Drop KC_HAS_SET_ACL

RHEL7 was the only conditional user of this define, but since support for that is removed, these can be dropped. Signed-off-by: Auke Kok <auke.kok@versity.com>
Collapse scoutfs_rename2 into scoutfs_rename_common.
2026-06-09 21:22:36 +00:00 · 2026-06-08 11:53:16 -07:00 · 2026-06-08 11:27:46 -07:00 · 2026-06-08 11:27:33 -07:00 · 2026-06-05 09:49:45 -07:00 · 2026-06-05 09:49:45 -07:00
54 changed files with 1041 additions and 1454 deletions
@@ -1,6 +1,52 @@
 Versity ScoutFS Release Notes
 =============================

+---
+v1.32
+\
+*June 2, 2026*
+
+Fix writing POSIX ACLs over NFS mounts that export the scoutfs
+filesystem.
+
+Add support for kernels in the RHEL 9.8 minor release.
+
+Reduce unneeded block allocation when data\_prealloc\_contig\_only was
+set to 0. This will help achieve more efficient data space usage when
+writing small files.
+
+---
+v1.31
+\
+*May 5, 2026*
+
+Fix race between modifying quota rules and internal reading of the rules
+that tripped an assertion.
+
+Fix a bug that could skip merging totl items under specific heavy write
+loads.  This could lead to merged totl items incorrectly tracking the
+sum of all the contributing totl xattrs.
+
+Fix many small low risk bugs in error paths that were found with code
+analysis and testing.
+
+---
+v1.30
+\
+*Apr 21, 2026*
+
+Fix a problem reading the accumulated totals of contributing .totl.
+xattrs when log merging is in progress.  The problem would have readers
+of the totals calculate the sums incorrectly.
+
+Fix a problem updating quota rules.  There was a race where updates
+could be corrupted if they happened while a transaction was being
+written.
+
+Fix a problem deleting files with .indx. xattrs.  The internal indexing
+metadata wouldn't be properly deleted so the files would still claim to
+be present and visible in the index, though the file no longer existed.
+
 ---
 v1.29
 \
@@ -6,231 +6,6 @@

 ccflags-y += -include $(src)/kernelcompat.h

-#
-# v3.18-rc2-19-gb5ae6b15bd73
-# 
-# Folds d_materialise_unique into d_splice_alias. Note reversal
-# of arguments (Also note Documentation/filesystems/porting.rst)
-#
-ifneq (,$(shell grep 'd_materialise_unique' include/linux/dcache.h))
-ccflags-y += -DKC_D_MATERIALISE_UNIQUE=1
-endif
-
-#
-# RHEL extended the fop struct so to use it we have to set
-# a flag to indicate that the struct is large enough and
-# contains the pointer.
-#
-ifneq (,$(shell grep 'FMODE_KABI_ITERATE' include/linux/fs.h))
-ccflags-y += -DKC_FMODE_KABI_ITERATE
-endif
-
-#
-# v4.7-rc2-23-g0d4d717f2583
-#
-# Added user_ns argument to posix_acl_valid
-#
-ifneq (,$(shell grep 'posix_acl_valid.*user_namespace' include/linux/posix_acl.h))
-ccflags-y += -DKC_POSIX_ACL_VALID_USER_NS
-endif
-
-#
-# v5.3-12296-g6d2052d188d9
-#
-# The RBCOMPUTE function is now passed an extra flag, and should return a bool
-# to indicate whether the propagated callback should stop or not.
-#
-ifneq (,$(shell grep 'static inline bool RBNAME.*_compute_max' include/linux/rbtree_augmented.h))
-ccflags-y += -DKC_RB_TREE_AUGMENTED_COMPUTE_MAX
-endif
-
-#
-# v3.13-25-g37bc15392a23
-#
-# Renames posix_acl_create to __posix_acl_create and provide some
-# new interfaces for creating ACLs
-#
-ifneq (,$(shell grep '__posix_acl_create' include/linux/posix_acl.h))
-ccflags-y += -DKC___POSIX_ACL_CREATE
-endif
-
-#
-# v4.8-rc1-29-g31051c85b5e2
-#
-# inode_change_ok() removed - replace with setattr_prepare()
-# v5.11-rc4-7-g2f221d6f7b88 removes extern attribute
-#
-ifneq (,$(shell grep 'int setattr_prepare' include/linux/fs.h))
-ccflags-y += -DKC_SETATTR_PREPARE
-endif
-
-#
-# v4.15-rc3-4-gae5e165d855d
-#
-# linux/iversion.h needs to manually be included for code that
-# manipulates this field.
-#
-ifneq (,$(shell grep -s 'define _LINUX_IVERSION_H' include/linux/iversion.h))
-ccflags-y += -DKC_NEED_LINUX_IVERSION_H=1
-endif
-
-# v4.11-12447-g104b4e5139fe
-#
-# Renamed __percpu_counter_add to percpu_counter_add_batch to clarify
-# that the __ wasn't less safe, just took an extra parameter.
-#
-ifneq (,$(shell grep 'percpu_counter_add_batch' include/linux/percpu_counter.h))
-ccflags-y += -DKC_PERCPU_COUNTER_ADD_BATCH
-endif
-
-#
-# v4.11-4550-g7dea19f9ee63
-#
-# Introduced memalloc_nofs_{save,restore} preferred instead of _noio_.
-#
-ifneq (,$(shell grep 'memalloc_nofs_save' include/linux/sched/mm.h))
-ccflags-y += -DKC_MEMALLOC_NOFS_SAVE
-endif
-
-#
-# v4.7-12414-g1eff9d322a44
-#
-# Renamed bi_rw to bi_opf to force old code to catch up.  We use it as a
-# single switch between old and new bio structures.
-#
-ifneq (,$(shell grep 'bi_opf' include/linux/blk_types.h))
-ccflags-y += -DKC_BIO_BI_OPF
-endif
-
-#
-# v4.12-rc2-201-g4e4cbee93d56
-#
-# Moves to bi_status BLK_STS_ API instead of having a mix of error
-# end_io args or bi_error.
-#
-ifneq (,$(shell grep 'bi_status' include/linux/blk_types.h))
-ccflags-y += -DKC_BIO_BI_STATUS
-endif
-
-#
-# v3.11-8765-ga0b02131c5fc
-#
-# Remove the old ->shrink() API, ->{scan,count}_objects is preferred.
-#
-ifneq (,$(shell grep '(*shrink)' include/linux/shrinker.h))
-ccflags-y += -DKC_SHRINKER_SHRINK
-endif
-
-#
-# v3.19-4777-g6bec00352861
-#
-# backing_dev_info is removed from address_space. Instead we need to use
-# inode_to_bdi() inline from <backing-dev.h>.
-#
-ifneq (,$(shell grep 'struct backing_dev_info.*backing_dev_info' include/linux/fs.h))
-ccflags-y += -DKC_LINUX_BACKING_DEV_INFO=1
-endif
-
-#
-# v4.3-9290-ge409de992e3e
-#
-# xattr handlers are now passed a struct that contains `flags`
-#
-ifneq (,$(shell grep 'int...get..const struct xattr_handler.*struct dentry.*dentry,' include/linux/xattr.h))
-ccflags-y += -DKC_XATTR_STRUCT_XATTR_HANDLER=1
-endif
-
-#
-# v4.16-rc1-1-g9b2c45d479d0
-#
-# kernel_getsockname() and kernel_getpeername dropped addrlen arg
-#
-ifneq (,$(shell grep 'kernel_getsockname.*,$$' include/linux/net.h))
-ccflags-y += -DKC_KERNEL_GETSOCKNAME_ADDRLEN=1
-endif
-
-#
-# v4.1-rc1-410-geeb1bd5c40ed
-#
-# Adds a struct net parameter to sock_create_kern
-#
-ifneq (,$(shell grep 'sock_create_kern.*struct net' include/linux/net.h))
-ccflags-y += -DKC_SOCK_CREATE_KERN_NET=1
-endif
-
-#
-# v4.17-rc6-7-g95582b008388
-#
-# Kernel has current_time(inode) to uniformly retreive timespec in the right unit
-#
-ifneq (,$(shell grep 'struct timespec64 current_time' include/linux/fs.h))
-ccflags-y += -DKC_CURRENT_TIME_INODE=1
-endif
-
-#
-# v4.9-12228-g530e9b76ae8f
-#
-# register_cpu_notifier and family were all removed and to be
-# replaced with cpuhp_* API calls.
-#
-ifneq (,$(shell grep 'define register_hotcpu_notifier' include/linux/cpu.h))
-ccflags-y += -DKC_CPU_NOTIFIER
-endif
-
-#
-# v3.14-rc8-130-gccad2365668f
-#
-# generic_file_buffered_write is removed, backport it
-#
-ifneq (,$(shell grep 'extern ssize_t generic_file_buffered_write' include/linux/fs.h))
-ccflags-y += -DKC_GENERIC_FILE_BUFFERED_WRITE=1
-endif
-
-#
-# v5.7-438-g8151b4c8bee4
-#
-# struct address_space_operations switches away from .readpages to .readahead
-#
-# RHEL has backported this feature all the way to RHEL8, as part of RHEL_KABI,
-# which means we need to detect this very precisely
-#
-ifneq (,$(shell grep 'readahead.*struct readahead_control' include/linux/fs.h))
-ccflags-y += -DKC_FILE_AOPS_READAHEAD
-endif
-
-#
-# v4.0-rc7-1743-g8436318205b9
-#
-# .aio_read and .aio_write no longer exist. All reads and writes now use the
-# .read_iter and .write_iter methods, or must implement .read and .write (which
-# we don't).
-#
-ifneq (,$(shell grep 'ssize_t.*aio_read' include/linux/fs.h))
-ccflags-y += -DKC_LINUX_HAVE_FOP_AIO_READ=1
-endif
-
-#
-# rhel7 has a custom inode_operations_wrapper struct that is discarded
-# entirely in favor of upstream structure since rhel8.
-#
-ifneq (,$(shell grep 'void.*follow_link.*struct dentry' include/linux/fs.h))
-ccflags-y += -DKC_LINUX_HAVE_RHEL_IOPS_WRAPPER=1
-endif
-
-ifneq (,$(shell grep 'size_t.*ki_left;' include/linux/aio.h))
-ccflags-y += -DKC_LINUX_AIO_KI_LEFT=1
-endif
-
-#
-# v4.4-rc4-4-g98e9cb5711c6
-#
-# Introduces a new xattr_handler .name member that can be used to match the
-# entire field, instead of just a prefix. For these kernels, we must use
-# the new .name field instead.
-ifneq (,$(shell grep 'static inline const char .xattr_prefix' include/linux/xattr.h))
-ccflags-y += -DKC_XATTR_HANDLER_NAME=1
-endif
-
 #
 # v5.19-rc4-96-g342a72a33407
 #
@@ -334,14 +109,6 @@ ifneq (,$(shell grep 'int tcp_sock_set_keepintvl' include/linux/tcp.h))
 ccflags-y += -DKC_HAVE_TCP_SET_SOCKFN
 endif

-#
-# v4.16-rc3-13-ga84d1169164b
-#
-# Fixes y2038 issues with struct timeval.
-ifneq (,$(shell grep -s '^struct __kernel_old_timeval .' include/uapi/linux/time_types.h))
-ccflags-y += -DKC_KERNEL_OLD_TIMEVAL_STRUCT
-endif
-
 #
 # v5.19-rc4-52-ge33c267ab70d
 #
@@ -411,47 +178,6 @@ ifneq (,$(shell grep 'struct file.*bdev_file_open_by_path.const char.*path' incl
 ccflags-y += -DKC_BDEV_FILE_OPEN_BY_PATH
 endif

-# v4.0-rc7-1796-gfe0f07d08ee3
-#
-# direct-io changes modify inode_dio_done to now be called inode_dio_end
-ifneq (,$(shell grep 'void inode_dio_end.struct inode' include/linux/fs.h))
-ccflags-y += -DKC_INODE_DIO_END
-endif
-
-#
-# v5.0-6476-g3d3539018d2c
-#
-# page fault handlers return a bitmask vm_fault_t instead
-# Note: el8's header has a slightly modified prefix here
-ifneq (,$(shell grep 'typedef.*__bitwise unsigned.*int vm_fault_t' include/linux/mm_types.h))
-ccflags-y += -DKC_MM_VM_FAULT_T
-endif
-
-# v3.19-499-gd83a08db5ba6
-#
-# .remap pages becomes obsolete
-ifneq (,$(shell grep 'int ..remap_pages..struct vm_area_struct' include/linux/mm.h))
-ccflags-y += -DKC_MM_REMAP_PAGES
-endif
-
-#
-# v3.19-4742-g503c358cf192
-#
-# list_lru_shrink_count() and list_lru_shrink_walk() introduced
-#
-ifneq (,$(shell grep 'list_lru_shrink_count.*struct list_lru' include/linux/list_lru.h))
-ccflags-y += -DKC_LIST_LRU_SHRINK_COUNT_WALK
-endif
-
-#
-# v3.19-4757-g3f97b163207c
-#
-# lru_list_walk_cb lru arg added
-#
-ifneq (,$(shell grep 'struct list_head \*item, spinlock_t \*lock, void \*cb_arg' include/linux/list_lru.h))
-ccflags-y += -DKC_LIST_LRU_WALK_CB_ITEM_LOCK
-endif
-
 #
 # v6.7-rc4-153-g0a97c01cd20b
 #
@@ -470,15 +196,6 @@ ifneq (,$(shell grep 'struct list_lru_one \*list, spinlock_t \*lock, void \*cb_a
 ccflags-y += -DKC_LIST_LRU_WALK_CB_LIST_LOCK
 endif

-#
-# v5.1-rc4-273-ge9b98e162aa5
-#
-# introduce stack trace helpers
-#
-ifneq (,$(shell grep '^unsigned int stack_trace_save' include/linux/stacktrace.h))
-ccflags-y += -DKC_STACK_TRACE_SAVE
-endif
-
 #
 # v6.1-rc1-2-g138060ba92b3
 #
@@ -496,3 +213,12 @@ endif
 ifneq (,$(shell grep 'struct posix_acl.*get_inode_acl' include/linux/fs.h))
 ccflags-y += -DKC_GET_INODE_ACL
 endif
+
+#
+# v6.15-13744-g41cb08555c41
+#
+# from_timer renamed to timer_container_of.
+#
+ifneq (,$(shell grep 'define timer_container_of' include/linux/timer.h))
+ccflags-y += -DKC_TIMER_CONTAINER_OF
+endif
@@ -16,6 +16,7 @@
 #include <linux/xattr.h>
 #include <linux/posix_acl.h>
 #include <linux/posix_acl_xattr.h>
+#include <linux/iversion.h>

 #include "format.h"
 #include "super.h"
@@ -69,15 +70,6 @@ struct posix_acl *scoutfs_get_acl_locked(struct inode *inode, int type, struct s
 	char *name;
 	int ret;

-#ifndef KC___POSIX_ACL_CREATE
-	if (!IS_POSIXACL(inode))
-		return NULL;
-
-	acl = get_cached_acl(inode, type);
-	if (acl != ACL_NOT_CACHED)
-		return acl;
-#endif
-
 	ret = acl_xattr_name_len(type, &name, NULL);
 	if (ret < 0)
 		return ERR_PTR(ret);
@@ -123,11 +115,6 @@ struct posix_acl *scoutfs_get_acl(struct inode *inode, int type)
 		return ERR_PTR(-ECHILD);
 #endif

-#ifndef KC___POSIX_ACL_CREATE
-	if (!IS_POSIXACL(inode))
-		return NULL;
-#endif
-
 	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ, 0, inode, &lock);
 	if (ret < 0) {
 		acl = ERR_PTR(ret);
@@ -216,7 +203,8 @@ int scoutfs_set_acl(KC_VFS_NS_DEF
 {
 	struct inode *inode = dentry->d_inode;
 #else
-int scoutfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+int scoutfs_set_acl(KC_VFS_NS_DEF
+		    struct inode *inode, struct posix_acl *acl, int type)
 {
 #endif
 	struct super_block *sb = inode->i_sb;
@@ -239,17 +227,11 @@ int scoutfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	scoutfs_unlock(sb, lock, SCOUTFS_LOCK_WRITE);
 	return ret;
 }
-#ifdef KC_XATTR_STRUCT_XATTR_HANDLER
 int scoutfs_acl_get_xattr(const struct xattr_handler *handler, struct dentry *dentry,
 			  struct inode *inode, const char *name, void *value,
 			  size_t size)
 {
 	int type = handler->flags;
-#else
-int scoutfs_acl_get_xattr(struct dentry *dentry, const char *name, void *value, size_t size,
-			  int type)
-{
-#endif
 	struct posix_acl *acl;
 	int ret = 0;

@@ -272,7 +254,6 @@ int scoutfs_acl_get_xattr(struct dentry *dentry, const char *name, void *value,
 	return ret;
 }

-#ifdef KC_XATTR_STRUCT_XATTR_HANDLER
 int scoutfs_acl_set_xattr(const struct xattr_handler *handler,
 			  KC_VFS_NS_DEF
 			  struct dentry *dentry,
@@ -280,11 +261,6 @@ int scoutfs_acl_set_xattr(const struct xattr_handler *handler,
 			  size_t size, int flags)
 {
 	int type = handler->flags;
-#else
-int scoutfs_acl_set_xattr(struct dentry *dentry, const char *name, const void *value, size_t size,
-			  int flags, int type)
-{
-#endif
 	struct posix_acl *acl = NULL;
 	int ret;

@@ -300,7 +276,7 @@ int scoutfs_acl_set_xattr(struct dentry *dentry, const char *name, const void *v
 			return PTR_ERR(acl);

 		if (acl) {
-			ret = kc_posix_acl_valid(&init_user_ns, acl);
+			ret = posix_acl_valid(&init_user_ns, acl);
 			if (ret)
 				goto out;
 		}
@@ -309,7 +285,7 @@ int scoutfs_acl_set_xattr(struct dentry *dentry, const char *name, const void *v
 #ifdef KC_SET_ACL_DENTRY
 	ret = scoutfs_set_acl(KC_VFS_INIT_NS dentry, acl, type);
 #else
-	ret = scoutfs_set_acl(dentry->d_inode, acl, type);
+	ret = scoutfs_set_acl(KC_VFS_INIT_NS dentry->d_inode, acl, type);
 #endif
 out:
 	posix_acl_release(acl);
@@ -5,7 +5,8 @@
 int scoutfs_set_acl(KC_VFS_NS_DEF
 		    struct dentry *dentry, struct posix_acl *acl, int type);
 #else
-int scoutfs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+int scoutfs_set_acl(KC_VFS_NS_DEF
+		    struct inode *inode, struct posix_acl *acl, int type);
 #endif
 #ifdef KC_GET_INODE_ACL
 struct posix_acl *scoutfs_get_acl(struct inode *inode, int type, bool rcu);
@@ -15,7 +16,6 @@ struct posix_acl *scoutfs_get_acl(struct inode *inode, int type);
 struct posix_acl *scoutfs_get_acl_locked(struct inode *inode, int type, struct scoutfs_lock *lock);
 int scoutfs_set_acl_locked(struct inode *inode, struct posix_acl *acl, int type,
 			   struct scoutfs_lock *lock, struct list_head *ind_locks);
-#ifdef KC_XATTR_STRUCT_XATTR_HANDLER
 int scoutfs_acl_get_xattr(const struct xattr_handler *, struct dentry *dentry,
 			  struct inode *inode, const char *name, void *value,
 			  size_t size);
@@ -24,12 +24,6 @@ int scoutfs_acl_set_xattr(const struct xattr_handler *,
 			  struct dentry *dentry,
 			  struct inode *inode, const char *name, const void *value,
 			  size_t size, int flags);
-#else
-int scoutfs_acl_get_xattr(struct dentry *dentry, const char *name, void *value, size_t size,
-			  int type);
-int scoutfs_acl_set_xattr(struct dentry *dentry, const char *name, const void *value, size_t size,
-			  int flags, int type);
-#endif
 int scoutfs_acl_chmod_locked(struct inode *inode, struct iattr *attr,
 			     struct scoutfs_lock *lock, struct list_head *ind_locks);
 int scoutfs_init_acl_locked(struct inode *inode, struct inode *dir,
@@ -218,6 +218,7 @@ static void block_free_work(struct work_struct *work)

 	llist_for_each_entry_safe(bp, tmp, deleted, free_node) {
 		block_free(sb, bp);
+		cond_resched();
 	}
 }

@@ -443,13 +444,13 @@ static void block_end_io(struct super_block *sb, blk_opf_t opf,
 		wake_up(&binf->waitq);
 }

-static void KC_DECLARE_BIO_END_IO(block_bio_end_io, struct bio *bio)
+static void block_bio_end_io(struct bio *bio)
 {
 	struct block_private *bp = bio->bi_private;
 	struct super_block *sb = bp->sb;

 	TRACE_BLOCK(end_io, bp);
-	block_end_io(sb, kc_bio_get_opf(bio), bp, kc_bio_get_errno(bio));
+	block_end_io(sb, bio->bi_opf, bp, blk_status_to_errno(bio->bi_status));
 	bio_put(bio);
 }

@@ -467,9 +468,6 @@ static int block_submit_bio(struct super_block *sb, struct block_private *bp,
 	sector_t sector;
 	int ret = 0;

-	if (scoutfs_forcing_unmount(sb))
-		return -ENOLINK;
-
 	sector = bp->bl.blkno << (SCOUTFS_BLOCK_LG_SHIFT - 9);

 	WARN_ON_ONCE(bp->bl.blkno == U64_MAX);
@@ -480,6 +478,17 @@ static int block_submit_bio(struct super_block *sb, struct block_private *bp,
 	set_bit(BLOCK_BIT_IO_BUSY, &bp->bits);
 	block_get(bp);

+	/*
+	 * A second thread may already be waiting on this block's completion
+	 * after this thread won the race to submit the block.  We exit through
+	 * the block_end_io error path which sets BLOCK_BIT_ERROR and assures
+	 * that other callers in the waitq get woken up.
+	 */
+	if (scoutfs_forcing_unmount(sb)) {
+		ret = -ENOLINK;
+		goto end_io;
+	}
+
 	blk_start_plug(&plug);

 	for (off = 0; off < SCOUTFS_BLOCK_LG_SIZE; off += PAGE_SIZE) {
@@ -490,7 +499,7 @@ static int block_submit_bio(struct super_block *sb, struct block_private *bp,
 				break;
 			}

-			kc_bio_set_sector(bio, sector + (off >> 9));
+			bio->bi_iter.bi_sector = sector + (off >> 9);
 			bio->bi_end_io = block_bio_end_io;
 			bio->bi_private = bp;

@@ -507,16 +516,17 @@ static int block_submit_bio(struct super_block *sb, struct block_private *bp,
 			BUG();

 		if (!bio_add_page(bio, page, PAGE_SIZE, 0)) {
-			kc_submit_bio(bio);
+			submit_bio(bio);
 			bio = NULL;
 		}
 	}

 	if (bio)
-		kc_submit_bio(bio);
+		submit_bio(bio);

 	blk_finish_plug(&plug);

+end_io:
 	/* let racing end_io know we're done */
 	block_end_io(sb, opf, bp, ret);

@@ -1169,11 +1179,11 @@ struct sm_block_completion {
 	int err;
 };

-static void KC_DECLARE_BIO_END_IO(sm_block_bio_end_io, struct bio *bio)
+static void sm_block_bio_end_io(struct bio *bio)
 {
 	struct sm_block_completion *sbc = bio->bi_private;

-	sbc->err = kc_bio_get_errno(bio);
+	sbc->err = blk_status_to_errno(bio->bi_status);
 	complete(&sbc->comp);
 	bio_put(bio);
 }
@@ -1226,7 +1236,7 @@ static int sm_block_io(struct super_block *sb, struct block_device *bdev, blk_op
 		goto out;
 	}

-	kc_bio_set_sector(bio, blkno << (SCOUTFS_BLOCK_SM_SHIFT - 9));
+	bio->bi_iter.bi_sector = blkno << (SCOUTFS_BLOCK_SM_SHIFT - 9);
 	bio->bi_end_io = sm_block_bio_end_io;
 	bio->bi_private = &sbc;
 	bio_add_page(bio, page, SCOUTFS_BLOCK_SM_SIZE, 0);
@@ -1234,7 +1244,7 @@ static int sm_block_io(struct super_block *sb, struct block_device *bdev, blk_op
 	init_completion(&sbc.comp);
 	sbc.err = 0;

-	kc_submit_bio(bio);
+	submit_bio(bio);

 	wait_for_completion(&sbc.comp);
 	ret = sbc.err;
@@ -2183,6 +2183,8 @@ static int merge_read_item(struct super_block *sb, struct scoutfs_key *key, u64
 		if (ret > 0) {
 			if (ret == SCOUTFS_DELTA_COMBINED) {
 				scoutfs_inc_counter(sb, btree_merge_delta_combined);
+				if (seq > found->seq)
+					found->seq = seq;
 			} else if (ret == SCOUTFS_DELTA_COMBINED_NULL) {
 				scoutfs_inc_counter(sb, btree_merge_delta_null);
 				free_mitem(rng, found);
@@ -2486,6 +2488,14 @@ int scoutfs_btree_merge(struct super_block *sb,
 			mitem = next_mitem(mitem);
 			free_mitem(&rng, tmp);
 		}
+
+		if (mitem && walk_val_len == 0 &&
+		    !(walk_flags & (BTW_INSERT | BTW_DELETE)) &&
+		    scoutfs_trigger(sb, LOG_MERGE_FORCE_PARTIAL)) {
+			ret = -ERANGE;
+			*next_ret = mitem->key;
+			goto out;
+		}
 	}

 	ret = 0;
@@ -23,6 +23,7 @@
 #include <linux/fiemap.h>
 #include <linux/writeback.h>
 #include <linux/overflow.h>
+#include <linux/iversion.h>

 #include "format.h"
 #include "super.h"
@@ -422,6 +423,8 @@ static int alloc_block(struct super_block *sb, struct inode *inode,

 	mutex_lock(&datinf->mutex);

+	scoutfs_inode_get_onoff(inode, &online, &offline);
+
 	/* default to single allocation at the written block */
 	start = iblock;
 	count = 1;
@@ -444,7 +447,6 @@ static int alloc_block(struct super_block *sb, struct inode *inode,
 		 * the preallocation size to the number of online
 		 * blocks.
 		 */
-		scoutfs_inode_get_onoff(inode, &online, &offline);
 		if (iblock > 1 && iblock == online) {
 			ret = scoutfs_ext_next(sb, &data_ext_ops, &args,
 					       iblock, 1, &found);
@@ -486,6 +488,13 @@ static int alloc_block(struct super_block *sb, struct inode *inode,
 		/* trim count by next extent after iblock */
 		if (found.len && found.start > start && found.start < start + count)
 			count = (found.start - start);
+
+		/*
+		 * Ramp the aligned region size up proportionally with
+		 * the file's online block count rather than jumping to
+		 * the full prealloc size.
+		 */
+		count = max_t(u64, 1, min(count, online));
 	}

 	/* overall prealloc limit */
@@ -749,54 +758,6 @@ static int scoutfs_readpage(struct file *file, struct page *page)
 	return ret;
 }

-#ifndef KC_FILE_AOPS_READAHEAD
-/*
- * This is used for opportunistic read-ahead which can throw the pages
- * away if it needs to.  If the caller didn't deal with offline extents
- * then we drop those pages rather than trying to wait.  Whoever is
- * staging offline extents should be doing it in enormous chunks so that
- * read-ahead can ramp up within each staged region.  The check for
- * offline extents is cheap when the inode has no offline extents.
- */
-static int scoutfs_readpages(struct file *file, struct address_space *mapping,
-			     struct list_head *pages, unsigned nr_pages)
-{
-	struct inode *inode = file->f_inode;
-	struct super_block *sb = inode->i_sb;
-	struct scoutfs_lock *inode_lock = NULL;
-	struct page *page;
-	struct page *tmp;
-	int ret;
-
-	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ,
-				 SCOUTFS_LKF_REFRESH_INODE, inode, &inode_lock);
-	if (ret)
-		goto out;
-
-	list_for_each_entry_safe(page, tmp, pages, lru) {
-		ret = scoutfs_data_wait_check(inode, page_offset(page),
-					      PAGE_SIZE, SEF_OFFLINE,
-					      SCOUTFS_IOC_DWO_READ, NULL,
-					      inode_lock);
-		if (ret < 0)
-			goto out;
-		if (ret > 0) {
-			list_del(&page->lru);
-			put_page(page);
-			if (--nr_pages == 0) {
-				ret = 0;
-				goto out;
-			}
-		}
-	}
-
-	ret = mpage_readpages(mapping, pages, nr_pages, scoutfs_get_block_read);
-out:
-	scoutfs_unlock(sb, inode_lock, SCOUTFS_LOCK_READ);
-	BUG_ON(!list_empty(pages));
-	return ret;
-}
-#else
 static void scoutfs_readahead(struct readahead_control *rac)
 {
 	struct inode *inode = rac->file->f_inode;
@@ -818,7 +779,6 @@ static void scoutfs_readahead(struct readahead_control *rac)

 	scoutfs_unlock(sb, inode_lock, SCOUTFS_LOCK_READ);
 }
-#endif

 static int scoutfs_writepage(struct page *page, struct writeback_control *wbc)
 {
@@ -1259,7 +1219,7 @@ int scoutfs_data_move_blocks(struct inode *from, u64 from_off,
 	struct data_ext_args from_args;
 	struct data_ext_args to_args;
 	struct scoutfs_extent ext;
-	struct kc_timespec cur_time;
+	struct timespec64 cur_time;
 	LIST_HEAD(locks);
 	bool done = false;
 	loff_t from_size;
@@ -2055,15 +2015,9 @@ int scoutfs_data_waiting(struct super_block *sb, u64 ino, u64 iblock,
 	return ret;
 }

-#ifdef KC_MM_VM_FAULT_T
 static vm_fault_t scoutfs_data_page_mkwrite(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
-#else
-static int scoutfs_data_page_mkwrite(struct vm_area_struct *vma,
-				     struct vm_fault *vmf)
-{
-#endif
 	struct page *page = vmf->page;
 	struct file *file = vma->vm_file;
 	struct inode *inode = file_inode(file);
@@ -2205,14 +2159,9 @@ out:
 	return ret;
 }

-#ifdef KC_MM_VM_FAULT_T
 static vm_fault_t scoutfs_data_filemap_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
-#else
-static int scoutfs_data_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-#endif
 	struct file *file = vma->vm_file;
 	struct inode *inode = file_inode(file);
 	struct scoutfs_inode_info *si = SCOUTFS_I(inode);
@@ -2247,15 +2196,11 @@ retry:
 		}
 	}

-#ifdef KC_MM_VM_FAULT_T
 	ret = filemap_fault(vmf);
-#else
-	ret = filemap_fault(vma, vmf);
-#endif

 out:
 	if (scoutfs_per_task_del(&si->pt_data_lock, &pt_ent))
-		kc_inode_dio_end(inode);
+		inode_dio_end(inode);
 	scoutfs_unlock(sb, inode_lock, SCOUTFS_LOCK_READ);
 	if (scoutfs_data_wait_found(&dw)) {
 		err = scoutfs_data_wait(inode, &dw);
@@ -2273,9 +2218,6 @@ out:
 static const struct vm_operations_struct scoutfs_data_file_vm_ops = {
 	.fault		= scoutfs_data_filemap_fault,
 	.page_mkwrite	= scoutfs_data_page_mkwrite,
-#ifdef KC_MM_REMAP_PAGES
-	.remap_pages	= generic_file_remap_pages,
-#endif
 };

 static int scoutfs_file_mmap(struct file *file, struct vm_area_struct *vma)
@@ -2293,11 +2235,7 @@ const struct address_space_operations scoutfs_file_aops = {
 #else
 	.readpage		= scoutfs_readpage,
 #endif
-#ifndef KC_FILE_AOPS_READAHEAD
-	.readpages		= scoutfs_readpages,
-#else
 	.readahead		= scoutfs_readahead,
-#endif
 	.writepage		= scoutfs_writepage,
 	.writepages		= scoutfs_writepages,
 	.write_begin		= scoutfs_write_begin,
@@ -2305,17 +2243,10 @@ const struct address_space_operations scoutfs_file_aops = {
 };

 const struct file_operations scoutfs_file_fops = {
-#ifdef KC_LINUX_HAVE_FOP_AIO_READ
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= scoutfs_file_aio_read,
-	.aio_write	= scoutfs_file_aio_write,
-#else
 	.read_iter	= scoutfs_file_read_iter,
 	.write_iter	= scoutfs_file_write_iter,
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
-#endif
 	.mmap		= scoutfs_file_mmap,
 	.unlocked_ioctl	= scoutfs_ioctl,
 	.fsync		= scoutfs_file_fsync,
@@ -18,6 +18,7 @@
 #include <linux/xattr.h>
 #include <linux/namei.h>
 #include <linux/mm.h>
+#include <linux/iversion.h>

 #include "format.h"
 #include "file.h"
@@ -422,18 +423,7 @@ out:
 	else
 		inode = scoutfs_iget(sb, ino, 0, 0);

-	/*
-	 * We can't splice dir aliases into the dcache.  dir entries
-	 * might have changed on other nodes so our dcache could still
-	 * contain them, rather than having been moved in rename.  For
-	 * dirs, we use d_materialize_unique to remove any existing
-	 * aliases which must be stale.  Our inode numbers aren't reused
-	 * so inodes pointed to by entries can't change types.
-	 */
-	if (!IS_ERR_OR_NULL(inode) && S_ISDIR(inode->i_mode))
-		return d_materialise_unique(dentry, inode);
-	else
-		return d_splice_alias(inode, dentry);
+	return d_splice_alias(inode, dentry);
 }

 /*
@@ -962,7 +952,7 @@ static int scoutfs_unlink(struct inode *dir, struct dentry *dentry)
 {
 	struct super_block *sb = dir->i_sb;
 	struct inode *inode = dentry->d_inode;
-	struct kc_timespec ts = current_time(inode);
+	struct timespec64 ts = current_time(inode);
 	struct scoutfs_lock *inode_lock = NULL;
 	struct scoutfs_lock *orph_lock = NULL;
 	struct scoutfs_lock *dir_lock = NULL;
@@ -1197,24 +1187,6 @@ out:
 	return path;
 }

-#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
-static void *scoutfs_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
-	char *path;
-
-	path = scoutfs_get_link_target(dentry);
-	if (!IS_ERR_OR_NULL(path))
-		nd_set_link(nd, path);
-	return path;
-}
-
-static void scoutfs_put_link(struct dentry *dentry, struct nameidata *nd,
-			     void *cookie)
-{
-	if (!IS_ERR_OR_NULL(cookie))
-		kfree(cookie);
-}
-#else
 static const char *scoutfs_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done)
 {
 	char *path;
@@ -1225,7 +1197,6 @@ static const char *scoutfs_get_link(struct dentry *dentry, struct inode *inode,

 	return path;
 }
-#endif

 /*
 * Symlink target paths can be annoyingly large.  We store relatively
@@ -1635,7 +1606,7 @@ static int scoutfs_rename_common(KC_VFS_NS_DEF
 	struct scoutfs_lock *orph_lock = NULL;
 	struct scoutfs_dirent new_dent;
 	struct scoutfs_dirent old_dent;
-	struct kc_timespec now;
+	struct timespec64 now;
 	bool ins_new = false;
 	bool del_new = false;
 	bool ins_old = false;
@@ -1647,6 +1618,9 @@ static int scoutfs_rename_common(KC_VFS_NS_DEF
 	int ret;
 	int err;

+	if (flags & ~RENAME_NOREPLACE)
+		return -EINVAL;
+
 	trace_scoutfs_rename(sb, old_dir, old_dentry, new_dir, new_dentry);

 	old_hash = dirent_name_hash(old_dentry->d_name.name,
@@ -1892,36 +1866,7 @@ out_unlock:
 	return ret;
 }

-#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
-static int scoutfs_rename(struct inode *old_dir,
-			  struct dentry *old_dentry, struct inode *new_dir,
-			  struct dentry *new_dentry)
-{
-	return scoutfs_rename_common(KC_VFS_INIT_NS
-				     old_dir, old_dentry, new_dir, new_dentry, 0);
-}
-#endif

-static int scoutfs_rename2(KC_VFS_NS_DEF
-			  struct inode *old_dir,
-			  struct dentry *old_dentry, struct inode *new_dir,
-			  struct dentry *new_dentry, unsigned int flags)
-{
-	if (flags & ~RENAME_NOREPLACE)
-		return -EINVAL;
-
-	return scoutfs_rename_common(KC_VFS_NS
-				     old_dir, old_dentry, new_dir, new_dentry, flags);
-}
-
-#ifdef KC_FMODE_KABI_ITERATE
-/* we only need this to set the iterate flag for kabi :/ */
-static int scoutfs_dir_open(struct inode *inode, struct file *file)
-{
-        file->f_mode |= FMODE_KABI_ITERATE;
-        return 0;
-}
-#endif

 static int scoutfs_tmpfile(KC_VFS_NS_DEF
 			   struct inode *dir,
@@ -1991,29 +1936,15 @@ out:
 }

 const struct inode_operations scoutfs_symlink_iops = {
-#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
-	.readlink       = generic_readlink,
-	.follow_link    = scoutfs_follow_link,
-	.put_link       = scoutfs_put_link,
-#else
 	.get_link	= scoutfs_get_link,
-#endif
 	.getattr	= scoutfs_getattr,
 	.setattr	= scoutfs_setattr,
-#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
-	.setxattr	= generic_setxattr,
-	.getxattr	= generic_getxattr,
-#endif
 	.listxattr	= scoutfs_listxattr,
-#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
-	.removexattr	= generic_removexattr,
-#endif
 #ifdef KC_GET_INODE_ACL
 	.get_inode_acl	= scoutfs_get_acl,
 #else
 	.get_acl	= scoutfs_get_acl,
 #endif
-#ifndef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
 	.tmpfile	= scoutfs_tmpfile,
 	.rename		= scoutfs_rename_common,
 	.symlink	= scoutfs_symlink,
@@ -2022,26 +1953,17 @@ const struct inode_operations scoutfs_symlink_iops = {
 	.mkdir		= scoutfs_mkdir,
 	.create		= scoutfs_create,
 	.lookup		= scoutfs_lookup,
-#endif
 };

 const struct file_operations scoutfs_dir_fops = {
 	.iterate	= scoutfs_readdir,
-#ifdef KC_FMODE_KABI_ITERATE
-	.open		= scoutfs_dir_open,
-#endif
 	.unlocked_ioctl	= scoutfs_ioctl,
 	.fsync		= scoutfs_file_fsync,
 	.llseek		= generic_file_llseek,
 };


-#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
-const struct inode_operations_wrapper scoutfs_dir_iops = {
-	.ops = {
-#else
 const struct inode_operations scoutfs_dir_iops = {
-#endif
 	.lookup		= scoutfs_lookup,
 	.mknod		= scoutfs_mknod,
 	.create		= scoutfs_create,
@@ -2051,30 +1973,15 @@ const struct inode_operations scoutfs_dir_iops = {
 	.rmdir		= scoutfs_unlink,
 	.getattr	= scoutfs_getattr,
 	.setattr	= scoutfs_setattr,
-#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
-	.rename		= scoutfs_rename,
-	.setxattr	= generic_setxattr,
-	.getxattr	= generic_getxattr,
-	.removexattr	= generic_removexattr,
-#endif
 	.listxattr	= scoutfs_listxattr,
 #ifdef KC_GET_INODE_ACL
 	.get_inode_acl	= scoutfs_get_acl,
 #else
 	.get_acl	= scoutfs_get_acl,
 #endif
-#ifdef KC_SET_ACL_DENTRY
 	.set_acl	= scoutfs_set_acl,
-#endif
 	.symlink	= scoutfs_symlink,
 	.permission	= scoutfs_permission,
-#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
-	},
-#endif
 	.tmpfile	= scoutfs_tmpfile,
-#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
-	.rename2	= scoutfs_rename2,
-#else
-	.rename		= scoutfs_rename2,
-#endif
+	.rename		= scoutfs_rename_common,
 };
@@ -5,11 +5,7 @@
 #include "lock.h"

 extern const struct file_operations scoutfs_dir_fops;
-#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
-extern const struct inode_operations_wrapper scoutfs_dir_iops;
-#else
 extern const struct inode_operations scoutfs_dir_iops;
-#endif
 extern const struct inode_operations scoutfs_symlink_iops;

 extern const struct dentry_operations scoutfs_dentry_ops;
@@ -222,7 +222,7 @@ static struct attribute *fence_attrs[] = {

 static void fence_timeout(struct timer_list *timer)
 {
-	struct pending_fence *fence = from_timer(fence, timer, timer);
+	struct pending_fence *fence = timer_container_of(fence, timer, timer);
 	struct super_block *sb = fence->sb;
 	DECLARE_FENCE_INFO(sb, fi);

@@ -424,8 +424,7 @@ int scoutfs_fence_setup(struct super_block *sb)
 		goto out;
 	}

-	fi->wq = alloc_workqueue("scoutfs_fence",
-				 WQ_UNBOUND | WQ_NON_REENTRANT, 0);
+	fi->wq = alloc_workqueue("scoutfs_fence", WQ_UNBOUND, 0);
 	if (!fi->wq) {
 		ret = -ENOMEM;
 		goto out;
@@ -30,133 +30,6 @@
 #include "omap.h"
 #include "quota.h"

-#ifdef KC_LINUX_HAVE_FOP_AIO_READ
-/*
- * Start a high level file read.  We check for offline extents in the
- * read region here so that we only check the extents once.  We use the
- * dio count to prevent releasing while we're reading after we've
- * checked the extents.
- */
-ssize_t scoutfs_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
-			      unsigned long nr_segs, loff_t pos)
-{
-	struct file *file = iocb->ki_filp;
-	struct inode *inode = file_inode(file);
-	struct scoutfs_inode_info *si = SCOUTFS_I(inode);
-	struct super_block *sb = inode->i_sb;
-	struct scoutfs_lock *scoutfs_inode_lock = NULL;
-	SCOUTFS_DECLARE_PER_TASK_ENTRY(pt_ent);
-	DECLARE_DATA_WAIT(dw);
-	int ret;
-
-retry:
-	/* protect checked extents from release */
-	inode_lock(inode);
-	atomic_inc(&inode->i_dio_count);
-	inode_unlock(inode);
-
-	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ,
-				 SCOUTFS_LKF_REFRESH_INODE, inode, &scoutfs_inode_lock);
-	if (ret)
-		goto out;
-
-	if (scoutfs_per_task_add_excl(&si->pt_data_lock, &pt_ent, scoutfs_inode_lock)) {
-		ret = scoutfs_data_wait_check_iov(inode, iov, nr_segs, pos,
-						  SEF_OFFLINE,
-						  SCOUTFS_IOC_DWO_READ,
-						  &dw, scoutfs_inode_lock);
-		if (ret != 0)
-			goto out;
-	} else {
-		WARN_ON_ONCE(true);
-	}
-
-	ret = generic_file_aio_read(iocb, iov, nr_segs, pos);
-
-out:
-	inode_dio_done(inode);
-	scoutfs_per_task_del(&si->pt_data_lock, &pt_ent);
-	scoutfs_unlock(sb, scoutfs_inode_lock, SCOUTFS_LOCK_READ);
-
-	if (scoutfs_data_wait_found(&dw)) {
-		ret = scoutfs_data_wait(inode, &dw);
-		if (ret == 0)
-			goto retry;
-	}
-
-	return ret;
-}
-
-ssize_t scoutfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
-			       unsigned long nr_segs, loff_t pos)
-{
-	struct file *file = iocb->ki_filp;
-	struct inode *inode = file_inode(file);
-	struct scoutfs_inode_info *si = SCOUTFS_I(inode);
-	struct super_block *sb = inode->i_sb;
-	struct scoutfs_lock *scoutfs_inode_lock = NULL;
-	SCOUTFS_DECLARE_PER_TASK_ENTRY(pt_ent);
-	DECLARE_DATA_WAIT(dw);
-	int ret;
-
-	if (iocb->ki_left == 0) /* Does this even happen? */
-		return 0;
-
-retry:
-	inode_lock(inode);
-	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_WRITE,
-				 SCOUTFS_LKF_REFRESH_INODE, inode, &scoutfs_inode_lock);
-	if (ret)
-		goto out;
-
-	ret = scoutfs_inode_check_retention(inode);
-	if (ret < 0)
-		goto out;
-
-	ret = scoutfs_complete_truncate(inode, scoutfs_inode_lock);
-	if (ret)
-		goto out;
-
-	if (scoutfs_per_task_add_excl(&si->pt_data_lock, &pt_ent, scoutfs_inode_lock)) {
-		/* data_version is per inode, whole file must be online */
-		ret = scoutfs_data_wait_check(inode, 0, i_size_read(inode),
-					      SEF_OFFLINE,
-					      SCOUTFS_IOC_DWO_WRITE,
-					      &dw, scoutfs_inode_lock);
-		if (ret != 0)
-			goto out;
-	}
-
-	ret = scoutfs_quota_check_data(sb, inode);
-	if (ret)
-		goto out;
-
-	/* XXX: remove SUID bit */
-
-	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
-
-out:
-	scoutfs_per_task_del(&si->pt_data_lock, &pt_ent);
-	scoutfs_unlock(sb, scoutfs_inode_lock, SCOUTFS_LOCK_WRITE);
-	inode_unlock(inode);
-
-	if (scoutfs_data_wait_found(&dw)) {
-		ret = scoutfs_data_wait(inode, &dw);
-		if (ret == 0)
-			goto retry;
-	}
-
-	if (ret > 0 || ret == -EIOCBQUEUED) {
-		ssize_t err;
-
-		err = generic_write_sync(file, pos, ret);
-		if (err < 0 && ret > 0)
-			ret = err;
-	}
-
-	return ret;
-}
-#else
 ssize_t scoutfs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct file *file = iocb->ki_filp;
@@ -265,7 +138,6 @@ out:

 	return ret;
 }
-#endif

 int scoutfs_permission(KC_VFS_NS_DEF
 		       struct inode *inode, int mask)
@@ -1,15 +1,8 @@
 #ifndef _SCOUTFS_FILE_H_
 #define _SCOUTFS_FILE_H_

-#ifdef KC_LINUX_HAVE_FOP_AIO_READ
-ssize_t scoutfs_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
-			      unsigned long nr_segs, loff_t pos);
-ssize_t scoutfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
-			       unsigned long nr_segs, loff_t pos);
-#else
 ssize_t scoutfs_file_read_iter(struct kiocb *, struct iov_iter *);
 ssize_t scoutfs_file_write_iter(struct kiocb *, struct iov_iter *);
-#endif
 int scoutfs_permission(KC_VFS_NS_DEF
 		       struct inode *inode, int mask);
 loff_t scoutfs_file_llseek(struct file *file, loff_t offset, int whence);
@@ -239,9 +239,9 @@ static int forest_read_items(struct super_block *sb, struct scoutfs_key *key, u6
 * to reset their state and retry with a newer version of the btrees.
 */
 int scoutfs_forest_read_items_roots(struct super_block *sb, struct scoutfs_net_roots *roots,
-				    struct scoutfs_key *key, struct scoutfs_key *bloom_key,
-				    struct scoutfs_key *start, struct scoutfs_key *end,
-				    scoutfs_forest_item_cb cb, void *arg)
+				    u64 merge_input_seq, struct scoutfs_key *key,
+				    struct scoutfs_key *bloom_key, struct scoutfs_key *start,
+				    struct scoutfs_key *end, scoutfs_forest_item_cb cb, void *arg)
 {
 	struct forest_read_items_data rid = {
 		.cb = cb,
@@ -317,15 +317,17 @@ int scoutfs_forest_read_items_roots(struct super_block *sb, struct scoutfs_net_r

 		scoutfs_inc_counter(sb, forest_bloom_pass);

-		if ((le64_to_cpu(lt.flags) & SCOUTFS_LOG_TREES_FINALIZED))
-			rid.fic |= FIC_FINALIZED;
+		if ((le64_to_cpu(lt.flags) & SCOUTFS_LOG_TREES_FINALIZED) &&
+		    (merge_input_seq == 0 ||
+		     le64_to_cpu(lt.finalize_seq) < merge_input_seq))
+			rid.fic |= FIC_MERGE_INPUT;

 		ret = scoutfs_btree_read_items(sb, &lt.item_root, key, start,
 					       end, forest_read_items, &rid);
 		if (ret < 0)
 			goto out;

-		rid.fic &= ~FIC_FINALIZED;
+		rid.fic &= ~FIC_MERGE_INPUT;
 	}

 	ret = 0;
@@ -345,7 +347,7 @@ int scoutfs_forest_read_items(struct super_block *sb,

 	ret = scoutfs_client_get_roots(sb, &roots);
 	if (ret == 0)
-		ret = scoutfs_forest_read_items_roots(sb, &roots, key, bloom_key, start, end,
+		ret = scoutfs_forest_read_items_roots(sb, &roots, 0, key, bloom_key, start, end,
 						      cb, arg);
 	return ret;
 }
@@ -781,7 +783,7 @@ int scoutfs_forest_setup(struct super_block *sb)
 			  scoutfs_forest_log_merge_worker);
 	sbi->forest_info = finf;

-	finf->workq = alloc_workqueue("scoutfs_log_merge", WQ_NON_REENTRANT |
+	finf->workq = alloc_workqueue("scoutfs_log_merge",
 				      WQ_UNBOUND | WQ_HIGHPRI, 0);
 	if (!finf->workq) {
 		ret = -ENOMEM;
@@ -11,7 +11,7 @@ struct scoutfs_lock;
 /* caller gives an item to the callback */
 enum {
 	FIC_FS_ROOT = (1 << 0),
-	FIC_FINALIZED = (1 << 1),
+	FIC_MERGE_INPUT = (1 << 1),
 };
 typedef int (*scoutfs_forest_item_cb)(struct super_block *sb, struct scoutfs_key *key, u64 seq,
 				      u8 flags, void *val, int val_len, int fic, void *arg);
@@ -25,9 +25,9 @@ int scoutfs_forest_read_items(struct super_block *sb,
 			      struct scoutfs_key *end,
 			      scoutfs_forest_item_cb cb, void *arg);
 int scoutfs_forest_read_items_roots(struct super_block *sb, struct scoutfs_net_roots *roots,
-				    struct scoutfs_key *key, struct scoutfs_key *bloom_key,
-				    struct scoutfs_key *start, struct scoutfs_key *end,
-				    scoutfs_forest_item_cb cb, void *arg);
+				    u64 merge_input_seq, struct scoutfs_key *key,
+				    struct scoutfs_key *bloom_key, struct scoutfs_key *start,
+				    struct scoutfs_key *end, scoutfs_forest_item_cb cb, void *arg);
 int scoutfs_forest_set_bloom_bits(struct super_block *sb,
 				  struct scoutfs_lock *lock);
 void scoutfs_forest_set_max_seq(struct super_block *sb, u64 max_seq);
@@ -21,6 +21,7 @@
 #include <linux/list_sort.h>
 #include <linux/workqueue.h>
 #include <linux/buffer_head.h>
+#include <linux/iversion.h>

 #include "format.h"
 #include "super.h"
@@ -143,40 +144,26 @@ void scoutfs_destroy_inode(struct inode *inode)
 static const struct inode_operations scoutfs_file_iops = {
 	.getattr	= scoutfs_getattr,
 	.setattr	= scoutfs_setattr,
-#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
-	.setxattr	= generic_setxattr,
-	.getxattr	= generic_getxattr,
-	.removexattr	= generic_removexattr,
-#endif
 	.listxattr	= scoutfs_listxattr,
 #ifdef KC_GET_INODE_ACL
 	.get_inode_acl	= scoutfs_get_acl,
 #else
 	.get_acl	= scoutfs_get_acl,
 #endif
-#ifdef KC_SET_ACL_DENTRY
 	.set_acl	= scoutfs_set_acl,
-#endif
 	.fiemap		= scoutfs_data_fiemap,
 };

 static const struct inode_operations scoutfs_special_iops = {
 	.getattr	= scoutfs_getattr,
 	.setattr	= scoutfs_setattr,
-#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
-	.setxattr	= generic_setxattr,
-	.getxattr	= generic_getxattr,
-	.removexattr	= generic_removexattr,
-#endif
 	.listxattr	= scoutfs_listxattr,
 #ifdef KC_GET_INODE_ACL
 	.get_inode_acl	= scoutfs_get_acl,
 #else
 	.get_acl	= scoutfs_get_acl,
 #endif
-#ifdef KC_SET_ACL_DENTRY
 	.set_acl	= scoutfs_set_acl,
-#endif
 };

 /*
@@ -192,12 +179,7 @@ static void set_inode_ops(struct inode *inode)
 		inode->i_fop = &scoutfs_file_fops;
 		break;
 	case S_IFDIR:
-#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
-		inode->i_op = &scoutfs_dir_iops.ops;
-		inode->i_flags |= S_IOPS_WRAPPER;
-#else
 		inode->i_op = &scoutfs_dir_iops;
-#endif
 		inode->i_fop = &scoutfs_dir_fops;
 		break;
 	case S_IFLNK:
@@ -381,18 +363,11 @@ int scoutfs_inode_refresh(struct inode *inode, struct scoutfs_lock *lock)
 	return ret;
 }

-#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
-int scoutfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		    struct kstat *stat)
-{
-	struct inode *inode = dentry->d_inode;
-#else
 int scoutfs_getattr(KC_VFS_NS_DEF
 		    const struct path *path, struct kstat *stat,
 		    u32 request_mask, unsigned int query_flags)
 {
 	struct inode *inode = d_inode(path->dentry);
-#endif
 	struct super_block *sb = inode->i_sb;
 	struct scoutfs_lock *lock = NULL;
 	int ret;
@@ -549,6 +524,7 @@ retry:
 				goto out;
 			if (scoutfs_data_wait_found(&dw)) {
 				scoutfs_unlock(sb, lock, SCOUTFS_LOCK_WRITE);
+				lock = NULL;

 				/* XXX callee locks instead? */
 				inode_unlock(inode);
@@ -23,7 +23,7 @@ struct scoutfs_inode_info {
 	u64 offline_blocks;
 	u64 proj;
 	u32 flags;
-	struct kc_timespec crtime;
+	struct timespec64 crtime;

 	/*
 	 * Protects per-inode extent items, most particularly readers
@@ -131,14 +131,9 @@ int scoutfs_complete_truncate(struct inode *inode, struct scoutfs_lock *lock);
 int scoutfs_inode_check_retention(struct inode *inode);

 int scoutfs_inode_refresh(struct inode *inode, struct scoutfs_lock *lock);
-#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
-int scoutfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		    struct kstat *stat);
-#else
 int scoutfs_getattr(KC_VFS_NS_DEF
 		    const struct path *path, struct kstat *stat,
 		    u32 request_mask, unsigned int query_flags);
-#endif
 int scoutfs_setattr(KC_VFS_NS_DEF
 		    struct dentry *dentry, struct iattr *attr);

@@ -489,6 +489,7 @@ static long scoutfs_ioc_stage(struct file *file, unsigned long arg)
 	struct scoutfs_lock *lock = NULL;
 	struct kiocb kiocb;
 	struct iovec iov;
+	struct iov_iter iter;
 	size_t written;
 	loff_t end_size;
 	loff_t isize;
@@ -514,10 +515,6 @@ static long scoutfs_ioc_stage(struct file *file, unsigned long arg)
 	/* the iocb is really only used for the file pointer :P */
 	init_sync_kiocb(&kiocb, file);
 	kiocb.ki_pos = args.offset;
-#ifdef KC_LINUX_AIO_KI_LEFT
-	kiocb.ki_left = args.length;
-	kiocb.ki_nbytes = args.length;
-#endif
 	iov.iov_base = (void __user *)(unsigned long)args.buf_ptr;
 	iov.iov_len = args.length;

@@ -559,8 +556,9 @@ static long scoutfs_ioc_stage(struct file *file, unsigned long arg)
 	pos = args.offset;
 	written = 0;
 	do {
-		ret = generic_file_buffered_write(&kiocb, &iov, 1, pos, &pos,
-						  args.length, written);
+		iov_iter_init(&iter, WRITE, &iov, 1, args.length);
+		ret = kc_generic_perform_write(&kiocb, &iter, pos);
+
 		BUG_ON(ret == -EIOCBQUEUED);
 		if (ret > 0)
 			written += ret;
@@ -1739,6 +1737,43 @@ out:
 	return ret;
 }

+static long scoutfs_ioc_inject_totl_delta(struct file *file, unsigned long arg)
+{
+	struct super_block *sb = file_inode(file)->i_sb;
+	struct scoutfs_ioctl_inject_totl_delta __user *uitd = (void __user *)arg;
+	struct scoutfs_ioctl_inject_totl_delta itd;
+	struct scoutfs_xattr_totl_val tval;
+	struct scoutfs_lock *lock = NULL;
+	struct scoutfs_key key;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (copy_from_user(&itd, uitd, sizeof(itd)))
+		return -EFAULT;
+
+	scoutfs_xattr_init_totl_key(&key, itd.name);
+	tval.total = cpu_to_le64((u64)itd.total);
+	tval.count = cpu_to_le64((u64)itd.count);
+
+	ret = scoutfs_lock_xattr_totl(sb, SCOUTFS_LOCK_WRITE_ONLY, 0, &lock);
+	if (ret < 0)
+		goto out;
+
+	ret = scoutfs_hold_trans(sb, true);
+	if (ret < 0)
+		goto unlock;
+
+	ret = scoutfs_item_delta(sb, &key, &tval, sizeof(tval), lock);
+
+	scoutfs_release_trans(sb);
+unlock:
+	scoutfs_unlock(sb, lock, SCOUTFS_LOCK_WRITE_ONLY);
+out:
+	return ret;
+}
+
 long scoutfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	switch (cmd) {
@@ -1790,6 +1825,8 @@ long scoutfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		return scoutfs_ioc_read_xattr_index(file, arg);
 	case SCOUTFS_IOC_PUNCH_OFFLINE:
 		return scoutfs_ioc_punch_offline(file, arg);
+	case SCOUTFS_IOC_INJECT_TOTL_DELTA:
+		return scoutfs_ioc_inject_totl_delta(file, arg);
 	}

 	return -ENOTTY;
@@ -876,4 +876,17 @@ struct scoutfs_ioctl_punch_offline {
 #define SCOUTFS_IOC_PUNCH_OFFLINE \
 	_IOW(SCOUTFS_IOCTL_MAGIC, 24, struct scoutfs_ioctl_punch_offline)

+/*
+ * Inject a signed (total, count) delta at the totl key @name (a, b, c
+ * match the trailing dotted u64s of a totl xattr name).
+ */
+struct scoutfs_ioctl_inject_totl_delta {
+	__u64	name[SCOUTFS_IOCTL_XATTR_TOTAL_NAME_NR];
+	__s64	total;
+	__s64	count;
+};
+
+#define SCOUTFS_IOC_INJECT_TOTL_DELTA \
+	_IOW(SCOUTFS_IOCTL_MAGIC, 25, struct scoutfs_ioctl_inject_totl_delta)
+
 #endif
@@ -79,9 +79,6 @@ struct item_cache_info {
 	struct super_block *sb;
 	struct item_percpu_pages __percpu *pcpu_pages;
 	KC_DEFINE_SHRINKER(shrinker);
-#ifdef KC_CPU_NOTIFIER
-	struct notifier_block notifier;
-#endif

 	/* often walked, but per-cpu refs are fast path */
 	rwlock_t rwlock;
@@ -2584,22 +2581,6 @@ static unsigned long item_cache_scan_objects(struct shrinker *shrink,
 	return freed;
 }

-#ifdef KC_CPU_NOTIFIER
-static int item_cpu_callback(struct notifier_block *nfb,
-			     unsigned long action, void *hcpu)
-{
-	struct item_cache_info *cinf = container_of(nfb,
-						    struct item_cache_info,
-						    notifier);
-	struct super_block *sb = cinf->sb;
-	unsigned long cpu = (unsigned long)hcpu;
-
-        if (action == CPU_DEAD)
-		drop_pcpu_pages(sb, cinf, cpu);
-
-	return NOTIFY_OK;
-}
-#endif

 int scoutfs_item_setup(struct super_block *sb)
 {
@@ -2630,10 +2611,6 @@ int scoutfs_item_setup(struct super_block *sb)
 	KC_INIT_SHRINKER_FUNCS(&cinf->shrinker, item_cache_count_objects,
 			       item_cache_scan_objects);
 	KC_REGISTER_SHRINKER(&cinf->shrinker, "scoutfs-item:" SCSBF, SCSB_ARGS(sb));
-#ifdef KC_CPU_NOTIFIER
-        cinf->notifier.notifier_call = item_cpu_callback;
-        register_hotcpu_notifier(&cinf->notifier);
-#endif

 	sbi->item_cache_info = cinf;
 	return 0;
@@ -2651,9 +2628,6 @@ void scoutfs_item_destroy(struct super_block *sb)
 	int cpu;

 	if (cinf) {
-#ifdef KC_CPU_NOTIFIER
-		unregister_hotcpu_notifier(&cinf->notifier);
-#endif
 		KC_UNREGISTER_SHRINKER(&cinf->shrinker);

 		for_each_possible_cpu(cpu)
@@ -3,119 +3,8 @@

 #include "kernelcompat.h"

-#ifdef KC_SHRINKER_SHRINK
-#include <linux/shrinker.h>
-/*
- * If a target doesn't have that .{count,scan}_objects() interface then
- * we have a .shrink() helper that performs the shrink work in terms of
- * count/scan.
- */
-int kc_shrink_wrapper_fn(struct shrinker *shrink, struct shrink_control *sc)
-{
-	struct kc_shrinker_wrapper *wrapper = container_of(shrink, struct kc_shrinker_wrapper, shrink);
-	unsigned long nr;
-	unsigned long rc;
-
-	if (sc->nr_to_scan != 0) {
-		rc = wrapper->scan_objects(shrink, sc);
-		/* translate magic values to the equivalent for older kernels */
-		if (rc == SHRINK_STOP)
-			return -1;
-		else if (rc == SHRINK_EMPTY)
-			return 0;
-	}
-
-	nr = wrapper->count_objects(shrink, sc);
-
-	return min_t(unsigned long, nr, INT_MAX);
-}
-#endif
-
-#ifndef KC_CURRENT_TIME_INODE
-struct timespec64 kc_current_time(struct inode *inode)
-{
-	struct timespec64 now;
-	unsigned gran;
-
-	getnstimeofday64(&now);
-
-	if (unlikely(!inode->i_sb)) {
-		WARN(1, "current_time() called with uninitialized super_block in the inode");
-		return now;
-	}
-
-	gran = inode->i_sb->s_time_gran;
-
-	/* Avoid division in the common cases 1 ns and 1 s. */
-	if (gran == 1) {
-		/* nothing */
-	} else if (gran == NSEC_PER_SEC) {
-		now.tv_nsec = 0;
-	} else if (gran > 1 && gran < NSEC_PER_SEC) {
-		now.tv_nsec -= now.tv_nsec % gran;
-	} else {
-		WARN(1, "illegal file time granularity: %u", gran);
-	}
-
-	return now;
-}
-#endif
-
-#ifndef KC_GENERIC_FILE_BUFFERED_WRITE
-ssize_t
-kc_generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
-			       unsigned long nr_segs, loff_t pos, loff_t *ppos,
-			       size_t count, ssize_t written)
-{
-	ssize_t status;
-	struct iov_iter i;
-
-	iov_iter_init(&i, WRITE, iov, nr_segs, count);
-	status = kc_generic_perform_write(iocb, &i, pos);
-
-	if (likely(status >= 0)) {
-		written += status;
-		*ppos = pos + status;
-	}
-
-	return written ? written : status;
-}
-#endif
-
 #include <linux/list_lru.h>

-#ifdef KC_LIST_LRU_WALK_CB_ITEM_LOCK
-static enum lru_status kc_isolate(struct list_head *item, spinlock_t *lock, void *cb_arg)
-{
-	struct kc_isolate_args *args = cb_arg;
-
-	/* isolate doesn't use list, nr_items updated in caller */
-	return args->isolate(item, NULL, args->cb_arg);
-}
-
-unsigned long kc_list_lru_walk(struct list_lru *lru, kc_list_lru_walk_cb_t isolate, void *cb_arg,
-				      unsigned long nr_to_walk)
-{
-	struct kc_isolate_args args = {
-		.isolate = isolate,
-		.cb_arg = cb_arg,
-	};
-
-	return list_lru_walk(lru, kc_isolate, &args, nr_to_walk);
-}
-
-unsigned long kc_list_lru_shrink_walk(struct list_lru *lru, struct shrink_control *sc,
-				      kc_list_lru_walk_cb_t isolate, void *cb_arg)
-{
-	struct kc_isolate_args args = {
-		.isolate = isolate,
-		.cb_arg = cb_arg,
-	};
-
-	return list_lru_shrink_walk(lru, sc, kc_isolate, &args);
-}
-#endif
-
 #ifdef KC_LIST_LRU_WALK_CB_LIST_LOCK
 static enum lru_status kc_isolate(struct list_head *item, struct list_lru_one *list,
 				  spinlock_t *lock, void *cb_arg)
@@ -4,146 +4,6 @@
 #include <linux/kernel.h>
 #include <linux/fs.h>

-/*
- * v4.15-rc3-4-gae5e165d855d
- *
- * new API for handling inode->i_version. This forces us to
- * include this API where we need. We include it here for
- * convenience instead of where it's needed.
- */
-#ifdef KC_NEED_LINUX_IVERSION_H
-#include <linux/iversion.h>
-#else
-/*
- * Kernels before above version will need to fall back to
- * manipulating inode->i_version as previous with degraded
- * methods.
- */
-#define inode_set_iversion_queried(inode, val)	\
-do {						\
-	(inode)->i_version = val;		\
-} while (0)
-#define inode_peek_iversion(inode)		\
-({						\
-	(inode)->i_version;			\
-})
-#endif
-
-#ifdef KC_POSIX_ACL_VALID_USER_NS
-#define kc_posix_acl_valid(user_ns, acl) posix_acl_valid(user_ns, acl)
-#else
-#define kc_posix_acl_valid(user_ns, acl) posix_acl_valid(acl)
-#endif
-
-/*
- * v3.6-rc1-24-gdbf2576e37da
- *
- * All workqueues are now non-reentrant, and the bit flag is removed
- * shortly after its uses were removed.
- */
-#ifndef WQ_NON_REENTRANT
-#define WQ_NON_REENTRANT 0
-#endif
-
-/*
- * v3.18-rc2-19-gb5ae6b15bd73
- *
- * Folds d_materialise_unique into d_splice_alias. Note reversal
- * of arguments (Also note Documentation/filesystems/porting.rst)
- */
-#ifndef KC_D_MATERIALISE_UNIQUE
-#define d_materialise_unique(dentry, inode) d_splice_alias(inode, dentry)
-#endif
-
-/*
- * v4.8-rc1-29-g31051c85b5e2
- *
- * fall back to inode_change_ok() if setattr_prepare() isn't available
- */
-#ifndef KC_SETATTR_PREPARE
-#define setattr_prepare(dentry, attr) inode_change_ok(d_inode(dentry), attr)
-#endif
-
-#ifndef KC___POSIX_ACL_CREATE
-#define __posix_acl_create posix_acl_create
-#define __posix_acl_chmod posix_acl_chmod
-#endif
-
-#ifndef KC_PERCPU_COUNTER_ADD_BATCH
-#define percpu_counter_add_batch __percpu_counter_add
-#endif
-
-#ifndef KC_MEMALLOC_NOFS_SAVE
-#define memalloc_nofs_save memalloc_noio_save
-#define memalloc_nofs_restore memalloc_noio_restore
-#endif
-
-#ifdef KC_BIO_BI_OPF
-#define kc_bio_get_opf(bio)		\
-({					\
-	(bio)->bi_opf;			\
-})
-#define kc_bio_set_opf(bio, opf)	\
-do {					\
-	(bio)->bi_opf = opf;		\
-} while (0)
-#define kc_bio_set_sector(bio, sect)	\
-do {					\
-	(bio)->bi_iter.bi_sector = sect;\
-} while (0)
-#define kc_submit_bio(bio) submit_bio(bio)
-#else
-#define kc_bio_get_opf(bio)		\
-({					\
-	(bio)->bi_rw;			\
-})
-#define kc_bio_set_opf(bio, opf)	\
-do {					\
-	(bio)->bi_rw = opf;		\
-} while (0)
-#define kc_bio_set_sector(bio, sect)	\
-do {					\
-	(bio)->bi_sector = sect;	\
-} while (0)
-#define kc_submit_bio(bio)		\
-do {					\
-	submit_bio((bio)->bi_rw, bio);	\
-} while (0)
-#define bio_set_dev(bio, bdev)		\
-do {					\
-	(bio)->bi_bdev = (bdev);	\
-} while (0)
-#endif
-
-#ifdef KC_BIO_BI_STATUS
-#define KC_DECLARE_BIO_END_IO(name, bio)	name(bio)
-#define kc_bio_get_errno(bio)			({ blk_status_to_errno((bio)->bi_status); })
-#else
-#define KC_DECLARE_BIO_END_IO(name, bio)	name(bio, int _error_arg)
-#define kc_bio_get_errno(bio)			({ (int)((void)(bio), _error_arg); })
-#endif
-
-/*
- * v4.13-rc1-6-ge462ec50cb5f
- *
- * MS_* (mount) flags from <linux/mount.h> should not be used in the kernel
- * anymore from 4.x onwards. Instead, we need to use the SB_* (superblock) flags
- */
-#ifndef SB_POSIXACL
-#define SB_POSIXACL MS_POSIXACL
-#define SB_I_VERSION MS_I_VERSION
-#endif
-
-#ifndef KC_CURRENT_TIME_INODE
-struct timespec64 kc_current_time(struct inode *inode);
-#define current_time kc_current_time
-#define kc_timespec timespec
-#else
-#define kc_timespec timespec64
-#endif
-
-#ifndef KC_SHRINKER_SHRINK
-
 #define KC_DEFINE_SHRINKER(name) struct shrinker name
 #define KC_INIT_SHRINKER_FUNCS(name, countfn, scanfn) do {	\
 	__typeof__(name) _shrink = (name);			\
@@ -160,77 +20,7 @@ struct timespec64 kc_current_time(struct inode *inode);
 #endif /* KC_SHRINKER_NAME */
 #define KC_UNREGISTER_SHRINKER(ptr) (unregister_shrinker(ptr))
 #define KC_SHRINKER_FN(ptr) (ptr)
-#else

-#include <linux/shrinker.h>
-#ifndef SHRINK_STOP
-#define SHRINK_STOP (~0UL)
-#define SHRINK_EMPTY (~0UL - 1)
-#endif
-
-int kc_shrink_wrapper_fn(struct shrinker *shrink, struct shrink_control *sc);
-struct kc_shrinker_wrapper {
-	unsigned long (*count_objects)(struct shrinker *, struct shrink_control *sc);
-	unsigned long (*scan_objects)(struct shrinker *, struct shrink_control *sc);
-	struct shrinker shrink;
-};
-
-#define KC_DEFINE_SHRINKER(name) struct kc_shrinker_wrapper name;
-#define KC_INIT_SHRINKER_FUNCS(name, countfn, scanfn) do {	\
-	struct kc_shrinker_wrapper *_wrap = (name);		\
-	_wrap->count_objects = (countfn);			\
-	_wrap->scan_objects = (scanfn);				\
-	_wrap->shrink.shrink = kc_shrink_wrapper_fn;		\
-	_wrap->shrink.seeks = DEFAULT_SEEKS;			\
-} while (0)
-#define KC_SHRINKER_CONTAINER_OF(ptr, type) container_of(container_of(ptr, struct kc_shrinker_wrapper, shrink), type, shrinker)
-#define KC_REGISTER_SHRINKER(ptr, fmt, ...) (register_shrinker(ptr.shrink))
-#define KC_UNREGISTER_SHRINKER(ptr) (unregister_shrinker(ptr.shrink))
-#define KC_SHRINKER_FN(ptr) (ptr.shrink)
-
-#endif /* KC_SHRINKER_SHRINK */
-
-#ifdef KC_KERNEL_GETSOCKNAME_ADDRLEN
-#include <linux/net.h>
-#include <linux/inet.h>
-static inline int kc_kernel_getsockname(struct socket *sock, struct sockaddr *addr)
-{
-	int addrlen = sizeof(struct sockaddr_in);
-	int ret = kernel_getsockname(sock, addr, &addrlen);
-	if (ret == 0 && addrlen != sizeof(struct sockaddr_in))
-		return -EAFNOSUPPORT;
-	else if (ret < 0)
-		return ret;
-
-	return sizeof(struct sockaddr_in);
-}
-static inline int kc_kernel_getpeername(struct socket *sock, struct sockaddr *addr)
-{
-	int addrlen = sizeof(struct sockaddr_in);
-	int ret = kernel_getpeername(sock, addr, &addrlen);
-	if (ret == 0 && addrlen != sizeof(struct sockaddr_in))
-		return -EAFNOSUPPORT;
-	else if (ret < 0)
-		return ret;
-
-	return sizeof(struct sockaddr_in);
-}
-#else
-#define kc_kernel_getsockname(sock, addr) kernel_getsockname(sock, addr)
-#define kc_kernel_getpeername(sock, addr) kernel_getpeername(sock, addr)
-#endif
-
-#ifdef KC_SOCK_CREATE_KERN_NET
-#define kc_sock_create_kern(family, type, proto, res) sock_create_kern(&init_net, family, type, proto, res)
-#else
-#define kc_sock_create_kern sock_create_kern
-#endif
-
-#ifndef KC_GENERIC_FILE_BUFFERED_WRITE
-ssize_t kc_generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
-               unsigned long nr_segs, loff_t pos, loff_t *ppos,
-               size_t count, ssize_t written);
-#define generic_file_buffered_write kc_generic_file_buffered_write
 #ifdef KC_GENERIC_PERFORM_WRITE_KIOCB_IOV_ITER
 static inline int kc_generic_perform_write(struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
 {
@@ -244,7 +34,6 @@ static inline int kc_generic_perform_write(struct kiocb *iocb, struct iov_iter *
 	return generic_perform_write(file, iter, pos);
 }
 #endif
-#endif // KC_GENERIC_FILE_BUFFERED_WRITE

 #ifndef KC_HAVE_BLK_OPF_T
 /* typedef __u32 __bitwise blk_opf_t; */
@@ -288,7 +77,7 @@ static inline struct bio *kc_bio_alloc(struct block_device *bdev, unsigned short
 {
 	struct bio *b = bio_alloc(gfp_mask, nr_vecs);
 	if (b) {
-		kc_bio_set_opf(b, opf);
+		b->bi_opf = opf;
 		bio_set_dev(b, bdev);
 	}
 	return b;
@@ -299,11 +88,6 @@ static inline struct bio *kc_bio_alloc(struct block_device *bdev, unsigned short
 #define fiemap_prep(inode, fieinfo, start, len, flags) fiemap_check_flags(fieinfo, flags)
 #endif

-#ifndef KC_KERNEL_OLD_TIMEVAL_STRUCT
-#define __kernel_old_timeval timeval
-#define ns_to_kernel_old_timeval(ktime) ns_to_timeval(ktime.tv64)
-#endif
-
 #ifdef KC_SOCK_SET_SNDTIMEO
 #include <net/sock.h>
 static inline int kc_sock_set_sndtimeo(struct socket *sock, s64 secs)
@@ -400,45 +184,14 @@ static inline int kc_tcp_sock_set_nodelay(struct socket *sock)
 }
 #endif

-#ifdef KC_INODE_DIO_END
-#define kc_inode_dio_end inode_dio_end
-#else
-#define kc_inode_dio_end inode_dio_done
-#endif
-
-#ifndef KC_MM_VM_FAULT_T
-typedef unsigned int vm_fault_t;
-static inline vm_fault_t vmf_error(int err)
-{
-	if (err == -ENOMEM)
-		return VM_FAULT_OOM;
-	return VM_FAULT_SIGBUS;
-}
-#endif
-
 #include <linux/list_lru.h>

-#ifndef KC_LIST_LRU_SHRINK_COUNT_WALK
-/* we don't bother with sc->{nid,memcg} (which doesn't exist in oldest kernels) */
-static inline unsigned long list_lru_shrink_count(struct list_lru *lru,
-                                                  struct shrink_control *sc)
-{
-        return list_lru_count(lru);
-}
-static inline unsigned long
-list_lru_shrink_walk(struct list_lru *lru, struct shrink_control *sc,
-		     list_lru_walk_cb isolate, void *cb_arg)
-{
-	return list_lru_walk(lru, isolate, cb_arg, sc->nr_to_scan);
-}
-#endif
-
 #ifndef KC_LIST_LRU_ADD_OBJ
 #define list_lru_add_obj list_lru_add
 #define list_lru_del_obj list_lru_del
 #endif

-#if defined(KC_LIST_LRU_WALK_CB_LIST_LOCK) || defined(KC_LIST_LRU_WALK_CB_ITEM_LOCK)
+#if defined(KC_LIST_LRU_WALK_CB_LIST_LOCK)
 struct list_lru_one;
 typedef enum lru_status (*kc_list_lru_walk_cb_t)(struct list_head *item, struct list_lru_one *list,
 						 void *cb_arg);
@@ -454,39 +207,9 @@ unsigned long kc_list_lru_shrink_walk(struct list_lru *lru, struct shrink_contro
 #define kc_list_lru_shrink_walk list_lru_shrink_walk
 #endif

-#if defined(KC_LIST_LRU_WALK_CB_ITEM_LOCK)
-/* isolate moved by hand, nr_items updated in walk as _REMOVE returned */
-static inline void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item,
-					 struct list_head *head)
-{
-        list_move(item, head);
-}
-#endif
-
-#ifndef KC_STACK_TRACE_SAVE
-#include <linux/stacktrace.h>
-static inline unsigned int stack_trace_save(unsigned long *store, unsigned int size,
-					    unsigned int skipnr)
-{
-        struct stack_trace trace = {
-                .entries        = store,
-                .max_entries    = size,
-                .skip           = skipnr,
-        };
-
-        save_stack_trace(&trace);
-        return trace.nr_entries;
-}
-
-static inline void stack_trace_print(unsigned long *entries, unsigned int nr_entries, int spaces)
-{
-        struct stack_trace trace = {
-                .entries        = entries,
-                .nr_entries     = nr_entries,
-        };
-
-	print_stack_trace(&trace, spaces);
-}
+#ifndef KC_TIMER_CONTAINER_OF
+#define timer_container_of(var, callback_timer, timer_fieldname) \
+	from_timer(var, callback_timer, timer_fieldname)
 #endif

 #endif
@@ -813,6 +813,7 @@ int scoutfs_lock_invalidate_request(struct super_block *sb, u64 net_id,

 out:
 	if (!lock) {
+		kfree(ireq);
 		ret = scoutfs_client_lock_response(sb, net_id, nl);
 		BUG_ON(ret); /* lock server doesn't fence timed out client requests */
 	}
@@ -1692,8 +1693,7 @@ int scoutfs_lock_setup(struct super_block *sb)
 	}

 	linfo->workq = alloc_workqueue("scoutfs_lock_client_work",
-				       WQ_NON_REENTRANT | WQ_UNBOUND |
-				       WQ_HIGHPRI, 0);
+				       WQ_UNBOUND | WQ_HIGHPRI, 0);
 	if (!linfo->workq) {
 		ret = -ENOMEM;
 		goto out;
@@ -525,7 +525,7 @@ static int process_response(struct scoutfs_net_connection *conn,
 	struct super_block *sb = conn->sb;
 	struct message_send *msend;
 	scoutfs_net_response_t resp_func = NULL;
-	void *resp_data;
+	void *resp_data = NULL;

 	spin_lock(&conn->lock);

@@ -804,7 +804,7 @@ static void scoutfs_net_recv_worker(struct work_struct *work)
 			if (invalid_message(conn, nh)) {
 				scoutfs_inc_counter(sb, net_recv_invalid_message);
 				ret = -EBADMSG;
-				break;
+				goto out;
 			}

 			data_len = le16_to_cpu(nh->data_len);
@@ -1113,11 +1113,11 @@ static int sock_opts_and_names(struct super_block *sb,
 	if (ret)
 		goto out;

-	ret = kc_kernel_getsockname(sock, (struct sockaddr *)&conn->sockname);
+	ret = kernel_getsockname(sock, (struct sockaddr *)&conn->sockname);
 	if (ret < 0)
 		goto out;

-	ret = kc_kernel_getpeername(sock, (struct sockaddr *)&conn->peername);
+	ret = kernel_getpeername(sock, (struct sockaddr *)&conn->peername);
 	if (ret < 0)
 		goto out;

@@ -1218,7 +1218,7 @@ static void scoutfs_net_connect_worker(struct work_struct *work)

 	trace_scoutfs_net_connect_work_enter(sb, 0, 0);

-	ret = kc_sock_create_kern(AF_INET, SOCK_STREAM, IPPROTO_TCP, &sock);
+	ret = sock_create_kern(&init_net, AF_INET, SOCK_STREAM, IPPROTO_TCP, &sock);
 	if (ret)
 		goto out;

@@ -1517,8 +1517,7 @@ scoutfs_net_alloc_conn(struct super_block *sb,
 		conn->ordered_proc_wlists = kmalloc_array(nr, sizeof(struct scoutfs_work_list),
 							  GFP_NOFS);
 		conn->workq = alloc_workqueue("scoutfs_net_%s",
-					      WQ_UNBOUND | WQ_NON_REENTRANT, 0,
-					      name_suffix);
+					      WQ_UNBOUND, 0, name_suffix);
 	}
 	if (!conn || (info_size && !conn->info) || !conn->workq || !conn->ordered_proc_wlists) {
 		if (conn) {
@@ -1630,7 +1629,7 @@ int scoutfs_net_bind(struct super_block *sb,
 	if (WARN_ON_ONCE(conn->sock))
 		return -EINVAL;

-	ret = kc_sock_create_kern(AF_INET, SOCK_STREAM, IPPROTO_TCP, &sock);
+	ret = sock_create_kern(&init_net, AF_INET, SOCK_STREAM, IPPROTO_TCP, &sock);
 	if (ret)
 		goto out;

@@ -1651,7 +1650,7 @@ int scoutfs_net_bind(struct super_block *sb,
 	if (ret < 0)
 		goto out;

-	ret = kc_kernel_getsockname(sock, (struct sockaddr *)&conn->sockname);
+	ret = kernel_getsockname(sock, (struct sockaddr *)&conn->sockname);
 	if (ret < 0)
 		goto out;

@@ -2099,11 +2098,9 @@ int scoutfs_net_setup(struct super_block *sb)
 	scoutfs_tseq_tree_init(&ninf->msg_tseq_tree, net_tseq_show_msg);

 	ninf->shutdown_workq = alloc_workqueue("scoutfs_net_shutdown",
-					       WQ_UNBOUND | WQ_NON_REENTRANT,
-					       0);
+					       WQ_UNBOUND, 0);
 	ninf->destroy_workq = alloc_workqueue("scoutfs_net_destroy",
-					       WQ_UNBOUND | WQ_NON_REENTRANT,
-					       0);
+					       WQ_UNBOUND, 0);
 	if (!ninf->shutdown_workq || !ninf->destroy_workq) {
 		ret = -ENOMEM;
 		goto out;
@@ -183,7 +183,7 @@ static int create_socket(struct super_block *sb)
 	int addrlen;
 	int ret;

-	ret = kc_sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
+	ret = sock_create_kern(&init_net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
 	if (ret) {
 		scoutfs_err(sb, "quorum couldn't create udp socket: %d", ret);
 		goto out;
@@ -1332,8 +1332,7 @@ int scoutfs_quorum_setup(struct super_block *sb)

 	/* a high priority single threaded context without mem reclaim */
 	qinf->workq = alloc_workqueue("scoutfs_quorum_work",
-				       WQ_NON_REENTRANT | WQ_UNBOUND |
-				       WQ_HIGHPRI, 1);
+				       WQ_UNBOUND | WQ_HIGHPRI, 1);
 	if (!qinf->workq) {
 		ret = -ENOMEM;
 		goto out;
@@ -34,6 +34,7 @@
 #include "totl.h"
 #include "util.h"
 #include "quota.h"
+#include "trans.h"
 #include "counters.h"
 #include "scoutfs_trace.h"

@@ -1086,6 +1087,10 @@ int scoutfs_quota_mod_rule(struct super_block *sb, bool is_add,
 	if (ret < 0)
 		goto out;

+	ret = scoutfs_hold_trans(sb, true);
+	if (ret < 0)
+		goto out;
+
 	down_write(&qtinf->rwsem);

 	if (is_add) {
@@ -1095,28 +1100,31 @@ int scoutfs_quota_mod_rule(struct super_block *sb, bool is_add,
 		else if (ret == 0)
 			ret = -EEXIST;
 		if (ret < 0)
-			goto unlock;
+			goto release;

 		rule_to_rule_val(&rv, &rule);
 		ret = scoutfs_item_create(sb, &key, &rv, sizeof(rv), lock);
 		if (ret < 0)
-			goto unlock;
+			goto release;

 	} else {
 		ret = find_rule(sb, &rule, &key, lock) ?:
 		      scoutfs_item_delete(sb, &key, lock);
 		if (ret < 0)
-			goto unlock;
+			goto release;
 	}

+	wait_event(qtinf->waitq, !ruleset_is_busy(qtinf));
 	scoutfs_quota_invalidate(sb);
 	ret = 0;

-unlock:
+release:
 	up_write(&qtinf->rwsem);
-	scoutfs_unlock(sb, lock, SCOUTFS_LOCK_WRITE);
+	scoutfs_release_trans(sb);

 out:
+	scoutfs_unlock(sb, lock, SCOUTFS_LOCK_WRITE);
+
 	if (is_add)
 		trace_scoutfs_quota_add_rule(sb, &rule, ret);
 	else
@@ -1135,12 +1143,17 @@ void scoutfs_quota_get_lock_range(struct scoutfs_key *start, struct scoutfs_key
 }

 /*
- * This is called during cluster lock invalidation to indicate that the
- * ruleset is no longer protected by cluster locking and might have been
- * modified.  We mark the ruleset invalid and free it once all readers
- * drain.  The next check will acquire the cluster lock and read the
- * rules.  Because this is called during invalidation this is serialized
- * with write holders of cluster locks so we can never see -EBUSY here.
+ * Mark the cached ruleset invalid and free the previous one once readers
+ * drain.  Called from cluster lock invalidation and from quota rule
+ * modification.
+ *
+ * Cluster lock invalidation runs only after the lock layer has drained
+ * local READ users.  Since EBUSY is set only while a reader holds READ,
+ * the reader has already published by the time we run.
+ *
+ * Quota rule modification waits on the waitq for any in-flight reader
+ * to publish before calling here, so the next check rebuilds against
+ * the newly written rules rather than the reader's stale result.
 */
 void scoutfs_quota_invalidate(struct super_block *sb)
 {
@@ -1154,13 +1167,10 @@ void scoutfs_quota_invalidate(struct super_block *sb)

 	spin_lock(&qtinf->lock);
 	rs = rcu_dereference_protected(qtinf->ruleset, lockdep_is_held(&qtinf->lock));
-	if (rs != ERR_PTR(-EINVAL))
+	if (rs == ERR_PTR(-ENOENT) || !IS_ERR(rs))
 		rcu_assign_pointer(qtinf->ruleset, ERR_PTR(-EINVAL));
 	spin_unlock(&qtinf->lock);

-	/* cluster locking should have prevented this */
-	BUG_ON(rs == ERR_PTR(-EBUSY));
-
 	if (!IS_ERR(rs))
 		call_rcu(&rs->rcu, free_ruleset_rcu);

@@ -134,7 +134,7 @@ static int recov_finished(struct recov_info *recinf)

 static void timer_callback(struct timer_list *timer)
 {
-	struct recov_info *recinf = from_timer(recinf, timer, timer);
+	struct recov_info *recinf = timer_container_of(recinf, timer, timer);

 	recinf->timeout_fn(recinf->sb);
 }
@@ -1077,8 +1077,7 @@ static int next_log_merge_range(struct super_block *sb, struct scoutfs_btree_roo
 	struct scoutfs_key key;
 	int ret;

-	key = *start;
-	key.sk_zone = SCOUTFS_LOG_MERGE_RANGE_ZONE;
+	init_log_merge_key(&key, SCOUTFS_LOG_MERGE_RANGE_ZONE, 0, 0);
 	scoutfs_key_set_ones(&rng->start);

 	do {
@@ -4752,7 +4751,7 @@ int scoutfs_server_setup(struct super_block *sb)
 	INIT_DELAYED_WORK(&server->reclaim_dwork, reclaim_worker);

 	server->wq = alloc_workqueue("scoutfs_server",
-				     WQ_UNBOUND | WQ_NON_REENTRANT, 0);
+				     WQ_UNBOUND, 0);
 	if (!server->wq) {
 		kfree(server);
 		return -ENOMEM;
@@ -2392,8 +2392,7 @@ int scoutfs_srch_setup(struct super_block *sb)
 		goto out;

 	srinf->workq = alloc_workqueue("scoutfs_srch_compact",
-				       WQ_NON_REENTRANT | WQ_UNBOUND |
-				       WQ_HIGHPRI, 0);
+				       WQ_UNBOUND | WQ_HIGHPRI, 0);
 	if (!srinf->workq) {
 		ret = -ENOMEM;
 		goto out;
@@ -30,6 +30,11 @@ void scoutfs_totl_merge_init(struct scoutfs_totl_merging *merg)
 	memset(merg, 0, sizeof(struct scoutfs_totl_merging));
 }

+/*
+ * bin the incoming merge inputs so that we can resolve delta items
+ * properly. Finalized logs that are merge inputs are kept separately
+ * from those that are not.
+ */
 void scoutfs_totl_merge_contribute(struct scoutfs_totl_merging *merg,
 				   u64 seq, u8 flags, void *val, int val_len, int fic)
 {
@@ -39,10 +44,10 @@ void scoutfs_totl_merge_contribute(struct scoutfs_totl_merging *merg,
 		merg->fs_seq = seq;
 		merg->fs_total = le64_to_cpu(tval->total);
 		merg->fs_count = le64_to_cpu(tval->count);
-	} else if (fic & FIC_FINALIZED) {
-		merg->fin_seq = seq;
-		merg->fin_total += le64_to_cpu(tval->total);
-		merg->fin_count += le64_to_cpu(tval->count);
+	} else if (fic & FIC_MERGE_INPUT) {
+		merg->inp_seq = seq;
+		merg->inp_total += le64_to_cpu(tval->total);
+		merg->inp_count += le64_to_cpu(tval->count);
 	} else {
 		merg->log_seq = seq;
 		merg->log_total += le64_to_cpu(tval->total);
@@ -53,15 +58,18 @@ void scoutfs_totl_merge_contribute(struct scoutfs_totl_merging *merg,
 /*
 * .totl. item merging has to be careful because the log btree merging
 * code can write partial results to the fs_root.  This means that a
- * reader can see both cases where new finalized logs should be applied
- * to the old fs items and where old finalized logs have already been
- * applied to the partially merged fs items.  Currently active logged
- * items are always applied on top of all cases.
+ * reader can see both cases where merge input deltas should be applied
+ * to the old fs items and where they have already been applied to the
+ * partially merged fs items.
+ *
+ * Only finalized log trees that are inputs to the current merge cycle
+ * are tracked in the inp_ bucket.  Finalized trees that aren't merge
+ * inputs and active log trees are always applied unconditionally since
+ * they cannot be in fs_root.
 *
 * These cases are differentiated with a combination of sequence numbers
- * in items, the count of contributing xattrs, and a flag
- * differentiating finalized and active logged items.  This lets us
- * recognize all cases, including when finalized logs were merged and
+ * in items and the count of contributing xattrs.  This lets us
+ * recognize all cases, including when merge inputs were merged and
 * deleted the fs item.
 */
 void scoutfs_totl_merge_resolve(struct scoutfs_totl_merging *merg, __u64 *total, __u64 *count)
@@ -75,14 +83,14 @@ void scoutfs_totl_merge_resolve(struct scoutfs_totl_merging *merg, __u64 *total,
 		*count = merg->fs_count;
 	}

-	/* apply finalized logs if they're newer or creating */
-	if (((merg->fs_seq != 0) && (merg->fin_seq > merg->fs_seq)) ||
-	    ((merg->fs_seq == 0) && (merg->fin_count > 0))) {
-		*total += merg->fin_total;
-		*count += merg->fin_count;
+	/* apply merge input deltas if they're newer or creating */
+	if (((merg->fs_seq != 0) && (merg->inp_seq > merg->fs_seq)) ||
+	    ((merg->fs_seq == 0) && (merg->inp_count > 0))) {
+		*total += merg->inp_total;
+		*count += merg->inp_count;
 	}

-	/* always apply active logs which must be newer than fs and finalized */
+	/* always apply non-input finalized and active logs */
 	if (merg->log_seq > 0) {
 		*total += merg->log_total;
 		*count += merg->log_count;
@@ -7,9 +7,9 @@ struct scoutfs_totl_merging {
 	u64 fs_seq;
 	u64 fs_total;
 	u64 fs_count;
-	u64 fin_seq;
-	u64 fin_total;
-	s64 fin_count;
+	u64 inp_seq;
+	u64 inp_total;
+	s64 inp_count;
 	u64 log_seq;
 	u64 log_total;
 	s64 log_count;
@@ -46,6 +46,7 @@ static char *names[] = {
 	[SCOUTFS_TRIGGER_SRCH_MERGE_STOP_SAFE] = "srch_merge_stop_safe",
 	[SCOUTFS_TRIGGER_STATFS_LOCK_PURGE] = "statfs_lock_purge",
 	[SCOUTFS_TRIGGER_RECLAIM_SKIP_FINALIZE] = "reclaim_skip_finalize",
+	[SCOUTFS_TRIGGER_LOG_MERGE_FORCE_PARTIAL] = "log_merge_force_partial",
 };

 bool scoutfs_trigger_test_and_clear(struct super_block *sb, unsigned int t)
@@ -9,6 +9,7 @@ enum scoutfs_trigger {
 	SCOUTFS_TRIGGER_SRCH_MERGE_STOP_SAFE,
 	SCOUTFS_TRIGGER_STATFS_LOCK_PURGE,
 	SCOUTFS_TRIGGER_RECLAIM_SKIP_FINALIZE,
+	SCOUTFS_TRIGGER_LOG_MERGE_FORCE_PARTIAL,
 	SCOUTFS_TRIGGER_NR,
 };

@@ -46,7 +46,6 @@ static struct scoutfs_tseq_entry *tseq_rb_next(struct scoutfs_tseq_entry *ent)
 	return rb_entry(node, struct scoutfs_tseq_entry, node);
 }

-#ifdef KC_RB_TREE_AUGMENTED_COMPUTE_MAX
 static bool tseq_compute_total(struct scoutfs_tseq_entry *ent, bool exit)
 {
 	loff_t total = 1 + tseq_node_total(ent->node.rb_left) +
@@ -61,17 +60,6 @@ static bool tseq_compute_total(struct scoutfs_tseq_entry *ent, bool exit)

 RB_DECLARE_CALLBACKS(static, tseq_rb_callbacks, struct scoutfs_tseq_entry,
 		     node, total, tseq_compute_total);
-#else
-
-static loff_t tseq_compute_total(struct scoutfs_tseq_entry *ent)
-{
-	return 1 + tseq_node_total(ent->node.rb_left) +
-	       tseq_node_total(ent->node.rb_right);
-}
-
-RB_DECLARE_CALLBACKS(static, tseq_rb_callbacks, struct scoutfs_tseq_entry,
-		     node, loff_t, total, tseq_compute_total);
-#endif

 void scoutfs_tseq_tree_init(struct scoutfs_tseq_tree *tree,
 			    scoutfs_tseq_show_t show)
@@ -95,6 +95,7 @@ struct wkic_info {
 	/* block reading slow path */
 	struct mutex roots_mutex;
 	struct scoutfs_net_roots roots;
+	u64 merge_input_seq;
 	u64 roots_read_seq;
 	ktime_t roots_expire;

@@ -805,29 +806,79 @@ static void free_page_list(struct super_block *sb, struct list_head *list)
 * read_seq number so that we can compare the age of the items in cached
 * pages.  Only one request to refresh the roots is in progress at a
 * time.  This is the slow path that's only used when the cache isn't
- * populated and the roots aren't cached.  The root request is fast
- * enough, especially compared to the resulting item reading IO, that we
- * don't mind hiding it behind a trivial mutex.
+ * populated and the roots aren't cached.
+ *
+ * We read roots directly from the on-disk superblock rather than
+ * requesting them from the server so that we can also read the
+ * log_merge btree from the same superblock.  The merge status item
+ * seq tells us which finalized log trees are inputs to the current
+ * merge, which is needed to correctly resolve totl delta items.
 */
-static int get_roots(struct super_block *sb, struct wkic_info *winf,
-		     struct scoutfs_net_roots *roots_ret, u64 *read_seq, bool force_new)
+static int refresh_roots(struct super_block *sb, struct wkic_info *winf)
+{
+	struct scoutfs_super_block *super;
+	struct scoutfs_log_merge_status *stat;
+	SCOUTFS_BTREE_ITEM_REF(iref);
+	struct scoutfs_key key;
+	int ret;
+
+	super = kmalloc(sizeof(*super), GFP_NOFS);
+	if (!super)
+		return -ENOMEM;
+
+	ret = scoutfs_read_super(sb, super);
+	if (ret < 0)
+		goto out;
+
+	winf->roots = (struct scoutfs_net_roots){
+		.fs_root = super->fs_root,
+		.logs_root = super->logs_root,
+		.srch_root = super->srch_root,
+	};
+
+	winf->merge_input_seq = 0;
+	if (super->log_merge.ref.blkno) {
+		scoutfs_key_set_zeros(&key);
+		key.sk_zone = SCOUTFS_LOG_MERGE_STATUS_ZONE;
+		ret = scoutfs_btree_lookup(sb, &super->log_merge, &key, &iref);
+		if (ret == 0) {
+			if (iref.val_len == sizeof(*stat)) {
+				stat = iref.val;
+				winf->merge_input_seq = le64_to_cpu(stat->seq);
+			} else {
+				ret = -EUCLEAN;
+			}
+			scoutfs_btree_put_iref(&iref);
+		} else if (ret == -ENOENT) {
+			ret = 0;
+		}
+		if (ret < 0)
+			goto out;
+	}
+
+	winf->roots_read_seq++;
+	winf->roots_expire = ktime_add_ms(ktime_get_raw(), WKIC_CACHE_LIFETIME_MS);
+out:
+	kfree(super);
+	return ret;
+}
+
+static int get_roots(struct super_block *sb, struct wkic_info *winf,
+		     struct scoutfs_net_roots *roots_ret, u64 *merge_input_seq,
+		     u64 *read_seq, bool force_new)
 {
-	struct scoutfs_net_roots roots;
 	int ret;

 	mutex_lock(&winf->roots_mutex);

 	if (force_new || ktime_before(winf->roots_expire, ktime_get_raw())) {
-		ret = scoutfs_client_get_roots(sb, &roots);
+		ret = refresh_roots(sb, winf);
 		if (ret < 0)
 			goto out;
-
-		winf->roots = roots;
-		winf->roots_read_seq++;
-		winf->roots_expire = ktime_add_ms(ktime_get_raw(), WKIC_CACHE_LIFETIME_MS);
 	}

 	*roots_ret = winf->roots;
+	*merge_input_seq = winf->merge_input_seq;
 	*read_seq = winf->roots_read_seq;
 	ret = 0;
 out:
@@ -870,24 +921,30 @@ static int insert_read_pages(struct super_block *sb, struct wkic_info *winf,
 	struct scoutfs_key end;
 	struct wkic_page *wpage;
 	LIST_HEAD(pages);
-	u64 read_seq;
+	u64 merge_input_seq;
+	u64 read_seq = 0;
 	int ret;

 	ret = 0;
 retry_stale:
-	ret = get_roots(sb, winf, &roots, &read_seq, ret == -ESTALE);
+	ret = get_roots(sb, winf, &roots, &merge_input_seq, &read_seq, ret == -ESTALE);
 	if (ret < 0)
-		goto out;
+		goto check_stale;

 	start = *range_start;
 	end = *range_end;
-	ret = scoutfs_forest_read_items_roots(sb, &roots, key, range_start, &start, &end,
-					      read_items_cb, &root);
+	ret = scoutfs_forest_read_items_roots(sb, &roots, merge_input_seq, key, range_start,
+					      &start, &end, read_items_cb, &root);
 	trace_scoutfs_wkic_read_items(sb, key, &start, &end);
+check_stale:
 	ret = scoutfs_block_check_stale(sb, ret, &saved, &roots.fs_root.ref, &roots.logs_root.ref);
 	if (ret < 0) {
-		if (ret == -ESTALE)
+		if (ret == -ESTALE) {
+			/* not safe to retry due to delta items, must restart clean */
+			free_item_tree(&root);
+			root = RB_ROOT;
 			goto retry_stale;
+		}
 		goto out;
 	}

@@ -16,6 +16,7 @@
 #include <linux/xattr.h>
 #include <linux/crc32c.h>
 #include <linux/posix_acl.h>
+#include <linux/iversion.h>

 #include "format.h"
 #include "inode.h"
@@ -994,38 +995,17 @@ unlock:
 	return ret;
 }

-#ifndef KC_XATTR_STRUCT_XATTR_HANDLER
-/*
- * Future kernels have this amazing hack to rewind the name to get the
- * skipped prefix.  We're back in the stone ages without the handler
- * arg, so we Just Know that this is possible.  This will become a
- * compat hook to either call the kernel's xattr_full_name(handler), or
- * our hack to use the flags as the prefix length.
- */
-static const char *full_name_hack(const char *name, int len)
-{
-	return name - len;
-}
-#endif

 static int scoutfs_xattr_get_handler
-#ifdef KC_XATTR_STRUCT_XATTR_HANDLER
 		(const struct xattr_handler *handler, struct dentry *dentry,
 		 struct inode *inode, const char *name, void *value,
 		 size_t size)
 {
 	name = xattr_full_name(handler, name);
-#else
-		(struct dentry *dentry, const char *name,
-		 void *value, size_t size, int handler_flags)
-{
-	name = full_name_hack(name, handler_flags);
-#endif
 	return scoutfs_xattr_get(dentry, name, value, size);
 }

 static int scoutfs_xattr_set_handler
-#ifdef KC_XATTR_STRUCT_XATTR_HANDLER
 		(const struct xattr_handler *handler,
 		 KC_VFS_NS_DEF
 		 struct dentry *dentry,
@@ -1033,12 +1013,6 @@ static int scoutfs_xattr_set_handler
 		 size_t size, int flags)
 {
 	name = xattr_full_name(handler, name);
-#else
-		(struct dentry *dentry, const char *name,
-		 const void *value, size_t size, int flags, int handler_flags)
-{
-	name = full_name_hack(name, handler_flags);
-#endif
 	return scoutfs_xattr_set(dentry, name, value, size, flags);
 }

@@ -1071,22 +1045,14 @@ static const struct xattr_handler scoutfs_xattr_security_handler = {
 };

 static const struct xattr_handler scoutfs_xattr_acl_access_handler = {
-#ifdef KC_XATTR_HANDLER_NAME
 	.name   = XATTR_NAME_POSIX_ACL_ACCESS,
-#else
-	.prefix = XATTR_NAME_POSIX_ACL_ACCESS,
-#endif
 	.flags  = ACL_TYPE_ACCESS,
 	.get    = scoutfs_acl_get_xattr,
 	.set    = scoutfs_acl_set_xattr,
 };

 static const struct xattr_handler scoutfs_xattr_acl_default_handler = {
-#ifdef KC_XATTR_HANDLER_NAME
 	.name   = XATTR_NAME_POSIX_ACL_DEFAULT,
-#else
-	.prefix = XATTR_NAME_POSIX_ACL_DEFAULT,
-#endif
 	.flags  = ACL_TYPE_DEFAULT,
 	.get    = scoutfs_acl_get_xattr,
 	.set    = scoutfs_acl_set_xattr,
@@ -1265,6 +1231,7 @@ int scoutfs_xattr_drop(struct super_block *sb, u64 ino,
 			ret = parse_indx_key(&tag_key, xat->name, xat->name_len, ino);
 			if (ret < 0)
 				goto out;
+			scoutfs_xattr_set_indx_key_xid(&tag_key, le64_to_cpu(key.skx_id));
 		}

 		if ((tgs.totl || tgs.indx) && locked_zone != tag_key.sk_zone) {
@@ -12,3 +12,4 @@ src/o_tmpfile_umask
 src/o_tmpfile_linkat
 src/mmap_stress
 src/mmap_validate
+src/totl-delta-inject
@@ -15,7 +15,8 @@ BIN := src/createmany			\
 	src/o_tmpfile_umask		\
 	src/o_tmpfile_linkat		\
 	src/mmap_stress			\
-	src/mmap_validate
+	src/mmap_validate		\
+	src/totl-delta-inject

 DEPS := $(wildcard src/*.d)

@@ -20,9 +20,6 @@ t_filter_fs()
 # [ 2687.691366] BUG: KASAN: stack-out-of-bounds in get_reg+0x1bc/0x230
 # ...
 # [ 2687.706220] ==================================================================
-# [ 2687.707284] Disabling lock debugging due to kernel taint
-#
-# That final lock debugging message may not be included.
 #
 ignore_harmless_unwind_kasan_stack_oob()
 {
@@ -46,10 +43,6 @@ awk '
 		saved=""
        }
        ( in_soob == 2 && $0 ~ /==================================================================/ ) {
-                in_soob = 3
-                soob_nr = NR
-        }
-        ( in_soob == 3 && NR > soob_nr && $0 !~ /Disabling lock debugging/ ) {
                in_soob = 0
        }
        ( !in_soob ) { print $0 }
@@ -61,6 +54,58 @@ awk '
 '
 }

+#
+# in el97+, XFS can generate a spurious lockdep circular dependency
+# warning about reclaim. Fixed upstream in e.g. v5.7-rc4-129-g6dcde60efd94
+#
+ignore_harmless_xfs_lockdep_warning()
+{
+awk '
+	BEGIN {
+		in_block = 0
+		block_nr = 0
+		buf = ""
+	}
+	( !in_block && $0 ~ /======================================================/ ) {
+		in_block = 1
+		block_nr = NR
+		buf = $0 "\n"
+		next
+	}
+	( in_block == 1 && NR == (block_nr + 1) ) {
+		if (match($0, /WARNING: possible circular locking dependency detected/) != 0) {
+			in_block = 2
+			buf = buf $0 "\n"
+		} else {
+			in_block = 0
+			printf "%s", buf
+			print $0
+			buf = ""
+		}
+		next
+	}
+	( in_block == 2 ) {
+		buf = buf $0 "\n"
+		if ($0 ~ /<\/TASK>/) {
+			if (buf ~ /xfs_(nondir_|dir_)?ilock_class/ && buf ~ /fs_reclaim/) {
+				# known xfs lockdep false positive, discard
+			} else {
+				printf "%s", buf
+			}
+			in_block = 0
+			buf = ""
+		}
+		next
+	}
+	{ print $0 }
+	END {
+		if (buf) {
+			printf "%s", buf
+		}
+	}
+'
+}
+
 #
 # Filter out expected messages.  Putting messages here implies that
 # tests aren't relying on messages to discover failures.. they're
@@ -126,6 +171,13 @@ t_filter_dmesg()
 	# orphan log trees reclaim is handled, not an error
 	re="$re|scoutfs .* reclaiming orphan log trees"

+	# nfs can emit a whole range of messages we can ignore
+	re="$re|Installing knfsd .*"
+	re="$re|nfsd: .*"
+	re="$re|NFSD: .*"
+	re="$re|RPC: .*"
+	re="$re|FS-Cache: .*"
+
 	# fencing tests force unmounts and trigger timeouts
 	re="$re|scoutfs .* forcing unmount"
 	re="$re|scoutfs .* reconnect timed out"
@@ -176,6 +228,10 @@ t_filter_dmesg()
 	# creating block devices may trigger this
 	re="$re|block device autoloading is deprecated and will be removed."

+	# lockdep or kasan warnings can cause this
+	re="$re|Disabling lock debugging due to kernel taint"
+
 	egrep -v "($re)" | \
-		ignore_harmless_unwind_kasan_stack_oob
+		ignore_harmless_unwind_kasan_stack_oob | \
+		ignore_harmless_xfs_lockdep_warning
 }
@@ -0,0 +1,32 @@
+== write via NFS, read both sides
+== POSIX ACL set via NFS, read both sides
+user::rw-
+user:22222:rw-
+group::r--
+mask::rw-
+other::r--
+
+user::rw-
+user:22222:rw-
+group::r--
+mask::rw-
+other::r--
+
+== POSIX ACL set on scoutfs, read via NFS
+user::rw-
+user:22222:rw-
+group::r--
+group:44444:r--
+mask::rw-
+other::r--
+
+== default ACL inheritance via NFS
+user::rw-
+user:22222:rwx	#effective:rw-
+group::r-x	#effective:r--
+mask::rw-
+other::r--
+
+== NFS read demand-stages a released file
+1
+== cleanup
@@ -0,0 +1,54 @@
+== testing invalid read-xattr-index arguments
+bad index position entry argument 'bad', it must be in the form "a.b.ino" where each value can be prefixed by '0' for octal or '0x' for hex
+scoutfs: read-xattr-index failed: Invalid argument (22)
+bad index position entry argument '1.2', it must be in the form "a.b.ino" where each value can be prefixed by '0' for octal or '0x' for hex
+scoutfs: read-xattr-index failed: Invalid argument (22)
+initial major index position '256' must be between 0 and 255, inclusive.
+scoutfs: read-xattr-index failed: Invalid argument (22)
+first index position 1.2.3 must be less than last index position 0.0.0
+scoutfs: read-xattr-index failed: Invalid argument (22)
+first index position 1.2.0 must be less than last index position 1.1.2
+scoutfs: read-xattr-index failed: Invalid argument (22)
+first index position 2.2.2 must be less than last index position 2.2.1
+scoutfs: read-xattr-index failed: Invalid argument (22)
+== testing invalid names
+setfattr: /mnt/test/test/basic-xattr-indx/invalid: Invalid argument
+setfattr: /mnt/test/test/basic-xattr-indx/invalid: Invalid argument
+setfattr: /mnt/test/test/basic-xattr-indx/invalid: Invalid argument
+setfattr: /mnt/test/test/basic-xattr-indx/invalid: Invalid argument
+setfattr: /mnt/test/test/basic-xattr-indx/invalid: Invalid argument
+setfattr: /mnt/test/test/basic-xattr-indx/invalid: Invalid argument
+setfattr: /mnt/test/test/basic-xattr-indx/invalid: Invalid argument
+setfattr: /mnt/test/test/basic-xattr-indx/invalid: Invalid argument
+setfattr: /mnt/test/test/basic-xattr-indx/invalid: Invalid argument
+setfattr: /mnt/test/test/basic-xattr-indx/invalid: Invalid argument
+setfattr: /mnt/test/test/basic-xattr-indx/invalid: Invalid argument
+setfattr: /mnt/test/test/basic-xattr-indx/invalid: Numerical result out of range
+== testing boundary values
+0.0 found
+255.max found
+== indx xattr must have no value
+setfattr: /mnt/test/test/basic-xattr-indx/noval: Invalid argument
+setfattr: /mnt/test/test/basic-xattr-indx/noval: Invalid argument
+== set indx xattr and verify index entry
+found
+== setting same indx xattr again is a no-op
+found
+== removing non-existent indx xattr succeeds
+setfattr: /mnt/test/test/basic-xattr-indx/file: No such attribute
+still found
+== explicit xattr removal cleans up index entry
+== file deletion cleans up index entry
+found before delete
+== multiple indx xattrs on one file cleaned up by deletion
+entries before delete: 2
+entries after delete: 0
+== partial removal leaves other entries
+300 found
+== multiple files at same index position
+files at same position: 2
+surviving file found
+== cross-mount visibility
+found on mount 1
+== duplicate position deduplication
+entries for same position: 1
@@ -8,10 +8,10 @@
 /mnt/test/test/data-prealloc/file-1: extents: 32
 /mnt/test/test/data-prealloc/file-2: extents: 32
 == any writes to region prealloc get full extents
-/mnt/test/test/data-prealloc/file-1: extents: 4
-/mnt/test/test/data-prealloc/file-2: extents: 4
-/mnt/test/test/data-prealloc/file-1: extents: 4
-/mnt/test/test/data-prealloc/file-2: extents: 4
+/mnt/test/test/data-prealloc/file-1: extents: 8
+/mnt/test/test/data-prealloc/file-2: extents: 8
+/mnt/test/test/data-prealloc/file-1: extents: 8
+/mnt/test/test/data-prealloc/file-2: extents: 8
 == streaming offline writes get full extents either way
 /mnt/test/test/data-prealloc/file-1: extents: 4
 /mnt/test/test/data-prealloc/file-2: extents: 4
@@ -20,8 +20,8 @@
 == goofy preallocation amounts work
 /mnt/test/test/data-prealloc/file-1: extents: 6
 /mnt/test/test/data-prealloc/file-2: extents: 6
-/mnt/test/test/data-prealloc/file-1: extents: 6
-/mnt/test/test/data-prealloc/file-2: extents: 6
+/mnt/test/test/data-prealloc/file-1: extents: 10
+/mnt/test/test/data-prealloc/file-2: extents: 10
 /mnt/test/test/data-prealloc/file-1: extents: 3
 /mnt/test/test/data-prealloc/file-2: extents: 3
 == block writes into region allocs hole
@@ -1,4 +0,0 @@
-== ensuring utils and module for old versions
-== unmounting test fs and removing test module
-== testing combinations of old and new format versions
-== restoring test module and mount
@@ -0,0 +1,6 @@
+== setup
+== concurrent quota mod and check across mounts
+== verify quota rules are consistent after race
+== verify file creation still works under quota
+file visible on mount 1
+== cleanup
@@ -0,0 +1,10 @@
+== setup three files contributing to totl 8888.0.0
+== merge baseline into fs_root
+8888.0.0 = 42, 3
+== inject (+128, +2) unbalances totl 8888.0.0
+8888.0.0 = 170, 5
+== unlink f3 (value 32) produces a -32/-1 delta
+8888.0.0 = 138, 4
+== inject (-128, -2) restores accounting for the remaining files
+8888.0.0 = 10, 2
+== cleanup
@@ -0,0 +1,3 @@
+== setup
+expected 4681
+== cleanup
@@ -694,8 +694,8 @@ for t in $tests; do
 		if [ "$sts" == "$T_PASS_STATUS" ]; then
 			dmesg | t_filter_dmesg > "$T_TMPDIR/dmesg.after"
 			diff --old-line-format="" --unchanged-line-format="" \
-				"$T_TMPDIR/dmesg.before" "$T_TMPDIR/dmesg.after" > \
-				"$T_TMPDIR/dmesg.new"
+				"$T_TMPDIR/dmesg.before" "$T_TMPDIR/dmesg.after" | \
+				grep -v '^$' > "$T_TMPDIR/dmesg.new"

 			if [ -s "$T_TMPDIR/dmesg.new" ]; then
 				message="unexpected messages in dmesg"
@@ -3,6 +3,7 @@ basic-block-counts.sh
 basic-bad-mounts.sh
 basic-posix-acl.sh
 basic-acl-consistency.sh
+basic-nfs.sh
 inode-items-updated.sh
 simple-inode-index.sh
 simple-staging.sh
@@ -18,7 +19,6 @@ offline-extent-waiting.sh
 move-blocks.sh
 projects.sh
 large-fragmented-free.sh
-format-version-forward-back.sh
 enospc.sh
 mmap.sh
 srch-safe-merge-pos.sh
@@ -26,7 +26,11 @@ srch-basic-functionality.sh
 simple-xattr-unit.sh
 retention-basic.sh
 totl-xattr-tag.sh
+basic-xattr-indx.sh
 quota.sh
+totl-merge-read.sh
+quota-invalidate-race.sh
+totl-delta-inject.sh
 lock-refleak.sh
 lock-shrink-consistency.sh
 lock-shrink-read-race.sh
@@ -0,0 +1,121 @@
+/*
+ * Test helper that calls SCOUTFS_IOC_INJECT_TOTL_DELTA to seed
+ * arbitrary totl deltas.
+ *
+ * Copyright (C) 2026 Versity Software, Inc.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ */
+
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE
+#endif
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdint.h>
+#include <inttypes.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <sys/ioctl.h>
+#include <linux/types.h>
+
+#include "ioctl.h"
+
+static void usage(const char *prog)
+{
+	fprintf(stderr,
+		"Usage: %s <mountpoint> <a>.<b>.<c> <total> <count>\n",
+		prog);
+	exit(2);
+}
+
+static int parse_s64(const char *s, int64_t *out)
+{
+	char *end;
+	int64_t v;
+
+	errno = 0;
+	v = strtoll(s, &end, 0);
+	if (errno || *end != '\0' || end == s)
+		return -1;
+	*out = v;
+	return 0;
+}
+
+/*
+ * Parse "<a>.<b>.<c>" into abc[0..2] (skxt_a, skxt_b, skxt_c).  Each
+ * component must be a non-empty unsigned base-0 integer.
+ */
+static int parse_dotted_name(const char *s, uint64_t abc[3])
+{
+	const char *p = s;
+	char *end;
+	int i;
+
+	for (i = 0; i < 3; i++) {
+		if (*p == '\0' || *p == '.')
+			return -1;
+		errno = 0;
+		abc[i] = strtoull(p, &end, 0);
+		if (errno || end == p)
+			return -1;
+
+		if (i < 2) {
+			if (*end != '.')
+				return -1;
+			p = end + 1;
+		} else {
+			if (*end != '\0')
+				return -1;
+		}
+	}
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	struct scoutfs_ioctl_inject_totl_delta itd = {{0,}};
+	uint64_t abc[3];
+	int64_t total, count;
+	int fd;
+	int ret;
+
+	if (argc != 5)
+		usage(argv[0]);
+
+	if (parse_dotted_name(argv[2], abc) ||
+	    parse_s64(argv[3], &total) ||
+	    parse_s64(argv[4], &count)) {
+		fprintf(stderr, "could not parse arguments\n");
+		usage(argv[0]);
+	}
+
+	itd.name[0] = abc[0];
+	itd.name[1] = abc[1];
+	itd.name[2] = abc[2];
+	itd.total = total;
+	itd.count = count;
+
+	fd = open(argv[1], O_RDONLY | O_DIRECTORY);
+	if (fd < 0) {
+		fprintf(stderr, "open(%s): %s\n", argv[1], strerror(errno));
+		return 1;
+	}
+
+	ret = ioctl(fd, SCOUTFS_IOC_INJECT_TOTL_DELTA, &itd);
+	if (ret < 0) {
+		fprintf(stderr,
+			"INJECT_TOTL_DELTA(%" PRIu64 ".%" PRIu64 ".%" PRIu64
+			", total=%" PRId64 ", count=%" PRId64 "): %s\n",
+			abc[0], abc[1], abc[2], total, count, strerror(errno));
+		close(fd);
+		return 1;
+	}
+
+	close(fd);
+	return 0;
+}
@@ -0,0 +1,86 @@
+#
+# Test basic scoutfs-nfs interactions:
+# - read/write
+# - stage/release and data wait
+# - nfs setacl/getacl mapping
+#
+
+t_require_commands scoutfs setfacl getfacl exportfs mount.nfs umount \
+		   stat dd cmp systemctl
+
+systemctl start nfs-server >> "$T_TMPDIR/nfs.log" 2>&1 || \
+	t_skip "nfs-server not available"
+
+# Keep file creation modes deterministic for the ACL golden output.
+umask 022
+
+EXPORT_OPTS="rw,async,no_root_squash,no_subtree_check,fsid=42"
+NFS_MNT="$T_TMP.nfs"
+NFS_DIR="$NFS_MNT/test/basic-nfs"
+
+filter() { sed "s@$T_TMPDIR@T_TMPDIR@g" | t_filter_fs; }
+gf() { getfacl -n --omit-header "$@" 2>/dev/null; }
+
+teardown_nfs()
+{
+	(
+		umount "$NFS_MNT"
+		exportfs -u "127.0.0.1:$T_M0"
+		exportfs -f
+		systemctl stop nfs-server
+		rmdir "$NFS_MNT"
+	) >> "$T_TMPDIR/nfs.log" 2>&1
+}
+trap teardown_nfs EXIT
+
+exportfs -u "127.0.0.1:$T_M0" >> "$T_TMPDIR/nfs.log" 2>&1 || true
+t_quiet mkdir -p "$NFS_MNT"
+exportfs -o "$EXPORT_OPTS" "127.0.0.1:$T_M0" >> "$T_TMPDIR/nfs.log" 2>&1
+mount.nfs -o vers=3,noac,actimeo=0 "127.0.0.1:$T_M0" "$NFS_MNT" >> "$T_TMPDIR/nfs.log" 2>&1
+
+test -d "$NFS_DIR" || t_fail "test dir $NFS_DIR not visible over NFS"
+
+echo "== write via NFS, read both sides"
+dd if=/dev/urandom bs=4096 count=1 of="$T_TMP.data" status=none
+cp "$T_TMP.data" "$NFS_DIR/file"
+cmp "$T_TMP.data" "$T_D0/file"
+cmp "$T_TMP.data" "$NFS_DIR/file"
+
+echo "== POSIX ACL set via NFS, read both sides"
+setfacl -m u:22222:rw "$NFS_DIR/file" 2>&1 | filter
+gf "$NFS_DIR/file"
+gf "$T_D0/file"
+
+echo "== POSIX ACL set on scoutfs, read via NFS"
+setfacl -m g:44444:r "$T_D0/file" 2>&1 | filter
+gf "$NFS_DIR/file"
+
+echo "== default ACL inheritance via NFS"
+mkdir "$NFS_DIR/d"
+setfacl -d -m u:22222:rwx "$NFS_DIR/d" 2>&1 | filter
+touch "$NFS_DIR/d/child"
+gf "$NFS_DIR/d/child"
+
+echo "== NFS read demand-stages a released file"
+dd if=/dev/urandom bs=4096 count=1 of="$T_TMP.big" status=none
+cp "$T_TMP.big" "$T_D0/big"
+sync
+vers=$(scoutfs stat -s data_version "$T_D0/big")
+t_quiet scoutfs release "$T_D0/big" -V "$vers" -o 0 -l 4K
+
+# NFS read against the offline file blocks in scoutfs_read waiting
+# for the data to come back online.
+cat "$NFS_DIR/big" > "$T_TMP.read" &
+read_pid=$!
+sleep 1
+scoutfs data-waiting -B 0 -I 0 -p "$T_D0" | wc -l
+
+t_quiet scoutfs stage "$T_TMP.big" "$T_D0/big" -V "$vers" -o 0 -l 4096
+wait "$read_pid"
+cmp "$T_TMP.big" "$T_TMP.read"
+
+echo "== cleanup"
+rm -f "$T_D0/file" "$T_D0/big"
+rm -rf "$T_D0/d"
+
+t_pass
@@ -0,0 +1,143 @@
+#
+# Test basic .indx. xattr tag functionality and index entry lifecycle
+#
+
+t_require_commands touch rm setfattr scoutfs stat
+t_require_mounts 2
+
+# query index from a specific mount, default mount 0
+read_xattr_index()
+{
+	local nr="${1:-0}"
+	local mnt="$(eval echo \$T_M$nr)"
+	shift
+
+	sync
+	echo 1 > $(t_debugfs_path $nr)/drop_weak_item_cache
+	scoutfs read-xattr-index -p "$mnt" "$@"
+}
+
+MAJOR=5
+MINOR=100
+
+echo "== testing invalid read-xattr-index arguments"
+scoutfs read-xattr-index -p "$T_M0" bad 2>&1
+scoutfs read-xattr-index -p "$T_M0" 1.2 2>&1
+scoutfs read-xattr-index -p "$T_M0" 1.2.3 256.0.0 2>&1
+scoutfs read-xattr-index -p "$T_M0" 1.2.3 0.0.0 2>&1
+scoutfs read-xattr-index -p "$T_M0" 1.2.0 1.1.2 2>&1
+scoutfs read-xattr-index -p "$T_M0" 2.2.2 2.2.1 2>&1
+
+echo "== testing invalid names"
+touch "$T_D0/invalid"
+setfattr -n scoutfs.hide.indx.test.$MAJOR "$T_D0/invalid" 2>&1 | t_filter_fs
+setfattr -n scoutfs.hide.indx.test "$T_D0/invalid" 2>&1 | t_filter_fs
+setfattr -n scoutfs.hide.indx.test.. "$T_D0/invalid" 2>&1 | t_filter_fs
+setfattr -n scoutfs.hide.indx.test..$MINOR "$T_D0/invalid" 2>&1 | t_filter_fs
+setfattr -n scoutfs.hide.indx.test.$MAJOR. "$T_D0/invalid" 2>&1 | t_filter_fs
+setfattr -n scoutfs.hide.indx.test.256.$MINOR "$T_D0/invalid" 2>&1 | t_filter_fs
+setfattr -n scoutfs.hide.indx.test.abc.$MINOR "$T_D0/invalid" 2>&1 | t_filter_fs
+setfattr -n scoutfs.hide.indx.test.$MAJOR.abc "$T_D0/invalid" 2>&1 | t_filter_fs
+setfattr -n scoutfs.hide.indx.test.-1.$MINOR "$T_D0/invalid" 2>&1 | t_filter_fs
+setfattr -n scoutfs.hide.indx.test.$MAJOR.-1 "$T_D0/invalid" 2>&1 | t_filter_fs
+setfattr -n scoutfs.hide.indx.test.18446744073709551616.$MINOR "$T_D0/invalid" 2>&1 | t_filter_fs
+setfattr -n scoutfs.hide.indx.$(printf 'x%.0s' $(seq 1 240)).$MAJOR.$MINOR "$T_D0/invalid" 2>&1 | t_filter_fs
+rm -f "$T_D0/invalid"
+
+echo "== testing boundary values"
+touch "$T_D0/boundary"
+INO=$(stat -c "%i" "$T_D0/boundary")
+setfattr -n scoutfs.hide.indx.test.0.0 "$T_D0/boundary"
+read_xattr_index 0 0.0.0 0.0.-1 | awk '($3 == "'$INO'") {print "0.0 found"}'
+setfattr -x scoutfs.hide.indx.test.0.0 "$T_D0/boundary"
+setfattr -n scoutfs.hide.indx.test.255.18446744073709551615 "$T_D0/boundary"
+read_xattr_index 0 255.0.0 255.-1.-1 | awk '($3 == "'$INO'") {print "255.max found"}'
+setfattr -x scoutfs.hide.indx.test.255.18446744073709551615 "$T_D0/boundary"
+rm -f "$T_D0/boundary"
+
+echo "== indx xattr must have no value"
+touch "$T_D0/noval"
+setfattr -n scoutfs.hide.indx.test.$MAJOR.$MINOR -v "" "$T_D0/noval" 2>&1 | t_filter_fs
+setfattr -n scoutfs.hide.indx.test.$MAJOR.$MINOR -v 0 "$T_D0/noval" 2>&1 | t_filter_fs
+setfattr -n scoutfs.hide.indx.test.$MAJOR.$MINOR -v 1 "$T_D0/noval" 2>&1 | t_filter_fs
+rm -f "$T_D0/noval"
+
+echo "== set indx xattr and verify index entry"
+touch "$T_D0/file"
+INO=$(stat -c "%i" "$T_D0/file")
+setfattr -n scoutfs.hide.indx.test.$MAJOR.$MINOR "$T_D0/file"
+read_xattr_index 0 $MAJOR.0.0 $MAJOR.-1.-1 | awk '($3 == "'$INO'") {print "found"}'
+
+echo "== setting same indx xattr again is a no-op"
+setfattr -n scoutfs.hide.indx.test.$MAJOR.$MINOR "$T_D0/file"
+read_xattr_index 0 $MAJOR.0.0 $MAJOR.-1.-1 | awk '($3 == "'$INO'") {print "found"}'
+
+echo "== removing non-existent indx xattr succeeds"
+setfattr -x scoutfs.hide.indx.nonexistent.$MAJOR.999 "$T_D0/file" 2>&1 | t_filter_fs
+read_xattr_index 0 $MAJOR.0.0 $MAJOR.-1.-1 | awk '($3 == "'$INO'") {print "still found"}'
+
+echo "== explicit xattr removal cleans up index entry"
+setfattr -x scoutfs.hide.indx.test.$MAJOR.$MINOR "$T_D0/file"
+read_xattr_index 0 $MAJOR.0.0 $MAJOR.-1.-1 | awk '($3 == "'$INO'") {print "found orphan"}'
+rm -f "$T_D0/file"
+
+echo "== file deletion cleans up index entry"
+touch "$T_D0/file2"
+INO=$(stat -c "%i" "$T_D0/file2")
+setfattr -n scoutfs.hide.indx.test.$MAJOR.$MINOR "$T_D0/file2"
+read_xattr_index 0 $MAJOR.0.0 $MAJOR.-1.-1 | awk '($3 == "'$INO'") {print "found before delete"}'
+rm -f "$T_D0/file2"
+read_xattr_index 0 $MAJOR.0.0 $MAJOR.-1.-1 | awk '($3 == "'$INO'") {print "found orphan after delete"}'
+
+echo "== multiple indx xattrs on one file cleaned up by deletion"
+touch "$T_D0/file3"
+INO=$(stat -c "%i" "$T_D0/file3")
+setfattr -n scoutfs.hide.indx.a.$MAJOR.200 "$T_D0/file3"
+setfattr -n scoutfs.hide.indx.b.$MAJOR.300 "$T_D0/file3"
+BEFORE=$(read_xattr_index 0 $MAJOR.0.0 $MAJOR.-1.-1 | awk '($3 == "'$INO'")' | wc -l)
+echo "entries before delete: $BEFORE"
+rm -f "$T_D0/file3"
+AFTER=$(read_xattr_index 0 $MAJOR.0.0 $MAJOR.-1.-1 | awk '($3 == "'$INO'")' | wc -l)
+echo "entries after delete: $AFTER"
+
+echo "== partial removal leaves other entries"
+touch "$T_D0/partial"
+INO=$(stat -c "%i" "$T_D0/partial")
+setfattr -n scoutfs.hide.indx.a.$MAJOR.200 "$T_D0/partial"
+setfattr -n scoutfs.hide.indx.b.$MAJOR.300 "$T_D0/partial"
+setfattr -x scoutfs.hide.indx.a.$MAJOR.200 "$T_D0/partial"
+read_xattr_index 0 $MAJOR.200.0 $MAJOR.200.-1 | awk '($3 == "'$INO'") {print "200 found"}'
+read_xattr_index 0 $MAJOR.300.0 $MAJOR.300.-1 | awk '($3 == "'$INO'") {print "300 found"}'
+rm -f "$T_D0/partial"
+
+echo "== multiple files at same index position"
+touch "$T_D0/multi_a" "$T_D0/multi_b"
+INO_A=$(stat -c "%i" "$T_D0/multi_a")
+INO_B=$(stat -c "%i" "$T_D0/multi_b")
+setfattr -n scoutfs.hide.indx.test.$MAJOR.$MINOR "$T_D0/multi_a"
+setfattr -n scoutfs.hide.indx.test.$MAJOR.$MINOR "$T_D0/multi_b"
+COUNT=$(read_xattr_index 0 $MAJOR.$MINOR.0 $MAJOR.$MINOR.-1 | wc -l)
+echo "files at same position: $COUNT"
+rm -f "$T_D0/multi_a"
+read_xattr_index 0 $MAJOR.$MINOR.0 $MAJOR.$MINOR.-1 | awk '($3 == "'$INO_A'") {print "deleted file still found"}'
+read_xattr_index 0 $MAJOR.$MINOR.0 $MAJOR.$MINOR.-1 | awk '($3 == "'$INO_B'") {print "surviving file found"}'
+rm -f "$T_D0/multi_b"
+
+echo "== cross-mount visibility"
+touch "$T_D0/file4"
+INO=$(stat -c "%i" "$T_D0/file4")
+setfattr -n scoutfs.hide.indx.test.$MAJOR.$MINOR "$T_D0/file4"
+read_xattr_index 1 $MAJOR.0.0 $MAJOR.-1.-1 | awk '($3 == "'$INO'") {print "found on mount 1"}'
+rm -f "$T_D0/file4"
+read_xattr_index 1 $MAJOR.0.0 $MAJOR.-1.-1 | awk '($3 == "'$INO'") {print "found orphan on mount 1"}'
+
+echo "== duplicate position deduplication"
+touch "$T_D0/file5"
+INO=$(stat -c "%i" "$T_D0/file5")
+setfattr -n scoutfs.hide.indx.aa.$MAJOR.$MINOR "$T_D0/file5"
+setfattr -n scoutfs.hide.indx.bb.$MAJOR.$MINOR "$T_D0/file5"
+COUNT=$(read_xattr_index 0 $MAJOR.0.0 $MAJOR.-1.-1 | awk '($3 == "'$INO'")' | wc -l)
+echo "entries for same position: $COUNT"
+rm -f "$T_D0/file5"
+
+t_pass
@@ -1,184 +0,0 @@
-#
-# Test our basic ability to work with different format versions.
-#
-# The current code being tested has a range of supported format
-# versions.   For each of the older supported format versions we have a
-# git hash of the commit before the next greater version was introduced.
-# We build versions of the scoutfs utility and kernel module for the
-# last commit in tree that had a lesser supported version as its max
-# supported version.   We use those binaries to test forward and back
-# compat as new and old code works with a persistent volume with a given
-# format version.
-#
-
-# not supported on el8 or higher
-if [ $(source /etc/os-release ; echo ${VERSION_ID:0:1}) -gt 7 ]; then
-	t_skip_permitted "Unsupported OS version"
-fi
-
-mount_has_format_version()
-{
-	local mnt="$1"
-	local vers="$2"
-	local sysfs_fmt_vers="$(t_sysfs_path_from_mnt $SCR)/format_version"
-
-	test "$(cat $sysfs_fmt_vers)" == "$vers"
-}
-
-SCR="/mnt/scoutfs.scratch"
-
-MIN=$(modinfo $T_MODULE | awk '($1 == "scoutfs_format_version_min:"){print $2}')
-MAX=$(modinfo $T_MODULE | awk '($1 == "scoutfs_format_version_max:"){print $2}')
-
-echo "min: $MIN max: $MAX" > "$T_TMP.log"
-
-test "$MIN" -gt 0 -a "$MAX" -gt 0 -a "$MIN" -le "$MAX" || \
-	t_fail "parsed bad versions, min: $MIN max: $MAX"
-
-test "$MIN" == "$MAX" && \
-	t_skip "only one supported format version: $MIN"
-
-# prepare dir and wipe any weird old partial state
-builds="$T_RESULTS/format_version_builds"
-mkdir -p "$builds"
-
-echo "== ensuring utils and module for old versions"
-declare -A commits
-commits[1]=c3c4b080
-for vers in $(seq $MIN $((MAX - 1))); do
-	dir="$builds/$vers"
-	platform=$(uname -rp)
-	buildmark="$dir/buildmark"
-	commit="${commits[$vers]}"
-
-	test -n "$commit" || \
-		t_fail "no commit for vers $vers"
-
-	# have our files for this version
-	test "$(cat $buildmark 2>&1)" == "$platform" && \
-		continue
-
-	# build as one big sequence of commands that can return failure
-	(
-		set -o pipefail
-
-		rm -rf $dir							&&
-		mkdir -p $dir/building						&&
-		cd "$T_TESTS/.."						&&
-		git archive --format=tar "$commit" | tar -C "$dir/building" -xf - &&
-		cd -								&&
-		find $dir							&&
-		make -C "$dir/building"						&&
-		mv $dir/building/utils/src/scoutfs $dir				&&
-		mv $dir/building/kmod/src/scoutfs.ko $dir			&&
-		rm -rf $dir/building						&&
-		echo "$platform" > $buildmark					&&
-		find $dir							&&
-		cat $buildmark
-	) >> "$T_TMP.log" 2>&1 || t_fail "version $vers build failed"
-done
-
-echo "== unmounting test fs and removing test module"
-t_quiet t_umount_all
-t_quiet rmmod scoutfs
-
-echo "== testing combinations of old and new format versions"
-mkdir -p "$SCR"
-for vers in $(seq $MIN $((MAX - 1))); do
-	old_scoutfs="$builds/$vers/scoutfs"
-	old_module="$builds/$vers/scoutfs.ko"
-
-	echo "mkfs $vers" >> "$T_TMP.log"
-	t_quiet $old_scoutfs mkfs -f -Q 0,127.0.0.1,$T_SCRATCH_PORT "$T_EX_META_DEV" "$T_EX_DATA_DEV" \
-		|| t_fail "mkfs $vers failed"
-
-	echo "mount $vers with $vers" >> "$T_TMP.log"
-	t_quiet insmod $old_module
-	t_quiet mount -t scoutfs -o metadev_path=$T_EX_META_DEV,quorum_slot_nr=0 \
-		"$T_EX_DATA_DEV" "$SCR"
-	t_quiet mount_has_format_version "$SCR" "$vers"
-
-	echo "creating files in $vers" >> "$T_TMP.log"
-	t_quiet touch "$SCR/file-"{1,2,3}
-	stat "$SCR"/file-* > "$T_TMP.stat" || \
-		t_fail "stat in $vers failed"
-
-	echo "remounting $vers fs with $MAX" >> "$T_TMP.log"
-	t_quiet umount "$SCR"
-	rmmod scoutfs
-	insmod "$T_MODULE"
-	t_quiet mount -t scoutfs -o metadev_path=$T_EX_META_DEV,quorum_slot_nr=0 \
-		"$T_EX_DATA_DEV" "$SCR"
-	t_quiet mount_has_format_version "$SCR" "$vers"
-
-	echo "verifying stat in $vers with $MAX" >> "$T_TMP.log"
-	diff -u "$T_TMP.stat" <(stat "$SCR"/file-*)
-
-	echo "keep/update/del existing, create new in $vers" >> "$T_TMP.log"
-	t_quiet touch "$SCR/file-2"
-	t_quiet rm -f "$SCR/file-3"
-	t_quiet touch "$SCR/file-4"
-	stat "$SCR"/file-* > "$T_TMP.stat" || \
-		t_fail "stat in $vers failed"
-
-	echo "remounting $vers fs with $vers" >> "$T_TMP.log"
-	t_quiet umount "$SCR"
-	rmmod scoutfs
-	insmod "$old_module"
-	t_quiet mount -t scoutfs -o metadev_path=$T_EX_META_DEV,quorum_slot_nr=0 \
-		"$T_EX_DATA_DEV" "$SCR"
-	t_quiet mount_has_format_version "$SCR" "$vers"
-
-	echo "verifying stat in $vers with $vers" >> "$T_TMP.log"
-	diff -u "$T_TMP.stat" <(stat "$SCR"/file-*)
-
-	echo "changing format vers to $MAX" >> "$T_TMP.log"
-	t_quiet umount "$SCR"
-	rmmod scoutfs
-	t_quiet scoutfs change-format-version -F -V $MAX $T_EX_META_DEV "$T_EX_DATA_DEV"
-
-	echo "mount fs $MAX with old $vers should fail" >> "$T_TMP.log"
-	insmod "$old_module"
-	mount -t scoutfs -o metadev_path=$T_EX_META_DEV,quorum_slot_nr=0 \
-		"$T_EX_DATA_DEV" "$SCR" >> "$T_TMP.log" 2>&1
-	if [ "$?" == "0" ]; then
-		umount "$SCR"
-		t_fail "old code ver $vers able to mount new ver $MAX"
-	fi
-
-	echo "remounting $MAX fs with $MAX" >> "$T_TMP.log"
-	rmmod scoutfs
-	insmod "$T_MODULE"
-	t_quiet mount -t scoutfs -o metadev_path=$T_EX_META_DEV,quorum_slot_nr=0 \
-		"$T_EX_DATA_DEV" "$SCR"
-	t_quiet mount_has_format_version "$SCR" "$MAX"
-
-	echo "verifying stat in $MAX with $MAX" >> "$T_TMP.log"
-	diff -u "$T_TMP.stat" <(stat "$SCR"/file-*)
-
-	echo "keep/update/del existing, create new in $MAX" >> "$T_TMP.log"
-	t_quiet touch "$SCR/file-2"
-	t_quiet rm -f "$SCR/file-4"
-	t_quiet touch "$SCR/file-5"
-	stat "$SCR"/file-* > "$T_TMP.stat" || \
-		t_fail "stat in $MAX failed"
-
-	echo "remounting $MAX fs with $MAX again" >> "$T_TMP.log"
-	t_quiet umount "$SCR"
-	t_quiet mount -t scoutfs -o metadev_path=$T_EX_META_DEV,quorum_slot_nr=0 \
-		"$T_EX_DATA_DEV" "$SCR"
-	t_quiet mount_has_format_version "$SCR" "$MAX"
-
-	echo "verifying stat in $MAX with $MAX again" >> "$T_TMP.log"
-	diff -u "$T_TMP.stat" <(stat "$SCR"/file-*)
-
-	echo "done with old vers $vers" >> "$T_TMP.log"
-	t_quiet umount "$SCR"
-	rmmod scoutfs
-done
-
-echo "== restoring test module and mount"
-insmod "$T_MODULE"
-t_mount_all
-
-t_pass
@@ -0,0 +1,70 @@
+#
+# Regression for the BUG_ON in scoutfs_quota_invalidate when a concurrent
+# ruleset read on one mount races with a quota rule modification.
+#
+
+t_require_mounts 2
+
+TEST_UID=22222
+SET_UID="--ruid=$TEST_UID --euid=$TEST_UID"
+
+echo "== setup"
+mkdir -p "$T_D0/dir"
+chown --quiet $TEST_UID "$T_D0/dir"
+
+# totl xattr gives quota checks something to consult
+setfattr -n scoutfs.totl.test.1.1.1 -v 1 "$T_D0/dir"
+
+echo "== concurrent quota mod and check across mounts"
+
+(
+	for i in $(seq 1 20); do
+		scoutfs quota-add -p "$T_M0" \
+			-r "1 1,L,- 1,L,- $i,L,- I 999999 -" 2>/dev/null
+		scoutfs quota-del -p "$T_M0" \
+			-r "1 1,L,- 1,L,- $i,L,- I 999999 -" 2>/dev/null
+	done
+) &
+MOD_PID=$!
+
+# same mount as the mod: races local read against invalidate
+(
+	for i in $(seq 1 50); do
+		setpriv $SET_UID touch "$T_D0/dir/race0_$i" 2>/dev/null
+		rm -f "$T_D0/dir/race0_$i"
+	done
+) &
+CHECK0_PID=$!
+
+# other mount: drives cross-node lock traffic
+(
+	for i in $(seq 1 50); do
+		setpriv $SET_UID touch "$T_D1/dir/race1_$i" 2>/dev/null
+		rm -f "$T_D1/dir/race1_$i"
+	done
+) &
+CHECK1_PID=$!
+
+t_quiet wait $MOD_PID
+t_quiet wait $CHECK0_PID
+t_quiet wait $CHECK1_PID
+
+echo "== verify quota rules are consistent after race"
+scoutfs quota-wipe -p "$T_M0"
+scoutfs quota-list -p "$T_M0"
+
+echo "== verify file creation still works under quota"
+scoutfs quota-add -p "$T_M0" -r "1 1,L,- 1,L,- 1,L,- I 999999 -"
+sync
+echo 1 > $(t_debugfs_path)/drop_weak_item_cache
+echo 1 > $(t_debugfs_path)/drop_quota_check_cache
+setpriv $SET_UID touch "$T_D0/dir/verify_file"
+test -f "$T_D1/dir/verify_file" && echo "file visible on mount 1"
+rm -f "$T_D0/dir/verify_file"
+scoutfs quota-wipe -p "$T_M0"
+
+echo "== cleanup"
+setfattr -x scoutfs.totl.test.1.1.1 "$T_D0/dir"
+rm -rf "$T_D0/dir"
+
+t_pass
@@ -0,0 +1,43 @@
+#
+# Exercise the SCOUTFS_IOC_INJECT_TOTL_DELTA ioctl that injects totl
+# deltas directly via totl-delta-inject(1).
+#
+
+t_require_commands setfattr scoutfs sync rm touch totl-delta-inject
+
+# force a log merge then read-xattr-totals filtered to our own keys
+read_totals()
+{
+	t_force_log_merge
+	sync
+	echo 1 > $(t_debugfs_path)/drop_weak_item_cache
+	scoutfs read-xattr-totals -p "$T_M0" | \
+		grep -E '^8888\.' || true
+}
+
+echo "== setup three files contributing to totl 8888.0.0"
+touch "$T_D0/f1" "$T_D0/f2" "$T_D0/f3"
+setfattr -n scoutfs.totl.inj.8888.0.0 -v 2  "$T_D0/f1"
+setfattr -n scoutfs.totl.inj.8888.0.0 -v 8  "$T_D0/f2"
+setfattr -n scoutfs.totl.inj.8888.0.0 -v 32 "$T_D0/f3"
+
+echo "== merge baseline into fs_root"
+read_totals
+
+echo "== inject (+128, +2) unbalances totl 8888.0.0"
+totl-delta-inject "$T_M0" 8888.0.0 128 2
+read_totals
+
+echo "== unlink f3 (value 32) produces a -32/-1 delta"
+rm -f "$T_D0/f3"
+read_totals
+
+echo "== inject (-128, -2) restores accounting for the remaining files"
+totl-delta-inject "$T_M0" 8888.0.0 -128 -2
+read_totals
+
+echo "== cleanup"
+rm -f "$T_D0/f1" "$T_D0/f2"
+read_totals
+
+t_pass
@@ -0,0 +1,50 @@
+#
+# Test that merge_read_item() correctly updates the sequence number when
+# combining delta items from multiple finalized log trees.  Each mount
+# sets a totl value in its own 3-bit lane (powers of 8) so that any
+# double-counting overflows the lane and is caught by: or(v, exp) != exp.
+#
+
+t_require_commands setfattr scoutfs
+t_require_mounts 5
+
+echo "== setup"
+for nr in $(t_fs_nrs); do
+	d=$(eval echo \$T_D$nr)
+	for i in $(seq 1 2500); do : > "$d/f$nr$i"; done
+done
+sync
+t_force_log_merge
+
+vals=(1 8 64 512 4096)
+expected=4681
+n=0
+for nr in $(t_fs_nrs); do
+	d=$(eval echo \$T_D$nr)
+	v=${vals[$((n++))]}
+	for i in $(seq 1 2500); do
+		setfattr -n "scoutfs.totl.t.$i.0.0" -v $v "$d/f$nr$i"
+	done
+done
+
+t_trigger_arm_silent log_merge_force_partial $(t_server_nr)
+
+bad="$T_TMPDIR/bad"
+for nr in $(t_fs_nrs); do
+	( while true; do
+		echo 1 > "$(t_debugfs_path $nr)/drop_weak_item_cache"
+		scoutfs read-xattr-totals -p "$(eval echo \$T_M$nr)" | \
+			awk -F'[ =,]+' -v e=$expected 'or($2+0,e) != e'
+	done ) >> "$bad" &
+done
+
+echo "expected $expected"
+t_force_log_merge
+t_silent_kill $(jobs -p)
+test -s "$bad" && echo "double-counted:" && cat "$bad"
+
+echo "== cleanup"
+for nr in $(t_fs_nrs); do
+	find "$(eval echo \$T_D$nr)" -name "f$nr*" -delete
+done
+t_pass