Message ID | 20241111234842.2024180-10-axboe@kernel.dk |
---|---|
State | Not Applicable |
Headers | show |
Series | Uncached buffered IO | expand |
On Mon, Nov 11, 2024 at 04:37:36PM -0700, Jens Axboe wrote: > If the folio is marked as uncached, drop pages when writeback completes. > Intended to be used with RWF_UNCACHED, to avoid needing sync writes for > uncached IO. > > Signed-off-by: Jens Axboe <axboe@kernel.dk> > --- > mm/filemap.c | 28 ++++++++++++++++++++++++++++ > 1 file changed, 28 insertions(+) > > diff --git a/mm/filemap.c b/mm/filemap.c > index 3d0614ea5f59..40debe742abe 100644 > --- a/mm/filemap.c > +++ b/mm/filemap.c > @@ -1600,6 +1600,27 @@ int folio_wait_private_2_killable(struct folio *folio) > } > EXPORT_SYMBOL(folio_wait_private_2_killable); > > +/* > + * If folio was marked as uncached, then pages should be dropped when writeback > + * completes. Do that now. If we fail, it's likely because of a big folio - > + * just reset uncached for that case and latter completions should invalidate. > + */ > +static void folio_end_uncached(struct folio *folio) > +{ > + /* > + * Hitting !in_task() should not happen off RWF_UNCACHED writeback, but > + * can happen if normal writeback just happens to find dirty folios > + * that were created as part of uncached writeback, and that writeback > + * would otherwise not need non-IRQ handling. Just skip the > + * invalidation in that case. > + */ > + if (in_task() && folio_trylock(folio)) { > + if (folio->mapping) > + folio_unmap_invalidate(folio->mapping, folio, 0); > + folio_unlock(folio); > + } > +} > + > /** > * folio_end_writeback - End writeback against a folio. > * @folio: The folio. > @@ -1610,6 +1631,8 @@ EXPORT_SYMBOL(folio_wait_private_2_killable); > */ > void folio_end_writeback(struct folio *folio) > { > + bool folio_uncached = false; > + > VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio); > > /* > @@ -1631,9 +1654,14 @@ void folio_end_writeback(struct folio *folio) > * reused before the folio_wake_bit(). > */ > folio_get(folio); > + if (folio_test_uncached(folio) && folio_test_clear_uncached(folio)) > + folio_uncached = true; Hm? Maybe folio_uncached = folio_test_clear_uncached(folio); ? > if (__folio_end_writeback(folio)) > folio_wake_bit(folio, PG_writeback); > acct_reclaim_writeback(folio); > + > + if (folio_uncached) > + folio_end_uncached(folio); > folio_put(folio); > } > EXPORT_SYMBOL(folio_end_writeback); > -- > 2.45.2 >
On 11/12/24 2:31 AM, Kirill A. Shutemov wrote: > On Mon, Nov 11, 2024 at 04:37:36PM -0700, Jens Axboe wrote: >> If the folio is marked as uncached, drop pages when writeback completes. >> Intended to be used with RWF_UNCACHED, to avoid needing sync writes for >> uncached IO. >> >> Signed-off-by: Jens Axboe <axboe@kernel.dk> >> --- >> mm/filemap.c | 28 ++++++++++++++++++++++++++++ >> 1 file changed, 28 insertions(+) >> >> diff --git a/mm/filemap.c b/mm/filemap.c >> index 3d0614ea5f59..40debe742abe 100644 >> --- a/mm/filemap.c >> +++ b/mm/filemap.c >> @@ -1600,6 +1600,27 @@ int folio_wait_private_2_killable(struct folio *folio) >> } >> EXPORT_SYMBOL(folio_wait_private_2_killable); >> >> +/* >> + * If folio was marked as uncached, then pages should be dropped when writeback >> + * completes. Do that now. If we fail, it's likely because of a big folio - >> + * just reset uncached for that case and latter completions should invalidate. >> + */ >> +static void folio_end_uncached(struct folio *folio) >> +{ >> + /* >> + * Hitting !in_task() should not happen off RWF_UNCACHED writeback, but >> + * can happen if normal writeback just happens to find dirty folios >> + * that were created as part of uncached writeback, and that writeback >> + * would otherwise not need non-IRQ handling. Just skip the >> + * invalidation in that case. >> + */ >> + if (in_task() && folio_trylock(folio)) { >> + if (folio->mapping) >> + folio_unmap_invalidate(folio->mapping, folio, 0); >> + folio_unlock(folio); >> + } >> +} >> + >> /** >> * folio_end_writeback - End writeback against a folio. >> * @folio: The folio. >> @@ -1610,6 +1631,8 @@ EXPORT_SYMBOL(folio_wait_private_2_killable); >> */ >> void folio_end_writeback(struct folio *folio) >> { >> + bool folio_uncached = false; >> + >> VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio); >> >> /* >> @@ -1631,9 +1654,14 @@ void folio_end_writeback(struct folio *folio) >> * reused before the folio_wake_bit(). >> */ >> folio_get(folio); >> + if (folio_test_uncached(folio) && folio_test_clear_uncached(folio)) >> + folio_uncached = true; > > Hm? Maybe > > folio_uncached = folio_test_clear_uncached(folio); > > ? It's done that way to avoid a RMW for the (for now, at least) common case of not seeing cached folios. For that case, you can get by with a cheap test_bit, for the cached case you pay the full price of the test_clear. Previous versions just had the test_clear, happy to just go back or add a comment, whatever is preferred.
diff --git a/mm/filemap.c b/mm/filemap.c index 3d0614ea5f59..40debe742abe 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1600,6 +1600,27 @@ int folio_wait_private_2_killable(struct folio *folio) } EXPORT_SYMBOL(folio_wait_private_2_killable); +/* + * If folio was marked as uncached, then pages should be dropped when writeback + * completes. Do that now. If we fail, it's likely because of a big folio - + * just reset uncached for that case and latter completions should invalidate. + */ +static void folio_end_uncached(struct folio *folio) +{ + /* + * Hitting !in_task() should not happen off RWF_UNCACHED writeback, but + * can happen if normal writeback just happens to find dirty folios + * that were created as part of uncached writeback, and that writeback + * would otherwise not need non-IRQ handling. Just skip the + * invalidation in that case. + */ + if (in_task() && folio_trylock(folio)) { + if (folio->mapping) + folio_unmap_invalidate(folio->mapping, folio, 0); + folio_unlock(folio); + } +} + /** * folio_end_writeback - End writeback against a folio. * @folio: The folio. @@ -1610,6 +1631,8 @@ EXPORT_SYMBOL(folio_wait_private_2_killable); */ void folio_end_writeback(struct folio *folio) { + bool folio_uncached = false; + VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio); /* @@ -1631,9 +1654,14 @@ void folio_end_writeback(struct folio *folio) * reused before the folio_wake_bit(). */ folio_get(folio); + if (folio_test_uncached(folio) && folio_test_clear_uncached(folio)) + folio_uncached = true; if (__folio_end_writeback(folio)) folio_wake_bit(folio, PG_writeback); acct_reclaim_writeback(folio); + + if (folio_uncached) + folio_end_uncached(folio); folio_put(folio); } EXPORT_SYMBOL(folio_end_writeback);
If the folio is marked as uncached, drop pages when writeback completes. Intended to be used with RWF_UNCACHED, to avoid needing sync writes for uncached IO. Signed-off-by: Jens Axboe <axboe@kernel.dk> --- mm/filemap.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+)