mm, x86: add support for PUD-sized transparent hugepages

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.  x86 support code also added.

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.

[dave.jiang@intel.com: fix SMP x86 32bit build for native_pud_clear()]
  Link: http://lkml.kernel.org/r/148719066814.31111.3239231168815337012.stgit@djiang5-desk3.ch.intel.com
[dave.jiang@intel.com: native_pud_clear missing on i386 build]
  Link: http://lkml.kernel.org/r/148640375195.69754.3315433724330910314.stgit@djiang5-desk3.ch.intel.com
Link: http://lkml.kernel.org/r/148545059381.17912.8602162635537598445.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 90 insertions, 4 deletions

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 18af2bcefe6a..a0aba0f9c57b 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 +141,40 @@ 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 +211,9 @@ 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
@@ -208,6 +241,23 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
+#ifndef __HAVE_ARCH_PUDP_SET_WRPROTECT
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+static inline void pudp_set_wrprotect(struct mm_struct *mm,
+				      unsigned long address, pud_t *pudp)
+{
+	pud_t old_pud = *pudp;
+
+	set_pud_at(mm, address, pudp, pud_wrprotect(old_pud));
+}
+#else
+static inline void pudp_set_wrprotect(struct mm_struct *mm,
+				      unsigned long address, pud_t *pudp)
+{
+	BUILD_BUG();
+}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+#endif
 
 #ifndef pmdp_collapse_flush
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -273,12 +323,23 @@ 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
 
@@ -640,6 +701,15 @@ static inline int pmd_write(pmd_t pmd)
 #endif /* __HAVE_ARCH_PMD_WRITE */
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+#if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \
+	(defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
+	 !defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD))
+static inline int pud_trans_huge(pud_t pud)
+{
+	return 0;
+}
+#endif
+
 #ifndef pmd_read_atomic
 static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
 {
@@ -785,8 +855,10 @@ static inline int pmd_clear_huge(pmd_t *pmd)
  * 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)
 #else
 #define flush_pmd_tlb_range(vma, addr, end)	BUILD_BUG()
+#define flush_pud_tlb_range(vma, addr, end)	BUILD_BUG()
 #endif
 #endif
 
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 7eed8cf3130a..4329bc6ef04b 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -232,6 +232,20 @@ static inline void tlb_remove_check_page_size_change(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, HPAGE_PUD_SIZE);	\
+		__tlb_remove_pud_tlb_entry(tlb, pudp, address);		\
+	} while (0)
+
 /*
  * For things like page tables caches (ie caching addresses "inside" the
  * page tables, like x86 does), for legacy reasons, flushing an