Merge tag 'xfs-zoned-allocator-2025-03-03' of git://git.infradead.org/users/hch/xfs into xfs-6.15-zoned_devices

xfs: add support for zoned devices

Add support for the new zoned space allocator and thus for zoned devices:

    https://zonedstorage.io/docs/introduction/zoned-storage

to XFS. This has been developed for and tested on both SMR hard drives,
which are the oldest and most common class of zoned devices:

   https://zonedstorage.io/docs/introduction/smr

and ZNS SSDs:

   https://zonedstorage.io/docs/introduction/zns

It has not been tested with zoned UFS devices, as their current capacity
points and performance characteristics aren't too interesting for XFS
use cases (but never say never).

Sequential write only zones are only supported for data using a new
allocator for the RT device, which maps each zone to a rtgroup which
is written sequentially.  All metadata and (for now) the log require
using randomly writable space. This means a realtime device is required
to support zoned storage, but for the common case of SMR hard drives
that contain random writable zones and sequential write required zones
on the same block device, the concept of an internal RT device is added
which means using XFS on a SMR HDD is as simple as:

$ mkfs.xfs /dev/sda
$ mount /dev/sda /mnt

When using NVMe ZNS SSDs that do not support conventional zones, the
traditional multi-device RT configuration is required.  E.g. for an
SSD with a conventional namespace 1 and a zoned namespace 2:

$ mkfs.xfs /dev/nvme0n1 -o rtdev=/dev/nvme0n2
$ mount -o rtdev=/dev/nvme0n2 /dev/nvme0n1 /mnt

The zoned allocator can also be used on conventional block devices, or
on conventional zones (e.g. when using an SMR HDD as the external RT
device).  For example using zoned XFS on normal SSDs shows very nice
performance advantages and write amplification reduction for intelligent
workloads like RocksDB.

Some work is still in progress or planned, but should not affect the
integration with the rest of XFS or the on-disk format:

 - support for quotas
 - support for reflinks

Note that the I/O path already supports reflink, but garbage collection
isn't refcount aware yet and would unshare shared blocks, thus rendering
the feature useless.

1 files changed, 199 insertions, 15 deletions

diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index bfc2f1249022..83f894c07866 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -102,6 +102,7 @@ struct xfs_rmap_intent;
 struct xfs_refcount_intent;
 struct xfs_metadir_update;
 struct xfs_rtgroup;
+struct xfs_open_zone;
 
 #define XFS_ATTR_FILTER_FLAGS \
 	{ XFS_ATTR_ROOT,	"ROOT" }, \
@@ -265,6 +266,152 @@ DEFINE_GROUP_REF_EVENT(xfs_group_grab);
 DEFINE_GROUP_REF_EVENT(xfs_group_grab_next_tag);
 DEFINE_GROUP_REF_EVENT(xfs_group_rele);
 
+#ifdef CONFIG_XFS_RT
+DECLARE_EVENT_CLASS(xfs_zone_class,
+	TP_PROTO(struct xfs_rtgroup *rtg),
+	TP_ARGS(rtg),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_rgnumber_t, rgno)
+		__field(xfs_rgblock_t, used)
+		__field(unsigned int, nr_open)
+	),
+	TP_fast_assign(
+		struct xfs_mount	*mp = rtg_mount(rtg);
+
+		__entry->dev = mp->m_super->s_dev;
+		__entry->rgno = rtg_rgno(rtg);
+		__entry->used = rtg_rmap(rtg)->i_used_blocks;
+		__entry->nr_open = mp->m_zone_info->zi_nr_open_zones;
+	),
+	TP_printk("dev %d:%d rgno 0x%x used 0x%x nr_open %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rgno,
+		  __entry->used,
+		  __entry->nr_open)
+);
+
+#define DEFINE_ZONE_EVENT(name)				\
+DEFINE_EVENT(xfs_zone_class, name,			\
+	TP_PROTO(struct xfs_rtgroup *rtg),		\
+	TP_ARGS(rtg))
+DEFINE_ZONE_EVENT(xfs_zone_emptied);
+DEFINE_ZONE_EVENT(xfs_zone_full);
+DEFINE_ZONE_EVENT(xfs_zone_opened);
+DEFINE_ZONE_EVENT(xfs_zone_reset);
+DEFINE_ZONE_EVENT(xfs_zone_gc_target_opened);
+
+TRACE_EVENT(xfs_zone_free_blocks,
+	TP_PROTO(struct xfs_rtgroup *rtg, xfs_rgblock_t rgbno,
+		 xfs_extlen_t len),
+	TP_ARGS(rtg, rgbno, len),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_rgnumber_t, rgno)
+		__field(xfs_rgblock_t, used)
+		__field(xfs_rgblock_t, rgbno)
+		__field(xfs_extlen_t, len)
+	),
+	TP_fast_assign(
+		__entry->dev = rtg_mount(rtg)->m_super->s_dev;
+		__entry->rgno = rtg_rgno(rtg);
+		__entry->used = rtg_rmap(rtg)->i_used_blocks;
+		__entry->rgbno = rgbno;
+		__entry->len = len;
+	),
+	TP_printk("dev %d:%d rgno 0x%x used 0x%x rgbno 0x%x len 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rgno,
+		  __entry->used,
+		  __entry->rgbno,
+		  __entry->len)
+);
+
+DECLARE_EVENT_CLASS(xfs_zone_alloc_class,
+	TP_PROTO(struct xfs_open_zone *oz, xfs_rgblock_t rgbno,
+		 xfs_extlen_t len),
+	TP_ARGS(oz, rgbno, len),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_rgnumber_t, rgno)
+		__field(xfs_rgblock_t, used)
+		__field(xfs_rgblock_t, written)
+		__field(xfs_rgblock_t, write_pointer)
+		__field(xfs_rgblock_t, rgbno)
+		__field(xfs_extlen_t, len)
+	),
+	TP_fast_assign(
+		__entry->dev = rtg_mount(oz->oz_rtg)->m_super->s_dev;
+		__entry->rgno = rtg_rgno(oz->oz_rtg);
+		__entry->used = rtg_rmap(oz->oz_rtg)->i_used_blocks;
+		__entry->written = oz->oz_written;
+		__entry->write_pointer = oz->oz_write_pointer;
+		__entry->rgbno = rgbno;
+		__entry->len = len;
+	),
+	TP_printk("dev %d:%d rgno 0x%x used 0x%x written 0x%x wp 0x%x rgbno 0x%x len 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rgno,
+		  __entry->used,
+		  __entry->written,
+		  __entry->write_pointer,
+		  __entry->rgbno,
+		  __entry->len)
+);
+
+#define DEFINE_ZONE_ALLOC_EVENT(name)				\
+DEFINE_EVENT(xfs_zone_alloc_class, name,			\
+	TP_PROTO(struct xfs_open_zone *oz, xfs_rgblock_t rgbno,	\
+		 xfs_extlen_t len),				\
+	TP_ARGS(oz, rgbno, len))
+DEFINE_ZONE_ALLOC_EVENT(xfs_zone_record_blocks);
+DEFINE_ZONE_ALLOC_EVENT(xfs_zone_alloc_blocks);
+
+TRACE_EVENT(xfs_zone_gc_select_victim,
+	TP_PROTO(struct xfs_rtgroup *rtg, unsigned int bucket),
+	TP_ARGS(rtg, bucket),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_rgnumber_t, rgno)
+		__field(xfs_rgblock_t, used)
+		__field(unsigned int, bucket)
+	),
+	TP_fast_assign(
+		__entry->dev = rtg_mount(rtg)->m_super->s_dev;
+		__entry->rgno = rtg_rgno(rtg);
+		__entry->used = rtg_rmap(rtg)->i_used_blocks;
+		__entry->bucket = bucket;
+	),
+	TP_printk("dev %d:%d rgno 0x%x used 0x%x bucket %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rgno,
+		  __entry->used,
+		  __entry->bucket)
+);
+
+TRACE_EVENT(xfs_zones_mount,
+	TP_PROTO(struct xfs_mount *mp),
+	TP_ARGS(mp),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_rgnumber_t, rgcount)
+		__field(uint32_t, blocks)
+		__field(unsigned int, max_open_zones)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->rgcount = mp->m_sb.sb_rgcount;
+		__entry->blocks = mp->m_groups[XG_TYPE_RTG].blocks;
+		__entry->max_open_zones = mp->m_max_open_zones;
+	),
+	TP_printk("dev %d:%d zoned %u blocks_per_zone %u, max_open %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		__entry->rgcount,
+		__entry->blocks,
+		__entry->max_open_zones)
+);
+#endif /* CONFIG_XFS_RT */
+
 TRACE_EVENT(xfs_inodegc_worker,
 	TP_PROTO(struct xfs_mount *mp, unsigned int shrinker_hits),
 	TP_ARGS(mp, shrinker_hits),
@@ -1596,6 +1743,7 @@ DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write);
 DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write_unwritten);
 DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write_append);
 DEFINE_SIMPLE_IO_EVENT(xfs_file_splice_read);
+DEFINE_SIMPLE_IO_EVENT(xfs_zoned_map_blocks);
 
 DECLARE_EVENT_CLASS(xfs_itrunc_class,
 	TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size),
@@ -3983,6 +4131,7 @@ DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range);
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_from);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_to);
+DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_skip);
 
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_cancel_cow_range_error);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_end_cow_error);
@@ -5606,11 +5755,10 @@ DEFINE_METADIR_EVENT(xfs_metadir_lookup);
 /* metadata inode space reservations */
 
 DECLARE_EVENT_CLASS(xfs_metafile_resv_class,
-	TP_PROTO(struct xfs_inode *ip, xfs_filblks_t len),
-	TP_ARGS(ip, len),
+	TP_PROTO(struct xfs_mount *mp, xfs_filblks_t len),
+	TP_ARGS(mp, len),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
-		__field(xfs_ino_t, ino)
 		__field(unsigned long long, freeblks)
 		__field(unsigned long long, reserved)
 		__field(unsigned long long, asked)
@@ -5618,19 +5766,15 @@ DECLARE_EVENT_CLASS(xfs_metafile_resv_class,
 		__field(unsigned long long, len)
 	),
 	TP_fast_assign(
-		struct xfs_mount *mp = ip->i_mount;
-
 		__entry->dev = mp->m_super->s_dev;
-		__entry->ino = ip->i_ino;
-		__entry->freeblks = percpu_counter_sum(&mp->m_fdblocks);
-		__entry->reserved = ip->i_delayed_blks;
-		__entry->asked = ip->i_meta_resv_asked;
-		__entry->used = ip->i_nblocks;
+		__entry->freeblks = xfs_sum_freecounter_raw(mp, XC_FREE_BLOCKS);
+		__entry->reserved = mp->m_metafile_resv_avail;
+		__entry->asked = mp->m_metafile_resv_target;
+		__entry->used = mp->m_metafile_resv_used;
 		__entry->len = len;
 	),
-	TP_printk("dev %d:%d ino 0x%llx freeblks %llu resv %llu ask %llu used %llu len %llu",
+	TP_printk("dev %d:%d freeblks %llu resv %llu ask %llu used %llu len %llu",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->ino,
 		  __entry->freeblks,
 		  __entry->reserved,
 		  __entry->asked,
@@ -5639,14 +5783,14 @@ DECLARE_EVENT_CLASS(xfs_metafile_resv_class,
 )
 #define DEFINE_METAFILE_RESV_EVENT(name) \
 DEFINE_EVENT(xfs_metafile_resv_class, name, \
-	TP_PROTO(struct xfs_inode *ip, xfs_filblks_t len), \
-	TP_ARGS(ip, len))
+	TP_PROTO(struct xfs_mount *mp, xfs_filblks_t len), \
+	TP_ARGS(mp, len))
 DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_init);
 DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_free);
 DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_alloc_space);
 DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_free_space);
 DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_critical);
-DEFINE_INODE_ERROR_EVENT(xfs_metafile_resv_init_error);
+DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_init_error);
 
 #ifdef CONFIG_XFS_RT
 TRACE_EVENT(xfs_growfs_check_rtgeom,
@@ -5669,6 +5813,46 @@ TRACE_EVENT(xfs_growfs_check_rtgeom,
 );
 #endif /* CONFIG_XFS_RT */
 
+TRACE_DEFINE_ENUM(XC_FREE_BLOCKS);
+TRACE_DEFINE_ENUM(XC_FREE_RTEXTENTS);
+TRACE_DEFINE_ENUM(XC_FREE_RTAVAILABLE);
+
+DECLARE_EVENT_CLASS(xfs_freeblocks_resv_class,
+	TP_PROTO(struct xfs_mount *mp, enum xfs_free_counter ctr,
+		 uint64_t delta, unsigned long caller_ip),
+	TP_ARGS(mp, ctr, delta, caller_ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(enum xfs_free_counter, ctr)
+		__field(uint64_t, delta)
+		__field(uint64_t, avail)
+		__field(uint64_t, total)
+		__field(unsigned long, caller_ip)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->ctr = ctr;
+		__entry->delta = delta;
+		__entry->avail = mp->m_free[ctr].res_avail;
+		__entry->total = mp->m_free[ctr].res_total;
+		__entry->caller_ip = caller_ip;
+	),
+	TP_printk("dev %d:%d ctr %s delta %llu avail %llu total %llu caller %pS",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __print_symbolic(__entry->ctr, XFS_FREECOUNTER_STR),
+		  __entry->delta,
+		  __entry->avail,
+		  __entry->total,
+		  (char *)__entry->caller_ip)
+)
+#define DEFINE_FREEBLOCKS_RESV_EVENT(name) \
+DEFINE_EVENT(xfs_freeblocks_resv_class, name, \
+	TP_PROTO(struct xfs_mount *mp, enum xfs_free_counter ctr, \
+		 uint64_t delta, unsigned long caller_ip), \
+	TP_ARGS(mp, ctr, delta, caller_ip))
+DEFINE_FREEBLOCKS_RESV_EVENT(xfs_freecounter_reserved);
+DEFINE_FREEBLOCKS_RESV_EVENT(xfs_freecounter_enospc);
+
 #endif /* _TRACE_XFS_H */
 
 #undef TRACE_INCLUDE_PATH