SELFTEST is not set
CONFIG_CRC32_SLICEBY8=y
# CONFIG_CRC32_SLICEBY4 is not set
# CONFIG_CRC32_SARWATE is not set
# CONFIG_CRC32_BIT is not set
# CONFIG_CRC7 is not set
# CONFIG_LIBCRC32C is not set
# CONFIG_CRC8 is not set
# CONFIG_CRC64_ECMA is not set
# CONFIG_AUDIT_ARCH_COMPAT_GENERIC is not set
# CONFIG_RANDOM32_SELFTEST is not set
CONFIG_ZLIB_INFLATE=y
CONFIG_LZO_COMPRESS=y
CONFIG_LZO_DECOMPRESS=y
CONFIG_LZ4_DECOMPRESS=y
CONFIG_XZ_DEC=y
CONFIG_XZ_DEC_X86=y
CONFIG_XZ_DEC_POWERPC=y
CONFIG_XZ_DEC_IA64=y
CONFIG_XZ_DEC_ARM=y
CONFIG_XZ_DEC_ARMTHUMB=y
CONFIG_XZ_DEC_SPARC=y
CONFIG_XZ_DEC_BCJ=y
# CONFIG_XZ_DEC_TEST is not set
CONFIG_DECOMPRESS_GZIP=y
CONFIG_DECOMPRESS_BZIP2=y
CONFIG_DECOMPRESS_LZMA=y
CONFIG_DECOMPRESS_XZ=y
CONFIG_DECOMPRESS_LZO=y
CONFIG_DECOMPRESS_LZ4=y
CONFIG_GENERIC_ALLOCATOR=y
CONFIG_INTERVAL_TREE=y
CONFIG_ASSOCIATIVE_ARRAY=y
CONFIG_HAS_IOMEM=y
CONFIG_HAS_IOPORT_MAP=y
CONFIG_HAS_DMA=y
CONFIG_CHECK_SIGNATURE=y
CONFIG_CPU_RMAP=y
CONFIG_DQL=y
CONFIG_GLOB=y
# CONFIG_GLOB_SELFTEST is not set
CONFIG_NLATTR=y
CONFIG_ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE=y
# CONFIG_CORDIC is not set
# CONFIG_DDR is not set
CONFIG_OID_REGISTRY=y
CONFIG_UCS2_STRING=y
CONFIG_FONT_SUPPORT=y
# CONFIG_FONTS is not set
CONFIG_FONT_8x8=y
CONFIG_FONT_8x16=y
# CONFIG_SG_SPLIT is not set
CONFIG_ARCH_HAS_SG_CHAIN=y
CONFIG_ARCH_HAS_PMEM_API=y
CONFIG_ARCH_HAS_MMIO_FLUSH=y

Re: [PATCH 03/16] page-flags: introduce page flags policies wrt compound pages

[Kirill A. Shutemov]

On Fri, Sep 25, 2015 at 03:29:17PM +0300, Konstantin Khlebnikov wrote:
> On 24.09.2015 17:50, Kirill A. Shutemov wrote:
> >This patch adds a third argument to macros which create function
> >definitions for page flags.  This argument defines how page-flags helpers
> >behave on compound functions.
> >
> >For now we define four policies:
> >
> >- PF_ANY: the helper function operates on the page it gets, regardless
> >   if it's non-compound, head or tail.
> >
> >- PF_HEAD: the helper function operates on the head page of the compound
> >   page if it gets tail page.
> >
> >- PF_NO_TAIL: only head and non-compond pages are acceptable for this
> >   helper function.
> >
> >- PF_NO_COMPOUND: only non-compound pages are acceptable for this helper
> >   function.
> >
> >For now we use policy PF_ANY for all helpers, which matches current
> >behaviour.
> >
> >We do not enforce the policy for TESTPAGEFLAG, because we have flags
> >checked for random pages all over the kernel.  Noticeable exception to
> >this is PageTransHuge() which triggers VM_BUG_ON() for tail page.
> >
> >Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> >---
> >  include/linux/page-flags.h | 154 ++++++++++++++++++++++++++-------------------
> >  1 file changed, 90 insertions(+), 64 deletions(-)
> >
> >diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
> >index 713d3f2c2468..1b3babe5ff69 100644
> >--- a/include/linux/page-flags.h
> >+++ b/include/linux/page-flags.h
> >@@ -154,49 +154,68 @@ static inline int PageCompound(struct page *page)
> >  	return test_bit(PG_head, &page->flags) || PageTail(page);
> >  }
> >
> >+/* Page flags policies wrt compound pages */
> >+#define PF_ANY(page, enforce)	page
> >+#define PF_HEAD(page, enforce)	compound_head(page)
> >+#define PF_NO_TAIL(page, enforce) ({					\
> >+		if (enforce)						\
> >+			VM_BUG_ON_PAGE(PageTail(page), page);		\
> >+		else							\
> >+			page = compound_head(page);			\
> >+		page;})
> >+#define PF_NO_COMPOUND(page, enforce) ({					\
> >+		if (enforce)						\
> >+			VM_BUG_ON_PAGE(PageCompound(page), page);	\
> 
> Linux next-20150925 crashes here (at least in lkvm)
> if CONFIG_DEFERRED_STRUCT_PAGE_INIT=y

Hm. I don't see the crash in qemu. Could you share your config?

> [    0.000000] Kernel command line: noapic noacpi pci=conf1 reboot=k panic=1
> i8042.direct=1 i8042.dumbkbd=1 i8042.nopnp=1 console=ttyS0
> earlyprintk=serial i8042.noaux=1  root=/dev/root rw
> rootflags=rw,trans=virtio,version=9p2000.L rootfstype=9p init=/virt/init
> ip=dhcp
> [    0.000000] PID hash table entries: 2048 (order: 2, 16384 bytes)
> [    0.000000] BUG: unable to handle kernel NULL pointer dereference at
> 000000000000000c
> [    0.000000] IP: [<ffffffff811aaafb>] dump_page_badflags+0x2b/0xe0
> [    0.000000] PGD 0
> [    0.000000] Oops: 0000 [#1] SMP
> [    0.000000] Modules linked in:
> [    0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted
> 4.3.0-rc2-next-20150925+ #2
> [    0.000000] task: ffffffff81c12580 ti: ffffffff81c00000 task.ti:
> ffffffff81c00000
> [    0.000000] RIP: 0010:[<ffffffff811aaafb>]  [<ffffffff811aaafb>]
> dump_page_badflags+0x2b/0xe0
> [    0.000000] RSP: 0000:ffffffff81c03ea8  EFLAGS: 00010002
> [    0.000000] RAX: 000000000000000c RBX: ffffea00006dfd40 RCX:
> 0000000000000100
> [    0.000000] RDX: 0000000000000001 RSI: ffffffff81a4aeb8 RDI:
> ffffea00006dfd40
> [    0.000000] RBP: ffffffff81c03ec0 R08: 0000000000000000 R09:
> 0000000000000000
> [    0.000000] R10: 0000000000000001 R11: 0000000000000000 R12:
> 0000000000000000
> [    0.000000] R13: 000000000001b7f7 R14: ffffffff81fe50c0 R15:
> ffffffff81c03fb0
> [    0.000000] FS:  0000000000000000(0000) GS:ffff88001a400000(0000)
> knlGS:0000000000000000
> [    0.000000] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [    0.000000] CR2: 000000000000000c CR3: 0000000001c0b000 CR4:
> 00000000000406b0
> [    0.000000] DR0: 0000000000000000 DR1: 0000000000000000 DR2:
> 0000000000000000
> [    0.000000] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7:
> 0000000000000400
> [    0.000000] Stack:
> [    0.000000]  000000000001b7f5 ffffea00006dfd40 000000000001b7f7
> ffffffff81c03ed0
> [    0.000000]  ffffffff811aabc0 ffffffff81c03ef8 ffffffff81785eda
> ffffffff81c03f10
> [    0.000000]  0000000000000040 ffffffff81fd99c0 ffffffff81c03f30
> ffffffff81f66600
> [    0.000000] Call Trace:
> [    0.000000]  [<ffffffff811aabc0>] dump_page+0x10/0x20
> [    0.000000]  [<ffffffff81785eda>] reserve_bootmem_region+0xd9/0xe2
> [    0.000000]  [<ffffffff81f66600>] free_all_bootmem+0x4b/0x11a
> [    0.000000]  [<ffffffff81f5428d>] mem_init+0x6a/0x9d
> [    0.000000]  [<ffffffff81f37d48>] start_kernel+0x214/0x46a
> [    0.000000]  [<ffffffff81f37120>] ? early_idt_handler_array+0x120/0x120
> [    0.000000]  [<ffffffff81f374d7>] x86_64_start_reservations+0x2a/0x2c
> [    0.000000]  [<ffffffff81f3760f>] x86_64_start_kernel+0x136/0x145
> [    0.000000] Code: e8 3b 7b 5e 00 55 48 89 e5 41 55 41 54 49 89 d4 53 48
> 8b 57 20 48 89 fb 4c 8b 4f 10 4c 8b 47 08 48 8d 42 ff 83 e2 01 48 0f 44 c7
> <48> 8b 00 a8 80 75 4b 8b 4f 18 8b 57 1c 49 89 f5 31 c0 48 89 fe
> [    0.000000] RIP  [<ffffffff811aaafb>] dump_page_badflags+0x2b/0xe0
> [    0.000000]  RSP <ffffffff81c03ea8>
> [    0.000000] CR2: 000000000000000c
> [    0.000000] ---[ end trace cb88537fdc8fa200 ]---

Could you try this:

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9bcfd70b1eb8..eff685f83879 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -929,8 +929,6 @@ static void init_reserved_page(unsigned long pfn)
 #else
 static inline void init_reserved_page(unsigned long pfn)
 {
-       /* Avoid false-positive PageTail() */
-       INIT_LIST_HEAD(&pfn_to_page(pfn)->lru);
 }
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 
@@ -950,6 +948,10 @@ void __meminit reserve_bootmem_region(unsigned long start, unsigned long end)
                        struct page *page = pfn_to_page(start_pfn);
 
                        init_reserved_page(start_pfn);
+
+                       /* Avoid false-positive PageTail() */
+                       INIT_LIST_HEAD(&pfn_to_page(pfn)->lru);
+
                        SetPageReserved(page);
                }
        }
-- 
 Kirill A. Shutemov

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH 03/16] page-flags: introduce page flags policies wrt compound pages

[Konstantin Khlebnikov]

On 24.09.2015 17:50, Kirill A. Shutemov wrote:
> This patch adds a third argument to macros which create function
> definitions for page flags.  This argument defines how page-flags helpers
> behave on compound functions.
>
> For now we define four policies:
>
> - PF_ANY: the helper function operates on the page it gets, regardless
>    if it's non-compound, head or tail.
>
> - PF_HEAD: the helper function operates on the head page of the compound
>    page if it gets tail page.
>
> - PF_NO_TAIL: only head and non-compond pages are acceptable for this
>    helper function.
>
> - PF_NO_COMPOUND: only non-compound pages are acceptable for this helper
>    function.
>
> For now we use policy PF_ANY for all helpers, which matches current
> behaviour.
>
> We do not enforce the policy for TESTPAGEFLAG, because we have flags
> checked for random pages all over the kernel.  Noticeable exception to
> this is PageTransHuge() which triggers VM_BUG_ON() for tail page.
>
> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> ---
>   include/linux/page-flags.h | 154 ++++++++++++++++++++++++++-------------------
>   1 file changed, 90 insertions(+), 64 deletions(-)
>
> diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
> index 713d3f2c2468..1b3babe5ff69 100644
> --- a/include/linux/page-flags.h
> +++ b/include/linux/page-flags.h
> @@ -154,49 +154,68 @@ static inline int PageCompound(struct page *page)
>   	return test_bit(PG_head, &page->flags) || PageTail(page);
>   }
>
> +/* Page flags policies wrt compound pages */
> +#define PF_ANY(page, enforce)	page
> +#define PF_HEAD(page, enforce)	compound_head(page)
> +#define PF_NO_TAIL(page, enforce) ({					\
> +		if (enforce)						\
> +			VM_BUG_ON_PAGE(PageTail(page), page);		\
> +		else							\
> +			page = compound_head(page);			\
> +		page;})
> +#define PF_NO_COMPOUND(page, enforce) ({					\
> +		if (enforce)						\
> +			VM_BUG_ON_PAGE(PageCompound(page), page);	\

Linux next-20150925 crashes here (at least in lkvm)
if CONFIG_DEFERRED_STRUCT_PAGE_INIT=y

[    0.000000] Policy zone: DMA32
[    0.000000] Kernel command line: noapic noacpi pci=conf1 reboot=k 
panic=1 i8042.direct=1 i8042.dumbkbd=1 i8042.nopnp=1 console=ttyS0 
earlyprintk=serial i8042.noaux=1  root=/dev/root rw 
rootflags=rw,trans=virtio,version=9p2000.L rootfstype=9p init=/virt/init 
  ip=dhcp
[    0.000000] PID hash table entries: 2048 (order: 2, 16384 bytes)
[    0.000000] BUG: unable to handle kernel NULL pointer dereference at 
000000000000000c
[    0.000000] IP: [<ffffffff811aaafb>] dump_page_badflags+0x2b/0xe0
[    0.000000] PGD 0
[    0.000000] Oops: 0000 [#1] SMP
[    0.000000] Modules linked in:
[    0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 
4.3.0-rc2-next-20150925+ #2
[    0.000000] task: ffffffff81c12580 ti: ffffffff81c00000 task.ti: 
ffffffff81c00000
[    0.000000] RIP: 0010:[<ffffffff811aaafb>]  [<ffffffff811aaafb>] 
dump_page_badflags+0x2b/0xe0
[    0.000000] RSP: 0000:ffffffff81c03ea8  EFLAGS: 00010002
[    0.000000] RAX: 000000000000000c RBX: ffffea00006dfd40 RCX: 
0000000000000100
[    0.000000] RDX: 0000000000000001 RSI: ffffffff81a4aeb8 RDI: 
ffffea00006dfd40
[    0.000000] RBP: ffffffff81c03ec0 R08: 0000000000000000 R09: 
0000000000000000
[    0.000000] R10: 0000000000000001 R11: 0000000000000000 R12: 
0000000000000000
[    0.000000] R13: 000000000001b7f7 R14: ffffffff81fe50c0 R15: 
ffffffff81c03fb0
[    0.000000] FS:  0000000000000000(0000) GS:ffff88001a400000(0000) 
knlGS:0000000000000000
[    0.000000] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    0.000000] CR2: 000000000000000c CR3: 0000000001c0b000 CR4: 
00000000000406b0
[    0.000000] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 
0000000000000000
[    0.000000] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 
0000000000000400
[    0.000000] Stack:
[    0.000000]  000000000001b7f5 ffffea00006dfd40 000000000001b7f7 
ffffffff81c03ed0
[    0.000000]  ffffffff811aabc0 ffffffff81c03ef8 ffffffff81785eda 
ffffffff81c03f10
[    0.000000]  0000000000000040 ffffffff81fd99c0 ffffffff81c03f30 
ffffffff81f66600
[    0.000000] Call Trace:
[    0.000000]  [<ffffffff811aabc0>] dump_page+0x10/0x20
[    0.000000]  [<ffffffff81785eda>] reserve_bootmem_region+0xd9/0xe2
[    0.000000]  [<ffffffff81f66600>] free_all_bootmem+0x4b/0x11a
[    0.000000]  [<ffffffff81f5428d>] mem_init+0x6a/0x9d
[    0.000000]  [<ffffffff81f37d48>] start_kernel+0x214/0x46a
[    0.000000]  [<ffffffff81f37120>] ? early_idt_handler_array+0x120/0x120
[    0.000000]  [<ffffffff81f374d7>] x86_64_start_reservations+0x2a/0x2c
[    0.000000]  [<ffffffff81f3760f>] x86_64_start_kernel+0x136/0x145
[    0.000000] Code: e8 3b 7b 5e 00 55 48 89 e5 41 55 41 54 49 89 d4 53 
48 8b 57 20 48 89 fb 4c 8b 4f 10 4c 8b 47 08 48 8d 42 ff 83 e2 01 48 0f 
44 c7 <48> 8b 00 a8 80 75 4b 8b 4f 18 8b 57 1c 49 89 f5 31 c0 48 89 fe
[    0.000000] RIP  [<ffffffff811aaafb>] dump_page_badflags+0x2b/0xe0
[    0.000000]  RSP <ffffffff81c03ea8>
[    0.000000] CR2: 000000000000000c
[    0.000000] ---[ end trace cb88537fdc8fa200 ]---


> +		page;})
> +

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH 03/16] page-flags: introduce page flags policies wrt compound pages

[Kirill A. Shutemov]

This patch adds a third argument to macros which create function
definitions for page flags.  This argument defines how page-flags helpers
behave on compound functions.

For now we define four policies:

- PF_ANY: the helper function operates on the page it gets, regardless
  if it's non-compound, head or tail.

- PF_HEAD: the helper function operates on the head page of the compound
  page if it gets tail page.

- PF_NO_TAIL: only head and non-compond pages are acceptable for this
  helper function.

- PF_NO_COMPOUND: only non-compound pages are acceptable for this helper
  function.

For now we use policy PF_ANY for all helpers, which matches current
behaviour.

We do not enforce the policy for TESTPAGEFLAG, because we have flags
checked for random pages all over the kernel.  Noticeable exception to
this is PageTransHuge() which triggers VM_BUG_ON() for tail page.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 include/linux/page-flags.h | 154 ++++++++++++++++++++++++++-------------------
 1 file changed, 90 insertions(+), 64 deletions(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 713d3f2c2468..1b3babe5ff69 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -154,49 +154,68 @@ static inline int PageCompound(struct page *page)
 	return test_bit(PG_head, &page->flags) || PageTail(page);
 }
 
+/* Page flags policies wrt compound pages */
+#define PF_ANY(page, enforce)	page
+#define PF_HEAD(page, enforce)	compound_head(page)
+#define PF_NO_TAIL(page, enforce) ({					\
+		if (enforce)						\
+			VM_BUG_ON_PAGE(PageTail(page), page);		\
+		else							\
+			page = compound_head(page);			\
+		page;})
+#define PF_NO_COMPOUND(page, enforce) ({					\
+		if (enforce)						\
+			VM_BUG_ON_PAGE(PageCompound(page), page);	\
+		page;})
+
 /*
  * Macros to create function definitions for page flags
  */
-#define TESTPAGEFLAG(uname, lname)					\
-static inline int Page##uname(const struct page *page)			\
-			{ return test_bit(PG_##lname, &page->flags); }
+#define TESTPAGEFLAG(uname, lname, policy)				\
+static inline int Page##uname(struct page *page)			\
+	{ return test_bit(PG_##lname, &policy(page, 0)->flags); }
 
-#define SETPAGEFLAG(uname, lname)					\
+#define SETPAGEFLAG(uname, lname, policy)				\
 static inline void SetPage##uname(struct page *page)			\
-			{ set_bit(PG_##lname, &page->flags); }
+	{ set_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define CLEARPAGEFLAG(uname, lname)					\
+#define CLEARPAGEFLAG(uname, lname, policy)				\
 static inline void ClearPage##uname(struct page *page)			\
-			{ clear_bit(PG_##lname, &page->flags); }
+	{ clear_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define __SETPAGEFLAG(uname, lname)					\
+#define __SETPAGEFLAG(uname, lname, policy)				\
 static inline void __SetPage##uname(struct page *page)			\
-			{ __set_bit(PG_##lname, &page->flags); }
+	{ __set_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define __CLEARPAGEFLAG(uname, lname)					\
+#define __CLEARPAGEFLAG(uname, lname, policy)				\
 static inline void __ClearPage##uname(struct page *page)		\
-			{ __clear_bit(PG_##lname, &page->flags); }
+	{ __clear_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define TESTSETFLAG(uname, lname)					\
+#define TESTSETFLAG(uname, lname, policy)				\
 static inline int TestSetPage##uname(struct page *page)			\
-		{ return test_and_set_bit(PG_##lname, &page->flags); }
+	{ return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define TESTCLEARFLAG(uname, lname)					\
+#define TESTCLEARFLAG(uname, lname, policy)				\
 static inline int TestClearPage##uname(struct page *page)		\
-		{ return test_and_clear_bit(PG_##lname, &page->flags); }
+	{ return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define __TESTCLEARFLAG(uname, lname)					\
+#define __TESTCLEARFLAG(uname, lname, policy)				\
 static inline int __TestClearPage##uname(struct page *page)		\
-		{ return __test_and_clear_bit(PG_##lname, &page->flags); }
+	{ return __test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); }
 
-#define PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname)		\
-	SETPAGEFLAG(uname, lname) CLEARPAGEFLAG(uname, lname)
+#define PAGEFLAG(uname, lname, policy)					\
+	TESTPAGEFLAG(uname, lname, policy)				\
+	SETPAGEFLAG(uname, lname, policy)				\
+	CLEARPAGEFLAG(uname, lname, policy)
 
-#define __PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname)		\
-	__SETPAGEFLAG(uname, lname)  __CLEARPAGEFLAG(uname, lname)
+#define __PAGEFLAG(uname, lname, policy)				\
+	TESTPAGEFLAG(uname, lname, policy)				\
+	__SETPAGEFLAG(uname, lname, policy)				\
+	__CLEARPAGEFLAG(uname, lname, policy)
 
-#define TESTSCFLAG(uname, lname)					\
-	TESTSETFLAG(uname, lname) TESTCLEARFLAG(uname, lname)
+#define TESTSCFLAG(uname, lname, policy)				\
+	TESTSETFLAG(uname, lname, policy)				\
+	TESTCLEARFLAG(uname, lname, policy)
 
 #define TESTPAGEFLAG_FALSE(uname)					\
 static inline int Page##uname(const struct page *page) { return 0; }
@@ -225,46 +244,48 @@ static inline int __TestClearPage##uname(struct page *page) { return 0; }
 #define TESTSCFLAG_FALSE(uname)						\
 	TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname)
 
-
-TESTPAGEFLAG(Locked, locked)
-PAGEFLAG(Error, error) TESTCLEARFLAG(Error, error)
-PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced)
-	__SETPAGEFLAG(Referenced, referenced)
-PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty)
-PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru)
-PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active)
-	TESTCLEARFLAG(Active, active)
-__PAGEFLAG(Slab, slab)
-PAGEFLAG(Checked, checked)		/* Used by some filesystems */
-PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned)	/* Xen */
-PAGEFLAG(SavePinned, savepinned);			/* Xen */
-PAGEFLAG(Foreign, foreign);				/* Xen */
-PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved)
-PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked)
-	__SETPAGEFLAG(SwapBacked, swapbacked)
-
-__PAGEFLAG(SlobFree, slob_free)
+TESTPAGEFLAG(Locked, locked, PF_ANY)
+PAGEFLAG(Error, error, PF_ANY) TESTCLEARFLAG(Error, error, PF_ANY)
+PAGEFLAG(Referenced, referenced, PF_ANY) TESTCLEARFLAG(Referenced, referenced, PF_ANY)
+	__SETPAGEFLAG(Referenced, referenced, PF_ANY)
+PAGEFLAG(Dirty, dirty, PF_ANY) TESTSCFLAG(Dirty, dirty, PF_ANY)
+	__CLEARPAGEFLAG(Dirty, dirty, PF_ANY)
+PAGEFLAG(LRU, lru, PF_ANY) __CLEARPAGEFLAG(LRU, lru, PF_ANY)
+PAGEFLAG(Active, active, PF_ANY) __CLEARPAGEFLAG(Active, active, PF_ANY)
+	TESTCLEARFLAG(Active, active, PF_ANY)
+__PAGEFLAG(Slab, slab, PF_ANY)
+PAGEFLAG(Checked, checked, PF_ANY)		/* Used by some filesystems */
+PAGEFLAG(Pinned, pinned, PF_ANY) TESTSCFLAG(Pinned, pinned, PF_ANY)	/* Xen */
+PAGEFLAG(SavePinned, savepinned, PF_ANY);			/* Xen */
+PAGEFLAG(Foreign, foreign, PF_ANY);				/* Xen */
+PAGEFLAG(Reserved, reserved, PF_ANY) __CLEARPAGEFLAG(Reserved, reserved, PF_ANY)
+PAGEFLAG(SwapBacked, swapbacked, PF_ANY)
+	__CLEARPAGEFLAG(SwapBacked, swapbacked, PF_ANY)
+	__SETPAGEFLAG(SwapBacked, swapbacked, PF_ANY)
+
+__PAGEFLAG(SlobFree, slob_free, PF_ANY)
 
 /*
  * Private page markings that may be used by the filesystem that owns the page
  * for its own purposes.
  * - PG_private and PG_private_2 cause releasepage() and co to be invoked
  */
-PAGEFLAG(Private, private) __SETPAGEFLAG(Private, private)
-	__CLEARPAGEFLAG(Private, private)
-PAGEFLAG(Private2, private_2) TESTSCFLAG(Private2, private_2)
-PAGEFLAG(OwnerPriv1, owner_priv_1) TESTCLEARFLAG(OwnerPriv1, owner_priv_1)
+PAGEFLAG(Private, private, PF_ANY) __SETPAGEFLAG(Private, private, PF_ANY)
+	__CLEARPAGEFLAG(Private, private, PF_ANY)
+PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY)
+PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY)
+	TESTCLEARFLAG(OwnerPriv1, owner_priv_1, PF_ANY)
 
 /*
  * Only test-and-set exist for PG_writeback.  The unconditional operators are
  * risky: they bypass page accounting.
  */
-TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback)
-PAGEFLAG(MappedToDisk, mappedtodisk)
+TESTPAGEFLAG(Writeback, writeback, PF_ANY) TESTSCFLAG(Writeback, writeback, PF_ANY)
+PAGEFLAG(MappedToDisk, mappedtodisk, PF_ANY)
 
 /* PG_readahead is only used for reads; PG_reclaim is only for writes */
-PAGEFLAG(Reclaim, reclaim) TESTCLEARFLAG(Reclaim, reclaim)
-PAGEFLAG(Readahead, reclaim) TESTCLEARFLAG(Readahead, reclaim)
+PAGEFLAG(Reclaim, reclaim, PF_ANY) TESTCLEARFLAG(Reclaim, reclaim, PF_ANY)
+PAGEFLAG(Readahead, reclaim, PF_ANY) TESTCLEARFLAG(Readahead, reclaim, PF_ANY)
 
 #ifdef CONFIG_HIGHMEM
 /*
@@ -277,31 +298,32 @@ PAGEFLAG_FALSE(HighMem)
 #endif
 
 #ifdef CONFIG_SWAP
-PAGEFLAG(SwapCache, swapcache)
+PAGEFLAG(SwapCache, swapcache, PF_ANY)
 #else
 PAGEFLAG_FALSE(SwapCache)
 #endif
 
-PAGEFLAG(Unevictable, unevictable) __CLEARPAGEFLAG(Unevictable, unevictable)
-	TESTCLEARFLAG(Unevictable, unevictable)
+PAGEFLAG(Unevictable, unevictable, PF_ANY)
+	__CLEARPAGEFLAG(Unevictable, unevictable, PF_ANY)
+	TESTCLEARFLAG(Unevictable, unevictable, PF_ANY)
 
 #ifdef CONFIG_MMU
-PAGEFLAG(Mlocked, mlocked) __CLEARPAGEFLAG(Mlocked, mlocked)
-	TESTSCFLAG(Mlocked, mlocked) __TESTCLEARFLAG(Mlocked, mlocked)
+PAGEFLAG(Mlocked, mlocked, PF_ANY) __CLEARPAGEFLAG(Mlocked, mlocked, PF_ANY)
+	TESTSCFLAG(Mlocked, mlocked, PF_ANY) __TESTCLEARFLAG(Mlocked, mlocked, PF_ANY)
 #else
 PAGEFLAG_FALSE(Mlocked) __CLEARPAGEFLAG_NOOP(Mlocked)
 	TESTSCFLAG_FALSE(Mlocked) __TESTCLEARFLAG_FALSE(Mlocked)
 #endif
 
 #ifdef CONFIG_ARCH_USES_PG_UNCACHED
-PAGEFLAG(Uncached, uncached)
+PAGEFLAG(Uncached, uncached, PF_ANY)
 #else
 PAGEFLAG_FALSE(Uncached)
 #endif
 
 #ifdef CONFIG_MEMORY_FAILURE
-PAGEFLAG(HWPoison, hwpoison)
-TESTSCFLAG(HWPoison, hwpoison)
+PAGEFLAG(HWPoison, hwpoison, PF_ANY)
+TESTSCFLAG(HWPoison, hwpoison, PF_ANY)
 #define __PG_HWPOISON (1UL << PG_hwpoison)
 #else
 PAGEFLAG_FALSE(HWPoison)
@@ -309,10 +331,10 @@ PAGEFLAG_FALSE(HWPoison)
 #endif
 
 #if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
-TESTPAGEFLAG(Young, young)
-SETPAGEFLAG(Young, young)
-TESTCLEARFLAG(Young, young)
-PAGEFLAG(Idle, idle)
+TESTPAGEFLAG(Young, young, PF_ANY)
+SETPAGEFLAG(Young, young, PF_ANY)
+TESTCLEARFLAG(Young, young, PF_ANY)
+PAGEFLAG(Idle, idle, PF_ANY)
 #endif
 
 /*
@@ -393,7 +415,7 @@ static inline void SetPageUptodate(struct page *page)
 	set_bit(PG_uptodate, &(page)->flags);
 }
 
-CLEARPAGEFLAG(Uptodate, uptodate)
+CLEARPAGEFLAG(Uptodate, uptodate, PF_ANY)
 
 int test_clear_page_writeback(struct page *page);
 int __test_set_page_writeback(struct page *page, bool keep_write);
@@ -413,7 +435,7 @@ static inline void set_page_writeback_keepwrite(struct page *page)
 	test_set_page_writeback_keepwrite(page);
 }
 
-__PAGEFLAG(Head, head) CLEARPAGEFLAG(Head, head)
+__PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY)
 
 static inline void set_compound_head(struct page *page, struct page *head)
 {
@@ -615,6 +637,10 @@ static inline int page_has_private(struct page *page)
 	return !!(page->flags & PAGE_FLAGS_PRIVATE);
 }
 
+#undef PF_ANY
+#undef PF_HEAD
+#undef PF_NO_TAIL
+#undef PF_NO_COMPOUND
 #endif /* !__GENERATING_BOUNDS_H */
 
 #endif	/* PAGE_FLAGS_H */
-- 
2.5.1

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>