[PATCH] drm/i915/userptr: Convert page APIs to folio equivalents in put_pages

[PATCH] drm/i915/userptr: Convert page APIs to folio equivalents in put_pages

[Hongfu Li]

From: Hongfu Li <lihongfu@kylinos.cn>

Cache the folio with page_folio() at the start of the sg_table loop,
then use folio helpers directly to eliminate repeated compound_head()
lookups inside page API wrappers.

Signed-off-by: Hongfu Li <lihongfu@kylinos.cn>
---
 drivers/gpu/drm/i915/gem/i915_gem_userptr.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 043095f93ac6..0ae68c52cc12 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -160,6 +160,7 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj,
 			   struct sg_table *pages)
 {
 	struct sgt_iter sgt_iter;
 	struct page *page;
+	struct folio *folio;
 
 	if (!pages)
@@ -177,7 +178,9 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj,
 		obj->mm.dirty = false;
 
 	for_each_sgt_page(page, sgt_iter, pages) {
-		if (obj->mm.dirty && trylock_page(page)) {
+		folio = page_folio(page);
+
+		if (obj->mm.dirty && folio_trylock(folio)) {
 			/*
 			 * As this may not be anonymous memory (e.g. shmem)
 			 * but exist on a real mapping, we have to lock
@@ -193,14 +196,14 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj,
 			 * on the folio. Such a try_to_unmap() will result
 			 * in us calling put_pages() and so recursively try
 			 * to lock the page. We avoid that deadlock with
-			 * a trylock_page() and in exchange we risk missing
+			 * a folio_trylock() and in exchange we risk missing
 			 * some page dirtying.
 			 */
-			set_page_dirty(page);
-			unlock_page(page);
+			folio_mark_dirty(folio);
+			folio_unlock(folio);
 		}
 
-		mark_page_accessed(page);
+		folio_mark_accessed(folio);
 	}
 	obj->mm.dirty = false;
 
-- 
2.54.0

Re: [PATCH] drm/i915/userptr: Convert page APIs to folio equivalents in put_pages

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] Unconditional PAGE_SIZE stepping over a scatterlist performs non-idempotent folio operations multiple times for large folios.
--

--- Patch [1]: [PATCH] drm/i915/userptr: Convert page APIs to folio equivalents in put_pages ---
commit a2440a520ca40b971ab3143efb8ecac51e56d073
Author: Hongfu Li <lihongfu@kylinos.cn>

drm/i915/userptr: Convert page APIs to folio equivalents in put_pages

This commit replaces page-based APIs with folio equivalents in
i915_gem_userptr_put_pages(). It caches the folio at the start of the loop
to avoid repeated compound head lookups inside page API wrappers.

> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
> index 043095f93ac60..bd91782f4bbc7 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
[ ... ]
> @@ -177,7 +178,9 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj,
>  		obj->mm.dirty = false;
>  
>  	for_each_sgt_page(page, sgt_iter, pages) {
> -		if (obj->mm.dirty && trylock_page(page)) {
> +		folio = page_folio(page);
> +
> +		if (obj->mm.dirty && folio_trylock(folio)) {

[Severity: High]
This isn't a bug introduced by this patch, but does this loop process the same
folio multiple times for large folios?

In i915_gem_userptr_put_pages(), the for_each_sgt_page() macro unconditionally
steps by PAGE_SIZE. This causes page_folio() to repeatedly return the same folio
for the tail pages of a large folio.

For non-idempotent operations, this causes the folio to be processed redundantly.
If the scatterlist is backed by a 2MB THP, the same folio is processed 512
times. This means the code unnecessarily locks and unlocks the folio 512 times,
and folio_mark_accessed() causes the folio to repeatedly toggle between
referenced and active states.

Because large folios bypass per-CPU LRU batches, this hammers the global zone
LRU spinlock repeatedly per THP, causing severe system-wide lock contention.

Could we track the last processed folio to avoid duplicate processing of tail
pages in this loop?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260723064651.4100-1-hongfu.li@linux.dev?part=1

✓ i915.CI.BAT: success for drm/i915/userptr: Convert page APIs to folio equivalents in put_pages

[Patchwork]

[-- Attachment #1: Type: text/plain, Size: 2778 bytes --]

== Series Details ==

Series: drm/i915/userptr: Convert page APIs to folio equivalents in put_pages
URL   : https://patchwork.freedesktop.org/series/170999/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_18885 -> Patchwork_170999v1
====================================================

Summary
-------

  **SUCCESS**

  No regressions found.

  External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_170999v1/index.html

Participating hosts (41 -> 40)
------------------------------

  Additional (1): fi-pnv-d510 
  Missing    (2): bat-dg2-13 fi-snb-2520m 

Known issues
------------

  Here are the changes found in Patchwork_170999v1 that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@fbdev@info:
    - fi-pnv-d510:        NOTRUN -> [SKIP][1] ([i915#1849])
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_170999v1/fi-pnv-d510/igt@fbdev@info.html

  * igt@kms_pipe_crc_basic@nonblocking-crc:
    - fi-pnv-d510:        NOTRUN -> [SKIP][2] ([i915#11190]) +16 other tests skip
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_170999v1/fi-pnv-d510/igt@kms_pipe_crc_basic@nonblocking-crc.html

  * igt@kms_psr@psr-primary-mmap-gtt:
    - fi-pnv-d510:        NOTRUN -> [SKIP][3] +31 other tests skip
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_170999v1/fi-pnv-d510/igt@kms_psr@psr-primary-mmap-gtt.html

  
#### Possible fixes ####

  * igt@i915_selftest@live:
    - fi-bsw-nick:        [INCOMPLETE][4] -> [PASS][5] +1 other test pass
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_18885/fi-bsw-nick/igt@i915_selftest@live.html
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_170999v1/fi-bsw-nick/igt@i915_selftest@live.html

  * igt@kms_flip@basic-flip-vs-wf_vblank:
    - fi-bsw-n3050:       [DMESG-WARN][6] ([i915#16057]) -> [PASS][7] +1 other test pass
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_18885/fi-bsw-n3050/igt@kms_flip@basic-flip-vs-wf_vblank.html
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_170999v1/fi-bsw-n3050/igt@kms_flip@basic-flip-vs-wf_vblank.html

  
  [i915#11190]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/11190
  [i915#16057]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/16057
  [i915#1849]: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/1849


Build changes
-------------

  * Linux: CI_DRM_18885 -> Patchwork_170999v1

  CI-20190529: 20190529
  CI_DRM_18885: 2c64192f1ad194a53800f6dd8c779d5b4bbc1831 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_9020: 9020
  Patchwork_170999v1: 2c64192f1ad194a53800f6dd8c779d5b4bbc1831 @ git://anongit.freedesktop.org/gfx-ci/linux

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_170999v1/index.html

[-- Attachment #2: Type: text/html, Size: 3502 bytes --]