Re: [PATCH v11 02/14] HMM: add special swap filetype for memory migrated to device v2.

Re: [PATCH v11 02/14] HMM: add special swap filetype for memory migrated to device v2.

[Hillf Danton]

> 
> When migrating anonymous memory from system memory to device memory
> CPU pte are replaced with special HMM swap entry so that page fault,
> get user page (gup), fork, ... are properly redirected to HMM helpers.
> 
> This patch only add the new swap type entry and hooks HMM helpers
> functions inside the page fault and fork code path.
> 
> Changed since v1:

But the subject line says this work is v11

>   - Fix name when of HMM CPU page fault function.
> 
> Signed-off-by: Jérôme Glisse <jglisse@...hat.com>
> Signed-off-by: Sherry Cheung <SCheung@...dia.com>
> Signed-off-by: Subhash Gutti <sgutti@...dia.com>
> Signed-off-by: Mark Hairgrove <mhairgrove@...dia.com>
> Signed-off-by: John Hubbard <jhubbard@...dia.com>
> Signed-off-by: Jatin Kumar <jakumar@...dia.com>
> ---
>  include/linux/hmm.h     | 34 ++++++++++++++++++++++++++++++++++
>  include/linux/swap.h    | 13 ++++++++++++-
>  include/linux/swapops.h | 43 ++++++++++++++++++++++++++++++++++++++++++-
>  mm/hmm.c                | 21 +++++++++++++++++++++
>  mm/memory.c             | 22 ++++++++++++++++++++++
>  5 files changed, 131 insertions(+), 2 deletions(-)
> 
> diff --git a/include/linux/hmm.h b/include/linux/hmm.h
> index 4bc132a..7c66513 100644
> --- a/include/linux/hmm.h
> +++ b/include/linux/hmm.h

I find no hmm.h in 4.3-rc6

> @@ -272,6 +272,40 @@ void hmm_mirror_range_dirty(struct hmm_mirror *mirror,
>  			    unsigned long start,
>  			    unsigned long end);
> 
> +int hmm_handle_cpu_fault(struct mm_struct *mm,
> +			struct vm_area_struct *vma,
> +			pmd_t *pmdp, unsigned long addr,
> +			unsigned flags, pte_t orig_pte);
> +
> +int hmm_mm_fork(struct mm_struct *src_mm,
> +		struct mm_struct *dst_mm,
> +		struct vm_area_struct *dst_vma,
> +		pmd_t *dst_pmd,
> +		unsigned long start,
> +		unsigned long end);
> +
> +#else /* CONFIG_HMM */
> +
> +static inline int hmm_handle_cpu_fault(struct mm_struct *mm,
> +				       struct vm_area_struct *vma,
> +				       pmd_t *pmdp, unsigned long addr,
> +				       unsigned flags, pte_t orig_pte)
> +{
> +	return VM_FAULT_SIGBUS;
> +}
> +
> +static inline int hmm_mm_fork(struct mm_struct *src_mm,
> +			      struct mm_struct *dst_mm,
> +			      struct vm_area_struct *dst_vma,
> +			      pmd_t *dst_pmd,
> +			      unsigned long start,
> +			      unsigned long end)
> +{
> +	BUG();

s/BUG/BUILD_BUG/ ?

> +	return -ENOMEM;
> +}
> 
>  #endif /* CONFIG_HMM */
> +
> +
>  #endif
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 7ba7dcc..5c8b871 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -70,8 +70,19 @@ static inline int current_is_kswapd(void)
>  #define SWP_HWPOISON_NUM 0
>  #endif
> 
> +/*
> + * HMM (heterogeneous memory management) used when data is in remote memory.
> + */
> +#ifdef CONFIG_HMM
> +#define SWP_HMM_NUM 1
> +#define SWP_HMM		(MAX_SWAPFILES + SWP_MIGRATION_NUM + SWP_HWPOISON_NUM)
> +#else
> +#define SWP_HMM_NUM 0
> +#endif
> +
>  #define MAX_SWAPFILES \
> -	((1 << MAX_SWAPFILES_SHIFT) - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM)
> +	((1 << MAX_SWAPFILES_SHIFT) - SWP_MIGRATION_NUM - \
> +	 SWP_HWPOISON_NUM - SWP_HMM_NUM)
> 
>  /*
>   * Magic header for a swap area. The first part of the union is
> diff --git a/include/linux/swapops.h b/include/linux/swapops.h
> index 5c3a5f3..8c6ba9f 100644
> --- a/include/linux/swapops.h
> +++ b/include/linux/swapops.h
> @@ -227,7 +227,7 @@ static inline void num_poisoned_pages_inc(void)
>  }
>  #endif
> 
> -#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION)
> +#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION) || defined(CONFIG_HMM)
>  static inline int non_swap_entry(swp_entry_t entry)
>  {
>  	return swp_type(entry) >= MAX_SWAPFILES;
> @@ -239,4 +239,45 @@ static inline int non_swap_entry(swp_entry_t entry)
>  }
>  #endif
> 
> +#ifdef CONFIG_HMM
> +static inline swp_entry_t make_hmm_entry(void)
> +{
> +	/* We do not store anything inside the CPU page table entry (pte). */

pte is clear enough, no?

> +	return swp_entry(SWP_HMM, 0);
> +}
> +
> +static inline swp_entry_t make_hmm_entry_locked(void)
> +{
> +	/* We do not store anything inside the CPU page table entry (pte). */
> +	return swp_entry(SWP_HMM, 1);
> +}
> +
> +static inline swp_entry_t make_hmm_entry_poisonous(void)
> +{
> +	/* We do not store anything inside the CPU page table entry (pte). */
> +	return swp_entry(SWP_HMM, 2);
> +}
> +
> +static inline int is_hmm_entry(swp_entry_t entry)
> +{
> +	return (swp_type(entry) == SWP_HMM);
> +}
> +
> +static inline int is_hmm_entry_locked(swp_entry_t entry)
> +{
> +	return (swp_type(entry) == SWP_HMM) && (swp_offset(entry) == 1);
> +}
> +
> +static inline int is_hmm_entry_poisonous(swp_entry_t entry)
> +{
> +	return (swp_type(entry) == SWP_HMM) && (swp_offset(entry) == 2);
> +}

So SWP_HMM_LOCKED and SWP_HMM_POISON should be defined.

> +#else /* CONFIG_HMM */
> +static inline int is_hmm_entry(swp_entry_t swp)
> +{
> +	return 0;
> +}
> +#endif /* CONFIG_HMM */
> +
> +
>  #endif /* _LINUX_SWAPOPS_H */
> diff --git a/mm/hmm.c b/mm/hmm.c
> index 9e5017a..7fb493f 100644
> --- a/mm/hmm.c
> +++ b/mm/hmm.c
> @@ -416,6 +416,27 @@ static struct mmu_notifier_ops hmm_notifier_ops = {
>  };
> 
> 
> +int hmm_handle_cpu_fault(struct mm_struct *mm,
> +			struct vm_area_struct *vma,
> +			pmd_t *pmdp, unsigned long addr,
> +			unsigned flags, pte_t orig_pte)
> +{
> +	return VM_FAULT_SIGBUS;
> +}
> +EXPORT_SYMBOL(hmm_handle_cpu_fault);
> +
> +int hmm_mm_fork(struct mm_struct *src_mm,
> +		struct mm_struct *dst_mm,
> +		struct vm_area_struct *dst_vma,
> +		pmd_t *dst_pmd,
> +		unsigned long start,
> +		unsigned long end)
> +{
> +	return -ENOMEM;
> +}
> +EXPORT_SYMBOL(hmm_mm_fork);
> +
> +
>  struct mm_pt_iter {
>  	struct mm_struct	*mm;
>  	pte_t			*ptep;
> diff --git a/mm/memory.c b/mm/memory.c
> index bbab5e9..08bc37e 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -53,6 +53,7 @@
>  #include <linux/writeback.h>
>  #include <linux/memcontrol.h>
>  #include <linux/mmu_notifier.h>
> +#include <linux/hmm.h>
>  #include <linux/kallsyms.h>
>  #include <linux/swapops.h>
>  #include <linux/elf.h>
> @@ -894,9 +895,11 @@ static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
>  	pte_t *orig_src_pte, *orig_dst_pte;
>  	pte_t *src_pte, *dst_pte;
>  	spinlock_t *src_ptl, *dst_ptl;
> +	unsigned cnt_hmm_entry = 0;

s/cnt_hmm_entry/hmm_ptes/ ?

>  	int progress = 0;
>  	int rss[NR_MM_COUNTERS];
>  	swp_entry_t entry = (swp_entry_t){0};
> +	unsigned long start;
> 
>  again:
>  	init_rss_vec(rss);
> @@ -910,6 +913,7 @@ again:
>  	orig_src_pte = src_pte;
>  	orig_dst_pte = dst_pte;
>  	arch_enter_lazy_mmu_mode();
> +	start = addr;
> 
>  	do {
>  		/*
> @@ -926,6 +930,12 @@ again:
>  			progress++;
>  			continue;
>  		}
> +		if (unlikely(!pte_present(*src_pte))) {
> +			entry = pte_to_swp_entry(*src_pte);
> +
> +			if (is_hmm_entry(entry))
> +				cnt_hmm_entry++;
> +		}
>  		entry.val = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte,
>  							vma, addr, rss);
>  		if (entry.val)
> @@ -940,6 +950,15 @@ again:
>  	pte_unmap_unlock(orig_dst_pte, dst_ptl);
>  	cond_resched();
> 
> +	if (cnt_hmm_entry) {
> +		int ret;
> +
> +		ret = hmm_mm_fork(src_mm, dst_mm, dst_vma,
> +				  dst_pmd, start, end);

Given start, s/end/addr/, no?

> +		if (ret)
> +			return ret;
> +	}
> +
>  	if (entry.val) {
>  		if (add_swap_count_continuation(entry, GFP_KERNEL) < 0)
>  			return -ENOMEM;

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH v11 02/14] HMM: add special swap filetype for memory migrated to device v2.

[Jerome Glisse]

On Thu, Oct 22, 2015 at 03:52:53PM +0800, Hillf Danton wrote:
> > 
> > When migrating anonymous memory from system memory to device memory
> > CPU pte are replaced with special HMM swap entry so that page fault,
> > get user page (gup), fork, ... are properly redirected to HMM helpers.
> > 
> > This patch only add the new swap type entry and hooks HMM helpers
> > functions inside the page fault and fork code path.
> > 
> > Changed since v1:
> 
> But the subject line says this work is v11

This is the v11 of the whole patchset. But this particular patch only
add 2 different version (v2 at the end of subject line). I do not bump
version of patches each time i rebase this seems pointless.

> > diff --git a/include/linux/hmm.h b/include/linux/hmm.h
> > index 4bc132a..7c66513 100644
> > --- a/include/linux/hmm.h
> > +++ b/include/linux/hmm.h
> 
> I find no hmm.h in 4.3-rc6

This patchset depends on patchset i posted before this one and that the
introduction mail reference namely :

https://lkml.org/lkml/2015/10/21/739

[...]

> > +static inline int hmm_mm_fork(struct mm_struct *src_mm,
> > +			      struct mm_struct *dst_mm,
> > +			      struct vm_area_struct *dst_vma,
> > +			      pmd_t *dst_pmd,
> > +			      unsigned long start,
> > +			      unsigned long end)
> > +{
> > +	BUG();
> 
> s/BUG/BUILD_BUG/ ?

I use BUG(); to keep bisectability working. The core of this function
is implemented in a latter patch but this function is reference in
this one.

[...]

> > +#ifdef CONFIG_HMM
> > +static inline swp_entry_t make_hmm_entry(void)
> > +{
> > +	/* We do not store anything inside the CPU page table entry (pte). */
> 
> pte is clear enough, no?

Yes i will remove this redundancy.

[...]

> > +static inline int is_hmm_entry_poisonous(swp_entry_t entry)
> > +{
> > +	return (swp_type(entry) == SWP_HMM) && (swp_offset(entry) == 2);
> > +}
> 
> So SWP_HMM_LOCKED and SWP_HMM_POISON should be defined.

Good point.

[...]

> > @@ -894,9 +895,11 @@ static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
> >  	pte_t *orig_src_pte, *orig_dst_pte;
> >  	pte_t *src_pte, *dst_pte;
> >  	spinlock_t *src_ptl, *dst_ptl;
> > +	unsigned cnt_hmm_entry = 0;
> 
> s/cnt_hmm_entry/hmm_ptes/ ?
> 

Maybe hmm_swap_ptes is even better name in this context.

[...]

> > +	if (cnt_hmm_entry) {
> > +		int ret;
> > +
> > +		ret = hmm_mm_fork(src_mm, dst_mm, dst_vma,
> > +				  dst_pmd, start, end);
> 
> Given start, s/end/addr/, no?

No, end is the right upper limit here.

Cheers,
Jerome

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH v11 02/14] HMM: add special swap filetype for memory migrated to device v2.

[Hillf Danton]

> > > +	if (cnt_hmm_entry) {
> > > +		int ret;
> > > +
> > > +		ret = hmm_mm_fork(src_mm, dst_mm, dst_vma,
> > > +				  dst_pmd, start, end);
> >
> > Given start, s/end/addr/, no?
> 
> No, end is the right upper limit here.
> 
Then in the first loop, hmm_mm_fork is invoked for
the _entire_ range, from input addr to end.
In subsequent loops(if necessary), start is updated to
addr, and hmm_mm_fork is also invoked for remaining
range, from start to end.

Is the above overlap in range making sense?

Hillf

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

Re: [PATCH v11 02/14] HMM: add special swap filetype for memory migrated to device v2.

[Jerome Glisse]

On Fri, Oct 23, 2015 at 11:23:26AM +0800, Hillf Danton wrote:
> > > > +	if (cnt_hmm_entry) {
> > > > +		int ret;
> > > > +
> > > > +		ret = hmm_mm_fork(src_mm, dst_mm, dst_vma,
> > > > +				  dst_pmd, start, end);
> > >
> > > Given start, s/end/addr/, no?
> > 
> > No, end is the right upper limit here.
> > 
> Then in the first loop, hmm_mm_fork is invoked for
> the _entire_ range, from input addr to end.
> In subsequent loops(if necessary), start is updated to
> addr, and hmm_mm_fork is also invoked for remaining
> range, from start to end.
> 
> Is the above overlap in range making sense?

Well yes and no, hmm_mm_fork() will do nothing for address >= addr
i feel like end is easier to understand.

Cheers,
Jerome

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH v11 00/14] HMM anomymous memory migration to device memory

[Jérôme Glisse]

Minor fixes since last post, apply on top of 4.3rc6. Tree with
the patchset:

git://people.freedesktop.org/~glisse/linux hmm-v11 branch

This patchset implement anonymous memory migration for HMM.
See HMM patchset for full description of what is HMM and why
doing HMM :

https://lkml.org/lkml/2015/10/21/739

Seamless migration from system memory to device memory ie on CPU
access we migrate memory back to system memory so CPU can access
it again.

Design is simple, a new special swap type is added and CPU pte are
set to this special swap type for migrated memory. On CPU page fault
HMM use its mirror page table to find proper page into device memory
and migrate it back to system memory.

Migration to device memory involves several steps :
  - First CPU page table is updated to special pte and current
    pte is save to temporary array.
  - We check that all pte are for normal/real pages.
  - We check that no one holds an extra reference on the page.
  - At this point we know we are the only one know about that
    memory and we can safely copy it to device memory.
  - Once everything is copied and fine on device side we free
    the system ram pages.

Migration from device memory back to system memory is simpler:
  - We get exclusive access for each pte we want to migrate back
    (special swap pte value).
  - We allocate system memory (memcg and anon_vma handled here).
  - We copy back device memory content into system memory and
    update device page table to point to system memory.
  - We update CPU page table to point to new system memory.

Cheers,
JA(C)rA'me

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

[PATCH v11 02/14] HMM: add special swap filetype for memory migrated to device v2.

[Jérôme Glisse]

From: Jerome Glisse <jglisse@redhat.com>

When migrating anonymous memory from system memory to device memory
CPU pte are replaced with special HMM swap entry so that page fault,
get user page (gup), fork, ... are properly redirected to HMM helpers.

This patch only add the new swap type entry and hooks HMM helpers
functions inside the page fault and fork code path.

Changed since v1:
  - Fix name when of HMM CPU page fault function.

Signed-off-by: JA(C)rA'me Glisse <jglisse@redhat.com>
Signed-off-by: Sherry Cheung <SCheung@nvidia.com>
Signed-off-by: Subhash Gutti <sgutti@nvidia.com>
Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Signed-off-by: Jatin Kumar <jakumar@nvidia.com>
---
 include/linux/hmm.h     | 34 ++++++++++++++++++++++++++++++++++
 include/linux/swap.h    | 13 ++++++++++++-
 include/linux/swapops.h | 43 ++++++++++++++++++++++++++++++++++++++++++-
 mm/hmm.c                | 21 +++++++++++++++++++++
 mm/memory.c             | 22 ++++++++++++++++++++++
 5 files changed, 131 insertions(+), 2 deletions(-)

diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index 4bc132a..7c66513 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -272,6 +272,40 @@ void hmm_mirror_range_dirty(struct hmm_mirror *mirror,
 			    unsigned long start,
 			    unsigned long end);
 
+int hmm_handle_cpu_fault(struct mm_struct *mm,
+			struct vm_area_struct *vma,
+			pmd_t *pmdp, unsigned long addr,
+			unsigned flags, pte_t orig_pte);
+
+int hmm_mm_fork(struct mm_struct *src_mm,
+		struct mm_struct *dst_mm,
+		struct vm_area_struct *dst_vma,
+		pmd_t *dst_pmd,
+		unsigned long start,
+		unsigned long end);
+
+#else /* CONFIG_HMM */
+
+static inline int hmm_handle_cpu_fault(struct mm_struct *mm,
+				       struct vm_area_struct *vma,
+				       pmd_t *pmdp, unsigned long addr,
+				       unsigned flags, pte_t orig_pte)
+{
+	return VM_FAULT_SIGBUS;
+}
+
+static inline int hmm_mm_fork(struct mm_struct *src_mm,
+			      struct mm_struct *dst_mm,
+			      struct vm_area_struct *dst_vma,
+			      pmd_t *dst_pmd,
+			      unsigned long start,
+			      unsigned long end)
+{
+	BUG();
+	return -ENOMEM;
+}
 
 #endif /* CONFIG_HMM */
+
+
 #endif
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 7ba7dcc..5c8b871 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -70,8 +70,19 @@ static inline int current_is_kswapd(void)
 #define SWP_HWPOISON_NUM 0
 #endif
 
+/*
+ * HMM (heterogeneous memory management) used when data is in remote memory.
+ */
+#ifdef CONFIG_HMM
+#define SWP_HMM_NUM 1
+#define SWP_HMM		(MAX_SWAPFILES + SWP_MIGRATION_NUM + SWP_HWPOISON_NUM)
+#else
+#define SWP_HMM_NUM 0
+#endif
+
 #define MAX_SWAPFILES \
-	((1 << MAX_SWAPFILES_SHIFT) - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM)
+	((1 << MAX_SWAPFILES_SHIFT) - SWP_MIGRATION_NUM - \
+	 SWP_HWPOISON_NUM - SWP_HMM_NUM)
 
 /*
  * Magic header for a swap area. The first part of the union is
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 5c3a5f3..8c6ba9f 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -227,7 +227,7 @@ static inline void num_poisoned_pages_inc(void)
 }
 #endif
 
-#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION)
+#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION) || defined(CONFIG_HMM)
 static inline int non_swap_entry(swp_entry_t entry)
 {
 	return swp_type(entry) >= MAX_SWAPFILES;
@@ -239,4 +239,45 @@ static inline int non_swap_entry(swp_entry_t entry)
 }
 #endif
 
+#ifdef CONFIG_HMM
+static inline swp_entry_t make_hmm_entry(void)
+{
+	/* We do not store anything inside the CPU page table entry (pte). */
+	return swp_entry(SWP_HMM, 0);
+}
+
+static inline swp_entry_t make_hmm_entry_locked(void)
+{
+	/* We do not store anything inside the CPU page table entry (pte). */
+	return swp_entry(SWP_HMM, 1);
+}
+
+static inline swp_entry_t make_hmm_entry_poisonous(void)
+{
+	/* We do not store anything inside the CPU page table entry (pte). */
+	return swp_entry(SWP_HMM, 2);
+}
+
+static inline int is_hmm_entry(swp_entry_t entry)
+{
+	return (swp_type(entry) == SWP_HMM);
+}
+
+static inline int is_hmm_entry_locked(swp_entry_t entry)
+{
+	return (swp_type(entry) == SWP_HMM) && (swp_offset(entry) == 1);
+}
+
+static inline int is_hmm_entry_poisonous(swp_entry_t entry)
+{
+	return (swp_type(entry) == SWP_HMM) && (swp_offset(entry) == 2);
+}
+#else /* CONFIG_HMM */
+static inline int is_hmm_entry(swp_entry_t swp)
+{
+	return 0;
+}
+#endif /* CONFIG_HMM */
+
+
 #endif /* _LINUX_SWAPOPS_H */
diff --git a/mm/hmm.c b/mm/hmm.c
index 9e5017a..7fb493f 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -416,6 +416,27 @@ static struct mmu_notifier_ops hmm_notifier_ops = {
 };
 
 
+int hmm_handle_cpu_fault(struct mm_struct *mm,
+			struct vm_area_struct *vma,
+			pmd_t *pmdp, unsigned long addr,
+			unsigned flags, pte_t orig_pte)
+{
+	return VM_FAULT_SIGBUS;
+}
+EXPORT_SYMBOL(hmm_handle_cpu_fault);
+
+int hmm_mm_fork(struct mm_struct *src_mm,
+		struct mm_struct *dst_mm,
+		struct vm_area_struct *dst_vma,
+		pmd_t *dst_pmd,
+		unsigned long start,
+		unsigned long end)
+{
+	return -ENOMEM;
+}
+EXPORT_SYMBOL(hmm_mm_fork);
+
+
 struct mm_pt_iter {
 	struct mm_struct	*mm;
 	pte_t			*ptep;
diff --git a/mm/memory.c b/mm/memory.c
index bbab5e9..08bc37e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -53,6 +53,7 @@
 #include <linux/writeback.h>
 #include <linux/memcontrol.h>
 #include <linux/mmu_notifier.h>
+#include <linux/hmm.h>
 #include <linux/kallsyms.h>
 #include <linux/swapops.h>
 #include <linux/elf.h>
@@ -894,9 +895,11 @@ static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	pte_t *orig_src_pte, *orig_dst_pte;
 	pte_t *src_pte, *dst_pte;
 	spinlock_t *src_ptl, *dst_ptl;
+	unsigned cnt_hmm_entry = 0;
 	int progress = 0;
 	int rss[NR_MM_COUNTERS];
 	swp_entry_t entry = (swp_entry_t){0};
+	unsigned long start;
 
 again:
 	init_rss_vec(rss);
@@ -910,6 +913,7 @@ again:
 	orig_src_pte = src_pte;
 	orig_dst_pte = dst_pte;
 	arch_enter_lazy_mmu_mode();
+	start = addr;
 
 	do {
 		/*
@@ -926,6 +930,12 @@ again:
 			progress++;
 			continue;
 		}
+		if (unlikely(!pte_present(*src_pte))) {
+			entry = pte_to_swp_entry(*src_pte);
+
+			if (is_hmm_entry(entry))
+				cnt_hmm_entry++;
+		}
 		entry.val = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte,
 							vma, addr, rss);
 		if (entry.val)
@@ -940,6 +950,15 @@ again:
 	pte_unmap_unlock(orig_dst_pte, dst_ptl);
 	cond_resched();
 
+	if (cnt_hmm_entry) {
+		int ret;
+
+		ret = hmm_mm_fork(src_mm, dst_mm, dst_vma,
+				  dst_pmd, start, end);
+		if (ret)
+			return ret;
+	}
+
 	if (entry.val) {
 		if (add_swap_count_continuation(entry, GFP_KERNEL) < 0)
 			return -ENOMEM;
@@ -2489,6 +2508,9 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			migration_entry_wait(mm, pmd, address);
 		} else if (is_hwpoison_entry(entry)) {
 			ret = VM_FAULT_HWPOISON;
+		} else if (is_hmm_entry(entry)) {
+			ret = hmm_handle_cpu_fault(mm, vma, pmd, address,
+						   flags, orig_pte);
 		} else {
 			print_bad_pte(vma, address, orig_pte, NULL);
 			ret = VM_FAULT_SIGBUS;
-- 
2.4.3

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>