Merge branch 'xfs-7.1-merge' into for-next

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

6 files changed, 137 insertions, 57 deletions

diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index d165de607d17..185f09f327c0 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -995,7 +995,8 @@ struct xfs_rtgroup_geometry {
 	__u32 rg_sick;		/* o: sick things in ag */
 	__u32 rg_checked;	/* o: checked metadata in ag */
 	__u32 rg_flags;		/* i/o: flags for this ag */
-	__u32 rg_reserved[27];	/* o: zero */
+	__u32 rg_writepointer;  /* o: write pointer block offset for zoned */
+	__u32 rg_reserved[26];	/* o: zero */
 };
 #define XFS_RTGROUP_GEOM_SICK_SUPER	(1U << 0)  /* superblock */
 #define XFS_RTGROUP_GEOM_SICK_BITMAP	(1U << 1)  /* rtbitmap */
@@ -1003,6 +1004,8 @@ struct xfs_rtgroup_geometry {
 #define XFS_RTGROUP_GEOM_SICK_RMAPBT	(1U << 3)  /* reverse mappings */
 #define XFS_RTGROUP_GEOM_SICK_REFCNTBT	(1U << 4)  /* reference counts */
 
+#define XFS_RTGROUP_GEOM_WRITEPOINTER  (1U << 0)  /* write pointer */
+
 /* Health monitor event domains */
 
 /* affects the whole fs */
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 6246f34df9fd..7918968e1d62 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -560,6 +560,72 @@ xfs_zoned_write_space_reserve(
 			flags, ac);
 }
 
+/*
+ * We need to lock the test/set EOF update as we can be racing with
+ * other IO completions here to update the EOF. Failing to serialise
+ * here can result in EOF moving backwards and Bad Things Happen when
+ * that occurs.
+ *
+ * As IO completion only ever extends EOF, we can do an unlocked check
+ * here to avoid taking the spinlock. If we land within the current EOF,
+ * then we do not need to do an extending update at all, and we don't
+ * need to take the lock to check this. If we race with an update moving
+ * EOF, then we'll either still be beyond EOF and need to take the lock,
+ * or we'll be within EOF and we don't need to take it at all.
+ */
+static int
+xfs_dio_endio_set_isize(
+	struct inode		*inode,
+	loff_t			offset,
+	ssize_t			size)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+
+	if (offset + size <= i_size_read(inode))
+		return 0;
+
+	spin_lock(&ip->i_flags_lock);
+	if (offset + size <= i_size_read(inode)) {
+		spin_unlock(&ip->i_flags_lock);
+		return 0;
+	}
+
+	i_size_write(inode, offset + size);
+	spin_unlock(&ip->i_flags_lock);
+
+	return xfs_setfilesize(ip, offset, size);
+}
+
+static int
+xfs_zoned_dio_write_end_io(
+	struct kiocb		*iocb,
+	ssize_t			size,
+	int			error,
+	unsigned		flags)
+{
+	struct inode		*inode = file_inode(iocb->ki_filp);
+	struct xfs_inode	*ip = XFS_I(inode);
+	unsigned int		nofs_flag;
+
+	ASSERT(!(flags & (IOMAP_DIO_UNWRITTEN | IOMAP_DIO_COW)));
+
+	trace_xfs_end_io_direct_write(ip, iocb->ki_pos, size);
+
+	if (xfs_is_shutdown(ip->i_mount))
+		return -EIO;
+
+	if (error || !size)
+		return error;
+
+	XFS_STATS_ADD(ip->i_mount, xs_write_bytes, size);
+
+	nofs_flag = memalloc_nofs_save();
+	error = xfs_dio_endio_set_isize(inode, iocb->ki_pos, size);
+	memalloc_nofs_restore(nofs_flag);
+
+	return error;
+}
+
 static int
 xfs_dio_write_end_io(
 	struct kiocb		*iocb,
@@ -572,8 +638,7 @@ xfs_dio_write_end_io(
 	loff_t			offset = iocb->ki_pos;
 	unsigned int		nofs_flag;
 
-	ASSERT(!xfs_is_zoned_inode(ip) ||
-	       !(flags & (IOMAP_DIO_UNWRITTEN | IOMAP_DIO_COW)));
+	ASSERT(!xfs_is_zoned_inode(ip));
 
 	trace_xfs_end_io_direct_write(ip, offset, size);
 
@@ -623,30 +688,8 @@ xfs_dio_write_end_io(
 	 * with the on-disk inode size being outside the in-core inode size. We
 	 * have no other method of updating EOF for AIO, so always do it here
 	 * if necessary.
-	 *
-	 * We need to lock the test/set EOF update as we can be racing with
-	 * other IO completions here to update the EOF. Failing to serialise
-	 * here can result in EOF moving backwards and Bad Things Happen when
-	 * that occurs.
-	 *
-	 * As IO completion only ever extends EOF, we can do an unlocked check
-	 * here to avoid taking the spinlock. If we land within the current EOF,
-	 * then we do not need to do an extending update at all, and we don't
-	 * need to take the lock to check this. If we race with an update moving
-	 * EOF, then we'll either still be beyond EOF and need to take the lock,
-	 * or we'll be within EOF and we don't need to take it at all.
 	 */
-	if (offset + size <= i_size_read(inode))
-		goto out;
-
-	spin_lock(&ip->i_flags_lock);
-	if (offset + size > i_size_read(inode)) {
-		i_size_write(inode, offset + size);
-		spin_unlock(&ip->i_flags_lock);
-		error = xfs_setfilesize(ip, offset, size);
-	} else {
-		spin_unlock(&ip->i_flags_lock);
-	}
+	error = xfs_dio_endio_set_isize(inode, offset, size);
 
 out:
 	memalloc_nofs_restore(nofs_flag);
@@ -688,7 +731,7 @@ xfs_dio_zoned_submit_io(
 static const struct iomap_dio_ops xfs_dio_zoned_write_ops = {
 	.bio_set	= &iomap_ioend_bioset,
 	.submit_io	= xfs_dio_zoned_submit_io,
-	.end_io		= xfs_dio_write_end_io,
+	.end_io		= xfs_zoned_dio_write_end_io,
 };
 
 /*
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index facffdc8dca8..46e234863644 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -37,12 +37,15 @@
 #include "xfs_ioctl.h"
 #include "xfs_xattr.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_rtrmap_btree.h"
 #include "xfs_file.h"
 #include "xfs_exchrange.h"
 #include "xfs_handle.h"
 #include "xfs_rtgroup.h"
 #include "xfs_healthmon.h"
 #include "xfs_verify_media.h"
+#include "xfs_zone_priv.h"
+#include "xfs_zone_alloc.h"
 
 #include <linux/mount.h>
 #include <linux/fileattr.h>
@@ -413,6 +416,7 @@ xfs_ioc_rtgroup_geometry(
 {
 	struct xfs_rtgroup	*rtg;
 	struct xfs_rtgroup_geometry rgeo;
+	xfs_rgblock_t		highest_rgbno;
 	int			error;
 
 	if (copy_from_user(&rgeo, arg, sizeof(rgeo)))
@@ -433,6 +437,21 @@ xfs_ioc_rtgroup_geometry(
 	if (error)
 		return error;
 
+	if (xfs_has_zoned(mp)) {
+		xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP);
+		if (rtg->rtg_open_zone) {
+			rgeo.rg_writepointer = rtg->rtg_open_zone->oz_allocated;
+		} else {
+			highest_rgbno = xfs_rtrmap_highest_rgbno(rtg);
+			if (highest_rgbno == NULLRGBLOCK)
+				rgeo.rg_writepointer = 0;
+			else
+				rgeo.rg_writepointer = highest_rgbno + 1;
+		}
+		xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP);
+		rgeo.rg_flags |= XFS_RTGROUP_GEOM_WRITEPOINTER;
+	}
+
 	if (copy_to_user(arg, &rgeo, sizeof(rgeo)))
 		return -EFAULT;
 	return 0;
diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c
index e3d19b6dc64a..06e2cb79030e 100644
--- a/fs/xfs/xfs_zone_alloc.c
+++ b/fs/xfs/xfs_zone_alloc.c
@@ -189,27 +189,16 @@ xfs_open_zone_mark_full(
 		xfs_zone_account_reclaimable(rtg, rtg_blocks(rtg) - used);
 }
 
-static void
-xfs_zone_record_blocks(
-	struct xfs_trans	*tp,
+static inline void
+xfs_zone_inc_written(
 	struct xfs_open_zone	*oz,
-	xfs_fsblock_t		fsbno,
 	xfs_filblks_t		len)
 {
-	struct xfs_mount	*mp = tp->t_mountp;
-	struct xfs_rtgroup	*rtg = oz->oz_rtg;
-	struct xfs_inode	*rmapip = rtg_rmap(rtg);
-
-	trace_xfs_zone_record_blocks(oz, xfs_rtb_to_rgbno(mp, fsbno), len);
+	xfs_assert_ilocked(rtg_rmap(oz->oz_rtg), XFS_ILOCK_EXCL);
 
-	xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP);
-	xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_RMAP);
-	rmapip->i_used_blocks += len;
-	ASSERT(rmapip->i_used_blocks <= rtg_blocks(rtg));
 	oz->oz_written += len;
-	if (oz->oz_written == rtg_blocks(rtg))
+	if (oz->oz_written == rtg_blocks(oz->oz_rtg))
 		xfs_open_zone_mark_full(oz);
-	xfs_trans_log_inode(tp, rmapip, XFS_ILOG_CORE);
 }
 
 /*
@@ -227,9 +216,7 @@ xfs_zone_skip_blocks(
 	trace_xfs_zone_skip_blocks(oz, 0, len);
 
 	xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP);
-	oz->oz_written += len;
-	if (oz->oz_written == rtg_blocks(rtg))
-		xfs_open_zone_mark_full(oz);
+	xfs_zone_inc_written(oz, len);
 	xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP);
 
 	xfs_add_frextents(rtg_mount(rtg), len);
@@ -244,6 +231,8 @@ xfs_zoned_map_extent(
 	xfs_fsblock_t		old_startblock)
 {
 	struct xfs_bmbt_irec	data;
+	struct xfs_rtgroup	*rtg = oz->oz_rtg;
+	struct xfs_inode	*rmapip = rtg_rmap(rtg);
 	int			nmaps = 1;
 	int			error;
 
@@ -302,7 +291,15 @@ xfs_zoned_map_extent(
 		}
 	}
 
-	xfs_zone_record_blocks(tp, oz, new->br_startblock, new->br_blockcount);
+	trace_xfs_zone_record_blocks(oz,
+		xfs_rtb_to_rgbno(tp->t_mountp, new->br_startblock),
+		new->br_blockcount);
+	xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP);
+	xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_RMAP);
+	rmapip->i_used_blocks += new->br_blockcount;
+	ASSERT(rmapip->i_used_blocks <= rtg_blocks(rtg));
+	xfs_zone_inc_written(oz, new->br_blockcount);
+	xfs_trans_log_inode(tp, rmapip, XFS_ILOG_CORE);
 
 	/* Map the new blocks into the data fork. */
 	xfs_bmap_map_extent(tp, ip, XFS_DATA_FORK, new);
@@ -681,10 +678,11 @@ xfs_select_zone_nowait(
 	if (oz)
 		goto out_unlock;
 
-	if (pack_tight)
+	if (pack_tight) {
 		oz = xfs_select_open_zone_mru(zi, write_hint);
-	if (oz)
-		goto out_unlock;
+		if (oz)
+			goto out_unlock;
+	}
 
 	/*
 	 * See if we can open a new zone and use that so that data for different
@@ -695,7 +693,7 @@ xfs_select_zone_nowait(
 		goto out_unlock;
 
 	/*
-	 * Try to find an zone that is an ok match to colocate data with.
+	 * Try to find a zone that is an ok match to colocate data with.
 	 */
 	oz = xfs_select_open_zone_lru(zi, write_hint, XFS_ZONE_ALLOC_OK);
 	if (oz)
diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c
index 309f70098524..0ff710fa0ee7 100644
--- a/fs/xfs/xfs_zone_gc.c
+++ b/fs/xfs/xfs_zone_gc.c
@@ -170,25 +170,37 @@ xfs_zoned_need_gc(
 	s64			available, free, threshold;
 	s32			remainder;
 
+	/* If we have no reclaimable blocks, running GC is useless. */
 	if (!xfs_zoned_have_reclaimable(mp->m_zone_info))
 		return false;
 
+	/*
+	 * In order to avoid file fragmentation as much as possible, we should
+	 * make sure that we can open enough zones. So trigger GC if the number
+	 * of blocks immediately available for writes is lower than the total
+	 * number of blocks from all possible open zones.
+	 */
 	available = xfs_estimate_freecounter(mp, XC_FREE_RTAVAILABLE);
-
 	if (available <
 	    xfs_rtgs_to_rfsbs(mp, mp->m_max_open_zones - XFS_OPEN_GC_ZONES))
 		return true;
 
-	free = xfs_estimate_freecounter(mp, XC_FREE_RTEXTENTS);
+	/*
+	 * For cases where the user wants to be more aggressive with GC,
+	 * the sysfs attribute zonegc_low_space may be set to a non zero value,
+	 * to indicate that GC should try to maintain at least zonegc_low_space
+	 * percent of the free space to be directly available for writing. Check
+	 * this here.
+	 */
+	if (!mp->m_zonegc_low_space)
+		return false;
 
+	free = xfs_estimate_freecounter(mp, XC_FREE_RTEXTENTS);
 	threshold = div_s64_rem(free, 100, &remainder);
 	threshold = threshold * mp->m_zonegc_low_space +
 		    remainder * div_s64(mp->m_zonegc_low_space, 100);
 
-	if (available < threshold)
-		return true;
-
-	return false;
+	return available < threshold;
 }
 
 static struct xfs_zone_gc_data *
diff --git a/fs/xfs/xfs_zone_info.c b/fs/xfs/xfs_zone_info.c
index 53eabbc3334c..a2af44011654 100644
--- a/fs/xfs/xfs_zone_info.c
+++ b/fs/xfs/xfs_zone_info.c
@@ -90,9 +90,14 @@ xfs_zoned_show_stats(
 	seq_printf(m, "\tRT GC required: %d\n",
 		xfs_zoned_need_gc(mp));
 
+	seq_printf(m, "\ttotal number of zones: %u\n",
+		mp->m_sb.sb_rgcount);
 	seq_printf(m, "\tfree zones: %d\n", atomic_read(&zi->zi_nr_free_zones));
-	seq_puts(m, "\topen zones:\n");
+
 	spin_lock(&zi->zi_open_zones_lock);
+	seq_printf(m, "\tnumber of open zones: %u / %u\n",
+		zi->zi_nr_open_zones, mp->m_max_open_zones);
+	seq_puts(m, "\topen zones:\n");
 	list_for_each_entry(oz, &zi->zi_open_zones, oz_entry)
 		xfs_show_open_zone(m, oz);
 	if (zi->zi_open_gc_zone) {