Merge tag 'for-6.17-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

f92b71ff · Linus Torvalds <[email protected]> · 2025-07-28 08:42:29 -07:00

Pull btrfs updates from David Sterba:
 "A number of usability and feature updates, scattered performance
  improvements and fixes. Highlight of the core changes is getting
  closer to enabling large folios (now behind a config option).

  User visible changes:

   - update defrag ioctl, add new flag to request no compression on
     existing extents

   - restrict writes to block devices after mount

   - in experimental config, enable large folios for data, almost
     complete but not widely tested

   - add stats tracking duration of critical section in transaction
     commit to /sys/fs/btrfs/FSID/commit_stats

  Performance improvements:

   - caching of lookup results of free space bitmap (20% runtime
     improvement on an empty file creation benchmark)

   - accessors to metadata (b-tree items) simplified and optimized,
     minor improvement in metadata-heavy workloads

   - readahead on compressed data improves sequential read

   - the xarray for extent buffers is indexed by denser keys, leading to
     better packing of the nodes (50-70% reduction of leaf nodes)

  Notable fixes:

   - stricter compression mount option parsing

   - send properly emits fallocate command for file holes when protocol
     v2 is used

   - fix overallocation of chunks with mount option 'ssd_spread', due to
     interaction with size classes not finding the right chunk
     (workaround: manual reclaim by 'usage' balance filter)

   - various quota enable/disable races with rescan, more verbose
     notifications about inconsistent state

   - populate otime in tree-log during log replay

   - handle ENOSPC when NOCOW file is used with mmap()

  Core:

   - large data folios enabled in experimental config

   - improved error handling, transaction abort call sites

   - in zoned mode, allocate reloc block group on mount to make sure
     there's always one available for zone reclaim under heavy load

   - rework device opening, they're always open as read-only and delayed
     until the super block is created, allowing the restricted writes
     after mount

   - preparatory work for adding blk_holder_ops, allowing device
     freeze/thaw in the future

  Cleanups, refactoring:

   - type and naming unifications (int/bool, return variables)

   - rb-tree helper refactoring and simplifications

   - reorder memory allocations to less critical places

   - RCU string (used for device name) refactoring and API removal

   - replace all remaining use of strcpy()"

* tag 'for-6.17-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (209 commits)
  btrfs: send: use fallocate for hole punching with send stream v2
  btrfs: unfold transaction aborts when writing dirty block groups
  btrfs: use saner variable type and name to indicate extrefs at add_inode_ref()
  btrfs: don't skip remaining extrefs if dir not found during log replay
  btrfs: don't ignore inode missing when replaying log tree
  btrfs: enable large data folios for data reloc inode
  btrfs: output more info when btrfs_subpage_assert() failed
  btrfs: reloc: unconditionally invalidate the page cache for each cluster
  btrfs: defrag: add flag to force no-compression
  btrfs: fix ssd_spread overallocation
  btrfs: zoned: requeue to unused block group list if zone finish failed
  btrfs: zoned: do not remove unwritten non-data block group
  btrfs: remove btrfs_clear_extent_bits()
  btrfs: use cached state when falling back from NOCoW write to CoW write
  btrfs: set EXTENT_NORESERVE before range unlock in btrfs_truncate_block()
  btrfs: don't print relocation messages from auto reclaim
  btrfs: remove redundant auto reclaim log message
  btrfs: make btrfs_check_nocow_lock() check more than one extent
  btrfs: assert we can NOCOW the range in btrfs_truncate_block()
  btrfs: update function comment for btrfs_check_nocow_lock()
  ...

Commit: f92b71ffca8c7e45e194aecc85e31bd11582f4d2
Parents: 038d61fd · 005b0a0c

Merge commit. Changes below are compared with the first parent: 038d61fd.

Changes

76 files changed · +2634 −2620

File	Status	Add	Del	Content
fs/btrfs/Kconfig	modified	+2	−0	View file
fs/btrfs/accessors.c	modified	+51	−111	View file
fs/btrfs/accessors.h	modified	+0	−37	View file
fs/btrfs/backref.c	modified	+21	−26	View file
fs/btrfs/backref.h	modified	+10	−13	View file
fs/btrfs/bio.c	modified	+9	−15	View file
fs/btrfs/block-group.c	modified	+48	−38	View file
fs/btrfs/block-group.h	modified	+5	−0	View file
fs/btrfs/btrfs_inode.h	modified	+13	−0	View file
fs/btrfs/compression.c	modified	+12	−12	View file
fs/btrfs/compression.h	modified	+5	−4	View file
fs/btrfs/ctree.c	modified	+94	−107	View file
fs/btrfs/ctree.h	modified	+17	−18	View file
fs/btrfs/defrag.c	modified	+39	−41	View file
fs/btrfs/delayed-inode.c	modified	+53	−53	View file
fs/btrfs/delayed-inode.h	modified	+3	−4	View file
fs/btrfs/delayed-ref.c	modified	+5	−5	View file
fs/btrfs/delayed-ref.h	modified	+3	−3	View file
fs/btrfs/dev-replace.c	modified	+9	−9	View file
fs/btrfs/dir-item.c	modified	+2	−2	View file
fs/btrfs/dir-item.h	modified	+1	−1	View file
fs/btrfs/disk-io.c	modified	+11	−10	View file
fs/btrfs/extent-io-tree.c	modified	+10	−10	View file
fs/btrfs/extent-io-tree.h	modified	+2	−7	View file
fs/btrfs/extent-tree.c	modified	+71	−63	View file
fs/btrfs/extent-tree.h	modified	+1	−1	View file
fs/btrfs/extent_io.c	modified	+109	−79	View file
fs/btrfs/extent_io.h	modified	+3	−3	View file
fs/btrfs/extent_map.c	modified	+3	−3	View file
fs/btrfs/fiemap.c	modified	+1	−1	View file
fs/btrfs/file-item.c	modified	+1	−1	View file
fs/btrfs/file.c	modified	+117	−61	View file
fs/btrfs/free-space-cache.c	modified	+4	−4	View file
fs/btrfs/free-space-tree.c	modified	+177	−186	View file
fs/btrfs/free-space-tree.h	modified	+26	−26	View file
fs/btrfs/fs.h	modified	+4	−9	View file
fs/btrfs/inode-item.c	modified	+10	−14	View file
fs/btrfs/inode-item.h	modified	+4	−7	View file
fs/btrfs/inode.c	modified	+190	−199	View file
fs/btrfs/ioctl.c	modified	+56	−77	View file
fs/btrfs/messages.h	modified	+17	−88	View file
fs/btrfs/misc.h	modified	+20	−18	View file
fs/btrfs/ordered-data.c	modified	+1	−1	View file
fs/btrfs/print-tree.c	modified	+2	−2	View file
fs/btrfs/qgroup.c	modified	+173	−189	View file
fs/btrfs/raid-stripe-tree.c	modified	+5	−2	View file
fs/btrfs/rcu-string.h	deleted	+0	−58	View before deletion
fs/btrfs/ref-verify.c	modified	+64	−82	View file
fs/btrfs/ref-verify.h	modified	+2	−2	View file
fs/btrfs/reflink.c	modified	+13	−11	View file
fs/btrfs/relocation.c	modified	+56	−84	View file
fs/btrfs/relocation.h	modified	+2	−1	View file
fs/btrfs/scrub.c	modified	+13	−13	View file
fs/btrfs/send.c	modified	+37	−10	View file
fs/btrfs/space-info.c	modified	+7	−7	View file
fs/btrfs/space-info.h	modified	+1	−2	View file
fs/btrfs/subpage.c	modified	+121	−126	View file
fs/btrfs/subpage.h	modified	+35	−24	View file
fs/btrfs/super.c	modified	+154	−135	View file
fs/btrfs/sysfs.c	modified	+42	−36	View file
fs/btrfs/tests/extent-io-tests.c	modified	+14	−14	View file
fs/btrfs/tests/free-space-tree-tests.c	modified	+45	−48	View file
fs/btrfs/tests/inode-tests.c	modified	+12	−12	View file
fs/btrfs/transaction.c	modified	+25	−23	View file
fs/btrfs/tree-checker.c	modified	+6	−6	View file
fs/btrfs/tree-log.c	modified	+273	−210	View file
fs/btrfs/tree-mod-log.c	modified	+59	−22	View file
fs/btrfs/ulist.c	modified	+29	−30	View file
fs/btrfs/volumes.c	modified	+71	−61	View file
fs/btrfs/volumes.h	modified	+31	−7	View file
fs/btrfs/xattr.c	modified	+5	−4	View file
fs/btrfs/zoned.c	modified	+87	−28	View file
fs/btrfs/zoned.h	modified	+3	−0	View file
fs/btrfs/zstd.c	modified	+1	−2	View file
include/trace/events/btrfs.h	modified	+3	−2	View file
include/uapi/linux/btrfs.h	modified	+3	−0	View file

Only the first 600 diff lines are shown. Download the complete patch.

fs/btrfs/Kconfig

View file

diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index c352f3a..ea95c90 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -114,6 +114,8 @@ config BTRFS_EXPERIMENTAL
 
 	  - extent tree v2 - complex rework of extent tracking
 
+	  - large folio support
+
 	  If unsure, say N.
 
 config BTRFS_FS_REF_VERIFY

fs/btrfs/accessors.c

View file

diff --git a/fs/btrfs/accessors.c b/fs/btrfs/accessors.c
index e371651..861c7d9 100644
--- a/fs/btrfs/accessors.c
+++ b/fs/btrfs/accessors.c
@@ -9,27 +9,24 @@
 #include "fs.h"
 #include "accessors.h"
 
-static bool check_setget_bounds(const struct extent_buffer *eb,
-				const void *ptr, unsigned off, int size)
+static void __cold report_setget_bounds(const struct extent_buffer *eb,
+					const void *ptr, unsigned off, int size)
 {
-	const unsigned long member_offset = (unsigned long)ptr + off;
+	unsigned long member_offset = (unsigned long)ptr + off;
 
-	if (unlikely(member_offset + size > eb->len)) {
-		btrfs_warn(eb->fs_info,
-		"bad eb member %s: ptr 0x%lx start %llu member offset %lu size %d",
-			(member_offset > eb->len ? "start" : "end"),
-			(unsigned long)ptr, eb->start, member_offset, size);
-		return false;
-	}
-
-	return true;
+	btrfs_warn(eb->fs_info,
+		   "bad eb member %s: ptr 0x%lx start %llu member offset %lu size %d",
+		   (member_offset > eb->len ? "start" : "end"),
+		   (unsigned long)ptr, eb->start, member_offset, size);
 }
 
-void btrfs_init_map_token(struct btrfs_map_token *token, struct extent_buffer *eb)
+/* Copy bytes from @src1 and @src2 to @dest. */
+static __always_inline void memcpy_split_src(char *dest, const char *src1,
+					     const char *src2, const size_t len1,
+					     const size_t total)
 {
-	token->eb = eb;
-	token->kaddr = folio_address(eb->folios[0]);
-	token->offset = 0;
+	memcpy(dest, src1, len1);
+	memcpy(dest + len1, src2, total - len1);
 }
 
 /*
@@ -41,11 +38,6 @@ void btrfs_init_map_token(struct btrfs_map_token *token, struct extent_buffer *e
  * - btrfs_set_8 (for 8/16/32/64)
  * - btrfs_get_8 (for 8/16/32/64)
  *
- * Generic helpers with a token (cached address of the most recently accessed
- * page):
- * - btrfs_set_token_8 (for 8/16/32/64)
- * - btrfs_get_token_8 (for 8/16/32/64)
- *
  * The set/get functions handle data spanning two pages transparently, in case
  * metadata block size is larger than page.  Every pointer to metadata items is
  * an offset into the extent buffer page array, cast to a specific type.  This
@@ -57,118 +49,66 @@ void btrfs_init_map_token(struct btrfs_map_token *token, struct extent_buffer *e
  */
 
 #define DEFINE_BTRFS_SETGET_BITS(bits)					\
-u##bits btrfs_get_token_##bits(struct btrfs_map_token *token,		\
-			       const void *ptr, unsigned long off)	\
-{									\
-	const unsigned long member_offset = (unsigned long)ptr + off;	\
-	const unsigned long idx = get_eb_folio_index(token->eb, member_offset); \
-	const unsigned long oil = get_eb_offset_in_folio(token->eb,	\
-							 member_offset);\
-	const int unit_size = token->eb->folio_size;			\
-	const int unit_shift = token->eb->folio_shift;			\
-	const int size = sizeof(u##bits);				\
-	u8 lebytes[sizeof(u##bits)];					\
-	const int part = unit_size - oil;				\
-									\
-	ASSERT(token);							\
-	ASSERT(token->kaddr);						\
-	ASSERT(check_setget_bounds(token->eb, ptr, off, size));		\
-	if (token->offset <= member_offset &&				\
-	    member_offset + size <= token->offset + unit_size) {	\
-		return get_unaligned_le##bits(token->kaddr + oil);	\
-	}								\
-	token->kaddr = folio_address(token->eb->folios[idx]);		\
-	token->offset = idx << unit_shift;				\
-	if (INLINE_EXTENT_BUFFER_PAGES == 1 || oil + size <= unit_size) \
-		return get_unaligned_le##bits(token->kaddr + oil);	\
-									\
-	memcpy(lebytes, token->kaddr + oil, part);			\
-	token->kaddr = folio_address(token->eb->folios[idx + 1]);	\
-	token->offset = (idx + 1) << unit_shift;			\
-	memcpy(lebytes + part, token->kaddr, size - part);		\
-	return get_unaligned_le##bits(lebytes);				\
-}									\
 u##bits btrfs_get_##bits(const struct extent_buffer *eb,		\
 			 const void *ptr, unsigned long off)		\
 {									\
 	const unsigned long member_offset = (unsigned long)ptr + off;	\
 	const unsigned long idx = get_eb_folio_index(eb, member_offset);\
-	const unsigned long oil = get_eb_offset_in_folio(eb,		\
-							 member_offset);\
-	const int unit_size = eb->folio_size;				\
-	char *kaddr = folio_address(eb->folios[idx]);			\
-	const int size = sizeof(u##bits);				\
-	const int part = unit_size - oil;				\
-	u8 lebytes[sizeof(u##bits)];					\
-									\
-	ASSERT(check_setget_bounds(eb, ptr, off, size));		\
-	if (INLINE_EXTENT_BUFFER_PAGES == 1 || oil + size <= unit_size)	\
-		return get_unaligned_le##bits(kaddr + oil);		\
-									\
-	memcpy(lebytes, kaddr + oil, part);				\
-	kaddr = folio_address(eb->folios[idx + 1]);			\
-	memcpy(lebytes + part, kaddr, size - part);			\
-	return get_unaligned_le##bits(lebytes);				\
-}									\
-void btrfs_set_token_##bits(struct btrfs_map_token *token,		\
-			    const void *ptr, unsigned long off,		\
-			    u##bits val)				\
-{									\
-	const unsigned long member_offset = (unsigned long)ptr + off;	\
-	const unsigned long idx = get_eb_folio_index(token->eb, member_offset); \
-	const unsigned long oil = get_eb_offset_in_folio(token->eb,	\
+	const unsigned long oif = get_eb_offset_in_folio(eb,		\
 							 member_offset);\
-	const int unit_size = token->eb->folio_size;			\
-	const int unit_shift = token->eb->folio_shift;			\
-	const int size = sizeof(u##bits);				\
+	char *kaddr = folio_address(eb->folios[idx]) + oif;		\
+	const int part = eb->folio_size - oif;				\
 	u8 lebytes[sizeof(u##bits)];					\
-	const int part = unit_size - oil;				\
 									\
-	ASSERT(token);							\
-	ASSERT(token->kaddr);						\
-	ASSERT(check_setget_bounds(token->eb, ptr, off, size));		\
-	if (token->offset <= member_offset &&				\
-	    member_offset + size <= token->offset + unit_size) {	\
-		put_unaligned_le##bits(val, token->kaddr + oil);	\
-		return;							\
+	if (unlikely(member_offset + sizeof(u##bits) > eb->len)) {	\
+		report_setget_bounds(eb, ptr, off, sizeof(u##bits));	\
+		return 0;						\
 	}								\
-	token->kaddr = folio_address(token->eb->folios[idx]);		\
-	token->offset = idx << unit_shift;				\
-	if (INLINE_EXTENT_BUFFER_PAGES == 1 ||				\
-	    oil + size <= unit_size) {					\
-		put_unaligned_le##bits(val, token->kaddr + oil);	\
-		return;							\
+	if (INLINE_EXTENT_BUFFER_PAGES == 1 || sizeof(u##bits) == 1 ||	\
+	    likely(sizeof(u##bits) <= part))				\
+		return get_unaligned_le##bits(kaddr);			\
+									\
+	if (sizeof(u##bits) == 2) {					\
+		lebytes[0] = *kaddr;					\
+		kaddr = folio_address(eb->folios[idx + 1]);		\
+		lebytes[1] = *kaddr;					\
+	} else {							\
+		memcpy_split_src(lebytes, kaddr,			\
+				 folio_address(eb->folios[idx + 1]),	\
+				 part, sizeof(u##bits));		\
 	}								\
-	put_unaligned_le##bits(val, lebytes);				\
-	memcpy(token->kaddr + oil, lebytes, part);			\
-	token->kaddr = folio_address(token->eb->folios[idx + 1]);	\
-	token->offset = (idx + 1) << unit_shift;			\
-	memcpy(token->kaddr, lebytes + part, size - part);		\
+	return get_unaligned_le##bits(lebytes);				\
 }									\
 void btrfs_set_##bits(const struct extent_buffer *eb, void *ptr,	\
 		      unsigned long off, u##bits val)			\
 {									\
 	const unsigned long member_offset = (unsigned long)ptr + off;	\
 	const unsigned long idx = get_eb_folio_index(eb, member_offset);\
-	const unsigned long oil = get_eb_offset_in_folio(eb,		\
+	const unsigned long oif = get_eb_offset_in_folio(eb,		\
 							 member_offset);\
-	const int unit_size = eb->folio_size;				\
-	char *kaddr = folio_address(eb->folios[idx]);			\
-	const int size = sizeof(u##bits);				\
-	const int part = unit_size - oil;				\
+	char *kaddr = folio_address(eb->folios[idx]) + oif;		\
+	const int part = eb->folio_size - oif;				\
 	u8 lebytes[sizeof(u##bits)];					\
 									\
-	ASSERT(check_setget_bounds(eb, ptr, off, size));		\
-	if (INLINE_EXTENT_BUFFER_PAGES == 1 ||				\
-	    oil + size <= unit_size) {					\
-		put_unaligned_le##bits(val, kaddr + oil);		\
+	if (unlikely(member_offset + sizeof(u##bits) > eb->len)) {	\
+		report_setget_bounds(eb, ptr, off, sizeof(u##bits));	\
+		return;							\
+	}								\
+	if (INLINE_EXTENT_BUFFER_PAGES == 1 || sizeof(u##bits) == 1 ||	\
+	    likely(sizeof(u##bits) <= part)) {				\
+		put_unaligned_le##bits(val, kaddr);			\
 		return;							\
 	}								\
-									\
 	put_unaligned_le##bits(val, lebytes);				\
-	memcpy(kaddr + oil, lebytes, part);				\
-	kaddr = folio_address(eb->folios[idx + 1]);			\
-	memcpy(kaddr, lebytes + part, size - part);			\
+	if (sizeof(u##bits) == 2) {					\
+		*kaddr = lebytes[0];					\
+		kaddr = folio_address(eb->folios[idx + 1]);		\
+		*kaddr = lebytes[1];					\
+	} else {							\
+		memcpy(kaddr, lebytes, part);				\
+		kaddr = folio_address(eb->folios[idx + 1]);		\
+		memcpy(kaddr, lebytes + part, sizeof(u##bits) - part);	\
+	}								\
 }
 
 DEFINE_BTRFS_SETGET_BITS(8)

fs/btrfs/accessors.h

View file

diff --git a/fs/btrfs/accessors.h b/fs/btrfs/accessors.h
index 15ea634..99b3ced 100644
--- a/fs/btrfs/accessors.h
+++ b/fs/btrfs/accessors.h
@@ -16,14 +16,6 @@
 
 struct extent_buffer;
 
-struct btrfs_map_token {
-	struct extent_buffer *eb;
-	char *kaddr;
-	unsigned long offset;
-};
-
-void btrfs_init_map_token(struct btrfs_map_token *token, struct extent_buffer *eb);
-
 /*
  * Some macros to generate set/get functions for the struct fields.  This
  * assumes there is a lefoo_to_cpu for every type, so lets make a simple one
@@ -56,11 +48,6 @@ static inline void put_unaligned_le8(u8 val, void *p)
 			    sizeof_field(type, member)))
 
 #define DECLARE_BTRFS_SETGET_BITS(bits)					\
-u##bits btrfs_get_token_##bits(struct btrfs_map_token *token,		\
-			       const void *ptr, unsigned long off);	\
-void btrfs_set_token_##bits(struct btrfs_map_token *token,		\
-			    const void *ptr, unsigned long off,		\
-			    u##bits val);				\
 u##bits btrfs_get_##bits(const struct extent_buffer *eb,		\
 			 const void *ptr, unsigned long off);		\
 void btrfs_set_##bits(const struct extent_buffer *eb, void *ptr,	\
@@ -83,18 +70,6 @@ static inline void btrfs_set_##name(const struct extent_buffer *eb, type *s, \
 {									\
 	static_assert(sizeof(u##bits) == sizeof_field(type, member));	\
 	btrfs_set_##bits(eb, s, offsetof(type, member), val);		\
-}									\
-static inline u##bits btrfs_token_##name(struct btrfs_map_token *token,	\
-					 const type *s)			\
-{									\
-	static_assert(sizeof(u##bits) == sizeof_field(type, member));	\
-	return btrfs_get_token_##bits(token, s, offsetof(type, member));\
-}									\
-static inline void btrfs_set_token_##name(struct btrfs_map_token *token,\
-					  type *s, u##bits val)		\
-{									\
-	static_assert(sizeof(u##bits) == sizeof_field(type, member));	\
-	btrfs_set_token_##bits(token, s, offsetof(type, member), val);	\
 }
 
 #define BTRFS_SETGET_HEADER_FUNCS(name, type, member, bits)		\
@@ -479,18 +454,6 @@ static inline void btrfs_set_item_##member(const struct extent_buffer *eb,	\
 					   int slot, u32 val)			\
 {										\
 	btrfs_set_raw_item_##member(eb, btrfs_item_nr(eb, slot), val);		\
-}										\
-static inline u32 btrfs_token_item_##member(struct btrfs_map_token *token,	\
-					    int slot)				\
-{										\
-	struct btrfs_item *item = btrfs_item_nr(token->eb, slot);		\
-	return btrfs_token_raw_item_##member(token, item);			\
-}										\
-static inline void btrfs_set_token_item_##member(struct btrfs_map_token *token,	\
-						 int slot, u32 val)		\
-{										\
-	struct btrfs_item *item = btrfs_item_nr(token->eb, slot);		\
-	btrfs_set_token_raw_item_##member(token, item, val);			\
 }
 
 BTRFS_ITEM_SETGET_FUNCS(offset)

fs/btrfs/backref.c

View file

diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index ed497f5..6a450be 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -733,7 +733,6 @@ static int resolve_indirect_refs(struct btrfs_backref_walk_ctx *ctx,
 				 struct preftrees *preftrees,
 				 struct share_check *sc)
 {
-	int err;
 	int ret = 0;
 	struct ulist *parents;
 	struct ulist_node *node;
@@ -752,6 +751,7 @@ static int resolve_indirect_refs(struct btrfs_backref_walk_ctx *ctx,
 	 */
 	while ((rnode = rb_first_cached(&preftrees->indirect.root))) {
 		struct prelim_ref *ref;
+		int ret2;
 
 		ref = rb_entry(rnode, struct prelim_ref, rbnode);
 		if (WARN(ref->parent,
@@ -773,18 +773,18 @@ static int resolve_indirect_refs(struct btrfs_backref_walk_ctx *ctx,
 			ret = BACKREF_FOUND_SHARED;
 			goto out;
 		}
-		err = resolve_indirect_ref(ctx, path, preftrees, ref, parents);
+		ret2 = resolve_indirect_ref(ctx, path, preftrees, ref, parents);
 		/*
 		 * we can only tolerate ENOENT,otherwise,we should catch error
 		 * and return directly.
 		 */
-		if (err == -ENOENT) {
+		if (ret2 == -ENOENT) {
 			prelim_ref_insert(ctx->fs_info, &preftrees->direct, ref,
 					  NULL);
 			continue;
-		} else if (err) {
+		} else if (ret2) {
 			free_pref(ref);
-			ret = err;
+			ret = ret2;
 			goto out;
 		}
 
@@ -2201,7 +2201,6 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
 	int ret;
 	u64 flags;
 	u64 size = 0;
-	u32 item_size;
 	const struct extent_buffer *eb;
 	struct btrfs_extent_item *ei;
 	struct btrfs_key key;
@@ -2244,7 +2243,6 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
 	}
 
 	eb = path->nodes[0];
-	item_size = btrfs_item_size(eb, path->slots[0]);
 
 	ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item);
 	flags = btrfs_extent_flags(eb, ei);
@@ -2252,7 +2250,7 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
 	btrfs_debug(fs_info,
 		"logical %llu is at position %llu within the extent (%llu EXTENT_ITEM %llu) flags %#llx size %u",
 		 logical, logical - found_key->objectid, found_key->objectid,
-		 found_key->offset, flags, item_size);
+		 found_key->offset, flags, btrfs_item_size(eb, path->slots[0]));
 
 	WARN_ON(!flags_ret);
 	if (flags_ret) {
@@ -2548,17 +2546,20 @@ static int build_ino_list(u64 inum, u64 offset, u64 num_bytes, u64 root, void *c
 }
 
 int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info,
-				struct btrfs_path *path,
 				void *ctx, bool ignore_offset)
 {
 	struct btrfs_backref_walk_ctx walk_ctx = { 0 };
 	int ret;
 	u64 flags = 0;
 	struct btrfs_key found_key;
-	int search_commit_root = path->search_commit_root;
+	struct btrfs_path *path;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
 
 	ret = extent_from_logical(fs_info, logical, path, &found_key, &flags);
-	btrfs_release_path(path);
+	btrfs_free_path(path);
 	if (ret < 0)
 		return ret;
 	if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK)
@@ -2571,8 +2572,7 @@ int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info,
 		walk_ctx.extent_item_pos = logical - found_key.objectid;
 	walk_ctx.fs_info = fs_info;
 
-	return iterate_extent_inodes(&walk_ctx, search_commit_root,
-				     build_ino_list, ctx);
+	return iterate_extent_inodes(&walk_ctx, false, build_ino_list, ctx);
 }
 
 static int inode_to_path(u64 inum, u32 name_len, unsigned long name_off,
@@ -3161,18 +3161,14 @@ void btrfs_backref_release_cache(struct btrfs_backref_cache *cache)
 	ASSERT(!cache->nr_edges);
 }
 
-void btrfs_backref_link_edge(struct btrfs_backref_edge *edge,
-			     struct btrfs_backref_node *lower,
-			     struct btrfs_backref_node *upper,
-			     int link_which)
+static void btrfs_backref_link_edge(struct btrfs_backref_edge *edge,
+				    struct btrfs_backref_node *lower,
+				    struct btrfs_backref_node *upper)
 {
 	ASSERT(upper && lower && upper->level == lower->level + 1);
 	edge->node[LOWER] = lower;
 	edge->node[UPPER] = upper;
-	if (link_which & LINK_LOWER)
-		list_add_tail(&edge->list[LOWER], &lower->upper);
-	if (link_which & LINK_UPPER)
-		list_add_tail(&edge->list[UPPER], &upper->lower);
+	list_add_tail(&edge->list[LOWER], &lower->upper);
 }
 /*
  * Handle direct tree backref
@@ -3242,7 +3238,7 @@ static int handle_direct_tree_backref(struct btrfs_backref_cache *cache,
 		ASSERT(upper->checked);
 		INIT_LIST_HEAD(&edge->list[UPPER]);
 	}
-	btrfs_backref_link_edge(edge, cur, upper, LINK_LOWER);
+	btrfs_backref_link_edge(edge, cur, upper);
 	return 0;
 }
 
@@ -3412,7 +3408,7 @@ static int handle_indirect_tree_backref(struct btrfs_trans_handle *trans,
 			if (!upper->owner)
 				upper->owner = btrfs_header_owner(eb);
 		}
-		btrfs_backref_link_edge(edge, lower, upper, LINK_LOWER);
+		btrfs_backref_link_edge(edge, lower, upper);
 
 		if (rb_node) {
 			btrfs_put_root(root);
@@ -3570,7 +3566,7 @@ int btrfs_backref_finish_upper_links(struct btrfs_backref_cache *cache,
 
 	ASSERT(start->checked);
 
-	rb_node = rb_simple_insert(&cache->rb_root, start->bytenr, &start->rb_node);
+	rb_node = rb_simple_insert(&cache->rb_root, &start->simple_node);
 	if (rb_node)
 		btrfs_backref_panic(cache->fs_info, start->bytenr, -EEXIST);
 
@@ -3621,8 +3617,7 @@ int btrfs_backref_finish_upper_links(struct btrfs_backref_cache *cache,
 			return -EUCLEAN;
 		}
 
-		rb_node = rb_simple_insert(&cache->rb_root, upper->bytenr,
-					   &upper->rb_node);
+		rb_node = rb_simple_insert(&cache->rb_root, &upper->simple_node);
 		if (unlikely(rb_node)) {
 			btrfs_backref_panic(cache->fs_info, upper->bytenr, -EEXIST);
 			return -EUCLEAN;

fs/btrfs/backref.h

View file

diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h
index 9536371..34b0193 100644
--- a/fs/btrfs/backref.h
+++ b/fs/btrfs/backref.h
@@ -226,8 +226,7 @@ int iterate_extent_inodes(struct btrfs_backref_walk_ctx *ctx,
 			  iterate_extent_inodes_t *iterate, void *user_ctx);
 
 int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info,
-				struct btrfs_path *path, void *ctx,
-				bool ignore_offset);
+				void *ctx, bool ignore_offset);
 
 int paths_from_inode(u64 inum, struct inode_fs_paths *ipath);
 
@@ -313,10 +312,15 @@ int btrfs_backref_iter_next(struct btrfs_backref_iter *iter);
  * Represent a tree block in the backref cache
  */
 struct btrfs_backref_node {
-	struct {
-		struct rb_node rb_node;
-		u64 bytenr;
-	}; /* Use rb_simple_node for search/insert */
+	union{
+		/* Use rb_simple_node for search/insert */
+		struct {
+			struct rb_node rb_node;
+			u64 bytenr;
+		};
+
+		struct rb_simple_node simple_node;
+	};
 
 	/*
 	 * This is a sanity check, whenever we COW a block we will update
@@ -423,13 +427,6 @@ struct btrfs_backref_node *btrfs_backref_alloc_node(
 struct btrfs_backref_edge *btrfs_backref_alloc_edge(
 		struct btrfs_backref_cache *cache);
 
-#define		LINK_LOWER	(1U << 0)
-#define		LINK_UPPER	(1U << 1)
-
-void btrfs_backref_link_edge(struct btrfs_backref_edge *edge,
-			     struct btrfs_backref_node *lower,
-			     struct btrfs_backref_node *upper,
-			     int link_which);
 void btrfs_backref_free_node(struct btrfs_backref_cache *cache,
 			     struct btrfs_backref_node *node);
 void btrfs_backref_free_edge(struct btrfs_backref_cache *cache,

fs/btrfs/bio.c

View file

diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index f7d8958..50b5fc1 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -27,12 +27,12 @@ struct btrfs_failed_bio {
 };
 
 /* Is this a data path I/O that needs storage layer checksum and repair? */
-static inline bool is_data_bbio(struct btrfs_bio *bbio)
+static inline bool is_data_bbio(const struct btrfs_bio *bbio)
 {
 	return bbio->inode && is_data_inode(bbio->inode);
 }
 
-static bool bbio_has_ordered_extent(struct btrfs_bio *bbio)
+static bool bbio_has_ordered_extent(const struct btrfs_bio *bbio)
 {
 	return is_data_bbio(bbio) && btrfs_op(&bbio->bio) == BTRFS_MAP_WRITE;
 }
@@ -134,14 +134,14 @@ void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status)
 	}
 }
 
-static int next_repair_mirror(struct btrfs_failed_bio *fbio, int cur_mirror)
+static int next_repair_mirror(const struct btrfs_failed_bio *fbio, int cur_mirror)
 {
 	if (cur_mirror == fbio->num_copies)
 		return cur_mirror + 1 - fbio->num_copies;
 	return cur_mirror + 1;
 }
 
-static int prev_repair_mirror(struct btrfs_failed_bio *fbio, int cur_mirror)
+static int prev_repair_mirror(const struct btrfs_failed_bio *fbio, int cur_mirror)
 {
 	if (cur_mirror == 1)
 		return fbio->num_copies;
@@ -165,12 +165,6 @@ static void btrfs_end_repair_bio(struct btrfs_bio *repair_bbio,
 	struct bio_vec *bv = bio_first_bvec_all(&repair_bbio->bio);
 	int mirror = repair_bbio->mirror_num;
 
-	/*
-	 * We can only trigger this for data bio, which doesn't support larger
-	 * folios yet.
-	 */
-	ASSERT(folio_order(page_folio(bv->bv_page)) == 0);
-
 	if (repair_bbio->bio.bi_status ||
 	    !btrfs_data_csum_ok(repair_bbio, dev, 0, bv)) {
 		bio_reset(&repair_bbio->bio, NULL, REQ_OP_READ);
@@ -301,7 +295,7 @@ static void btrfs_check_read_bio(struct btrfs_bio *bbio, struct btrfs_device *de
 		btrfs_bio_end_io(bbio, bbio->bio.bi_status);
 }
 
-static void btrfs_log_dev_io_error(struct bio *bio, struct btrfs_device *dev)
+static void btrfs_log_dev_io_error(const struct bio *bio, struct btrfs_device *dev)
 {
 	if (!dev || !dev->bdev)
 		return;
@@ -316,8 +310,8 @@ static void btrfs_log_dev_io_error(struct bio *bio, struct btrfs_device *dev)
 		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_FLUSH_ERRS);
 }
 
-static struct workqueue_struct *btrfs_end_io_wq(struct btrfs_fs_info *fs_info,
-						struct bio *bio)
+static struct workqueue_struct *btrfs_end_io_wq(const struct btrfs_fs_info *fs_info,
+						const struct bio *bio)
 {
 	if (bio->bi_opf & REQ_META)
 		return fs_info->endio_meta_workers;
@@ -439,7 +433,7 @@ static void btrfs_submit_dev_bio(struct btrfs_device *dev, struct bio *bio)
 		ASSERT(btrfs_dev_is_sequential(dev, physical));
 		bio->bi_iter.bi_sector = zone_start >> SECTOR_SHIFT;
 	}
-	btrfs_debug_in_rcu(dev->fs_info,
+	btrfs_debug(dev->fs_info,
 	"%s: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u",
 		__func__, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_sector,
 		(unsigned long)dev->bdev->bd_dev, btrfs_dev_name(dev),
@@ -845,7 +839,7 @@ int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
 		goto out_bio_uninit;
 	}
 
-	btrfs_info_rl_in_rcu(fs_info,
+	btrfs_info_rl(fs_info,
 		"read error corrected: ino %llu off %llu (dev %s sector %llu)",
 			     ino, start, btrfs_dev_name(smap.dev),
 			     smap.physical >> SECTOR_SHIFT);

fs/btrfs/block-group.c

View file

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 5b0cb04..9bf282d 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -34,6 +34,19 @@ int btrfs_should_fragment_free_space(const struct btrfs_block_group *block_group
 }
 #endif

This diff is incomplete. Download the complete patch.