mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
* [PATCH] drm/i915/gem: Skip writeback of shmem folios with extra references
@ 2026-11-19 13:42 Kiryl Shutsemau (Meta)
  2026-11-19 17:43 ` Andi Shyti
  0 siblings, 1 reply; 3+ messages in thread
From: Kiryl Shutsemau (Meta) @ 2026-11-19 13:42 UTC (permalink / raw)
  To: Jani Nikula, Joonas Lahtinen, Rodrigo Vivi, Tvrtko Ursulin
  Cc: Kiryl Shutsemau (Meta),
	David Airlie, Simona Vetter, Andi Shyti, David Hildenbrand,
	Hugh Dickins, Baolin Wang, intel-gfx, dri-devel, linux-mm,
	linux-kernel, kernel-team

__shmem_writeback() writes out every dirty folio that is not mapped. A
folio stops being mapped when munmap() removes its rmap, but the TLB
flush comes later. Until then another thread can still store to it
through a stale TLB entry:

    CPU0 (munmap)            CPU1 (same mm)       CPU2 (i915 shrinker)
    zap_huge_pmd()
      folio_remove_rmap_pmd()
                                                  __shmem_writeback()
                                                    clear dirty
                                                    !folio_mapped()
                                                    shmem_write_folio()
                             store via stale TLB
    tlb_finish_mmu()

The store leaves the folio clean in the swap cache. Once reclaim frees
it, the object reads back from swap without that store.

The legacy mmap ioctl maps the shmem file directly, and i915 mounts it
with huge=within_size on some platforms, so the folio can be PMD-mapped.
The core mm keeps the rmap until after the flush for PTEs, but not for
shmem PMDs: shmem has no writeback, and pageout() refuses a folio with
an extra reference.

Do the same here. The unmapping side holds its reference until the TLB
is flushed, so a folio with references beyond the page cache and
writeback_iter() is left to reclaim, as a mapped one already is.

Fixes: 2d6692e642e7 ("drm/i915: Start writeback from the shrinker")
Signed-off-by: Kiryl Shutsemau (Meta) <kas@kernel.org>
---
Found while reviewing David's fix for the same race on file PMDs, which
leaves shmem out because shmem has no writeback:
https://patch.msgid.link/20261116-dirty_file_pmd-v2-2-571883053174@kernel.org

Build-tested only.

 drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index bf9e7480f0f5..748772c358ac 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -316,9 +316,15 @@ void __shmem_writeback(size_t size, struct address_space *mapping)
 	 * leaving only CPU mmapings around) and add those folios to the LRU
 	 * instead of invoking writeback so they are aged and paged out
 	 * as normal.
+	 *
+	 * The same goes for a folio with references beyond the page cache
+	 * and writeback_iter(). A folio that was just unmapped can still be
+	 * written through a stale TLB entry until the unmapping side flushes
+	 * the TLB and drops its reference. pageout() checks the same.
 	 */
 	while ((folio = writeback_iter(mapping, &wbc, folio, &error))) {
-		if (folio_mapped(folio))
+		if (folio_mapped(folio) ||
+		    folio_ref_count(folio) != 1 + folio_nr_pages(folio))
 			folio_redirty_for_writepage(&wbc, folio);
 		else
 			error = shmem_write_folio(folio);

base-commit: 4405c18c95d2d0f99f6c581ef0ee8591a1aa6ccd
-- 
2.54.0


^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [PATCH] drm/i915/gem: Skip writeback of shmem folios with extra references
  2026-11-19 13:42 [PATCH] drm/i915/gem: Skip writeback of shmem folios with extra references Kiryl Shutsemau (Meta)
@ 2026-11-19 17:43 ` Andi Shyti
  2026-11-20 13:17   ` Kiryl Shutsemau (Meta)
  0 siblings, 1 reply; 3+ messages in thread
From: Andi Shyti @ 2026-11-19 17:43 UTC (permalink / raw)
  To: Kiryl Shutsemau (Meta)
  Cc: Jani Nikula, Joonas Lahtinen, Rodrigo Vivi, Tvrtko Ursulin,
	David Airlie, Simona Vetter, Andi Shyti, David Hildenbrand,
	Hugh Dickins, Baolin Wang, intel-gfx, dri-devel, linux-mm,
	linux-kernel, kernel-team

Hi Kiryl,

On Thu, Nov 19, 2026 at 01:42:41PM +0000, Kiryl Shutsemau (Meta) wrote:
> __shmem_writeback() writes out every dirty folio that is not mapped. A
> folio stops being mapped when munmap() removes its rmap, but the TLB
> flush comes later. Until then another thread can still store to it
> through a stale TLB entry:
> 
>     CPU0 (munmap)            CPU1 (same mm)       CPU2 (i915 shrinker)
>     zap_huge_pmd()
>       folio_remove_rmap_pmd()
>                                                   __shmem_writeback()
>                                                     clear dirty
>                                                     !folio_mapped()
>                                                     shmem_write_folio()
>                              store via stale TLB
>     tlb_finish_mmu()
> 
> The store leaves the folio clean in the swap cache. Once reclaim frees
> it, the object reads back from swap without that store.
> 
> The legacy mmap ioctl maps the shmem file directly, and i915 mounts it
> with huge=within_size on some platforms, so the folio can be PMD-mapped.
> The core mm keeps the rmap until after the flush for PTEs, but not for
> shmem PMDs: shmem has no writeback, and pageout() refuses a folio with
> an extra reference.
> 
> Do the same here. The unmapping side holds its reference until the TLB
> is flushed, so a folio with references beyond the page cache and
> writeback_iter() is left to reclaim, as a mapped one already is.
> 
> Fixes: 2d6692e642e7 ("drm/i915: Start writeback from the shrinker")
> Signed-off-by: Kiryl Shutsemau (Meta) <kas@kernel.org>
> ---
> Found while reviewing David's fix for the same race on file PMDs, which
> leaves shmem out because shmem has no writeback:
> https://patch.msgid.link/20261116-dirty_file_pmd-v2-2-571883053174@kernel.org
> 
> Build-tested only.
> 
>  drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 8 +++++++-
>  1 file changed, 7 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
> index bf9e7480f0f5..748772c358ac 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
> @@ -316,9 +316,15 @@ void __shmem_writeback(size_t size, struct address_space *mapping)
>  	 * leaving only CPU mmapings around) and add those folios to the LRU
>  	 * instead of invoking writeback so they are aged and paged out
>  	 * as normal.
> +	 *
> +	 * The same goes for a folio with references beyond the page cache
> +	 * and writeback_iter(). A folio that was just unmapped can still be
> +	 * written through a stale TLB entry until the unmapping side flushes
> +	 * the TLB and drops its reference. pageout() checks the same.
>  	 */
>  	while ((folio = writeback_iter(mapping, &wbc, folio, &error))) {
> -		if (folio_mapped(folio))
> +		if (folio_mapped(folio) ||
> +		    folio_ref_count(folio) != 1 + folio_nr_pages(folio))

I don't think we need this fix in the current tree. The i915
writeback iterator already skips the shmem folio in the case you
describe, so the new refcount check doesn't change the outcome.

Thanks,
Andi

>  			folio_redirty_for_writepage(&wbc, folio);
>  		else
>  			error = shmem_write_folio(folio);
> 
> base-commit: 4405c18c95d2d0f99f6c581ef0ee8591a1aa6ccd
> -- 
> 2.54.0
> 

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [PATCH] drm/i915/gem: Skip writeback of shmem folios with extra references
  2026-11-19 17:43 ` Andi Shyti
@ 2026-11-20 13:17   ` Kiryl Shutsemau (Meta)
  0 siblings, 0 replies; 3+ messages in thread
From: Kiryl Shutsemau (Meta) @ 2026-11-20 13:17 UTC (permalink / raw)
  To: Andi Shyti
  Cc: Jani Nikula, Joonas Lahtinen, Rodrigo Vivi, Tvrtko Ursulin,
	David Airlie, Simona Vetter, Andi Shyti, David Hildenbrand,
	Hugh Dickins, Baolin Wang, intel-gfx, dri-devel, linux-mm,
	linux-kernel, kernel-team

On Thu, Nov 19, 2026 at 06:43:08PM +0100, Andi Shyti wrote:
> > diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
> > index bf9e7480f0f5..748772c358ac 100644
> > --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
> > +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
> > @@ -316,9 +316,15 @@ void __shmem_writeback(size_t size, struct address_space *mapping)
> >  	 * leaving only CPU mmapings around) and add those folios to the LRU
> >  	 * instead of invoking writeback so they are aged and paged out
> >  	 * as normal.
> > +	 *
> > +	 * The same goes for a folio with references beyond the page cache
> > +	 * and writeback_iter(). A folio that was just unmapped can still be
> > +	 * written through a stale TLB entry until the unmapping side flushes
> > +	 * the TLB and drops its reference. pageout() checks the same.
> >  	 */
> >  	while ((folio = writeback_iter(mapping, &wbc, folio, &error))) {
> > -		if (folio_mapped(folio))
> > +		if (folio_mapped(folio) ||
> > +		    folio_ref_count(folio) != 1 + folio_nr_pages(folio))
> 
> I don't think we need this fix in the current tree. The i915
> writeback iterator already skips the shmem folio in the case you
> describe, so the new refcount check doesn't change the outcome.

Oh. It took me a while to see why.

__shmem_writeback() asks writeback_iter() for PAGECACHE_TAG_DIRTY
folios, and shmem never sets that tag, its ->dirty_folio is
noop_dirty_folio(). So the loop body never runs for any folio, and
hasn't since 776a853a43c9 ("i915: Use writeback_iter()").

That makes me question the whole writeback thing. What's going on
there, and what's the plan?

-- 
  Kiryl Shutsemau / Kirill A. Shutemov

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2026-11-20 13:17 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2026-11-19 13:42 [PATCH] drm/i915/gem: Skip writeback of shmem folios with extra references Kiryl Shutsemau (Meta)
2026-11-19 17:43 ` Andi Shyti
2026-11-20 13:17   ` Kiryl Shutsemau (Meta)

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®