Merge branch 'xfs-6.15-folios_vmalloc' into XFS-for-linus-6.15-merge

Merge buffer cache conversion to folios and vmalloc

Signed-off-by: Carlos Maiolino <cem@kernel.org>

Documentation/filesystems/iomap/operations.rst

@@ -514,8 +514,8 @@ IOMAP_WRITE`` with any combination of the following enhancements:
    if the mapping is unwritten and the filesystem cannot handle zeroing
    the unaligned regions without exposing stale contents.
 
- * ``IOMAP_ATOMIC``: This write is being issued with torn-write
-   protection.
+ * ``IOMAP_ATOMIC_HW``: This write is being issued with torn-write
+   protection based on HW-offload support.
    Only a single bio can be created for the write, and the write must
    not be split into multiple I/O requests, i.e. flag REQ_ATOMIC must be
    set.
@@ -526,8 +526,20 @@ IOMAP_WRITE`` with any combination of the following enhancements:
    conversion or copy on write), all updates for the entire file range
    must be committed atomically as well.
    Only one space mapping is allowed per untorn write.
-   Untorn writes must be aligned to, and must not be longer than, a
-   single file block.
+   Untorn writes may be longer than a single file block. In all cases,
+   the mapping start disk block must have at least the same alignment as
+   the write offset.
+
+ * ``IOMAP_ATOMIC_SW``: This write is being issued with torn-write
+   protection via a software mechanism provided by the filesystem.
+   All the disk block alignment and single bio restrictions which apply
+   to IOMAP_ATOMIC_HW do not apply here.
+   SW-based untorn writes would typically be used as a fallback when
+   HW-based untorn writes may not be issued, e.g. the range of the write
+   covers multiple extents, meaning that it is not possible to issue
+   a single bio.
+   All filesystem metadata updates for the entire file range must be
+   committed atomically as well.
 
 Callers commonly hold ``i_rwsem`` in shared or exclusive mode before
 calling this function.

fs/ext4/inode.c

@@ -3467,7 +3467,7 @@ static inline bool ext4_want_directio_fallback(unsigned flags, ssize_t written)
 		return false;
 
 	/* atomic writes are all-or-nothing */
-	if (flags & IOMAP_ATOMIC)
+	if (flags & IOMAP_ATOMIC_HW)
 		return false;
 
 	/* can only try again if we wrote nothing */

fs/iomap/direct-io.c

@@ -317,7 +317,7 @@ static int iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio,
  * clearing the WRITE_THROUGH flag in the dio request.
  */
 static inline blk_opf_t iomap_dio_bio_opflags(struct iomap_dio *dio,
-		const struct iomap *iomap, bool use_fua, bool atomic)
+		const struct iomap *iomap, bool use_fua, bool atomic_hw)
 {
 	blk_opf_t opflags = REQ_SYNC | REQ_IDLE;
 
@@ -329,7 +329,7 @@ static inline blk_opf_t iomap_dio_bio_opflags(struct iomap_dio *dio,
 		opflags |= REQ_FUA;
 	else
 		dio->flags &= ~IOMAP_DIO_WRITE_THROUGH;
-	if (atomic)
+	if (atomic_hw)
 		opflags |= REQ_ATOMIC;
 
 	return opflags;
@@ -340,8 +340,8 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio)
 	const struct iomap *iomap = &iter->iomap;
 	struct inode *inode = iter->inode;
 	unsigned int fs_block_size = i_blocksize(inode), pad;
+	bool atomic_hw = iter->flags & IOMAP_ATOMIC_HW;
 	const loff_t length = iomap_length(iter);
-	bool atomic = iter->flags & IOMAP_ATOMIC;
 	loff_t pos = iter->pos;
 	blk_opf_t bio_opf;
 	struct bio *bio;
@@ -351,7 +351,7 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio)
 	u64 copied = 0;
 	size_t orig_count;
 
-	if (atomic && length != fs_block_size)
+	if (atomic_hw && length != iter->len)
 		return -EINVAL;
 
 	if ((pos | length) & (bdev_logical_block_size(iomap->bdev) - 1) ||
@@ -428,7 +428,7 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio)
 			goto out;
 	}
 
-	bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua, atomic);
+	bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua, atomic_hw);
 
 	nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_VECS);
 	do {
@@ -461,7 +461,7 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio)
 		}
 
 		n = bio->bi_iter.bi_size;
-		if (WARN_ON_ONCE(atomic && n != length)) {
+		if (WARN_ON_ONCE(atomic_hw && n != length)) {
 			/*
 			 * This bio should have covered the complete length,
 			 * which it doesn't, so error. We may need to zero out
@@ -650,9 +650,6 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (iocb->ki_flags & IOCB_NOWAIT)
 		iomi.flags |= IOMAP_NOWAIT;
 
-	if (iocb->ki_flags & IOCB_ATOMIC)
-		iomi.flags |= IOMAP_ATOMIC;
-
 	if (iov_iter_rw(iter) == READ) {
 		/* reads can always complete inline */
 		dio->flags |= IOMAP_DIO_INLINE_COMP;
@@ -687,6 +684,11 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 			iomi.flags |= IOMAP_OVERWRITE_ONLY;
 		}
 
+		if (dio_flags & IOMAP_DIO_ATOMIC_SW)
+			iomi.flags |= IOMAP_ATOMIC_SW;
+		else if (iocb->ki_flags & IOCB_ATOMIC)
+			iomi.flags |= IOMAP_ATOMIC_HW;
+
 		/* for data sync or sync, we need sync completion processing */
 		if (iocb_is_dsync(iocb)) {
 			dio->flags |= IOMAP_DIO_NEED_SYNC;

fs/iomap/trace.h

@@ -99,7 +99,7 @@ DEFINE_RANGE_EVENT(iomap_dio_rw_queued);
 	{ IOMAP_FAULT,		"FAULT" }, \
 	{ IOMAP_DIRECT,		"DIRECT" }, \
 	{ IOMAP_NOWAIT,		"NOWAIT" }, \
-	{ IOMAP_ATOMIC,		"ATOMIC" }
+	{ IOMAP_ATOMIC_HW,	"ATOMIC_HW" }
 
 #define IOMAP_F_FLAGS_STRINGS \
 	{ IOMAP_F_NEW,		"NEW" }, \

fs/xfs/libxfs/xfs_ialloc.c

@@ -364,7 +364,7 @@ xfs_ialloc_inode_init(
 				(j * M_IGEO(mp)->blocks_per_cluster));
 		error = xfs_trans_get_buf(tp, mp->m_ddev_targp, d,
 				mp->m_bsize * M_IGEO(mp)->blocks_per_cluster,
-				XBF_UNMAPPED, &fbuf);
+				0, &fbuf);
 		if (error)
 			return error;
 

fs/xfs/libxfs/xfs_inode_buf.c

@@ -137,7 +137,7 @@ xfs_imap_to_bp(
 	int			error;
 
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
-			imap->im_len, XBF_UNMAPPED, bpp, &xfs_inode_buf_ops);
+			imap->im_len, 0, bpp, &xfs_inode_buf_ops);
 	if (xfs_metadata_is_sick(error))
 		xfs_agno_mark_sick(mp, xfs_daddr_to_agno(mp, imap->im_blkno),
 				XFS_SICK_AG_INODES);

fs/xfs/scrub/inode_repair.c

@@ -1560,8 +1560,7 @@ xrep_dinode_core(
 
 	/* Read the inode cluster buffer. */
 	error = xfs_trans_read_buf(sc->mp, sc->tp, sc->mp->m_ddev_targp,
-			ri->imap.im_blkno, ri->imap.im_len, XBF_UNMAPPED, &bp,
-			NULL);
+			ri->imap.im_blkno, ri->imap.im_len, 0, &bp, NULL);
 	if (error)
 		return error;
 

fs/xfs/xfs_buf.c

@@ -55,27 +55,6 @@ static inline bool xfs_buf_is_uncached(struct xfs_buf *bp)
 	return bp->b_rhash_key == XFS_BUF_DADDR_NULL;
 }
 
-static inline int
-xfs_buf_is_vmapped(
-	struct xfs_buf	*bp)
-{
-	/*
-	 * Return true if the buffer is vmapped.
-	 *
-	 * b_addr is null if the buffer is not mapped, but the code is clever
-	 * enough to know it doesn't have to map a single page, so the check has
-	 * to be both for b_addr and bp->b_page_count > 1.
-	 */
-	return bp->b_addr && bp->b_page_count > 1;
-}
-
-static inline int
-xfs_buf_vmap_len(
-	struct xfs_buf	*bp)
-{
-	return (bp->b_page_count * PAGE_SIZE);
-}
-
 /*
  * When we mark a buffer stale, we remove the buffer from the LRU and clear the
  * b_lru_ref count so that the buffer is freed immediately when the buffer
@@ -159,7 +138,7 @@ _xfs_buf_alloc(
 	 * We don't want certain flags to appear in b_flags unless they are
 	 * specifically set by later operations on the buffer.
 	 */
-	flags &= ~(XBF_UNMAPPED | XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD);
+	flags &= ~(XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD);
 
 	/*
 	 * A new buffer is held and locked by the owner.  This ensures that the
@@ -204,29 +183,6 @@ _xfs_buf_alloc(
 	return 0;
 }
 
-static void
-xfs_buf_free_pages(
-	struct xfs_buf	*bp)
-{
-	uint		i;
-
-	ASSERT(bp->b_flags & _XBF_PAGES);
-
-	if (xfs_buf_is_vmapped(bp))
-		vm_unmap_ram(bp->b_addr, bp->b_page_count);
-
-	for (i = 0; i < bp->b_page_count; i++) {
-		if (bp->b_pages[i])
-			__free_page(bp->b_pages[i]);
-	}
-	mm_account_reclaimed_pages(bp->b_page_count);
-
-	if (bp->b_pages != bp->b_page_array)
-		kfree(bp->b_pages);
-	bp->b_pages = NULL;
-	bp->b_flags &= ~_XBF_PAGES;
-}
-
 static void
 xfs_buf_free_callback(
 	struct callback_head	*cb)
@@ -241,154 +197,148 @@ static void
 xfs_buf_free(
 	struct xfs_buf		*bp)
 {
+	unsigned int		size = BBTOB(bp->b_length);
+
 	trace_xfs_buf_free(bp, _RET_IP_);
 
 	ASSERT(list_empty(&bp->b_lru));
 
-	if (xfs_buftarg_is_mem(bp->b_target))
-		xmbuf_unmap_page(bp);
-	else if (bp->b_flags & _XBF_PAGES)
-		xfs_buf_free_pages(bp);
+	if (!xfs_buftarg_is_mem(bp->b_target) && size >= PAGE_SIZE)
+		mm_account_reclaimed_pages(howmany(size, PAGE_SHIFT));
+
+	if (is_vmalloc_addr(bp->b_addr))
+		vfree(bp->b_addr);
 	else if (bp->b_flags & _XBF_KMEM)
 		kfree(bp->b_addr);
+	else
+		folio_put(virt_to_folio(bp->b_addr));
 
 	call_rcu(&bp->b_rcu, xfs_buf_free_callback);
 }
 
 static int
 xfs_buf_alloc_kmem(
-	struct xfs_buf	*bp,
-	xfs_buf_flags_t	flags)
+	struct xfs_buf		*bp,
+	size_t			size,
+	gfp_t			gfp_mask)
 {
-	gfp_t		gfp_mask = GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL;
-	size_t		size = BBTOB(bp->b_length);
+	ASSERT(is_power_of_2(size));
+	ASSERT(size < PAGE_SIZE);
 
-	/* Assure zeroed buffer for non-read cases. */
-	if (!(flags & XBF_READ))
-		gfp_mask |= __GFP_ZERO;
-
-	bp->b_addr = kmalloc(size, gfp_mask);
+	bp->b_addr = kmalloc(size, gfp_mask | __GFP_NOFAIL);
 	if (!bp->b_addr)
 		return -ENOMEM;
 
-	if (((unsigned long)(bp->b_addr + size - 1) & PAGE_MASK) !=
-	    ((unsigned long)bp->b_addr & PAGE_MASK)) {
-		/* b_addr spans two pages - use alloc_page instead */
+	/*
+	 * Slab guarantees that we get back naturally aligned allocations for
+	 * power of two sizes.  Keep this check as the canary in the coal mine
+	 * if anything changes in slab.
+	 */
+	if (WARN_ON_ONCE(!IS_ALIGNED((unsigned long)bp->b_addr, size))) {
 		kfree(bp->b_addr);
 		bp->b_addr = NULL;
 		return -ENOMEM;
 	}
-	bp->b_offset = offset_in_page(bp->b_addr);
-	bp->b_pages = bp->b_page_array;
-	bp->b_pages[0] = kmem_to_page(bp->b_addr);
-	bp->b_page_count = 1;
 	bp->b_flags |= _XBF_KMEM;
+	trace_xfs_buf_backing_kmem(bp, _RET_IP_);
 	return 0;
 }
 
+/*
+ * Allocate backing memory for a buffer.
+ *
+ * For tmpfs-backed buffers used by in-memory btrees this directly maps the
+ * tmpfs page cache folios.
+ *
+ * For real file system buffers there are three different kinds backing memory:
+ *
+ * The first type backs the buffer by a kmalloc allocation.  This is done for
+ * less than PAGE_SIZE allocations to avoid wasting memory.
+ *
+ * The second type is a single folio buffer - this may be a high order folio or
+ * just a single page sized folio, but either way they get treated the same way
+ * by the rest of the code - the buffer memory spans a single contiguous memory
+ * region that we don't have to map and unmap to access the data directly.
+ *
+ * The third type of buffer is the vmalloc()d buffer. This provides the buffer
+ * with the required contiguous memory region but backed by discontiguous
+ * physical pages.
+ */
 static int
-xfs_buf_alloc_pages(
+xfs_buf_alloc_backing_mem(
 	struct xfs_buf	*bp,
 	xfs_buf_flags_t	flags)
 {
+	size_t		size = BBTOB(bp->b_length);
 	gfp_t		gfp_mask = GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOWARN;
-	long		filled = 0;
+	struct folio	*folio;
 
-	if (flags & XBF_READ_AHEAD)
-		gfp_mask |= __GFP_NORETRY;
-
-	/* Make sure that we have a page list */
-	bp->b_page_count = DIV_ROUND_UP(BBTOB(bp->b_length), PAGE_SIZE);
-	if (bp->b_page_count <= XB_PAGES) {
-		bp->b_pages = bp->b_page_array;
-	} else {
-		bp->b_pages = kzalloc(sizeof(struct page *) * bp->b_page_count,
-					gfp_mask);
-		if (!bp->b_pages)
-			return -ENOMEM;
-	}
-	bp->b_flags |= _XBF_PAGES;
+	if (xfs_buftarg_is_mem(bp->b_target))
+		return xmbuf_map_backing_mem(bp);
 
 	/* Assure zeroed buffer for non-read cases. */
 	if (!(flags & XBF_READ))
 		gfp_mask |= __GFP_ZERO;
 
+	if (flags & XBF_READ_AHEAD)
+		gfp_mask |= __GFP_NORETRY;
+
 	/*
-	 * Bulk filling of pages can take multiple calls. Not filling the entire
-	 * array is not an allocation failure, so don't back off if we get at
-	 * least one extra page.
+	 * For buffers smaller than PAGE_SIZE use a kmalloc allocation if that
+	 * is properly aligned.  The slab allocator now guarantees an aligned
+	 * allocation for all power of two sizes, which matches most of the
+	 * smaller than PAGE_SIZE buffers used by XFS.
 	 */
-	for (;;) {
-		long	last = filled;
+	if (size < PAGE_SIZE && is_power_of_2(size))
+		return xfs_buf_alloc_kmem(bp, size, gfp_mask);
 
-		filled = alloc_pages_bulk(gfp_mask, bp->b_page_count,
-					  bp->b_pages);
-		if (filled == bp->b_page_count) {
-			XFS_STATS_INC(bp->b_mount, xb_page_found);
-			break;
-		}
+	/*
+	 * Don't bother with the retry loop for single PAGE allocations: vmalloc
+	 * won't do any better.
+	 */
+	if (size <= PAGE_SIZE)
+		gfp_mask |= __GFP_NOFAIL;
 
-		if (filled != last)
-			continue;
-
-		if (flags & XBF_READ_AHEAD) {
-			xfs_buf_free_pages(bp);
+	/*
+	 * Optimistically attempt a single high order folio allocation for
+	 * larger than PAGE_SIZE buffers.
+	 *
+	 * Allocating a high order folio makes the assumption that buffers are a
+	 * power-of-2 size, matching the power-of-2 folios sizes available.
+	 *
+	 * The exception here are user xattr data buffers, which can be arbitrarily
+	 * sized up to 64kB plus structure metadata, skip straight to the vmalloc
+	 * path for them instead of wasting memory here.
+	 */
+	if (size > PAGE_SIZE) {
+		if (!is_power_of_2(size))
+			goto fallback;
+		gfp_mask &= ~__GFP_DIRECT_RECLAIM;
+		gfp_mask |= __GFP_NORETRY;
+	}
+	folio = folio_alloc(gfp_mask, get_order(size));
+	if (!folio) {
+		if (size <= PAGE_SIZE)
 			return -ENOMEM;
-		}
+		trace_xfs_buf_backing_fallback(bp, _RET_IP_);
+		goto fallback;
+	}
+	bp->b_addr = folio_address(folio);
+	trace_xfs_buf_backing_folio(bp, _RET_IP_);
+	return 0;
 
+fallback:
+	for (;;) {
+		bp->b_addr = __vmalloc(size, gfp_mask);
+		if (bp->b_addr)
+			break;
+		if (flags & XBF_READ_AHEAD)
+			return -ENOMEM;
 		XFS_STATS_INC(bp->b_mount, xb_page_retries);
 		memalloc_retry_wait(gfp_mask);
 	}
-	return 0;
-}
-
-/*
- *	Map buffer into kernel address-space if necessary.
- */
-STATIC int
-_xfs_buf_map_pages(
-	struct xfs_buf		*bp,
-	xfs_buf_flags_t		flags)
-{
-	ASSERT(bp->b_flags & _XBF_PAGES);
-	if (bp->b_page_count == 1) {
-		/* A single page buffer is always mappable */
-		bp->b_addr = page_address(bp->b_pages[0]);
-	} else if (flags & XBF_UNMAPPED) {
-		bp->b_addr = NULL;
-	} else {
-		int retried = 0;
-		unsigned nofs_flag;
-
-		/*
-		 * vm_map_ram() will allocate auxiliary structures (e.g.
-		 * pagetables) with GFP_KERNEL, yet we often under a scoped nofs
-		 * context here. Mixing GFP_KERNEL with GFP_NOFS allocations
-		 * from the same call site that can be run from both above and
-		 * below memory reclaim causes lockdep false positives. Hence we
-		 * always need to force this allocation to nofs context because
-		 * we can't pass __GFP_NOLOCKDEP down to auxillary structures to
-		 * prevent false positive lockdep reports.
-		 *
-		 * XXX(dgc): I think dquot reclaim is the only place we can get
-		 * to this function from memory reclaim context now. If we fix
-		 * that like we've fixed inode reclaim to avoid writeback from
-		 * reclaim, this nofs wrapping can go away.
-		 */
-		nofs_flag = memalloc_nofs_save();
-		do {
-			bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count,
-						-1);
-			if (bp->b_addr)
-				break;
-			vm_unmap_aliases();
-		} while (retried++ <= 1);
-		memalloc_nofs_restore(nofs_flag);
-
-		if (!bp->b_addr)
-			return -ENOMEM;
-	}
 
+	trace_xfs_buf_backing_vmalloc(bp, _RET_IP_);
 	return 0;
 }
 
@@ -507,7 +457,7 @@ xfs_buf_find_lock(
 			return -ENOENT;
 		}
 		ASSERT((bp->b_flags & _XBF_DELWRI_Q) == 0);
-		bp->b_flags &= _XBF_KMEM | _XBF_PAGES;
+		bp->b_flags &= _XBF_KMEM;
 		bp->b_ops = NULL;
 	}
 	return 0;
@@ -579,18 +529,7 @@ xfs_buf_find_insert(
 	if (error)
 		goto out_drop_pag;
 
-	if (xfs_buftarg_is_mem(new_bp->b_target)) {
-		error = xmbuf_map_page(new_bp);
-	} else if (BBTOB(new_bp->b_length) >= PAGE_SIZE ||
-		   xfs_buf_alloc_kmem(new_bp, flags) < 0) {
-		/*
-		 * For buffers that fit entirely within a single page, first
-		 * attempt to allocate the memory from the heap to minimise
-		 * memory usage. If we can't get heap memory for these small
-		 * buffers, we fall back to using the page allocator.
-		 */
-		error = xfs_buf_alloc_pages(new_bp, flags);
-	}
+	error = xfs_buf_alloc_backing_mem(new_bp, flags);
 	if (error)
 		goto out_free_buf;
 
@@ -704,18 +643,6 @@ xfs_buf_get_map(
 			xfs_perag_put(pag);
 	}
 
-	/* We do not hold a perag reference anymore. */
-	if (!bp->b_addr) {
-		error = _xfs_buf_map_pages(bp, flags);
-		if (unlikely(error)) {
-			xfs_warn_ratelimited(btp->bt_mount,
-				"%s: failed to map %u pages", __func__,
-				bp->b_page_count);
-			xfs_buf_relse(bp);
-			return error;
-		}
-	}
-
 	/*
 	 * Clear b_error if this is a lookup from a caller that doesn't expect
 	 * valid data to be found in the buffer.
@@ -954,20 +881,10 @@ xfs_buf_get_uncached(
 	if (error)
 		return error;
 
-	if (xfs_buftarg_is_mem(bp->b_target))
-		error = xmbuf_map_page(bp);
-	else
-		error = xfs_buf_alloc_pages(bp, flags);
+	error = xfs_buf_alloc_backing_mem(bp, flags);
 	if (error)
 		goto fail_free_buf;
 
-	error = _xfs_buf_map_pages(bp, 0);
-	if (unlikely(error)) {
-		xfs_warn(target->bt_mount,
-			"%s: failed to map pages", __func__);
-		goto fail_free_buf;
-	}
-
 	trace_xfs_buf_get_uncached(bp, _RET_IP_);
 	*bpp = bp;
 	return 0;
@@ -1299,9 +1216,9 @@ __xfs_buf_ioend(
 	trace_xfs_buf_iodone(bp, _RET_IP_);
 
 	if (bp->b_flags & XBF_READ) {
-		if (!bp->b_error && xfs_buf_is_vmapped(bp))
+		if (!bp->b_error && is_vmalloc_addr(bp->b_addr))
 			invalidate_kernel_vmap_range(bp->b_addr,
-					xfs_buf_vmap_len(bp));
+				roundup(BBTOB(bp->b_length), PAGE_SIZE));
 		if (!bp->b_error && bp->b_ops)
 			bp->b_ops->verify_read(bp);
 		if (!bp->b_error)
@@ -1462,29 +1379,48 @@ static void
 xfs_buf_submit_bio(
 	struct xfs_buf		*bp)
 {
-	unsigned int		size = BBTOB(bp->b_length);
-	unsigned int		map = 0, p;
+	unsigned int		map = 0;
 	struct blk_plug		plug;
 	struct bio		*bio;
 
-	bio = bio_alloc(bp->b_target->bt_bdev, bp->b_page_count,
-			xfs_buf_bio_op(bp), GFP_NOIO);
+	if (is_vmalloc_addr(bp->b_addr)) {
+		unsigned int	size = BBTOB(bp->b_length);
+		unsigned int	alloc_size = roundup(size, PAGE_SIZE);
+		void		*data = bp->b_addr;
+
+		bio = bio_alloc(bp->b_target->bt_bdev, alloc_size >> PAGE_SHIFT,
+				xfs_buf_bio_op(bp), GFP_NOIO);
+
+		do {
+			unsigned int	len = min(size, PAGE_SIZE);
+
+			ASSERT(offset_in_page(data) == 0);
+			__bio_add_page(bio, vmalloc_to_page(data), len, 0);
+			data += len;
+			size -= len;
+		} while (size);
+
+		flush_kernel_vmap_range(bp->b_addr, alloc_size);
+	} else {
+		/*
+		 * Single folio or slab allocation.  Must be contiguous and thus
+		 * only a single bvec is needed.
+		 *
+		 * This uses the page based bio add helper for now as that is
+		 * the lowest common denominator between folios and slab
+		 * allocations.  To be replaced with a better block layer
+		 * helper soon (hopefully).
+		 */
+		bio = bio_alloc(bp->b_target->bt_bdev, 1, xfs_buf_bio_op(bp),
+				GFP_NOIO);
+		__bio_add_page(bio, virt_to_page(bp->b_addr),
+				BBTOB(bp->b_length),
+				offset_in_page(bp->b_addr));
+	}
+
 	bio->bi_private = bp;
 	bio->bi_end_io = xfs_buf_bio_end_io;
 
-	if (bp->b_flags & _XBF_KMEM) {
-		__bio_add_page(bio, virt_to_page(bp->b_addr), size,
-				bp->b_offset);
-	} else {
-		for (p = 0; p < bp->b_page_count; p++)
-			__bio_add_page(bio, bp->b_pages[p], PAGE_SIZE, 0);
-		bio->bi_iter.bi_size = size; /* limit to the actual size used */
-
-		if (xfs_buf_is_vmapped(bp))
-			flush_kernel_vmap_range(bp->b_addr,
-					xfs_buf_vmap_len(bp));
-	}
-
 	/*
 	 * If there is more than one map segment, split out a new bio for each
 	 * map except of the last one.  The last map is handled by the
@@ -1611,47 +1547,6 @@ xfs_buf_submit(
 	xfs_buf_submit_bio(bp);
 }
 
-void *
-xfs_buf_offset(
-	struct xfs_buf		*bp,
-	size_t			offset)
-{
-	struct page		*page;
-
-	if (bp->b_addr)
-		return bp->b_addr + offset;
-
-	page = bp->b_pages[offset >> PAGE_SHIFT];
-	return page_address(page) + (offset & (PAGE_SIZE-1));
-}
-
-void
-xfs_buf_zero(
-	struct xfs_buf		*bp,
-	size_t			boff,
-	size_t			bsize)
-{
-	size_t			bend;
-
-	bend = boff + bsize;
-	while (boff < bend) {
-		struct page	*page;
-		int		page_index, page_offset, csize;
-
-		page_index = (boff + bp->b_offset) >> PAGE_SHIFT;
-		page_offset = (boff + bp->b_offset) & ~PAGE_MASK;
-		page = bp->b_pages[page_index];
-		csize = min_t(size_t, PAGE_SIZE - page_offset,
-				      BBTOB(bp->b_length) - boff);
-
-		ASSERT((csize + page_offset) <= PAGE_SIZE);
-
-		memset(page_address(page) + page_offset, 0, csize);
-
-		boff += csize;
-	}
-}
-
 /*
  * Log a message about and stale a buffer that a caller has decided is corrupt.
  *

fs/xfs/xfs_buf.h

@@ -36,7 +36,6 @@ struct xfs_buf;
 #define _XBF_LOGRECOVERY (1u << 18)/* log recovery buffer */
 
 /* flags used only internally */
-#define _XBF_PAGES	 (1u << 20)/* backed by refcounted pages */
 #define _XBF_KMEM	 (1u << 21)/* backed by heap memory */
 #define _XBF_DELWRI_Q	 (1u << 22)/* buffer on a delwri queue */
 
@@ -48,7 +47,6 @@ struct xfs_buf;
 #define XBF_LIVESCAN	 (1u << 28)
 #define XBF_INCORE	 (1u << 29)/* lookup only, return if found in cache */
 #define XBF_TRYLOCK	 (1u << 30)/* lock requested, but do not wait */
-#define XBF_UNMAPPED	 (1u << 31)/* do not map the buffer */
 
 
 typedef unsigned int xfs_buf_flags_t;
@@ -62,14 +60,12 @@ typedef unsigned int xfs_buf_flags_t;
 	{ XBF_STALE,		"STALE" }, \
 	{ XBF_WRITE_FAIL,	"WRITE_FAIL" }, \
 	{ _XBF_LOGRECOVERY,	"LOG_RECOVERY" }, \
-	{ _XBF_PAGES,		"PAGES" }, \
 	{ _XBF_KMEM,		"KMEM" }, \
 	{ _XBF_DELWRI_Q,	"DELWRI_Q" }, \
 	/* The following interface flags should never be set */ \
 	{ XBF_LIVESCAN,		"LIVESCAN" }, \
 	{ XBF_INCORE,		"INCORE" }, \
-	{ XBF_TRYLOCK,		"TRYLOCK" }, \
-	{ XBF_UNMAPPED,		"UNMAPPED" }
+	{ XBF_TRYLOCK,		"TRYLOCK" }
 
 /*
  * Internal state flags.
@@ -124,8 +120,6 @@ struct xfs_buftarg {
 	struct xfs_buf_cache	bt_cache[];
 };
 
-#define XB_PAGES	2
-
 struct xfs_buf_map {
 	xfs_daddr_t		bm_bn;	/* block number for I/O */
 	int			bm_len;	/* size of I/O */
@@ -187,15 +181,10 @@ struct xfs_buf {
 	struct xfs_buf_log_item	*b_log_item;
 	struct list_head	b_li_list;	/* Log items list head */
 	struct xfs_trans	*b_transp;
-	struct page		**b_pages;	/* array of page pointers */
-	struct page		*b_page_array[XB_PAGES]; /* inline pages */
 	struct xfs_buf_map	*b_maps;	/* compound buffer map */
 	struct xfs_buf_map	__b_map;	/* inline compound buffer map */
 	int			b_map_count;
 	atomic_t		b_pin_count;	/* pin count */
-	unsigned int		b_page_count;	/* size of page array */
-	unsigned int		b_offset;	/* page offset of b_addr,
-						   only for _XBF_KMEM buffers */
 	int			b_error;	/* error code on I/O */
 	void			(*b_iodone)(struct xfs_buf *bp);
 
@@ -315,12 +304,20 @@ extern void __xfs_buf_ioerror(struct xfs_buf *bp, int error,
 #define xfs_buf_ioerror(bp, err) __xfs_buf_ioerror((bp), (err), __this_address)
 extern void xfs_buf_ioerror_alert(struct xfs_buf *bp, xfs_failaddr_t fa);
 void xfs_buf_ioend_fail(struct xfs_buf *);
-void xfs_buf_zero(struct xfs_buf *bp, size_t boff, size_t bsize);
 void __xfs_buf_mark_corrupt(struct xfs_buf *bp, xfs_failaddr_t fa);
 #define xfs_buf_mark_corrupt(bp) __xfs_buf_mark_corrupt((bp), __this_address)
 
 /* Buffer Utility Routines */
-extern void *xfs_buf_offset(struct xfs_buf *, size_t);
+static inline void *xfs_buf_offset(struct xfs_buf *bp, size_t offset)
+{
+	return bp->b_addr + offset;
+}
+
+static inline void xfs_buf_zero(struct xfs_buf *bp, size_t boff, size_t bsize)
+{
+	memset(bp->b_addr + boff, 0, bsize);
+}
+
 extern void xfs_buf_stale(struct xfs_buf *bp);
 
 /* Delayed Write Buffer Routines */

fs/xfs/xfs_buf_item.c

@@ -57,24 +57,6 @@ xfs_buf_log_format_size(
 			(blfp->blf_map_size * sizeof(blfp->blf_data_map[0]));
 }
 
-static inline bool
-xfs_buf_item_straddle(
-	struct xfs_buf		*bp,
-	uint			offset,
-	int			first_bit,
-	int			nbits)
-{
-	void			*first, *last;
-
-	first = xfs_buf_offset(bp, offset + (first_bit << XFS_BLF_SHIFT));
-	last = xfs_buf_offset(bp,
-			offset + ((first_bit + nbits) << XFS_BLF_SHIFT));
-
-	if (last - first != nbits * XFS_BLF_CHUNK)
-		return true;
-	return false;
-}
-
 /*
  * Return the number of log iovecs and space needed to log the given buf log
  * item segment.
@@ -91,11 +73,8 @@ xfs_buf_item_size_segment(
 	int				*nvecs,
 	int				*nbytes)
 {
-	struct xfs_buf			*bp = bip->bli_buf;
 	int				first_bit;
 	int				nbits;
-	int				next_bit;
-	int				last_bit;
 
 	first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
 	if (first_bit == -1)
@@ -108,15 +87,6 @@ xfs_buf_item_size_segment(
 		nbits = xfs_contig_bits(blfp->blf_data_map,
 					blfp->blf_map_size, first_bit);
 		ASSERT(nbits > 0);
-
-		/*
-		 * Straddling a page is rare because we don't log contiguous
-		 * chunks of unmapped buffers anywhere.
-		 */
-		if (nbits > 1 &&
-		    xfs_buf_item_straddle(bp, offset, first_bit, nbits))
-			goto slow_scan;
-
 		(*nvecs)++;
 		*nbytes += nbits * XFS_BLF_CHUNK;
 
@@ -131,40 +101,6 @@ xfs_buf_item_size_segment(
 	} while (first_bit != -1);
 
 	return;
-
-slow_scan:
-	/* Count the first bit we jumped out of the above loop from */
-	(*nvecs)++;
-	*nbytes += XFS_BLF_CHUNK;
-	last_bit = first_bit;
-	while (last_bit != -1) {
-		/*
-		 * This takes the bit number to start looking from and
-		 * returns the next set bit from there.  It returns -1
-		 * if there are no more bits set or the start bit is
-		 * beyond the end of the bitmap.
-		 */
-		next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
-					last_bit + 1);
-		/*
-		 * If we run out of bits, leave the loop,
-		 * else if we find a new set of bits bump the number of vecs,
-		 * else keep scanning the current set of bits.
-		 */
-		if (next_bit == -1) {
-			break;
-		} else if (next_bit != last_bit + 1 ||
-		           xfs_buf_item_straddle(bp, offset, first_bit, nbits)) {
-			last_bit = next_bit;
-			first_bit = next_bit;
-			(*nvecs)++;
-			nbits = 1;
-		} else {
-			last_bit++;
-			nbits++;
-		}
-		*nbytes += XFS_BLF_CHUNK;
-	}
 }
 
 /*
@@ -277,8 +213,6 @@ xfs_buf_item_format_segment(
 	struct xfs_buf		*bp = bip->bli_buf;
 	uint			base_size;
 	int			first_bit;
-	int			last_bit;
-	int			next_bit;
 	uint			nbits;
 
 	/* copy the flags across from the base format item */
@@ -323,15 +257,6 @@ xfs_buf_item_format_segment(
 		nbits = xfs_contig_bits(blfp->blf_data_map,
 					blfp->blf_map_size, first_bit);
 		ASSERT(nbits > 0);
-
-		/*
-		 * Straddling a page is rare because we don't log contiguous
-		 * chunks of unmapped buffers anywhere.
-		 */
-		if (nbits > 1 &&
-		    xfs_buf_item_straddle(bp, offset, first_bit, nbits))
-			goto slow_scan;
-
 		xfs_buf_item_copy_iovec(lv, vecp, bp, offset,
 					first_bit, nbits);
 		blfp->blf_size++;
@@ -347,45 +272,6 @@ xfs_buf_item_format_segment(
 	} while (first_bit != -1);
 
 	return;
-
-slow_scan:
-	ASSERT(bp->b_addr == NULL);
-	last_bit = first_bit;
-	nbits = 1;
-	for (;;) {
-		/*
-		 * This takes the bit number to start looking from and
-		 * returns the next set bit from there.  It returns -1
-		 * if there are no more bits set or the start bit is
-		 * beyond the end of the bitmap.
-		 */
-		next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
-					(uint)last_bit + 1);
-		/*
-		 * If we run out of bits fill in the last iovec and get out of
-		 * the loop.  Else if we start a new set of bits then fill in
-		 * the iovec for the series we were looking at and start
-		 * counting the bits in the new one.  Else we're still in the
-		 * same set of bits so just keep counting and scanning.
-		 */
-		if (next_bit == -1) {
-			xfs_buf_item_copy_iovec(lv, vecp, bp, offset,
-						first_bit, nbits);
-			blfp->blf_size++;
-			break;
-		} else if (next_bit != last_bit + 1 ||
-		           xfs_buf_item_straddle(bp, offset, first_bit, nbits)) {
-			xfs_buf_item_copy_iovec(lv, vecp, bp, offset,
-						first_bit, nbits);
-			blfp->blf_size++;
-			first_bit = next_bit;
-			last_bit = next_bit;
-			nbits = 1;
-		} else {
-			last_bit++;
-			nbits++;
-		}
-	}
 }
 
 /*

fs/xfs/xfs_buf_item_recover.c

@@ -1006,7 +1006,6 @@ xlog_recover_buf_commit_pass2(
 	struct xfs_mount		*mp = log->l_mp;
 	struct xfs_buf			*bp;
 	int				error;
-	uint				buf_flags;
 	xfs_lsn_t			lsn;
 
 	/*
@@ -1025,13 +1024,8 @@ xlog_recover_buf_commit_pass2(
 	}
 
 	trace_xfs_log_recover_buf_recover(log, buf_f);
-
-	buf_flags = 0;
-	if (buf_f->blf_flags & XFS_BLF_INODE_BUF)
-		buf_flags |= XBF_UNMAPPED;
-
 	error = xfs_buf_read(mp->m_ddev_targp, buf_f->blf_blkno, buf_f->blf_len,
-			  buf_flags, &bp, NULL);
+			  0, &bp, NULL);
 	if (error)
 		return error;
 

fs/xfs/xfs_buf_mem.c

@@ -74,7 +74,7 @@ xmbuf_alloc(
 
 	/*
 	 * We don't want to bother with kmapping data during repair, so don't
-	 * allow highmem pages to back this mapping.
+	 * allow highmem folios to back this mapping.
 	 */
 	mapping_set_gfp_mask(inode->i_mapping, GFP_KERNEL);
 
@@ -127,14 +127,13 @@ xmbuf_free(
 	kfree(btp);
 }
 
-/* Directly map a shmem page into the buffer cache. */
+/* Directly map a shmem folio into the buffer cache. */
 int
-xmbuf_map_page(
+xmbuf_map_backing_mem(
 	struct xfs_buf		*bp)
 {
 	struct inode		*inode = file_inode(bp->b_target->bt_file);
 	struct folio		*folio = NULL;
-	struct page		*page;
 	loff_t                  pos = BBTOB(xfs_buf_daddr(bp));
 	int			error;
 
@@ -159,39 +158,17 @@ xmbuf_map_page(
 		return -EIO;
 	}
 
-	page = folio_file_page(folio, pos >> PAGE_SHIFT);
-
 	/*
-	 * Mark the page dirty so that it won't be reclaimed once we drop the
-	 * (potentially last) reference in xmbuf_unmap_page.
+	 * Mark the folio dirty so that it won't be reclaimed once we drop the
+	 * (potentially last) reference in xfs_buf_free.
 	 */
-	set_page_dirty(page);
-	unlock_page(page);
+	folio_set_dirty(folio);
+	folio_unlock(folio);
 
-	bp->b_addr = page_address(page);
-	bp->b_pages = bp->b_page_array;
-	bp->b_pages[0] = page;
-	bp->b_page_count = 1;
+	bp->b_addr = folio_address(folio);
 	return 0;
 }
 
-/* Unmap a shmem page that was mapped into the buffer cache. */
-void
-xmbuf_unmap_page(
-	struct xfs_buf		*bp)
-{
-	struct page		*page = bp->b_pages[0];
-
-	ASSERT(xfs_buftarg_is_mem(bp->b_target));
-
-	put_page(page);
-
-	bp->b_addr = NULL;
-	bp->b_pages[0] = NULL;
-	bp->b_pages = NULL;
-	bp->b_page_count = 0;
-}
-
 /* Is this a valid daddr within the buftarg? */
 bool
 xmbuf_verify_daddr(
@@ -205,7 +182,7 @@ xmbuf_verify_daddr(
 	return daddr < (inode->i_sb->s_maxbytes >> BBSHIFT);
 }
 
-/* Discard the page backing this buffer. */
+/* Discard the folio backing this buffer. */
 static void
 xmbuf_stale(
 	struct xfs_buf		*bp)
@@ -220,7 +197,7 @@ xmbuf_stale(
 }
 
 /*
- * Finalize a buffer -- discard the backing page if it's stale, or run the
+ * Finalize a buffer -- discard the backing folio if it's stale, or run the
  * write verifier to detect problems.
  */
 int

fs/xfs/xfs_buf_mem.h

@@ -19,16 +19,14 @@ int xmbuf_alloc(struct xfs_mount *mp, const char *descr,
 		struct xfs_buftarg **btpp);
 void xmbuf_free(struct xfs_buftarg *btp);
 
-int xmbuf_map_page(struct xfs_buf *bp);
-void xmbuf_unmap_page(struct xfs_buf *bp);
 bool xmbuf_verify_daddr(struct xfs_buftarg *btp, xfs_daddr_t daddr);
 void xmbuf_trans_bdetach(struct xfs_trans *tp, struct xfs_buf *bp);
 int xmbuf_finalize(struct xfs_buf *bp);
 #else
 # define xfs_buftarg_is_mem(...)	(false)
-# define xmbuf_map_page(...)		(-ENOMEM)
-# define xmbuf_unmap_page(...)		((void)0)
 # define xmbuf_verify_daddr(...)	(false)
 #endif /* CONFIG_XFS_MEMORY_BUFS */
 
+int xmbuf_map_backing_mem(struct xfs_buf *bp);
+
 #endif /* __XFS_BUF_MEM_H__ */

fs/xfs/xfs_inode.c

@@ -1721,8 +1721,7 @@ xfs_ifree_cluster(
 		 * to mark all the active inodes on the buffer stale.
 		 */
 		error = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno,
-				mp->m_bsize * igeo->blocks_per_cluster,
-				XBF_UNMAPPED, &bp);
+				mp->m_bsize * igeo->blocks_per_cluster, 0, &bp);
 		if (error)
 			return error;
 

fs/xfs/xfs_trace.h

@@ -692,6 +692,10 @@ DEFINE_BUF_EVENT(xfs_buf_iodone_async);
 DEFINE_BUF_EVENT(xfs_buf_error_relse);
 DEFINE_BUF_EVENT(xfs_buf_drain_buftarg);
 DEFINE_BUF_EVENT(xfs_trans_read_buf_shut);
+DEFINE_BUF_EVENT(xfs_buf_backing_folio);
+DEFINE_BUF_EVENT(xfs_buf_backing_kmem);
+DEFINE_BUF_EVENT(xfs_buf_backing_vmalloc);
+DEFINE_BUF_EVENT(xfs_buf_backing_fallback);
 
 /* not really buffer traces, but the buf provides useful information */
 DEFINE_BUF_EVENT(xfs_btree_corrupt);

include/linux/iomap.h

@@ -189,8 +189,9 @@ struct iomap_folio_ops {
 #else
 #define IOMAP_DAX		0
 #endif /* CONFIG_FS_DAX */
-#define IOMAP_ATOMIC		(1 << 9)
+#define IOMAP_ATOMIC_HW		(1 << 9) /* HW-based torn-write protection */
 #define IOMAP_DONTCACHE		(1 << 10)
+#define IOMAP_ATOMIC_SW		(1 << 11)/* SW-based torn-write protection */
 
 struct iomap_ops {
 	/*
@@ -502,6 +503,11 @@ struct iomap_dio_ops {
  */
 #define IOMAP_DIO_PARTIAL		(1 << 2)
 
+/*
+ * Use software-based torn-write protection.
+ */
+#define IOMAP_DIO_ATOMIC_SW		(1 << 3)
+
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		unsigned int dio_flags, void *private, size_t done_before);