[PATCH 0/4] pgtable bytes mis-accounting v3

[PATCH 0/4] pgtable bytes mis-accounting v3

[Martin Schwidefsky]

Greetings,

version #3 of the fix for the pgtable_bytes mis-accounting problem
on s390. Three times is a charm..

Changes v2 -> v3:

 - Add a fourth patch to redefine __PAGETABLE_PxD_FOLDED as non-empty

 - Move mm_pxd_folded() to include/asm-generic/pgtable.h and use
    __is_defined() again with the redefined __PAGETABLE_PxD_FOLDED

 - Add a missing mm_inc_nr_puds() in arch/s390/mm/pgalloc.c

Changes v1 -> v2:

 - Split the patch into three parts, one patch to add the mm_pxd_folded
    helpers, one patch to use to the helpers in mm_[dec|inc]_nr_[pmds|puds]
       and finally the fix for s390.

 - Drop the use of __is_defined, it does not work with the
    __PAGETABLE_PxD_FOLDED defines

 - Do not change the basic #ifdef'ery in mm.h, just add the calls
    to mm_pxd_folded to the pgtable_bytes accounting functions. This
       fixes the compile error on alpha (and potentially on other archs).

Martin Schwidefsky (4):
  mm: make the __PAGETABLE_PxD_FOLDED defines non-empty
  mm: introduce mm_[p4d|pud|pmd]_folded
  mm: add mm_pxd_folded checks to pgtable_bytes accounting functions
  s390/mm: fix mis-accounting of pgtable_bytes

 arch/arm/include/asm/pgtable-2level.h    |  2 +-
 arch/m68k/include/asm/pgtable_mm.h       |  4 ++--
 arch/microblaze/include/asm/pgtable.h    |  2 +-
 arch/nds32/include/asm/pgtable.h         |  2 +-
 arch/parisc/include/asm/pgtable.h        |  2 +-
 arch/s390/include/asm/mmu_context.h      |  5 -----
 arch/s390/include/asm/pgalloc.h          |  6 +++---
 arch/s390/include/asm/pgtable.h          | 18 ++++++++++++++++++
 arch/s390/include/asm/tlb.h              |  6 +++---
 arch/s390/mm/pgalloc.c                   |  1 +
 include/asm-generic/4level-fixup.h       |  2 +-
 include/asm-generic/5level-fixup.h       |  2 +-
 include/asm-generic/pgtable-nop4d-hack.h |  2 +-
 include/asm-generic/pgtable-nop4d.h      |  2 +-
 include/asm-generic/pgtable-nopmd.h      |  2 +-
 include/asm-generic/pgtable-nopud.h      |  2 +-
 include/asm-generic/pgtable.h            | 16 ++++++++++++++++
 include/linux/mm.h                       |  8 ++++++++
 18 files changed, 61 insertions(+), 23 deletions(-)

-- 
2.7.4

[PATCH 1/4] mm: make the __PAGETABLE_PxD_FOLDED defines non-empty

[Martin Schwidefsky]

Change the currently empty defines for __PAGETABLE_PMD_FOLDED,
__PAGETABLE_PUD_FOLDED and __PAGETABLE_P4D_FOLDED to return 1.
This makes it possible to use __is_defined() to test if the
preprocessor define exists.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/arm/include/asm/pgtable-2level.h    | 2 +-
 arch/m68k/include/asm/pgtable_mm.h       | 4 ++--
 arch/microblaze/include/asm/pgtable.h    | 2 +-
 arch/nds32/include/asm/pgtable.h         | 2 +-
 arch/parisc/include/asm/pgtable.h        | 2 +-
 include/asm-generic/4level-fixup.h       | 2 +-
 include/asm-generic/5level-fixup.h       | 2 +-
 include/asm-generic/pgtable-nop4d-hack.h | 2 +-
 include/asm-generic/pgtable-nop4d.h      | 2 +-
 include/asm-generic/pgtable-nopmd.h      | 2 +-
 include/asm-generic/pgtable-nopud.h      | 2 +-
 11 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index 92fd2c8..12659ce 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -10,7 +10,7 @@
 #ifndef _ASM_PGTABLE_2LEVEL_H
 #define _ASM_PGTABLE_2LEVEL_H
 
-#define __PAGETABLE_PMD_FOLDED
+#define __PAGETABLE_PMD_FOLDED 1
 
 /*
  * Hardware-wise, we have a two level page table structure, where the first
diff --git a/arch/m68k/include/asm/pgtable_mm.h b/arch/m68k/include/asm/pgtable_mm.h
index 6181e41..fe3ddd7 100644
--- a/arch/m68k/include/asm/pgtable_mm.h
+++ b/arch/m68k/include/asm/pgtable_mm.h
@@ -55,12 +55,12 @@
  */
 #ifdef CONFIG_SUN3
 #define PTRS_PER_PTE   16
-#define __PAGETABLE_PMD_FOLDED
+#define __PAGETABLE_PMD_FOLDED 1
 #define PTRS_PER_PMD   1
 #define PTRS_PER_PGD   2048
 #elif defined(CONFIG_COLDFIRE)
 #define PTRS_PER_PTE	512
-#define __PAGETABLE_PMD_FOLDED
+#define __PAGETABLE_PMD_FOLDED 1
 #define PTRS_PER_PMD	1
 #define PTRS_PER_PGD	1024
 #else
diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h
index f64ebb9..e14b662 100644
--- a/arch/microblaze/include/asm/pgtable.h
+++ b/arch/microblaze/include/asm/pgtable.h
@@ -63,7 +63,7 @@ extern int mem_init_done;
 
 #include <asm-generic/4level-fixup.h>
 
-#define __PAGETABLE_PMD_FOLDED
+#define __PAGETABLE_PMD_FOLDED 1
 
 #ifdef __KERNEL__
 #ifndef __ASSEMBLY__
diff --git a/arch/nds32/include/asm/pgtable.h b/arch/nds32/include/asm/pgtable.h
index d3e19a5..9f52db9 100644
--- a/arch/nds32/include/asm/pgtable.h
+++ b/arch/nds32/include/asm/pgtable.h
@@ -4,7 +4,7 @@
 #ifndef _ASMNDS32_PGTABLE_H
 #define _ASMNDS32_PGTABLE_H
 
-#define __PAGETABLE_PMD_FOLDED
+#define __PAGETABLE_PMD_FOLDED 1
 #include <asm-generic/4level-fixup.h>
 #include <asm-generic/sizes.h>
 
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index b941ac7..c7bb74e 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -111,7 +111,7 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
 #if CONFIG_PGTABLE_LEVELS == 3
 #define BITS_PER_PMD	(PAGE_SHIFT + PMD_ORDER - BITS_PER_PMD_ENTRY)
 #else
-#define __PAGETABLE_PMD_FOLDED
+#define __PAGETABLE_PMD_FOLDED 1
 #define BITS_PER_PMD	0
 #endif
 #define PTRS_PER_PMD    (1UL << BITS_PER_PMD)
diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h
index 89f3b03..e3667c9 100644
--- a/include/asm-generic/4level-fixup.h
+++ b/include/asm-generic/4level-fixup.h
@@ -3,7 +3,7 @@
 #define _4LEVEL_FIXUP_H
 
 #define __ARCH_HAS_4LEVEL_HACK
-#define __PAGETABLE_PUD_FOLDED
+#define __PAGETABLE_PUD_FOLDED 1
 
 #define PUD_SHIFT			PGDIR_SHIFT
 #define PUD_SIZE			PGDIR_SIZE
diff --git a/include/asm-generic/5level-fixup.h b/include/asm-generic/5level-fixup.h
index 9c2e070..73474bb 100644
--- a/include/asm-generic/5level-fixup.h
+++ b/include/asm-generic/5level-fixup.h
@@ -3,7 +3,7 @@
 #define _5LEVEL_FIXUP_H
 
 #define __ARCH_HAS_5LEVEL_HACK
-#define __PAGETABLE_P4D_FOLDED
+#define __PAGETABLE_P4D_FOLDED 1
 
 #define P4D_SHIFT			PGDIR_SHIFT
 #define P4D_SIZE			PGDIR_SIZE
diff --git a/include/asm-generic/pgtable-nop4d-hack.h b/include/asm-generic/pgtable-nop4d-hack.h
index 0c34215..1d6dd38 100644
--- a/include/asm-generic/pgtable-nop4d-hack.h
+++ b/include/asm-generic/pgtable-nop4d-hack.h
@@ -5,7 +5,7 @@
 #ifndef __ASSEMBLY__
 #include <asm-generic/5level-fixup.h>
 
-#define __PAGETABLE_PUD_FOLDED
+#define __PAGETABLE_PUD_FOLDED 1
 
 /*
  * Having the pud type consist of a pgd gets the size right, and allows
diff --git a/include/asm-generic/pgtable-nop4d.h b/include/asm-generic/pgtable-nop4d.h
index 1a29b2a..04cb913 100644
--- a/include/asm-generic/pgtable-nop4d.h
+++ b/include/asm-generic/pgtable-nop4d.h
@@ -4,7 +4,7 @@
 
 #ifndef __ASSEMBLY__
 
-#define __PAGETABLE_P4D_FOLDED
+#define __PAGETABLE_P4D_FOLDED 1
 
 typedef struct { pgd_t pgd; } p4d_t;
 
diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h
index f35f6e8..b85b827 100644
--- a/include/asm-generic/pgtable-nopmd.h
+++ b/include/asm-generic/pgtable-nopmd.h
@@ -8,7 +8,7 @@
 
 struct mm_struct;
 
-#define __PAGETABLE_PMD_FOLDED
+#define __PAGETABLE_PMD_FOLDED 1
 
 /*
  * Having the pmd type consist of a pud gets the size right, and allows
diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h
index e950b9c..9bef475 100644
--- a/include/asm-generic/pgtable-nopud.h
+++ b/include/asm-generic/pgtable-nopud.h
@@ -9,7 +9,7 @@
 #else
 #include <asm-generic/pgtable-nop4d.h>
 
-#define __PAGETABLE_PUD_FOLDED
+#define __PAGETABLE_PUD_FOLDED 1
 
 /*
  * Having the pud type consist of a p4d gets the size right, and allows
-- 
2.7.4

[PATCH 2/4] mm: introduce mm_[p4d|pud|pmd]_folded

[Martin Schwidefsky]

Add three architecture overrideable functions to test if the
p4d, pud, or pmd layer of a page table is folded or not.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 include/asm-generic/pgtable.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 5657a20..359fb93 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -1127,4 +1127,20 @@ static inline bool arch_has_pfn_modify_check(void)
 #endif
 #endif
 
+/*
+ * On some architectures it depends on the mm if the p4d/pud or pmd
+ * layer of the page table hierarchy is folded or not.
+ */
+#ifndef mm_p4d_folded
+#define mm_p4d_folded(mm)	__is_defined(__PAGETABLE_P4D_FOLDED)
+#endif
+
+#ifndef mm_pud_folded
+#define mm_pud_folded(mm)	__is_defined(__PAGETABLE_PUD_FOLDED)
+#endif
+
+#ifndef mm_pmd_folded
+#define mm_pmd_folded(mm)	__is_defined(__PAGETABLE_PMD_FOLDED)
+#endif
+
 #endif /* _ASM_GENERIC_PGTABLE_H */
-- 
2.7.4

[PATCH 3/4] mm: add mm_pxd_folded checks to pgtable_bytes accounting functions

[Martin Schwidefsky]

The common mm code calls mm_dec_nr_pmds() and mm_dec_nr_puds()
in free_pgtables() if the address range spans a full pud or pmd.
If mm_dec_nr_puds/mm_dec_nr_pmds are non-empty due to configuration
settings they blindly subtract the size of the pmd or pud table from
pgtable_bytes even if the pud or pmd page table layer is folded.

Add explicit mm_[pmd|pud]_folded checks to the four pgtable_bytes
accounting functions mm_inc_nr_puds, mm_inc_nr_pmds, mm_dec_nr_puds
and mm_dec_nr_pmds. As the check for folded page tables can be
overwritten by the architecture, this allows to keep a correct
pgtable_bytes value for platforms that use a dynamic number of
page table levels.

Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 include/linux/mm.h | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1e52b8f..844a853 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1744,11 +1744,15 @@ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address);
 
 static inline void mm_inc_nr_puds(struct mm_struct *mm)
 {
+	if (mm_pud_folded(mm))
+		return;
 	atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes);
 }
 
 static inline void mm_dec_nr_puds(struct mm_struct *mm)
 {
+	if (mm_pud_folded(mm))
+		return;
 	atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes);
 }
 #endif
@@ -1768,11 +1772,15 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);
 
 static inline void mm_inc_nr_pmds(struct mm_struct *mm)
 {
+	if (mm_pmd_folded(mm))
+		return;
 	atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes);
 }
 
 static inline void mm_dec_nr_pmds(struct mm_struct *mm)
 {
+	if (mm_pmd_folded(mm))
+		return;
 	atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes);
 }
 #endif
-- 
2.7.4

[PATCH 4/4] s390/mm: fix mis-accounting of pgtable_bytes

[Martin Schwidefsky]

In case a fork or a clone system fails in copy_process and the error
handling does the mmput() at the bad_fork_cleanup_mm label, the
following warning messages will appear on the console:

  BUG: non-zero pgtables_bytes on freeing mm: 16384

The reason for that is the tricks we play with mm_inc_nr_puds() and
mm_inc_nr_pmds() in init_new_context().

A normal 64-bit process has 3 levels of page table, the p4d level and
the pud level are folded. On process termination the free_pud_range()
function in mm/memory.c will subtract 16KB from pgtable_bytes with a
mm_dec_nr_puds() call, but there actually is not really a pud table.

One issue with this is the fact that pgtable_bytes is usually off
by a few kilobytes, but the more severe problem is that for a failed
fork or clone the free_pgtables() function is not called. In this case
there is no mm_dec_nr_puds() or mm_dec_nr_pmds() that go together with
the mm_inc_nr_puds() and mm_inc_nr_pmds in init_new_context().
The pgtable_bytes will be off by 16384 or 32768 bytes and we get the
BUG message. The message itself is purely cosmetic, but annoying.

To fix this override the mm_pmd_folded, mm_pud_folded and mm_p4d_folded
function to check for the true size of the address space.

Reported-by: Li Wang <liwang@redhat.com>
Tested-by: Li Wang <liwang@redhat.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/mmu_context.h |  5 -----
 arch/s390/include/asm/pgalloc.h     |  6 +++---
 arch/s390/include/asm/pgtable.h     | 18 ++++++++++++++++++
 arch/s390/include/asm/tlb.h         |  6 +++---
 arch/s390/mm/pgalloc.c              |  1 +
 5 files changed, 25 insertions(+), 11 deletions(-)

diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index dbd689d..ccbb53e 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -46,8 +46,6 @@ static inline int init_new_context(struct task_struct *tsk,
 		mm->context.asce_limit = STACK_TOP_MAX;
 		mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
 				   _ASCE_USER_BITS | _ASCE_TYPE_REGION3;
-		/* pgd_alloc() did not account this pud */
-		mm_inc_nr_puds(mm);
 		break;
 	case -PAGE_SIZE:
 		/* forked 5-level task, set new asce with new_mm->pgd */
@@ -63,9 +61,6 @@ static inline int init_new_context(struct task_struct *tsk,
 		/* forked 2-level compat task, set new asce with new mm->pgd */
 		mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
 				   _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT;
-		/* pgd_alloc() did not account this pmd */
-		mm_inc_nr_pmds(mm);
-		mm_inc_nr_puds(mm);
 	}
 	crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
 	return 0;
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index f0f9bcf..5ee7337 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -36,11 +36,11 @@ static inline void crst_table_init(unsigned long *crst, unsigned long entry)
 
 static inline unsigned long pgd_entry_type(struct mm_struct *mm)
 {
-	if (mm->context.asce_limit <= _REGION3_SIZE)
+	if (mm_pmd_folded(mm))
 		return _SEGMENT_ENTRY_EMPTY;
-	if (mm->context.asce_limit <= _REGION2_SIZE)
+	if (mm_pud_folded(mm))
 		return _REGION3_ENTRY_EMPTY;
-	if (mm->context.asce_limit <= _REGION1_SIZE)
+	if (mm_p4d_folded(mm))
 		return _REGION2_ENTRY_EMPTY;
 	return _REGION1_ENTRY_EMPTY;
 }
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 411d435..0637324 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -493,6 +493,24 @@ static inline int is_module_addr(void *addr)
 				   _REGION_ENTRY_PROTECT | \
 				   _REGION_ENTRY_NOEXEC)
 
+static inline bool mm_p4d_folded(struct mm_struct *mm)
+{
+	return mm->context.asce_limit <= _REGION1_SIZE;
+}
+#define mm_p4d_folded(mm) mm_p4d_folded(mm)
+
+static inline bool mm_pud_folded(struct mm_struct *mm)
+{
+	return mm->context.asce_limit <= _REGION2_SIZE;
+}
+#define mm_pud_folded(mm) mm_pud_folded(mm)
+
+static inline bool mm_pmd_folded(struct mm_struct *mm)
+{
+	return mm->context.asce_limit <= _REGION3_SIZE;
+}
+#define mm_pmd_folded(mm) mm_pmd_folded(mm)
+
 static inline int mm_has_pgste(struct mm_struct *mm)
 {
 #ifdef CONFIG_PGSTE
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 457b7ba..b31c779 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -136,7 +136,7 @@ static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 				unsigned long address)
 {
-	if (tlb->mm->context.asce_limit <= _REGION3_SIZE)
+	if (mm_pmd_folded(tlb->mm))
 		return;
 	pgtable_pmd_page_dtor(virt_to_page(pmd));
 	tlb_remove_table(tlb, pmd);
@@ -152,7 +152,7 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
 				unsigned long address)
 {
-	if (tlb->mm->context.asce_limit <= _REGION1_SIZE)
+	if (mm_p4d_folded(tlb->mm))
 		return;
 	tlb_remove_table(tlb, p4d);
 }
@@ -167,7 +167,7 @@ static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
 static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 				unsigned long address)
 {
-	if (tlb->mm->context.asce_limit <= _REGION2_SIZE)
+	if (mm_pud_folded(tlb->mm))
 		return;
 	tlb_remove_table(tlb, pud);
 }
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 76d89ee..814f265 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -101,6 +101,7 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long end)
 			mm->context.asce_limit = _REGION1_SIZE;
 			mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
 				_ASCE_USER_BITS | _ASCE_TYPE_REGION2;
+			mm_inc_nr_puds(mm);
 		} else {
 			crst_table_init(table, _REGION1_ENTRY_EMPTY);
 			pgd_populate(mm, (pgd_t *) table, (p4d_t *) pgd);
-- 
2.7.4

Re: [PATCH 1/4] mm: make the __PAGETABLE_PxD_FOLDED defines non-empty

[Kirill A. Shutemov]

On Wed, Oct 31, 2018 at 01:59:58PM +0100, Martin Schwidefsky wrote:
> Change the currently empty defines for __PAGETABLE_PMD_FOLDED,
> __PAGETABLE_PUD_FOLDED and __PAGETABLE_P4D_FOLDED to return 1.
> This makes it possible to use __is_defined() to test if the
> preprocessor define exists.
> 
> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

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

-- 
 Kirill A. Shutemov

Re: [PATCH 2/4] mm: introduce mm_[p4d|pud|pmd]_folded

[Kirill A. Shutemov]

On Wed, Oct 31, 2018 at 01:59:59PM +0100, Martin Schwidefsky wrote:
> Add three architecture overrideable functions to test if the
> p4d, pud, or pmd layer of a page table is folded or not.
> 
> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

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

-- 
 Kirill A. Shutemov