Merge tag 'for-5.20-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "This brings some long awaited changes, the send protocol bump,
  otherwise lots of small improvements and fixes. The main core part is
  reworking bio handling, cleaning up the submission and endio and
  improving error handling.

  There are some changes outside of btrfs adding helpers or updating
  API, listed at the end of the changelog.

  Features:

   - sysfs:
      - export chunk size, in debug mode add tunable for setting its size
      - show zoned among features (was only in debug mode)
      - show commit stats (number, last/max/total duration)

   - send protocol updated to 2
      - new commands:
         - ability write larger data chunks than 64K
         - send raw compressed extents (uses the encoded data ioctls),
           ie. no decompression on send side, no compression needed on
           receive side if supported
         - send 'otime' (inode creation time) among other timestamps
         - send file attributes (a.k.a file flags and xflags)
      - this is first version bump, backward compatibility on send and
        receive side is provided
      - there are still some known and wanted commands that will be
        implemented in the near future, another version bump will be
        needed, however we want to minimize that to avoid causing
        usability issues

   - print checksum type and implementation at mount time

   - don't print some messages at mount (mentioned as people asked about
     it), we want to print messages namely for new features so let's
     make some space for that
      - big metadata - this has been supported for a long time and is
        not a feature that's worth mentioning
      - skinny metadata - same reason, set by default by mkfs

  Performance improvements:

   - reduced amount of reserved metadata for delayed items
      - when inserted items can be batched into one leaf
      - when deleting batched directory index items
      - when deleting delayed items used for deletion
      - overall improved count of files/sec, decreased subvolume lock
        contention

   - metadata item access bounds checker micro-optimized, with a few
     percent of improved runtime for metadata-heavy operations

   - increase direct io limit for read to 256 sectors, improved
     throughput by 3x on sample workload

  Notable fixes:

   - raid56
      - reduce parity writes, skip sectors of stripe when there are no
        data updates
      - restore reading from on-disk data instead of using stripe cache,
        this reduces chances to damage correct data due to RMW cycle

   - refuse to replay log with unknown incompat read-only feature bit
     set

   - zoned
      - fix page locking when COW fails in the middle of allocation
      - improved tracking of active zones, ZNS drives may limit the
        number and there are ENOSPC errors due to that limit and not
        actual lack of space
      - adjust maximum extent size for zone append so it does not cause
        late ENOSPC due to underreservation

   - mirror reading error messages show the mirror number

   - don't fallback to buffered IO for NOWAIT direct IO writes, we don't
     have the NOWAIT semantics for buffered io yet

   - send, fix sending link commands for existing file paths when there
     are deleted and created hardlinks for same files

   - repair all mirrors for profiles with more than 1 copy (raid1c34)

   - fix repair of compressed extents, unify where error detection and
     repair happen

  Core changes:

   - bio completion cleanups
      - don't double defer compression bios
      - simplify endio workqueues
      - add more data to btrfs_bio to avoid allocation for read requests
      - rework bio error handling so it's same what block layer does,
        the submission works and errors are consumed in endio
      - when asynchronous bio offload fails fall back to synchronous
        checksum calculation to avoid errors under writeback or memory
        pressure

   - new trace points
      - raid56 events
      - ordered extent operations

   - super block log_root_transid deprecated (never used)

   - mixed_backref and big_metadata sysfs feature files removed, they've
     been default for sufficiently long time, there are no known users
     and mixed_backref could be confused with mixed_groups

  Non-btrfs changes, API updates:

   - minor highmem API update to cover const arguments

   - switch all kmap/kmap_atomic to kmap_local

   - remove redundant flush_dcache_page()

   - address_space_operations::writepage callback removed

   - add bdev_max_segments() helper"

* tag 'for-5.20-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (163 commits)
  btrfs: don't call btrfs_page_set_checked in finish_compressed_bio_read
  btrfs: fix repair of compressed extents
  btrfs: remove the start argument to check_data_csum and export
  btrfs: pass a btrfs_bio to btrfs_repair_one_sector
  btrfs: simplify the pending I/O counting in struct compressed_bio
  btrfs: repair all known bad mirrors
  btrfs: merge btrfs_dev_stat_print_on_error with its only caller
  btrfs: join running log transaction when logging new name
  btrfs: simplify error handling in btrfs_lookup_dentry
  btrfs: send: always use the rbtree based inode ref management infrastructure
  btrfs: send: fix sending link commands for existing file paths
  btrfs: send: introduce recorded_ref_alloc and recorded_ref_free
  btrfs: zoned: wait until zone is finished when allocation didn't progress
  btrfs: zoned: write out partially allocated region
  btrfs: zoned: activate necessary block group
  btrfs: zoned: activate metadata block group on flush_space
  btrfs: zoned: disable metadata overcommit for zoned
  btrfs: zoned: introduce space_info->active_total_bytes
  btrfs: zoned: finish least available block group on data bg allocation
  btrfs: let can_allocate_chunk return error
  ...

1 files changed, 177 insertions, 9 deletions

diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 92a1fa8e3da6..d5d0717fd09a 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -21,6 +21,7 @@
 #include "space-info.h"
 #include "block-group.h"
 #include "qgroup.h"
+#include "misc.h"
 
 /*
  * Structure name                       Path
@@ -61,6 +62,10 @@ struct raid_kobject {
 	.store	= _store,						\
 }
 
+#define BTRFS_ATTR_W(_prefix, _name, _store)			        \
+	static struct kobj_attribute btrfs_attr_##_prefix##_##_name =	\
+			__INIT_KOBJ_ATTR(_name, 0200, NULL, _store)
+
 #define BTRFS_ATTR_RW(_prefix, _name, _show, _store)			\
 	static struct kobj_attribute btrfs_attr_##_prefix##_##_name =	\
 			__INIT_KOBJ_ATTR(_name, 0644, _show, _store)
@@ -92,6 +97,7 @@ static struct btrfs_feature_attr btrfs_attr_features_##_name = {	     \
 
 static inline struct btrfs_fs_info *to_fs_info(struct kobject *kobj);
 static inline struct btrfs_fs_devices *to_fs_devs(struct kobject *kobj);
+static struct kobject *get_btrfs_kobj(struct kobject *kobj);
 
 static struct btrfs_feature_attr *to_btrfs_feature_attr(struct kobj_attribute *a)
 {
@@ -270,12 +276,10 @@ static umode_t btrfs_feature_visible(struct kobject *kobj,
 	return mode;
 }
 
-BTRFS_FEAT_ATTR_INCOMPAT(mixed_backref, MIXED_BACKREF);
 BTRFS_FEAT_ATTR_INCOMPAT(default_subvol, DEFAULT_SUBVOL);
 BTRFS_FEAT_ATTR_INCOMPAT(mixed_groups, MIXED_GROUPS);
 BTRFS_FEAT_ATTR_INCOMPAT(compress_lzo, COMPRESS_LZO);
 BTRFS_FEAT_ATTR_INCOMPAT(compress_zstd, COMPRESS_ZSTD);
-BTRFS_FEAT_ATTR_INCOMPAT(big_metadata, BIG_METADATA);
 BTRFS_FEAT_ATTR_INCOMPAT(extended_iref, EXTENDED_IREF);
 BTRFS_FEAT_ATTR_INCOMPAT(raid56, RAID56);
 BTRFS_FEAT_ATTR_INCOMPAT(skinny_metadata, SKINNY_METADATA);
@@ -283,9 +287,10 @@ BTRFS_FEAT_ATTR_INCOMPAT(no_holes, NO_HOLES);
 BTRFS_FEAT_ATTR_INCOMPAT(metadata_uuid, METADATA_UUID);
 BTRFS_FEAT_ATTR_COMPAT_RO(free_space_tree, FREE_SPACE_TREE);
 BTRFS_FEAT_ATTR_INCOMPAT(raid1c34, RAID1C34);
-#ifdef CONFIG_BTRFS_DEBUG
-/* Remove once support for zoned allocation is feature complete */
+#ifdef CONFIG_BLK_DEV_ZONED
 BTRFS_FEAT_ATTR_INCOMPAT(zoned, ZONED);
+#endif
+#ifdef CONFIG_BTRFS_DEBUG
 /* Remove once support for extent tree v2 is feature complete */
 BTRFS_FEAT_ATTR_INCOMPAT(extent_tree_v2, EXTENT_TREE_V2);
 #endif
@@ -296,17 +301,15 @@ BTRFS_FEAT_ATTR_COMPAT_RO(verity, VERITY);
 /*
  * Features which depend on feature bits and may differ between each fs.
  *
- * /sys/fs/btrfs/features      - all available features implemeted by this version
+ * /sys/fs/btrfs/features      - all available features implemented by this version
  * /sys/fs/btrfs/UUID/features - features of the fs which are enabled or
  *                               can be changed on a mounted filesystem.
  */
 static struct attribute *btrfs_supported_feature_attrs[] = {
-	BTRFS_FEAT_ATTR_PTR(mixed_backref),
 	BTRFS_FEAT_ATTR_PTR(default_subvol),
 	BTRFS_FEAT_ATTR_PTR(mixed_groups),
 	BTRFS_FEAT_ATTR_PTR(compress_lzo),
 	BTRFS_FEAT_ATTR_PTR(compress_zstd),
-	BTRFS_FEAT_ATTR_PTR(big_metadata),
 	BTRFS_FEAT_ATTR_PTR(extended_iref),
 	BTRFS_FEAT_ATTR_PTR(raid56),
 	BTRFS_FEAT_ATTR_PTR(skinny_metadata),
@@ -314,8 +317,10 @@ static struct attribute *btrfs_supported_feature_attrs[] = {
 	BTRFS_FEAT_ATTR_PTR(metadata_uuid),
 	BTRFS_FEAT_ATTR_PTR(free_space_tree),
 	BTRFS_FEAT_ATTR_PTR(raid1c34),
-#ifdef CONFIG_BTRFS_DEBUG
+#ifdef CONFIG_BLK_DEV_ZONED
 	BTRFS_FEAT_ATTR_PTR(zoned),
+#endif
+#ifdef CONFIG_BTRFS_DEBUG
 	BTRFS_FEAT_ATTR_PTR(extent_tree_v2),
 #endif
 #ifdef CONFIG_FS_VERITY
@@ -709,6 +714,112 @@ static ssize_t btrfs_space_info_show_##field(struct kobject *kobj,	\
 }									\
 BTRFS_ATTR(space_info, field, btrfs_space_info_show_##field)
 
+static ssize_t btrfs_chunk_size_show(struct kobject *kobj,
+				     struct kobj_attribute *a, char *buf)
+{
+	struct btrfs_space_info *sinfo = to_space_info(kobj);
+
+	return sysfs_emit(buf, "%llu\n", READ_ONCE(sinfo->chunk_size));
+}
+
+/*
+ * Store new chunk size in space info. Can be called on a read-only filesystem.
+ *
+ * If the new chunk size value is larger than 10% of free space it is reduced
+ * to match that limit. Alignment must be to 256M and the system chunk size
+ * cannot be set.
+ */
+static ssize_t btrfs_chunk_size_store(struct kobject *kobj,
+				      struct kobj_attribute *a,
+				      const char *buf, size_t len)
+{
+	struct btrfs_space_info *space_info = to_space_info(kobj);
+	struct btrfs_fs_info *fs_info = to_fs_info(get_btrfs_kobj(kobj));
+	char *retptr;
+	u64 val;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!fs_info->fs_devices)
+		return -EINVAL;
+
+	if (btrfs_is_zoned(fs_info))
+		return -EINVAL;
+
+	/* System block type must not be changed. */
+	if (space_info->flags & BTRFS_BLOCK_GROUP_SYSTEM)
+		return -EPERM;
+
+	val = memparse(buf, &retptr);
+	/* There could be trailing '\n', also catch any typos after the value */
+	retptr = skip_spaces(retptr);
+	if (*retptr != 0 || val == 0)
+		return -EINVAL;
+
+	val = min(val, BTRFS_MAX_DATA_CHUNK_SIZE);
+
+	/* Limit stripe size to 10% of available space. */
+	val = min(div_factor(fs_info->fs_devices->total_rw_bytes, 1), val);
+
+	/* Must be multiple of 256M. */
+	val &= ~((u64)SZ_256M - 1);
+
+	/* Must be at least 256M. */
+	if (val < SZ_256M)
+		return -EINVAL;
+
+	btrfs_update_space_info_chunk_size(space_info, val);
+
+	return len;
+}
+
+#ifdef CONFIG_BTRFS_DEBUG
+/*
+ * Request chunk allocation with current chunk size.
+ */
+static ssize_t btrfs_force_chunk_alloc_store(struct kobject *kobj,
+					     struct kobj_attribute *a,
+					     const char *buf, size_t len)
+{
+	struct btrfs_space_info *space_info = to_space_info(kobj);
+	struct btrfs_fs_info *fs_info = to_fs_info(get_btrfs_kobj(kobj));
+	struct btrfs_trans_handle *trans;
+	bool val;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (sb_rdonly(fs_info->sb))
+		return -EROFS;
+
+	ret = kstrtobool(buf, &val);
+	if (ret)
+		return ret;
+
+	if (!val)
+		return -EINVAL;
+
+	/*
+	 * This is unsafe to be called from sysfs context and may cause
+	 * unexpected problems.
+	 */
+	trans = btrfs_start_transaction(fs_info->tree_root, 0);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
+	ret = btrfs_force_chunk_alloc(trans, space_info->flags);
+	btrfs_end_transaction(trans);
+
+	if (ret == 1)
+		return len;
+
+	return -ENOSPC;
+}
+BTRFS_ATTR_W(space_info, force_chunk_alloc, btrfs_force_chunk_alloc_store);
+
+#endif
+
 SPACE_INFO_ATTR(flags);
 SPACE_INFO_ATTR(total_bytes);
 SPACE_INFO_ATTR(bytes_used);
@@ -719,6 +830,7 @@ SPACE_INFO_ATTR(bytes_readonly);
 SPACE_INFO_ATTR(bytes_zone_unusable);
 SPACE_INFO_ATTR(disk_used);
 SPACE_INFO_ATTR(disk_total);
+BTRFS_ATTR_RW(space_info, chunk_size, btrfs_chunk_size_show, btrfs_chunk_size_store);
 
 static ssize_t btrfs_sinfo_bg_reclaim_threshold_show(struct kobject *kobj,
 						     struct kobj_attribute *a,
@@ -773,6 +885,10 @@ static struct attribute *space_info_attrs[] = {
 	BTRFS_ATTR_PTR(space_info, disk_used),
 	BTRFS_ATTR_PTR(space_info, disk_total),
 	BTRFS_ATTR_PTR(space_info, bg_reclaim_threshold),
+	BTRFS_ATTR_PTR(space_info, chunk_size),
+#ifdef CONFIG_BTRFS_DEBUG
+	BTRFS_ATTR_PTR(space_info, force_chunk_alloc),
+#endif
 	NULL,
 };
 ATTRIBUTE_GROUPS(space_info);
@@ -871,6 +987,48 @@ static ssize_t btrfs_sectorsize_show(struct kobject *kobj,
 
 BTRFS_ATTR(, sectorsize, btrfs_sectorsize_show);
 
+static ssize_t btrfs_commit_stats_show(struct kobject *kobj,
+				       struct kobj_attribute *a, char *buf)
+{
+	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+
+	return sysfs_emit(buf,
+		"commits %llu\n"
+		"last_commit_ms %llu\n"
+		"max_commit_ms %llu\n"
+		"total_commit_ms %llu\n",
+		fs_info->commit_stats.commit_count,
+		div_u64(fs_info->commit_stats.last_commit_dur, NSEC_PER_MSEC),
+		div_u64(fs_info->commit_stats.max_commit_dur, NSEC_PER_MSEC),
+		div_u64(fs_info->commit_stats.total_commit_dur, NSEC_PER_MSEC));
+}
+
+static ssize_t btrfs_commit_stats_store(struct kobject *kobj,
+					struct kobj_attribute *a,
+					const char *buf, size_t len)
+{
+	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+	unsigned long val;
+	int ret;
+
+	if (!fs_info)
+		return -EPERM;
+
+	if (!capable(CAP_SYS_RESOURCE))
+		return -EPERM;
+
+	ret = kstrtoul(buf, 10, &val);
+	if (ret)
+		return ret;
+	if (val)
+		return -EINVAL;
+
+	WRITE_ONCE(fs_info->commit_stats.max_commit_dur, 0);
+
+	return len;
+}
+BTRFS_ATTR_RW(, commit_stats, btrfs_commit_stats_show, btrfs_commit_stats_store);
+
 static ssize_t btrfs_clone_alignment_show(struct kobject *kobj,
 				struct kobj_attribute *a, char *buf)
 {
@@ -1110,6 +1268,7 @@ static const struct attribute *btrfs_attrs[] = {
 	BTRFS_ATTR_PTR(, generation),
 	BTRFS_ATTR_PTR(, read_policy),
 	BTRFS_ATTR_PTR(, bg_reclaim_threshold),
+	BTRFS_ATTR_PTR(, commit_stats),
 	NULL,
 };
 
@@ -1140,6 +1299,16 @@ static inline struct btrfs_fs_info *to_fs_info(struct kobject *kobj)
 	return to_fs_devs(kobj)->fs_info;
 }
 
+static struct kobject *get_btrfs_kobj(struct kobject *kobj)
+{
+	while (kobj) {
+		if (kobj->ktype == &btrfs_ktype)
+			return kobj;
+		kobj = kobj->parent;
+	}
+	return NULL;
+}
+
 #define NUM_FEATURE_BITS 64
 #define BTRFS_FEATURE_NAME_MAX 13
 static char btrfs_unknown_feature_names[FEAT_MAX][NUM_FEATURE_BITS][BTRFS_FEATURE_NAME_MAX];
@@ -2106,4 +2275,3 @@ void __cold btrfs_exit_sysfs(void)
 #endif
 	kset_unregister(btrfs_kset);
 }
-