Merge tag 'for-5.9-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "We don't have any big feature updates this time, there are lots of
  small enhacements or fixes. A highlight perhaps is the parallel fsync
  performance improvements, numbers below.

  Regarding the dio/iomap that was reverted last time, the required API
  changes are likely to land in the upcoming cycle, the btrfs part will
  be updated afterwards.

  User visible changes:

   - new mount option rescue= to group all recovery-related mount
     options so we don't have many specific options, currently
     introducing only aliases for existing options, future extensions
     are in development to allow read-only mount with partially damaged
     structures:
      - usebackuproot is an alias for rescue=usebackuproot
      - nologreplay is an alias for rescue=nologreplay

   - start deprecation of mount option inode_cache, removal scheduled to
     v5.11

   - removed deprecated mount options alloc_start and subvolrootid

   - device stats corruption counter gets incremented when a checksum
     mismatch is found

   - qgroup information exported in /sys/fs/btrfs/<UUID>/qgroups/<id>
     using sysfs

   - add link /sys/fs/btrfs/<UUID>/bdi pointing to the associated
     backing dev info

   - FS_INFO ioctl enhancements:
      - add flags to request/describe newly added items
      - new item: numeric checksum type and checksum size
      - new item: generation
      - new item: metadata_uuid

   - seed device: with one new read-write device added, print the new
     device information in /proc/mounts

   - balance: detect cancellation by Ctrl-C in existing cancellation
     points

  Performance improvements:

   - optimized versions of various helpers on little-endian
     architectures, where we don't have to do LE/BE conversion from
     on-disk format

   - tree-log/fsync optimizations leading to lower max latency reported
     by dbench, reduced by about 12%

   - all chunk tree leaves are prefetched at mount time, can improve
     mount time on large (terabyte-sized) filesystems

   - speed up parallel fsync of files with reflinked/deduped extents,
     with jobs 16 to 1024 the throughput gets improved roughly by 50% on
     average and runtime decreased roughly by 30% on average, notable
     outlier is 128 jobs with +121.2% on throughput and -54.6% runtime

   - another speed up of parallel fsync, reduce number of checksum tree
     lookups and contention, the improvements start to show up with 2
     tasks with +20% throughput and -16% runtime up to 64 with +200%
     throughput and -66% runtime

  Core:

   - umount-time qgroup leak checker

   - qgroups
      - add a way to unreserve partial range after failure, avoiding
        some EDQUOT errors
      - improved flushing logic when EDQUOT is hit

   - possible EINTR interruption caused by failed reservations after
     transaction start is better handled and documented

   - transaction abort errors are unified to EROFS in case it's not the
     original reason of abort or we don't have other way to determine
     the reason

  Fixes:

   - make truncate succeed on a NOCOW file even if data space is
     exhausted

   - fix cancelling balance on filesystem with exhausted metadata space

   - anon block device:
      - preallocate anon bdev when subvolume is created to report
        failure early
      - shorten time the anon bdev id is allocated
      - don't allocate anon bdev for internal roots

   - minor memory leak in ref-verify

   - refuse invalid combinations of compression and NOCOW file flags

   - lockdep fixes, updating the device locks

   - remove obsolete fallback logic for block group profile adjustments
     when switching from 1 to more devices, causing allocation of
     unwanted block groups

  Other cleanups, refactoring, simplifications:

   - conversions from struct inode to struct btrfs_inode in internal
     functions

   - removal of unused struct members"

* tag 'for-5.9-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (151 commits)
  btrfs: do not set the full sync flag on the inode during page release
  btrfs: release old extent maps during page release
  btrfs: fix race between page release and a fast fsync
  btrfs: open-code remount flag setting in btrfs_remount
  btrfs: if we're restriping, use the target restripe profile
  btrfs: don't adjust bg flags and use default allocation profiles
  btrfs: fix lockdep splat from btrfs_dump_space_info
  btrfs: move the chunk_mutex in btrfs_read_chunk_tree
  btrfs: open device without device_list_mutex
  btrfs: sysfs: use NOFS for device creation
  btrfs: return EROFS for BTRFS_FS_STATE_ERROR cases
  btrfs: document special case error codes for fs errors
  btrfs: don't WARN if we abort a transaction with EROFS
  btrfs: reduce contention on log trees when logging checksums
  btrfs: remove done label in writepage_delalloc
  btrfs: add comments for btrfs_reserve_flush_enum
  btrfs: relocation: review the call sites which can be interrupted by signal
  btrfs: avoid possible signal interruption of btrfs_drop_snapshot() on relocation tree
  btrfs: relocation: allow signal to cancel balance
  btrfs: raid56: remove out label in __raid56_parity_recover
  ...

3 files changed, 98 insertions, 64 deletions

diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 360b0f9d2220..863335ecb7e8 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -31,13 +31,6 @@ struct extent_io_tree;
 struct prelim_ref;
 struct btrfs_space_info;
 
-TRACE_DEFINE_ENUM(FLUSH_DELAYED_ITEMS_NR);
-TRACE_DEFINE_ENUM(FLUSH_DELAYED_ITEMS);
-TRACE_DEFINE_ENUM(FLUSH_DELALLOC);
-TRACE_DEFINE_ENUM(FLUSH_DELALLOC_WAIT);
-TRACE_DEFINE_ENUM(ALLOC_CHUNK);
-TRACE_DEFINE_ENUM(COMMIT_TRANS);
-
 #define show_ref_type(type)						\
 	__print_symbolic(type,						\
 		{ BTRFS_TREE_BLOCK_REF_KEY, 	"TREE_BLOCK_REF" },	\
@@ -67,30 +60,72 @@ TRACE_DEFINE_ENUM(COMMIT_TRANS);
 	      (obj >= BTRFS_ROOT_TREE_OBJECTID &&			\
 	       obj <= BTRFS_QUOTA_TREE_OBJECTID)) ? __show_root_type(obj) : "-"
 
-#define show_fi_type(type)						\
-	__print_symbolic(type,						\
-		 { BTRFS_FILE_EXTENT_INLINE,	"INLINE" },		\
-		 { BTRFS_FILE_EXTENT_REG,	"REG"	 },		\
-		 { BTRFS_FILE_EXTENT_PREALLOC,	"PREALLOC"})
+#define FLUSH_ACTIONS								\
+	EM( BTRFS_RESERVE_NO_FLUSH,		"BTRFS_RESERVE_NO_FLUSH")	\
+	EM( BTRFS_RESERVE_FLUSH_LIMIT,		"BTRFS_RESERVE_FLUSH_LIMIT")	\
+	EM( BTRFS_RESERVE_FLUSH_ALL,		"BTRFS_RESERVE_FLUSH_ALL")	\
+	EMe(BTRFS_RESERVE_FLUSH_ALL_STEAL,	"BTRFS_RESERVE_FLUSH_ALL_STEAL")
+
+#define FI_TYPES							\
+	EM( BTRFS_FILE_EXTENT_INLINE,		"INLINE")		\
+	EM( BTRFS_FILE_EXTENT_REG,		"REG")			\
+	EMe(BTRFS_FILE_EXTENT_PREALLOC,		"PREALLOC")
+
+#define QGROUP_RSV_TYPES						\
+	EM( BTRFS_QGROUP_RSV_DATA,		"DATA")			\
+	EM( BTRFS_QGROUP_RSV_META_PERTRANS,	"META_PERTRANS")	\
+	EMe(BTRFS_QGROUP_RSV_META_PREALLOC,	"META_PREALLOC")
+
+#define IO_TREE_OWNER						    \
+	EM( IO_TREE_FS_PINNED_EXTENTS, 	  "PINNED_EXTENTS")	    \
+	EM( IO_TREE_FS_EXCLUDED_EXTENTS,  "EXCLUDED_EXTENTS")	    \
+	EM( IO_TREE_INODE_IO,		  "INODE_IO")		    \
+	EM( IO_TREE_INODE_IO_FAILURE,	  "INODE_IO_FAILURE")	    \
+	EM( IO_TREE_RELOC_BLOCKS,	  "RELOC_BLOCKS")	    \
+	EM( IO_TREE_TRANS_DIRTY_PAGES,	  "TRANS_DIRTY_PAGES")      \
+	EM( IO_TREE_ROOT_DIRTY_LOG_PAGES, "ROOT_DIRTY_LOG_PAGES")   \
+	EM( IO_TREE_INODE_FILE_EXTENT,	  "INODE_FILE_EXTENT")      \
+	EM( IO_TREE_LOG_CSUM_RANGE,	  "LOG_CSUM_RANGE")         \
+	EMe(IO_TREE_SELFTEST,		  "SELFTEST")
+
+#define FLUSH_STATES							\
+	EM( FLUSH_DELAYED_ITEMS_NR,	"FLUSH_DELAYED_ITEMS_NR")	\
+	EM( FLUSH_DELAYED_ITEMS,	"FLUSH_DELAYED_ITEMS")		\
+	EM( FLUSH_DELALLOC,		"FLUSH_DELALLOC")		\
+	EM( FLUSH_DELALLOC_WAIT,	"FLUSH_DELALLOC_WAIT")		\
+	EM( FLUSH_DELAYED_REFS_NR,	"FLUSH_DELAYED_REFS_NR")	\
+	EM( FLUSH_DELAYED_REFS,		"FLUSH_ELAYED_REFS")		\
+	EM( ALLOC_CHUNK,		"ALLOC_CHUNK")			\
+	EM( ALLOC_CHUNK_FORCE,		"ALLOC_CHUNK_FORCE")		\
+	EM( RUN_DELAYED_IPUTS,		"RUN_DELAYED_IPUTS")		\
+	EMe(COMMIT_TRANS,		"COMMIT_TRANS")
+
+/*
+ * First define the enums in the above macros to be exported to userspace via
+ * TRACE_DEFINE_ENUM().
+ */
+
+#undef EM
+#undef EMe
+#define EM(a, b)	TRACE_DEFINE_ENUM(a);
+#define EMe(a, b)	TRACE_DEFINE_ENUM(a);
+
+FLUSH_ACTIONS
+FI_TYPES
+QGROUP_RSV_TYPES
+IO_TREE_OWNER
+FLUSH_STATES
+
+/*
+ * Now redefine the EM and EMe macros to map the enums to the strings that will
+ * be printed in the output
+ */
+
+#undef EM
+#undef EMe
+#define EM(a, b)        {a, b},
+#define EMe(a, b)       {a, b}
 
-#define show_qgroup_rsv_type(type)					\
-	__print_symbolic(type,						\
-		{ BTRFS_QGROUP_RSV_DATA,	  "DATA"	},	\
-		{ BTRFS_QGROUP_RSV_META_PERTRANS, "META_PERTRANS" },	\
-		{ BTRFS_QGROUP_RSV_META_PREALLOC, "META_PREALLOC" })
-
-#define show_extent_io_tree_owner(owner)				       \
-	__print_symbolic(owner,						       \
-		{ IO_TREE_FS_PINNED_EXTENTS, 	  "PINNED_EXTENTS" },	       \
-		{ IO_TREE_FS_EXCLUDED_EXTENTS,	  "EXCLUDED_EXTENTS" },	       \
-		{ IO_TREE_INODE_IO,		  "INODE_IO" },		       \
-		{ IO_TREE_INODE_IO_FAILURE,	  "INODE_IO_FAILURE" },	       \
-		{ IO_TREE_RELOC_BLOCKS,		  "RELOC_BLOCKS" },	       \
-		{ IO_TREE_TRANS_DIRTY_PAGES,	  "TRANS_DIRTY_PAGES" },       \
-		{ IO_TREE_ROOT_DIRTY_LOG_PAGES,	  "ROOT_DIRTY_LOG_PAGES" },    \
-		{ IO_TREE_INODE_FILE_EXTENT,	  "INODE_FILE_EXTENT" },       \
-		{ IO_TREE_LOG_CSUM_RANGE,	  "LOG_CSUM_RANGE" },          \
-		{ IO_TREE_SELFTEST,		  "SELFTEST" })
 
 #define BTRFS_GROUP_FLAGS	\
 	{ BTRFS_BLOCK_GROUP_DATA,	"DATA"},	\
@@ -380,7 +415,7 @@ DECLARE_EVENT_CLASS(btrfs__file_extent_item_regular,
 		__entry->disk_isize, __entry->extent_start,
 		__entry->extent_end, __entry->num_bytes, __entry->ram_bytes,
 		__entry->disk_bytenr, __entry->disk_num_bytes,
-		__entry->extent_offset, show_fi_type(__entry->extent_type),
+		__entry->extent_offset, __print_symbolic(__entry->extent_type, FI_TYPES),
 		__entry->compression)
 );
 
@@ -421,7 +456,7 @@ DECLARE_EVENT_CLASS(
 		"extent_type=%s compression=%u",
 		show_root_type(__entry->root_obj), __entry->ino, __entry->isize,
 		__entry->disk_isize, __entry->extent_start,
-		__entry->extent_end, show_fi_type(__entry->extent_type),
+		__entry->extent_end, __print_symbolic(__entry->extent_type, FI_TYPES),
 		__entry->compression)
 );
 
@@ -1042,12 +1077,6 @@ TRACE_EVENT(btrfs_space_reservation,
 			__entry->bytes)
 );
 
-#define show_flush_action(action)						\
-	__print_symbolic(action,						\
-		{ BTRFS_RESERVE_NO_FLUSH,	"BTRFS_RESERVE_NO_FLUSH"},	\
-		{ BTRFS_RESERVE_FLUSH_LIMIT,	"BTRFS_RESERVE_FLUSH_LIMIT"},	\
-		{ BTRFS_RESERVE_FLUSH_ALL,	"BTRFS_RESERVE_FLUSH_ALL"})
-
 TRACE_EVENT(btrfs_trigger_flush,
 
 	TP_PROTO(const struct btrfs_fs_info *fs_info, u64 flags, u64 bytes,
@@ -1071,25 +1100,13 @@ TRACE_EVENT(btrfs_trigger_flush,
 
 	TP_printk_btrfs("%s: flush=%d(%s) flags=%llu(%s) bytes=%llu",
 		  __get_str(reason), __entry->flush,
-		  show_flush_action(__entry->flush),
+		  __print_symbolic(__entry->flush, FLUSH_ACTIONS),
 		  __entry->flags,
 		  __print_flags((unsigned long)__entry->flags, "|",
 				BTRFS_GROUP_FLAGS),
 		  __entry->bytes)
 );
 
-#define show_flush_state(state)							\
-	__print_symbolic(state,							\
-		{ FLUSH_DELAYED_ITEMS_NR,	"FLUSH_DELAYED_ITEMS_NR"},	\
-		{ FLUSH_DELAYED_ITEMS,		"FLUSH_DELAYED_ITEMS"},		\
-		{ FLUSH_DELALLOC,		"FLUSH_DELALLOC"},		\
-		{ FLUSH_DELALLOC_WAIT,		"FLUSH_DELALLOC_WAIT"},		\
-		{ FLUSH_DELAYED_REFS_NR,	"FLUSH_DELAYED_REFS_NR"},	\
-		{ FLUSH_DELAYED_REFS,		"FLUSH_ELAYED_REFS"},		\
-		{ ALLOC_CHUNK,			"ALLOC_CHUNK"},			\
-		{ ALLOC_CHUNK_FORCE,		"ALLOC_CHUNK_FORCE"},		\
-		{ RUN_DELAYED_IPUTS,		"RUN_DELAYED_IPUTS"},		\
-		{ COMMIT_TRANS,			"COMMIT_TRANS"})
 
 TRACE_EVENT(btrfs_flush_space,
 
@@ -1114,7 +1131,7 @@ TRACE_EVENT(btrfs_flush_space,
 
 	TP_printk_btrfs("state=%d(%s) flags=%llu(%s) num_bytes=%llu ret=%d",
 		  __entry->state,
-		  show_flush_state(__entry->state),
+		  __print_symbolic(__entry->state, FLUSH_STATES),
 		  __entry->flags,
 		  __print_flags((unsigned long)__entry->flags, "|",
 				BTRFS_GROUP_FLAGS),
@@ -1690,7 +1707,7 @@ TRACE_EVENT(qgroup_update_reserve,
 	),
 
 	TP_printk_btrfs("qgid=%llu type=%s cur_reserved=%llu diff=%lld",
-		__entry->qgid, show_qgroup_rsv_type(__entry->type),
+		__entry->qgid, __print_symbolic(__entry->type, QGROUP_RSV_TYPES),
 		__entry->cur_reserved, __entry->diff)
 );
 
@@ -1714,7 +1731,7 @@ TRACE_EVENT(qgroup_meta_reserve,
 
 	TP_printk_btrfs("refroot=%llu(%s) type=%s diff=%lld",
 		show_root_type(__entry->refroot),
-		show_qgroup_rsv_type(__entry->type), __entry->diff)
+		__print_symbolic(__entry->type, QGROUP_RSV_TYPES), __entry->diff)
 );
 
 TRACE_EVENT(qgroup_meta_convert,
@@ -1735,8 +1752,8 @@ TRACE_EVENT(qgroup_meta_convert,
 
 	TP_printk_btrfs("refroot=%llu(%s) type=%s->%s diff=%lld",
 		show_root_type(__entry->refroot),
-		show_qgroup_rsv_type(BTRFS_QGROUP_RSV_META_PREALLOC),
-		show_qgroup_rsv_type(BTRFS_QGROUP_RSV_META_PERTRANS),
+		__print_symbolic(BTRFS_QGROUP_RSV_META_PREALLOC, QGROUP_RSV_TYPES),
+		__print_symbolic(BTRFS_QGROUP_RSV_META_PERTRANS, QGROUP_RSV_TYPES),
 		__entry->diff)
 );
 
@@ -1762,7 +1779,7 @@ TRACE_EVENT(qgroup_meta_free_all_pertrans,
 
 	TP_printk_btrfs("refroot=%llu(%s) type=%s diff=%lld",
 		show_root_type(__entry->refroot),
-		show_qgroup_rsv_type(__entry->type), __entry->diff)
+		__print_symbolic(__entry->type, QGROUP_RSV_TYPES), __entry->diff)
 );
 
 DECLARE_EVENT_CLASS(btrfs__prelim_ref,
@@ -1920,7 +1937,7 @@ TRACE_EVENT(btrfs_set_extent_bit,
 
 	TP_printk_btrfs(
 		"io_tree=%s ino=%llu root=%llu start=%llu len=%llu set_bits=%s",
-		show_extent_io_tree_owner(__entry->owner), __entry->ino,
+		__print_symbolic(__entry->owner, IO_TREE_OWNER), __entry->ino,
 		__entry->rootid, __entry->start, __entry->len,
 		__print_flags(__entry->set_bits, "|", EXTENT_FLAGS))
 );
@@ -1959,7 +1976,7 @@ TRACE_EVENT(btrfs_clear_extent_bit,
 
 	TP_printk_btrfs(
 		"io_tree=%s ino=%llu root=%llu start=%llu len=%llu clear_bits=%s",
-		show_extent_io_tree_owner(__entry->owner), __entry->ino,
+		__print_symbolic(__entry->owner, IO_TREE_OWNER), __entry->ino,
 		__entry->rootid, __entry->start, __entry->len,
 		__print_flags(__entry->clear_bits, "|", EXTENT_FLAGS))
 );
@@ -2000,7 +2017,7 @@ TRACE_EVENT(btrfs_convert_extent_bit,
 
 	TP_printk_btrfs(
 "io_tree=%s ino=%llu root=%llu start=%llu len=%llu set_bits=%s clear_bits=%s",
-		  show_extent_io_tree_owner(__entry->owner), __entry->ino,
+		  __print_symbolic(__entry->owner, IO_TREE_OWNER), __entry->ino,
 		  __entry->rootid, __entry->start, __entry->len,
 		  __print_flags(__entry->set_bits , "|", EXTENT_FLAGS),
 		  __print_flags(__entry->clear_bits, "|", EXTENT_FLAGS))
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index e6b6cb0f8bc6..2c39d15a2beb 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -243,6 +243,18 @@ struct btrfs_ioctl_dev_info_args {
 	__u8 path[BTRFS_DEVICE_PATH_NAME_MAX];	/* out */
 };
 
+/*
+ * Retrieve information about the filesystem
+ */
+
+/* Request information about checksum type and size */
+#define BTRFS_FS_INFO_FLAG_CSUM_INFO			(1 << 0)
+
+/* Request information about filesystem generation */
+#define BTRFS_FS_INFO_FLAG_GENERATION			(1 << 1)
+/* Request information about filesystem metadata UUID */
+#define BTRFS_FS_INFO_FLAG_METADATA_UUID		(1 << 2)
+
 struct btrfs_ioctl_fs_info_args {
 	__u64 max_id;				/* out */
 	__u64 num_devices;			/* out */
@@ -250,8 +262,13 @@ struct btrfs_ioctl_fs_info_args {
 	__u32 nodesize;				/* out */
 	__u32 sectorsize;			/* out */
 	__u32 clone_alignment;			/* out */
-	__u32 reserved32;
-	__u64 reserved[122];			/* pad to 1k */
+	/* See BTRFS_FS_INFO_FLAG_* */
+	__u16 csum_type;			/* out */
+	__u16 csum_size;			/* out */
+	__u64 flags;				/* in/out */
+	__u64 generation;			/* out */
+	__u8 metadata_uuid[BTRFS_FSID_SIZE];	/* out */
+	__u8 reserved[944];			/* pad to 1k */
 };
 
 /*
diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h
index a3f3975df0de..9ba64ca6b4ac 100644
--- a/include/uapi/linux/btrfs_tree.h
+++ b/include/uapi/linux/btrfs_tree.h
@@ -913,9 +913,9 @@ struct btrfs_free_space_info {
 #define BTRFS_FREE_SPACE_USING_BITMAPS (1ULL << 0)
 
 #define BTRFS_QGROUP_LEVEL_SHIFT		48
-static inline __u64 btrfs_qgroup_level(__u64 qgroupid)
+static inline __u16 btrfs_qgroup_level(__u64 qgroupid)
 {
-	return qgroupid >> BTRFS_QGROUP_LEVEL_SHIFT;
+	return (__u16)(qgroupid >> BTRFS_QGROUP_LEVEL_SHIFT);
 }
 
 /*