[CI 0/2] drm/mm: Add an iterator to optimally walk over holes suitable for an allocation

[CI 0/2] drm/mm: Add an iterator to optimally walk over holes suitable for an allocation

[Vivek Kasireddy]

The first patch is a drm core patch that replaces the for loop in
drm_mm_insert_node_in_range() with the iterator and would not
cause any functional changes. The second patch is a i915 driver
specific patch that also uses the iterator but solves a different
problem.

v2:
- Added a new patch to this series to fix a potential NULL
  dereference.
- Fixed a typo associated with the iterator introduced in the
  drm core patch.
- Added locking around the snippet in the i915 patch that
  traverses the GGTT hole nodes.

v3: (Tvrtko)
- Replaced mutex_lock with mutex_lock_interruptible_nested() in
  the i915 patch.

v4: (Tvrtko)
- Dropped the patch added in v2 as it was deemed unnecessary.

Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Nirmoy Das <nirmoy.das@intel.com>
Cc: Christian König <christian.koenig@amd.com>

Vivek Kasireddy (2):
  drm/mm: Add an iterator to optimally walk over holes for an allocation
    (v4)
  drm/i915/gem: Don't try to map and fence large scanout buffers (v9)

 drivers/gpu/drm/drm_mm.c        |  32 ++++----
 drivers/gpu/drm/i915/i915_gem.c | 128 +++++++++++++++++++++++---------
 include/drm/drm_mm.h            |  36 +++++++++
 3 files changed, 145 insertions(+), 51 deletions(-)

-- 
2.34.1

[CI 1/2] drm/mm: Add an iterator to optimally walk over holes for an allocation (v4)

[Vivek Kasireddy]

This iterator relies on drm_mm_first_hole() and drm_mm_next_hole()
functions to identify suitable holes for an allocation of a given
size by efficiently traversing the rbtree associated with the given
allocator.

It replaces the for loop in drm_mm_insert_node_in_range() and can
also be used by drm drivers to quickly identify holes of a certain
size within a given range.

v2: (Tvrtko)
- Prepend a double underscore for the newly exported first/next_hole
- s/each_best_hole/each_suitable_hole/g
- Mask out DRM_MM_INSERT_ONCE from the mode before calling
  first/next_hole and elsewhere.

v3: (Tvrtko)
- Reduce the number of hunks by retaining the "mode" variable name

v4:
- Typo: s/__drm_mm_next_hole(.., hole/__drm_mm_next_hole(.., pos

Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Acked-by: Christian König <christian.koenig@amd.com>
Suggested-by: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
---
 drivers/gpu/drm/drm_mm.c | 32 +++++++++++++++-----------------
 include/drm/drm_mm.h     | 36 ++++++++++++++++++++++++++++++++++++
 2 files changed, 51 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index 8257f9d4f619..8efea548ae9f 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -352,10 +352,10 @@ static struct drm_mm_node *find_hole_addr(struct drm_mm *mm, u64 addr, u64 size)
 	return node;
 }
 
-static struct drm_mm_node *
-first_hole(struct drm_mm *mm,
-	   u64 start, u64 end, u64 size,
-	   enum drm_mm_insert_mode mode)
+struct drm_mm_node *
+__drm_mm_first_hole(struct drm_mm *mm,
+		    u64 start, u64 end, u64 size,
+		    enum drm_mm_insert_mode mode)
 {
 	switch (mode) {
 	default:
@@ -374,6 +374,7 @@ first_hole(struct drm_mm *mm,
 						hole_stack);
 	}
 }
+EXPORT_SYMBOL(__drm_mm_first_hole);
 
 /**
  * DECLARE_NEXT_HOLE_ADDR - macro to declare next hole functions
@@ -410,11 +411,11 @@ static struct drm_mm_node *name(struct drm_mm_node *entry, u64 size)	\
 DECLARE_NEXT_HOLE_ADDR(next_hole_high_addr, rb_left, rb_right)
 DECLARE_NEXT_HOLE_ADDR(next_hole_low_addr, rb_right, rb_left)
 
-static struct drm_mm_node *
-next_hole(struct drm_mm *mm,
-	  struct drm_mm_node *node,
-	  u64 size,
-	  enum drm_mm_insert_mode mode)
+struct drm_mm_node *
+__drm_mm_next_hole(struct drm_mm *mm,
+		   struct drm_mm_node *node,
+		   u64 size,
+		   enum drm_mm_insert_mode mode)
 {
 	switch (mode) {
 	default:
@@ -432,6 +433,7 @@ next_hole(struct drm_mm *mm,
 		return &node->hole_stack == &mm->hole_stack ? NULL : node;
 	}
 }
+EXPORT_SYMBOL(__drm_mm_next_hole);
 
 /**
  * drm_mm_reserve_node - insert an pre-initialized node
@@ -516,11 +518,11 @@ int drm_mm_insert_node_in_range(struct drm_mm * const mm,
 				u64 size, u64 alignment,
 				unsigned long color,
 				u64 range_start, u64 range_end,
-				enum drm_mm_insert_mode mode)
+				enum drm_mm_insert_mode caller_mode)
 {
 	struct drm_mm_node *hole;
 	u64 remainder_mask;
-	bool once;
+	enum drm_mm_insert_mode mode = caller_mode & ~DRM_MM_INSERT_ONCE;
 
 	DRM_MM_BUG_ON(range_start > range_end);
 
@@ -533,13 +535,9 @@ int drm_mm_insert_node_in_range(struct drm_mm * const mm,
 	if (alignment <= 1)
 		alignment = 0;
 
-	once = mode & DRM_MM_INSERT_ONCE;
-	mode &= ~DRM_MM_INSERT_ONCE;
-
 	remainder_mask = is_power_of_2(alignment) ? alignment - 1 : 0;
-	for (hole = first_hole(mm, range_start, range_end, size, mode);
-	     hole;
-	     hole = once ? NULL : next_hole(mm, hole, size, mode)) {
+	drm_mm_for_each_suitable_hole(hole, mm, range_start, range_end,
+				      size, mode) {
 		u64 hole_start = __drm_mm_hole_node_start(hole);
 		u64 hole_end = hole_start + hole->hole_size;
 		u64 adj_start, adj_end;
diff --git a/include/drm/drm_mm.h b/include/drm/drm_mm.h
index ac33ba1b18bc..dff6db627807 100644
--- a/include/drm/drm_mm.h
+++ b/include/drm/drm_mm.h
@@ -400,6 +400,42 @@ static inline u64 drm_mm_hole_node_end(const struct drm_mm_node *hole_node)
 	     1 : 0; \
 	     pos = list_next_entry(pos, hole_stack))
 
+struct drm_mm_node *
+__drm_mm_first_hole(struct drm_mm *mm,
+		    u64 start, u64 end, u64 size,
+		    enum drm_mm_insert_mode mode);
+
+struct drm_mm_node *
+__drm_mm_next_hole(struct drm_mm *mm,
+		   struct drm_mm_node *node,
+		   u64 size,
+		   enum drm_mm_insert_mode mode);
+
+/**
+ * drm_mm_for_each_suitable_hole - iterator to optimally walk over all
+ * holes that can fit an allocation of the given @size.
+ * @pos: &drm_mm_node used internally to track progress
+ * @mm: &drm_mm allocator to walk
+ * @range_start: start of the allowed range for the allocation
+ * @range_end: end of the allowed range for the allocation
+ * @size: size of the allocation
+ * @mode: fine-tune the allocation search
+ *
+ * This iterator walks over all holes suitable for the allocation of given
+ * @size in a very efficient manner. It is implemented by calling
+ * drm_mm_first_hole() and drm_mm_next_hole() which identify the
+ * appropriate holes within the given range by efficiently traversing the
+ * rbtree associated with @mm.
+ */
+#define drm_mm_for_each_suitable_hole(pos, mm, range_start, range_end, \
+				      size, mode) \
+	for (pos = __drm_mm_first_hole(mm, range_start, range_end, size, \
+				       mode & ~DRM_MM_INSERT_ONCE); \
+	     pos; \
+	     pos = mode & DRM_MM_INSERT_ONCE ? \
+	     NULL : __drm_mm_next_hole(mm, pos, size, \
+				       mode & ~DRM_MM_INSERT_ONCE))
+
 /*
  * Basic range manager support (drm_mm.c)
  */
-- 
2.34.1

Re: [Intel-gfx] [CI 1/2] drm/mm: Add an iterator to optimally walk over holes for an allocation (v4)

[Tvrtko Ursulin]

Hi Vivek,

On 27/02/2022 17:29, Vivek Kasireddy wrote:
> This iterator relies on drm_mm_first_hole() and drm_mm_next_hole()
> functions to identify suitable holes for an allocation of a given
> size by efficiently traversing the rbtree associated with the given
> allocator.
> 
> It replaces the for loop in drm_mm_insert_node_in_range() and can
> also be used by drm drivers to quickly identify holes of a certain
> size within a given range.
> 
> v2: (Tvrtko)
> - Prepend a double underscore for the newly exported first/next_hole
> - s/each_best_hole/each_suitable_hole/g
> - Mask out DRM_MM_INSERT_ONCE from the mode before calling
>    first/next_hole and elsewhere.
> 
> v3: (Tvrtko)
> - Reduce the number of hunks by retaining the "mode" variable name
> 
> v4:
> - Typo: s/__drm_mm_next_hole(.., hole/__drm_mm_next_hole(.., pos
> 
> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> Acked-by: Christian König <christian.koenig@amd.com>
> Suggested-by: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
> Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
> ---
>   drivers/gpu/drm/drm_mm.c | 32 +++++++++++++++-----------------
>   include/drm/drm_mm.h     | 36 ++++++++++++++++++++++++++++++++++++
>   2 files changed, 51 insertions(+), 17 deletions(-)
> 
> diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
> index 8257f9d4f619..8efea548ae9f 100644
> --- a/drivers/gpu/drm/drm_mm.c
> +++ b/drivers/gpu/drm/drm_mm.c
> @@ -352,10 +352,10 @@ static struct drm_mm_node *find_hole_addr(struct drm_mm *mm, u64 addr, u64 size)
>   	return node;
>   }
>   
> -static struct drm_mm_node *
> -first_hole(struct drm_mm *mm,
> -	   u64 start, u64 end, u64 size,
> -	   enum drm_mm_insert_mode mode)
> +struct drm_mm_node *
> +__drm_mm_first_hole(struct drm_mm *mm,
> +		    u64 start, u64 end, u64 size,
> +		    enum drm_mm_insert_mode mode)
>   {
>   	switch (mode) {
>   	default:
> @@ -374,6 +374,7 @@ first_hole(struct drm_mm *mm,
>   						hole_stack);
>   	}
>   }
> +EXPORT_SYMBOL(__drm_mm_first_hole);
>   
>   /**
>    * DECLARE_NEXT_HOLE_ADDR - macro to declare next hole functions
> @@ -410,11 +411,11 @@ static struct drm_mm_node *name(struct drm_mm_node *entry, u64 size)	\
>   DECLARE_NEXT_HOLE_ADDR(next_hole_high_addr, rb_left, rb_right)
>   DECLARE_NEXT_HOLE_ADDR(next_hole_low_addr, rb_right, rb_left)
>   
> -static struct drm_mm_node *
> -next_hole(struct drm_mm *mm,
> -	  struct drm_mm_node *node,
> -	  u64 size,
> -	  enum drm_mm_insert_mode mode)
> +struct drm_mm_node *
> +__drm_mm_next_hole(struct drm_mm *mm,
> +		   struct drm_mm_node *node,
> +		   u64 size,
> +		   enum drm_mm_insert_mode mode)
>   {
>   	switch (mode) {
>   	default:
> @@ -432,6 +433,7 @@ next_hole(struct drm_mm *mm,
>   		return &node->hole_stack == &mm->hole_stack ? NULL : node;
>   	}
>   }
> +EXPORT_SYMBOL(__drm_mm_next_hole);
>   
>   /**
>    * drm_mm_reserve_node - insert an pre-initialized node
> @@ -516,11 +518,11 @@ int drm_mm_insert_node_in_range(struct drm_mm * const mm,
>   				u64 size, u64 alignment,
>   				unsigned long color,
>   				u64 range_start, u64 range_end,
> -				enum drm_mm_insert_mode mode)
> +				enum drm_mm_insert_mode caller_mode)
>   {
>   	struct drm_mm_node *hole;
>   	u64 remainder_mask;
> -	bool once;
> +	enum drm_mm_insert_mode mode = caller_mode & ~DRM_MM_INSERT_ONCE;
>   
>   	DRM_MM_BUG_ON(range_start > range_end);
>   
> @@ -533,13 +535,9 @@ int drm_mm_insert_node_in_range(struct drm_mm * const mm,
>   	if (alignment <= 1)
>   		alignment = 0;
>   
> -	once = mode & DRM_MM_INSERT_ONCE;
> -	mode &= ~DRM_MM_INSERT_ONCE;
> -
>   	remainder_mask = is_power_of_2(alignment) ? alignment - 1 : 0;
> -	for (hole = first_hole(mm, range_start, range_end, size, mode);
> -	     hole;
> -	     hole = once ? NULL : next_hole(mm, hole, size, mode)) {
> +	drm_mm_for_each_suitable_hole(hole, mm, range_start, range_end,
> +				      size, mode) {

I was doing one last read of the patch before I ask the maintainers 
where to merge it and realized - don't you need to pass in the 
caller_mode just here (not mode which has been masked out from "once")? 
Otherwise "once" mode will not be respected by the iterator.

Regards,

Tvrtko

>   		u64 hole_start = __drm_mm_hole_node_start(hole);
>   		u64 hole_end = hole_start + hole->hole_size;
>   		u64 adj_start, adj_end;
> diff --git a/include/drm/drm_mm.h b/include/drm/drm_mm.h
> index ac33ba1b18bc..dff6db627807 100644
> --- a/include/drm/drm_mm.h
> +++ b/include/drm/drm_mm.h
> @@ -400,6 +400,42 @@ static inline u64 drm_mm_hole_node_end(const struct drm_mm_node *hole_node)
>   	     1 : 0; \
>   	     pos = list_next_entry(pos, hole_stack))
>   
> +struct drm_mm_node *
> +__drm_mm_first_hole(struct drm_mm *mm,
> +		    u64 start, u64 end, u64 size,
> +		    enum drm_mm_insert_mode mode);
> +
> +struct drm_mm_node *
> +__drm_mm_next_hole(struct drm_mm *mm,
> +		   struct drm_mm_node *node,
> +		   u64 size,
> +		   enum drm_mm_insert_mode mode);
> +
> +/**
> + * drm_mm_for_each_suitable_hole - iterator to optimally walk over all
> + * holes that can fit an allocation of the given @size.
> + * @pos: &drm_mm_node used internally to track progress
> + * @mm: &drm_mm allocator to walk
> + * @range_start: start of the allowed range for the allocation
> + * @range_end: end of the allowed range for the allocation
> + * @size: size of the allocation
> + * @mode: fine-tune the allocation search
> + *
> + * This iterator walks over all holes suitable for the allocation of given
> + * @size in a very efficient manner. It is implemented by calling
> + * drm_mm_first_hole() and drm_mm_next_hole() which identify the
> + * appropriate holes within the given range by efficiently traversing the
> + * rbtree associated with @mm.
> + */
> +#define drm_mm_for_each_suitable_hole(pos, mm, range_start, range_end, \
> +				      size, mode) \
> +	for (pos = __drm_mm_first_hole(mm, range_start, range_end, size, \
> +				       mode & ~DRM_MM_INSERT_ONCE); \
> +	     pos; \
> +	     pos = mode & DRM_MM_INSERT_ONCE ? \
> +	     NULL : __drm_mm_next_hole(mm, pos, size, \
> +				       mode & ~DRM_MM_INSERT_ONCE))
> +
>   /*
>    * Basic range manager support (drm_mm.c)
>    */

RE: [Intel-gfx] [CI 1/2] drm/mm: Add an iterator to optimally walk over holes for an allocation (v4)

[Kasireddy, Vivek]

Hi Tvrtko,

> 
> Hi Vivek,
> 
> On 27/02/2022 17:29, Vivek Kasireddy wrote:
> > This iterator relies on drm_mm_first_hole() and drm_mm_next_hole()
> > functions to identify suitable holes for an allocation of a given
> > size by efficiently traversing the rbtree associated with the given
> > allocator.
> >
> > It replaces the for loop in drm_mm_insert_node_in_range() and can
> > also be used by drm drivers to quickly identify holes of a certain
> > size within a given range.
> >
> > v2: (Tvrtko)
> > - Prepend a double underscore for the newly exported first/next_hole
> > - s/each_best_hole/each_suitable_hole/g
> > - Mask out DRM_MM_INSERT_ONCE from the mode before calling
> >    first/next_hole and elsewhere.
> >
> > v3: (Tvrtko)
> > - Reduce the number of hunks by retaining the "mode" variable name
> >
> > v4:
> > - Typo: s/__drm_mm_next_hole(.., hole/__drm_mm_next_hole(.., pos
> >
> > Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> > Acked-by: Christian König <christian.koenig@amd.com>
> > Suggested-by: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
> > Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
> > ---
> >   drivers/gpu/drm/drm_mm.c | 32 +++++++++++++++-----------------
> >   include/drm/drm_mm.h     | 36 ++++++++++++++++++++++++++++++++++++
> >   2 files changed, 51 insertions(+), 17 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
> > index 8257f9d4f619..8efea548ae9f 100644
> > --- a/drivers/gpu/drm/drm_mm.c
> > +++ b/drivers/gpu/drm/drm_mm.c
> > @@ -352,10 +352,10 @@ static struct drm_mm_node *find_hole_addr(struct drm_mm
> *mm, u64 addr, u64 size)
> >   	return node;
> >   }
> >
> > -static struct drm_mm_node *
> > -first_hole(struct drm_mm *mm,
> > -	   u64 start, u64 end, u64 size,
> > -	   enum drm_mm_insert_mode mode)
> > +struct drm_mm_node *
> > +__drm_mm_first_hole(struct drm_mm *mm,
> > +		    u64 start, u64 end, u64 size,
> > +		    enum drm_mm_insert_mode mode)
> >   {
> >   	switch (mode) {
> >   	default:
> > @@ -374,6 +374,7 @@ first_hole(struct drm_mm *mm,
> >   						hole_stack);
> >   	}
> >   }
> > +EXPORT_SYMBOL(__drm_mm_first_hole);
> >
> >   /**
> >    * DECLARE_NEXT_HOLE_ADDR - macro to declare next hole functions
> > @@ -410,11 +411,11 @@ static struct drm_mm_node *name(struct drm_mm_node
> *entry, u64 size)	\
> >   DECLARE_NEXT_HOLE_ADDR(next_hole_high_addr, rb_left, rb_right)
> >   DECLARE_NEXT_HOLE_ADDR(next_hole_low_addr, rb_right, rb_left)
> >
> > -static struct drm_mm_node *
> > -next_hole(struct drm_mm *mm,
> > -	  struct drm_mm_node *node,
> > -	  u64 size,
> > -	  enum drm_mm_insert_mode mode)
> > +struct drm_mm_node *
> > +__drm_mm_next_hole(struct drm_mm *mm,
> > +		   struct drm_mm_node *node,
> > +		   u64 size,
> > +		   enum drm_mm_insert_mode mode)
> >   {
> >   	switch (mode) {
> >   	default:
> > @@ -432,6 +433,7 @@ next_hole(struct drm_mm *mm,
> >   		return &node->hole_stack == &mm->hole_stack ? NULL : node;
> >   	}
> >   }
> > +EXPORT_SYMBOL(__drm_mm_next_hole);
> >
> >   /**
> >    * drm_mm_reserve_node - insert an pre-initialized node
> > @@ -516,11 +518,11 @@ int drm_mm_insert_node_in_range(struct drm_mm * const
> mm,
> >   				u64 size, u64 alignment,
> >   				unsigned long color,
> >   				u64 range_start, u64 range_end,
> > -				enum drm_mm_insert_mode mode)
> > +				enum drm_mm_insert_mode caller_mode)
> >   {
> >   	struct drm_mm_node *hole;
> >   	u64 remainder_mask;
> > -	bool once;
> > +	enum drm_mm_insert_mode mode = caller_mode &
> ~DRM_MM_INSERT_ONCE;
> >
> >   	DRM_MM_BUG_ON(range_start > range_end);
> >
> > @@ -533,13 +535,9 @@ int drm_mm_insert_node_in_range(struct drm_mm * const
> mm,
> >   	if (alignment <= 1)
> >   		alignment = 0;
> >
> > -	once = mode & DRM_MM_INSERT_ONCE;
> > -	mode &= ~DRM_MM_INSERT_ONCE;
> > -
> >   	remainder_mask = is_power_of_2(alignment) ? alignment - 1 : 0;
> > -	for (hole = first_hole(mm, range_start, range_end, size, mode);
> > -	     hole;
> > -	     hole = once ? NULL : next_hole(mm, hole, size, mode)) {
> > +	drm_mm_for_each_suitable_hole(hole, mm, range_start, range_end,
> > +				      size, mode) {
> 
> I was doing one last read of the patch before I ask the maintainers
> where to merge it and realized - don't you need to pass in the
> caller_mode just here (not mode which has been masked out from "once")?
> Otherwise "once" mode will not be respected by the iterator.
[Kasireddy, Vivek] Right, yet another typo; it should have been caller_mode
instead of mode. Let me fix it and run it through another CI cycle.

Thanks,
Vivek
> 
> Regards,
> 
> Tvrtko
> 
> >   		u64 hole_start = __drm_mm_hole_node_start(hole);
> >   		u64 hole_end = hole_start + hole->hole_size;
> >   		u64 adj_start, adj_end;
> > diff --git a/include/drm/drm_mm.h b/include/drm/drm_mm.h
> > index ac33ba1b18bc..dff6db627807 100644
> > --- a/include/drm/drm_mm.h
> > +++ b/include/drm/drm_mm.h
> > @@ -400,6 +400,42 @@ static inline u64 drm_mm_hole_node_end(const struct
> drm_mm_node *hole_node)
> >   	     1 : 0; \
> >   	     pos = list_next_entry(pos, hole_stack))
> >
> > +struct drm_mm_node *
> > +__drm_mm_first_hole(struct drm_mm *mm,
> > +		    u64 start, u64 end, u64 size,
> > +		    enum drm_mm_insert_mode mode);
> > +
> > +struct drm_mm_node *
> > +__drm_mm_next_hole(struct drm_mm *mm,
> > +		   struct drm_mm_node *node,
> > +		   u64 size,
> > +		   enum drm_mm_insert_mode mode);
> > +
> > +/**
> > + * drm_mm_for_each_suitable_hole - iterator to optimally walk over all
> > + * holes that can fit an allocation of the given @size.
> > + * @pos: &drm_mm_node used internally to track progress
> > + * @mm: &drm_mm allocator to walk
> > + * @range_start: start of the allowed range for the allocation
> > + * @range_end: end of the allowed range for the allocation
> > + * @size: size of the allocation
> > + * @mode: fine-tune the allocation search
> > + *
> > + * This iterator walks over all holes suitable for the allocation of given
> > + * @size in a very efficient manner. It is implemented by calling
> > + * drm_mm_first_hole() and drm_mm_next_hole() which identify the
> > + * appropriate holes within the given range by efficiently traversing the
> > + * rbtree associated with @mm.
> > + */
> > +#define drm_mm_for_each_suitable_hole(pos, mm, range_start, range_end, \
> > +				      size, mode) \
> > +	for (pos = __drm_mm_first_hole(mm, range_start, range_end, size, \
> > +				       mode & ~DRM_MM_INSERT_ONCE); \
> > +	     pos; \
> > +	     pos = mode & DRM_MM_INSERT_ONCE ? \
> > +	     NULL : __drm_mm_next_hole(mm, pos, size, \
> > +				       mode & ~DRM_MM_INSERT_ONCE))
> > +
> >   /*
> >    * Basic range manager support (drm_mm.c)
> >    */

[CI 2/2] drm/i915/gem: Don't try to map and fence large scanout buffers (v9)

[Vivek Kasireddy]

On platforms capable of allowing 8K (7680 x 4320) modes, pinning 2 or
more framebuffers/scanout buffers results in only one that is mappable/
fenceable. Therefore, pageflipping between these 2 FBs where only one
is mappable/fenceable creates latencies large enough to miss alternate
vblanks thereby producing less optimal framerate.

This mainly happens because when i915_gem_object_pin_to_display_plane()
is called to pin one of the FB objs, the associated vma is identified
as misplaced and therefore i915_vma_unbind() is called which unbinds and
evicts it. This misplaced vma gets subseqently pinned only when
i915_gem_object_ggtt_pin_ww() is called without PIN_MAPPABLE. This
results in a latency of ~10ms and happens every other vblank/repaint cycle.
Therefore, to fix this issue, we try to see if there is space to map
at-least two objects of a given size and return early if there isn't. This
would ensure that we do not try with PIN_MAPPABLE for any objects that
are too big to map thereby preventing unncessary unbind.

Testcase:
Running Weston and weston-simple-egl on an Alderlake_S (ADLS) platform
with a 8K@60 mode results in only ~40 FPS. Since upstream Weston submits
a frame ~7ms before the next vblank, the latencies seen between atomic
commit and flip event are 7, 24 (7 + 16.66), 7, 24..... suggesting that
it misses the vblank every other frame.

Here is the ftrace snippet that shows the source of the ~10ms latency:
              i915_gem_object_pin_to_display_plane() {
0.102 us   |    i915_gem_object_set_cache_level();
                i915_gem_object_ggtt_pin_ww() {
0.390 us   |      i915_vma_instance();
0.178 us   |      i915_vma_misplaced();
                  i915_vma_unbind() {
                  __i915_active_wait() {
0.082 us   |        i915_active_acquire_if_busy();
0.475 us   |      }
                  intel_runtime_pm_get() {
0.087 us   |        intel_runtime_pm_acquire();
0.259 us   |      }
                  __i915_active_wait() {
0.085 us   |        i915_active_acquire_if_busy();
0.240 us   |      }
                  __i915_vma_evict() {
                    ggtt_unbind_vma() {
                      gen8_ggtt_clear_range() {
10507.255 us |        }
10507.689 us |      }
10508.516 us |   }

v2: Instead of using bigjoiner checks, determine whether a scanout
    buffer is too big by checking to see if it is possible to map
    two of them into the ggtt.

v3 (Ville):
- Count how many fb objects can be fit into the available holes
  instead of checking for a hole twice the object size.
- Take alignment constraints into account.
- Limit this large scanout buffer check to >= Gen 11 platforms.

v4:
- Remove existing heuristic that checks just for size. (Ville)
- Return early if we find space to map at-least two objects. (Tvrtko)
- Slightly update the commit message.

v5: (Tvrtko)
- Rename the function to indicate that the object may be too big to
  map into the aperture.
- Account for guard pages while calculating the total size required
  for the object.
- Do not subject all objects to the heuristic check and instead
  consider objects only of a certain size.
- Do the hole walk using the rbtree.
- Preserve the existing PIN_NONBLOCK logic.
- Drop the PIN_MAPPABLE check while pinning the VMA.

v6: (Tvrtko)
- Return 0 on success and the specific error code on failure to
  preserve the existing behavior.

v7: (Ville)
- Drop the HAS_GMCH(i915), DISPLAY_VER(i915) < 11 and
  size < ggtt->mappable_end / 4 checks.
- Drop the redundant check that is based on previous heuristic.

v8:
- Make sure that we are holding the mutex associated with ggtt vm
  as we traverse the hole nodes.

v9: (Tvrtko)
- Use mutex_lock_interruptible_nested() instead of mutex_lock().

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Manasi Navare <manasi.d.navare@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c | 128 +++++++++++++++++++++++---------
 1 file changed, 94 insertions(+), 34 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 2e10187cd0a0..4bef9eaa8b2e 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -49,6 +49,7 @@
 #include "gem/i915_gem_pm.h"
 #include "gem/i915_gem_region.h"
 #include "gem/i915_gem_userptr.h"
+#include "gem/i915_gem_tiling.h"
 #include "gt/intel_engine_user.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
@@ -879,6 +880,96 @@ static void discard_ggtt_vma(struct i915_vma *vma)
 	spin_unlock(&obj->vma.lock);
 }
 
+static int
+i915_gem_object_fits_in_aperture(struct drm_i915_gem_object *obj,
+				 u64 alignment, u64 flags)
+{
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	struct i915_ggtt *ggtt = to_gt(i915)->ggtt;
+	struct drm_mm_node *hole;
+	u64 hole_start, hole_end, start, end;
+	u64 fence_size, fence_alignment;
+	unsigned int count = 0;
+	int err = 0;
+
+	/*
+	 * If the required space is larger than the available
+	 * aperture, we will not able to find a slot for the
+	 * object and unbinding the object now will be in
+	 * vain. Worse, doing so may cause us to ping-pong
+	 * the object in and out of the Global GTT and
+	 * waste a lot of cycles under the mutex.
+	 */
+	if (obj->base.size > ggtt->mappable_end)
+		return -E2BIG;
+
+	/*
+	 * If NONBLOCK is set the caller is optimistically
+	 * trying to cache the full object within the mappable
+	 * aperture, and *must* have a fallback in place for
+	 * situations where we cannot bind the object. We
+	 * can be a little more lax here and use the fallback
+	 * more often to avoid costly migrations of ourselves
+	 * and other objects within the aperture.
+	 */
+	if (!(flags & PIN_NONBLOCK))
+		return 0;
+
+	/*
+	 * Other objects such as batchbuffers are fairly small compared
+	 * to FBs and are unlikely to exahust the aperture space.
+	 * Therefore, return early if this obj is not an FB.
+	 */
+	if (!i915_gem_object_is_framebuffer(obj))
+		return 0;
+
+	fence_size = i915_gem_fence_size(i915, obj->base.size,
+					 i915_gem_object_get_tiling(obj),
+					 i915_gem_object_get_stride(obj));
+
+	if (i915_vm_has_cache_coloring(&ggtt->vm))
+		fence_size += 2 * I915_GTT_PAGE_SIZE;
+
+	fence_alignment = i915_gem_fence_alignment(i915, obj->base.size,
+						   i915_gem_object_get_tiling(obj),
+						   i915_gem_object_get_stride(obj));
+	alignment = max_t(u64, alignment, fence_alignment);
+
+	err = mutex_lock_interruptible_nested(&ggtt->vm.mutex, 0);
+	if (err)
+		return err;
+
+	/*
+	 * Assuming this object is a large scanout buffer, we try to find
+	 * out if there is room to map at-least two of them. There could
+	 * be space available to map one but to be consistent, we try to
+	 * avoid mapping/fencing any of them.
+	 */
+	drm_mm_for_each_suitable_hole(hole, &ggtt->vm.mm, 0, ggtt->mappable_end,
+				      fence_size, DRM_MM_INSERT_LOW) {
+		hole_start = drm_mm_hole_node_start(hole);
+		hole_end = hole_start + hole->hole_size;
+
+		do {
+			start = round_up(hole_start, alignment);
+			end = min_t(u64, hole_end, ggtt->mappable_end);
+
+			if (range_overflows(start, fence_size, end))
+				break;
+
+			if (++count >= 2) {
+				mutex_unlock(&ggtt->vm.mutex);
+				return 0;
+			}
+
+			hole_start = start + fence_size;
+		} while (1);
+	}
+
+	mutex_unlock(&ggtt->vm.mutex);
+	return -ENOSPC;
+}
+
 struct i915_vma *
 i915_gem_object_ggtt_pin_ww(struct drm_i915_gem_object *obj,
 			    struct i915_gem_ww_ctx *ww,
@@ -894,36 +985,9 @@ i915_gem_object_ggtt_pin_ww(struct drm_i915_gem_object *obj,
 
 	if (flags & PIN_MAPPABLE &&
 	    (!view || view->type == I915_GGTT_VIEW_NORMAL)) {
-		/*
-		 * If the required space is larger than the available
-		 * aperture, we will not able to find a slot for the
-		 * object and unbinding the object now will be in
-		 * vain. Worse, doing so may cause us to ping-pong
-		 * the object in and out of the Global GTT and
-		 * waste a lot of cycles under the mutex.
-		 */
-		if (obj->base.size > ggtt->mappable_end)
-			return ERR_PTR(-E2BIG);
-
-		/*
-		 * If NONBLOCK is set the caller is optimistically
-		 * trying to cache the full object within the mappable
-		 * aperture, and *must* have a fallback in place for
-		 * situations where we cannot bind the object. We
-		 * can be a little more lax here and use the fallback
-		 * more often to avoid costly migrations of ourselves
-		 * and other objects within the aperture.
-		 *
-		 * Half-the-aperture is used as a simple heuristic.
-		 * More interesting would to do search for a free
-		 * block prior to making the commitment to unbind.
-		 * That caters for the self-harm case, and with a
-		 * little more heuristics (e.g. NOFAULT, NOEVICT)
-		 * we could try to minimise harm to others.
-		 */
-		if (flags & PIN_NONBLOCK &&
-		    obj->base.size > ggtt->mappable_end / 2)
-			return ERR_PTR(-ENOSPC);
+		ret = i915_gem_object_fits_in_aperture(obj, alignment, flags);
+		if (ret)
+			return ERR_PTR(ret);
 	}
 
 new_vma:
@@ -935,10 +999,6 @@ i915_gem_object_ggtt_pin_ww(struct drm_i915_gem_object *obj,
 		if (flags & PIN_NONBLOCK) {
 			if (i915_vma_is_pinned(vma) || i915_vma_is_active(vma))
 				return ERR_PTR(-ENOSPC);
-
-			if (flags & PIN_MAPPABLE &&
-			    vma->fence_size > ggtt->mappable_end / 2)
-				return ERR_PTR(-ENOSPC);
 		}
 
 		if (i915_vma_is_pinned(vma) || i915_vma_is_active(vma)) {
-- 
2.34.1