Re: [PATCH v5 9/9] mm/mmu_notifier: set MMU_NOTIFIER_USE_CHANGE_PTE flag where appropriate v2

2019-02-25 Thread Ralph Campbell 


On 2/19/19 12:04 PM, jgli...@redhat.com wrote:

From: Jérôme Glisse 

When notifying change for a range use MMU_NOTIFIER_USE_CHANGE_PTE flag
for page table update that use set_pte_at_notify() and where the we are
going either from read and write to read only with same pfn or read only
to read and write with new pfn.

Note that set_pte_at_notify() itself should only be use in rare cases
ie we do not want to use it when we are updating a significant range of
virtual addresses and thus a significant number of pte. Instead for
those cases the event provided to mmu notifer invalidate_range_start()
callback should be use for optimization.

Changes since v1:
 - Use the new unsigned flags field in struct mmu_notifier_range
 - Use the new flags parameter to mmu_notifier_range_init()
 - Explicitly list all the patterns where we can use change_pte()

Signed-off-by: Jérôme Glisse 
Cc: Christian König 
Cc: Joonas Lahtinen 
Cc: Jani Nikula 
Cc: Rodrigo Vivi 
Cc: Jan Kara 
Cc: Andrea Arcangeli 
Cc: Peter Xu 
Cc: Felix Kuehling 
Cc: Jason Gunthorpe 
Cc: Ross Zwisler 
Cc: Dan Williams 
Cc: Paolo Bonzini 
Cc: Radim Krčmář 
Cc: Michal Hocko 
Cc: Christian Koenig 
Cc: Ralph Campbell 
Cc: John Hubbard 
Cc: k...@vger.kernel.org
Cc: dri-devel@lists.freedesktop.org
Cc: linux-r...@vger.kernel.org
Cc: Arnd Bergmann 
---
  include/linux/mmu_notifier.h | 34 --
  mm/ksm.c | 11 ++-
  mm/memory.c  |  5 +++--
  3 files changed, 41 insertions(+), 9 deletions(-)

diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index b6c004bd9f6a..0230a4b06b46 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -40,6 +40,26 @@ enum mmu_notifier_event {
MMU_NOTIFY_SOFT_DIRTY,
  };
  
+/*

+ * @MMU_NOTIFIER_RANGE_BLOCKABLE: can the mmu notifier range_start/range_end
+ * callback block or not ? If set then the callback can block.
+ *
+ * @MMU_NOTIFIER_USE_CHANGE_PTE: only set when the page table it updated with
+ * the set_pte_at_notify() the valid patterns for this are:
+ *  - pte read and write to read only same pfn
+ *  - pte read only to read and write (pfn can change or stay the same)
+ *  - pte read only to read only with different pfn
+ * It is illegal to set in any other circumstances.
+ *
+ * Note that set_pte_at_notify() should not be use outside of the above cases.
+ * When updating a range in batch (like write protecting a range) it is better
+ * to rely on invalidate_range_start() and struct mmu_notifier_range to infer
+ * the kind of update that is happening (as an example you can look at the
+ * mmu_notifier_range_update_to_read_only() function).
+ */
+#define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0)
+#define MMU_NOTIFIER_USE_CHANGE_PTE (1 << 1)
+
  #ifdef CONFIG_MMU_NOTIFIER
  
  /*

@@ -55,8 +75,6 @@ struct mmu_notifier_mm {
spinlock_t lock;
  };
  
-#define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0)

-
  struct mmu_notifier_range {
struct vm_area_struct *vma;
struct mm_struct *mm;
@@ -268,6 +286,12 @@ mmu_notifier_range_blockable(const struct 
mmu_notifier_range *range)
return (range->flags & MMU_NOTIFIER_RANGE_BLOCKABLE);
  }
  
+static inline bool

+mmu_notifier_range_use_change_pte(const struct mmu_notifier_range *range)
+{
+   return (range->flags & MMU_NOTIFIER_USE_CHANGE_PTE);
+}
+
  static inline void mmu_notifier_release(struct mm_struct *mm)
  {
if (mm_has_notifiers(mm))
@@ -509,6 +533,12 @@ mmu_notifier_range_blockable(const struct 
mmu_notifier_range *range)
return true;
  }
  
+static inline bool

+mmu_notifier_range_use_change_pte(const struct mmu_notifier_range *range)
+{
+   return false;
+}
+
  static inline int mm_has_notifiers(struct mm_struct *mm)
  {
return 0;
diff --git a/mm/ksm.c b/mm/ksm.c
index b782fadade8f..41e51882f999 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1066,9 +1066,9 @@ static int write_protect_page(struct vm_area_struct *vma, 
struct page *page,
  
  	BUG_ON(PageTransCompound(page));
  
-	mmu_notifier_range_init(, MMU_NOTIFY_CLEAR, 0, vma, mm,

-   pvmw.address,
-   pvmw.address + PAGE_SIZE);
+   mmu_notifier_range_init(, MMU_NOTIFY_CLEAR,
+   MMU_NOTIFIER_USE_CHANGE_PTE, vma, mm,
+   pvmw.address, pvmw.address + PAGE_SIZE);
mmu_notifier_invalidate_range_start();
  
  	if (!page_vma_mapped_walk())

@@ -1155,8 +1155,9 @@ static int replace_page(struct vm_area_struct *vma, 
struct page *page,
if (!pmd)
goto out;
  
-	mmu_notifier_range_init(, MMU_NOTIFY_CLEAR, 0, vma, mm, addr,

-   addr + PAGE_SIZE);
+   mmu_notifier_range_init(, MMU_NOTIFY_CLEAR,
+   MMU_NOTIFIER_USE_CHANGE_PTE,
+   vma, mm, addr, addr + PAGE_SIZE);
mmu_notifier_invalidate_range_start();

[PATCH v5 9/9] mm/mmu_notifier: set MMU_NOTIFIER_USE_CHANGE_PTE flag where appropriate v2

2019-02-19 Thread jglisse 
From: Jérôme Glisse 

When notifying change for a range use MMU_NOTIFIER_USE_CHANGE_PTE flag
for page table update that use set_pte_at_notify() and where the we are
going either from read and write to read only with same pfn or read only
to read and write with new pfn.

Note that set_pte_at_notify() itself should only be use in rare cases
ie we do not want to use it when we are updating a significant range of
virtual addresses and thus a significant number of pte. Instead for
those cases the event provided to mmu notifer invalidate_range_start()
callback should be use for optimization.

Changes since v1:
- Use the new unsigned flags field in struct mmu_notifier_range
- Use the new flags parameter to mmu_notifier_range_init()
- Explicitly list all the patterns where we can use change_pte()

Signed-off-by: Jérôme Glisse 
Cc: Christian König 
Cc: Joonas Lahtinen 
Cc: Jani Nikula 
Cc: Rodrigo Vivi 
Cc: Jan Kara 
Cc: Andrea Arcangeli 
Cc: Peter Xu 
Cc: Felix Kuehling 
Cc: Jason Gunthorpe 
Cc: Ross Zwisler 
Cc: Dan Williams 
Cc: Paolo Bonzini 
Cc: Radim Krčmář 
Cc: Michal Hocko 
Cc: Christian Koenig 
Cc: Ralph Campbell 
Cc: John Hubbard 
Cc: k...@vger.kernel.org
Cc: dri-devel@lists.freedesktop.org
Cc: linux-r...@vger.kernel.org
Cc: Arnd Bergmann 
---
 include/linux/mmu_notifier.h | 34 --
 mm/ksm.c | 11 ++-
 mm/memory.c  |  5 +++--
 3 files changed, 41 insertions(+), 9 deletions(-)

diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index b6c004bd9f6a..0230a4b06b46 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -40,6 +40,26 @@ enum mmu_notifier_event {
MMU_NOTIFY_SOFT_DIRTY,
 };
 
+/*
+ * @MMU_NOTIFIER_RANGE_BLOCKABLE: can the mmu notifier range_start/range_end
+ * callback block or not ? If set then the callback can block.
+ *
+ * @MMU_NOTIFIER_USE_CHANGE_PTE: only set when the page table it updated with
+ * the set_pte_at_notify() the valid patterns for this are:
+ *  - pte read and write to read only same pfn
+ *  - pte read only to read and write (pfn can change or stay the same)
+ *  - pte read only to read only with different pfn
+ * It is illegal to set in any other circumstances.
+ *
+ * Note that set_pte_at_notify() should not be use outside of the above cases.
+ * When updating a range in batch (like write protecting a range) it is better
+ * to rely on invalidate_range_start() and struct mmu_notifier_range to infer
+ * the kind of update that is happening (as an example you can look at the
+ * mmu_notifier_range_update_to_read_only() function).
+ */
+#define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0)
+#define MMU_NOTIFIER_USE_CHANGE_PTE (1 << 1)
+
 #ifdef CONFIG_MMU_NOTIFIER
 
 /*
@@ -55,8 +75,6 @@ struct mmu_notifier_mm {
spinlock_t lock;
 };
 
-#define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0)
-
 struct mmu_notifier_range {
struct vm_area_struct *vma;
struct mm_struct *mm;
@@ -268,6 +286,12 @@ mmu_notifier_range_blockable(const struct 
mmu_notifier_range *range)
return (range->flags & MMU_NOTIFIER_RANGE_BLOCKABLE);
 }
 
+static inline bool
+mmu_notifier_range_use_change_pte(const struct mmu_notifier_range *range)
+{
+   return (range->flags & MMU_NOTIFIER_USE_CHANGE_PTE);
+}
+
 static inline void mmu_notifier_release(struct mm_struct *mm)
 {
if (mm_has_notifiers(mm))
@@ -509,6 +533,12 @@ mmu_notifier_range_blockable(const struct 
mmu_notifier_range *range)
return true;
 }
 
+static inline bool
+mmu_notifier_range_use_change_pte(const struct mmu_notifier_range *range)
+{
+   return false;
+}
+
 static inline int mm_has_notifiers(struct mm_struct *mm)
 {
return 0;
diff --git a/mm/ksm.c b/mm/ksm.c
index b782fadade8f..41e51882f999 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1066,9 +1066,9 @@ static int write_protect_page(struct vm_area_struct *vma, 
struct page *page,
 
BUG_ON(PageTransCompound(page));
 
-   mmu_notifier_range_init(, MMU_NOTIFY_CLEAR, 0, vma, mm,
-   pvmw.address,
-   pvmw.address + PAGE_SIZE);
+   mmu_notifier_range_init(, MMU_NOTIFY_CLEAR,
+   MMU_NOTIFIER_USE_CHANGE_PTE, vma, mm,
+   pvmw.address, pvmw.address + PAGE_SIZE);
mmu_notifier_invalidate_range_start();
 
if (!page_vma_mapped_walk())
@@ -1155,8 +1155,9 @@ static int replace_page(struct vm_area_struct *vma, 
struct page *page,
if (!pmd)
goto out;
 
-   mmu_notifier_range_init(, MMU_NOTIFY_CLEAR, 0, vma, mm, addr,
-   addr + PAGE_SIZE);
+   mmu_notifier_range_init(, MMU_NOTIFY_CLEAR,
+   MMU_NOTIFIER_USE_CHANGE_PTE,
+   vma, mm, addr, addr + PAGE_SIZE);
mmu_notifier_invalidate_range_start();
 
ptep = pte_offset_map_lock(mm, pmd, addr, );
diff