Merge tag 'xfs-merge-6.16' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs updates from Carlos Maiolino:

 - Atomic writes for XFS

 - Remove experimental warnings for pNFS, scrub and parent pointers

* tag 'xfs-merge-6.16' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (26 commits)
  xfs: add inode to zone caching for data placement
  xfs: free the item in xfs_mru_cache_insert on failure
  xfs: remove the EXPERIMENTAL warning for pNFS
  xfs: remove some EXPERIMENTAL warnings
  xfs: Remove deprecated xfs_bufd sysctl parameters
  xfs: stop using set_blocksize
  xfs: allow sysadmins to specify a maximum atomic write limit at mount time
  xfs: update atomic write limits
  xfs: add xfs_calc_atomic_write_unit_max()
  xfs: add xfs_file_dio_write_atomic()
  xfs: commit CoW-based atomic writes atomically
  xfs: add large atomic writes checks in xfs_direct_write_iomap_begin()
  xfs: add xfs_atomic_write_cow_iomap_begin()
  xfs: refine atomic write size check in xfs_file_write_iter()
  xfs: refactor xfs_reflink_end_cow_extent()
  xfs: allow block allocator to take an alignment hint
  xfs: ignore HW which cannot atomic write a single block
  xfs: add helpers to compute transaction reservation for finishing intent items
  xfs: add helpers to compute log item overhead
  xfs: separate out setting buftarg atomic writes limits
  ...

Documentation/admin-guide/xfs.rst

@@ -151,6 +151,17 @@ When mounting an XFS filesystem, the following options are accepted.
 	optional, and the log section can be separate from the data
 	section or contained within it.
 
+  max_atomic_write=value
+	Set the maximum size of an atomic write.  The size may be
+	specified in bytes, in kilobytes with a "k" suffix, in megabytes
+	with a "m" suffix, or in gigabytes with a "g" suffix.  The size
+	cannot be larger than the maximum write size, larger than the
+	size of any allocation group, or larger than the size of a
+	remapping operation that the log can complete atomically.
+
+	The default value is to set the maximum I/O completion size
+	to allow each CPU to handle one at a time.
+
   max_open_zones=value
 	Specify the max number of zones to keep open for writing on a
 	zoned rt device. Many open zones aids file data separation

block/bdev.c

@@ -1335,7 +1335,8 @@ void bdev_statx(const struct path *path, struct kstat *stat, u32 request_mask)
 
 		generic_fill_statx_atomic_writes(stat,
 			queue_atomic_write_unit_min_bytes(bd_queue),
-			queue_atomic_write_unit_max_bytes(bd_queue));
+			queue_atomic_write_unit_max_bytes(bd_queue),
+			0);
 	}
 
 	stat->blksize = bdev_io_min(bdev);

fs/ext4/inode.c

@@ -5692,7 +5692,7 @@ int ext4_getattr(struct mnt_idmap *idmap, const struct path *path,
 			awu_max = sbi->s_awu_max;
 		}
 
-		generic_fill_statx_atomic_writes(stat, awu_min, awu_max);
+		generic_fill_statx_atomic_writes(stat, awu_min, awu_max, 0);
 	}
 
 	flags = ei->i_flags & EXT4_FL_USER_VISIBLE;

fs/stat.c

@@ -136,13 +136,15 @@ EXPORT_SYMBOL(generic_fill_statx_attr);
  * @stat:	Where to fill in the attribute flags
  * @unit_min:	Minimum supported atomic write length in bytes
  * @unit_max:	Maximum supported atomic write length in bytes
+ * @unit_max_opt: Optimised maximum supported atomic write length in bytes
  *
  * Fill in the STATX{_ATTR}_WRITE_ATOMIC flags in the kstat structure from
  * atomic write unit_min and unit_max values.
  */
 void generic_fill_statx_atomic_writes(struct kstat *stat,
 				      unsigned int unit_min,
-				      unsigned int unit_max)
+				      unsigned int unit_max,
+				      unsigned int unit_max_opt)
 {
 	/* Confirm that the request type is known */
 	stat->result_mask |= STATX_WRITE_ATOMIC;
@@ -153,6 +155,7 @@ void generic_fill_statx_atomic_writes(struct kstat *stat,
 	if (unit_min) {
 		stat->atomic_write_unit_min = unit_min;
 		stat->atomic_write_unit_max = unit_max;
+		stat->atomic_write_unit_max_opt = unit_max_opt;
 		/* Initially only allow 1x segment */
 		stat->atomic_write_segments_max = 1;
 
@@ -741,6 +744,7 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer)
 	tmp.stx_atomic_write_unit_min = stat->atomic_write_unit_min;
 	tmp.stx_atomic_write_unit_max = stat->atomic_write_unit_max;
 	tmp.stx_atomic_write_segments_max = stat->atomic_write_segments_max;
+	tmp.stx_atomic_write_unit_max_opt = stat->atomic_write_unit_max_opt;
 
 	return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0;
 }

fs/xfs/libxfs/xfs_bmap.c

@@ -3312,6 +3312,11 @@ xfs_bmap_compute_alignments(
 		align = xfs_get_cowextsz_hint(ap->ip);
 	else if (ap->datatype & XFS_ALLOC_USERDATA)
 		align = xfs_get_extsz_hint(ap->ip);
+
+	/* Try to align start block to any minimum allocation alignment */
+	if (align > 1 && (ap->flags & XFS_BMAPI_EXTSZALIGN))
+		args->alignment = align;
+
 	if (align) {
 		if (xfs_bmap_extsize_align(mp, &ap->got, &ap->prev, align, 0,
 					ap->eof, 0, ap->conv, &ap->offset,

fs/xfs/libxfs/xfs_bmap.h

@@ -87,6 +87,9 @@ struct xfs_bmalloca {
 /* Do not update the rmap btree.  Used for reconstructing bmbt from rmapbt. */
 #define XFS_BMAPI_NORMAP	(1u << 10)
 
+/* Try to align allocations to the extent size hint */
+#define XFS_BMAPI_EXTSZALIGN	(1u << 11)
+
 #define XFS_BMAPI_FLAGS \
 	{ XFS_BMAPI_ENTIRE,	"ENTIRE" }, \
 	{ XFS_BMAPI_METADATA,	"METADATA" }, \
@@ -98,7 +101,8 @@ struct xfs_bmalloca {
 	{ XFS_BMAPI_REMAP,	"REMAP" }, \
 	{ XFS_BMAPI_COWFORK,	"COWFORK" }, \
 	{ XFS_BMAPI_NODISCARD,	"NODISCARD" }, \
-	{ XFS_BMAPI_NORMAP,	"NORMAP" }
+	{ XFS_BMAPI_NORMAP,	"NORMAP" },\
+	{ XFS_BMAPI_EXTSZALIGN,	"EXTSZALIGN" }
 
 
 static inline int xfs_bmapi_aflag(int w)

fs/xfs/libxfs/xfs_log_rlimit.c

@@ -91,6 +91,7 @@ xfs_log_calc_trans_resv_for_minlogblocks(
 	 */
 	if (xfs_want_minlogsize_fixes(&mp->m_sb)) {
 		xfs_trans_resv_calc(mp, resv);
+		resv->tr_atomic_ioend = M_RES(mp)->tr_atomic_ioend;
 		return;
 	}
 
@@ -107,6 +108,9 @@ xfs_log_calc_trans_resv_for_minlogblocks(
 
 	xfs_trans_resv_calc(mp, resv);
 
+	/* Copy the dynamic transaction reservation types from the running fs */
+	resv->tr_atomic_ioend = M_RES(mp)->tr_atomic_ioend;
+
 	if (xfs_has_reflink(mp)) {
 		/*
 		 * In the early days of reflink, typical log operation counts

fs/xfs/libxfs/xfs_trans_resv.c

@@ -22,6 +22,12 @@
 #include "xfs_rtbitmap.h"
 #include "xfs_attr_item.h"
 #include "xfs_log.h"
+#include "xfs_defer.h"
+#include "xfs_bmap_item.h"
+#include "xfs_extfree_item.h"
+#include "xfs_rmap_item.h"
+#include "xfs_refcount_item.h"
+#include "xfs_trace.h"
 
 #define _ALLOC	true
 #define _FREE	false
@@ -263,6 +269,42 @@ xfs_rtalloc_block_count(
  * register overflow from temporaries in the calculations.
  */
 
+/*
+ * Finishing a data device refcount updates (t1):
+ *    the agfs of the ags containing the blocks: nr_ops * sector size
+ *    the refcount btrees: nr_ops * 1 trees * (2 * max depth - 1) * block size
+ */
+inline unsigned int
+xfs_calc_finish_cui_reservation(
+	struct xfs_mount	*mp,
+	unsigned int		nr_ops)
+{
+	if (!xfs_has_reflink(mp))
+		return 0;
+
+	return xfs_calc_buf_res(nr_ops, mp->m_sb.sb_sectsize) +
+	       xfs_calc_buf_res(xfs_refcountbt_block_count(mp, nr_ops),
+			       mp->m_sb.sb_blocksize);
+}
+
+/*
+ * Realtime refcount updates (t2);
+ *    the rt refcount inode
+ *    the rtrefcount btrees: nr_ops * 1 trees * (2 * max depth - 1) * block size
+ */
+inline unsigned int
+xfs_calc_finish_rt_cui_reservation(
+	struct xfs_mount	*mp,
+	unsigned int		nr_ops)
+{
+	if (!xfs_has_rtreflink(mp))
+		return 0;
+
+	return xfs_calc_inode_res(mp, 1) +
+	       xfs_calc_buf_res(xfs_rtrefcountbt_block_count(mp, nr_ops),
+				     mp->m_sb.sb_blocksize);
+}
+
 /*
  * Compute the log reservation required to handle the refcount update
  * transaction.  Refcount updates are always done via deferred log items.
@@ -280,19 +322,10 @@ xfs_calc_refcountbt_reservation(
 	struct xfs_mount	*mp,
 	unsigned int		nr_ops)
 {
-	unsigned int		blksz = XFS_FSB_TO_B(mp, 1);
-	unsigned int		t1, t2 = 0;
+	unsigned int		t1, t2;
 
-	if (!xfs_has_reflink(mp))
-		return 0;
-
-	t1 = xfs_calc_buf_res(nr_ops, mp->m_sb.sb_sectsize) +
-	     xfs_calc_buf_res(xfs_refcountbt_block_count(mp, nr_ops), blksz);
-
-	if (xfs_has_realtime(mp))
-		t2 = xfs_calc_inode_res(mp, 1) +
-		     xfs_calc_buf_res(xfs_rtrefcountbt_block_count(mp, nr_ops),
-				     blksz);
+	t1 = xfs_calc_finish_cui_reservation(mp, nr_ops);
+	t2 = xfs_calc_finish_rt_cui_reservation(mp, nr_ops);
 
 	return max(t1, t2);
 }
@@ -379,6 +412,96 @@ xfs_calc_write_reservation_minlogsize(
 	return xfs_calc_write_reservation(mp, true);
 }
 
+/*
+ * Finishing an EFI can free the blocks and bmap blocks (t2):
+ *    the agf for each of the ags: nr * sector size
+ *    the agfl for each of the ags: nr * sector size
+ *    the super block to reflect the freed blocks: sector size
+ *    worst case split in allocation btrees per extent assuming nr extents:
+ *		nr exts * 2 trees * (2 * max depth - 1) * block size
+ */
+inline unsigned int
+xfs_calc_finish_efi_reservation(
+	struct xfs_mount	*mp,
+	unsigned int		nr)
+{
+	return xfs_calc_buf_res((2 * nr) + 1, mp->m_sb.sb_sectsize) +
+	       xfs_calc_buf_res(xfs_allocfree_block_count(mp, nr),
+			       mp->m_sb.sb_blocksize);
+}
+
+/*
+ * Or, if it's a realtime file (t3):
+ *    the agf for each of the ags: 2 * sector size
+ *    the agfl for each of the ags: 2 * sector size
+ *    the super block to reflect the freed blocks: sector size
+ *    the realtime bitmap:
+ *		2 exts * ((XFS_BMBT_MAX_EXTLEN / rtextsize) / NBBY) bytes
+ *    the realtime summary: 2 exts * 1 block
+ *    worst case split in allocation btrees per extent assuming 2 extents:
+ *		2 exts * 2 trees * (2 * max depth - 1) * block size
+ */
+inline unsigned int
+xfs_calc_finish_rt_efi_reservation(
+	struct xfs_mount	*mp,
+	unsigned int		nr)
+{
+	if (!xfs_has_realtime(mp))
+		return 0;
+
+	return xfs_calc_buf_res((2 * nr) + 1, mp->m_sb.sb_sectsize) +
+	       xfs_calc_buf_res(xfs_rtalloc_block_count(mp, nr),
+			       mp->m_sb.sb_blocksize) +
+	       xfs_calc_buf_res(xfs_allocfree_block_count(mp, nr),
+			       mp->m_sb.sb_blocksize);
+}
+
+/*
+ * Finishing an RUI is the same as an EFI.  We can split the rmap btree twice
+ * on each end of the record, and that can cause the AGFL to be refilled or
+ * emptied out.
+ */
+inline unsigned int
+xfs_calc_finish_rui_reservation(
+	struct xfs_mount	*mp,
+	unsigned int		nr)
+{
+	if (!xfs_has_rmapbt(mp))
+		return 0;
+	return xfs_calc_finish_efi_reservation(mp, nr);
+}
+
+/*
+ * Finishing an RUI is the same as an EFI.  We can split the rmap btree twice
+ * on each end of the record, and that can cause the AGFL to be refilled or
+ * emptied out.
+ */
+inline unsigned int
+xfs_calc_finish_rt_rui_reservation(
+	struct xfs_mount	*mp,
+	unsigned int		nr)
+{
+	if (!xfs_has_rtrmapbt(mp))
+		return 0;
+	return xfs_calc_finish_rt_efi_reservation(mp, nr);
+}
+
+/*
+ * In finishing a BUI, we can modify:
+ *    the inode being truncated: inode size
+ *    dquots
+ *    the inode's bmap btree: (max depth + 1) * block size
+ */
+inline unsigned int
+xfs_calc_finish_bui_reservation(
+	struct xfs_mount	*mp,
+	unsigned int		nr)
+{
+	return xfs_calc_inode_res(mp, 1) + XFS_DQUOT_LOGRES +
+	       xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) + 1,
+			       mp->m_sb.sb_blocksize);
+}
+
 /*
  * In truncating a file we free up to two extents at once.  We can modify (t1):
  *    the inode being truncated: inode size
@@ -411,16 +534,8 @@ xfs_calc_itruncate_reservation(
 	t1 = xfs_calc_inode_res(mp, 1) +
 	     xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) + 1, blksz);
 
-	t2 = xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) +
-	     xfs_calc_buf_res(xfs_allocfree_block_count(mp, 4), blksz);
-
-	if (xfs_has_realtime(mp)) {
-		t3 = xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) +
-		     xfs_calc_buf_res(xfs_rtalloc_block_count(mp, 2), blksz) +
-		     xfs_calc_buf_res(xfs_allocfree_block_count(mp, 2), blksz);
-	} else {
-		t3 = 0;
-	}
+	t2 = xfs_calc_finish_efi_reservation(mp, 4);
+	t3 = xfs_calc_finish_rt_efi_reservation(mp, 2);
 
 	/*
 	 * In the early days of reflink, we included enough reservation to log
@@ -501,9 +616,7 @@ xfs_calc_rename_reservation(
 	     xfs_calc_buf_res(2 * XFS_DIROP_LOG_COUNT(mp),
 			XFS_FSB_TO_B(mp, 1));
 
-	t2 = xfs_calc_buf_res(7, mp->m_sb.sb_sectsize) +
-	     xfs_calc_buf_res(xfs_allocfree_block_count(mp, 3),
-			XFS_FSB_TO_B(mp, 1));
+	t2 = xfs_calc_finish_efi_reservation(mp, 3);
 
 	if (xfs_has_parent(mp)) {
 		unsigned int	rename_overhead, exchange_overhead;
@@ -611,9 +724,7 @@ xfs_calc_link_reservation(
 	overhead += xfs_calc_iunlink_remove_reservation(mp);
 	t1 = xfs_calc_inode_res(mp, 2) +
 	     xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1));
-	t2 = xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
-	     xfs_calc_buf_res(xfs_allocfree_block_count(mp, 1),
-			      XFS_FSB_TO_B(mp, 1));
+	t2 = xfs_calc_finish_efi_reservation(mp, 1);
 
 	if (xfs_has_parent(mp)) {
 		t3 = resp->tr_attrsetm.tr_logres;
@@ -676,9 +787,7 @@ xfs_calc_remove_reservation(
 
 	t1 = xfs_calc_inode_res(mp, 2) +
 	     xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1));
-	t2 = xfs_calc_buf_res(4, mp->m_sb.sb_sectsize) +
-	     xfs_calc_buf_res(xfs_allocfree_block_count(mp, 2),
-			      XFS_FSB_TO_B(mp, 1));
+	t2 = xfs_calc_finish_efi_reservation(mp, 2);
 
 	if (xfs_has_parent(mp)) {
 		t3 = resp->tr_attrrm.tr_logres;
@@ -1181,6 +1290,15 @@ xfs_calc_namespace_reservations(
 	resp->tr_mkdir.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
 }
 
+STATIC void
+xfs_calc_default_atomic_ioend_reservation(
+	struct xfs_mount	*mp,
+	struct xfs_trans_resv	*resp)
+{
+	/* Pick a default that will scale reasonably for the log size. */
+	resp->tr_atomic_ioend = resp->tr_itruncate;
+}
+
 void
 xfs_trans_resv_calc(
 	struct xfs_mount	*mp,
@@ -1275,4 +1393,167 @@ xfs_trans_resv_calc(
 	resp->tr_itruncate.tr_logcount += logcount_adj;
 	resp->tr_write.tr_logcount += logcount_adj;
 	resp->tr_qm_dqalloc.tr_logcount += logcount_adj;
+
+	/*
+	 * Now that we've finished computing the static reservations, we can
+	 * compute the dynamic reservation for atomic writes.
+	 */
+	xfs_calc_default_atomic_ioend_reservation(mp, resp);
+}
+
+/*
+ * Return the per-extent and fixed transaction reservation sizes needed to
+ * complete an atomic write.
+ */
+STATIC unsigned int
+xfs_calc_atomic_write_ioend_geometry(
+	struct xfs_mount	*mp,
+	unsigned int		*step_size)
+{
+	const unsigned int	efi = xfs_efi_log_space(1);
+	const unsigned int	efd = xfs_efd_log_space(1);
+	const unsigned int	rui = xfs_rui_log_space(1);
+	const unsigned int	rud = xfs_rud_log_space();
+	const unsigned int	cui = xfs_cui_log_space(1);
+	const unsigned int	cud = xfs_cud_log_space();
+	const unsigned int	bui = xfs_bui_log_space(1);
+	const unsigned int	bud = xfs_bud_log_space();
+
+	/*
+	 * Maximum overhead to complete an atomic write ioend in software:
+	 * remove data fork extent + remove cow fork extent + map extent into
+	 * data fork.
+	 *
+	 * tx0: Creates a BUI and a CUI and that's all it needs.
+	 *
+	 * tx1: Roll to finish the BUI.  Need space for the BUD, an RUI, and
+	 * enough space to relog the CUI (== CUI + CUD).
+	 *
+	 * tx2: Roll again to finish the RUI.  Need space for the RUD and space
+	 * to relog the CUI.
+	 *
+	 * tx3: Roll again, need space for the CUD and possibly a new EFI.
+	 *
+	 * tx4: Roll again, need space for an EFD.
+	 *
+	 * If the extent referenced by the pair of BUI/CUI items is not the one
+	 * being currently processed, then we need to reserve space to relog
+	 * both items.
+	 */
+	const unsigned int	tx0 = bui + cui;
+	const unsigned int	tx1 = bud + rui + cui + cud;
+	const unsigned int	tx2 = rud + cui + cud;
+	const unsigned int	tx3 = cud + efi;
+	const unsigned int	tx4 = efd;
+	const unsigned int	relog = bui + bud + cui + cud;
+
+	const unsigned int	per_intent = max(max3(tx0, tx1, tx2),
+						 max3(tx3, tx4, relog));
+
+	/* Overhead to finish one step of each intent item type */
+	const unsigned int	f1 = xfs_calc_finish_efi_reservation(mp, 1);
+	const unsigned int	f2 = xfs_calc_finish_rui_reservation(mp, 1);
+	const unsigned int	f3 = xfs_calc_finish_cui_reservation(mp, 1);
+	const unsigned int	f4 = xfs_calc_finish_bui_reservation(mp, 1);
+
+	/* We only finish one item per transaction in a chain */
+	*step_size = max(f4, max3(f1, f2, f3));
+
+	return per_intent;
+}
+
+/*
+ * Compute the maximum size (in fsblocks) of atomic writes that we can complete
+ * given the existing log reservations.
+ */
+xfs_extlen_t
+xfs_calc_max_atomic_write_fsblocks(
+	struct xfs_mount		*mp)
+{
+	const struct xfs_trans_res	*resv = &M_RES(mp)->tr_atomic_ioend;
+	unsigned int			per_intent = 0;
+	unsigned int			step_size = 0;
+	unsigned int			ret = 0;
+
+	if (resv->tr_logres > 0) {
+		per_intent = xfs_calc_atomic_write_ioend_geometry(mp,
+				&step_size);
+
+		if (resv->tr_logres >= step_size)
+			ret = (resv->tr_logres - step_size) / per_intent;
+	}
+
+	trace_xfs_calc_max_atomic_write_fsblocks(mp, per_intent, step_size,
+			resv->tr_logres, ret);
+
+	return ret;
+}
+
+/*
+ * Compute the log blocks and transaction reservation needed to complete an
+ * atomic write of a given number of blocks.  Worst case, each block requires
+ * separate handling.  A return value of 0 means something went wrong.
+ */
+xfs_extlen_t
+xfs_calc_atomic_write_log_geometry(
+	struct xfs_mount	*mp,
+	xfs_extlen_t		blockcount,
+	unsigned int		*new_logres)
+{
+	struct xfs_trans_res	*curr_res = &M_RES(mp)->tr_atomic_ioend;
+	uint			old_logres = curr_res->tr_logres;
+	unsigned int		per_intent, step_size;
+	unsigned int		logres;
+	xfs_extlen_t		min_logblocks;
+
+	ASSERT(blockcount > 0);
+
+	xfs_calc_default_atomic_ioend_reservation(mp, M_RES(mp));
+
+	per_intent = xfs_calc_atomic_write_ioend_geometry(mp, &step_size);
+
+	/* Check for overflows */
+	if (check_mul_overflow(blockcount, per_intent, &logres) ||
+	    check_add_overflow(logres, step_size, &logres))
+		return 0;
+
+	curr_res->tr_logres = logres;
+	min_logblocks = xfs_log_calc_minimum_size(mp);
+	curr_res->tr_logres = old_logres;
+
+	trace_xfs_calc_max_atomic_write_log_geometry(mp, per_intent, step_size,
+			blockcount, min_logblocks, logres);
+
+	*new_logres = logres;
+	return min_logblocks;
+}
+
+/*
+ * Compute the transaction reservation needed to complete an out of place
+ * atomic write of a given number of blocks.
+ */
+int
+xfs_calc_atomic_write_reservation(
+	struct xfs_mount	*mp,
+	xfs_extlen_t		blockcount)
+{
+	unsigned int		new_logres;
+	xfs_extlen_t		min_logblocks;
+
+	/*
+	 * If the caller doesn't ask for a specific atomic write size, then
+	 * use the defaults.
+	 */
+	if (blockcount == 0) {
+		xfs_calc_default_atomic_ioend_reservation(mp, M_RES(mp));
+		return 0;
+	}
+
+	min_logblocks = xfs_calc_atomic_write_log_geometry(mp, blockcount,
+			&new_logres);
+	if (!min_logblocks || min_logblocks > mp->m_sb.sb_logblocks)
+		return -EINVAL;
+
+	M_RES(mp)->tr_atomic_ioend.tr_logres = new_logres;
+	return 0;
 }

fs/xfs/libxfs/xfs_trans_resv.h

@@ -48,6 +48,7 @@ struct xfs_trans_resv {
 	struct xfs_trans_res	tr_qm_dqalloc;	/* allocate quota on disk */
 	struct xfs_trans_res	tr_sb;		/* modify superblock */
 	struct xfs_trans_res	tr_fsyncts;	/* update timestamps on fsync */
+	struct xfs_trans_res	tr_atomic_ioend; /* untorn write completion */
 };
 
 /* shorthand way of accessing reservation structure */
@@ -98,8 +99,32 @@ struct xfs_trans_resv {
 void xfs_trans_resv_calc(struct xfs_mount *mp, struct xfs_trans_resv *resp);
 uint xfs_allocfree_block_count(struct xfs_mount *mp, uint num_ops);
 
+unsigned int xfs_calc_finish_bui_reservation(struct xfs_mount *mp,
+		unsigned int nr_ops);
+
+unsigned int xfs_calc_finish_efi_reservation(struct xfs_mount *mp,
+		unsigned int nr_ops);
+unsigned int xfs_calc_finish_rt_efi_reservation(struct xfs_mount *mp,
+		unsigned int nr_ops);
+
+unsigned int xfs_calc_finish_rui_reservation(struct xfs_mount *mp,
+		unsigned int nr_ops);
+unsigned int xfs_calc_finish_rt_rui_reservation(struct xfs_mount *mp,
+		unsigned int nr_ops);
+
+unsigned int xfs_calc_finish_cui_reservation(struct xfs_mount *mp,
+		unsigned int nr_ops);
+unsigned int xfs_calc_finish_rt_cui_reservation(struct xfs_mount *mp,
+		unsigned int nr_ops);
+
 unsigned int xfs_calc_itruncate_reservation_minlogsize(struct xfs_mount *mp);
 unsigned int xfs_calc_write_reservation_minlogsize(struct xfs_mount *mp);
 unsigned int xfs_calc_qm_dqalloc_reservation_minlogsize(struct xfs_mount *mp);
 
+xfs_extlen_t xfs_calc_max_atomic_write_fsblocks(struct xfs_mount *mp);
+xfs_extlen_t xfs_calc_atomic_write_log_geometry(struct xfs_mount *mp,
+		xfs_extlen_t blockcount, unsigned int *new_logres);
+int xfs_calc_atomic_write_reservation(struct xfs_mount *mp,
+		xfs_extlen_t blockcount);
+
 #endif	/* __XFS_TRANS_RESV_H__ */

fs/xfs/scrub/scrub.c

@@ -680,8 +680,6 @@ xfs_scrub_metadata(
 	if (error)
 		goto out;
 
-	xfs_warn_experimental(mp, XFS_EXPERIMENTAL_SCRUB);
-
 	sc = kzalloc(sizeof(struct xfs_scrub), XCHK_GFP_FLAGS);
 	if (!sc) {
 		error = -ENOMEM;

fs/xfs/xfs_bmap_item.c

@@ -77,6 +77,11 @@ xfs_bui_item_size(
 	*nbytes += xfs_bui_log_format_sizeof(buip->bui_format.bui_nextents);
 }
 
+unsigned int xfs_bui_log_space(unsigned int nr)
+{
+	return xlog_item_space(1, xfs_bui_log_format_sizeof(nr));
+}
+
 /*
  * This is called to fill in the vector of log iovecs for the
  * given bui log item. We use only 1 iovec, and we point that
@@ -168,6 +173,11 @@ xfs_bud_item_size(
 	*nbytes += sizeof(struct xfs_bud_log_format);
 }
 
+unsigned int xfs_bud_log_space(void)
+{
+	return xlog_item_space(1, sizeof(struct xfs_bud_log_format));
+}
+
 /*
  * This is called to fill in the vector of log iovecs for the
  * given bud log item. We use only 1 iovec, and we point that

fs/xfs/xfs_bmap_item.h

@@ -72,4 +72,7 @@ struct xfs_bmap_intent;
 
 void xfs_bmap_defer_add(struct xfs_trans *tp, struct xfs_bmap_intent *bi);
 
+unsigned int xfs_bui_log_space(unsigned int nr);
+unsigned int xfs_bud_log_space(void);
+
 #endif	/* __XFS_BMAP_ITEM_H__ */

fs/xfs/xfs_buf.c

@@ -1687,23 +1687,65 @@ xfs_free_buftarg(
 	kfree(btp);
 }
 
+/*
+ * Configure this buffer target for hardware-assisted atomic writes if the
+ * underlying block device supports is congruent with the filesystem geometry.
+ */
+static inline void
+xfs_configure_buftarg_atomic_writes(
+	struct xfs_buftarg	*btp)
+{
+	struct xfs_mount	*mp = btp->bt_mount;
+	unsigned int		min_bytes, max_bytes;
+
+	min_bytes = bdev_atomic_write_unit_min_bytes(btp->bt_bdev);
+	max_bytes = bdev_atomic_write_unit_max_bytes(btp->bt_bdev);
+
+	/*
+	 * Ignore atomic write geometry that is nonsense or doesn't even cover
+	 * a single fsblock.
+	 */
+	if (min_bytes > max_bytes ||
+	    min_bytes > mp->m_sb.sb_blocksize ||
+	    max_bytes < mp->m_sb.sb_blocksize) {
+		min_bytes = 0;
+		max_bytes = 0;
+	}
+
+	btp->bt_bdev_awu_min = min_bytes;
+	btp->bt_bdev_awu_max = max_bytes;
+}
+
+/* Configure a buffer target that abstracts a block device. */
 int
-xfs_setsize_buftarg(
+xfs_configure_buftarg(
 	struct xfs_buftarg	*btp,
 	unsigned int		sectorsize)
 {
+	int			error;
+
+	ASSERT(btp->bt_bdev != NULL);
+
 	/* Set up metadata sector size info */
 	btp->bt_meta_sectorsize = sectorsize;
 	btp->bt_meta_sectormask = sectorsize - 1;
 
-	if (set_blocksize(btp->bt_bdev_file, sectorsize)) {
+	error = bdev_validate_blocksize(btp->bt_bdev, sectorsize);
+	if (error) {
 		xfs_warn(btp->bt_mount,
-			"Cannot set_blocksize to %u on device %pg",
-			sectorsize, btp->bt_bdev);
+			"Cannot use blocksize %u on device %pg, err %d",
+			sectorsize, btp->bt_bdev, error);
 		return -EINVAL;
 	}
 
-	return 0;
+	/*
+	 * Flush the block device pagecache so our bios see anything dirtied
+	 * before mount.
+	 */
+	if (bdev_can_atomic_write(btp->bt_bdev))
+		xfs_configure_buftarg_atomic_writes(btp);
+
+	return sync_blockdev(btp->bt_bdev);
 }
 
 int
@@ -1752,6 +1794,8 @@ xfs_alloc_buftarg(
 {
 	struct xfs_buftarg	*btp;
 	const struct dax_holder_operations *ops = NULL;
+	int			error;
+
 
 #if defined(CONFIG_FS_DAX) && defined(CONFIG_MEMORY_FAILURE)
 	ops = &xfs_dax_holder_operations;
@@ -1765,28 +1809,31 @@ xfs_alloc_buftarg(
 	btp->bt_daxdev = fs_dax_get_by_bdev(btp->bt_bdev, &btp->bt_dax_part_off,
 					    mp, ops);
 
-	if (bdev_can_atomic_write(btp->bt_bdev)) {
-		btp->bt_bdev_awu_min = bdev_atomic_write_unit_min_bytes(
-						btp->bt_bdev);
-		btp->bt_bdev_awu_max = bdev_atomic_write_unit_max_bytes(
-						btp->bt_bdev);
-	}
+	/*
+	 * Flush and invalidate all devices' pagecaches before reading any
+	 * metadata because XFS doesn't use the bdev pagecache.
+	 */
+	error = sync_blockdev(btp->bt_bdev);
+	if (error)
+		goto error_free;
 
 	/*
 	 * When allocating the buftargs we have not yet read the super block and
 	 * thus don't know the file system sector size yet.
 	 */
-	if (xfs_setsize_buftarg(btp, bdev_logical_block_size(btp->bt_bdev)))
-		goto error_free;
-	if (xfs_init_buftarg(btp, bdev_logical_block_size(btp->bt_bdev),
-			mp->m_super->s_id))
+	btp->bt_meta_sectorsize = bdev_logical_block_size(btp->bt_bdev);
+	btp->bt_meta_sectormask = btp->bt_meta_sectorsize - 1;
+
+	error = xfs_init_buftarg(btp, btp->bt_meta_sectorsize,
+				mp->m_super->s_id);
+	if (error)
 		goto error_free;
 
 	return btp;
 
 error_free:
 	kfree(btp);
-	return NULL;
+	return ERR_PTR(error);
 }
 
 static inline void

fs/xfs/xfs_buf.h

@@ -112,7 +112,7 @@ struct xfs_buftarg {
 	struct percpu_counter	bt_readahead_count;
 	struct ratelimit_state	bt_ioerror_rl;
 
-	/* Atomic write unit values */
+	/* Atomic write unit values, bytes */
 	unsigned int		bt_bdev_awu_min;
 	unsigned int		bt_bdev_awu_max;
 
@@ -374,7 +374,7 @@ struct xfs_buftarg *xfs_alloc_buftarg(struct xfs_mount *mp,
 extern void xfs_free_buftarg(struct xfs_buftarg *);
 extern void xfs_buftarg_wait(struct xfs_buftarg *);
 extern void xfs_buftarg_drain(struct xfs_buftarg *);
-extern int xfs_setsize_buftarg(struct xfs_buftarg *, unsigned int);
+int xfs_configure_buftarg(struct xfs_buftarg *btp, unsigned int sectorsize);
 
 #define xfs_getsize_buftarg(buftarg)	block_size((buftarg)->bt_bdev)
 #define xfs_readonly_buftarg(buftarg)	bdev_read_only((buftarg)->bt_bdev)

fs/xfs/xfs_buf_item.c

@@ -103,6 +103,25 @@ xfs_buf_item_size_segment(
 	return;
 }
 
+/*
+ * Compute the worst case log item overhead for an invalidated buffer with the
+ * given map count and block size.
+ */
+unsigned int
+xfs_buf_inval_log_space(
+	unsigned int	map_count,
+	unsigned int	blocksize)
+{
+	unsigned int	chunks = DIV_ROUND_UP(blocksize, XFS_BLF_CHUNK);
+	unsigned int	bitmap_size = DIV_ROUND_UP(chunks, NBWORD);
+	unsigned int	ret =
+		offsetof(struct xfs_buf_log_format, blf_data_map) +
+			(bitmap_size * sizeof_field(struct xfs_buf_log_format,
+						    blf_data_map[0]));
+
+	return ret * map_count;
+}
+
 /*
  * Return the number of log iovecs and space needed to log the given buf log
  * item.

fs/xfs/xfs_buf_item.h

@@ -64,6 +64,9 @@ static inline void xfs_buf_dquot_iodone(struct xfs_buf *bp)
 void	xfs_buf_iodone(struct xfs_buf *);
 bool	xfs_buf_log_check_iovec(struct xfs_log_iovec *iovec);
 
+unsigned int xfs_buf_inval_log_space(unsigned int map_count,
+		unsigned int blocksize);
+
 extern struct kmem_cache	*xfs_buf_item_cache;
 
 #endif	/* __XFS_BUF_ITEM_H__ */

fs/xfs/xfs_discard.c

@@ -167,6 +167,14 @@ xfs_discard_extents(
 	return error;
 }
 
+/*
+ * Care must be taken setting up the trim cursor as the perags may not have been
+ * initialised when the cursor is initialised. e.g. a clean mount which hasn't
+ * read in AGFs and the first operation run on the mounted fs is a trim. This
+ * can result in perag fields that aren't initialised until
+ * xfs_trim_gather_extents() calls xfs_alloc_read_agf() to lock down the AG for
+ * the free space search.
+ */
 struct xfs_trim_cur {
 	xfs_agblock_t	start;
 	xfs_extlen_t	count;
@@ -204,6 +212,14 @@ xfs_trim_gather_extents(
 	if (error)
 		goto out_trans_cancel;
 
+	/*
+	 * First time through tcur->count will not have been initialised as
+	 * pag->pagf_longest is not guaranteed to be valid before we read
+	 * the AGF buffer above.
+	 */
+	if (!tcur->count)
+		tcur->count = pag->pagf_longest;
+
 	if (tcur->by_bno) {
 		/* sub-AG discard request always starts at tcur->start */
 		cur = xfs_bnobt_init_cursor(mp, tp, agbp, pag);
@@ -350,7 +366,6 @@ xfs_trim_perag_extents(
 {
 	struct xfs_trim_cur	tcur = {
 		.start		= start,
-		.count		= pag->pagf_longest,
 		.end		= end,
 		.minlen		= minlen,
 	};

fs/xfs/xfs_extfree_item.c

@@ -83,6 +83,11 @@ xfs_efi_item_size(
 	*nbytes += xfs_efi_log_format_sizeof(efip->efi_format.efi_nextents);
 }
 
+unsigned int xfs_efi_log_space(unsigned int nr)
+{
+	return xlog_item_space(1, xfs_efi_log_format_sizeof(nr));
+}
+
 /*
  * This is called to fill in the vector of log iovecs for the
  * given efi log item. We use only 1 iovec, and we point that
@@ -254,6 +259,11 @@ xfs_efd_item_size(
 	*nbytes += xfs_efd_log_format_sizeof(efdp->efd_format.efd_nextents);
 }
 
+unsigned int xfs_efd_log_space(unsigned int nr)
+{
+	return xlog_item_space(1, xfs_efd_log_format_sizeof(nr));
+}
+
 /*
  * This is called to fill in the vector of log iovecs for the
  * given efd log item. We use only 1 iovec, and we point that

fs/xfs/xfs_extfree_item.h

@@ -94,4 +94,7 @@ void xfs_extent_free_defer_add(struct xfs_trans *tp,
 		struct xfs_extent_free_item *xefi,
 		struct xfs_defer_pending **dfpp);
 
+unsigned int xfs_efi_log_space(unsigned int nr);
+unsigned int xfs_efd_log_space(unsigned int nr);
+
 #endif	/* __XFS_EXTFREE_ITEM_H__ */

fs/xfs/xfs_file.c

@@ -576,7 +576,10 @@ xfs_dio_write_end_io(
 	nofs_flag = memalloc_nofs_save();
 
 	if (flags & IOMAP_DIO_COW) {
-		error = xfs_reflink_end_cow(ip, offset, size);
+		if (iocb->ki_flags & IOCB_ATOMIC)
+			error = xfs_reflink_end_atomic_cow(ip, offset, size);
+		else
+			error = xfs_reflink_end_cow(ip, offset, size);
 		if (error)
 			goto out;
 	}
@@ -725,6 +728,72 @@ xfs_file_dio_write_zoned(
 	return ret;
 }
 
+/*
+ * Handle block atomic writes
+ *
+ * Two methods of atomic writes are supported:
+ * - REQ_ATOMIC-based, which would typically use some form of HW offload in the
+ *   disk
+ * - COW-based, which uses a COW fork as a staging extent for data updates
+ *   before atomically updating extent mappings for the range being written
+ *
+ */
+static noinline ssize_t
+xfs_file_dio_write_atomic(
+	struct xfs_inode	*ip,
+	struct kiocb		*iocb,
+	struct iov_iter		*from)
+{
+	unsigned int		iolock = XFS_IOLOCK_SHARED;
+	ssize_t			ret, ocount = iov_iter_count(from);
+	const struct iomap_ops	*dops;
+
+	/*
+	 * HW offload should be faster, so try that first if it is already
+	 * known that the write length is not too large.
+	 */
+	if (ocount > xfs_inode_buftarg(ip)->bt_bdev_awu_max)
+		dops = &xfs_atomic_write_cow_iomap_ops;
+	else
+		dops = &xfs_direct_write_iomap_ops;
+
+retry:
+	ret = xfs_ilock_iocb_for_write(iocb, &iolock);
+	if (ret)
+		return ret;
+
+	ret = xfs_file_write_checks(iocb, from, &iolock, NULL);
+	if (ret)
+		goto out_unlock;
+
+	/* Demote similar to xfs_file_dio_write_aligned() */
+	if (iolock == XFS_IOLOCK_EXCL) {
+		xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
+		iolock = XFS_IOLOCK_SHARED;
+	}
+
+	trace_xfs_file_direct_write(iocb, from);
+	ret = iomap_dio_rw(iocb, from, dops, &xfs_dio_write_ops,
+			0, NULL, 0);
+
+	/*
+	 * The retry mechanism is based on the ->iomap_begin method returning
+	 * -ENOPROTOOPT, which would be when the REQ_ATOMIC-based write is not
+	 * possible. The REQ_ATOMIC-based method typically not be possible if
+	 * the write spans multiple extents or the disk blocks are misaligned.
+	 */
+	if (ret == -ENOPROTOOPT && dops == &xfs_direct_write_iomap_ops) {
+		xfs_iunlock(ip, iolock);
+		dops = &xfs_atomic_write_cow_iomap_ops;
+		goto retry;
+	}
+
+out_unlock:
+	if (iolock)
+		xfs_iunlock(ip, iolock);
+	return ret;
+}
+
 /*
  * Handle block unaligned direct I/O writes
  *
@@ -840,6 +909,8 @@ xfs_file_dio_write(
 		return xfs_file_dio_write_unaligned(ip, iocb, from);
 	if (xfs_is_zoned_inode(ip))
 		return xfs_file_dio_write_zoned(ip, iocb, from);
+	if (iocb->ki_flags & IOCB_ATOMIC)
+		return xfs_file_dio_write_atomic(ip, iocb, from);
 	return xfs_file_dio_write_aligned(ip, iocb, from,
 			&xfs_direct_write_iomap_ops, &xfs_dio_write_ops, NULL);
 }
@@ -1032,14 +1103,12 @@ xfs_file_write_iter(
 		return xfs_file_dax_write(iocb, from);
 
 	if (iocb->ki_flags & IOCB_ATOMIC) {
-		/*
-		 * Currently only atomic writing of a single FS block is
-		 * supported. It would be possible to atomic write smaller than
-		 * a FS block, but there is no requirement to support this.
-		 * Note that iomap also does not support this yet.
-		 */
-		if (ocount != ip->i_mount->m_sb.sb_blocksize)
+		if (ocount < xfs_get_atomic_write_min(ip))
 			return -EINVAL;
+
+		if (ocount > xfs_get_atomic_write_max(ip))
+			return -EINVAL;
+
 		ret = generic_atomic_write_valid(iocb, from);
 		if (ret)
 			return ret;
@@ -1488,7 +1557,7 @@ xfs_file_open(
 	if (xfs_is_shutdown(XFS_M(inode->i_sb)))
 		return -EIO;
 	file->f_mode |= FMODE_NOWAIT | FMODE_CAN_ODIRECT;
-	if (xfs_inode_can_atomicwrite(XFS_I(inode)))
+	if (xfs_get_atomic_write_min(XFS_I(inode)) > 0)
 		file->f_mode |= FMODE_CAN_ATOMIC_WRITE;
 	return generic_file_open(inode, file);
 }