【解説】Linux 6.14で導入されるUncached Buffered I/O について

diff --git a/mm/filemap.c b/mm/filemap.c
index f61cf51c2238..8b29323b15d7 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2459,15 +2459,17 @@ static int filemap_update_page(struct kiocb *iocb,
 	return error;
 }
 
-static int filemap_create_folio(struct file *file,
-		struct address_space *mapping, loff_t pos,
-		struct folio_batch *fbatch)
+static int filemap_create_folio(struct kiocb *iocb, struct folio_batch *fbatch)
 {
+	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct folio *folio;
 	int error;
 	unsigned int min_order = mapping_min_folio_order(mapping);
 	pgoff_t index;
 
+	if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ))
+		return -EAGAIN;
+
 	folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order);
 	if (!folio)
 		return -ENOMEM;
@@ -2486,7 +2488,7 @@ static int filemap_create_folio(struct file *file,
 	 * well to keep locking rules simple.
 	 */
 	filemap_invalidate_lock_shared(mapping);
-	index = (pos >> (PAGE_SHIFT + min_order)) << min_order;
+	index = (iocb->ki_pos >> (PAGE_SHIFT + min_order)) << min_order;
 	error = filemap_add_folio(mapping, folio, index,
 			mapping_gfp_constraint(mapping, GFP_KERNEL));
 	if (error == -EEXIST)
@@ -2494,7 +2496,8 @@ static int filemap_create_folio(struct file *file,
 	if (error)
 		goto error;
 
-	error = filemap_read_folio(file, mapping->a_ops->read_folio, folio);
+	error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio,
+					folio);
 	if (error)
 		goto error;
 
@@ -2550,9 +2553,7 @@ static int filemap_get_pages(struct kiocb *iocb, size_t count,
 		filemap_get_read_batch(mapping, index, last_index - 1, fbatch);
 	}
 	if (!folio_batch_count(fbatch)) {
-		if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ))
-			return -EAGAIN;
-		err = filemap_create_folio(filp, mapping, iocb->ki_pos, fbatch);
+		err = filemap_create_folio(iocb, fbatch);
 		if (err == AOP_TRUNCATED_PAGE)
 			goto retry;
 		return err;
-- 
2.45.2

diff --git a/mm/filemap.c b/mm/filemap.c
index 8b29323b15d7..220dc7c6e12f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2527,7 +2527,6 @@ static int filemap_get_pages(struct kiocb *iocb, size_t count,
 {
 	struct file *filp = iocb->ki_filp;
 	struct address_space *mapping = filp->f_mapping;
-	struct file_ra_state *ra = &filp->f_ra;
 	pgoff_t index = iocb->ki_pos >> PAGE_SHIFT;
 	pgoff_t last_index;
 	struct folio *folio;
@@ -2542,12 +2541,13 @@ static int filemap_get_pages(struct kiocb *iocb, size_t count,
 
 	filemap_get_read_batch(mapping, index, last_index - 1, fbatch);
 	if (!folio_batch_count(fbatch)) {
+		DEFINE_READAHEAD(ractl, filp, &filp->f_ra, mapping, index);
+
 		if (iocb->ki_flags & IOCB_NOIO)
 			return -EAGAIN;
 		if (iocb->ki_flags & IOCB_NOWAIT)
 			flags = memalloc_noio_save();
-		page_cache_sync_readahead(mapping, ra, filp, index,
-				last_index - index);
+		page_cache_sync_ra(&ractl, last_index - index);
 		if (iocb->ki_flags & IOCB_NOWAIT)
 			memalloc_noio_restore(flags);
 		filemap_get_read_batch(mapping, index, last_index - 1, fbatch);
-- 
2.45.2

static inline
void page_cache_sync_readahead(struct address_space *mapping,
		struct file_ra_state *ra, struct file *file, pgoff_t index,
		unsigned long req_count)
{
	DEFINE_READAHEAD(ractl, file, ra, mapping, index);
	page_cache_sync_ra(&ractl, req_count);
}

diff --git a/mm/readahead.c b/mm/readahead.c
index ea650b8b02fb..8a62ad4106ff 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -188,6 +188,12 @@ static void read_pages(struct readahead_control *rac)
 	BUG_ON(readahead_count(rac));
 }
 
+static struct folio *ractl_alloc_folio(struct readahead_control *ractl,
+				       gfp_t gfp_mask, unsigned int order)
+{
+	return filemap_alloc_folio(gfp_mask, order);
+}
+
 /**
  * page_cache_ra_unbounded - Start unchecked readahead.
  * @ractl: Readahead control.
@@ -265,8 +271,8 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 			continue;
 		}
 
-		folio = filemap_alloc_folio(gfp_mask,
-					    mapping_min_folio_order(mapping));
+		folio = ractl_alloc_folio(ractl, gfp_mask,
+					mapping_min_folio_order(mapping));
 		if (!folio)
 			break;
 
@@ -436,7 +442,7 @@ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index,
 		pgoff_t mark, unsigned int order, gfp_t gfp)
 {
 	int err;
-	struct folio *folio = filemap_alloc_folio(gfp, order);
+	struct folio *folio = ractl_alloc_folio(ractl, gfp, order);
 
 	if (!folio)
 		return -ENOMEM;
@@ -750,7 +756,7 @@ void readahead_expand(struct readahead_control *ractl,
 		if (folio && !xa_is_value(folio))
 			return; /* Folio apparently present */
 
-		folio = filemap_alloc_folio(gfp_mask, min_order);
+		folio = ractl_alloc_folio(ractl, gfp_mask, min_order);
 		if (!folio)
 			return;
 
@@ -779,7 +785,7 @@ void readahead_expand(struct readahead_control *ractl,
 		if (folio && !xa_is_value(folio))
 			return; /* Folio apparently present */
 
-		folio = filemap_alloc_folio(gfp_mask, min_order);
+		folio = ractl_alloc_folio(ractl, gfp_mask, min_order);
 		if (!folio)
 			return;
 
-- 
2.45.2

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index cf46ac720802..16607f02abd0 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -110,6 +110,7 @@ enum pageflags {
 	PG_reclaim,		/* To be reclaimed asap */
 	PG_swapbacked,		/* Page is backed by RAM/swap */
 	PG_unevictable,		/* Page is "unevictable"  */
+	PG_dropbehind,		/* drop pages on IO completion */
 #ifdef CONFIG_MMU
 	PG_mlocked,		/* Page is vma mlocked */
 #endif
@@ -562,6 +563,10 @@ PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL)
 FOLIO_FLAG(readahead, FOLIO_HEAD_PAGE)
 	FOLIO_TEST_CLEAR_FLAG(readahead, FOLIO_HEAD_PAGE)
 
+FOLIO_FLAG(dropbehind, FOLIO_HEAD_PAGE)
+	FOLIO_TEST_CLEAR_FLAG(dropbehind, FOLIO_HEAD_PAGE)
+	__FOLIO_SET_FLAG(dropbehind, FOLIO_HEAD_PAGE)
+
 #ifdef CONFIG_HIGHMEM
 /*
  * Must use a macro here due to header dependency issues. page_zone() is not
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index bb8a59c6caa2..3bc8656c8359 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -116,7 +116,8 @@
 	DEF_PAGEFLAG_NAME(head),					\
 	DEF_PAGEFLAG_NAME(reclaim),					\
 	DEF_PAGEFLAG_NAME(swapbacked),					\
-	DEF_PAGEFLAG_NAME(unevictable)					\
+	DEF_PAGEFLAG_NAME(unevictable),					\
+	DEF_PAGEFLAG_NAME(dropbehind)					\
 IF_HAVE_PG_MLOCK(mlocked)						\
 IF_HAVE_PG_HWPOISON(hwpoison)						\
 IF_HAVE_PG_IDLE(idle)							\
-- 
2.45.2

#define FOLIO_FLAG(name, page)						\
FOLIO_TEST_FLAG(name, page)						\
FOLIO_SET_FLAG(name, page)						\
FOLIO_CLEAR_FLAG(name, page)

#define FOLIO_TEST_FLAG(name, page)					\
static __always_inline bool folio_test_##name(const struct folio *folio) \
{ return test_bit(PG_##name, const_folio_flags(folio, page)); }

#define FOLIO_SET_FLAG(name, page)					\
static __always_inline void folio_set_##name(struct folio *folio)	\
{ set_bit(PG_##name, folio_flags(folio, page)); }

#define FOLIO_CLEAR_FLAG(name, page)					\
static __always_inline void folio_clear_##name(struct folio *folio)	\
{ clear_bit(PG_##name, folio_flags(folio, page)); }

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index bcf0865a38ae..5da4b6d42fae 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -1353,6 +1353,7 @@ struct readahead_control {
 	pgoff_t _index;
 	unsigned int _nr_pages;
 	unsigned int _batch_count;
+	bool dropbehind;
 	bool _workingset;
 	unsigned long _pflags;
 };
diff --git a/mm/readahead.c b/mm/readahead.c
index 8a62ad4106ff..c0a6dc5d5686 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -191,7 +191,13 @@ static void read_pages(struct readahead_control *rac)
 static struct folio *ractl_alloc_folio(struct readahead_control *ractl,
 				       gfp_t gfp_mask, unsigned int order)
 {
-	return filemap_alloc_folio(gfp_mask, order);
+	struct folio *folio;
+
+	folio = filemap_alloc_folio(gfp_mask, order);
+	if (folio && ractl->dropbehind)
+		__folio_set_dropbehind(folio);
+
+	return folio;
 }
 
 /**
-- 
2.45.2

diff --git a/mm/internal.h b/mm/internal.h
index cb8d8e8e3ffa..ed3c3690eb03 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -392,6 +392,8 @@ void unmap_page_range(struct mmu_gather *tlb,
 			     struct vm_area_struct *vma,
 			     unsigned long addr, unsigned long end,
 			     struct zap_details *details);
+int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio,
+			   gfp_t gfp);
 
 void page_cache_ra_order(struct readahead_control *, struct file_ra_state *,
 		unsigned int order);
diff --git a/mm/truncate.c b/mm/truncate.c
index 7c304d2f0052..e2e115adfbc5 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -525,6 +525,15 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 }
 EXPORT_SYMBOL(invalidate_mapping_pages);
 
+static int folio_launder(struct address_space *mapping, struct folio *folio)
+{
+	if (!folio_test_dirty(folio))
+		return 0;
+	if (folio->mapping != mapping || mapping->a_ops->launder_folio == NULL)
+		return 0;
+	return mapping->a_ops->launder_folio(folio);
+}
+
 /*
  * This is like mapping_evict_folio(), except it ignores the folio's
  * refcount.  We do this because invalidate_inode_pages2() needs stronger
@@ -532,14 +541,26 @@ EXPORT_SYMBOL(invalidate_mapping_pages);
  * shrink_folio_list() has a temp ref on them, or because they're transiently
  * sitting in the folio_add_lru() caches.
  */
-static int invalidate_complete_folio2(struct address_space *mapping,
-					struct folio *folio)
+int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio,
+			   gfp_t gfp)
 {
-	if (folio->mapping != mapping)
-		return 0;
+	int ret;
+
+	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 
-	if (!filemap_release_folio(folio, GFP_KERNEL))
+	if (folio_test_dirty(folio))
 		return 0;
+	if (folio_mapped(folio))
+		unmap_mapping_folio(folio);
+	BUG_ON(folio_mapped(folio));
+
+	ret = folio_launder(mapping, folio);
+	if (ret)
+		return ret;
+	if (folio->mapping != mapping)
+		return -EBUSY;
+	if (!filemap_release_folio(folio, gfp))
+		return -EBUSY;
 
 	spin_lock(&mapping->host->i_lock);
 	xa_lock_irq(&mapping->i_pages);
@@ -558,16 +579,7 @@ static int invalidate_complete_folio2(struct address_space *mapping,
 failed:
 	xa_unlock_irq(&mapping->i_pages);
 	spin_unlock(&mapping->host->i_lock);
-	return 0;
-}
-
-static int folio_launder(struct address_space *mapping, struct folio *folio)
-{
-	if (!folio_test_dirty(folio))
-		return 0;
-	if (folio->mapping != mapping || mapping->a_ops->launder_folio == NULL)
-		return 0;
-	return mapping->a_ops->launder_folio(folio);
+	return -EBUSY;
 }
 
 /**
@@ -631,16 +643,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 			}
 			VM_BUG_ON_FOLIO(!folio_contains(folio, indices[i]), folio);
 			folio_wait_writeback(folio);
-
-			if (folio_mapped(folio))
-				unmap_mapping_folio(folio);
-			BUG_ON(folio_mapped(folio));
-
-			ret2 = folio_launder(mapping, folio);
-			if (ret2 == 0) {
-				if (!invalidate_complete_folio2(mapping, folio))
-					ret2 = -EBUSY;
-			}
+			ret2 = folio_unmap_invalidate(mapping, folio, GFP_KERNEL);
 			if (ret2 < 0)
 				ret = ret2;
 			folio_unlock(folio);
-- 
2.45.2

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7e29433c5ecc..6a838b5479a6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -322,6 +322,7 @@ struct readahead_control;
 #define IOCB_NOWAIT		(__force int) RWF_NOWAIT
 #define IOCB_APPEND		(__force int) RWF_APPEND
 #define IOCB_ATOMIC		(__force int) RWF_ATOMIC
+#define IOCB_DONTCACHE		(__force int) RWF_DONTCACHE
 
 /* non-RWF related bits - start at 16 */
 #define IOCB_EVENTFD		(1 << 16)
@@ -356,7 +357,8 @@ struct readahead_control;
 	{ IOCB_SYNC,		"SYNC" }, \
 	{ IOCB_NOWAIT,		"NOWAIT" }, \
 	{ IOCB_APPEND,		"APPEND" }, \
-	{ IOCB_ATOMIC,		"ATOMIC"}, \
+	{ IOCB_ATOMIC,		"ATOMIC" }, \
+	{ IOCB_DONTCACHE,	"DONTCACHE" }, \
 	{ IOCB_EVENTFD,		"EVENTFD"}, \
 	{ IOCB_DIRECT,		"DIRECT" }, \
 	{ IOCB_WRITE,		"WRITE" }, \
@@ -2127,6 +2129,8 @@ struct file_operations {
 #define FOP_UNSIGNED_OFFSET	((__force fop_flags_t)(1 << 5))
 /* Supports asynchronous lock callbacks */
 #define FOP_ASYNC_LOCK		((__force fop_flags_t)(1 << 6))
+/* File system supports uncached read/write buffered IO */
+#define FOP_DONTCACHE		((__force fop_flags_t)(1 << 7))
 
 /* Wrap a directory iterator that needs exclusive inode access */
 int wrap_directory_iterator(struct file *, struct dir_context *,
@@ -3614,6 +3618,14 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags,
 		if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE))
 			return -EOPNOTSUPP;
 	}
+	if (flags & RWF_DONTCACHE) {
+		/* file system must support it */
+		if (!(ki->ki_filp->f_op->fop_flags & FOP_DONTCACHE))
+			return -EOPNOTSUPP;
+		/* DAX mappings not supported */
+		if (IS_DAX(ki->ki_filp->f_mapping->host))
+			return -EOPNOTSUPP;
+	}
 	kiocb_flags |= (__force int) (flags & RWF_SUPPORTED);
 	if (flags & RWF_SYNC)
 		kiocb_flags |= IOCB_DSYNC;
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 753971770733..56a4f93a08f4 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -332,9 +332,13 @@ typedef int __bitwise __kernel_rwf_t;
 /* Atomic Write */
 #define RWF_ATOMIC	((__force __kernel_rwf_t)0x00000040)
 
+/* buffered IO that drops the cache after reading or writing data */
+#define RWF_DONTCACHE	((__force __kernel_rwf_t)0x00000080)
+
 /* mask of flags supported by the kernel */
 #define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
-			 RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC)
+			 RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC |\
+			 RWF_DONTCACHE)
 
 #define PROCFS_IOCTL_MAGIC 'f'
 
-- 
2.45.2

diff --git a/mm/filemap.c b/mm/filemap.c
index 220dc7c6e12f..dd563208d09d 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2473,6 +2473,8 @@ static int filemap_create_folio(struct kiocb *iocb, struct folio_batch *fbatch)
 	folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order);
 	if (!folio)
 		return -ENOMEM;
+	if (iocb->ki_flags & IOCB_DONTCACHE)
+		__folio_set_dropbehind(folio);
 
 	/*
 	 * Protect against truncate / hole punch. Grabbing invalidate_lock
@@ -2518,6 +2520,8 @@ static int filemap_readahead(struct kiocb *iocb, struct file *file,
 
 	if (iocb->ki_flags & IOCB_NOIO)
 		return -EAGAIN;
+	if (iocb->ki_flags & IOCB_DONTCACHE)
+		ractl.dropbehind = 1;
 	page_cache_async_ra(&ractl, folio, last_index - folio->index);
 	return 0;
 }
@@ -2547,6 +2551,8 @@ static int filemap_get_pages(struct kiocb *iocb, size_t count,
 			return -EAGAIN;
 		if (iocb->ki_flags & IOCB_NOWAIT)
 			flags = memalloc_noio_save();
+		if (iocb->ki_flags & IOCB_DONTCACHE)
+			ractl.dropbehind = 1;
 		page_cache_sync_ra(&ractl, last_index - index);
 		if (iocb->ki_flags & IOCB_NOWAIT)
 			memalloc_noio_restore(flags);
@@ -2594,6 +2600,20 @@ static inline bool pos_same_folio(loff_t pos1, loff_t pos2, struct folio *folio)
 	return (pos1 >> shift == pos2 >> shift);
 }
 
+static void filemap_end_dropbehind_read(struct address_space *mapping,
+					struct folio *folio)
+{
+	if (!folio_test_dropbehind(folio))
+		return;
+	if (folio_test_writeback(folio) || folio_test_dirty(folio))
+		return;
+	if (folio_trylock(folio)) {
+		if (folio_test_clear_dropbehind(folio))
+			folio_unmap_invalidate(mapping, folio, 0);
+		folio_unlock(folio);
+	}
+}
+
 /**
  * filemap_read - Read data from the page cache.
  * @iocb: The iocb to read.
@@ -2707,8 +2727,12 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter,
 			}
 		}
 put_folios:
-		for (i = 0; i < folio_batch_count(&fbatch); i++)
-			folio_put(fbatch.folios[i]);
+		for (i = 0; i < folio_batch_count(&fbatch); i++) {
+			struct folio *folio = fbatch.folios[i];
+
+			filemap_end_dropbehind_read(mapping, folio);
+			folio_put(folio);
+		}
 		folio_batch_init(&fbatch);
 	} while (iov_iter_count(iter) && iocb->ki_pos < isize && !error);
 
diff --git a/mm/swap.c b/mm/swap.c
index 10decd9dffa1..ba02bd5ba145 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -427,6 +427,8 @@ static void folio_inc_refs(struct folio *folio)
  */
 void folio_mark_accessed(struct folio *folio)
 {
+	if (folio_test_dropbehind(folio))
+		return;
 	if (lru_gen_enabled()) {
 		folio_inc_refs(folio);
 		return;
-- 
2.45.2

diff --git a/mm/filemap.c b/mm/filemap.c
index dd563208d09d..aa0b3af6533d 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1599,6 +1599,27 @@ int folio_wait_private_2_killable(struct folio *folio)
 }
 EXPORT_SYMBOL(folio_wait_private_2_killable);
 
+/*
+ * If folio was marked as dropbehind, then pages should be dropped when writeback
+ * completes. Do that now. If we fail, it's likely because of a big folio -
+ * just reset dropbehind for that case and latter completions should invalidate.
+ */
+static void folio_end_dropbehind_write(struct folio *folio)
+{
+	/*
+	 * Hitting !in_task() should not happen off RWF_DONTCACHE 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.
@@ -1609,6 +1630,8 @@ EXPORT_SYMBOL(folio_wait_private_2_killable);
  */
 void folio_end_writeback(struct folio *folio)
 {
+	bool folio_dropbehind = false;
+
 	VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio);
 
 	/*
@@ -1630,9 +1653,14 @@ void folio_end_writeback(struct folio *folio)
 	 * reused before the folio_wake_bit().
 	 */
 	folio_get(folio);
+	if (!folio_test_dirty(folio))
+		folio_dropbehind = folio_test_clear_dropbehind(folio);
 	if (__folio_end_writeback(folio))
 		folio_wake_bit(folio, PG_writeback);
 	acct_reclaim_writeback(folio);
+
+	if (folio_dropbehind)
+		folio_end_dropbehind_write(folio);
 	folio_put(folio);
 }
 EXPORT_SYMBOL(folio_end_writeback);
-- 
2.45.2

diff --git a/mm/filemap.c b/mm/filemap.c
index aa0b3af6533d..9842258ba343 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -449,6 +449,24 @@ int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
 }
 EXPORT_SYMBOL(filemap_fdatawrite_range);
 
+/**
+ * filemap_fdatawrite_range_kick - start writeback on a range
+ * @mapping:	target address_space
+ * @start:	index to start writeback on
+ * @end:	last (non-inclusive) index for writeback
+ *
+ * This is a non-integrity writeback helper, to start writing back folios
+ * for the indicated range.
+ *
+ * Return: %0 on success, negative error code otherwise.
+ */
+int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start,
+				  loff_t end)
+{
+	return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_NONE);
+}
+EXPORT_SYMBOL_GPL(filemap_fdatawrite_range_kick);
+
 /**
  * filemap_flush - mostly a non-blocking flush
  * @mapping:	target address_space
-- 
2.45.2

int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
				loff_t end)
{
	return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);
}
EXPORT_SYMBOL(filemap_fdatawrite_range);

int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start,
				  loff_t end)
{
	return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_NONE);
}
EXPORT_SYMBOL_GPL(filemap_fdatawrite_range_kick);

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 653b5efa3d3f..58a618853574 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2912,6 +2912,11 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count)
 				(iocb->ki_flags & IOCB_SYNC) ? 0 : 1);
 		if (ret)
 			return ret;
+	} else if (iocb->ki_flags & IOCB_DONTCACHE) {
+		struct address_space *mapping = iocb->ki_filp->f_mapping;
+
+		filemap_fdatawrite_range_kick(mapping, iocb->ki_pos,
+					      iocb->ki_pos + count);
 	}
 
 	return count;
-- 
2.45.2

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 5da4b6d42fae..64c6dada837e 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -710,6 +710,7 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping,
  * * %FGP_NOFS - __GFP_FS will get cleared in gfp.
  * * %FGP_NOWAIT - Don't block on the folio lock.
  * * %FGP_STABLE - Wait for the folio to be stable (finished writeback)
+ * * %FGP_DONTCACHE - Uncached buffered IO
  * * %FGP_WRITEBEGIN - The flags to use in a filesystem write_begin()
  *   implementation.
  */
@@ -723,6 +724,7 @@ typedef unsigned int __bitwise fgf_t;
 #define FGP_NOWAIT		((__force fgf_t)0x00000020)
 #define FGP_FOR_MMAP		((__force fgf_t)0x00000040)
 #define FGP_STABLE		((__force fgf_t)0x00000080)
+#define FGP_DONTCACHE		((__force fgf_t)0x00000100)
 #define FGF_GET_ORDER(fgf)	(((__force unsigned)fgf) >> 26)	/* top 6 bits */
 
 #define FGP_WRITEBEGIN		(FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE)
diff --git a/mm/filemap.c b/mm/filemap.c
index 9842258ba343..68bdfff4117e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2001,6 +2001,8 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 			/* Init accessed so avoid atomic mark_page_accessed later */
 			if (fgp_flags & FGP_ACCESSED)
 				__folio_set_referenced(folio);
+			if (fgp_flags & FGP_DONTCACHE)
+				__folio_set_dropbehind(folio);
 
 			err = filemap_add_folio(mapping, folio, index, gfp);
 			if (!err)
@@ -2023,6 +2025,9 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 
 	if (!folio)
 		return ERR_PTR(-ENOENT);
+	/* not an uncached lookup, clear uncached if set */
+	if (folio_test_dropbehind(folio) && !(fgp_flags & FGP_DONTCACHE))
+		folio_clear_dropbehind(folio);
 	return folio;
 }
 EXPORT_SYMBOL(__filemap_get_folio);
-- 
2.45.2