[PATCH 1/3] drm/ttm: add set_pages_wb for handling page order more than zero

[PATCH 1/3] drm/ttm: add set_pages_wb for handling page order more than zero

[Roger He]

Change-Id: Idf5ccb579d264b343199d8b8344bddeec2c0019f
Signed-off-by: Roger He <Hongbo.He@amd.com>
---
 drivers/gpu/drm/ttm/ttm_page_alloc.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index a8b2bfa..cdbb731 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -223,6 +223,17 @@ static struct kobj_type ttm_pool_kobj_type = {
 static struct ttm_pool_manager *_manager;
 
 #ifndef CONFIG_X86
+static int set_pages_wb(struct page *page, int numpages)
+{
+#if IS_ENABLED(CONFIG_AGP)
+	int i;
+
+	for (i = 0; i < numpages; i++)
+		unmap_page_from_agp(page++);
+#endif
+	return 0;
+}
+
 static int set_pages_array_wb(struct page **pages, int addrinarray)
 {
 #if IS_ENABLED(CONFIG_AGP)
-- 
2.7.4

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH 2/3] drm/ttm: add page order support in ttm_pages_put

[Roger He]

Change-Id: Ia55b206d95812c5afcfd6cec29f580758d1f50f0
Signed-off-by: Roger He <Hongbo.He@amd.com>
---
 drivers/gpu/drm/ttm/ttm_page_alloc.c | 26 ++++++++++++++++++--------
 1 file changed, 18 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index cdbb731..25b0fa5 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -296,13 +296,23 @@ static struct ttm_page_pool *ttm_get_pool(int flags, bool huge,
 }
 
 /* set memory back to wb and free the pages. */
-static void ttm_pages_put(struct page *pages[], unsigned npages)
+static void ttm_pages_put(struct page *pages[], unsigned npages,
+		unsigned int order)
 {
-	unsigned i;
-	if (set_pages_array_wb(pages, npages))
-		pr_err("Failed to set %d pages to wb!\n", npages);
-	for (i = 0; i < npages; ++i)
-		__free_page(pages[i]);
+	unsigned int i, pages_nr = (1 << order);
+
+	if (order == 0) {
+		if (set_pages_array_wb(pages, npages))
+			pr_err("Failed to set %d pages to wb!\n", npages);
+	}
+
+	for (i = 0; i < npages; ++i) {
+		if (order > 0) {
+			if (set_pages_wb(pages[i], pages_nr))
+				pr_err("Failed to set %d pages to wb!\n", pages_nr);
+		}
+		__free_pages(pages[i], order);
+	}
 }
 
 static void ttm_pool_update_free_locked(struct ttm_page_pool *pool,
@@ -365,7 +375,7 @@ static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free,
 			 */
 			spin_unlock_irqrestore(&pool->lock, irq_flags);
 
-			ttm_pages_put(pages_to_free, freed_pages);
+			ttm_pages_put(pages_to_free, freed_pages, pool->order);
 			if (likely(nr_free != FREE_ALL_PAGES))
 				nr_free -= freed_pages;
 
@@ -400,7 +410,7 @@ static int ttm_page_pool_free(struct ttm_page_pool *pool, unsigned nr_free,
 	spin_unlock_irqrestore(&pool->lock, irq_flags);
 
 	if (freed_pages)
-		ttm_pages_put(pages_to_free, freed_pages);
+		ttm_pages_put(pages_to_free, freed_pages, pool->order);
 out:
 	if (pages_to_free != static_buf)
 		kfree(pages_to_free);
-- 
2.7.4

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Re: [PATCH 1/3] drm/ttm: add set_pages_wb for handling page order more than zero

[Chris Wilson]

Quoting Roger He (2017-11-22 11:44:27)
> Change-Id: Idf5ccb579d264b343199d8b8344bddeec2c0019f
> Signed-off-by: Roger He <Hongbo.He@amd.com>
> ---
>  drivers/gpu/drm/ttm/ttm_page_alloc.c | 11 +++++++++++
>  1 file changed, 11 insertions(+)
> 
> diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
> index a8b2bfa..cdbb731 100644
> --- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
> +++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
> @@ -223,6 +223,17 @@ static struct kobj_type ttm_pool_kobj_type = {
>  static struct ttm_pool_manager *_manager;
>  
>  #ifndef CONFIG_X86
> +static int set_pages_wb(struct page *page, int numpages)
> +{
> +#if IS_ENABLED(CONFIG_AGP)
> +       int i;
> +
> +       for (i = 0; i < numpages; i++)
> +               unmap_page_from_agp(page++);
> +#endif
> +       return 0;
> +}
> +
>  static int set_pages_array_wb(struct page **pages, int addrinarray)

Both of these are shadowing exports from arch/x86, probably not the
wisest choice of names.
-Chris
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Re: [PATCH 1/3] drm/ttm: add set_pages_wb for handling page order more than zero

[Christian König]

Am 22.11.2017 um 12:50 schrieb Chris Wilson:
> Quoting Roger He (2017-11-22 11:44:27)
>> Change-Id: Idf5ccb579d264b343199d8b8344bddeec2c0019f
>> Signed-off-by: Roger He <Hongbo.He@amd.com>
>> ---
>>   drivers/gpu/drm/ttm/ttm_page_alloc.c | 11 +++++++++++
>>   1 file changed, 11 insertions(+)
>>
>> diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
>> index a8b2bfa..cdbb731 100644
>> --- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
>> +++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
>> @@ -223,6 +223,17 @@ static struct kobj_type ttm_pool_kobj_type = {
>>   static struct ttm_pool_manager *_manager;
>>   
>>   #ifndef CONFIG_X86
>> +static int set_pages_wb(struct page *page, int numpages)
>> +{
>> +#if IS_ENABLED(CONFIG_AGP)
>> +       int i;
>> +
>> +       for (i = 0; i < numpages; i++)
>> +               unmap_page_from_agp(page++);
>> +#endif
>> +       return 0;
>> +}
>> +
>>   static int set_pages_array_wb(struct page **pages, int addrinarray)
> Both of these are shadowing exports from arch/x86, probably not the
> wisest choice of names.

That is intended, please note the "#ifndef CONFIG_X86".

Basically TTM provides the same function for other architectures that we 
have for X86.

Christian.

> -Chris
> _______________________________________________
> dri-devel mailing list
> dri-devel@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/dri-devel


_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH 3/3] drm/ttm: roundup the shrink request to prevent skip huge pool

[Roger He]

e.g. shrink reqeust is less than 512, the logic will skip huge pool

Change-Id: Id8bd4d1ecff9f3ab14355e2dbd1c59b9fe824e01
Signed-off-by: Roger He <Hongbo.He@amd.com>
---
 drivers/gpu/drm/ttm/ttm_page_alloc.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index 25b0fa5..1543532 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -442,17 +442,19 @@ ttm_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 	/* select start pool in round robin fashion */
 	for (i = 0; i < NUM_POOLS; ++i) {
 		unsigned nr_free = shrink_pages;
+		unsigned page_nr;
+
 		if (shrink_pages == 0)
 			break;
 
 		pool = &_manager->pools[(i + pool_offset)%NUM_POOLS];
+		page_nr = (1 << pool->order);
 		/* OK to use static buffer since global mutex is held. */
-		nr_free_pool = (nr_free >> pool->order);
-		if (nr_free_pool == 0)
-			continue;
-
+		nr_free_pool = roundup(nr_free, page_nr) >> pool->order;
 		shrink_pages = ttm_page_pool_free(pool, nr_free_pool, true);
-		freed += ((nr_free_pool - shrink_pages) << pool->order);
+		freed += (nr_free_pool - shrink_pages) << pool->order;
+		if (freed >= sc->nr_to_scan)
+			break;
 	}
 	mutex_unlock(&lock);
 	return freed;
-- 
2.7.4

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH 3/3] drm/ttm: roundup the shrink request to prevent skip huge pool

[Chris Wilson]

Quoting Roger He (2017-11-22 11:44:29)
> e.g. shrink reqeust is less than 512, the logic will skip huge pool

You should also tell the shrinker that you skipped objects so that it
knows to accumulate the request for the next pass. See
shrinkctl->nr_scanned.
-Chris
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH 1/3] drm/ttm: add set_pages_wb for handling page order more than zero

[Christian König]

Am 22.11.2017 um 12:44 schrieb Roger He:
> Change-Id: Idf5ccb579d264b343199d8b8344bddeec2c0019f
> Signed-off-by: Roger He <Hongbo.He@amd.com>

Reviewed-by: Christian König <christian.koenig@amd.com> for the whole 
series.

> ---
>   drivers/gpu/drm/ttm/ttm_page_alloc.c | 11 +++++++++++
>   1 file changed, 11 insertions(+)
>
> diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
> index a8b2bfa..cdbb731 100644
> --- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
> +++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
> @@ -223,6 +223,17 @@ static struct kobj_type ttm_pool_kobj_type = {
>   static struct ttm_pool_manager *_manager;
>   
>   #ifndef CONFIG_X86
> +static int set_pages_wb(struct page *page, int numpages)
> +{
> +#if IS_ENABLED(CONFIG_AGP)
> +	int i;
> +
> +	for (i = 0; i < numpages; i++)
> +		unmap_page_from_agp(page++);
> +#endif
> +	return 0;
> +}
> +
>   static int set_pages_array_wb(struct page **pages, int addrinarray)
>   {
>   #if IS_ENABLED(CONFIG_AGP)


_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel