[PATCH 0/8] Support for transparent PUD pages

[PATCH 0/8] Support for transparent PUD pages

[Matthew Wilcox]

From: Matthew Wilcox <willy@linux.intel.com>

We have customer demand to use 1GB pages to map DAX files.  Unlike the 2MB
page support, the Linux MM does not currently support PUD pages, so I have
attempted to add support for the necessary pieces for DAX huge PUD pages.

Filesystem support is a bit sticky.  I have not been able to persuade ext4
to give me more than 16MB of contiguous space, although it is aligned.
XFS will give me 80MB short of 1GB, but it's not aligned.  I'm in no
hurry to get patches 7 & 8 merged until the block allocation problem is
solved in those filesystems.

This patch set is against something approximately current -mm.  At this
point, I would be most grateful for MM developers to give feedback on
the first three patches.  Review from X86 maintainers on patch 4 would
also be welcome.  I'd like to thank Ross Zwisler for his helpful review
during development.

I've done some light testing using a program to mmap a block device
with DAX enabled, calling mincore() and examining /proc/smaps and
/proc/pagemap.

Matthew Wilcox (8):
  mm: Add optional support for PUD-sized transparent hugepages
  mincore: Add support for PUDs
  procfs: Add support for PUDs to smaps, clear_refs and pagemap
  x86: Add support for PUD-sized transparent hugepages
  dax: Support for transparent PUD pages
  block_dev: Support PUD DAX mappings
  xfs: Support for transparent PUD pages
  ext4: Transparent support for PUD-sized transparent huge pages

 arch/Kconfig                          |   3 +
 arch/x86/Kconfig                      |   1 +
 arch/x86/include/asm/paravirt.h       |  11 ++
 arch/x86/include/asm/paravirt_types.h |   2 +
 arch/x86/include/asm/pgtable.h        |  95 ++++++++++++++
 arch/x86/include/asm/pgtable_64.h     |  13 ++
 arch/x86/kernel/paravirt.c            |   1 +
 arch/x86/mm/pgtable.c                 |  31 +++++
 fs/block_dev.c                        |   7 +
 fs/dax.c                              | 239 +++++++++++++++++++++++++++++++---
 fs/ext4/file.c                        |  37 ++++++
 fs/proc/task_mmu.c                    | 109 ++++++++++++++++
 fs/xfs/xfs_file.c                     |  33 +++++
 fs/xfs/xfs_trace.h                    |   1 +
 include/asm-generic/pgtable.h         |  62 ++++++++-
 include/asm-generic/tlb.h             |  14 ++
 include/linux/dax.h                   |  21 +++
 include/linux/huge_mm.h               |  52 +++++++-
 include/linux/mm.h                    |  30 +++++
 include/linux/mmu_notifier.h          |  13 ++
 mm/huge_memory.c                      | 151 +++++++++++++++++++++
 mm/memory.c                           |  67 ++++++++++
 mm/mincore.c                          |  13 ++
 mm/pagewalk.c                         |  19 ++-
 mm/pgtable-generic.c                  |  14 ++
 25 files changed, 1016 insertions(+), 23 deletions(-)

-- 
2.6.2

[PATCH 1/8] mm: Add optional support for PUD-sized transparent hugepages

[Matthew Wilcox]

From: Matthew Wilcox <willy@linux.intel.com>

The current transparent hugepage code only supports PMDs.  This patch
adds support for transparent use of PUDs with DAX.  It does not include
support for anonymous pages.

Most of this patch simply parallels the work that was done for huge PMDs.
The only major difference is how the new ->pud_entry method in mm_walk
works.  The ->pmd_entry method replaces the ->pte_entry method, whereas
the ->pud_entry method works along with either ->pmd_entry or ->pte_entry.
The pagewalk code takes care of locking the PUD before calling ->pud_walk,
so handlers do not need to worry whether the PUD is stable.

Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
 arch/Kconfig                  |   3 +
 include/asm-generic/pgtable.h |  62 +++++++++++++++--
 include/asm-generic/tlb.h     |  14 ++++
 include/linux/huge_mm.h       |  52 ++++++++++++++-
 include/linux/mm.h            |  30 +++++++++
 include/linux/mmu_notifier.h  |  13 ++++
 mm/huge_memory.c              | 151 ++++++++++++++++++++++++++++++++++++++++++
 mm/memory.c                   |  67 +++++++++++++++++++
 mm/pagewalk.c                 |  19 +++++-
 mm/pgtable-generic.c          |  14 ++++
 10 files changed, 419 insertions(+), 6 deletions(-)

diff --git a/arch/Kconfig b/arch/Kconfig
index dc5e0f2..3864ad8 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -462,6 +462,9 @@ config HAVE_IRQ_TIME_ACCOUNTING
 config HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	bool
 
+config HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+	bool
+
 config HAVE_ARCH_HUGE_VMAP
 	bool
 
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 5459a66..9ea433a 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -36,6 +36,9 @@ extern int ptep_set_access_flags(struct vm_area_struct *vma,
 extern int pmdp_set_access_flags(struct vm_area_struct *vma,
 				 unsigned long address, pmd_t *pmdp,
 				 pmd_t entry, int dirty);
+extern int pudp_set_access_flags(struct vm_area_struct *vma,
+				 unsigned long address, pud_t *pudp,
+				 pud_t entry, int dirty);
 #else
 static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
 					unsigned long address, pmd_t *pmdp,
@@ -44,6 +47,13 @@ static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
 	BUILD_BUG();
 	return 0;
 }
+static inline int pudp_set_access_flags(struct vm_area_struct *vma,
+					unsigned long address, pud_t *pudp,
+					pud_t entry, int dirty)
+{
+	BUILD_BUG();
+	return 0;
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
 
@@ -121,8 +131,8 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 }
 #endif
 
-#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
 static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 					    unsigned long address,
 					    pmd_t *pmdp)
@@ -131,20 +141,39 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 	pmd_clear(pmdp);
 	return pmd;
 }
+#endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */
+#ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR
+static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm,
+					    unsigned long address,
+					    pud_t *pudp)
+{
+	pud_t pud = *pudp;
+	pud_clear(pudp);
+	return pud;
+}
+#endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-#endif
 
-#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL
 static inline pmd_t pmdp_huge_get_and_clear_full(struct mm_struct *mm,
 					    unsigned long address, pmd_t *pmdp,
 					    int full)
 {
 	return pmdp_huge_get_and_clear(mm, address, pmdp);
 }
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
 
+#ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR_FULL
+static inline pud_t pudp_huge_get_and_clear_full(struct mm_struct *mm,
+					    unsigned long address, pud_t *pudp,
+					    int full)
+{
+	return pudp_huge_get_and_clear(mm, address, pudp);
+}
+#endif
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
 static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
 					    unsigned long address, pte_t *ptep,
@@ -181,6 +210,9 @@ extern pte_t ptep_clear_flush(struct vm_area_struct *vma,
 extern pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma,
 			      unsigned long address,
 			      pmd_t *pmdp);
+extern pud_t pudp_huge_clear_flush(struct vm_area_struct *vma,
+			      unsigned long address,
+			      pud_t *pudp);
 #endif
 
 #ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT
@@ -265,12 +297,23 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
 {
 	return pmd_val(pmd_a) == pmd_val(pmd_b);
 }
+
+static inline int pud_same(pud_t pud_a, pud_t pud_b)
+{
+	return pud_val(pud_a) == pud_val(pud_b);
+}
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
 static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
 {
 	BUILD_BUG();
 	return 0;
 }
+
+static inline int pud_same(pud_t pud_a, pud_t pud_b)
+{
+	BUILD_BUG();
+	return 0;
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
 
@@ -629,6 +672,17 @@ static inline int pmd_write(pmd_t pmd)
 #endif /* __HAVE_ARCH_PMD_WRITE */
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+#ifndef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+static inline int pud_trans_huge(pud_t pud)
+{
+	return 0;
+}
+static inline int pud_devmap(pud_t pud)
+{
+	return 0;
+}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
 #ifndef pmd_read_atomic
 static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
 {
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 9dbb739..9d310c8 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -196,6 +196,20 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 		__tlb_remove_pmd_tlb_entry(tlb, pmdp, address);	\
 	} while (0)
 
+/**
+ * tlb_remove_pud_tlb_entry - remember a pud mapping for later tlb invalidation
+ * This is a nop so far, because only x86 needs it.
+ */
+#ifndef __tlb_remove_pud_tlb_entry
+#define __tlb_remove_pud_tlb_entry(tlb, pudp, address) do {} while (0)
+#endif
+
+#define tlb_remove_pud_tlb_entry(tlb, pudp, address)		\
+	do {							\
+		__tlb_adjust_range(tlb, address);		\
+		__tlb_remove_pud_tlb_entry(tlb, pudp, address);	\
+	} while (0)
+
 #define pte_free_tlb(tlb, ptep, address)			\
 	do {							\
 		__tlb_adjust_range(tlb, address);		\
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index bc141a6..d58cd19 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -12,6 +12,20 @@ extern void huge_pmd_set_accessed(struct mm_struct *mm,
 				  struct vm_area_struct *vma,
 				  unsigned long address, pmd_t *pmd,
 				  pmd_t orig_pmd, int dirty);
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+extern void huge_pud_set_accessed(struct mm_struct *mm,
+				  struct vm_area_struct *vma,
+				  unsigned long address, pud_t *pud,
+				  pud_t orig_pud, int dirty);
+#else
+static inline void huge_pud_set_accessed(struct mm_struct *mm,
+				  struct vm_area_struct *vma,
+				  unsigned long address, pud_t *pud,
+				  pud_t orig_pud, int dirty)
+{
+}
+#endif
+
 extern int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			       unsigned long address, pmd_t *pmd,
 			       pmd_t orig_pmd);
@@ -25,6 +39,9 @@ extern int madvise_free_huge_pmd(struct mmu_gather *tlb,
 extern int zap_huge_pmd(struct mmu_gather *tlb,
 			struct vm_area_struct *vma,
 			pmd_t *pmd, unsigned long addr);
+extern int zap_huge_pud(struct mmu_gather *tlb,
+			struct vm_area_struct *vma,
+			pud_t *pud, unsigned long addr);
 extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			unsigned long addr, unsigned long end,
 			unsigned char *vec);
@@ -38,6 +55,8 @@ extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			int prot_numa);
 int vmf_insert_pfn_pmd(struct vm_area_struct *, unsigned long addr, pmd_t *,
 			pfn_t pfn, bool write);
+int vmf_insert_pfn_pud(struct vm_area_struct *, unsigned long addr, pud_t *,
+			pfn_t pfn, bool write);
 enum transparent_hugepage_flag {
 	TRANSPARENT_HUGEPAGE_FLAG,
 	TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
@@ -61,6 +80,10 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
 #define HPAGE_PMD_SIZE	((1UL) << HPAGE_PMD_SHIFT)
 #define HPAGE_PMD_MASK	(~(HPAGE_PMD_SIZE - 1))
 
+#define HPAGE_PUD_SHIFT PUD_SHIFT
+#define HPAGE_PUD_SIZE	((1UL) << HPAGE_PUD_SHIFT)
+#define HPAGE_PUD_MASK	(~(HPAGE_PUD_SIZE - 1))
+
 extern bool is_vma_temporary_stack(struct vm_area_struct *vma);
 
 #define transparent_hugepage_enabled(__vma)				\
@@ -111,6 +134,17 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			__split_huge_pmd(__vma, __pmd, __address);	\
 	}  while (0)
 
+void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
+		unsigned long address);
+
+#define split_huge_pud(__vma, __pud, __address)				\
+	do {								\
+		pud_t *____pud = (__pud);				\
+		if (pud_trans_huge(*____pud)				\
+					|| pud_devmap(*____pud))	\
+			__split_huge_pud(__vma, __pud, __address);	\
+	}  while (0)
+
 #if HPAGE_PMD_ORDER >= MAX_ORDER
 #error "hugepages can't be allocated by the buddy allocator"
 #endif
@@ -122,16 +156,27 @@ extern void vma_adjust_trans_huge(struct vm_area_struct *vma,
 				    long adjust_next);
 extern bool __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
 		spinlock_t **ptl);
+extern bool __pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma,
+		spinlock_t **ptl);
 /* mmap_sem must be held on entry */
 static inline bool pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
 		spinlock_t **ptl)
 {
 	VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma);
-	if (pmd_trans_huge(*pmd))
+	if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd))
 		return __pmd_trans_huge_lock(pmd, vma, ptl);
 	else
 		return false;
 }
+static inline bool pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma,
+		spinlock_t **ptl)
+{
+	VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma);
+	if (pud_trans_huge(*pud) || pud_devmap(*pud))
+		return __pud_trans_huge_lock(pud, vma, ptl);
+	else
+		return false;
+}
 static inline int hpage_nr_pages(struct page *page)
 {
 	if (unlikely(PageTransHuge(page)))
@@ -154,6 +199,11 @@ static inline bool is_huge_zero_pmd(pmd_t pmd)
 	return is_huge_zero_page(pmd_page(pmd));
 }
 
+static inline bool is_huge_zero_pud(pud_t pud)
+{
+	return 0;
+}
+
 struct page *get_huge_zero_page(void);
 
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4bf3811..e14634f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -273,6 +273,8 @@ struct vm_operations_struct {
 	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
 	int (*pmd_fault)(struct vm_area_struct *, unsigned long address,
 						pmd_t *, unsigned int flags);
+	int (*pud_fault)(struct vm_area_struct *, unsigned long address,
+						pud_t *, unsigned int flags);
 	void (*map_pages)(struct vm_area_struct *vma, struct vm_fault *vmf);
 
 	/* notification that a previously read-only page is about to become
@@ -1136,6 +1138,13 @@ static inline pmd_t pfn_t_pmd(pfn_t pfn, pgprot_t pgprot)
 }
 #endif
 
+#ifdef pfn_pud
+static inline pud_t pfn_t_pud(pfn_t pfn, pgprot_t pgprot)
+{
+	return pfn_pud(pfn_t_to_pfn(pfn), pgprot);
+}
+#endif
+
 #ifdef __HAVE_ARCH_PTE_DEVMAP
 static inline bool pfn_t_devmap(pfn_t pfn)
 {
@@ -1359,6 +1368,10 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
 
 /**
  * mm_walk - callbacks for walk_page_range
+ * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry
+ *	       this handler should only handle pud_trans_huge() puds.
+ *	       the pmd_entry or pte_entry callbacks will be used for
+ *	       regular PUDs.
  * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry
  *	       this handler is required to be able to handle
  *	       pmd_trans_huge() pmds.  They may simply choose to
@@ -1378,6 +1391,8 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
  * (see the comment on walk_page_range() for more details)
  */
 struct mm_walk {
+	int (*pud_entry)(pud_t *pud, unsigned long addr,
+			 unsigned long next, struct mm_walk *walk);
 	int (*pmd_entry)(pmd_t *pmd, unsigned long addr,
 			 unsigned long next, struct mm_walk *walk);
 	int (*pte_entry)(pte_t *pte, unsigned long addr,
@@ -1951,6 +1966,10 @@ static inline void pgtable_pmd_page_dtor(struct page *page) {}
 #define pmd_devmap(x) (0)
 #endif
 
+#ifndef pud_devmap
+#define pud_devmap(x) (0)
+#endif
+
 static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
 {
 	spinlock_t *ptl = pmd_lockptr(mm, pmd);
@@ -1958,6 +1977,17 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
 	return ptl;
 }
 
+/*
+ * No scalability reason to split PUD locks yet, but follow the same pattern
+ * as the PMD locks to make it easier if we have to.
+ */
+static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud)
+{
+	spinlock_t *ptl = &mm->page_table_lock;
+	spin_lock(ptl);
+	return ptl;
+}
+
 extern void free_area_init(unsigned long * zones_size);
 extern void free_area_init_node(int nid, unsigned long * zones_size,
 		unsigned long zone_start_pfn, unsigned long *zholes_size);
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index a1a210d..32be698 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -381,6 +381,19 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 	___pmd;								\
 })
 
+#define pudp_huge_clear_flush_notify(__vma, __haddr, __pud)		\
+({									\
+	unsigned long ___haddr = __haddr & HPAGE_PUD_MASK;		\
+	struct mm_struct *___mm = (__vma)->vm_mm;			\
+	pud_t ___pud;							\
+									\
+	___pud = pudp_huge_clear_flush(__vma, __haddr, __pud);		\
+	mmu_notifier_invalidate_range(___mm, ___haddr,			\
+				      ___haddr + HPAGE_PUD_SIZE);	\
+									\
+	___pud;								\
+})
+
 #define pmdp_huge_get_and_clear_notify(__mm, __haddr, __pmd)		\
 ({									\
 	unsigned long ___haddr = __haddr & HPAGE_PMD_MASK;		\
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 76ccead..1d538e4 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1002,6 +1002,58 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 	return VM_FAULT_NOPAGE;
 }
 
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma)
+{
+	if (likely(vma->vm_flags & VM_WRITE))
+		pud = pud_mkwrite(pud);
+	return pud;
+}
+
+static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
+		pud_t *pud, pfn_t pfn, pgprot_t prot, bool write)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	pud_t entry;
+	spinlock_t *ptl;
+
+	ptl = pud_lock(mm, pud);
+	entry = pud_mkhuge(pfn_t_pud(pfn, prot));
+	if (pfn_t_devmap(pfn))
+		entry = pud_mkdevmap(entry);
+	if (write) {
+		entry = pud_mkyoung(pud_mkdirty(entry));
+		entry = maybe_pud_mkwrite(entry, vma);
+	}
+	set_pud_at(mm, addr, pud, entry);
+	update_mmu_cache_pud(vma, addr, pud);
+	spin_unlock(ptl);
+}
+
+int vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
+			pud_t *pud, pfn_t pfn, bool write)
+{
+	pgprot_t pgprot = vma->vm_page_prot;
+	/*
+	 * If we had pud_special, we could avoid all these restrictions,
+	 * but we need to be consistent with PTEs and architectures that
+	 * can't support a 'special' bit.
+	 */
+	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
+	BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
+						(VM_PFNMAP|VM_MIXEDMAP));
+	BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
+	BUG_ON(!pfn_t_devmap(pfn));
+
+	if (addr < vma->vm_start || addr >= vma->vm_end)
+		return VM_FAULT_SIGBUS;
+	if (track_pfn_insert(vma, &pgprot, pfn))
+		return VM_FAULT_SIGBUS;
+	insert_pfn_pud(vma, addr, pud, pfn, pgprot, write);
+	return VM_FAULT_NOPAGE;
+}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
 static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
 		pmd_t *pmd)
 {
@@ -1126,6 +1178,29 @@ out:
 	return ret;
 }
 
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+void huge_pud_set_accessed(struct mm_struct *mm, struct vm_area_struct *vma,
+			   unsigned long address, pud_t *pud, pud_t orig_pud,
+			   int dirty)
+{
+	spinlock_t *ptl;
+	pud_t entry;
+	unsigned long haddr;
+
+	ptl = pud_lock(mm, pud);
+	if (unlikely(!pud_same(*pud, orig_pud)))
+		goto unlock;
+
+	entry = pud_mkyoung(orig_pud);
+	haddr = address & HPAGE_PMD_MASK;
+	if (pudp_set_access_flags(vma, haddr, pud, entry, dirty))
+		update_mmu_cache_pud(vma, address, pud);
+
+unlock:
+	spin_unlock(ptl);
+}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
 void huge_pmd_set_accessed(struct mm_struct *mm,
 			   struct vm_area_struct *vma,
 			   unsigned long address,
@@ -1797,6 +1872,22 @@ bool __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
 	return false;
 }
 
+/*
+ * Returns true if a given pud maps a thp, false otherwise.
+ *
+ * Note that if it returns true, this routine returns without unlocking page
+ * table lock. So callers must unlock it.
+ */
+bool __pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma,
+		spinlock_t **ptl)
+{
+	*ptl = pud_lock(vma->vm_mm, pud);
+	if (likely(pud_trans_huge(*pud) || pud_devmap(*pud)))
+		return true;
+	spin_unlock(*ptl);
+	return false;
+}
+
 #define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE)
 
 int hugepage_madvise(struct vm_area_struct *vma,
@@ -2867,6 +2958,66 @@ static int khugepaged(void *none)
 	return 0;
 }
 
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
+		 pud_t *pud, unsigned long addr)
+{
+	pud_t orig_pud;
+	spinlock_t *ptl;
+
+	if (!__pud_trans_huge_lock(pud, vma, &ptl))
+		return 0;
+	/*
+	 * For architectures like ppc64 we look at deposited pgtable
+	 * when calling pudp_huge_get_and_clear. So do the
+	 * pgtable_trans_huge_withdraw after finishing pudp related
+	 * operations.
+	 */
+	orig_pud = pudp_huge_get_and_clear_full(tlb->mm, addr, pud,
+			tlb->fullmm);
+	tlb_remove_pud_tlb_entry(tlb, pud, addr);
+	if (vma_is_dax(vma)) {
+		spin_unlock(ptl);
+		/* No zero page support yet */
+	} else {
+		/* No support for anonymous PUD pages yet */
+		BUG();
+	}
+	return 1;
+}
+
+static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
+		unsigned long haddr)
+{
+	VM_BUG_ON(haddr & ~HPAGE_PUD_MASK);
+	VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
+	VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma);
+	VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud));
+
+	count_vm_event(THP_SPLIT_PMD);
+
+	pudp_huge_clear_flush_notify(vma, haddr, pud);
+}
+
+void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
+		unsigned long address)
+{
+	spinlock_t *ptl;
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long haddr = address & HPAGE_PUD_MASK;
+
+	mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PUD_SIZE);
+	ptl = pud_lock(mm, pud);
+	if (unlikely(!pud_trans_huge(*pud) && !pud_devmap(*pud)))
+		goto out;
+	__split_huge_pud_locked(vma, pud, haddr);
+
+out:
+	spin_unlock(ptl);
+	mmu_notifier_invalidate_range_end(mm, haddr, haddr + HPAGE_PUD_SIZE);
+}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
 static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
 		unsigned long haddr, pmd_t *pmd)
 {
diff --git a/mm/memory.c b/mm/memory.c
index 416b129..7328df0 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1220,9 +1220,27 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
 	pud = pud_offset(pgd, addr);
 	do {
 		next = pud_addr_end(addr, end);
+		if (pud_trans_huge(*pud) || pud_devmap(*pud)) {
+			if (next - addr != HPAGE_PUD_SIZE) {
+#ifdef CONFIG_DEBUG_VM
+				if (!rwsem_is_locked(&tlb->mm->mmap_sem)) {
+					pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n",
+						__func__, addr, end,
+						vma->vm_start,
+						vma->vm_end);
+					BUG();
+				}
+#endif
+				split_huge_pud(vma, pud, addr);
+			} else if (zap_huge_pud(tlb, vma, pud, addr))
+				goto next;
+			/* fall through */
+		}
 		if (pud_none_or_clear_bad(pud))
 			continue;
 		next = zap_pmd_range(tlb, vma, pud, addr, next, details);
+next:
+		cond_resched();
 	} while (pud++, addr = next, addr != end);
 
 	return addr;
@@ -3264,6 +3282,29 @@ static int wp_huge_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
 	return VM_FAULT_FALLBACK;
 }
 
+static int create_huge_pud(struct mm_struct *mm, struct vm_area_struct *vma,
+			unsigned long address, pud_t *pud, unsigned int flags)
+{
+	/* No support for anonymous transparent PUD pages yet */
+	if (vma_is_anonymous(vma))
+		return VM_FAULT_FALLBACK;
+	if (vma->vm_ops->pud_fault)
+		return vma->vm_ops->pud_fault(vma, address, pud, flags);
+	return VM_FAULT_FALLBACK;
+}
+
+static int wp_huge_pud(struct mm_struct *mm, struct vm_area_struct *vma,
+			unsigned long address, pud_t *pud, pud_t orig_pud,
+			unsigned int flags)
+{
+	/* No support for anonymous transparent PUD pages yet */
+	if (vma_is_anonymous(vma))
+		return VM_FAULT_FALLBACK;
+	if (vma->vm_ops->pud_fault)
+		return vma->vm_ops->pud_fault(vma, address, pud, flags);
+	return VM_FAULT_FALLBACK;
+}
+
 /*
  * These routines also need to handle stuff like marking pages dirty
  * and/or accessed for architectures that don't do it in hardware (most
@@ -3362,6 +3403,32 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	pud = pud_alloc(mm, pgd, address);
 	if (!pud)
 		return VM_FAULT_OOM;
+	if (pud_none(*pud) && transparent_hugepage_enabled(vma)) {
+		int ret = create_huge_pud(mm, vma, address, pud, flags);
+		if (!(ret & VM_FAULT_FALLBACK))
+			return ret;
+	} else {
+		pud_t orig_pud = *pud;
+		int ret;
+
+		barrier();
+		if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) {
+			unsigned int dirty = flags & FAULT_FLAG_WRITE;
+
+			/* NUMA case for anonymous PUDs would go here */
+
+			if (dirty && !pud_write(orig_pud)) {
+				ret = wp_huge_pud(mm, vma, address, pud,
+							orig_pud, flags);
+				if (!(ret & VM_FAULT_FALLBACK))
+					return ret;
+			} else {
+				huge_pud_set_accessed(mm, vma, address, pud,
+						      orig_pud, dirty);
+				return 0;
+			}
+		}
+	}
 	pmd = pmd_alloc(mm, pud, address);
 	if (!pmd)
 		return VM_FAULT_OOM;
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 2072444..200d771 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -78,14 +78,31 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 
 	pud = pud_offset(pgd, addr);
 	do {
+ again:
 		next = pud_addr_end(addr, end);
-		if (pud_none_or_clear_bad(pud)) {
+		if (pud_none(*pud) || !walk->vma) {
 			if (walk->pte_hole)
 				err = walk->pte_hole(addr, next, walk);
 			if (err)
 				break;
 			continue;
 		}
+
+		if (walk->pud_entry) {
+			spinlock_t *ptl;
+			if (pud_trans_huge_lock(pud, walk->vma, &ptl)) {
+				err = walk->pud_entry(pud, addr, next, walk);
+				spin_unlock(ptl);
+				if (err)
+					break;
+				continue;
+			}
+		}
+
+		split_huge_pud(walk->vma, pud, addr);
+		if (pud_none(*pud))
+			goto again;
+
 		if (walk->pmd_entry || walk->pte_entry)
 			err = walk_pmd_range(pud, addr, next, walk);
 		if (err)
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 9d47676..415fa5a 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -96,6 +96,7 @@ pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
  * e.g. see arch/arc: flush_pmd_tlb_range
  */
 #define flush_pmd_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)
+#define flush_pud_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)
 #endif
 
 #ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
@@ -137,6 +138,19 @@ pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address,
 	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	return pmd;
 }
+
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address,
+			    pud_t *pudp)
+{
+	pud_t pud;
+	VM_BUG_ON(address & ~HPAGE_PUD_MASK);
+	VM_BUG_ON(!pud_trans_huge(*pudp) && !pud_devmap(*pudp));
+	pud = pudp_huge_get_and_clear(vma->vm_mm, address, pudp);
+	flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE);
+	return pud;
+}
+#endif
 #endif
 
 #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
-- 
2.6.2

Re: [PATCH 1/8] mm: Add optional support for PUD-sized transparent hugepages

[Kirill A. Shutemov]

On Thu, Dec 24, 2015 at 11:20:30AM -0500, Matthew Wilcox wrote:
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 4bf3811..e14634f 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -1958,6 +1977,17 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
>  	return ptl;
>  }
>  
> +/*
> + * No scalability reason to split PUD locks yet, but follow the same pattern
> + * as the PMD locks to make it easier if we have to.
> + */

I don't think it makes any good unless you convert all other places where
we use page_table_lock to protect pud table (like __pud_alloc()) to the
same API.
I think this would deserve separate patch.

> +static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud)
> +{
> +	spinlock_t *ptl = &mm->page_table_lock;
> +	spin_lock(ptl);
> +	return ptl;
> +}
> +
>  extern void free_area_init(unsigned long * zones_size);
>  extern void free_area_init_node(int nid, unsigned long * zones_size,
>  		unsigned long zone_start_pfn, unsigned long *zholes_size);

...

> diff --git a/mm/memory.c b/mm/memory.c
> index 416b129..7328df0 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -1220,9 +1220,27 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
>  	pud = pud_offset(pgd, addr);
>  	do {
>  		next = pud_addr_end(addr, end);
> +		if (pud_trans_huge(*pud) || pud_devmap(*pud)) {
> +			if (next - addr != HPAGE_PUD_SIZE) {
> +#ifdef CONFIG_DEBUG_VM

IS_ENABLED(CONFIG_DEBUG_VM) ?

> +				if (!rwsem_is_locked(&tlb->mm->mmap_sem)) {
> +					pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n",
> +						__func__, addr, end,
> +						vma->vm_start,
> +						vma->vm_end);

dump_vma(), I guess.

> +					BUG();
> +				}
> +#endif
> +				split_huge_pud(vma, pud, addr);
> +			} else if (zap_huge_pud(tlb, vma, pud, addr))
> +				goto next;
> +			/* fall through */
> +		}
>  		if (pud_none_or_clear_bad(pud))
>  			continue;
>  		next = zap_pmd_range(tlb, vma, pud, addr, next, details);
> +next:
> +		cond_resched();
>  	} while (pud++, addr = next, addr != end);
>  
>  	return addr;
-- 
 Kirill A. Shutemov

Re: [PATCH 1/8] mm: Add optional support for PUD-sized transparent hugepages

[Matthew Wilcox]

On Mon, Dec 28, 2015 at 12:05:51PM +0200, Kirill A. Shutemov wrote:
> On Thu, Dec 24, 2015 at 11:20:30AM -0500, Matthew Wilcox wrote:
> > diff --git a/include/linux/mm.h b/include/linux/mm.h
> > index 4bf3811..e14634f 100644
> > --- a/include/linux/mm.h
> > +++ b/include/linux/mm.h
> > @@ -1958,6 +1977,17 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
> >  	return ptl;
> >  }
> >  
> > +/*
> > + * No scalability reason to split PUD locks yet, but follow the same pattern
> > + * as the PMD locks to make it easier if we have to.
> > + */
> 
> I don't think it makes any good unless you convert all other places where
> we use page_table_lock to protect pud table (like __pud_alloc()) to the
> same API.
> I think this would deserve separate patch.

Sure, a separate patch to convert existing users of the PTL.  But I
don't think it does any harm to introduce the PUD version of the PMD API.
Maybe with a comment indicating that tere is significant work to be done
in converting existing users to this API?

> > diff --git a/mm/memory.c b/mm/memory.c
> > index 416b129..7328df0 100644
> > --- a/mm/memory.c
> > +++ b/mm/memory.c
> > @@ -1220,9 +1220,27 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
> >  	pud = pud_offset(pgd, addr);
> >  	do {
> >  		next = pud_addr_end(addr, end);
> > +		if (pud_trans_huge(*pud) || pud_devmap(*pud)) {
> > +			if (next - addr != HPAGE_PUD_SIZE) {
> > +#ifdef CONFIG_DEBUG_VM
> 
> IS_ENABLED(CONFIG_DEBUG_VM) ?
> 
> > +				if (!rwsem_is_locked(&tlb->mm->mmap_sem)) {
> > +					pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n",
> > +						__func__, addr, end,
> > +						vma->vm_start,
> > +						vma->vm_end);
> 
> dump_vma(), I guess.

These two issues are copy-and-paste from the existing PMD code.  I'm happy
to update the PMD code to the new-and-improved way of doing things;
I'm just not keen to have the PMD and PUD code diverge unnecessarily.

Re: [PATCH 1/8] mm: Add optional support for PUD-sized transparent hugepages

[Kirill A. Shutemov]

On Sat, Jan 02, 2016 at 12:06:38PM -0500, Matthew Wilcox wrote:
> On Mon, Dec 28, 2015 at 12:05:51PM +0200, Kirill A. Shutemov wrote:
> > On Thu, Dec 24, 2015 at 11:20:30AM -0500, Matthew Wilcox wrote:
> > > diff --git a/include/linux/mm.h b/include/linux/mm.h
> > > index 4bf3811..e14634f 100644
> > > --- a/include/linux/mm.h
> > > +++ b/include/linux/mm.h
> > > @@ -1958,6 +1977,17 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
> > >  	return ptl;
> > >  }
> > >  
> > > +/*
> > > + * No scalability reason to split PUD locks yet, but follow the same pattern
> > > + * as the PMD locks to make it easier if we have to.
> > > + */
> > 
> > I don't think it makes any good unless you convert all other places where
> > we use page_table_lock to protect pud table (like __pud_alloc()) to the
> > same API.
> > I think this would deserve separate patch.
> 
> Sure, a separate patch to convert existing users of the PTL.  But I
> don't think it does any harm to introduce the PUD version of the PMD API.
> Maybe with a comment indicating that tere is significant work to be done
> in converting existing users to this API?

I think that's fine with the fat comment around pud_lock() definition.
 
> > > diff --git a/mm/memory.c b/mm/memory.c
> > > index 416b129..7328df0 100644
> > > --- a/mm/memory.c
> > > +++ b/mm/memory.c
> > > @@ -1220,9 +1220,27 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
> > >  	pud = pud_offset(pgd, addr);
> > >  	do {
> > >  		next = pud_addr_end(addr, end);
> > > +		if (pud_trans_huge(*pud) || pud_devmap(*pud)) {
> > > +			if (next - addr != HPAGE_PUD_SIZE) {
> > > +#ifdef CONFIG_DEBUG_VM
> > 
> > IS_ENABLED(CONFIG_DEBUG_VM) ?
> > 
> > > +				if (!rwsem_is_locked(&tlb->mm->mmap_sem)) {
> > > +					pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n",
> > > +						__func__, addr, end,
> > > +						vma->vm_start,
> > > +						vma->vm_end);
> > 
> > dump_vma(), I guess.
> 
> These two issues are copy-and-paste from the existing PMD code.  I'm happy
> to update the PMD code to the new-and-improved way of doing things;
> I'm just not keen to have the PMD and PUD code diverge unnecessarily.

Yes, please update PMD too. It looks ugly. VM_BUG_ON_VMA() is probably
right way to deal with this.

-- 
 Kirill A. Shutemov

Re: [PATCH 1/8] mm: Add optional support for PUD-sized transparent hugepages

[Kirill A. Shutemov]

On Thu, Dec 24, 2015 at 11:20:30AM -0500, Matthew Wilcox wrote:
> The only major difference is how the new ->pud_entry method in mm_walk
> works.  The ->pmd_entry method replaces the ->pte_entry method, whereas
> the ->pud_entry method works along with either ->pmd_entry or ->pte_entry.

I think it makes pagewalk API confusing. We need something more coherent.

-- 
 Kirill A. Shutemov

[PATCH 2/8] mincore: Add support for PUDs

[Matthew Wilcox]

From: Matthew Wilcox <willy@linux.intel.com>

We don't actually care about the contents of the PUD, just set the bits
to indicate presence and return.

Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
 mm/mincore.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/mm/mincore.c b/mm/mincore.c
index 2a565ed..8e6ce12 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -108,6 +108,18 @@ static int mincore_unmapped_range(unsigned long addr, unsigned long end,
 	return 0;
 }
 
+static int mincore_pud_range(pud_t *pud, unsigned long addr, unsigned long end,
+			struct mm_walk *walk)
+{
+	unsigned char *vec = walk->private;
+	int nr = (end - addr) >> PAGE_SHIFT;
+
+	memset(vec, 1, nr);
+	walk->private += nr;
+
+	return 0;
+}
+
 static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			struct mm_walk *walk)
 {
@@ -176,6 +188,7 @@ static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *v
 	unsigned long end;
 	int err;
 	struct mm_walk mincore_walk = {
+		.pud_entry = mincore_pud_range,
 		.pmd_entry = mincore_pte_range,
 		.pte_hole = mincore_unmapped_range,
 		.hugetlb_entry = mincore_hugetlb,
-- 
2.6.2

[PATCH 3/8] procfs: Add support for PUDs to smaps, clear_refs and pagemap

[Matthew Wilcox]

From: Matthew Wilcox <willy@linux.intel.com>

Because there's no 'struct page' for DAX THPs, a lot of this code is
simpler than the PMD code it mimics.  Extra code would need to be added
to support PUDs of anonymous or page-cache THPs.

Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
 fs/proc/task_mmu.c | 109 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 109 insertions(+)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 67aaaad..6a9dad7 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -596,6 +596,33 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
 }
 #endif
 
+static int smaps_pud_range(pud_t *pud, unsigned long addr, unsigned long end,
+		struct mm_walk *walk)
+{
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+	struct vm_area_struct *vma = walk->vma;
+	struct mem_size_stats *mss = walk->private;
+
+	if (is_huge_zero_pud(*pud))
+		return 0;
+
+	mss->resident += HPAGE_PUD_SIZE;
+	if (vma->vm_flags & VM_SHARED) {
+		if (pud_dirty(*pud))
+			mss->shared_dirty += HPAGE_PUD_SIZE;
+		else
+			mss->shared_clean += HPAGE_PUD_SIZE;
+	} else {
+		if (pud_dirty(*pud))
+			mss->private_dirty += HPAGE_PUD_SIZE;
+		else
+			mss->private_clean += HPAGE_PUD_SIZE;
+	}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
+	return 0;
+}
+
 static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			   struct mm_walk *walk)
 {
@@ -716,6 +743,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 	struct vm_area_struct *vma = v;
 	struct mem_size_stats mss;
 	struct mm_walk smaps_walk = {
+		.pud_entry = smaps_pud_range,
 		.pmd_entry = smaps_pte_range,
 #ifdef CONFIG_HUGETLB_PAGE
 		.hugetlb_entry = smaps_hugetlb_range,
@@ -901,13 +929,50 @@ static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
 
 	set_pmd_at(vma->vm_mm, addr, pmdp, pmd);
 }
+static inline void clear_soft_dirty_pud(struct vm_area_struct *vma,
+		unsigned long addr, pud_t *pudp)
+{
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+	pud_t pud = pudp_huge_get_and_clear(vma->vm_mm, addr, pudp);
+
+	pud = pud_wrprotect(pud);
+	pud = pud_clear_soft_dirty(pud);
+
+	if (vma->vm_flags & VM_SOFTDIRTY)
+		vma->vm_flags &= ~VM_SOFTDIRTY;
+
+	set_pud_at(vma->vm_mm, addr, pudp, pud);
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+}
 #else
 static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
 		unsigned long addr, pmd_t *pmdp)
 {
 }
+static inline void clear_soft_dirty_pud(struct vm_area_struct *vma,
+		unsigned long addr, pud_t *pudp)
+{
+}
 #endif
 
+static int clear_refs_pud_range(pud_t *pud, unsigned long addr,
+				unsigned long end, struct mm_walk *walk)
+{
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+	struct clear_refs_private *cp = walk->private;
+	struct vm_area_struct *vma = walk->vma;
+
+	if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
+		clear_soft_dirty_pud(vma, addr, pud);
+	} else {
+		/* Clear accessed and referenced bits. */
+		pudp_test_and_clear_young(vma, addr, pud);
+	}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
+	return 0;
+}
+
 static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 				unsigned long end, struct mm_walk *walk)
 {
@@ -1017,6 +1082,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 			.type = type,
 		};
 		struct mm_walk clear_refs_walk = {
+			.pud_entry = clear_refs_pud_range,
 			.pmd_entry = clear_refs_pte_range,
 			.test_walk = clear_refs_test_walk,
 			.mm = mm,
@@ -1181,6 +1247,48 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
 	return make_pme(frame, flags);
 }
 
+static int pagemap_pud_range(pud_t *pudp, unsigned long addr, unsigned long end,
+			     struct mm_walk *walk)
+{
+	int err = 0;
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+	struct vm_area_struct *vma = walk->vma;
+	struct pagemapread *pm = walk->private;
+	u64 flags = 0, frame = 0;
+	pud_t pud = *pudp;
+
+	if ((vma->vm_flags & VM_SOFTDIRTY) || pud_soft_dirty(pud))
+		flags |= PM_SOFT_DIRTY;
+
+	/*
+	 * Currently pud for thp is always present because thp
+	 * can not be swapped-out, migrated, or HWPOISONed
+	 * (split in such cases instead.)
+	 * This if-check is just to prepare for future implementation.
+	 */
+	if (pud_present(pud)) {
+		flags |= PM_PRESENT;
+		if (!(vma->vm_flags & VM_SHARED))
+			flags |= PM_MMAP_EXCLUSIVE;
+
+		if (pm->show_pfn)
+			frame = pud_pfn(pud) +
+					((addr & ~PUD_MASK) >> PAGE_SHIFT);
+
+		for (; addr != end; addr += PAGE_SIZE) {
+			pagemap_entry_t pme = make_pme(frame, flags);
+
+			err = add_to_pagemap(addr, &pme, pm);
+			if (err)
+				break;
+			if (pm->show_pfn && (flags & PM_PRESENT))
+				frame++;
+		}
+	}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+	return err;
+}
+
 static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
 			     struct mm_walk *walk)
 {
@@ -1359,6 +1467,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	if (!pm.buffer)
 		goto out_mm;
 
+	pagemap_walk.pud_entry = pagemap_pud_range;
 	pagemap_walk.pmd_entry = pagemap_pmd_range;
 	pagemap_walk.pte_hole = pagemap_pte_hole;
 #ifdef CONFIG_HUGETLB_PAGE
-- 
2.6.2

[PATCH 4/8] x86: Add support for PUD-sized transparent hugepages

[Matthew Wilcox]

From: Matthew Wilcox <willy@linux.intel.com>

The x86-specific code needed to support the PUD uses in the transparent
hugepages code.

Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
 arch/x86/Kconfig                      |  1 +
 arch/x86/include/asm/paravirt.h       | 11 ++++
 arch/x86/include/asm/paravirt_types.h |  2 +
 arch/x86/include/asm/pgtable.h        | 95 +++++++++++++++++++++++++++++++++++
 arch/x86/include/asm/pgtable_64.h     | 13 +++++
 arch/x86/kernel/paravirt.c            |  1 +
 arch/x86/mm/pgtable.c                 | 31 ++++++++++++
 7 files changed, 154 insertions(+)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index fd0c8ea..df99d21 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -89,6 +89,7 @@ config X86
 	select HAVE_ARCH_SOFT_DIRTY		if X86_64
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+	select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64
 	select HAVE_BPF_JIT			if X86_64
 	select HAVE_CC_STACKPROTECTOR
 	select HAVE_CMPXCHG_DOUBLE
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index c261402..db4f274 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -479,6 +479,17 @@ static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 			    native_pmd_val(pmd));
 }
 
+static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
+			      pud_t *pudp, pud_t pud)
+{
+	if (sizeof(pudval_t) > sizeof(long))
+		/* 5 arg words */
+		pv_mmu_ops.set_pud_at(mm, addr, pudp, pud);
+	else
+		PVOP_VCALL4(pv_mmu_ops.set_pud_at, mm, addr, pudp,
+			    native_pud_val(pud));
+}
+
 static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
 	pmdval_t val = native_pmd_val(pmd);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 2489d6a..261c203 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -247,6 +247,8 @@ struct pv_mmu_ops {
 	void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval);
 	void (*set_pmd_at)(struct mm_struct *mm, unsigned long addr,
 			   pmd_t *pmdp, pmd_t pmdval);
+	void (*set_pud_at)(struct mm_struct *mm, unsigned long addr,
+			   pud_t *pudp, pud_t pudval);
 	void (*pte_update)(struct mm_struct *mm, unsigned long addr,
 			   pte_t *ptep);
 
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index c69f385..246bc5f 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -46,6 +46,7 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page);
 #define set_pte(ptep, pte)		native_set_pte(ptep, pte)
 #define set_pte_at(mm, addr, ptep, pte)	native_set_pte_at(mm, addr, ptep, pte)
 #define set_pmd_at(mm, addr, pmdp, pmd)	native_set_pmd_at(mm, addr, pmdp, pmd)
+#define set_pud_at(mm, addr, pudp, pud)	native_set_pud_at(mm, addr, pudp, pud)
 
 #define set_pte_atomic(ptep, pte)					\
 	native_set_pte_atomic(ptep, pte)
@@ -114,6 +115,16 @@ static inline int pmd_young(pmd_t pmd)
 	return pmd_flags(pmd) & _PAGE_ACCESSED;
 }
 
+static inline int pud_dirty(pud_t pud)
+{
+	return pud_flags(pud) & _PAGE_DIRTY;
+}
+
+static inline int pud_young(pud_t pud)
+{
+	return pud_flags(pud) & _PAGE_ACCESSED;
+}
+
 static inline int pte_write(pte_t pte)
 {
 	return pte_flags(pte) & _PAGE_RW;
@@ -167,12 +178,23 @@ static inline int pmd_trans_huge(pmd_t pmd)
 	return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE;
 }
 
+static inline int pud_trans_huge(pud_t pud)
+{
+	return (pud_val(pud) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE;
+}
+
 #define pmd_devmap pmd_devmap
 static inline int pmd_devmap(pmd_t pmd)
 {
 	return !!(pmd_val(pmd) & _PAGE_DEVMAP);
 }
 
+#define pud_devmap pud_devmap
+static inline int pud_devmap(pud_t pud)
+{
+	return !!(pud_val(pud) & _PAGE_DEVMAP);
+}
+
 static inline int has_transparent_hugepage(void)
 {
 	return cpu_has_pse;
@@ -317,6 +339,45 @@ static inline pmd_t pmd_mknotpresent(pmd_t pmd)
 	return pmd_clear_flags(pmd, _PAGE_PRESENT | _PAGE_PROTNONE);
 }
 
+static inline pud_t pud_set_flags(pud_t pud, pudval_t set)
+{
+	pudval_t v = native_pud_val(pud);
+
+	return __pud(v | set);
+}
+
+static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear)
+{
+	pudval_t v = native_pud_val(pud);
+
+	return __pud(v & ~clear);
+}
+
+static inline pud_t pud_mkdevmap(pud_t pud)
+{
+	return pud_set_flags(pud, _PAGE_DEVMAP);
+}
+
+static inline pud_t pud_mkhuge(pud_t pud)
+{
+	return pud_set_flags(pud, _PAGE_PSE);
+}
+
+static inline pud_t pud_mkdirty(pud_t pud)
+{
+	return pud_set_flags(pud, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
+}
+
+static inline pud_t pud_mkyoung(pud_t pud)
+{
+	return pud_set_flags(pud, _PAGE_ACCESSED);
+}
+
+static inline pud_t pud_mkwrite(pud_t pud)
+{
+	return pud_set_flags(pud, _PAGE_RW);
+}
+
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 static inline int pte_soft_dirty(pte_t pte)
 {
@@ -328,6 +389,11 @@ static inline int pmd_soft_dirty(pmd_t pmd)
 	return pmd_flags(pmd) & _PAGE_SOFT_DIRTY;
 }
 
+static inline int pud_soft_dirty(pud_t pud)
+{
+	return pud_flags(pud) & _PAGE_SOFT_DIRTY;
+}
+
 static inline pte_t pte_mksoft_dirty(pte_t pte)
 {
 	return pte_set_flags(pte, _PAGE_SOFT_DIRTY);
@@ -378,6 +444,13 @@ static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
 		     massage_pgprot(pgprot));
 }
 
+#define pfn_pud pfn_pud
+static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot)
+{
+	return __pud(((phys_addr_t)page_nr << PAGE_SHIFT) |
+		     massage_pgprot(pgprot));
+}
+
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	pteval_t val = pte_val(pte);
@@ -744,6 +817,12 @@ static inline void native_set_pmd_at(struct mm_struct *mm, unsigned long addr,
 	native_set_pmd(pmdp, pmd);
 }
 
+static inline void native_set_pud_at(struct mm_struct *mm, unsigned long addr,
+				     pud_t *pudp , pud_t pud)
+{
+	native_set_pud(pudp, pud);
+}
+
 #ifndef CONFIG_PARAVIRT
 /*
  * Rules for using pte_update - it must be called after any PTE update which
@@ -822,10 +901,15 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm,
 extern int pmdp_set_access_flags(struct vm_area_struct *vma,
 				 unsigned long address, pmd_t *pmdp,
 				 pmd_t entry, int dirty);
+extern int pudp_set_access_flags(struct vm_area_struct *vma,
+				 unsigned long address, pud_t *pudp,
+				 pud_t entry, int dirty);
 
 #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
 extern int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 				     unsigned long addr, pmd_t *pmdp);
+extern int pudp_test_and_clear_young(struct vm_area_struct *vma,
+				     unsigned long addr, pud_t *pudp);
 
 #define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
 extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
@@ -845,6 +929,13 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long
 	return native_pmdp_get_and_clear(pmdp);
 }
 
+#define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR
+static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr,
+				       pud_t *pudp)
+{
+	return native_pudp_get_and_clear(pudp);
+}
+
 #define __HAVE_ARCH_PMDP_SET_WRPROTECT
 static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 				      unsigned long addr, pmd_t *pmdp)
@@ -893,6 +984,10 @@ static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
 		unsigned long addr, pmd_t *pmd)
 {
 }
+static inline void update_mmu_cache_pud(struct vm_area_struct *vma,
+		unsigned long addr, pud_t *pud)
+{
+}
 
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 2ee7811..a3aa6b7 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -106,6 +106,19 @@ static inline void native_pud_clear(pud_t *pud)
 	native_set_pud(pud, native_make_pud(0));
 }
 
+static inline pud_t native_pudp_get_and_clear(pud_t *pudp)
+{
+#ifdef CONFIG_SMP
+	return native_make_pud(xchg(&pudp->pud, 0));
+#else
+	/* native_local_pudp_get_and_clear,
+	   but duplicated because of cyclic dependency */
+	pud_t ret = *pudp;
+	native_pud_clear(pudp);
+	return ret;
+#endif
+}
+
 static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
 	*pgdp = pgd;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index f08ac28..24d61f2 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -425,6 +425,7 @@ struct pv_mmu_ops pv_mmu_ops = {
 	.pmd_clear = native_pmd_clear,
 #endif
 	.set_pud = native_set_pud,
+	.set_pud_at = native_set_pud_at,
 
 	.pmd_val = PTE_IDENT,
 	.make_pmd = PTE_IDENT,
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 4eb287e..b7c8df6 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -441,6 +441,26 @@ int pmdp_set_access_flags(struct vm_area_struct *vma,
 
 	return changed;
 }
+
+int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
+			  pud_t *pudp, pud_t entry, int dirty)
+{
+	int changed = !pud_same(*pudp, entry);
+
+	VM_BUG_ON(address & ~HPAGE_PUD_MASK);
+
+	if (changed && dirty) {
+		*pudp = entry;
+		/*
+		 * We had a write-protection fault here and changed the pud
+		 * to to more permissive. No need to flush the TLB for that,
+		 * #PF is architecturally guaranteed to do that and in the
+		 * worst-case we'll generate a spurious fault.
+		 */
+	}
+
+	return changed;
+}
 #endif
 
 int ptep_test_and_clear_young(struct vm_area_struct *vma,
@@ -470,6 +490,17 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 
 	return ret;
 }
+int pudp_test_and_clear_young(struct vm_area_struct *vma,
+			      unsigned long addr, pud_t *pudp)
+{
+	int ret = 0;
+
+	if (pud_young(*pudp))
+		ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,
+					 (unsigned long *)pudp);
+
+	return ret;
+}
 #endif
 
 int ptep_clear_flush_young(struct vm_area_struct *vma,
-- 
2.6.2

[PATCH 5/8] dax: Support for transparent PUD pages

[Matthew Wilcox]

From: Matthew Wilcox <willy@linux.intel.com>

The DAX support for transparent huge PUD pages

Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
 fs/dax.c            | 239 ++++++++++++++++++++++++++++++++++++++++++++++++----
 include/linux/dax.h |  21 +++++
 2 files changed, 243 insertions(+), 17 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 82d0bff..63ca298 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -557,14 +557,24 @@ EXPORT_SYMBOL_GPL(dax_fault);
  */
 #define PG_PMD_COLOUR	((PMD_SIZE >> PAGE_SHIFT) - 1)
 
-static void dax_pmd_dbg(struct block_device *bdev, unsigned long address,
-		const char *reason)
+static void __dax_dbg(struct buffer_head *bh, unsigned long address,
+		const char *reason, const char *fn)
 {
-	pr_debug("%s%s dax_pmd: %s addr: %lx fallback: %s\n", bdev
-			? dev_name(part_to_dev(bdev->bd_part)) : "", bdev
-			? ": " : "", current->comm, address, reason);
+	if (bh) {
+		char bname[BDEVNAME_SIZE];
+		bdevname(bh->b_bdev, bname);
+		pr_debug("%s: %s addr: %lx dev %s state %lx start %lld "
+			"length %zd fallback: %s\n", fn, current->comm,
+			address, bname, bh->b_state, (u64)bh->b_blocknr,
+			bh->b_size, reason);
+	} else {
+		pr_debug("%s: %s addr: %lx fallback: %s\n", fn,
+			current->comm, address, reason);
+	}
 }
 
+#define dax_pmd_dbg(bh, address, reason)	__dax_dbg(bh, address, reason, "dax_pmd")
+
 int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		pmd_t *pmd, unsigned int flags, get_block_t get_block,
 		dax_iodone_t complete_unwritten)
@@ -576,7 +586,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	unsigned blkbits = inode->i_blkbits;
 	unsigned long pmd_addr = address & PMD_MASK;
 	bool write = flags & FAULT_FLAG_WRITE;
-	struct block_device *bdev = NULL;
+	struct block_device *bdev;
 	pgoff_t size, pgoff;
 	sector_t block;
 	int result = 0;
@@ -588,16 +598,16 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	/* Fall back to PTEs if we're going to COW */
 	if (write && !(vma->vm_flags & VM_SHARED)) {
 		split_huge_pmd(vma, pmd, address);
-		dax_pmd_dbg(bdev, address, "cow write");
+		dax_pmd_dbg(NULL, address, "cow write");
 		return VM_FAULT_FALLBACK;
 	}
 	/* If the PMD would extend outside the VMA */
 	if (pmd_addr < vma->vm_start) {
-		dax_pmd_dbg(bdev, address, "vma start unaligned");
+		dax_pmd_dbg(NULL, address, "vma start unaligned");
 		return VM_FAULT_FALLBACK;
 	}
 	if ((pmd_addr + PMD_SIZE) > vma->vm_end) {
-		dax_pmd_dbg(bdev, address, "vma end unaligned");
+		dax_pmd_dbg(NULL, address, "vma end unaligned");
 		return VM_FAULT_FALLBACK;
 	}
 
@@ -607,7 +617,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		return VM_FAULT_SIGBUS;
 	/* If the PMD would cover blocks out of the file */
 	if ((pgoff | PG_PMD_COLOUR) >= size) {
-		dax_pmd_dbg(bdev, address,
+		dax_pmd_dbg(NULL, address,
 				"offset + huge page size > file size");
 		return VM_FAULT_FALLBACK;
 	}
@@ -627,7 +637,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	 * would be silly.
 	 */
 	if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE) {
-		dax_pmd_dbg(bdev, address, "block allocation size invalid");
+		dax_pmd_dbg(&bh, address, "allocated block too small");
 		goto fallback;
 	}
 
@@ -653,7 +663,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		goto out;
 	}
 	if ((pgoff | PG_PMD_COLOUR) >= size) {
-		dax_pmd_dbg(bdev, address, "pgoff unaligned");
+		dax_pmd_dbg(&bh, address, "pgoff unaligned");
 		goto fallback;
 	}
 
@@ -663,14 +673,14 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		struct page *zero_page = get_huge_zero_page();
 
 		if (unlikely(!zero_page)) {
-			dax_pmd_dbg(bdev, address, "no zero page");
+			dax_pmd_dbg(&bh, address, "no zero page");
 			goto fallback;
 		}
 
 		ptl = pmd_lock(vma->vm_mm, pmd);
 		if (!pmd_none(*pmd)) {
 			spin_unlock(ptl);
-			dax_pmd_dbg(bdev, address, "pmd already present");
+			dax_pmd_dbg(&bh, address, "pmd already present");
 			goto fallback;
 		}
 
@@ -696,19 +706,19 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 			goto out;
 		}
 		if (length < PMD_SIZE) {
-			dax_pmd_dbg(bdev, address, "dax-length too small");
+			dax_pmd_dbg(&bh, address, "dax-length too small");
 			dax_unmap_atomic(bdev, &dax);
 			goto fallback;
 		}
 		if (pfn_t_to_pfn(dax.pfn) & PG_PMD_COLOUR) {
-			dax_pmd_dbg(bdev, address, "pfn unaligned");
+			dax_pmd_dbg(&bh, address, "pfn unaligned");
 			dax_unmap_atomic(bdev, &dax);
 			goto fallback;
 		}
 
 		if (!pfn_t_devmap(dax.pfn)) {
 			dax_unmap_atomic(bdev, &dax);
-			dax_pmd_dbg(bdev, address, "pfn not in memmap");
+			dax_pmd_dbg(&bh, address, "pfn not in memmap");
 			goto fallback;
 		}
 
@@ -773,6 +783,201 @@ int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	return result;
 }
 EXPORT_SYMBOL_GPL(dax_pmd_fault);
+
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+/*
+ * The 'colour' (ie low bits) within a PUD of a page offset.  This comes up
+ * more often than one might expect in the below function.
+ */
+#define PG_PUD_COLOUR	((PUD_SIZE >> PAGE_SHIFT) - 1)
+
+#define dax_pud_dbg(bh, address, reason)	__dax_dbg(bh, address, reason, "dax_pud")
+
+int __dax_pud_fault(struct vm_area_struct *vma, unsigned long address,
+		pud_t *pud, unsigned int flags, get_block_t get_block,
+		dax_iodone_t complete_unwritten)
+{
+	struct file *file = vma->vm_file;
+	struct address_space *mapping = file->f_mapping;
+	struct inode *inode = mapping->host;
+	struct buffer_head bh;
+	unsigned blkbits = inode->i_blkbits;
+	unsigned long pud_addr = address & PUD_MASK;
+	bool write = flags & FAULT_FLAG_WRITE;
+	struct block_device *bdev = NULL;
+	pgoff_t size, pgoff;
+	sector_t block;
+	int result = 0;
+
+	/* dax pud mappings require pfn_t_devmap() */
+	if (!IS_ENABLED(CONFIG_FS_DAX_PMD))
+		return VM_FAULT_FALLBACK;
+
+	/* Fall back to PTEs if we're going to COW */
+	if (write && !(vma->vm_flags & VM_SHARED)) {
+		split_huge_pud(vma, pud, address);
+		dax_pud_dbg(NULL, address, "cow write");
+		return VM_FAULT_FALLBACK;
+	}
+	/* If the PUD would extend outside the VMA */
+	if (pud_addr < vma->vm_start) {
+		dax_pud_dbg(NULL, address, "vma start unaligned");
+		return VM_FAULT_FALLBACK;
+	}
+	if ((pud_addr + PUD_SIZE) > vma->vm_end) {
+		dax_pud_dbg(NULL, address, "vma end unaligned");
+		return VM_FAULT_FALLBACK;
+	}
+
+	pgoff = linear_page_index(vma, pud_addr);
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (pgoff >= size)
+		return VM_FAULT_SIGBUS;
+	/* If the PUD would cover blocks out of the file */
+	if ((pgoff | PG_PUD_COLOUR) >= size) {
+		dax_pud_dbg(NULL, address,
+				"offset + huge page size > file size");
+		return VM_FAULT_FALLBACK;
+	}
+
+	memset(&bh, 0, sizeof(bh));
+	block = (sector_t)pgoff << (PAGE_SHIFT - blkbits);
+
+	bh.b_size = PUD_SIZE;
+	if (get_block(inode, block, &bh, write) != 0)
+		return VM_FAULT_SIGBUS;
+	bdev = bh.b_bdev;
+	i_mmap_lock_read(mapping);
+
+	/*
+	 * If the filesystem isn't willing to tell us the length of a hole,
+	 * just fall back to PTEs.  Calling get_block 512 times in a loop
+	 * would be silly.
+	 */
+	if (!buffer_size_valid(&bh) || bh.b_size < PUD_SIZE) {
+		dax_pud_dbg(&bh, address, "allocated block too small");
+		goto fallback;
+	}
+
+	/*
+	 * If we allocated new storage, make sure no process has any
+	 * zero pages covering this hole
+	 */
+	if (buffer_new(&bh)) {
+		i_mmap_unlock_read(mapping);
+		unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PUD_SIZE, 0);
+		i_mmap_lock_read(mapping);
+	}
+
+	/*
+	 * If a truncate happened while we were allocating blocks, we may
+	 * leave blocks allocated to the file that are beyond EOF.  We can't
+	 * take i_mutex here, so just leave them hanging; they'll be freed
+	 * when the file is deleted.
+	 */
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (pgoff >= size) {
+		result = VM_FAULT_SIGBUS;
+		goto out;
+	}
+	if ((pgoff | PG_PUD_COLOUR) >= size) {
+		dax_pud_dbg(&bh, address, "pgoff unaligned");
+		goto fallback;
+	}
+
+	if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) {
+		dax_pud_dbg(&bh, address, "no zero page");
+		goto fallback;
+	} else {
+		struct blk_dax_ctl dax = {
+			.sector = to_sector(&bh, inode),
+			.size = PUD_SIZE,
+		};
+		long length = dax_map_atomic(bdev, &dax);
+
+		if (length < 0) {
+			result = VM_FAULT_SIGBUS;
+			goto out;
+		}
+		if (length < PUD_SIZE) {
+			dax_pud_dbg(&bh, address, "dax-length too small");
+			dax_unmap_atomic(bdev, &dax);
+			goto fallback;
+		}
+		if (pfn_t_to_pfn(dax.pfn) & PG_PUD_COLOUR) {
+			dax_pud_dbg(&bh, address, "pfn unaligned");
+			dax_unmap_atomic(bdev, &dax);
+			goto fallback;
+		}
+
+		if (!pfn_t_devmap(dax.pfn)) {
+			dax_unmap_atomic(bdev, &dax);
+			dax_pud_dbg(&bh, address, "pfn not in memmap");
+			goto fallback;
+		}
+
+		if (buffer_unwritten(&bh) || buffer_new(&bh)) {
+			clear_pmem(dax.addr, PUD_SIZE);
+			wmb_pmem();
+			count_vm_event(PGMAJFAULT);
+			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+			result |= VM_FAULT_MAJOR;
+		}
+		dax_unmap_atomic(bdev, &dax);
+
+		dev_dbg(part_to_dev(bdev->bd_part),
+				"%s: %s addr: %lx pfn: %lx sect: %llx\n",
+				__func__, current->comm, address,
+				pfn_t_to_pfn(dax.pfn),
+				(unsigned long long) dax.sector);
+		result |= vmf_insert_pfn_pud(vma, address, pud,
+				dax.pfn, write);
+	}
+
+ out:
+	i_mmap_unlock_read(mapping);
+
+	if (buffer_unwritten(&bh))
+		complete_unwritten(&bh, !(result & VM_FAULT_ERROR));
+
+	return result;
+
+ fallback:
+	count_vm_event(THP_FAULT_FALLBACK);
+	result = VM_FAULT_FALLBACK;
+	goto out;
+}
+EXPORT_SYMBOL_GPL(__dax_pud_fault);
+
+/**
+ * dax_pud_fault - handle a PUD fault on a DAX file
+ * @vma: The virtual memory area where the fault occurred
+ * @vmf: The description of the fault
+ * @get_block: The filesystem method used to translate file offsets to blocks
+ *
+ * When a page fault occurs, filesystems may call this helper in their
+ * pud_fault handler for DAX files.
+ */
+int dax_pud_fault(struct vm_area_struct *vma, unsigned long address,
+			pud_t *pud, unsigned int flags, get_block_t get_block,
+			dax_iodone_t complete_unwritten)
+{
+	int result;
+	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
+
+	if (flags & FAULT_FLAG_WRITE) {
+		sb_start_pagefault(sb);
+		file_update_time(vma->vm_file);
+	}
+	result = __dax_pud_fault(vma, address, pud, flags, get_block,
+				complete_unwritten);
+	if (flags & FAULT_FLAG_WRITE)
+		sb_end_pagefault(sb);
+
+	return result;
+}
+EXPORT_SYMBOL_GPL(dax_pud_fault);
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 /**
diff --git a/include/linux/dax.h b/include/linux/dax.h
index b415e52..5c74c8e 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -19,6 +19,20 @@ int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
 				unsigned int flags, get_block_t, dax_iodone_t);
 int __dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
 				unsigned int flags, get_block_t, dax_iodone_t);
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+int dax_pud_fault(struct vm_area_struct *, unsigned long addr, pud_t *,
+				unsigned int flags, get_block_t, dax_iodone_t);
+int __dax_pud_fault(struct vm_area_struct *, unsigned long addr, pud_t *,
+				unsigned int flags, get_block_t, dax_iodone_t);
+#else
+static inline int dax_pud_fault(struct vm_area_struct *vma, unsigned long addr,
+				pud_t *pud, unsigned int flags, get_block_t gb,
+				dax_iodone_t di)
+{
+	return VM_FAULT_FALLBACK;
+}
+#define __dax_pud_fault dax_pud_fault
+#endif
 #else
 static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 				pmd_t *pmd, unsigned int flags, get_block_t gb,
@@ -27,6 +41,13 @@ static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	return VM_FAULT_FALLBACK;
 }
 #define __dax_pmd_fault dax_pmd_fault
+static inline int dax_pud_fault(struct vm_area_struct *vma, unsigned long addr,
+				pud_t *pud, unsigned int flags, get_block_t gb,
+				dax_iodone_t di)
+{
+	return VM_FAULT_FALLBACK;
+}
+#define __dax_pud_fault dax_pud_fault
 #endif
 int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
 #define dax_mkwrite(vma, vmf, gb, iod)		dax_fault(vma, vmf, gb, iod)
-- 
2.6.2

[PATCH 6/8] block_dev: Support PUD DAX mappings

[Matthew Wilcox]

From: Matthew Wilcox <willy@linux.intel.com>

Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
 fs/block_dev.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 2d9137e..ed73fdf 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1739,6 +1739,12 @@ static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL);
 }
 
+static int blkdev_dax_pud_fault(struct vm_area_struct *vma, unsigned long addr,
+		pud_t *pud, unsigned int flags)
+{
+	return __dax_pud_fault(vma, addr, pud, flags, blkdev_get_block, NULL);
+}
+
 static void blkdev_vm_open(struct vm_area_struct *vma)
 {
 	struct inode *bd_inode = bdev_file_inode(vma->vm_file);
@@ -1764,6 +1770,7 @@ static const struct vm_operations_struct blkdev_dax_vm_ops = {
 	.close		= blkdev_vm_close,
 	.fault		= blkdev_dax_fault,
 	.pmd_fault	= blkdev_dax_pmd_fault,
+	.pud_fault	= blkdev_dax_pud_fault,
 	.pfn_mkwrite	= blkdev_dax_fault,
 };
 
-- 
2.6.2

[PATCH 7/8] xfs: Support for transparent PUD pages

[Matthew Wilcox]

From: Matthew Wilcox <willy@linux.intel.com>

Call into DAX to provide support for PUD pages, just like the PMD cases.

Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
 fs/xfs/xfs_file.c  | 33 +++++++++++++++++++++++++++++++++
 fs/xfs/xfs_trace.h |  1 +
 2 files changed, 34 insertions(+)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index f5392ab..a81b942 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1600,6 +1600,38 @@ xfs_filemap_pmd_fault(
 	return ret;
 }
 
+STATIC int
+xfs_filemap_pud_fault(
+	struct vm_area_struct	*vma,
+	unsigned long		addr,
+	pud_t			*pud,
+	unsigned int		flags)
+{
+	struct inode		*inode = file_inode(vma->vm_file);
+	struct xfs_inode	*ip = XFS_I(inode);
+	int			ret;
+
+	if (!IS_DAX(inode))
+		return VM_FAULT_FALLBACK;
+
+	trace_xfs_filemap_pud_fault(ip);
+
+	if (flags & FAULT_FLAG_WRITE) {
+		sb_start_pagefault(inode->i_sb);
+		file_update_time(vma->vm_file);
+	}
+
+	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
+	ret = __dax_pud_fault(vma, addr, pud, flags, xfs_get_blocks_dax_fault,
+			      NULL);
+	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
+
+	if (flags & FAULT_FLAG_WRITE)
+		sb_end_pagefault(inode->i_sb);
+
+	return ret;
+}
+
 /*
  * pfn_mkwrite was originally inteneded to ensure we capture time stamp
  * updates on write faults. In reality, it's need to serialise against
@@ -1637,6 +1669,7 @@ xfs_filemap_pfn_mkwrite(
 static const struct vm_operations_struct xfs_file_vm_ops = {
 	.fault		= xfs_filemap_fault,
 	.pmd_fault	= xfs_filemap_pmd_fault,
+	.pud_fault	= xfs_filemap_pud_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= xfs_filemap_page_mkwrite,
 	.pfn_mkwrite	= xfs_filemap_pfn_mkwrite,
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 877079eb..16442bb 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -688,6 +688,7 @@ DEFINE_INODE_EVENT(xfs_inode_free_eofblocks_invalid);
 
 DEFINE_INODE_EVENT(xfs_filemap_fault);
 DEFINE_INODE_EVENT(xfs_filemap_pmd_fault);
+DEFINE_INODE_EVENT(xfs_filemap_pud_fault);
 DEFINE_INODE_EVENT(xfs_filemap_page_mkwrite);
 DEFINE_INODE_EVENT(xfs_filemap_pfn_mkwrite);
 
-- 
2.6.2

Re: [PATCH 7/8] xfs: Support for transparent PUD pages

[Dave Chinner]

On Thu, Dec 24, 2015 at 11:20:36AM -0500, Matthew Wilcox wrote:
> From: Matthew Wilcox <willy@linux.intel.com>
> 
> Call into DAX to provide support for PUD pages, just like the PMD cases.
> 
> Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
> ---
>  fs/xfs/xfs_file.c  | 33 +++++++++++++++++++++++++++++++++
>  fs/xfs/xfs_trace.h |  1 +
>  2 files changed, 34 insertions(+)
> 
> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
> index f5392ab..a81b942 100644
> --- a/fs/xfs/xfs_file.c
> +++ b/fs/xfs/xfs_file.c
> @@ -1600,6 +1600,38 @@ xfs_filemap_pmd_fault(
>  	return ret;
>  }
>  
> +STATIC int
> +xfs_filemap_pud_fault(
> +	struct vm_area_struct	*vma,
> +	unsigned long		addr,
> +	pud_t			*pud,
> +	unsigned int		flags)
> +{
> +	struct inode		*inode = file_inode(vma->vm_file);
> +	struct xfs_inode	*ip = XFS_I(inode);
> +	int			ret;
> +
> +	if (!IS_DAX(inode))
> +		return VM_FAULT_FALLBACK;
> +
> +	trace_xfs_filemap_pud_fault(ip);
> +
> +	if (flags & FAULT_FLAG_WRITE) {
> +		sb_start_pagefault(inode->i_sb);
> +		file_update_time(vma->vm_file);
> +	}
> +
> +	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
> +	ret = __dax_pud_fault(vma, addr, pud, flags, xfs_get_blocks_dax_fault,
> +			      NULL);
> +	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
> +
> +	if (flags & FAULT_FLAG_WRITE)
> +		sb_end_pagefault(inode->i_sb);
> +
> +	return ret;
> +}
> +
>  /*
>   * pfn_mkwrite was originally inteneded to ensure we capture time stamp
>   * updates on write faults. In reality, it's need to serialise against
> @@ -1637,6 +1669,7 @@ xfs_filemap_pfn_mkwrite(
>  static const struct vm_operations_struct xfs_file_vm_ops = {
>  	.fault		= xfs_filemap_fault,
>  	.pmd_fault	= xfs_filemap_pmd_fault,
> +	.pud_fault	= xfs_filemap_pud_fault,

This is getting silly - we now have 3 different page fault handlers
that all do exactly the same thing. Please abstract this so that the
page/pmd/pud is transparent and gets passed through to the generic
handler code that then handles the differences between page/pmd/pud
internally.

This, after all, is the original reason that the ->fault handler was
introduced....

Cheers,

Dave.
-- 
Dave Chinner
david@fromorbit.com

Re: [PATCH 7/8] xfs: Support for transparent PUD pages

[Matthew Wilcox]

On Thu, Dec 31, 2015 at 10:30:27AM +1100, Dave Chinner wrote:
> > @@ -1637,6 +1669,7 @@ xfs_filemap_pfn_mkwrite(
> >  static const struct vm_operations_struct xfs_file_vm_ops = {
> >  	.fault		= xfs_filemap_fault,
> >  	.pmd_fault	= xfs_filemap_pmd_fault,
> > +	.pud_fault	= xfs_filemap_pud_fault,
> 
> This is getting silly - we now have 3 different page fault handlers
> that all do exactly the same thing. Please abstract this so that the
> page/pmd/pud is transparent and gets passed through to the generic
> handler code that then handles the differences between page/pmd/pud
> internally.
> 
> This, after all, is the original reason that the ->fault handler was
> introduced....

I agree that it's silly, but this is the direction I was asked to go in by
the MM people at the last MM summit.  There was agreement that this needs
to be abstracted, but that should be left for a separate cleanup round.
I did prototype something I called a vpte (virtual pte), but that's very
much on the back burner for now.

Re: [PATCH 7/8] xfs: Support for transparent PUD pages

[Dave Chinner]

On Sat, Jan 02, 2016 at 11:43:09AM -0500, Matthew Wilcox wrote:
> On Thu, Dec 31, 2015 at 10:30:27AM +1100, Dave Chinner wrote:
> > > @@ -1637,6 +1669,7 @@ xfs_filemap_pfn_mkwrite(
> > >  static const struct vm_operations_struct xfs_file_vm_ops = {
> > >  	.fault		= xfs_filemap_fault,
> > >  	.pmd_fault	= xfs_filemap_pmd_fault,
> > > +	.pud_fault	= xfs_filemap_pud_fault,
> > 
> > This is getting silly - we now have 3 different page fault handlers
> > that all do exactly the same thing. Please abstract this so that the
> > page/pmd/pud is transparent and gets passed through to the generic
> > handler code that then handles the differences between page/pmd/pud
> > internally.
> > 
> > This, after all, is the original reason that the ->fault handler was
> > introduced....
> 
> I agree that it's silly, but this is the direction I was asked to go in by
> the MM people at the last MM summit.  There was agreement that this needs
> to be abstracted, but that should be left for a separate cleanup round.

Ok, so it's time to abstract it now, before we end up with another
round of broken filesystem code (like the first attempts at the
XFS pmd_fault code).

> I did prototype something I called a vpte (virtual pte), but that's very
> much on the back burner for now.

It's trivial to pack the parameters for pmd_fault and pud_fault
into the struct vm_fault - all you need to do is add pmd_t/pud_t
pointers to the structure, and everything else can be put into
existing members of that structure. There's no need for a "virtual
pte" type anywhere - you can do this effectively with an anonymous
union for the pte/pmd/pud pointer and a flag to indicate the fault
type.

Then in __dax_fault() you can check vmf->flags and call the
appropriate __dax_p{te,md,ud}_fault function, all without the
filesystem having to care about the different fault types. Similar
can be done with filemap_fault() - if it gets pmd/pud fault flags
set it can just reject them as they should never occur right now...

Cheers,

Dave.
-- 
Dave Chinner
david@fromorbit.com

Re: [PATCH 7/8] xfs: Support for transparent PUD pages

[Kirill A. Shutemov]

On Mon, Jan 04, 2016 at 07:33:56AM +1100, Dave Chinner wrote:
> On Sat, Jan 02, 2016 at 11:43:09AM -0500, Matthew Wilcox wrote:
> > On Thu, Dec 31, 2015 at 10:30:27AM +1100, Dave Chinner wrote:
> > > > @@ -1637,6 +1669,7 @@ xfs_filemap_pfn_mkwrite(
> > > >  static const struct vm_operations_struct xfs_file_vm_ops = {
> > > >  	.fault		= xfs_filemap_fault,
> > > >  	.pmd_fault	= xfs_filemap_pmd_fault,
> > > > +	.pud_fault	= xfs_filemap_pud_fault,
> > > 
> > > This is getting silly - we now have 3 different page fault handlers
> > > that all do exactly the same thing. Please abstract this so that the
> > > page/pmd/pud is transparent and gets passed through to the generic
> > > handler code that then handles the differences between page/pmd/pud
> > > internally.
> > > 
> > > This, after all, is the original reason that the ->fault handler was
> > > introduced....
> > 
> > I agree that it's silly, but this is the direction I was asked to go in by
> > the MM people at the last MM summit.  There was agreement that this needs
> > to be abstracted, but that should be left for a separate cleanup round.
> 
> Ok, so it's time to abstract it now, before we end up with another
> round of broken filesystem code (like the first attempts at the
> XFS pmd_fault code).
> 
> > I did prototype something I called a vpte (virtual pte), but that's very
> > much on the back burner for now.
> 
> It's trivial to pack the parameters for pmd_fault and pud_fault
> into the struct vm_fault - all you need to do is add pmd_t/pud_t
> pointers to the structure, and everything else can be put into
> existing members of that structure. There's no need for a "virtual
> pte" type anywhere - you can do this effectively with an anonymous
> union for the pte/pmd/pud pointer and a flag to indicate the fault
> type.
> 
> Then in __dax_fault() you can check vmf->flags and call the
> appropriate __dax_p{te,md,ud}_fault function, all without the
> filesystem having to care about the different fault types. Similar
> can be done with filemap_fault() - if it gets pmd/pud fault flags
> set it can just reject them as they should never occur right now...

I think the first 4 patches of my hugetmpfs RFD patchset[1] are relevant
here. Looks like it shouldn't be a big deal to extend the approach to
cover DAX case.

[1] http://lkml.kernel.org./r/1447889136-6928-1-git-send-email-kirill.shutemov@linux.intel.com
-- 
 Kirill A. Shutemov

Re: [PATCH 7/8] xfs: Support for transparent PUD pages

[Matthew Wilcox]

On Mon, Jan 04, 2016 at 10:41:21PM +0200, Kirill A. Shutemov wrote:
> On Mon, Jan 04, 2016 at 07:33:56AM +1100, Dave Chinner wrote:
> > Then in __dax_fault() you can check vmf->flags and call the
> > appropriate __dax_p{te,md,ud}_fault function, all without the
> > filesystem having to care about the different fault types. Similar
> > can be done with filemap_fault() - if it gets pmd/pud fault flags
> > set it can just reject them as they should never occur right now...
> 
> I think the first 4 patches of my hugetmpfs RFD patchset[1] are relevant
> here. Looks like it shouldn't be a big deal to extend the approach to
> cover DAX case.

Here's what I've currently got.

I can't quite see how to unify the XFS fault & huge_fault handlers yet.
Dave, did you want to do that piece?

DAX now has one dax_fault handler; no __ variations since all callers
were using the __, we can just drop the unused wrappers.

This patch is relative to the patchset I put out before, so there's a lot
of deleting the PUD cases that I had put in.  I'll resplit it for merging.

diff --git a/Documentation/filesystems/dax.txt b/Documentation/filesystems/dax.txt
index 7bde640..7c613fa 100644
--- a/Documentation/filesystems/dax.txt
+++ b/Documentation/filesystems/dax.txt
@@ -49,6 +49,7 @@ These block devices may be used for inspiration:
 - axonram: Axon DDR2 device driver
 - brd: RAM backed block device driver
 - dcssblk: s390 dcss block device driver
+- pmem: NV-DIMM Persistent Memory driver
 
 
 Implementation Tips for Filesystem Writers
@@ -61,9 +62,9 @@ Filesystem support consists of
   dax_do_io() instead of blockdev_direct_IO() if S_DAX is set
 - implementing an mmap file operation for DAX files which sets the
   VM_MIXEDMAP and VM_HUGEPAGE flags on the VMA, and setting the vm_ops to
-  include handlers for fault, pmd_fault and page_mkwrite (which should
-  probably call dax_fault(), dax_pmd_fault() and dax_mkwrite(), passing the
-  appropriate get_block() callback)
+  include handlers for fault, huge_fault and page_mkwrite (which should
+  probably call dax_fault(), and dax_mkwrite(), passing the appropriate
+  get_block() callback)
 - calling dax_truncate_page() instead of block_truncate_page() for DAX files
 - calling dax_zero_page_range() instead of zero_user() for DAX files
 - ensuring that there is sufficient locking between reads, writes,
@@ -77,6 +78,7 @@ or a write()) work correctly.
 These filesystems may be used for inspiration:
 - ext2: the second extended filesystem, see Documentation/filesystems/ext2.txt
 - ext4: the fourth extended filesystem, see Documentation/filesystems/ext4.txt
+- xfs: see Documentation/filesystems/xfs.txt
 
 
 Shortcomings
diff --git a/fs/block_dev.c b/fs/block_dev.c
index ed73fdf..3be3149 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1730,19 +1730,7 @@ static const struct address_space_operations def_blk_aops = {
  */
 static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	return __dax_fault(vma, vmf, blkdev_get_block, NULL);
-}
-
-static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
-		pmd_t *pmd, unsigned int flags)
-{
-	return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL);
-}
-
-static int blkdev_dax_pud_fault(struct vm_area_struct *vma, unsigned long addr,
-		pud_t *pud, unsigned int flags)
-{
-	return __dax_pud_fault(vma, addr, pud, flags, blkdev_get_block, NULL);
+	return dax_fault(vma, vmf, blkdev_get_block, NULL);
 }
 
 static void blkdev_vm_open(struct vm_area_struct *vma)
@@ -1769,8 +1757,7 @@ static const struct vm_operations_struct blkdev_dax_vm_ops = {
 	.open		= blkdev_vm_open,
 	.close		= blkdev_vm_close,
 	.fault		= blkdev_dax_fault,
-	.pmd_fault	= blkdev_dax_pmd_fault,
-	.pud_fault	= blkdev_dax_pud_fault,
+	.huge_fault	= blkdev_dax_fault,
 	.pfn_mkwrite	= blkdev_dax_fault,
 };
 
diff --git a/fs/dax.c b/fs/dax.c
index 63ca298..49bede0 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -370,23 +370,7 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
 	return error;
 }
 
-/**
- * __dax_fault - handle a page fault on a DAX file
- * @vma: The virtual memory area where the fault occurred
- * @vmf: The description of the fault
- * @get_block: The filesystem method used to translate file offsets to blocks
- * @complete_unwritten: The filesystem method used to convert unwritten blocks
- *	to written so the data written to them is exposed. This is required for
- *	required by write faults for filesystems that will return unwritten
- *	extent mappings from @get_block, but it is optional for reads as
- *	dax_insert_mapping() will always zero unwritten blocks. If the fs does
- *	not support unwritten extents, the it should pass NULL.
- *
- * When a page fault occurs, filesystems may call this helper in their
- * fault handler for DAX files. __dax_fault() assumes the caller has done all
- * the necessary locking for the page fault to proceed successfully.
- */
-int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+static int dax_pte_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			get_block_t get_block, dax_iodone_t complete_unwritten)
 {
 	struct file *file = vma->vm_file;
@@ -521,34 +505,6 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	}
 	goto out;
 }
-EXPORT_SYMBOL(__dax_fault);
-
-/**
- * dax_fault - handle a page fault on a DAX file
- * @vma: The virtual memory area where the fault occurred
- * @vmf: The description of the fault
- * @get_block: The filesystem method used to translate file offsets to blocks
- *
- * When a page fault occurs, filesystems may call this helper in their
- * fault handler for DAX files.
- */
-int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
-	      get_block_t get_block, dax_iodone_t complete_unwritten)
-{
-	int result;
-	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
-
-	if (vmf->flags & FAULT_FLAG_WRITE) {
-		sb_start_pagefault(sb);
-		file_update_time(vma->vm_file);
-	}
-	result = __dax_fault(vma, vmf, get_block, complete_unwritten);
-	if (vmf->flags & FAULT_FLAG_WRITE)
-		sb_end_pagefault(sb);
-
-	return result;
-}
-EXPORT_SYMBOL_GPL(dax_fault);
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 /*
@@ -575,7 +531,7 @@ static void __dax_dbg(struct buffer_head *bh, unsigned long address,
 
 #define dax_pmd_dbg(bh, address, reason)	__dax_dbg(bh, address, reason, "dax_pmd")
 
-int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
+static int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		pmd_t *pmd, unsigned int flags, get_block_t get_block,
 		dax_iodone_t complete_unwritten)
 {
@@ -753,36 +709,14 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	result = VM_FAULT_FALLBACK;
 	goto out;
 }
-EXPORT_SYMBOL_GPL(__dax_pmd_fault);
-
-/**
- * dax_pmd_fault - handle a PMD fault on a DAX file
- * @vma: The virtual memory area where the fault occurred
- * @vmf: The description of the fault
- * @get_block: The filesystem method used to translate file offsets to blocks
- *
- * When a page fault occurs, filesystems may call this helper in their
- * pmd_fault handler for DAX files.
- */
-int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
-			pmd_t *pmd, unsigned int flags, get_block_t get_block,
-			dax_iodone_t complete_unwritten)
+#else /* !CONFIG_TRANSPARENT_HUGEPAGE */
+static int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
+		pmd_t *pmd, unsigned int flags, get_block_t get_block,
+		dax_iodone_t complete_unwritten)
 {
-	int result;
-	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
-
-	if (flags & FAULT_FLAG_WRITE) {
-		sb_start_pagefault(sb);
-		file_update_time(vma->vm_file);
-	}
-	result = __dax_pmd_fault(vma, address, pmd, flags, get_block,
-				complete_unwritten);
-	if (flags & FAULT_FLAG_WRITE)
-		sb_end_pagefault(sb);
-
-	return result;
+	return VM_FAULT_FALLBACK;
 }
-EXPORT_SYMBOL_GPL(dax_pmd_fault);
+#endif /* !CONFIG_TRANSPARENT_HUGEPAGE */
 
 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
 /*
@@ -793,7 +727,7 @@ EXPORT_SYMBOL_GPL(dax_pmd_fault);
 
 #define dax_pud_dbg(bh, address, reason)	__dax_dbg(bh, address, reason, "dax_pud")
 
-int __dax_pud_fault(struct vm_area_struct *vma, unsigned long address,
+static int dax_pud_fault(struct vm_area_struct *vma, unsigned long address,
 		pud_t *pud, unsigned int flags, get_block_t get_block,
 		dax_iodone_t complete_unwritten)
 {
@@ -947,38 +881,52 @@ int __dax_pud_fault(struct vm_area_struct *vma, unsigned long address,
 	result = VM_FAULT_FALLBACK;
 	goto out;
 }
-EXPORT_SYMBOL_GPL(__dax_pud_fault);
+#else /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+static int dax_pud_fault(struct vm_area_struct *vma, unsigned long address,
+		pud_t *pud, unsigned int flags, get_block_t get_block,
+		dax_iodone_t complete_unwritten)
+{
+	return VM_FAULT_FALLBACK;
+}
+#endif /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
 
 /**
- * dax_pud_fault - handle a PUD fault on a DAX file
+ * dax_fault - handle a page fault on a DAX file
  * @vma: The virtual memory area where the fault occurred
  * @vmf: The description of the fault
  * @get_block: The filesystem method used to translate file offsets to blocks
+ * @iodone: The filesystem method used to convert unwritten blocks
+ *	to written so the data written to them is exposed. This is required
+ *	by write faults for filesystems that will return unwritten extent
+ *	mappings from @get_block, but it is optional for reads as
+ *	dax_insert_mapping() will always zero unwritten blocks. If the fs
+ *	does not support unwritten extents, then it should pass NULL.
  *
  * When a page fault occurs, filesystems may call this helper in their
- * pud_fault handler for DAX files.
+ * fault handler for DAX files.  dax_fault() assumes the caller has done all
+ * the necessary locking for the page fault to proceed successfully.
  */
-int dax_pud_fault(struct vm_area_struct *vma, unsigned long address,
-			pud_t *pud, unsigned int flags, get_block_t get_block,
-			dax_iodone_t complete_unwritten)
+int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+			get_block_t get_block, dax_iodone_t iodone)
 {
-	int result;
-	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
-
-	if (flags & FAULT_FLAG_WRITE) {
-		sb_start_pagefault(sb);
-		file_update_time(vma->vm_file);
+	unsigned long address = (unsigned long)vmf->virtual_address;
+	switch (vmf->flags & FAULT_FLAG_SIZE_MASK) {
+	case FAULT_FLAG_SIZE_PTE:
+		return dax_pte_fault(vma, vmf, get_block, iodone);
+	case FAULT_FLAG_SIZE_PMD:
+		return dax_pmd_fault(vma, address, vmf->pmd, vmf->flags,
+						get_block, iodone);
+	case FAULT_FLAG_SIZE_PUD:
+		return dax_pud_fault(vma, address, vmf->pud, vmf->flags,
+						get_block, iodone);
+	default:
+		printk(KERN_EMERG "%s: Unknown page size.  Flags %x\n",
+						__func__, vmf->flags);
+		VM_BUG_ON_VMA(1, vma);
+		return VM_FAULT_SIGBUS;
 	}
-	result = __dax_pud_fault(vma, address, pud, flags, get_block,
-				complete_unwritten);
-	if (flags & FAULT_FLAG_WRITE)
-		sb_end_pagefault(sb);
-
-	return result;
 }
-EXPORT_SYMBOL_GPL(dax_pud_fault);
-#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+EXPORT_SYMBOL_GPL(dax_fault);
 
 /**
  * dax_pfn_mkwrite - handle first write to DAX page
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 11a42c5..ad0a57a 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -51,7 +51,7 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	}
 	down_read(&ei->dax_sem);
 
-	ret = __dax_fault(vma, vmf, ext2_get_block, NULL);
+	ret = dax_fault(vma, vmf, ext2_get_block, NULL);
 
 	up_read(&ei->dax_sem);
 	if (vmf->flags & FAULT_FLAG_WRITE)
@@ -59,27 +59,6 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	return ret;
 }
 
-static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
-						pmd_t *pmd, unsigned int flags)
-{
-	struct inode *inode = file_inode(vma->vm_file);
-	struct ext2_inode_info *ei = EXT2_I(inode);
-	int ret;
-
-	if (flags & FAULT_FLAG_WRITE) {
-		sb_start_pagefault(inode->i_sb);
-		file_update_time(vma->vm_file);
-	}
-	down_read(&ei->dax_sem);
-
-	ret = __dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block, NULL);
-
-	up_read(&ei->dax_sem);
-	if (flags & FAULT_FLAG_WRITE)
-		sb_end_pagefault(inode->i_sb);
-	return ret;
-}
-
 static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct inode *inode = file_inode(vma->vm_file);
@@ -90,7 +69,7 @@ static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	file_update_time(vma->vm_file);
 	down_read(&ei->dax_sem);
 
-	ret = __dax_mkwrite(vma, vmf, ext2_get_block, NULL);
+	ret = dax_mkwrite(vma, vmf, ext2_get_block, NULL);
 
 	up_read(&ei->dax_sem);
 	sb_end_pagefault(inode->i_sb);
@@ -121,7 +100,7 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
 
 static const struct vm_operations_struct ext2_dax_vm_ops = {
 	.fault		= ext2_dax_fault,
-	.pmd_fault	= ext2_dax_pmd_fault,
+	.huge_fault	= ext2_dax_fault,
 	.page_mkwrite	= ext2_dax_mkwrite,
 	.pfn_mkwrite	= ext2_dax_pfn_mkwrite,
 };
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index b0cba51..5eda31e 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -202,90 +202,31 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
 
 	if (write) {
-		sb_start_pagefault(sb);
-		file_update_time(vma->vm_file);
-		down_read(&EXT4_I(inode)->i_mmap_sem);
-		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
-						EXT4_DATA_TRANS_BLOCKS(sb));
-	} else
-		down_read(&EXT4_I(inode)->i_mmap_sem);
-
-	if (IS_ERR(handle))
-		result = VM_FAULT_SIGBUS;
-	else
-		result = __dax_fault(vma, vmf, ext4_dax_mmap_get_block, NULL);
-
-	if (write) {
-		if (!IS_ERR(handle))
-			ext4_journal_stop(handle);
-		up_read(&EXT4_I(inode)->i_mmap_sem);
-		sb_end_pagefault(sb);
-	} else
-		up_read(&EXT4_I(inode)->i_mmap_sem);
-
-	return result;
-}
-
-static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
-						pmd_t *pmd, unsigned int flags)
-{
-	int result;
-	handle_t *handle = NULL;
-	struct inode *inode = file_inode(vma->vm_file);
-	struct super_block *sb = inode->i_sb;
-	bool write = flags & FAULT_FLAG_WRITE;
-
-	if (write) {
-		sb_start_pagefault(sb);
-		file_update_time(vma->vm_file);
-		down_read(&EXT4_I(inode)->i_mmap_sem);
-		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
-				ext4_chunk_trans_blocks(inode,
-							PMD_SIZE / PAGE_SIZE));
-	} else
-		down_read(&EXT4_I(inode)->i_mmap_sem);
-
-	if (IS_ERR(handle))
-		result = VM_FAULT_SIGBUS;
-	else
-		result = __dax_pmd_fault(vma, addr, pmd, flags,
-				ext4_dax_mmap_get_block, NULL);
-
-	if (write) {
-		if (!IS_ERR(handle))
-			ext4_journal_stop(handle);
-		up_read(&EXT4_I(inode)->i_mmap_sem);
-		sb_end_pagefault(sb);
-	} else
-		up_read(&EXT4_I(inode)->i_mmap_sem);
-
-	return result;
-}
-
-static int ext4_dax_pud_fault(struct vm_area_struct *vma, unsigned long addr,
-						pud_t *pud, unsigned int flags)
-{
-	int result;
-	handle_t *handle = NULL;
-	struct inode *inode = file_inode(vma->vm_file);
-	struct super_block *sb = inode->i_sb;
-	bool write = flags & FAULT_FLAG_WRITE;
+		unsigned nblocks = EXT4_DATA_TRANS_BLOCKS(sb);
+		switch (vmf->flags & FAULT_FLAG_SIZE_MASK) {
+		case FAULT_FLAG_SIZE_PMD:
+			nblocks = ext4_chunk_trans_blocks(inode,
+							PMD_SIZE / PAGE_SIZE);
+			break;
+		case FAULT_FLAG_SIZE_PUD:
+			nblocks = ext4_chunk_trans_blocks(inode,
+							PUD_SIZE / PAGE_SIZE);
+			break;
+		default:
+			BUG();
+		}
 
-	if (write) {
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
 		down_read(&EXT4_I(inode)->i_mmap_sem);
-		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
-				ext4_chunk_trans_blocks(inode,
-							PMD_SIZE / PAGE_SIZE));
+		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE, nblocks);
 	} else
 		down_read(&EXT4_I(inode)->i_mmap_sem);
 
 	if (IS_ERR(handle))
 		result = VM_FAULT_SIGBUS;
 	else
-		result = __dax_pud_fault(vma, addr, pud, flags,
-				ext4_dax_mmap_get_block, NULL);
+		result = dax_fault(vma, vmf, ext4_dax_mmap_get_block, NULL);
 
 	if (write) {
 		if (!IS_ERR(handle))
@@ -306,7 +247,7 @@ static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	sb_start_pagefault(inode->i_sb);
 	file_update_time(vma->vm_file);
 	down_read(&EXT4_I(inode)->i_mmap_sem);
-	err = __dax_mkwrite(vma, vmf, ext4_dax_mmap_get_block, NULL);
+	err = dax_mkwrite(vma, vmf, ext4_dax_mmap_get_block, NULL);
 	up_read(&EXT4_I(inode)->i_mmap_sem);
 	sb_end_pagefault(inode->i_sb);
 
@@ -344,8 +285,7 @@ static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
 
 static const struct vm_operations_struct ext4_dax_vm_ops = {
 	.fault		= ext4_dax_fault,
-	.pmd_fault	= ext4_dax_pmd_fault,
-	.pud_fault	= ext4_dax_pud_fault,
+	.huge_fault	= ext4_dax_fault,
 	.page_mkwrite	= ext4_dax_mkwrite,
 	.pfn_mkwrite	= ext4_dax_pfn_mkwrite,
 };
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a81b942..142f144 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1519,7 +1519,7 @@ xfs_filemap_page_mkwrite(
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (IS_DAX(inode)) {
-		ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault, NULL);
+		ret = dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault, NULL);
 	} else {
 		ret = block_page_mkwrite(vma, vmf, xfs_get_blocks);
 		ret = block_page_mkwrite_return(ret);
@@ -1553,7 +1553,7 @@ xfs_filemap_fault(
 		 * changes to xfs_get_blocks_direct() to map unwritten extent
 		 * ioend for conversion on read-only mappings.
 		 */
-		ret = __dax_fault(vma, vmf, xfs_get_blocks_dax_fault, NULL);
+		ret = dax_fault(vma, vmf, xfs_get_blocks_dax_fault, NULL);
 	} else
 		ret = filemap_fault(vma, vmf);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
@@ -1564,48 +1564,14 @@ xfs_filemap_fault(
 /*
  * Similar to xfs_filemap_fault(), the DAX fault path can call into here on
  * both read and write faults. Hence we need to handle both cases. There is no
- * ->pmd_mkwrite callout for huge pages, so we have a single function here to
+ * ->huge_mkwrite callout for huge pages, so we have a single function here to
  * handle both cases here. @flags carries the information on the type of fault
  * occuring.
  */
 STATIC int
-xfs_filemap_pmd_fault(
+xfs_filemap_huge_fault(
 	struct vm_area_struct	*vma,
-	unsigned long		addr,
-	pmd_t			*pmd,
-	unsigned int		flags)
-{
-	struct inode		*inode = file_inode(vma->vm_file);
-	struct xfs_inode	*ip = XFS_I(inode);
-	int			ret;
-
-	if (!IS_DAX(inode))
-		return VM_FAULT_FALLBACK;
-
-	trace_xfs_filemap_pmd_fault(ip);
-
-	if (flags & FAULT_FLAG_WRITE) {
-		sb_start_pagefault(inode->i_sb);
-		file_update_time(vma->vm_file);
-	}
-
-	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault,
-			      NULL);
-	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-
-	if (flags & FAULT_FLAG_WRITE)
-		sb_end_pagefault(inode->i_sb);
-
-	return ret;
-}
-
-STATIC int
-xfs_filemap_pud_fault(
-	struct vm_area_struct	*vma,
-	unsigned long		addr,
-	pud_t			*pud,
-	unsigned int		flags)
+	struct vm_fault		*vmf)
 {
 	struct inode		*inode = file_inode(vma->vm_file);
 	struct xfs_inode	*ip = XFS_I(inode);
@@ -1614,19 +1580,18 @@ xfs_filemap_pud_fault(
 	if (!IS_DAX(inode))
 		return VM_FAULT_FALLBACK;
 
-	trace_xfs_filemap_pud_fault(ip);
+	trace_xfs_filemap_huge_fault(ip);
 
-	if (flags & FAULT_FLAG_WRITE) {
+	if (vmf->flags & FAULT_FLAG_WRITE) {
 		sb_start_pagefault(inode->i_sb);
 		file_update_time(vma->vm_file);
 	}
 
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	ret = __dax_pud_fault(vma, addr, pud, flags, xfs_get_blocks_dax_fault,
-			      NULL);
+	ret = dax_fault(vma, vmf, xfs_get_blocks_dax_fault, NULL);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
-	if (flags & FAULT_FLAG_WRITE)
+	if (vmf->flags & FAULT_FLAG_WRITE)
 		sb_end_pagefault(inode->i_sb);
 
 	return ret;
@@ -1668,8 +1633,7 @@ xfs_filemap_pfn_mkwrite(
 
 static const struct vm_operations_struct xfs_file_vm_ops = {
 	.fault		= xfs_filemap_fault,
-	.pmd_fault	= xfs_filemap_pmd_fault,
-	.pud_fault	= xfs_filemap_pud_fault,
+	.huge_fault	= xfs_filemap_huge_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= xfs_filemap_page_mkwrite,
 	.pfn_mkwrite	= xfs_filemap_pfn_mkwrite,
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 16442bb..8f810db 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -687,8 +687,7 @@ DEFINE_INODE_EVENT(xfs_inode_clear_eofblocks_tag);
 DEFINE_INODE_EVENT(xfs_inode_free_eofblocks_invalid);
 
 DEFINE_INODE_EVENT(xfs_filemap_fault);
-DEFINE_INODE_EVENT(xfs_filemap_pmd_fault);
-DEFINE_INODE_EVENT(xfs_filemap_pud_fault);
+DEFINE_INODE_EVENT(xfs_filemap_huge_fault);
 DEFINE_INODE_EVENT(xfs_filemap_page_mkwrite);
 DEFINE_INODE_EVENT(xfs_filemap_pfn_mkwrite);
 
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 5c74c8e..8b5000a 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -12,46 +12,8 @@ int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
 int dax_truncate_page(struct inode *, loff_t from, get_block_t);
 int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
 		dax_iodone_t);
-int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
-		dax_iodone_t);
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
-				unsigned int flags, get_block_t, dax_iodone_t);
-int __dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
-				unsigned int flags, get_block_t, dax_iodone_t);
-#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
-int dax_pud_fault(struct vm_area_struct *, unsigned long addr, pud_t *,
-				unsigned int flags, get_block_t, dax_iodone_t);
-int __dax_pud_fault(struct vm_area_struct *, unsigned long addr, pud_t *,
-				unsigned int flags, get_block_t, dax_iodone_t);
-#else
-static inline int dax_pud_fault(struct vm_area_struct *vma, unsigned long addr,
-				pud_t *pud, unsigned int flags, get_block_t gb,
-				dax_iodone_t di)
-{
-	return VM_FAULT_FALLBACK;
-}
-#define __dax_pud_fault dax_pud_fault
-#endif
-#else
-static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
-				pmd_t *pmd, unsigned int flags, get_block_t gb,
-				dax_iodone_t di)
-{
-	return VM_FAULT_FALLBACK;
-}
-#define __dax_pmd_fault dax_pmd_fault
-static inline int dax_pud_fault(struct vm_area_struct *vma, unsigned long addr,
-				pud_t *pud, unsigned int flags, get_block_t gb,
-				dax_iodone_t di)
-{
-	return VM_FAULT_FALLBACK;
-}
-#define __dax_pud_fault dax_pud_fault
-#endif
 int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
-#define dax_mkwrite(vma, vmf, gb, iod)		dax_fault(vma, vmf, gb, iod)
-#define __dax_mkwrite(vma, vmf, gb, iod)	__dax_fault(vma, vmf, gb, iod)
+#define dax_mkwrite(vma, vmf, gb, iod)	dax_fault(vma, vmf, gb, iod)
 
 static inline bool vma_is_dax(struct vm_area_struct *vma)
 {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index e14634f..e63780b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -233,15 +233,21 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_TRIED	0x20	/* Second try */
 #define FAULT_FLAG_USER		0x40	/* The fault originated in userspace */
 
+#define FAULT_FLAG_SIZE_MASK	0x700	/* Support up to 8-level page tables */
+#define FAULT_FLAG_SIZE_PTE	0x000	/* First level (eg 4k) */
+#define FAULT_FLAG_SIZE_PMD	0x100	/* Second level (eg 2MB) */
+#define FAULT_FLAG_SIZE_PUD	0x200	/* Third level (eg 1GB) */
+#define FAULT_FLAG_SIZE_PGD	0x300	/* Fourth level (eg 512GB) */
+
 /*
- * vm_fault is filled by the the pagefault handler and passed to the vma's
+ * vm_fault is filled in by the pagefault handler and passed to the vma's
  * ->fault function. The vma's ->fault is responsible for returning a bitmask
  * of VM_FAULT_xxx flags that give details about how the fault was handled.
  *
  * MM layer fills up gfp_mask for page allocations but fault handler might
  * alter it if its implementation requires a different allocation context.
  *
- * pgoff should be used in favour of virtual_address, if possible.
+ * pgoff should be used instead of virtual_address, if possible.
  */
 struct vm_fault {
 	unsigned int flags;		/* FAULT_FLAG_xxx flags */
@@ -258,7 +264,11 @@ struct vm_fault {
 	/* for ->map_pages() only */
 	pgoff_t max_pgoff;		/* map pages for offset from pgoff till
 					 * max_pgoff inclusive */
-	pte_t *pte;			/* pte entry associated with ->pgoff */
+	union {
+		pte_t *pte;		/* pte entry associated with ->pgoff */
+		pmd_t *pmd;
+		pud_t *pud;
+	};
 };
 
 /*
@@ -271,10 +281,7 @@ struct vm_operations_struct {
 	void (*close)(struct vm_area_struct * area);
 	int (*mremap)(struct vm_area_struct * area);
 	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
-	int (*pmd_fault)(struct vm_area_struct *, unsigned long address,
-						pmd_t *, unsigned int flags);
-	int (*pud_fault)(struct vm_area_struct *, unsigned long address,
-						pud_t *, unsigned int flags);
+	int (*huge_fault)(struct vm_area_struct *, struct vm_fault *vmf);
 	void (*map_pages)(struct vm_area_struct *vma, struct vm_fault *vmf);
 
 	/* notification that a previously read-only page is about to become
diff --git a/mm/memory.c b/mm/memory.c
index 7328df0..9382f92 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3264,10 +3264,16 @@ out:
 static int create_huge_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pmd_t *pmd, unsigned int flags)
 {
+	struct vm_fault vmf = {
+		.virtual_address = (void __user *)address,
+		.flags = flags | FAULT_FLAG_SIZE_PUD,
+		.pmd = pmd,
+	};
+
 	if (vma_is_anonymous(vma))
 		return do_huge_pmd_anonymous_page(mm, vma, address, pmd, flags);
-	if (vma->vm_ops->pmd_fault)
-		return vma->vm_ops->pmd_fault(vma, address, pmd, flags);
+	if (vma->vm_ops->huge_fault)
+		return vma->vm_ops->huge_fault(vma, &vmf);
 	return VM_FAULT_FALLBACK;
 }
 
@@ -3275,21 +3281,33 @@ static int wp_huge_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pmd_t *pmd, pmd_t orig_pmd,
 			unsigned int flags)
 {
+	struct vm_fault vmf = {
+		.virtual_address = (void __user *)address,
+		.flags = flags | FAULT_FLAG_SIZE_PUD,
+		.pmd = pmd,
+	};
+
 	if (vma_is_anonymous(vma))
 		return do_huge_pmd_wp_page(mm, vma, address, pmd, orig_pmd);
-	if (vma->vm_ops->pmd_fault)
-		return vma->vm_ops->pmd_fault(vma, address, pmd, flags);
+	if (vma->vm_ops->huge_fault)
+		return vma->vm_ops->huge_fault(vma, &vmf);
 	return VM_FAULT_FALLBACK;
 }
 
 static int create_huge_pud(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pud_t *pud, unsigned int flags)
 {
+	struct vm_fault vmf = {
+		.virtual_address = (void __user *)address,
+		.flags = flags | FAULT_FLAG_SIZE_PUD,
+		.pud = pud,
+	};
+
 	/* No support for anonymous transparent PUD pages yet */
 	if (vma_is_anonymous(vma))
 		return VM_FAULT_FALLBACK;
-	if (vma->vm_ops->pud_fault)
-		return vma->vm_ops->pud_fault(vma, address, pud, flags);
+	if (vma->vm_ops->huge_fault)
+		return vma->vm_ops->huge_fault(vma, &vmf);
 	return VM_FAULT_FALLBACK;
 }
 
@@ -3297,11 +3315,17 @@ static int wp_huge_pud(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pud_t *pud, pud_t orig_pud,
 			unsigned int flags)
 {
+	struct vm_fault vmf = {
+		.virtual_address = (void __user *)address,
+		.flags = flags | FAULT_FLAG_SIZE_PUD,
+		.pud = pud,
+	};
+
 	/* No support for anonymous transparent PUD pages yet */
 	if (vma_is_anonymous(vma))
 		return VM_FAULT_FALLBACK;
-	if (vma->vm_ops->pud_fault)
-		return vma->vm_ops->pud_fault(vma, address, pud, flags);
+	if (vma->vm_ops->huge_fault)
+		return vma->vm_ops->huge_fault(vma, &vmf);
 	return VM_FAULT_FALLBACK;
 }
 

[PATCH 8/8] ext4: Transparent support for PUD-sized transparent huge pages

[Matthew Wilcox]

From: Matthew Wilcox <willy@linux.intel.com>

Call into DAX to provide support for PUD pages, just like the PMD cases.

Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
---
 fs/ext4/file.c | 37 +++++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 60683ab..b0cba51 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -262,6 +262,42 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	return result;
 }
 
+static int ext4_dax_pud_fault(struct vm_area_struct *vma, unsigned long addr,
+						pud_t *pud, unsigned int flags)
+{
+	int result;
+	handle_t *handle = NULL;
+	struct inode *inode = file_inode(vma->vm_file);
+	struct super_block *sb = inode->i_sb;
+	bool write = flags & FAULT_FLAG_WRITE;
+
+	if (write) {
+		sb_start_pagefault(sb);
+		file_update_time(vma->vm_file);
+		down_read(&EXT4_I(inode)->i_mmap_sem);
+		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
+				ext4_chunk_trans_blocks(inode,
+							PMD_SIZE / PAGE_SIZE));
+	} else
+		down_read(&EXT4_I(inode)->i_mmap_sem);
+
+	if (IS_ERR(handle))
+		result = VM_FAULT_SIGBUS;
+	else
+		result = __dax_pud_fault(vma, addr, pud, flags,
+				ext4_dax_mmap_get_block, NULL);
+
+	if (write) {
+		if (!IS_ERR(handle))
+			ext4_journal_stop(handle);
+		up_read(&EXT4_I(inode)->i_mmap_sem);
+		sb_end_pagefault(sb);
+	} else
+		up_read(&EXT4_I(inode)->i_mmap_sem);
+
+	return result;
+}
+
 static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	int err;
@@ -309,6 +345,7 @@ static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
 static const struct vm_operations_struct ext4_dax_vm_ops = {
 	.fault		= ext4_dax_fault,
 	.pmd_fault	= ext4_dax_pmd_fault,
+	.pud_fault	= ext4_dax_pud_fault,
 	.page_mkwrite	= ext4_dax_mkwrite,
 	.pfn_mkwrite	= ext4_dax_pfn_mkwrite,
 };
-- 
2.6.2