Merge tag 'iomap-6.6-merge-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull iomap updates from Darrick Wong:
 "We've got some big changes for this release -- I'm very happy to be
  landing willy's work to enable large folios for the page cache for
  general read and write IOs when the fs can make contiguous space
  allocations, and Ritesh's work to track sub-folio dirty state to
  eliminate the write amplification problems inherent in using large
  folios.

  As a bonus, io_uring can now process write completions in the caller's
  context instead of bouncing through a workqueue, which should reduce
  io latency dramatically. IOWs, XFS should see a nice performance bump
  for both IO paths.

  Summary:

   - Make large writes to the page cache fill sparse parts of the cache
     with large folios, then use large memcpy calls for the large folio.

   - Track the per-block dirty state of each large folio so that a
     buffered write to a single byte on a large folio does not result in
     a (potentially) multi-megabyte writeback IO.

   - Allow some directio completions to be performed in the initiating
     task's context instead of punting through a workqueue. This will
     reduce latency for some io_uring requests"

* tag 'iomap-6.6-merge-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (26 commits)
  iomap: support IOCB_DIO_CALLER_COMP
  io_uring/rw: add write support for IOCB_DIO_CALLER_COMP
  fs: add IOCB flags related to passing back dio completions
  iomap: add IOMAP_DIO_INLINE_COMP
  iomap: only set iocb->private for polled bio
  iomap: treat a write through cache the same as FUA
  iomap: use an unsigned type for IOMAP_DIO_* defines
  iomap: cleanup up iomap_dio_bio_end_io()
  iomap: Add per-block dirty state tracking to improve performance
  iomap: Allocate ifs in ->write_begin() early
  iomap: Refactor iomap_write_delalloc_punch() function out
  iomap: Use iomap_punch_t typedef
  iomap: Fix possible overflow condition in iomap_write_delalloc_scan
  iomap: Add some uptodate state handling helpers for ifs state bitmap
  iomap: Drop ifs argument from iomap_set_range_uptodate()
  iomap: Rename iomap_page to iomap_folio_state and others
  iomap: Copy larger chunks from userspace
  iomap: Create large folios in the buffered write path
  filemap: Allow __filemap_get_folio to allocate large folios
  filemap: Add fgf_t typedef
  ...

4 files changed, 114 insertions, 15 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4e270f3ed58e..dda08d973639 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -338,6 +338,20 @@ enum rw_hint {
 #define IOCB_NOIO		(1 << 20)
 /* can use bio alloc cache */
 #define IOCB_ALLOC_CACHE	(1 << 21)
+/*
+ * IOCB_DIO_CALLER_COMP can be set by the iocb owner, to indicate that the
+ * iocb completion can be passed back to the owner for execution from a safe
+ * context rather than needing to be punted through a workqueue. If this
+ * flag is set, the bio completion handling may set iocb->dio_complete to a
+ * handler function and iocb->private to context information for that handler.
+ * The issuer should call the handler with that context information from task
+ * context to complete the processing of the iocb. Note that while this
+ * provides a task context for the dio_complete() callback, it should only be
+ * used on the completion side for non-IO generating completions. It's fine to
+ * call blocking functions from this callback, but they should not wait for
+ * unrelated IO (like cache flushing, new IO generation, etc).
+ */
+#define IOCB_DIO_CALLER_COMP	(1 << 22)
 
 /* for use in trace events */
 #define TRACE_IOCB_STRINGS \
@@ -351,7 +365,8 @@ enum rw_hint {
 	{ IOCB_WRITE,		"WRITE" }, \
 	{ IOCB_WAITQ,		"WAITQ" }, \
 	{ IOCB_NOIO,		"NOIO" }, \
-	{ IOCB_ALLOC_CACHE,	"ALLOC_CACHE" }
+	{ IOCB_ALLOC_CACHE,	"ALLOC_CACHE" }, \
+	{ IOCB_DIO_CALLER_COMP,	"CALLER_COMP" }
 
 struct kiocb {
 	struct file		*ki_filp;
@@ -360,7 +375,23 @@ struct kiocb {
 	void			*private;
 	int			ki_flags;
 	u16			ki_ioprio; /* See linux/ioprio.h */
-	struct wait_page_queue	*ki_waitq; /* for async buffered IO */
+	union {
+		/*
+		 * Only used for async buffered reads, where it denotes the
+		 * page waitqueue associated with completing the read. Valid
+		 * IFF IOCB_WAITQ is set.
+		 */
+		struct wait_page_queue	*ki_waitq;
+		/*
+		 * Can be used for O_DIRECT IO, where the completion handling
+		 * is punted back to the issuer of the IO. May only be set
+		 * if IOCB_DIO_CALLER_COMP is set by the issuer, and the issuer
+		 * must then check for presence of this handler when ki_complete
+		 * is invoked. The data passed in to this handler must be
+		 * assigned to ->private when dio_complete is assigned.
+		 */
+		ssize_t (*dio_complete)(void *data);
+	};
 };
 
 static inline bool is_sync_kiocb(struct kiocb *kiocb)
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index e2b836c2e119..fdc6e64f49d6 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -261,9 +261,10 @@ int iomap_file_buffered_write_punch_delalloc(struct inode *inode,
 int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops);
 void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops);
 bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count);
-struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos);
+struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos, size_t len);
 bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags);
 void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len);
+bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio);
 int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
 		const struct iomap_ops *ops);
 int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 716953ee1ebd..d87840acbfb2 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -470,6 +470,19 @@ static inline void *detach_page_private(struct page *page)
 	return folio_detach_private(page_folio(page));
 }
 
+/*
+ * There are some parts of the kernel which assume that PMD entries
+ * are exactly HPAGE_PMD_ORDER.  Those should be fixed, but until then,
+ * limit the maximum allocation order to PMD size.  I'm not aware of any
+ * assumptions about maximum order if THP are disabled, but 8 seems like
+ * a good order (that's 1MB if you're using 4kB pages)
+ */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define MAX_PAGECACHE_ORDER	HPAGE_PMD_ORDER
+#else
+#define MAX_PAGECACHE_ORDER	8
+#endif
+
 #ifdef CONFIG_NUMA
 struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order);
 #else
@@ -501,22 +514,69 @@ pgoff_t page_cache_next_miss(struct address_space *mapping,
 pgoff_t page_cache_prev_miss(struct address_space *mapping,
 			     pgoff_t index, unsigned long max_scan);
 
-#define FGP_ACCESSED		0x00000001
-#define FGP_LOCK		0x00000002
-#define FGP_CREAT		0x00000004
-#define FGP_WRITE		0x00000008
-#define FGP_NOFS		0x00000010
-#define FGP_NOWAIT		0x00000020
-#define FGP_FOR_MMAP		0x00000040
-#define FGP_STABLE		0x00000080
+/**
+ * typedef fgf_t - Flags for getting folios from the page cache.
+ *
+ * Most users of the page cache will not need to use these flags;
+ * there are convenience functions such as filemap_get_folio() and
+ * filemap_lock_folio().  For users which need more control over exactly
+ * what is done with the folios, these flags to __filemap_get_folio()
+ * are available.
+ *
+ * * %FGP_ACCESSED - The folio will be marked accessed.
+ * * %FGP_LOCK - The folio is returned locked.
+ * * %FGP_CREAT - If no folio is present then a new folio is allocated,
+ *   added to the page cache and the VM's LRU list.  The folio is
+ *   returned locked.
+ * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the
+ *   folio is already in cache.  If the folio was allocated, unlock it
+ *   before returning so the caller can do the same dance.
+ * * %FGP_WRITE - The folio will be written to by the caller.
+ * * %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_WRITEBEGIN - The flags to use in a filesystem write_begin()
+ *   implementation.
+ */
+typedef unsigned int __bitwise fgf_t;
+
+#define FGP_ACCESSED		((__force fgf_t)0x00000001)
+#define FGP_LOCK		((__force fgf_t)0x00000002)
+#define FGP_CREAT		((__force fgf_t)0x00000004)
+#define FGP_WRITE		((__force fgf_t)0x00000008)
+#define FGP_NOFS		((__force fgf_t)0x00000010)
+#define FGP_NOWAIT		((__force fgf_t)0x00000020)
+#define FGP_FOR_MMAP		((__force fgf_t)0x00000040)
+#define FGP_STABLE		((__force fgf_t)0x00000080)
+#define FGF_GET_ORDER(fgf)	(((__force unsigned)fgf) >> 26)	/* top 6 bits */
 
 #define FGP_WRITEBEGIN		(FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE)
 
+/**
+ * fgf_set_order - Encode a length in the fgf_t flags.
+ * @size: The suggested size of the folio to create.
+ *
+ * The caller of __filemap_get_folio() can use this to suggest a preferred
+ * size for the folio that is created.  If there is already a folio at
+ * the index, it will be returned, no matter what its size.  If a folio
+ * is freshly created, it may be of a different size than requested
+ * due to alignment constraints, memory pressure, or the presence of
+ * other folios at nearby indices.
+ */
+static inline fgf_t fgf_set_order(size_t size)
+{
+	unsigned int shift = ilog2(size);
+
+	if (shift <= PAGE_SHIFT)
+		return 0;
+	return (__force fgf_t)((shift - PAGE_SHIFT) << 26);
+}
+
 void *filemap_get_entry(struct address_space *mapping, pgoff_t index);
 struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
-		int fgp_flags, gfp_t gfp);
+		fgf_t fgp_flags, gfp_t gfp);
 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
-		int fgp_flags, gfp_t gfp);
+		fgf_t fgp_flags, gfp_t gfp);
 
 /**
  * filemap_get_folio - Find and get a folio.
@@ -590,7 +650,7 @@ static inline struct page *find_get_page(struct address_space *mapping,
 }
 
 static inline struct page *find_get_page_flags(struct address_space *mapping,
-					pgoff_t offset, int fgp_flags)
+					pgoff_t offset, fgf_t fgp_flags)
 {
 	return pagecache_get_page(mapping, offset, fgp_flags, 0);
 }
diff --git a/include/linux/uio.h b/include/linux/uio.h
index ff81e5ccaef2..42bce38a8e87 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -163,7 +163,7 @@ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs)
 	return ret;
 }
 
-size_t copy_page_from_iter_atomic(struct page *page, unsigned offset,
+size_t copy_page_from_iter_atomic(struct page *page, size_t offset,
 				  size_t bytes, struct iov_iter *i);
 void iov_iter_advance(struct iov_iter *i, size_t bytes);
 void iov_iter_revert(struct iov_iter *i, size_t bytes);
@@ -184,6 +184,13 @@ static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset,
 {
 	return copy_page_to_iter(&folio->page, offset, bytes, i);
 }
+
+static inline size_t copy_folio_from_iter_atomic(struct folio *folio,
+		size_t offset, size_t bytes, struct iov_iter *i)
+{
+	return copy_page_from_iter_atomic(&folio->page, offset, bytes, i);
+}
+
 size_t copy_page_to_iter_nofault(struct page *page, unsigned offset,
 				 size_t bytes, struct iov_iter *i);