Re: [RFC/PATCH 3/5] mm: get_user_pages: use NON-MOVABLE pages when FOLL_DURABLE flag is set

2013-05-07 Thread Tang Chen 

Hi Marek,

On 05/07/2013 06:47 PM, Marek Szyprowski wrote:


I don't think that there was any conclusion after my patch, so I really see
no point in submitting it again now. If you need it for Your patchset, You
can include it directly. Just please keep my signed-off-by tag.



That's very kind of you. I'll keep you as the Author and your 
signed-off-by tag

if I use your patches, and will cc you.

Thanks. :)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Re: [RFC/PATCH 3/5] mm: get_user_pages: use NON-MOVABLE pages when FOLL_DURABLE flag is set

2013-05-07 Thread Marek Szyprowski 

Hello,

On 5/6/2013 9:19 AM, Tang Chen wrote:

Hi Marek,

It has been a long time since this patch-set was sent.
And I'm pushing memory hot-remove works. I think I need your
[patch3/5] to fix a problem I met.

We have sent a similar patch before. But I think yours may be better. :)
https://lkml.org/lkml/2013/2/21/126

So would you please update and resend your patch again ?
Or do you have your own plan to push it ?



I don't think that there was any conclusion after my patch, so I really see
no point in submitting it again now. If you need it for Your patchset, You
can include it directly. Just please keep my signed-off-by tag.


Thanks. :)

On 03/05/2013 02:57 PM, Marek Szyprowski wrote:

Ensure that newly allocated pages, which are faulted in in FOLL_DURABLE
mode comes from non-movalbe pageblocks, to workaround migration failures
with Contiguous Memory Allocator.

Signed-off-by: Marek Szyprowski
Signed-off-by: Kyungmin Park
---
  include/linux/highmem.h |   12 ++--
  include/linux/mm.h  |2 ++
  mm/memory.c |   24 ++--
  3 files changed, 30 insertions(+), 8 deletions(-)

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 7fb31da..cf0b9d8 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -168,7 +168,8 @@ __alloc_zeroed_user_highpage(gfp_t movableflags,
  #endif

  /**
- * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM 
page for a VMA that the caller knows can move
+ * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM 
page for

+ *a VMA that the caller knows can move
   * @vma: The VMA the page is to be allocated for
   * @vaddr: The virtual address the page will be inserted into
   *
@@ -177,11 +178,18 @@ __alloc_zeroed_user_highpage(gfp_t movableflags,
   */
  static inline struct page *
  alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
-unsigned long vaddr)
+   unsigned long vaddr)
  {
  return __alloc_zeroed_user_highpage(__GFP_MOVABLE, vma, vaddr);
  }

+static inline struct page *
+alloc_zeroed_user_highpage(gfp_t gfp, struct vm_area_struct *vma,
+   unsigned long vaddr)
+{
+return __alloc_zeroed_user_highpage(gfp, vma, vaddr);
+}
+
  static inline void clear_highpage(struct page *page)
  {
  void *kaddr = kmap_atomic(page);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9806e54..c11f58f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -165,6 +165,7 @@ extern pgprot_t protection_map[16];
  #define FAULT_FLAG_RETRY_NOWAIT0x10/* Don't drop mmap_sem 
and wait when retrying */
  #define FAULT_FLAG_KILLABLE0x20/* The fault task is in 
SIGKILL killable region */

  #define FAULT_FLAG_TRIED0x40/* second try */
+#define FAULT_FLAG_NO_CMA0x80/* don't use CMA pages */

  /*
   * vm_fault is filled by the the pagefault handler and passed to 
the vma's
@@ -1633,6 +1634,7 @@ static inline struct page *follow_page(struct 
vm_area_struct *vma,

  #define FOLL_HWPOISON0x100/* check page is hwpoisoned */
  #define FOLL_NUMA0x200/* force NUMA hinting page fault */
  #define FOLL_MIGRATION0x400/* wait for page to replace 
migration entry */
+#define FOLL_DURABLE0x800/* get the page reference for a 
long time */


  typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long 
addr,

  void *data);
diff --git a/mm/memory.c b/mm/memory.c
index 42dfd8e..2b9c2dd 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1816,6 +1816,9 @@ long __get_user_pages(struct task_struct *tsk, 
struct mm_struct *mm,

  int ret;
  unsigned int fault_flags = 0;

+if (gup_flags&  FOLL_DURABLE)
+fault_flags = FAULT_FLAG_NO_CMA;
+
  /* For mlock, just skip the stack guard page. */
  if (foll_flags&  FOLL_MLOCK) {
  if (stack_guard_page(vma, start))
@@ -2495,7 +2498,7 @@ static inline void cow_user_page(struct page 
*dst, struct page *src, unsigned lo

   */
  static int do_wp_page(struct mm_struct *mm, struct vm_area_struct 
*vma,

  unsigned long address, pte_t *page_table, pmd_t *pmd,
-spinlock_t *ptl, pte_t orig_pte)
+spinlock_t *ptl, pte_t orig_pte, unsigned int flags)
  __releases(ptl)
  {
  struct page *old_page, *new_page = NULL;
@@ -2505,6 +2508,10 @@ static int do_wp_page(struct mm_struct *mm, 
struct vm_area_struct *vma,

  struct page *dirty_page = NULL;
  unsigned long mmun_start = 0;/* For mmu_notifiers */
  unsigned long mmun_end = 0;/* For mmu_notifiers */
+gfp_t gfp = GFP_HIGHUSER_MOVABLE;
+
+if (IS_ENABLED(CONFIG_CMA)&&  (flags& FAULT_FLAG_NO_CMA))
+gfp&= ~__GFP_MOVABLE;

  old_page = vm_normal_page(vma, address, orig_pte);
  if (!old_page) {
@@ -2668,11 +2675,11 @@ gotten:
  goto oom;

  if

Re: [RFC/PATCH 3/5] mm: get_user_pages: use NON-MOVABLE pages when FOLL_DURABLE flag is set

2013-05-07 Thread Marek Szyprowski 

Hello,

On 5/6/2013 9:19 AM, Tang Chen wrote:

Hi Marek,

It has been a long time since this patch-set was sent.
And I'm pushing memory hot-remove works. I think I need your
[patch3/5] to fix a problem I met.

We have sent a similar patch before. But I think yours may be better. :)
https://lkml.org/lkml/2013/2/21/126

So would you please update and resend your patch again ?
Or do you have your own plan to push it ?



I don't think that there was any conclusion after my patch, so I really see
no point in submitting it again now. If you need it for Your patchset, You
can include it directly. Just please keep my signed-off-by tag.


Thanks. :)

On 03/05/2013 02:57 PM, Marek Szyprowski wrote:

Ensure that newly allocated pages, which are faulted in in FOLL_DURABLE
mode comes from non-movalbe pageblocks, to workaround migration failures
with Contiguous Memory Allocator.

Signed-off-by: Marek Szyprowskim.szyprow...@samsung.com
Signed-off-by: Kyungmin Parkkyungmin.p...@samsung.com
---
  include/linux/highmem.h |   12 ++--
  include/linux/mm.h  |2 ++
  mm/memory.c |   24 ++--
  3 files changed, 30 insertions(+), 8 deletions(-)

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 7fb31da..cf0b9d8 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -168,7 +168,8 @@ __alloc_zeroed_user_highpage(gfp_t movableflags,
  #endif

  /**
- * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM 
page for a VMA that the caller knows can move
+ * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM 
page for

+ *a VMA that the caller knows can move
   * @vma: The VMA the page is to be allocated for
   * @vaddr: The virtual address the page will be inserted into
   *
@@ -177,11 +178,18 @@ __alloc_zeroed_user_highpage(gfp_t movableflags,
   */
  static inline struct page *
  alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
-unsigned long vaddr)
+   unsigned long vaddr)
  {
  return __alloc_zeroed_user_highpage(__GFP_MOVABLE, vma, vaddr);
  }

+static inline struct page *
+alloc_zeroed_user_highpage(gfp_t gfp, struct vm_area_struct *vma,
+   unsigned long vaddr)
+{
+return __alloc_zeroed_user_highpage(gfp, vma, vaddr);
+}
+
  static inline void clear_highpage(struct page *page)
  {
  void *kaddr = kmap_atomic(page);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9806e54..c11f58f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -165,6 +165,7 @@ extern pgprot_t protection_map[16];
  #define FAULT_FLAG_RETRY_NOWAIT0x10/* Don't drop mmap_sem 
and wait when retrying */
  #define FAULT_FLAG_KILLABLE0x20/* The fault task is in 
SIGKILL killable region */

  #define FAULT_FLAG_TRIED0x40/* second try */
+#define FAULT_FLAG_NO_CMA0x80/* don't use CMA pages */

  /*
   * vm_fault is filled by the the pagefault handler and passed to 
the vma's
@@ -1633,6 +1634,7 @@ static inline struct page *follow_page(struct 
vm_area_struct *vma,

  #define FOLL_HWPOISON0x100/* check page is hwpoisoned */
  #define FOLL_NUMA0x200/* force NUMA hinting page fault */
  #define FOLL_MIGRATION0x400/* wait for page to replace 
migration entry */
+#define FOLL_DURABLE0x800/* get the page reference for a 
long time */


  typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long 
addr,

  void *data);
diff --git a/mm/memory.c b/mm/memory.c
index 42dfd8e..2b9c2dd 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1816,6 +1816,9 @@ long __get_user_pages(struct task_struct *tsk, 
struct mm_struct *mm,

  int ret;
  unsigned int fault_flags = 0;

+if (gup_flags  FOLL_DURABLE)
+fault_flags = FAULT_FLAG_NO_CMA;
+
  /* For mlock, just skip the stack guard page. */
  if (foll_flags  FOLL_MLOCK) {
  if (stack_guard_page(vma, start))
@@ -2495,7 +2498,7 @@ static inline void cow_user_page(struct page 
*dst, struct page *src, unsigned lo

   */
  static int do_wp_page(struct mm_struct *mm, struct vm_area_struct 
*vma,

  unsigned long address, pte_t *page_table, pmd_t *pmd,
-spinlock_t *ptl, pte_t orig_pte)
+spinlock_t *ptl, pte_t orig_pte, unsigned int flags)
  __releases(ptl)
  {
  struct page *old_page, *new_page = NULL;
@@ -2505,6 +2508,10 @@ static int do_wp_page(struct mm_struct *mm, 
struct vm_area_struct *vma,

  struct page *dirty_page = NULL;
  unsigned long mmun_start = 0;/* For mmu_notifiers */
  unsigned long mmun_end = 0;/* For mmu_notifiers */
+gfp_t gfp = GFP_HIGHUSER_MOVABLE;
+
+if (IS_ENABLED(CONFIG_CMA)  (flags FAULT_FLAG_NO_CMA))
+gfp= ~__GFP_MOVABLE;

  old_page = vm_normal_page(vma, address, orig_pte);
  if (!old_page) {
@@ -2668,11 +2675,11 @@ gotten:

Re: [RFC/PATCH 3/5] mm: get_user_pages: use NON-MOVABLE pages when FOLL_DURABLE flag is set

2013-05-07 Thread Tang Chen 

Hi Marek,

On 05/07/2013 06:47 PM, Marek Szyprowski wrote:


I don't think that there was any conclusion after my patch, so I really see
no point in submitting it again now. If you need it for Your patchset, You
can include it directly. Just please keep my signed-off-by tag.



That's very kind of you. I'll keep you as the Author and your 
signed-off-by tag

if I use your patches, and will cc you.

Thanks. :)
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Re: [RFC/PATCH 3/5] mm: get_user_pages: use NON-MOVABLE pages when FOLL_DURABLE flag is set

2013-05-06 Thread Tang Chen 

Hi Marek,

It has been a long time since this patch-set was sent.
And I'm pushing memory hot-remove works. I think I need your
[patch3/5] to fix a problem I met.

We have sent a similar patch before. But I think yours may be better. :)
https://lkml.org/lkml/2013/2/21/126

So would you please update and resend your patch again ?
Or do you have your own plan to push it ?

Thanks. :)

On 03/05/2013 02:57 PM, Marek Szyprowski wrote:

Ensure that newly allocated pages, which are faulted in in FOLL_DURABLE
mode comes from non-movalbe pageblocks, to workaround migration failures
with Contiguous Memory Allocator.

Signed-off-by: Marek Szyprowski
Signed-off-by: Kyungmin Park
---
  include/linux/highmem.h |   12 ++--
  include/linux/mm.h  |2 ++
  mm/memory.c |   24 ++--
  3 files changed, 30 insertions(+), 8 deletions(-)

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 7fb31da..cf0b9d8 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -168,7 +168,8 @@ __alloc_zeroed_user_highpage(gfp_t movableflags,
  #endif

  /**
- * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for a 
VMA that the caller knows can move
+ * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for
+ * a VMA that the caller knows can move
   * @vma: The VMA the page is to be allocated for
   * @vaddr: The virtual address the page will be inserted into
   *
@@ -177,11 +178,18 @@ __alloc_zeroed_user_highpage(gfp_t movableflags,
   */
  static inline struct page *
  alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
-   unsigned long vaddr)
+  unsigned long vaddr)
  {
return __alloc_zeroed_user_highpage(__GFP_MOVABLE, vma, vaddr);
  }

+static inline struct page *
+alloc_zeroed_user_highpage(gfp_t gfp, struct vm_area_struct *vma,
+  unsigned long vaddr)
+{
+   return __alloc_zeroed_user_highpage(gfp, vma, vaddr);
+}
+
  static inline void clear_highpage(struct page *page)
  {
void *kaddr = kmap_atomic(page);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9806e54..c11f58f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -165,6 +165,7 @@ extern pgprot_t protection_map[16];
  #define FAULT_FLAG_RETRY_NOWAIT   0x10/* Don't drop mmap_sem and wait 
when retrying */
  #define FAULT_FLAG_KILLABLE   0x20/* The fault task is in SIGKILL 
killable region */
  #define FAULT_FLAG_TRIED  0x40/* second try */
+#define FAULT_FLAG_NO_CMA  0x80/* don't use CMA pages */

  /*
   * vm_fault is filled by the the pagefault handler and passed to the vma's
@@ -1633,6 +1634,7 @@ static inline struct page *follow_page(struct 
vm_area_struct *vma,
  #define FOLL_HWPOISON 0x100   /* check page is hwpoisoned */
  #define FOLL_NUMA 0x200   /* force NUMA hinting page fault */
  #define FOLL_MIGRATION0x400   /* wait for page to replace migration 
entry */
+#define FOLL_DURABLE   0x800   /* get the page reference for a long time */

  typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
void *data);
diff --git a/mm/memory.c b/mm/memory.c
index 42dfd8e..2b9c2dd 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1816,6 +1816,9 @@ long __get_user_pages(struct task_struct *tsk, struct 
mm_struct *mm,
int ret;
unsigned int fault_flags = 0;

+   if (gup_flags&  FOLL_DURABLE)
+   fault_flags = FAULT_FLAG_NO_CMA;
+
/* For mlock, just skip the stack guard page. */
if (foll_flags&  FOLL_MLOCK) {
if (stack_guard_page(vma, start))
@@ -2495,7 +2498,7 @@ static inline void cow_user_page(struct page *dst, struct 
page *src, unsigned lo
   */
  static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table, pmd_t *pmd,
-   spinlock_t *ptl, pte_t orig_pte)
+   spinlock_t *ptl, pte_t orig_pte, unsigned int flags)
__releases(ptl)
  {
struct page *old_page, *new_page = NULL;
@@ -2505,6 +2508,10 @@ static int do_wp_page(struct mm_struct *mm, struct 
vm_area_struct *vma,
struct page *dirty_page = NULL;
unsigned long mmun_start = 0;   /* For mmu_notifiers */
unsigned long mmun_end = 0; /* For mmu_notifiers */
+   gfp_t gfp = GFP_HIGHUSER_MOVABLE;
+
+   if (IS_ENABLED(CONFIG_CMA)&&  (flags&  FAULT_FLAG_NO_CMA))
+   gfp&= ~__GFP_MOVABLE;

old_page = vm_normal_page(vma, address, orig_pte);
if (!old_page) {
@@ -2668,11 +2675,11 @@ gotten:
goto oom;

if (is_zero_pfn(pte_pfn(orig_pte))) {
-   new_page

Re: [RFC/PATCH 3/5] mm: get_user_pages: use NON-MOVABLE pages when FOLL_DURABLE flag is set

2013-05-06 Thread Tang Chen 

Hi Marek,

It has been a long time since this patch-set was sent.
And I'm pushing memory hot-remove works. I think I need your
[patch3/5] to fix a problem I met.

We have sent a similar patch before. But I think yours may be better. :)
https://lkml.org/lkml/2013/2/21/126

So would you please update and resend your patch again ?
Or do you have your own plan to push it ?

Thanks. :)

On 03/05/2013 02:57 PM, Marek Szyprowski wrote:

Ensure that newly allocated pages, which are faulted in in FOLL_DURABLE
mode comes from non-movalbe pageblocks, to workaround migration failures
with Contiguous Memory Allocator.

Signed-off-by: Marek Szyprowskim.szyprow...@samsung.com
Signed-off-by: Kyungmin Parkkyungmin.p...@samsung.com
---
  include/linux/highmem.h |   12 ++--
  include/linux/mm.h  |2 ++
  mm/memory.c |   24 ++--
  3 files changed, 30 insertions(+), 8 deletions(-)

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 7fb31da..cf0b9d8 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -168,7 +168,8 @@ __alloc_zeroed_user_highpage(gfp_t movableflags,
  #endif

  /**
- * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for a 
VMA that the caller knows can move
+ * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for
+ * a VMA that the caller knows can move
   * @vma: The VMA the page is to be allocated for
   * @vaddr: The virtual address the page will be inserted into
   *
@@ -177,11 +178,18 @@ __alloc_zeroed_user_highpage(gfp_t movableflags,
   */
  static inline struct page *
  alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
-   unsigned long vaddr)
+  unsigned long vaddr)
  {
return __alloc_zeroed_user_highpage(__GFP_MOVABLE, vma, vaddr);
  }

+static inline struct page *
+alloc_zeroed_user_highpage(gfp_t gfp, struct vm_area_struct *vma,
+  unsigned long vaddr)
+{
+   return __alloc_zeroed_user_highpage(gfp, vma, vaddr);
+}
+
  static inline void clear_highpage(struct page *page)
  {
void *kaddr = kmap_atomic(page);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9806e54..c11f58f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -165,6 +165,7 @@ extern pgprot_t protection_map[16];
  #define FAULT_FLAG_RETRY_NOWAIT   0x10/* Don't drop mmap_sem and wait 
when retrying */
  #define FAULT_FLAG_KILLABLE   0x20/* The fault task is in SIGKILL 
killable region */
  #define FAULT_FLAG_TRIED  0x40/* second try */
+#define FAULT_FLAG_NO_CMA  0x80/* don't use CMA pages */

  /*
   * vm_fault is filled by the the pagefault handler and passed to the vma's
@@ -1633,6 +1634,7 @@ static inline struct page *follow_page(struct 
vm_area_struct *vma,
  #define FOLL_HWPOISON 0x100   /* check page is hwpoisoned */
  #define FOLL_NUMA 0x200   /* force NUMA hinting page fault */
  #define FOLL_MIGRATION0x400   /* wait for page to replace migration 
entry */
+#define FOLL_DURABLE   0x800   /* get the page reference for a long time */

  typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
void *data);
diff --git a/mm/memory.c b/mm/memory.c
index 42dfd8e..2b9c2dd 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1816,6 +1816,9 @@ long __get_user_pages(struct task_struct *tsk, struct 
mm_struct *mm,
int ret;
unsigned int fault_flags = 0;

+   if (gup_flags  FOLL_DURABLE)
+   fault_flags = FAULT_FLAG_NO_CMA;
+
/* For mlock, just skip the stack guard page. */
if (foll_flags  FOLL_MLOCK) {
if (stack_guard_page(vma, start))
@@ -2495,7 +2498,7 @@ static inline void cow_user_page(struct page *dst, struct 
page *src, unsigned lo
   */
  static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table, pmd_t *pmd,
-   spinlock_t *ptl, pte_t orig_pte)
+   spinlock_t *ptl, pte_t orig_pte, unsigned int flags)
__releases(ptl)
  {
struct page *old_page, *new_page = NULL;
@@ -2505,6 +2508,10 @@ static int do_wp_page(struct mm_struct *mm, struct 
vm_area_struct *vma,
struct page *dirty_page = NULL;
unsigned long mmun_start = 0;   /* For mmu_notifiers */
unsigned long mmun_end = 0; /* For mmu_notifiers */
+   gfp_t gfp = GFP_HIGHUSER_MOVABLE;
+
+   if (IS_ENABLED(CONFIG_CMA)  (flags  FAULT_FLAG_NO_CMA))
+   gfp= ~__GFP_MOVABLE;

old_page = vm_normal_page(vma, address, orig_pte);
if (!old_page) {
@@ -2668,11 +2675,11 @@ gotten:
goto oom;

if

Re: [RFC/PATCH 3/5] mm: get_user_pages: use NON-MOVABLE pages when FOLL_DURABLE flag is set

2013-03-06 Thread Lin Feng 
Hi Marek,

On 03/05/2013 02:57 PM, Marek Szyprowski wrote:
> Ensure that newly allocated pages, which are faulted in in FOLL_DURABLE
> mode comes from non-movalbe pageblocks, to workaround migration failures
> with Contiguous Memory Allocator.

snip
> @@ -2495,7 +2498,7 @@ static inline void cow_user_page(struct page *dst, 
> struct page *src, unsigned lo
>   */
>  static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
>   unsigned long address, pte_t *page_table, pmd_t *pmd,
> - spinlock_t *ptl, pte_t orig_pte)
> + spinlock_t *ptl, pte_t orig_pte, unsigned int flags)
>   __releases(ptl)
>  {
>   struct page *old_page, *new_page = NULL;
> @@ -2505,6 +2508,10 @@ static int do_wp_page(struct mm_struct *mm, struct 
> vm_area_struct *vma,
>   struct page *dirty_page = NULL;
>   unsigned long mmun_start = 0;   /* For mmu_notifiers */
>   unsigned long mmun_end = 0; /* For mmu_notifiers */
> + gfp_t gfp = GFP_HIGHUSER_MOVABLE;
> +
> + if (IS_ENABLED(CONFIG_CMA) && (flags & FAULT_FLAG_NO_CMA))
> + gfp &= ~__GFP_MOVABLE;

snip
> @@ -3187,6 +3194,11 @@ static int __do_fault(struct mm_struct *mm, struct 
> vm_area_struct *vma,
>   struct vm_fault vmf;
>   int ret;
>   int page_mkwrite = 0;
> + gfp_t gfp = GFP_HIGHUSER_MOVABLE;
> +
> + if (IS_ENABLED(CONFIG_CMA) && (flags & FAULT_FLAG_NO_CMA))
> + gfp &= ~__GFP_MOVABLE;
> +
>  
>   /*

Since the GUP unmovable pages are only corner cases in all kinds of pagefaults, 
I'm afraid that adding special treatment codes in generic pagefault core 
interface
is not that necessary or worth to do.
But I'm not sure if the performance impact is as large as to be worried about.


thanks,
linfeng  
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Re: [RFC/PATCH 3/5] mm: get_user_pages: use NON-MOVABLE pages when FOLL_DURABLE flag is set

2013-03-06 Thread Lin Feng 
Hi Marek,

On 03/05/2013 02:57 PM, Marek Szyprowski wrote:
> @@ -2495,7 +2498,7 @@ static inline void cow_user_page(struct page *dst, 
> struct page *src, unsigned lo
>   */
>  static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
>   unsigned long address, pte_t *page_table, pmd_t *pmd,
> - spinlock_t *ptl, pte_t orig_pte)
> + spinlock_t *ptl, pte_t orig_pte, unsigned int flags)
>   __releases(ptl)
>  {
>   struct page *old_page, *new_page = NULL;
> @@ -2505,6 +2508,10 @@ static int do_wp_page(struct mm_struct *mm, struct 
> vm_area_struct *vma,
>   struct page *dirty_page = NULL;
>   unsigned long mmun_start = 0;   /* For mmu_notifiers */
>   unsigned long mmun_end = 0; /* For mmu_notifiers */
> + gfp_t gfp = GFP_HIGHUSER_MOVABLE;
> +
> + if (IS_ENABLED(CONFIG_CMA) && (flags & FAULT_FLAG_NO_CMA))
> + gfp &= ~__GFP_MOVABLE;

Here just simply strip the __GFP_MOVABLE flag, IIUC it will break the page 
migrate policy.  
Because " But GFP_MOVABLE is not only a zone specifier but also an allocation 
policy.".

Another problem is that you add a new flag to instruct the page allocation, 
do we have to also handle the hugepage or THP as Mel ever mentioned?
 
thanks,
linfeng
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Re: [RFC/PATCH 3/5] mm: get_user_pages: use NON-MOVABLE pages when FOLL_DURABLE flag is set

2013-03-06 Thread Lin Feng 
Hi Marek,

On 03/05/2013 02:57 PM, Marek Szyprowski wrote:
 @@ -2495,7 +2498,7 @@ static inline void cow_user_page(struct page *dst, 
 struct page *src, unsigned lo
   */
  static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
   unsigned long address, pte_t *page_table, pmd_t *pmd,
 - spinlock_t *ptl, pte_t orig_pte)
 + spinlock_t *ptl, pte_t orig_pte, unsigned int flags)
   __releases(ptl)
  {
   struct page *old_page, *new_page = NULL;
 @@ -2505,6 +2508,10 @@ static int do_wp_page(struct mm_struct *mm, struct 
 vm_area_struct *vma,
   struct page *dirty_page = NULL;
   unsigned long mmun_start = 0;   /* For mmu_notifiers */
   unsigned long mmun_end = 0; /* For mmu_notifiers */
 + gfp_t gfp = GFP_HIGHUSER_MOVABLE;
 +
 + if (IS_ENABLED(CONFIG_CMA)  (flags  FAULT_FLAG_NO_CMA))
 + gfp = ~__GFP_MOVABLE;

Here just simply strip the __GFP_MOVABLE flag, IIUC it will break the page 
migrate policy.  
Because  But GFP_MOVABLE is not only a zone specifier but also an allocation 
policy..

Another problem is that you add a new flag to instruct the page allocation, 
do we have to also handle the hugepage or THP as Mel ever mentioned?
 
thanks,
linfeng
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Re: [RFC/PATCH 3/5] mm: get_user_pages: use NON-MOVABLE pages when FOLL_DURABLE flag is set

2013-03-06 Thread Lin Feng 
Hi Marek,

On 03/05/2013 02:57 PM, Marek Szyprowski wrote:
 Ensure that newly allocated pages, which are faulted in in FOLL_DURABLE
 mode comes from non-movalbe pageblocks, to workaround migration failures
 with Contiguous Memory Allocator.

snip
 @@ -2495,7 +2498,7 @@ static inline void cow_user_page(struct page *dst, 
 struct page *src, unsigned lo
   */
  static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
   unsigned long address, pte_t *page_table, pmd_t *pmd,
 - spinlock_t *ptl, pte_t orig_pte)
 + spinlock_t *ptl, pte_t orig_pte, unsigned int flags)
   __releases(ptl)
  {
   struct page *old_page, *new_page = NULL;
 @@ -2505,6 +2508,10 @@ static int do_wp_page(struct mm_struct *mm, struct 
 vm_area_struct *vma,
   struct page *dirty_page = NULL;
   unsigned long mmun_start = 0;   /* For mmu_notifiers */
   unsigned long mmun_end = 0; /* For mmu_notifiers */
 + gfp_t gfp = GFP_HIGHUSER_MOVABLE;
 +
 + if (IS_ENABLED(CONFIG_CMA)  (flags  FAULT_FLAG_NO_CMA))
 + gfp = ~__GFP_MOVABLE;

snip
 @@ -3187,6 +3194,11 @@ static int __do_fault(struct mm_struct *mm, struct 
 vm_area_struct *vma,
   struct vm_fault vmf;
   int ret;
   int page_mkwrite = 0;
 + gfp_t gfp = GFP_HIGHUSER_MOVABLE;
 +
 + if (IS_ENABLED(CONFIG_CMA)  (flags  FAULT_FLAG_NO_CMA))
 + gfp = ~__GFP_MOVABLE;
 +
  
   /*

Since the GUP unmovable pages are only corner cases in all kinds of pagefaults, 
I'm afraid that adding special treatment codes in generic pagefault core 
interface
is not that necessary or worth to do.
But I'm not sure if the performance impact is as large as to be worried about.


thanks,
linfeng  
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Re: [RFC/PATCH 3/5] mm: get_user_pages: use NON-MOVABLE pages when FOLL_DURABLE flag is set

2013-03-05 Thread Yasuaki Ishimatsu 
2013/03/05 15:57, Marek Szyprowski wrote:
> Ensure that newly allocated pages, which are faulted in in FOLL_DURABLE
> mode comes from non-movalbe pageblocks, to workaround migration failures
> with Contiguous Memory Allocator.

In your idea, all users who uses non-movable pageblocks need to set
gup_flags. It's not good.

So how about prepare "get_user_pages_non_movable"? The idea is based on
following Lin Feng's idea:
https://lkml.org/lkml/2013/2/21/123

int get_user_pages_non_movable()
{
int flags = FOLL_TOUCH | FOLL_DURABLE;

if (pages)
flags |= FOLL_GET;
if (write)
flags |= FOLL_WRITE;
if (force)
flags |= FOLL_FORCE;

return __get_user_pages();
}

> 
> Signed-off-by: Marek Szyprowski 
> Signed-off-by: Kyungmin Park 
> ---
>   include/linux/highmem.h |   12 ++--
>   include/linux/mm.h  |2 ++
>   mm/memory.c |   24 ++--
>   3 files changed, 30 insertions(+), 8 deletions(-)
> 
> diff --git a/include/linux/highmem.h b/include/linux/highmem.h
> index 7fb31da..cf0b9d8 100644
> --- a/include/linux/highmem.h
> +++ b/include/linux/highmem.h
> @@ -168,7 +168,8 @@ __alloc_zeroed_user_highpage(gfp_t movableflags,
>   #endif
>   
>   /**
> - * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for a 
> VMA that the caller knows can move
> + * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for
> + *   a VMA that the caller knows can move
>* @vma: The VMA the page is to be allocated for
>* @vaddr: The virtual address the page will be inserted into
>*
> @@ -177,11 +178,18 @@ __alloc_zeroed_user_highpage(gfp_t movableflags,
>*/
>   static inline struct page *
>   alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
> - unsigned long vaddr)
> +unsigned long vaddr)
>   {
>   return __alloc_zeroed_user_highpage(__GFP_MOVABLE, vma, vaddr);
>   }
>   
> +static inline struct page *
> +alloc_zeroed_user_highpage(gfp_t gfp, struct vm_area_struct *vma,
> +unsigned long vaddr)
> +{
> + return __alloc_zeroed_user_highpage(gfp, vma, vaddr);
> +}
> +
>   static inline void clear_highpage(struct page *page)
>   {
>   void *kaddr = kmap_atomic(page);
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 9806e54..c11f58f 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -165,6 +165,7 @@ extern pgprot_t protection_map[16];
>   #define FAULT_FLAG_RETRY_NOWAIT 0x10/* Don't drop mmap_sem and wait 
> when retrying */
>   #define FAULT_FLAG_KILLABLE 0x20/* The fault task is in SIGKILL 
> killable region */
>   #define FAULT_FLAG_TRIED0x40/* second try */

> +#define FAULT_FLAG_NO_CMA0x80/* don't use CMA pages */

How about FAULT_FLAG_NO_MIGLATABLE? I want to use it to not only CMA but
also memory hotplug.

>   
>   /*
>* vm_fault is filled by the the pagefault handler and passed to the vma's
> @@ -1633,6 +1634,7 @@ static inline struct page *follow_page(struct 
> vm_area_struct *vma,
>   #define FOLL_HWPOISON   0x100   /* check page is hwpoisoned */
>   #define FOLL_NUMA   0x200   /* force NUMA hinting page fault */
>   #define FOLL_MIGRATION  0x400   /* wait for page to replace migration 
> entry */
> +#define FOLL_DURABLE 0x800   /* get the page reference for a long time */
>   
>   typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
>   void *data);
> diff --git a/mm/memory.c b/mm/memory.c
> index 42dfd8e..2b9c2dd 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -1816,6 +1816,9 @@ long __get_user_pages(struct task_struct *tsk, struct 
> mm_struct *mm,
>   int ret;
>   unsigned int fault_flags = 0;
>   
> + if (gup_flags & FOLL_DURABLE)
> + fault_flags = FAULT_FLAG_NO_CMA;
> +
>   /* For mlock, just skip the stack guard page. */
>   if (foll_flags & FOLL_MLOCK) {
>   if (stack_guard_page(vma, start))
> @@ -2495,7 +2498,7 @@ static inline void cow_user_page(struct page *dst, 
> struct page *src, unsigned lo
>*/
>   static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
>   unsigned long address, pte_t *page_table, pmd_t *pmd,
> - spinlock_t *ptl, pte_t orig_pte)
> + spinlock_t *ptl, pte_t orig_pte, unsigned int flags)
>   __releases(ptl)
>   {
>   struct page *old_page, *new_page = NULL;
> @@ -2505,6 +2508,10 @@ static int do_wp_page(struct mm_struct *mm, struct 
> vm_area_struct *vma,
>   struct page *dirty_page = NULL;
>   unsigned long mmun_start = 0;   /* For mmu_notifiers */
>   unsigned long mmun_end = 0; /*

Re: [RFC/PATCH 3/5] mm: get_user_pages: use NON-MOVABLE pages when FOLL_DURABLE flag is set

2013-03-05 Thread Yasuaki Ishimatsu 
2013/03/05 15:57, Marek Szyprowski wrote:
 Ensure that newly allocated pages, which are faulted in in FOLL_DURABLE
 mode comes from non-movalbe pageblocks, to workaround migration failures
 with Contiguous Memory Allocator.

In your idea, all users who uses non-movable pageblocks need to set
gup_flags. It's not good.

So how about prepare get_user_pages_non_movable? The idea is based on
following Lin Feng's idea:
https://lkml.org/lkml/2013/2/21/123

int get_user_pages_non_movable()
{
int flags = FOLL_TOUCH | FOLL_DURABLE;

if (pages)
flags |= FOLL_GET;
if (write)
flags |= FOLL_WRITE;
if (force)
flags |= FOLL_FORCE;

return __get_user_pages();
}

 
 Signed-off-by: Marek Szyprowski m.szyprow...@samsung.com
 Signed-off-by: Kyungmin Park kyungmin.p...@samsung.com
 ---
   include/linux/highmem.h |   12 ++--
   include/linux/mm.h  |2 ++
   mm/memory.c |   24 ++--
   3 files changed, 30 insertions(+), 8 deletions(-)
 
 diff --git a/include/linux/highmem.h b/include/linux/highmem.h
 index 7fb31da..cf0b9d8 100644
 --- a/include/linux/highmem.h
 +++ b/include/linux/highmem.h
 @@ -168,7 +168,8 @@ __alloc_zeroed_user_highpage(gfp_t movableflags,
   #endif
   
   /**
 - * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for a 
 VMA that the caller knows can move
 + * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for
 + *   a VMA that the caller knows can move
* @vma: The VMA the page is to be allocated for
* @vaddr: The virtual address the page will be inserted into
*
 @@ -177,11 +178,18 @@ __alloc_zeroed_user_highpage(gfp_t movableflags,
*/
   static inline struct page *
   alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
 - unsigned long vaddr)
 +unsigned long vaddr)
   {
   return __alloc_zeroed_user_highpage(__GFP_MOVABLE, vma, vaddr);
   }
   
 +static inline struct page *
 +alloc_zeroed_user_highpage(gfp_t gfp, struct vm_area_struct *vma,
 +unsigned long vaddr)
 +{
 + return __alloc_zeroed_user_highpage(gfp, vma, vaddr);
 +}
 +
   static inline void clear_highpage(struct page *page)
   {
   void *kaddr = kmap_atomic(page);
 diff --git a/include/linux/mm.h b/include/linux/mm.h
 index 9806e54..c11f58f 100644
 --- a/include/linux/mm.h
 +++ b/include/linux/mm.h
 @@ -165,6 +165,7 @@ extern pgprot_t protection_map[16];
   #define FAULT_FLAG_RETRY_NOWAIT 0x10/* Don't drop mmap_sem and wait 
 when retrying */
   #define FAULT_FLAG_KILLABLE 0x20/* The fault task is in SIGKILL 
 killable region */
   #define FAULT_FLAG_TRIED0x40/* second try */

 +#define FAULT_FLAG_NO_CMA0x80/* don't use CMA pages */

How about FAULT_FLAG_NO_MIGLATABLE? I want to use it to not only CMA but
also memory hotplug.

   
   /*
* vm_fault is filled by the the pagefault handler and passed to the vma's
 @@ -1633,6 +1634,7 @@ static inline struct page *follow_page(struct 
 vm_area_struct *vma,
   #define FOLL_HWPOISON   0x100   /* check page is hwpoisoned */
   #define FOLL_NUMA   0x200   /* force NUMA hinting page fault */
   #define FOLL_MIGRATION  0x400   /* wait for page to replace migration 
 entry */
 +#define FOLL_DURABLE 0x800   /* get the page reference for a long time */
   
   typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
   void *data);
 diff --git a/mm/memory.c b/mm/memory.c
 index 42dfd8e..2b9c2dd 100644
 --- a/mm/memory.c
 +++ b/mm/memory.c
 @@ -1816,6 +1816,9 @@ long __get_user_pages(struct task_struct *tsk, struct 
 mm_struct *mm,
   int ret;
   unsigned int fault_flags = 0;
   
 + if (gup_flags  FOLL_DURABLE)
 + fault_flags = FAULT_FLAG_NO_CMA;
 +
   /* For mlock, just skip the stack guard page. */
   if (foll_flags  FOLL_MLOCK) {
   if (stack_guard_page(vma, start))
 @@ -2495,7 +2498,7 @@ static inline void cow_user_page(struct page *dst, 
 struct page *src, unsigned lo
*/
   static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
   unsigned long address, pte_t *page_table, pmd_t *pmd,
 - spinlock_t *ptl, pte_t orig_pte)
 + spinlock_t *ptl, pte_t orig_pte, unsigned int flags)
   __releases(ptl)
   {
   struct page *old_page, *new_page = NULL;
 @@ -2505,6 +2508,10 @@ static int do_wp_page(struct mm_struct *mm, struct 
 vm_area_struct *vma,
   struct page *dirty_page = NULL;
   unsigned long mmun_start = 0;   /* For mmu_notifiers */
   unsigned long mmun_end = 0; /* For mmu_notifiers */
 + gfp_t gfp =

[RFC/PATCH 3/5] mm: get_user_pages: use NON-MOVABLE pages when FOLL_DURABLE flag is set

2013-03-04 Thread Marek Szyprowski 
Ensure that newly allocated pages, which are faulted in in FOLL_DURABLE
mode comes from non-movalbe pageblocks, to workaround migration failures
with Contiguous Memory Allocator.

Signed-off-by: Marek Szyprowski 
Signed-off-by: Kyungmin Park 
---
 include/linux/highmem.h |   12 ++--
 include/linux/mm.h  |2 ++
 mm/memory.c |   24 ++--
 3 files changed, 30 insertions(+), 8 deletions(-)

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 7fb31da..cf0b9d8 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -168,7 +168,8 @@ __alloc_zeroed_user_highpage(gfp_t movableflags,
 #endif
 
 /**
- * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for a 
VMA that the caller knows can move
+ * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for
+ * a VMA that the caller knows can move
  * @vma: The VMA the page is to be allocated for
  * @vaddr: The virtual address the page will be inserted into
  *
@@ -177,11 +178,18 @@ __alloc_zeroed_user_highpage(gfp_t movableflags,
  */
 static inline struct page *
 alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
-   unsigned long vaddr)
+  unsigned long vaddr)
 {
return __alloc_zeroed_user_highpage(__GFP_MOVABLE, vma, vaddr);
 }
 
+static inline struct page *
+alloc_zeroed_user_highpage(gfp_t gfp, struct vm_area_struct *vma,
+  unsigned long vaddr)
+{
+   return __alloc_zeroed_user_highpage(gfp, vma, vaddr);
+}
+
 static inline void clear_highpage(struct page *page)
 {
void *kaddr = kmap_atomic(page);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9806e54..c11f58f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -165,6 +165,7 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_RETRY_NOWAIT0x10/* Don't drop mmap_sem and wait 
when retrying */
 #define FAULT_FLAG_KILLABLE0x20/* The fault task is in SIGKILL 
killable region */
 #define FAULT_FLAG_TRIED   0x40/* second try */
+#define FAULT_FLAG_NO_CMA  0x80/* don't use CMA pages */
 
 /*
  * vm_fault is filled by the the pagefault handler and passed to the vma's
@@ -1633,6 +1634,7 @@ static inline struct page *follow_page(struct 
vm_area_struct *vma,
 #define FOLL_HWPOISON  0x100   /* check page is hwpoisoned */
 #define FOLL_NUMA  0x200   /* force NUMA hinting page fault */
 #define FOLL_MIGRATION 0x400   /* wait for page to replace migration entry */
+#define FOLL_DURABLE   0x800   /* get the page reference for a long time */
 
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
void *data);
diff --git a/mm/memory.c b/mm/memory.c
index 42dfd8e..2b9c2dd 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1816,6 +1816,9 @@ long __get_user_pages(struct task_struct *tsk, struct 
mm_struct *mm,
int ret;
unsigned int fault_flags = 0;
 
+   if (gup_flags & FOLL_DURABLE)
+   fault_flags = FAULT_FLAG_NO_CMA;
+
/* For mlock, just skip the stack guard page. */
if (foll_flags & FOLL_MLOCK) {
if (stack_guard_page(vma, start))
@@ -2495,7 +2498,7 @@ static inline void cow_user_page(struct page *dst, struct 
page *src, unsigned lo
  */
 static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table, pmd_t *pmd,
-   spinlock_t *ptl, pte_t orig_pte)
+   spinlock_t *ptl, pte_t orig_pte, unsigned int flags)
__releases(ptl)
 {
struct page *old_page, *new_page = NULL;
@@ -2505,6 +2508,10 @@ static int do_wp_page(struct mm_struct *mm, struct 
vm_area_struct *vma,
struct page *dirty_page = NULL;
unsigned long mmun_start = 0;   /* For mmu_notifiers */
unsigned long mmun_end = 0; /* For mmu_notifiers */
+   gfp_t gfp = GFP_HIGHUSER_MOVABLE;
+
+   if (IS_ENABLED(CONFIG_CMA) && (flags & FAULT_FLAG_NO_CMA))
+   gfp &= ~__GFP_MOVABLE;
 
old_page = vm_normal_page(vma, address, orig_pte);
if (!old_page) {
@@ -2668,11 +2675,11 @@ gotten:
goto oom;
 
if (is_zero_pfn(pte_pfn(orig_pte))) {
-   new_page = alloc_zeroed_user_highpage_movable(vma, address);
+   new_page = alloc_zeroed_user_highpage(gfp, vma, address);
if (!new_page)
goto oom;
} else {
-   new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
+   new_page = alloc_page_vma(gfp, vma, address);
if (!new_page)
goto oom;
cow_user_page(new_page,

[RFC/PATCH 3/5] mm: get_user_pages: use NON-MOVABLE pages when FOLL_DURABLE flag is set

2013-03-04 Thread Marek Szyprowski 
Ensure that newly allocated pages, which are faulted in in FOLL_DURABLE
mode comes from non-movalbe pageblocks, to workaround migration failures
with Contiguous Memory Allocator.

Signed-off-by: Marek Szyprowski m.szyprow...@samsung.com
Signed-off-by: Kyungmin Park kyungmin.p...@samsung.com
---
 include/linux/highmem.h |   12 ++--
 include/linux/mm.h  |2 ++
 mm/memory.c |   24 ++--
 3 files changed, 30 insertions(+), 8 deletions(-)

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 7fb31da..cf0b9d8 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -168,7 +168,8 @@ __alloc_zeroed_user_highpage(gfp_t movableflags,
 #endif
 
 /**
- * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for a 
VMA that the caller knows can move
+ * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for
+ * a VMA that the caller knows can move
  * @vma: The VMA the page is to be allocated for
  * @vaddr: The virtual address the page will be inserted into
  *
@@ -177,11 +178,18 @@ __alloc_zeroed_user_highpage(gfp_t movableflags,
  */
 static inline struct page *
 alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
-   unsigned long vaddr)
+  unsigned long vaddr)
 {
return __alloc_zeroed_user_highpage(__GFP_MOVABLE, vma, vaddr);
 }
 
+static inline struct page *
+alloc_zeroed_user_highpage(gfp_t gfp, struct vm_area_struct *vma,
+  unsigned long vaddr)
+{
+   return __alloc_zeroed_user_highpage(gfp, vma, vaddr);
+}
+
 static inline void clear_highpage(struct page *page)
 {
void *kaddr = kmap_atomic(page);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9806e54..c11f58f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -165,6 +165,7 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_RETRY_NOWAIT0x10/* Don't drop mmap_sem and wait 
when retrying */
 #define FAULT_FLAG_KILLABLE0x20/* The fault task is in SIGKILL 
killable region */
 #define FAULT_FLAG_TRIED   0x40/* second try */
+#define FAULT_FLAG_NO_CMA  0x80/* don't use CMA pages */
 
 /*
  * vm_fault is filled by the the pagefault handler and passed to the vma's
@@ -1633,6 +1634,7 @@ static inline struct page *follow_page(struct 
vm_area_struct *vma,
 #define FOLL_HWPOISON  0x100   /* check page is hwpoisoned */
 #define FOLL_NUMA  0x200   /* force NUMA hinting page fault */
 #define FOLL_MIGRATION 0x400   /* wait for page to replace migration entry */
+#define FOLL_DURABLE   0x800   /* get the page reference for a long time */
 
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
void *data);
diff --git a/mm/memory.c b/mm/memory.c
index 42dfd8e..2b9c2dd 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1816,6 +1816,9 @@ long __get_user_pages(struct task_struct *tsk, struct 
mm_struct *mm,
int ret;
unsigned int fault_flags = 0;
 
+   if (gup_flags  FOLL_DURABLE)
+   fault_flags = FAULT_FLAG_NO_CMA;
+
/* For mlock, just skip the stack guard page. */
if (foll_flags  FOLL_MLOCK) {
if (stack_guard_page(vma, start))
@@ -2495,7 +2498,7 @@ static inline void cow_user_page(struct page *dst, struct 
page *src, unsigned lo
  */
 static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table, pmd_t *pmd,
-   spinlock_t *ptl, pte_t orig_pte)
+   spinlock_t *ptl, pte_t orig_pte, unsigned int flags)
__releases(ptl)
 {
struct page *old_page, *new_page = NULL;
@@ -2505,6 +2508,10 @@ static int do_wp_page(struct mm_struct *mm, struct 
vm_area_struct *vma,
struct page *dirty_page = NULL;
unsigned long mmun_start = 0;   /* For mmu_notifiers */
unsigned long mmun_end = 0; /* For mmu_notifiers */
+   gfp_t gfp = GFP_HIGHUSER_MOVABLE;
+
+   if (IS_ENABLED(CONFIG_CMA)  (flags  FAULT_FLAG_NO_CMA))
+   gfp = ~__GFP_MOVABLE;
 
old_page = vm_normal_page(vma, address, orig_pte);
if (!old_page) {
@@ -2668,11 +2675,11 @@ gotten:
goto oom;
 
if (is_zero_pfn(pte_pfn(orig_pte))) {
-   new_page = alloc_zeroed_user_highpage_movable(vma, address);
+   new_page = alloc_zeroed_user_highpage(gfp, vma, address);
if (!new_page)
goto oom;
} else {
-   new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
+   new_page = alloc_page_vma(gfp, vma, address);
if (!new_page)
goto