Keep dist suffix

Sanitize kversion
Add kernel version to package release var
2026-01-29 06:42:03 +00:00 · 2024-09-26 12:12:03 -07:00 · 2024-09-26 12:09:00 -07:00 · 2024-09-26 12:02:51 -07:00
128 changed files with 2425 additions and 8036 deletions
--- a/ReleaseNotes.md
+++ b/ReleaseNotes.md
@@ -1,133 +1,6 @@
 Versity ScoutFS Release Notes
 =============================

---
-v1.27
-\
-*Jan 15, 2026*
-
-Switch away from using the general VM cache reclaim machinery to reduce
-idle cluster locks in the client.  The VM treated locks like a cache and
-let many accumulate, presuming that it would be efficient to free them
-in batches.  Lock freeing requires network communication so this could
-result in enormous backlogs in network messages (on the order of
-hundreds of thousands) and could result in signifcant delays of other
-network messaging.
-
-Fix inefficient network receive processing while many messages are in
-the send queue.  This consumed sufficient CPU to cause significant
-stalls, perhaps resulting in hung task warning messages due to delayed
-lock message delivery.
-
-Fix a server livelock case that could happen while committing client
-transactions that contain a large amount of freed file data extents.
-This would present as client tasks hanging and a server task spinning
-consuming cpu.
-
-Fix a rare server request processing failure that doesn't deal with
-retransmission of a request that a previous server partially processed.
-This would present as hung client tasks and repeated "error -2
-committing log merge: getting merge status item" kernel messages.
-
-Fix an unneccessary server shutdown during specific circumstances in
-client lock recovery.  The shutdown was due to server state and was
-ultimately harmless.  The next server that started up would proceed
-accordingly.
-
---
-v1.26
-\
-*Nov 17, 2025*
-
-Add the ino\_alloc\_per\_lock mount option.  This changes the number of
-inode numbers allocated under each cluster lock and can alleviate lock
-contention for some patterns of larger file creation.
-
-Add the tcp\_keepalive\_timeout\_ms mount option.  This can enable the
-system to survive longer periods of networking outages.
-
-Fix a rare double free of internal btree metadata blocks when merging
-log trees.  The duplicated freed metadata block numbers would cause
-persistent errors in the server, preventing the server from starting and
-hanging the system.
-
-Fix the data\_wait interface to not require the correct data\_version of
-the inode when raising an error.  This lets callers raise errors when
-they're unable to recall the details of the inode to discover its
-data\_version.
-
-Change scoutfs to more aggressively reclaim cached memory when under
-memory pressure.  This makes scoutfs behave more like other kernel
-components and it integrates better with the reclaim policy heuristics
-in the VM core of the kernel.
-
-Change scoutfs to more efficiently transmit and receive socket messages.
-Under heavy load this can process messages sufficiently more quickly to
-avoid hung task messages for tasks that were waiting for cluster lock
-messages to be processed.
-
-Fix faulty server block commit budget calculations that were generating
-spurious "holders exceeded alloc budget" console messages.
-
---
-v1.25
-\
-*Jun 3, 2025*
-
-Fix a bug that could cause indefinite retries of failed client commits.
-Under specific error conditions the client and server's understanding of
-the current client commit could get out of sync.  The client would retry
-commits indefinitely that could never succeed.  This manifested as
-infinite "critical transaction commit failure" messages in the kernel
-log on the client and matching "error <nr> committing client logs" on
-the server.
-
-Fix a bug in a specific case of server error handling that could result
-in sending references to unwritten blocks to the client.  The client
-would try to read blocks that hadn't been written and return spurious
-errors.  This was seen under low free space conditions on the server and
-resulted in error messages with error code 116 (The errno enum for
-ESTALE, the client's indication that it couldn't read the blocks that it
-expected.)
-
---
-v1.24
-\
-*Mar 14, 2025*
-
-Add support for coherent read and write mmap() mappings of regular file
-data between mounts.
-
-Fix a bug that was causing scoutfs utilities to parse and change some
-file names before passing them on to the kernel for processing.  This
-fixes spurious scoutfs command errors for files with the offending
-patterns in their names.
-
-Fix a bug where rename wasn't updating the ctime of the inode at the
-destination name if it existed.
-
---
-v1.23
-\
-*Dec 11, 2024*
-
-Add support for kernels in the RHEL 9.5 minor release.
-
---
-v1.22
-\
-*Nov 1, 2024*
-
-Add support for building against the RHEL9 family of kernels.
-
-Fix failure of the setattr\_more ioctl() to set the attributes of a
-zero-length file when restoring.
-
-Fix support for POSIX ACLs in the RHEL8 and later family of kernels.
-
-Fix a race condition in the lock server that could drop lock requests
-under heavy load and cause cluster lock attempts to hang.
-
 ---
 v1.21
 \
--- a/kmod/Makefile
+++ b/kmod/Makefile
@@ -5,6 +5,13 @@ ifeq ($(SK_KSRC),)
 SK_KSRC := $(shell echo /lib/modules/`uname -r`/build)
 endif

+# fail if sparse fails if we find it
+ifeq ($(shell sparse && echo found),found)
+SP =
+else
+SP = @:
+endif
+
 SCOUTFS_GIT_DESCRIBE ?= \
 	$(shell git describe --all --abbrev=6 --long 2>/dev/null || \
 		echo no-git)
@@ -29,7 +36,9 @@ TARFILE = scoutfs-kmod-$(RPM_VERSION).tar
 all: module

 module:
-	$(MAKE) CHECK=$(CURDIR)/src/sparse-filtered.sh C=1 CF="-D__CHECK_ENDIAN__" $(SCOUTFS_ARGS)
+	$(MAKE) $(SCOUTFS_ARGS)
+	$(SP) $(MAKE) C=2 CF="-D__CHECK_ENDIAN__" $(SCOUTFS_ARGS)
+

 modules_install:
 	$(MAKE) $(SCOUTFS_ARGS) modules_install
--- a/kmod/scoutfs-kmod.spec.in
+++ b/kmod/scoutfs-kmod.spec.in
@@ -4,13 +4,18 @@
 %define kmod_git_describe @@GITDESCRIBE@@
 %define pkg_date %(date +%%Y%%m%%d)

+# Disable the building of the debug package(s).
+%define debug_package %{nil}
+
 # take kernel version or default to uname -r
 %{!?kversion: %global kversion %(uname -r)}
 %global kernel_version %{kversion}
+%global sanitized_kversion %(echo %{kernel_version} | sed -e 's/-/_/g' -e 's/\.el.*//')

 %if 0%{?el7}
 %global kernel_source() /usr/src/kernels/%{kernel_version}.$(arch)
-%else
+%endif
+%if 0%{?el8}
 %global kernel_source() /usr/src/kernels/%{kernel_version}
 %endif

@@ -18,19 +23,21 @@

 %if 0%{?el7}
 Name:           %{kmod_name}
-%else
+%endif
+%if 0%{?el8}
 Name:           kmod-%{kmod_name}
 %endif
 Summary:        %{kmod_name} kernel module
 Version:        %{kmod_version}
-Release:        %{_release}%{?dist}
+Release:        %{_release}+%{sanitized_kversion}%{?dist}
 License:        GPLv2
 Group:          System/Kernel
 URL:            http://scoutfs.org/

 %if 0%{?el7}
 BuildRequires:  %{kernel_module_package_buildreqs}
-%else
+%endif
+%if 0%{?el8}
 BuildRequires:  elfutils-libelf-devel
 %endif
 BuildRequires:  kernel-devel-uname-r = %{kernel_version}
@@ -48,23 +55,10 @@ Source:		%{kmod_name}-kmod-%{kmod_version}.tar
 %endif

 %global install_mod_dir extra/%{kmod_name}
-
-%if ! 0%{?el7}
+%if 0%{?el8}
 %global flavors_to_build x86_64
 %endif

-# el9 sanity: make sure we lock to the minor release we built for and block upgrades
-%{lua:
-  if string.match(rpm.expand("%{dist}"), "%.el9") then
-    rpm.define("el9 1")
-  end
-}
-
-%if 0%{?el9}
-%define release_major_minor 9.%{lua: print(rpm.expand("%{dist}"):match("%.el9_(%d)"))}
-Requires: system-release = %{release_major_minor}
-%endif
-
 %description
 %{kmod_name} - kernel module

@@ -100,7 +94,7 @@ done
 # mark modules executable so that strip-to-file can strip them
 find %{buildroot} -type f -name \*.ko -exec %{__chmod} u+x \{\} \;

-%if ! 0%{?el7}
+%if 0%{?el8}
 %files
 /lib/modules

@@ -118,5 +112,8 @@ SCOUTFS_RPM_NAME=$(rpm -q %{name} | grep "%{version}-%{release}")
 rpm -ql $SCOUTFS_RPM_NAME | grep '\.ko$' > /var/run/%{name}-modules-%{version}-%{release} || true

 %postun
-cat /var/run/%{name}-modules-%{version}-%{release} | weak-modules --remove-modules --no-initramfs
+if [ -x /sbin/weak-modules ]; then
+    cat /var/run/%{name}-modules-%{version}-%{release} | /sbin/weak-modules --remove-modules --no-initramfs
+fi
+
 rm /var/run/%{name}-modules-%{version}-%{release} || true
--- a/kmod/src/Makefile.kernelcompat
+++ b/kmod/src/Makefile.kernelcompat
@@ -6,6 +6,26 @@

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

+#
+# v3.10-rc6-21-gbb6f619b3a49
+#
+# _readdir changes from fop->readdir() to fop->iterate() and from
+# filldir(dirent) to dir_emit(ctx).
+#
+ifneq (,$(shell grep 'iterate.*dir_context' include/linux/fs.h))
+ccflags-y += -DKC_ITERATE_DIR_CONTEXT
+endif
+
+#
+# v3.10-rc6-23-g5f99f4e79abc
+#
+# Helpers including dir_emit_dots() are added in the process of
+# switching dcache_readdir() from fop->readdir() to fop->iterate()
+#
+ifneq (,$(shell grep 'dir_emit_dots' include/linux/fs.h))
+ccflags-y += -DKC_DIR_EMIT_DOTS
+endif
+
 #
 # v3.18-rc2-19-gb5ae6b15bd73
 # 
@@ -58,9 +78,8 @@ endif
 # v4.8-rc1-29-g31051c85b5e2
 #
 # inode_change_ok() removed - replace with setattr_prepare()
-# v5.11-rc4-7-g2f221d6f7b88 removes extern attribute
 #
-ifneq (,$(shell grep 'int setattr_prepare' include/linux/fs.h))
+ifneq (,$(shell grep 'extern int setattr_prepare' include/linux/fs.h))
 ccflags-y += -DKC_SETATTR_PREPARE
 endif

@@ -158,12 +177,21 @@ ifneq (,$(shell grep 'sock_create_kern.*struct net' include/linux/net.h))
 ccflags-y += -DKC_SOCK_CREATE_KERN_NET=1
 endif

+#
+# v3.18-rc6-1619-gc0371da6047a
+#
+# iov_iter is now part of struct msghdr
+#
+ifneq (,$(shell grep 'struct iov_iter.*msg_iter' include/linux/socket.h))
+ccflags-y += -DKC_MSGHDR_STRUCT_IOV_ITER=1
+endif
+
 #
 # v4.17-rc6-7-g95582b008388
 #
 # Kernel has current_time(inode) to uniformly retreive timespec in the right unit
 #
-ifneq (,$(shell grep 'struct timespec64 current_time' include/linux/fs.h))
+ifneq (,$(shell grep 'extern struct timespec64 current_time' include/linux/fs.h))
 ccflags-y += -DKC_CURRENT_TIME_INODE=1
 endif

@@ -230,259 +258,3 @@ endif
 ifneq (,$(shell grep 'static inline const char .xattr_prefix' include/linux/xattr.h))
 ccflags-y += -DKC_XATTR_HANDLER_NAME=1
 endif
-
-#
-# v5.19-rc4-96-g342a72a33407
-#
-# Adds `typedef __u32 __bitwise blk_opf_t` to aid flag checking
-ifneq (,$(shell grep 'typedef __u32 __bitwise blk_opf_t' include/linux/blk_types.h))
-ccflags-y += -DKC_HAVE_BLK_OPF_T=1
-endif
-
-#
-# v5.12-rc6-9-g4f0f586bf0c8
-#
-# list_sort cmp function takes const list_head args
-ifneq (,$(shell grep 'const struct list_head ., const struct list_head .' include/linux/list_sort.h))
-ccflags-y += -DKC_LIST_CMP_CONST_ARG_LIST_HEAD
-endif
-
-# v5.7-523-g88dca4ca5a93
-#
-# The pgprot argument to vmalloc is always PAGE_KERNEL, so it is removed.
-ifneq (,$(shell grep 'extern void .__vmalloc.unsigned long size, gfp_t gfp_mask, pgprot_t prot' include/linux/vmalloc.h))
-ccflags-y += -DKC_VMALLOC_PGPROT_T
-endif
-
-# v6.2-rc1-18-g01beba7957a2
-#
-# fs: port inode_owner_or_capable() to mnt_idmap
-ifneq (,$(shell grep 'bool inode_owner_or_capable.struct user_namespace .mnt_userns' include/linux/fs.h))
-ccflags-y += -DKC_INODE_OWNER_OR_CAPABLE_USERNS
-endif
-
-#
-# v5.11-rc4-5-g47291baa8ddf
-#
-# namei: make permission helpers idmapped mount aware
-ifneq (,$(shell grep 'int inode_permission.struct user_namespace' include/linux/fs.h))
-ccflags-y += -DKC_INODE_PERMISSION_USERNS
-endif
-
-#
-# v5.11-rc4-24-g549c7297717c
-#
-# fs: make helpers idmap mount aware
-# Enlarges the VFS API methods to include user namespace argument.
-ifneq (,$(shell grep 'int ..mknod. .struct user_namespace' include/linux/fs.h))
-ccflags-y += -DKC_VFS_METHOD_USER_NAMESPACE_ARG
-endif
-
-#
-# v6.2-rc1-2-gabf08576afe3
-#
-# fs: vfs methods use struct mnt_idmap instead of struct user_namespace
-ifneq (,$(shell grep 'int vfs_mknod.struct mnt_idmap' include/linux/fs.h))
-ccflags-y += -DKC_VFS_METHOD_MNT_IDMAP_ARG
-endif
-
-#
-# v5.17-rc2-21-g07888c665b40
-#
-# Detect new style bio_alloc - pass bdev and opf.
-ifneq (,$(shell grep 'struct bio .bio_alloc.struct block_device .bdev' include/linux/bio.h))
-ccflags-y += -DKC_BIO_ALLOC_DEV_OPF_ARGS
-endif
-
-#
-# v5.7-rc4-53-gcddf8a2c4a82
-#
-# fiemap_prep() replaces fiemap_check_flags()
-ifneq (,$(shell grep -s 'int fiemap_prep.struct inode' include/linux/fiemap.h))
-ccflags-y += -DKC_FIEMAP_PREP
-endif
-
-#
-# v5.17-13043-g800ba29547e1
-#
-# generic_perform_write args use kiocb for passing filp and pos
-ifneq (,$(shell grep 'ssize_t generic_perform_write.struct kiocb ., struct iov_iter' include/linux/fs.h))
-ccflags-y += -DKC_GENERIC_PERFORM_WRITE_KIOCB_IOV_ITER
-endif
-
-#
-# v5.7-rc6-2496-g76ee0785f42a
-#
-# net: add sock_set_sndtimeo
-ifneq (,$(shell grep 'void sock_set_sndtimeo.struct sock' include/net/sock.h))
-ccflags-y += -DKC_SOCK_SET_SNDTIMEO
-endif
-
-#
-# v5.8-rc4-1931-gba423fdaa589
-#
-# setsockopt functions are now passed a sockptr_t value instead of char*
-ifneq (,$(shell grep -s 'include .linux/sockptr.h.' include/linux/net.h))
-ccflags-y += -DKC_SETSOCKOPT_SOCKPTR_T
-endif
-
-#
-# v5.7-rc6-2507-g71c48eb81c9e
-#
-# Adds a bunch of low level TCP sock parameter functions that we want to use.
-ifneq (,$(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 (,$(shell grep -s '^struct __kernel_old_timeval .' include/uapi/linux/time_types.h))
-ccflags-y += -DKC_KERNEL_OLD_TIMEVAL_STRUCT
-endif
-
-#
-# v5.19-rc4-52-ge33c267ab70d
-#
-# register_shrinker now requires a name, used for debug stats etc.
-ifneq (,$(shell grep 'int __printf.*register_shrinker.struct shrinker .shrinker,' include/linux/shrinker.h))
-ccflags-y += -DKC_SHRINKER_NAME
-endif
-
-#
-# v5.18-rc5-246-gf132ab7d3ab0
-#
-# mpage_readpage() is now replaced with mpage_read_folio.
-ifneq (,$(shell grep 'int mpage_read_folio.struct folio .folio' include/linux/mpage.h))
-ccflags-y += -DKC_MPAGE_READ_FOLIO
-endif
-
-#
-# v5.18-rc5-219-gb3992d1e2ebc
-#
-# block_write_begin() no longer is being passed aop_flags
-ifneq (,$(shell grep -C1 'int block_write_begin' include/linux/buffer_head.h | tail -n 2 | grep 'unsigned flags'))
-ccflags-y += -DKC_BLOCK_WRITE_BEGIN_AOP_FLAGS
-endif
-
-#
-# v6.0-rc6-9-g863f144f12ad
-#
-# the .tmpfile() vfs method calling convention changed and now a struct
-# file* is passed to this metiond instead of a dentry. The function also
-# should open the created file and call finish_open_simple() before returning.
-ifneq (,$(shell grep 'extern void d_tmpfile.struct dentry' include/linux/dcache.h))
-ccflags-y += -DKC_D_TMPFILE_DENTRY
-endif
-
-#
-# v6.4-rc2-201-g0733ad800291
-#
-# New blk_mode_t replaces abuse of fmode_t
-ifneq (,$(shell grep 'typedef unsigned int __bitwise blk_mode_t' include/linux/blkdev.h))
-ccflags-y += -DKC_HAVE_BLK_MODE_T
-endif
-
-#
-# v6.4-rc2-186-g2736e8eeb0cc
-#
-# Reworks FMODE_EXCL kludge and instead modifies the blkdev_put() call to pass in
-# the (exclusive) holder to implement FMODE_EXCL handling.
-ifneq (,$(shell grep 'blkdev_put.struct block_device .bdev, void .holder' include/linux/blkdev.h))
-ccflags-y += -DKC_BLKDEV_PUT_HOLDER_ARG
-endif
-
-#
-# v6.4-rc4-163-g0d625446d0a4
-#
-# Entirely removes current->backing_dev_info to ultimately remove buffer_head
-# completely at some point.
-ifneq (,$(shell grep 'struct backing_dev_info.*backing_dev_info;' include/linux/sched.h))
-ccflags-y += -DKC_CURRENT_BACKING_DEV_INFO
-endif
-
-#
-# v6.8-rc1-4-gf3a608827d1f
-#
-# adds bdev_file_open_by_path() and later in v6.8-rc1-30-ge97d06a46526 removes bdev_open_by_path()
-# which requires us to use the file method from now on.
-ifneq (,$(shell grep 'struct file.*bdev_file_open_by_path.const char.*path' include/linux/blkdev.h))
-ccflags-y += -DKC_BDEV_FILE_OPEN_BY_PATH
-endif
-
-# v4.0-rc7-1796-gfe0f07d08ee3
-#
-# direct-io changes modify inode_dio_done to now be called inode_dio_end
-ifneq (,$(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
-#
-# list_lru_{add,del} -> list_lru_{add,del}_obj
-#
-ifneq (,$(shell grep '^bool list_lru_add_obj' include/linux/list_lru.h))
-ccflags-y += -DKC_LIST_LRU_ADD_OBJ
-endif
-
-#
-# v6.12-rc6-227-gda0c02516c50
-#
-# lru_list_walk_cb lock arg removed
-#
-ifneq (,$(shell grep 'struct list_lru_one \*list, spinlock_t \*lock, void \*cb_arg' include/linux/list_lru.h))
-ccflags-y += -DKC_LIST_LRU_WALK_CB_LIST_LOCK
-endif
-
-#
-# v5.1-rc4-273-ge9b98e162aa5
-#
-# introduce stack trace helpers
-#
-ifneq (,$(shell grep '^unsigned int stack_trace_save' include/linux/stacktrace.h))
-ccflags-y += -DKC_STACK_TRACE_SAVE
-endif
-
-# v6.1-rc1-4-g7420332a6ff4
-#
-# .get_acl() method now has dentry arg (and mnt_idmap). The old get_acl has been renamed
-# to get_inode_acl() and is still available as well, but has an extra rcu param.
-ifneq (,$(shell grep 'struct posix_acl ...get_acl..struct mnt_idmap ., struct dentry' include/linux/fs.h))
-ccflags-y += -DKC_GET_ACL_DENTRY
-endif
--- a/kmod/src/acl.c
+++ b/kmod/src/acl.c
@@ -107,15 +107,8 @@ struct posix_acl *scoutfs_get_acl_locked(struct inode *inode, int type, struct s
 	return acl;
 }

-#ifdef KC_GET_ACL_DENTRY
-struct posix_acl *scoutfs_get_acl(KC_VFS_NS_DEF
-				  struct dentry *dentry, int type)
-{
-	struct inode *inode = dentry->d_inode;
-#else
 struct posix_acl *scoutfs_get_acl(struct inode *inode, int type)
 {
-#endif
 	struct super_block *sb = inode->i_sb;
 	struct scoutfs_lock *lock = NULL;
 	struct posix_acl *acl;
@@ -160,8 +153,7 @@ int scoutfs_set_acl_locked(struct inode *inode, struct posix_acl *acl, int type,
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		if (acl) {
-			ret = posix_acl_update_mode(KC_VFS_INIT_NS
-						    inode, &new_mode, &acl);
+			ret = posix_acl_update_mode(inode, &new_mode, &acl);
 			if (ret < 0)
 				goto out;
 			set_mode = true;
@@ -208,15 +200,8 @@ out:
 	return ret;
 }

-#ifdef KC_GET_ACL_DENTRY
-int scoutfs_set_acl(KC_VFS_NS_DEF
-		    struct dentry *dentry, struct posix_acl *acl, int type)
-{
-	struct inode *inode = dentry->d_inode;
-#else
 int scoutfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
-#endif
 	struct super_block *sb = inode->i_sb;
 	struct scoutfs_lock *lock = NULL;
 	LIST_HEAD(ind_locks);
@@ -254,12 +239,7 @@ int scoutfs_acl_get_xattr(struct dentry *dentry, const char *name, void *value,
 	if (!IS_POSIXACL(dentry->d_inode))
 		return -EOPNOTSUPP;

-#ifdef KC_GET_ACL_DENTRY
-	acl = scoutfs_get_acl(KC_VFS_INIT_NS
-			      dentry, type);
-#else
 	acl = scoutfs_get_acl(dentry->d_inode, type);
-#endif
 	if (IS_ERR(acl))
 		return PTR_ERR(acl);
 	if (acl == NULL)
@@ -272,9 +252,7 @@ int scoutfs_acl_get_xattr(struct dentry *dentry, const char *name, void *value,
 }

 #ifdef KC_XATTR_STRUCT_XATTR_HANDLER
-int scoutfs_acl_set_xattr(const struct xattr_handler *handler,
-			  KC_VFS_NS_DEF
-			  struct dentry *dentry,
+int scoutfs_acl_set_xattr(const struct xattr_handler *handler, struct dentry *dentry,
 			  struct inode *inode, const char *name, const void *value,
 			  size_t size, int flags)
 {
@@ -287,7 +265,7 @@ int scoutfs_acl_set_xattr(struct dentry *dentry, const char *name, const void *v
 	struct posix_acl *acl = NULL;
 	int ret;

-	if (!inode_owner_or_capable(KC_VFS_INIT_NS dentry->d_inode))
+	if (!inode_owner_or_capable(dentry->d_inode))
 		return -EPERM;

 	if (!IS_POSIXACL(dentry->d_inode))
@@ -305,11 +283,7 @@ int scoutfs_acl_set_xattr(struct dentry *dentry, const char *name, const void *v
 		}
 	}

-#ifdef KC_GET_ACL_DENTRY
-	ret = scoutfs_set_acl(KC_VFS_INIT_NS dentry, acl, type);
-#else
 	ret = scoutfs_set_acl(dentry->d_inode, acl, type);
-#endif
 out:
 	posix_acl_release(acl);

--- a/kmod/src/acl.h
+++ b/kmod/src/acl.h
@@ -1,23 +1,16 @@
 #ifndef _SCOUTFS_ACL_H_
 #define _SCOUTFS_ACL_H_

-#ifdef KC_GET_ACL_DENTRY
-struct posix_acl *scoutfs_get_acl(KC_VFS_NS_DEF struct dentry *dentry, int type);
-int scoutfs_set_acl(KC_VFS_NS_DEF struct dentry *dentry, struct posix_acl *acl, int type);
-#else
 struct posix_acl *scoutfs_get_acl(struct inode *inode, int type);
-int scoutfs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
-#endif
 struct posix_acl *scoutfs_get_acl_locked(struct inode *inode, int type, struct scoutfs_lock *lock);
+int scoutfs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
 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);
-int scoutfs_acl_set_xattr(const struct xattr_handler *,
-			  KC_VFS_NS_DEF
-			  struct dentry *dentry,
+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
--- a/kmod/src/alloc.c
+++ b/kmod/src/alloc.c
@@ -14,7 +14,6 @@
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
-#include <linux/blkdev.h>
 #include <linux/sort.h>
 #include <linux/random.h>

@@ -86,47 +85,18 @@ static u64 smallest_order_length(u64 len)
 }

 /*
- * Moving an extent between trees can dirty blocks in several ways. This
- * function calculates worst case number of blocks across these scenarions.
- * We treat the alloc and free counts independently, so the values below are
- * max(allocated, freed), not the sum.
- *
- * We track extents with two separate btree items: by block number and by size.
- *
- * If we're removing an extent from the btree (allocating), we can dirty
- * two blocks if the keys are in different leaves. If we wind up merging
- * leaves because we fall below the low water mark, we can wind up freeing
- * three leaves.
- *
- * That sequence is as follows, assuming the original keys are removed from
- * blocks A and B:
- *
- * Allocate new dirty A' and B'
- * Free old stable A and B
- * B' has fallen below the low water mark, so copy B' into A'
- * Free B'
- *
- * An extent insertion (freeing an extent) can dirty up to five distinct items
- * in the btree as it adds and removes the blkno and size sorted items for the
- * old and new lengths of the extent:
- *
- * In the by-blkno portion of the btree, we can dirty (allocate for COW) up
- * to two blocks- either by merging adjacent extents, which can cause us to
- * join leaf blocks; or by an insertion that causes a split.
- *
- * In the by-size portion, we never merge extents, so normally we just dirty
- * a single item with a size insertion. But if we merged adjacent extents in
- * the by-blkno portion of the tree, we might be working with three by-sizex
- * items: removing the two old ones that were combined in the merge; and
- * adding the new one for the larger, merged size.
- *
- * Finally, dirtying the paths to these leaves can grow the tree and grow/shrink
- * neighbours at each level, so we multiply by the height of the tree after
- * accounting for a possible new level.
+ * An extent modification dirties three distinct leaves of an allocator
+ * btree as it adds and removes the blkno and size sorted items for the
+ * old and new lengths of the extent.  Dirtying the paths to these
+ * leaves can grow the tree and grow/shrink neighbours at each level.
+ * We over-estimate the number of blocks allocated and freed (the paths
+ * share a root, growth doesn't free) to err on the simpler and safer
+ * side.  The overhead is minimal given the relatively large list blocks
+ * and relatively short allocator trees.
 */
 static u32 extent_mod_blocks(u32 height)
 {
-	return ((1 + height) * 3) * 5;
+	return ((1 + height) * 2) * 3;
 }

 /*
@@ -857,7 +827,7 @@ static int find_zone_extent(struct super_block *sb, struct scoutfs_alloc_root *r
 		.zone = SCOUTFS_FREE_EXTENT_ORDER_ZONE,
 	};
 	struct scoutfs_extent found;
-	struct scoutfs_extent ext = {0,};
+	struct scoutfs_extent ext;
 	u64 start;
 	u64 len;
 	int nr;
--- a/kmod/src/block.c
+++ b/kmod/src/block.c
@@ -22,8 +22,6 @@
 #include <linux/rhashtable.h>
 #include <linux/random.h>
 #include <linux/sched/mm.h>
-#include <linux/list_lru.h>
-#include <linux/stacktrace.h>

 #include "format.h"
 #include "super.h"
@@ -40,12 +38,26 @@
 * than the page size.  Callers can have their own contexts for tracking
 * dirty blocks that are written together.  We pin dirty blocks in
 * memory and only checksum them all as they're all written.
+ *
+ * Memory reclaim is driven by maintaining two very coarse groups of
+ * blocks.  As we access blocks we mark them with an increasing counter
+ * to discourage them from being reclaimed.  We then define a threshold
+ * at the current counter minus half the population.  Recent blocks have
+ * a counter greater than the threshold, and all other blocks with
+ * counters less than it are considered older and are candidates for
+ * reclaim.  This results in access updates rarely modifying an atomic
+ * counter as blocks need to be moved into the recent group, and shrink
+ * can randomly scan blocks looking for the half of the population that
+ * will be in the old group.  It's reasonably effective, but is
+ * particularly efficient and avoids contention between concurrent
+ * accesses and shrinking.
 */

 struct block_info {
 	struct super_block *sb;
+	atomic_t total_inserted;
+	atomic64_t access_counter;
 	struct rhashtable ht;
-	struct list_lru lru;
 	wait_queue_head_t waitq;
 	KC_DEFINE_SHRINKER(shrinker);
 	struct work_struct free_work;
@@ -64,15 +76,28 @@ enum block_status_bits {
 	BLOCK_BIT_PAGE_ALLOC,	/* page (possibly high order) allocation */
 	BLOCK_BIT_VIRT,		/* mapped virt allocation */
 	BLOCK_BIT_CRC_VALID,	/* crc has been verified */
-	BLOCK_BIT_ACCESSED,	/* seen by lookup since last lru add/walk */
 };

+/*
+ * We want to tie atomic changes in refcounts to whether or not the
+ * block is still visible in the hash table, so we store the hash
+ * table's reference up at a known high bit.  We could naturally set the
+ * inserted bit through excessive refcount increments.  We don't do
+ * anything about that but at least warn if we get close.
+ *
+ * We're avoiding the high byte for no real good reason, just out of a
+ * historical fear of implementations that don't provide the full
+ * precision.
+ */
+#define BLOCK_REF_INSERTED	(1U << 23)
+#define BLOCK_REF_FULL		(BLOCK_REF_INSERTED >> 1)
+
 struct block_private {
 	struct scoutfs_block bl;
 	struct super_block *sb;
 	atomic_t refcount;
+	u64 accessed;
 	struct rhash_head ht_head;
-	struct list_head lru_head;
 	struct list_head dirty_entry;
 	struct llist_node free_node;
 	unsigned long bits;
@@ -81,15 +106,13 @@ struct block_private {
 		struct page *page;
 		void *virt;
 	};
-	unsigned int stack_len;
-	unsigned long stack[10];
 };

 #define TRACE_BLOCK(which, bp)									\
 do {												\
 	__typeof__(bp) _bp = (bp);								\
 	trace_scoutfs_block_##which(_bp->sb, _bp, _bp->bl.blkno, atomic_read(&_bp->refcount),	\
-				    atomic_read(&_bp->io_count), _bp->bits);	\
+				    atomic_read(&_bp->io_count), _bp->bits, _bp->accessed);	\
 } while (0)

 #define BLOCK_PRIVATE(_bl) \
@@ -97,23 +120,14 @@ do {												\

 static __le32 block_calc_crc(struct scoutfs_block_header *hdr, u32 size)
 {
-	int off = offsetofend(struct scoutfs_block_header, crc);
+	int off = offsetof(struct scoutfs_block_header, crc) +
+		  FIELD_SIZEOF(struct scoutfs_block_header, crc);
 	u32 calc = crc32c(~0, (char *)hdr + off, size - off);

 	return cpu_to_le32(calc);
 }

-static noinline void save_block_stack(struct block_private *bp)
-{
-	bp->stack_len = stack_trace_save(bp->stack, ARRAY_SIZE(bp->stack), 2);
-}
-
-static void print_block_stack(struct block_private *bp)
-{
-	stack_trace_print(bp->stack, bp->stack_len, 1);
-}
-
-static noinline struct block_private *block_alloc(struct super_block *sb, u64 blkno)
+static struct block_private *block_alloc(struct super_block *sb, u64 blkno)
 {
 	struct block_private *bp;
 	unsigned int nofs_flags;
@@ -145,7 +159,7 @@ static noinline struct block_private *block_alloc(struct super_block *sb, u64 bl
 		 */
 		lockdep_off();
 		nofs_flags = memalloc_nofs_save();
-		bp->virt = kc__vmalloc(SCOUTFS_BLOCK_LG_SIZE, GFP_NOFS | __GFP_HIGHMEM);
+		bp->virt = __vmalloc(SCOUTFS_BLOCK_LG_SIZE, GFP_NOFS | __GFP_HIGHMEM, PAGE_KERNEL);
 		memalloc_nofs_restore(nofs_flags);
 		lockdep_on();

@@ -163,13 +177,11 @@ static noinline struct block_private *block_alloc(struct super_block *sb, u64 bl
 	bp->bl.blkno = blkno;
 	bp->sb = sb;
 	atomic_set(&bp->refcount, 1);
-	INIT_LIST_HEAD(&bp->lru_head);
 	INIT_LIST_HEAD(&bp->dirty_entry);
 	set_bit(BLOCK_BIT_NEW, &bp->bits);
 	atomic_set(&bp->io_count, 0);

 	TRACE_BLOCK(allocate, bp);
-	save_block_stack(bp);

 out:
 	if (!bp)
@@ -222,85 +234,32 @@ static void block_free_work(struct work_struct *work)
 }

 /*
- * Users of blocks hold a refcount.  If putting a refcount drops to zero
- * then the block is freed.
- *
- * Acquiring new references and claiming the exclusive right to tear
- * down a block is built around this LIVE_REFCOUNT_BASE refcount value.
- * As blocks are initially cached they have the live base added to their
- * refcount.  Lookups will only increment the refcount and return blocks
- * for reference holders while the refcount is >= than the base.
- *
- * To remove a block from the cache and eventually free it, either by
- * the lru walk in the shrinker, or by reference holders, the live base
- * is removed and turned into a normal refcount increment that will be
- * put by the caller.  This can only be done once for a block, and once
- * its done lookup will not return any more references.
- */
-#define LIVE_REFCOUNT_BASE (INT_MAX ^ (INT_MAX >> 1))
-
-/*
- * Inc the refcount while holding an incremented refcount.  We can't
- * have so many individual reference holders that they pass the live
- * base.
+ * Get a reference to a block while holding an existing reference.
 */
 static void block_get(struct block_private *bp)
 {
-	int now = atomic_inc_return(&bp->refcount);
+	WARN_ON_ONCE((atomic_read(&bp->refcount) & ~BLOCK_REF_INSERTED) <= 0);

-	BUG_ON(now <= 1);
-	BUG_ON(now == LIVE_REFCOUNT_BASE);
+	atomic_inc(&bp->refcount);
 }

 /*
- * if (*v >= u) {
- * 	*v += a;
- * 	return true;
- * }
- */
-static bool atomic_add_unless_less(atomic_t *v, int a, int u)
+ * Get a reference to a block as long as it's been inserted in the hash
+ * table and hasn't been removed.
+ */ 
+static struct block_private *block_get_if_inserted(struct block_private *bp)
 {
-	int c;
+	int cnt;

 	do {
-		c = atomic_read(v);
-		if (c < u)
-			return false;
-	} while (atomic_cmpxchg(v, c, c + a) != c);
+		cnt = atomic_read(&bp->refcount);
+		WARN_ON_ONCE(cnt & BLOCK_REF_FULL);
+		if (!(cnt & BLOCK_REF_INSERTED))
+			return NULL;

-	return true;
-}
+	} while (atomic_cmpxchg(&bp->refcount, cnt, cnt + 1) != cnt);

-static bool block_get_if_live(struct block_private *bp)
-{
-	return atomic_add_unless_less(&bp->refcount, 1, LIVE_REFCOUNT_BASE);
-}
-
-/*
- * If the refcount still has the live base, subtract it and increment
- * the callers refcount that they'll put.
- */
-static bool block_get_remove_live(struct block_private *bp)
-{
-	return atomic_add_unless_less(&bp->refcount, (1 - LIVE_REFCOUNT_BASE), LIVE_REFCOUNT_BASE);
-}
-
-/*
- * Only get the live base refcount if it is the only refcount remaining.
- * This means that there are no active refcount holders and the block
- * can't be dirty or under IO, which both hold references.
- */
-static bool block_get_remove_live_only(struct block_private *bp)
-{
-	int c;
-
-	do {
-		c = atomic_read(&bp->refcount);
-		if (c != LIVE_REFCOUNT_BASE)
-			return false;
-	} while (atomic_cmpxchg(&bp->refcount, c, c - LIVE_REFCOUNT_BASE + 1) != c);
-
-	return true;
+	return bp;
 }

 /*
@@ -332,81 +291,143 @@ static const struct rhashtable_params block_ht_params = {
 };

 /*
- * Insert the block into the cache so that it's visible for lookups.
- * The caller can hold references (including for a dirty block).
- *
- * We make sure the base is added and the block is in the lru once it's
- * in the hash.  If hash table insertion fails it'll be briefly visible
- * in the lru, but won't be isolated/evicted because we hold an
- * incremented refcount in addition to the live base.
+ * Insert a new block into the hash table.  Once it is inserted in the
+ * hash table readers can start getting references.  The caller may have
+ * multiple refs but the block can't already be inserted.
 */
 static int block_insert(struct super_block *sb, struct block_private *bp)
 {
 	DECLARE_BLOCK_INFO(sb, binf);
 	int ret;

-	BUG_ON(atomic_read(&bp->refcount) >= LIVE_REFCOUNT_BASE);
-	atomic_add(LIVE_REFCOUNT_BASE, &bp->refcount);
-	smp_mb__after_atomic(); /* make sure live base is visible to list_lru walk */
-	list_lru_add_obj(&binf->lru, &bp->lru_head);
+	WARN_ON_ONCE(atomic_read(&bp->refcount) & BLOCK_REF_INSERTED);
+
 retry:
+	atomic_add(BLOCK_REF_INSERTED, &bp->refcount);
 	ret = rhashtable_lookup_insert_fast(&binf->ht, &bp->ht_head, block_ht_params);
 	if (ret < 0) {
+		atomic_sub(BLOCK_REF_INSERTED, &bp->refcount);
 		if (ret == -EBUSY) {
 			/* wait for pending rebalance to finish */
 			synchronize_rcu();
 			goto retry;
-		} else {
-			atomic_sub(LIVE_REFCOUNT_BASE, &bp->refcount);
-			BUG_ON(atomic_read(&bp->refcount) >= LIVE_REFCOUNT_BASE);
-			list_lru_del_obj(&binf->lru, &bp->lru_head);
 		}
 	} else {
+		atomic_inc(&binf->total_inserted);
 		TRACE_BLOCK(insert, bp);
 	}

 	return ret;
 }

-/*
- * Indicate to the lru walker that this block has been accessed since it
- * was added or last walked.
- */
-static void block_accessed(struct super_block *sb, struct block_private *bp)
+static u64 accessed_recently(struct block_info *binf)
 {
-	if (!test_and_set_bit(BLOCK_BIT_ACCESSED, &bp->bits))
-		scoutfs_inc_counter(sb, block_cache_access_update);
+	return atomic64_read(&binf->access_counter) - (atomic_read(&binf->total_inserted) >> 1);
 }

 /*
- * Remove the block from the cache.  When this returns the block won't
- * be visible for additional references from lookup.
- *
- * We always try and remove from the hash table.  It's safe to remove a
- * block that isn't hashed, it just returns -ENOENT.
- *
- * This is racing with the lru walk in the shrinker also trying to
- * remove idle blocks from the cache.  They both try to remove the live
- * refcount base and perform their removal and put if they get it.
+ * Make sure that a block that is being accessed is less likely to be
+ * reclaimed if it is seen by the shrinker.   If the block hasn't been
+ * accessed recently we update its accessed value.
 */
-static void block_remove(struct super_block *sb, struct block_private *bp)
+static void block_accessed(struct super_block *sb, struct block_private *bp)
 {
 	DECLARE_BLOCK_INFO(sb, binf);

-	rhashtable_remove_fast(&binf->ht, &bp->ht_head, block_ht_params);
-
-	if (block_get_remove_live(bp)) {
-		list_lru_del_obj(&binf->lru, &bp->lru_head);
-		block_put(sb, bp);
+	if (bp->accessed == 0 || bp->accessed < accessed_recently(binf)) {
+		scoutfs_inc_counter(sb, block_cache_access_update);
+		bp->accessed = atomic64_inc_return(&binf->access_counter);
 	}
 }

+/*
+ * The caller wants to remove the block from the hash table and has an
+ * idea what the refcount should be.  If the refcount does still
+ * indicate that the block is hashed, and we're able to clear that bit,
+ * then we can remove it from the hash table.
+ *
+ * The caller makes sure that it's safe to be referencing this block,
+ * either with their own held reference (most everything) or by being in
+ * an rcu grace period (shrink).
+ */
+static bool block_remove_cnt(struct super_block *sb, struct block_private *bp, int cnt)
+{
+	DECLARE_BLOCK_INFO(sb, binf);
+	int ret;
+
+	if ((cnt & BLOCK_REF_INSERTED) &&
+	    (atomic_cmpxchg(&bp->refcount, cnt, cnt & ~BLOCK_REF_INSERTED) == cnt)) {
+
+		TRACE_BLOCK(remove, bp);
+		ret = rhashtable_remove_fast(&binf->ht, &bp->ht_head, block_ht_params);
+		WARN_ON_ONCE(ret); /* must have been inserted */
+		atomic_dec(&binf->total_inserted);
+		return true;
+	}
+
+	return false;
+}
+
+/*
+ * Try to remove the block from the hash table as long as the refcount
+ * indicates that it is still in the hash table.  This can be racing
+ * with normal refcount changes so it might have to retry.
+ */
+static void block_remove(struct super_block *sb, struct block_private *bp)
+{
+	int cnt;
+
+	do {
+		cnt = atomic_read(&bp->refcount);
+	} while ((cnt & BLOCK_REF_INSERTED) && !block_remove_cnt(sb, bp, cnt));
+}
+
+/*
+ * Take one shot at removing the block from the hash table if it's still
+ * in the hash table and the caller has the only other reference.
+ */
+static bool block_remove_solo(struct super_block *sb, struct block_private *bp)
+{
+	return block_remove_cnt(sb, bp, BLOCK_REF_INSERTED | 1);
+}
+
 static bool io_busy(struct block_private *bp)
 {
 	smp_rmb(); /* test after adding to wait queue */
 	return test_bit(BLOCK_BIT_IO_BUSY, &bp->bits);
 }

+/*
+ * Called during shutdown with no other users.
+ */
+static void block_remove_all(struct super_block *sb)
+{
+	DECLARE_BLOCK_INFO(sb, binf);
+	struct rhashtable_iter iter;
+	struct block_private *bp;
+
+	rhashtable_walk_enter(&binf->ht, &iter);
+	rhashtable_walk_start(&iter);
+
+	for (;;) {
+		bp = rhashtable_walk_next(&iter);
+		if (bp == NULL)
+			break;
+		if (bp == ERR_PTR(-EAGAIN))
+			continue;
+
+		if (block_get_if_inserted(bp)) {
+			block_remove(sb, bp);
+			WARN_ON_ONCE(atomic_read(&bp->refcount) != 1);
+			block_put(sb, bp);
+		}
+	}
+
+	rhashtable_walk_stop(&iter);
+	rhashtable_walk_exit(&iter);
+
+	WARN_ON_ONCE(atomic_read(&binf->total_inserted) != 0);
+}

 /*
 * XXX The io_count and sb fields in the block_private are only used
@@ -417,7 +438,7 @@ static bool io_busy(struct block_private *bp)
 * possible.  Final freeing, verifying checksums, and unlinking errored
 * blocks are all done by future users of the blocks.
 */
-static void block_end_io(struct super_block *sb, blk_opf_t opf,
+static void block_end_io(struct super_block *sb, unsigned int opf,
 			 struct block_private *bp, int err)
 {
 	DECLARE_BLOCK_INFO(sb, binf);
@@ -457,7 +478,7 @@ static void KC_DECLARE_BIO_END_IO(block_bio_end_io, struct bio *bio)
 * Kick off IO for a single block.
 */
 static int block_submit_bio(struct super_block *sb, struct block_private *bp,
-			    blk_opf_t opf)
+			    unsigned int opf)
 {
 	struct scoutfs_sb_info *sbi = SCOUTFS_SB(sb);
 	struct bio *bio = NULL;
@@ -468,7 +489,7 @@ static int block_submit_bio(struct super_block *sb, struct block_private *bp,
 	int ret = 0;

 	if (scoutfs_forcing_unmount(sb))
-		return -ENOLINK;
+		return -EIO;

 	sector = bp->bl.blkno << (SCOUTFS_BLOCK_LG_SHIFT - 9);

@@ -484,13 +505,15 @@ static int block_submit_bio(struct super_block *sb, struct block_private *bp,

 	for (off = 0; off < SCOUTFS_BLOCK_LG_SIZE; off += PAGE_SIZE) {
 		if (!bio) {
-			bio = kc_bio_alloc(sbi->meta_bdev, SCOUTFS_BLOCK_LG_PAGES_PER, opf, GFP_NOFS);
+			bio = bio_alloc(GFP_NOFS, SCOUTFS_BLOCK_LG_PAGES_PER);
 			if (!bio) {
 				ret = -ENOMEM;
 				break;
 			}

+			kc_bio_set_opf(bio, opf);
 			kc_bio_set_sector(bio, sector + (off >> 9));
+			bio_set_dev(bio, sbi->meta_bdev);
 			bio->bi_end_io = block_bio_end_io;
 			bio->bi_private = bp;

@@ -523,10 +546,6 @@ static int block_submit_bio(struct super_block *sb, struct block_private *bp,
 	return ret;
 }

-/*
- * Return a block with an elevated refcount if it was present in the
- * hash table and its refcount didn't indicate that it was being freed.
- */
 static struct block_private *block_lookup(struct super_block *sb, u64 blkno)
 {
 	DECLARE_BLOCK_INFO(sb, binf);
@@ -534,8 +553,8 @@ static struct block_private *block_lookup(struct super_block *sb, u64 blkno)

 	rcu_read_lock();
 	bp = rhashtable_lookup(&binf->ht, &blkno, block_ht_params);
-	if (bp && !block_get_if_live(bp))
-		bp = NULL;
+	if (bp)
+		bp = block_get_if_inserted(bp);
 	rcu_read_unlock();

 	return bp;
@@ -696,8 +715,8 @@ retry:

 	ret = 0;
 out:
-	if (!retried && !IS_ERR_OR_NULL(bp) && !block_is_dirty(bp) &&
-	    (ret == -ESTALE || scoutfs_trigger(sb, BLOCK_REMOVE_STALE))) {
+	if ((ret == -ESTALE || scoutfs_trigger(sb, BLOCK_REMOVE_STALE)) &&
+	    !retried && !block_is_dirty(bp)) {
 		retried = true;
 		scoutfs_inc_counter(sb, block_cache_remove_stale);
 		block_remove(sb, bp);
@@ -1062,106 +1081,100 @@ static unsigned long block_count_objects(struct shrinker *shrink, struct shrink_
 	struct super_block *sb = binf->sb;

 	scoutfs_inc_counter(sb, block_cache_count_objects);
-	return list_lru_shrink_count(&binf->lru, sc);
-}
-
-struct isolate_args {
-	struct super_block *sb;
-	struct list_head dispose;
-};
-
-#define DECLARE_ISOLATE_ARGS(sb_, name_) \
-	struct isolate_args name_ = { \
-		.sb = sb_, \
-		.dispose = LIST_HEAD_INIT(name_.dispose), \
-	}
-
-static enum lru_status isolate_lru_block(struct list_head *item, struct list_lru_one *list,
-					 void *cb_arg)
-{
-	struct block_private *bp = container_of(item, struct block_private, lru_head);
-	struct isolate_args *ia = cb_arg;
-
-	TRACE_BLOCK(isolate, bp);
-
-	/* rotate accessed blocks to the tail of the list (lazy promotion) */
-	if (test_and_clear_bit(BLOCK_BIT_ACCESSED, &bp->bits)) {
-		scoutfs_inc_counter(ia->sb, block_cache_isolate_rotate);
-		return LRU_ROTATE;
-	}
-
-	/* any refs, including dirty/io, stop us from acquiring lru refcount */
-	if (!block_get_remove_live_only(bp)) {
-		scoutfs_inc_counter(ia->sb, block_cache_isolate_skip);
-		return LRU_SKIP;
-	}
-
-	scoutfs_inc_counter(ia->sb, block_cache_isolate_removed);
-	list_lru_isolate_move(list, &bp->lru_head, &ia->dispose);
-	return LRU_REMOVED;
-}
-
-static void shrink_dispose_blocks(struct super_block *sb, struct list_head *dispose)
-{
-	struct block_private *bp;
-	struct block_private *bp__;
-
-	list_for_each_entry_safe(bp, bp__, dispose, lru_head) {
-		list_del_init(&bp->lru_head);
-		block_remove(sb, bp);
-		block_put(sb, bp);
-	}
+
+	return shrinker_min_long(atomic_read(&binf->total_inserted));
 }

+/*
+ * Remove a number of cached blocks that haven't been used recently.
+ *
+ * We don't maintain a strictly ordered LRU to avoid the contention of
+ * accesses always moving blocks around in some precise global
+ * structure.
+ *
+ * Instead we use counters to divide the blocks into two roughly equal
+ * groups by how recently they were accessed.  We randomly walk all
+ * inserted blocks looking for any blocks in the older half to remove
+ * and free.  The random walk and there being two groups means that we
+ * typically only walk a small multiple of the number we're looking for
+ * before we find them all.
+ *
+ * Our rcu walk of blocks can see blocks in all stages of their life
+ * cycle, from dirty blocks to those with 0 references that are queued
+ * for freeing.  We only want to free idle inserted blocks so we
+ * atomically remove blocks when the only references are ours and the
+ * hash table.
+ */
 static unsigned long block_scan_objects(struct shrinker *shrink, struct shrink_control *sc)
 {
 	struct block_info *binf = KC_SHRINKER_CONTAINER_OF(shrink, struct block_info);
 	struct super_block *sb = binf->sb;
-	DECLARE_ISOLATE_ARGS(sb, ia);
-	unsigned long freed;
+	struct rhashtable_iter iter;
+	struct block_private *bp;
+	bool stop = false;
+	unsigned long freed = 0;
+	unsigned long nr = sc->nr_to_scan;
+	u64 recently;

 	scoutfs_inc_counter(sb, block_cache_scan_objects);

-	freed = kc_list_lru_shrink_walk(&binf->lru, sc, isolate_lru_block, &ia);
-	shrink_dispose_blocks(sb, &ia.dispose);
-	return freed;
-}
+	recently = accessed_recently(binf);
+	rhashtable_walk_enter(&binf->ht, &iter);
+	rhashtable_walk_start(&iter);

-static enum lru_status dump_lru_block(struct list_head *item, struct list_lru_one *list,
-					 void *cb_arg)
-{
-	struct block_private *bp = container_of(item, struct block_private, lru_head);
+	/*
+	 * This isn't great but I don't see a better way.  We want to
+	 * walk the hash from a random point so that we're not
+	 * constantly walking over the same region that we've already
+	 * freed old blocks within.  The interface doesn't let us do
+	 * this explicitly, but this seems to work?  The difference this
+	 * makes is enormous, around a few orders of magnitude fewer
+	 * _nexts per shrink.
+	 */
+	if (iter.walker.tbl)
+		iter.slot = prandom_u32_max(iter.walker.tbl->size);

-	printk("blkno %llu refcount 0x%x io_count %d bits 0x%lx\n",
-		bp->bl.blkno, atomic_read(&bp->refcount), atomic_read(&bp->io_count),
-		bp->bits);
-	print_block_stack(bp);
+	while (nr > 0) {
+		bp = rhashtable_walk_next(&iter);
+		if (bp == NULL)
+			break;
+		if (bp == ERR_PTR(-EAGAIN)) {
+			/*
+			 * We can be called from reclaim in the allocation
+			 * to resize the hash table itself.  We have to
+			 * return so that the caller can proceed and
+			 * enable hash table iteration again.
+			 */
+			scoutfs_inc_counter(sb, block_cache_shrink_stop);
+			stop = true;
+			break;
+		}

-	return LRU_SKIP;
-}
+		scoutfs_inc_counter(sb, block_cache_shrink_next);

-/*
- * Called during shutdown with no other users.  The isolating walk must
- * find blocks on the lru that only have references for presence on the
- * lru and in the hash table.
- */
-static void block_shrink_all(struct super_block *sb)
-{
-	DECLARE_BLOCK_INFO(sb, binf);
-	DECLARE_ISOLATE_ARGS(sb, ia);
-	long count;
+		if (bp->accessed >= recently) {
+			scoutfs_inc_counter(sb, block_cache_shrink_recent);
+			continue;
+		}

-	count = DIV_ROUND_UP(list_lru_count(&binf->lru), 128) * 2;
-	do {
-		kc_list_lru_walk(&binf->lru, isolate_lru_block, &ia, 128);
-		shrink_dispose_blocks(sb, &ia.dispose);
-	} while (list_lru_count(&binf->lru) > 0 && --count > 0);
-
-	count = list_lru_count(&binf->lru);
-	if (count > 0) {
-		scoutfs_err(sb, "failed to isolate/dispose %ld blocks", count);
-		kc_list_lru_walk(&binf->lru, dump_lru_block, sb, count);
+		if (block_get_if_inserted(bp)) {
+			if (block_remove_solo(sb, bp)) {
+				scoutfs_inc_counter(sb, block_cache_shrink_remove);
+				TRACE_BLOCK(shrink, bp);
+				freed++;
+				nr--;
+			}
+			block_put(sb, bp);
+		}
 	}
+
+	rhashtable_walk_stop(&iter);
+	rhashtable_walk_exit(&iter);
+
+	if (stop)
+		return SHRINK_STOP;
+	else
+		return freed;
 }

 struct sm_block_completion {
@@ -1188,7 +1201,7 @@ static void KC_DECLARE_BIO_END_IO(sm_block_bio_end_io, struct bio *bio)
 * only layer that sees the full block buffer so we pass the calculated
 * crc to the caller for them to check in their context.
 */
-static int sm_block_io(struct super_block *sb, struct block_device *bdev, blk_opf_t opf,
+static int sm_block_io(struct super_block *sb, struct block_device *bdev, unsigned int opf,
 		       u64 blkno, struct scoutfs_block_header *hdr, size_t len, __le32 *blk_crc)
 {
 	struct scoutfs_block_header *pg_hdr;
@@ -1200,7 +1213,7 @@ static int sm_block_io(struct super_block *sb, struct block_device *bdev, blk_op
 	BUILD_BUG_ON(PAGE_SIZE < SCOUTFS_BLOCK_SM_SIZE);

 	if (scoutfs_forcing_unmount(sb))
-		return -ENOLINK;
+		return -EIO;

 	if (WARN_ON_ONCE(len > SCOUTFS_BLOCK_SM_SIZE) ||
 	    WARN_ON_ONCE(!op_is_write(opf) && !blk_crc))
@@ -1220,13 +1233,15 @@ static int sm_block_io(struct super_block *sb, struct block_device *bdev, blk_op
 		pg_hdr->crc = block_calc_crc(pg_hdr, SCOUTFS_BLOCK_SM_SIZE);
 	}

-	bio = kc_bio_alloc(bdev, 1, opf, GFP_NOFS);
+	bio = bio_alloc(GFP_NOFS, 1);
 	if (!bio) {
 		ret = -ENOMEM;
 		goto out;
 	}

+	kc_bio_set_opf(bio, opf | REQ_SYNC);
 	kc_bio_set_sector(bio, blkno << (SCOUTFS_BLOCK_SM_SHIFT - 9));
+	bio_set_dev(bio, bdev);
 	bio->bi_end_io = sm_block_bio_end_io;
 	bio->bi_private = &sbc;
 	bio_add_page(bio, page, SCOUTFS_BLOCK_SM_SIZE, 0);
@@ -1266,7 +1281,7 @@ int scoutfs_block_write_sm(struct super_block *sb,
 int scoutfs_block_setup(struct super_block *sb)
 {
 	struct scoutfs_sb_info *sbi = SCOUTFS_SB(sb);
-	struct block_info *binf = NULL;
+	struct block_info *binf;
 	int ret;

 	binf = kzalloc(sizeof(struct block_info), GFP_KERNEL);
@@ -1275,19 +1290,19 @@ int scoutfs_block_setup(struct super_block *sb)
 		goto out;
 	}

-	ret = list_lru_init(&binf->lru);
-	if (ret < 0)
-		goto out;
-
 	ret = rhashtable_init(&binf->ht, &block_ht_params);
-	if (ret < 0)
+	if (ret < 0) {
+		kfree(binf);
 		goto out;
+	}

 	binf->sb = sb;
+	atomic_set(&binf->total_inserted, 0);
+	atomic64_set(&binf->access_counter, 0);
 	init_waitqueue_head(&binf->waitq);
 	KC_INIT_SHRINKER_FUNCS(&binf->shrinker, block_count_objects,
 			       block_scan_objects);
-	KC_REGISTER_SHRINKER(&binf->shrinker, "scoutfs-block:" SCSBF, SCSB_ARGS(sb));
+	KC_REGISTER_SHRINKER(&binf->shrinker);
 	INIT_WORK(&binf->free_work, block_free_work);
 	init_llist_head(&binf->free_llist);

@@ -1295,10 +1310,8 @@ int scoutfs_block_setup(struct super_block *sb)

 	ret = 0;
 out:
-	if (ret < 0 && binf) {
-		list_lru_destroy(&binf->lru);
-		kfree(binf);
-	}
+	if (ret)
+		scoutfs_block_destroy(sb);

 	return ret;
 }
@@ -1310,10 +1323,9 @@ void scoutfs_block_destroy(struct super_block *sb)

 	if (binf) {
 		KC_UNREGISTER_SHRINKER(&binf->shrinker);
-		block_shrink_all(sb);
+		block_remove_all(sb);
 		flush_work(&binf->free_work);
 		rhashtable_destroy(&binf->ht);
-		list_lru_destroy(&binf->lru);

 		kfree(binf);
 		sbi->block_info = NULL;
--- a/kmod/src/client.c
+++ b/kmod/src/client.c
@@ -20,7 +20,6 @@
 #include <net/sock.h>
 #include <net/tcp.h>
 #include <asm/barrier.h>
-#include <linux/overflow.h>

 #include "format.h"
 #include "counters.h"
@@ -69,7 +68,6 @@ int scoutfs_client_alloc_inodes(struct super_block *sb, u64 count,
 	struct client_info *client = SCOUTFS_SB(sb)->client_info;
 	struct scoutfs_net_inode_alloc ial;
 	__le64 lecount = cpu_to_le64(count);
-	u64 tmp;
 	int ret;

 	ret = scoutfs_net_sync_request(sb, client->conn,
@@ -82,7 +80,7 @@ int scoutfs_client_alloc_inodes(struct super_block *sb, u64 count,

 		if (*nr == 0)
 			ret = -ENOSPC;
-		else if (check_add_overflow(*ino, *nr - 1, &tmp))
+		else if (*ino + *nr < *ino)
 			ret = -EINVAL;
 	}

@@ -435,8 +433,8 @@ static int lookup_mounted_client_item(struct super_block *sb, u64 rid)
 	if (ret == -ENOENT)
 		ret = 0;

-out:
 	kfree(super);
+out:
 	return ret;
 }

--- a/kmod/src/counters.h
+++ b/kmod/src/counters.h
@@ -26,15 +26,17 @@
 	EXPAND_COUNTER(block_cache_alloc_page_order)		\
 	EXPAND_COUNTER(block_cache_alloc_virt)			\
 	EXPAND_COUNTER(block_cache_end_io_error)		\
-	EXPAND_COUNTER(block_cache_isolate_removed)		\
-	EXPAND_COUNTER(block_cache_isolate_rotate)		\
-	EXPAND_COUNTER(block_cache_isolate_skip)		\
 	EXPAND_COUNTER(block_cache_forget)			\
 	EXPAND_COUNTER(block_cache_free)			\
 	EXPAND_COUNTER(block_cache_free_work)			\
 	EXPAND_COUNTER(block_cache_remove_stale)		\
 	EXPAND_COUNTER(block_cache_count_objects)		\
 	EXPAND_COUNTER(block_cache_scan_objects)		\
+	EXPAND_COUNTER(block_cache_shrink)			\
+	EXPAND_COUNTER(block_cache_shrink_next)			\
+	EXPAND_COUNTER(block_cache_shrink_recent)		\
+	EXPAND_COUNTER(block_cache_shrink_remove)		\
+	EXPAND_COUNTER(block_cache_shrink_stop)			\
 	EXPAND_COUNTER(btree_compact_values)			\
 	EXPAND_COUNTER(btree_compact_values_enomem)		\
 	EXPAND_COUNTER(btree_delete)				\
@@ -88,7 +90,6 @@
 	EXPAND_COUNTER(forest_read_items)			\
 	EXPAND_COUNTER(forest_roots_next_hint)			\
 	EXPAND_COUNTER(forest_set_bloom_bits)			\
-	EXPAND_COUNTER(inode_deleted)				\
 	EXPAND_COUNTER(item_cache_count_objects)		\
 	EXPAND_COUNTER(item_cache_scan_objects)			\
 	EXPAND_COUNTER(item_clear_dirty)			\
@@ -116,15 +117,15 @@
 	EXPAND_COUNTER(item_pcpu_page_hit)			\
 	EXPAND_COUNTER(item_pcpu_page_miss)			\
 	EXPAND_COUNTER(item_pcpu_page_miss_keys)		\
-	EXPAND_COUNTER(item_read_pages_barrier)			\
-	EXPAND_COUNTER(item_read_pages_retry)			\
 	EXPAND_COUNTER(item_read_pages_split)			\
 	EXPAND_COUNTER(item_shrink_page)			\
 	EXPAND_COUNTER(item_shrink_page_dirty)			\
+	EXPAND_COUNTER(item_shrink_page_reader)			\
 	EXPAND_COUNTER(item_shrink_page_trylock)		\
 	EXPAND_COUNTER(item_update)				\
 	EXPAND_COUNTER(item_write_dirty)			\
 	EXPAND_COUNTER(lock_alloc)				\
+	EXPAND_COUNTER(lock_count_objects)			\
 	EXPAND_COUNTER(lock_free)				\
 	EXPAND_COUNTER(lock_grant_request)			\
 	EXPAND_COUNTER(lock_grant_response)			\
@@ -138,13 +139,12 @@
 	EXPAND_COUNTER(lock_lock_error)				\
 	EXPAND_COUNTER(lock_nonblock_eagain)			\
 	EXPAND_COUNTER(lock_recover_request)			\
+	EXPAND_COUNTER(lock_scan_objects)			\
 	EXPAND_COUNTER(lock_shrink_attempted)			\
-	EXPAND_COUNTER(lock_shrink_request_failed)		\
+	EXPAND_COUNTER(lock_shrink_aborted)			\
+	EXPAND_COUNTER(lock_shrink_work)			\
 	EXPAND_COUNTER(lock_unlock)				\
 	EXPAND_COUNTER(lock_wait)				\
-	EXPAND_COUNTER(log_merge_complete)			\
-	EXPAND_COUNTER(log_merge_no_finalized)			\
-	EXPAND_COUNTER(log_merge_start)				\
 	EXPAND_COUNTER(log_merge_wait_timeout)			\
 	EXPAND_COUNTER(net_dropped_response)			\
 	EXPAND_COUNTER(net_send_bytes)				\
@@ -159,7 +159,6 @@
 	EXPAND_COUNTER(orphan_scan)				\
 	EXPAND_COUNTER(orphan_scan_attempts)			\
 	EXPAND_COUNTER(orphan_scan_cached)			\
-	EXPAND_COUNTER(orphan_scan_empty)			\
 	EXPAND_COUNTER(orphan_scan_error)			\
 	EXPAND_COUNTER(orphan_scan_item)			\
 	EXPAND_COUNTER(orphan_scan_omap_set)			\
@@ -182,7 +181,6 @@
 	EXPAND_COUNTER(quorum_send_vote)			\
 	EXPAND_COUNTER(quorum_server_shutdown)			\
 	EXPAND_COUNTER(quorum_term_follower)			\
-	EXPAND_COUNTER(reclaimed_open_logs)			\
 	EXPAND_COUNTER(server_commit_hold)			\
 	EXPAND_COUNTER(server_commit_queue)			\
 	EXPAND_COUNTER(server_commit_worker)			\
--- a/kmod/src/data.c
+++ b/kmod/src/data.c
@@ -20,9 +20,7 @@
 #include <linux/hash.h>
 #include <linux/log2.h>
 #include <linux/falloc.h>
-#include <linux/fiemap.h>
 #include <linux/writeback.h>
-#include <linux/overflow.h>

 #include "format.h"
 #include "super.h"
@@ -560,7 +558,7 @@ static int scoutfs_get_block(struct inode *inode, sector_t iblock,
 	u64 offset;
 	int ret;

-	WARN_ON_ONCE(create && !rwsem_is_locked(&si->extent_sem));
+	WARN_ON_ONCE(create && !inode_is_locked(inode));

 	/* make sure caller holds a cluster lock */
 	lock = scoutfs_per_task_get(&si->pt_data_lock);
@@ -681,14 +679,8 @@ int scoutfs_get_block_write(struct inode *inode, sector_t iblock, struct buffer_
 * We can return errors from locking and checking offline extents.  The
 * page is unlocked if we return an error.
 */
-#ifdef KC_MPAGE_READ_FOLIO
-static int scoutfs_read_folio(struct file *file, struct folio *folio)
-{
-	struct page *page = &folio->page;
-#else
 static int scoutfs_readpage(struct file *file, struct page *page)
 {
-#endif
 	struct inode *inode = file->f_inode;
 	struct scoutfs_inode_info *si = SCOUTFS_I(inode);
 	struct super_block *sb = inode->i_sb;
@@ -735,11 +727,7 @@ static int scoutfs_readpage(struct file *file, struct page *page)
 			return ret;
 	}

-#ifdef KC_MPAGE_READ_FOLIO
-	ret = mpage_read_folio(folio, scoutfs_get_block_read);
-#else
 	ret = mpage_readpage(page, scoutfs_get_block_read);
-#endif

 	scoutfs_unlock(sb, inode_lock, SCOUTFS_LOCK_READ);
 	scoutfs_per_task_del(&si->pt_data_lock, &pt_ent);
@@ -837,10 +825,7 @@ struct write_begin_data {

 static int scoutfs_write_begin(struct file *file,
 			       struct address_space *mapping, loff_t pos,
-			       unsigned len,
-#ifdef KC_BLOCK_WRITE_BEGIN_AOP_FLAGS
-			       unsigned flags,
-#endif
+			       unsigned len, unsigned flags,
 			       struct page **pagep, void **fsdata)
 {
 	struct inode *inode = mapping->host;
@@ -875,18 +860,13 @@ retry:
 	if (ret < 0)
 		goto out;

-#ifdef KC_BLOCK_WRITE_BEGIN_AOP_FLAGS
 	/* can't re-enter fs, have trans */
 	flags |= AOP_FLAG_NOFS;
-#endif

 	/* generic write_end updates i_size and calls dirty_inode */
 	ret = scoutfs_dirty_inode_item(inode, wbd->lock) ?:
-	      block_write_begin(mapping, pos, len,
-#ifdef KC_BLOCK_WRITE_BEGIN_AOP_FLAGS
-				flags,
-#endif
-				pagep, scoutfs_get_block_write);
+	      block_write_begin(mapping, pos, len, flags, pagep,
+				scoutfs_get_block_write);
 	if (ret < 0) {
 		scoutfs_release_trans(sb);
 		scoutfs_inode_index_unlock(sb, &wbd->ind_locks);
@@ -1088,7 +1068,6 @@ long scoutfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	loff_t end;
 	u64 iblock;
 	u64 last;
-	loff_t tmp;
 	s64 ret;

 	/* XXX support more flags */
@@ -1097,14 +1076,14 @@ long scoutfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 		goto out;
 	}

-	if (len == 0) {
-		ret = 0;
+	/* catch wrapping */
+	if (offset + len < offset) {
+		ret = -EINVAL;
 		goto out;
 	}

-	/* catch wrapping */
-	if (check_add_overflow(offset, len - 1, &tmp)) {
-		ret = -EINVAL;
+	if (len == 0) {
+		ret = 0;
 		goto out;
 	}

@@ -1325,8 +1304,8 @@ int scoutfs_data_move_blocks(struct inode *from, u64 from_off,
 		goto out;
 	}

-	ret = inode_permission(KC_VFS_INIT_NS from, MAY_WRITE) ?:
-	      inode_permission(KC_VFS_INIT_NS to, MAY_WRITE);
+	ret = inode_permission(from, MAY_WRITE) ?:
+	      inode_permission(to, MAY_WRITE);
 	if (ret < 0)
 		goto out;

@@ -1551,32 +1530,33 @@ int scoutfs_data_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	struct super_block *sb = inode->i_sb;
 	const u64 ino = scoutfs_ino(inode);
 	struct scoutfs_lock *lock = NULL;
-	struct scoutfs_extent *info = NULL;
-	struct page *page = NULL;
 	struct scoutfs_extent ext;
 	struct scoutfs_extent cur;
 	struct data_ext_args args;
 	u32 last_flags;
 	u64 iblock;
 	u64 last;
-	int entries = 0;
 	int ret;
-	int complete = 0;

 	if (len == 0) {
 		ret = 0;
 		goto out;
 	}

-	ret = fiemap_prep(inode, fieinfo, start, &len, FIEMAP_FLAG_SYNC);
+	ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
 	if (ret)
 		goto out;

-	page = alloc_page(GFP_KERNEL);
-	if (!page) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	inode_lock(inode);
+	down_read(&si->extent_sem);
+
+	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ, 0, inode, &lock);
+	if (ret)
+		goto unlock;
+
+	args.ino = ino;
+	args.inode = inode;
+	args.lock = lock;

 	/* use a dummy extent to track */
 	memset(&cur, 0, sizeof(cur));
@@ -1585,93 +1565,48 @@ int scoutfs_data_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	iblock = start >> SCOUTFS_BLOCK_SM_SHIFT;
 	last = (start + len - 1) >> SCOUTFS_BLOCK_SM_SHIFT;

-	args.ino = ino;
-	args.inode = inode;
-
-	/* outer loop */
 	while (iblock <= last) {
-		/* lock */
-		inode_lock(inode);
-		down_read(&si->extent_sem);
-
-		ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ, 0, inode, &lock);
-		if (ret) {
-			up_read(&si->extent_sem);
-			inode_unlock(inode);
-			break;
-		}
-
-		args.lock = lock;
-
-		/* collect entries */
-		info = page_address(page);
-		memset(info, 0, PAGE_SIZE);
-		while (entries < (PAGE_SIZE / sizeof(struct fiemap_extent)) - 1) {
-			ret = scoutfs_ext_next(sb, &data_ext_ops, &args,
-					       iblock, 1, &ext);
-			if (ret < 0) {
-				if (ret == -ENOENT)
-					ret = 0;
-				complete = 1;
-				last_flags = FIEMAP_EXTENT_LAST;
-				break;
-			}
-
-			trace_scoutfs_data_fiemap_extent(sb, ino, &ext);
-
-			if (ext.start > last) {
-				/* not setting _LAST, it's for end of file */
+		ret = scoutfs_ext_next(sb, &data_ext_ops, &args,
+				       iblock, 1, &ext);
+		if (ret < 0) {
+			if (ret == -ENOENT)
 				ret = 0;
-				complete = 1;
-				break;
-			}
-
-			if (scoutfs_ext_can_merge(&cur, &ext)) {
-				/* merged extents could be greater than input len */
-				cur.len += ext.len;
-			} else {
-				/* fill it */
-				memcpy(info, &cur, sizeof(cur));
-
-				entries++;
-				info++;
-
-				cur = ext;
-			}
-
-			iblock = ext.start + ext.len;
+			last_flags = FIEMAP_EXTENT_LAST;
+			break;
 		}

-		/* unlock */
-		scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);
-		up_read(&si->extent_sem);
-		inode_unlock(inode);
+		trace_scoutfs_data_fiemap_extent(sb, ino, &ext);

-		if (ret)
+		if (ext.start > last) {
+			/* not setting _LAST, it's for end of file */
+			ret = 0;
 			break;
+		}

-		/* emit entries */
-		info = page_address(page);
-		for (; entries > 0; entries--) {
-			ret = fill_extent(fieinfo, info, 0);
+		if (scoutfs_ext_can_merge(&cur, &ext)) {
+			/* merged extents could be greater than input len */
+			cur.len += ext.len;
+		} else {
+			ret = fill_extent(fieinfo, &cur, 0);
 			if (ret != 0)
-				goto out;
-			info++;
+				goto unlock;
+			cur = ext;
 		}

-		if (complete)
-			break;
+		iblock = ext.start + ext.len;
 	}

-	/* still one left, it's in cur */
 	if (cur.len)
 		ret = fill_extent(fieinfo, &cur, last_flags);
+unlock:
+	scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);
+	up_read(&si->extent_sem);
+	inode_unlock(inode);

 out:
 	if (ret == 1)
 		ret = 0;
-	if (page)
-		__free_page(page);
+
 	trace_scoutfs_data_fiemap(sb, start, len, ret);

 	return ret;
@@ -1774,16 +1709,12 @@ int scoutfs_data_wait_check(struct inode *inode, loff_t pos, loff_t len,
 	u64 last_block;
 	u64 on;
 	u64 off;
-	loff_t tmp;
 	int ret = 0;

-	if (len == 0)
-		goto out;
-
 	if (WARN_ON_ONCE(sef & SEF_UNKNOWN) ||
 	    WARN_ON_ONCE(op & SCOUTFS_IOC_DWO_UNKNOWN) ||
 	    WARN_ON_ONCE(dw && !RB_EMPTY_NODE(&dw->node)) ||
-	    WARN_ON_ONCE(check_add_overflow(pos, len - 1, &tmp))) {
+	    WARN_ON_ONCE(pos + len < pos)) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -1958,244 +1889,8 @@ 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);
-	struct scoutfs_inode_info *si = SCOUTFS_I(inode);
-	struct super_block *sb = inode->i_sb;
-	struct scoutfs_lock *lock = NULL;
-	SCOUTFS_DECLARE_PER_TASK_ENTRY(pt_ent);
-	DECLARE_DATA_WAIT(dw);
-	struct write_begin_data wbd;
-	u64 ind_seq;
-	loff_t pos;
-	loff_t size;
-	unsigned int len = PAGE_SIZE;
-	vm_fault_t ret = VM_FAULT_SIGBUS;
-	int err;
-
-	pos = vmf->pgoff << PAGE_SHIFT;
-
-	sb_start_pagefault(sb);
-
-	err = scoutfs_lock_inode(sb, SCOUTFS_LOCK_WRITE,
-				 SCOUTFS_LKF_REFRESH_INODE, inode, &lock);
-	if (err) {
-		ret = vmf_error(err);
-		goto out;
-	}
-
-	size = i_size_read(inode);
-
-	if (scoutfs_per_task_add_excl(&si->pt_data_lock, &pt_ent, lock)) {
-		/* data_version is per inode, whole file must be online */
-		err = scoutfs_data_wait_check(inode, 0, size,
-					      SEF_OFFLINE,
-					      SCOUTFS_IOC_DWO_WRITE,
-					      &dw, lock);
-		if (err != 0) {
-			if (err < 0)
-				ret = vmf_error(err);
-			goto out_unlock;
-		}
-	}
-
-
-	/* scoutfs_write_begin */
-	memset(&wbd, 0, sizeof(wbd));
-	INIT_LIST_HEAD(&wbd.ind_locks);
-	wbd.lock = lock;
-
-	/*
-	 * Start transaction before taking page locks - we want to make sure we're
-	 * not locking a page, then waiting for trans, because writeback might race
-	 * against it and cause a lock inversion hang - as demonstrated by both
-	 * holetest and fsstress tests in xfstests.
-	 */
-	do {
-		err = scoutfs_inode_index_start(sb, &ind_seq) ?:
-			scoutfs_inode_index_prepare(sb, &wbd.ind_locks, inode,
-						    true) ?:
-			scoutfs_inode_index_try_lock_hold(sb, &wbd.ind_locks,
-							  ind_seq, false);
-	} while (err > 0);
-	if (err < 0) {
-		ret = vmf_error(err);
-		goto out_trans;
-	}
-
-	down_write(&si->extent_sem);
-
-	if (!trylock_page(page)) {
-		ret = VM_FAULT_NOPAGE;
-		goto out_sem;
-	}
-	ret = VM_FAULT_LOCKED;
-
-	if ((page->mapping != inode->i_mapping) ||
-	    (!PageUptodate(page)) ||
-	    (page_offset(page) > size))	 {
-		unlock_page(page);
-		ret = VM_FAULT_NOPAGE;
-		goto out_sem;
-	}
-
-	if (page->index == (size - 1) >> PAGE_SHIFT)
-		len = ((size - 1) & ~PAGE_MASK) + 1;
-
-	err = __block_write_begin(page, pos, PAGE_SIZE, scoutfs_get_block);
-	if (err) {
-		ret = vmf_error(err);
-		unlock_page(page);
-		goto out_sem;
-	}
-	/* end scoutfs_write_begin */
-
-	/*
-	 * We mark the page dirty already here so that when freeze is in
-	 * progress, we are guaranteed that writeback during freezing will
-	 * see the dirty page and writeprotect it again.
-	 */
-	set_page_dirty(page);
-	wait_for_stable_page(page);
-
-	/* scoutfs_write_end */
-	scoutfs_inode_set_data_seq(inode);
-	scoutfs_inode_inc_data_version(inode);
-
-	file_update_time(vma->vm_file);
-
-	scoutfs_update_inode_item(inode, wbd.lock, &wbd.ind_locks);
-	scoutfs_inode_queue_writeback(inode);
-
-out_sem:
-	up_write(&si->extent_sem);
-out_trans:
-	scoutfs_release_trans(sb);
-	scoutfs_inode_index_unlock(sb, &wbd.ind_locks);
-	/* end scoutfs_write_end */
-
-out_unlock:
-	scoutfs_per_task_del(&si->pt_data_lock, &pt_ent);
-	scoutfs_unlock(sb, lock, SCOUTFS_LOCK_WRITE);
-
-out:
-	sb_end_pagefault(sb);
-
-	if (scoutfs_data_wait_found(&dw)) {
-		/*
-		 * It'd be really nice to not hold the mmap_sem lock here
-		 * before waiting for data, and then return VM_FAULT_RETRY
-		 */
-		err = scoutfs_data_wait(inode, &dw);
-		if (err == 0)
-			ret = VM_FAULT_NOPAGE;
-		else
-			ret = vmf_error(err);
-	}
-
-	trace_scoutfs_data_page_mkwrite(sb, scoutfs_ino(inode), pos, (__force u32)ret);
-
-	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);
-	struct super_block *sb = inode->i_sb;
-	struct scoutfs_lock *inode_lock = NULL;
-	SCOUTFS_DECLARE_PER_TASK_ENTRY(pt_ent);
-	DECLARE_DATA_WAIT(dw);
-	loff_t pos;
-	int err;
-	vm_fault_t ret = VM_FAULT_SIGBUS;
-
-	pos = vmf->pgoff;
-	pos <<= PAGE_SHIFT;
-
-retry:
-	err = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ,
-				 SCOUTFS_LKF_REFRESH_INODE, inode, &inode_lock);
-	if (err < 0)
-		return vmf_error(err);
-
-	if (scoutfs_per_task_add_excl(&si->pt_data_lock, &pt_ent, inode_lock)) {
-		/* protect checked extents from stage/release */
-		atomic_inc(&inode->i_dio_count);
-
-		err = scoutfs_data_wait_check(inode, pos, PAGE_SIZE,
-					      SEF_OFFLINE, SCOUTFS_IOC_DWO_READ,
-					      &dw, inode_lock);
-		if (err != 0) {
-			if (err < 0)
-				ret = vmf_error(err);
-			goto out;
-		}
-	}
-
-#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);
-	scoutfs_unlock(sb, inode_lock, SCOUTFS_LOCK_READ);
-	if (scoutfs_data_wait_found(&dw)) {
-		err = scoutfs_data_wait(inode, &dw);
-		if (err == 0)
-			goto retry;
-
-		ret = VM_FAULT_RETRY;
-	}
-
-	trace_scoutfs_data_filemap_fault(sb, scoutfs_ino(inode), pos, (__force u32)ret);
-
-	return ret;
-}
-
-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)
-{
-	file_accessed(file);
-	vma->vm_ops = &scoutfs_data_file_vm_ops;
-	return 0;
-}
-
 const struct address_space_operations scoutfs_file_aops = {
-#ifdef KC_MPAGE_READ_FOLIO
-	.dirty_folio		= block_dirty_folio,
-	.invalidate_folio	= block_invalidate_folio,
-	.read_folio		= scoutfs_read_folio,
-#else
 	.readpage		= scoutfs_readpage,
-#endif
 #ifndef KC_FILE_AOPS_READAHEAD
 	.readpages		= scoutfs_readpages,
 #else
@@ -2216,10 +1911,7 @@ const struct file_operations scoutfs_file_fops = {
 #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,
 	.llseek		= scoutfs_file_llseek,
--- a/kmod/src/dir.c
+++ b/kmod/src/dir.c
@@ -11,13 +11,11 @@
 * General Public License for more details.
 */
 #include <linux/kernel.h>
-#include <linux/stddef.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/uio.h>
 #include <linux/xattr.h>
 #include <linux/namei.h>
-#include <linux/mm.h>

 #include "format.h"
 #include "file.h"
@@ -436,15 +434,6 @@ out:
 		return d_splice_alias(inode, dentry);
 }

-/*
- * Helper to make iterating through dirent ptrs aligned
- */
-static inline struct scoutfs_dirent *next_aligned_dirent(struct scoutfs_dirent *dent, u8 len)
-{
-	return (void *)dent +
-		ALIGN(offsetof(struct scoutfs_dirent, name[len]), __alignof__(struct scoutfs_dirent));
-}
-
 /*
 * readdir simply iterates over the dirent items for the dir inode and
 * uses their offset as the readdir position.
@@ -452,112 +441,76 @@ static inline struct scoutfs_dirent *next_aligned_dirent(struct scoutfs_dirent *
 * It will need to be careful not to read past the region of the dirent
 * hash offset keys that it has access to.
 */
-static int scoutfs_readdir(struct file *file, struct dir_context *ctx)
+static int KC_DECLARE_READDIR(scoutfs_readdir, struct file *file,
+			      void *dirent, kc_readdir_ctx_t ctx)
 {
 	struct inode *inode = file_inode(file);
 	struct super_block *sb = inode->i_sb;
 	struct scoutfs_lock *dir_lock = NULL;
 	struct scoutfs_dirent *dent = NULL;
-/* we'll store name_len in dent->__pad[0] */
-#define hacky_name_len __pad[0]
 	struct scoutfs_key last_key;
 	struct scoutfs_key key;
-	struct page *page = NULL;
 	int name_len;
 	u64 pos;
-	int entries = 0;
 	int ret;
-	int complete = 0;
-	struct scoutfs_dirent *end;

-	if (!dir_emit_dots(file, ctx))
+	if (!kc_dir_emit_dots(file, dirent, ctx))
 		return 0;

-	page = alloc_page(GFP_KERNEL);
-	if (!page)
+	dent = alloc_dirent(SCOUTFS_NAME_LEN);
+	if (!dent) {
 		return -ENOMEM;
-
-	end = page_address(page) + PAGE_SIZE;
+	}

 	init_dirent_key(&last_key, SCOUTFS_READDIR_TYPE, scoutfs_ino(inode),
 			SCOUTFS_DIRENT_LAST_POS, 0);

-	/*
-	 * lock and fetch dirent items, until the page no longer fits
-	 * a max size dirent (288b). Then unlock and dir_emit the ones
-	 * we stored in the page.
-	 */
+	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ, 0, inode, &dir_lock);
+	if (ret)
+		goto out;
+
 	for (;;) {
-		/* lock */
-		ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ, 0, inode, &dir_lock);
-		if (ret)
-			break;
+		init_dirent_key(&key, SCOUTFS_READDIR_TYPE, scoutfs_ino(inode),
+				kc_readdir_pos(file, ctx), 0);

-		dent = page_address(page);
-		pos = ctx->pos;
-		while (next_aligned_dirent(dent, SCOUTFS_NAME_LEN) < end) {
-			init_dirent_key(&key, SCOUTFS_READDIR_TYPE, scoutfs_ino(inode),
-					pos, 0);
-
-			ret = scoutfs_item_next(sb, &key, &last_key, dent,
-						dirent_bytes(SCOUTFS_NAME_LEN),
-						dir_lock);
-			if (ret < 0) {
-				if (ret == -ENOENT) {
-					ret = 0;
-					complete = 1;
-				}
-				break;
-			}
-
-			name_len = ret - sizeof(struct scoutfs_dirent);
-			dent->hacky_name_len = name_len;
-			if (name_len < 1 || name_len > SCOUTFS_NAME_LEN) {
-				scoutfs_corruption(sb, SC_DIRENT_READDIR_NAME_LEN,
-						   corrupt_dirent_readdir_name_len,
-						   "dir_ino %llu pos %llu key "SK_FMT" len %d",
-						   scoutfs_ino(inode),
-						   pos,
-						   SK_ARG(&key), name_len);
-				ret = -EIO;
-				break;
-			}
-
-			pos = le64_to_cpu(dent->pos) + 1;
-
-			dent = next_aligned_dirent(dent, name_len);
-			entries++;
-		}
-
-		/* unlock */
-		scoutfs_unlock(sb, dir_lock, SCOUTFS_LOCK_READ);
-
-		if (ret < 0)
-			break;
-
-		dent = page_address(page);
-		for (; entries > 0; entries--) {
-			ctx->pos = le64_to_cpu(dent->pos);
-			if (!dir_emit(ctx, dent->name, dent->hacky_name_len,
-					le64_to_cpu(dent->ino),
-					dentry_type(dent->type))) {
+		ret = scoutfs_item_next(sb, &key, &last_key, dent,
+					dirent_bytes(SCOUTFS_NAME_LEN),
+					dir_lock);
+		if (ret < 0) {
+			if (ret == -ENOENT)
 				ret = 0;
-				goto out;
-			}
-
-			dent = next_aligned_dirent(dent, dent->hacky_name_len);
-
-			/* always advance ctx->pos past */
-			ctx->pos++;
+			break;
 		}

-		if (complete)
+		name_len = ret - sizeof(struct scoutfs_dirent);
+		if (name_len < 1 || name_len > SCOUTFS_NAME_LEN) {
+			scoutfs_corruption(sb, SC_DIRENT_READDIR_NAME_LEN,
+					   corrupt_dirent_readdir_name_len,
+					   "dir_ino %llu pos %llu key "SK_FMT" len %d",
+					   scoutfs_ino(inode),
+					   kc_readdir_pos(file, ctx),
+					   SK_ARG(&key), name_len);
+			ret = -EIO;
+			goto out;
+		}
+
+		pos = le64_to_cpu(key.skd_major);
+		kc_readdir_pos(file, ctx) = pos;
+
+		if (!kc_dir_emit(ctx, dirent, dent->name, name_len, pos,
+				le64_to_cpu(dent->ino),
+				dentry_type(dent->type))) {
+			ret = 0;
 			break;
+		}
+
+		kc_readdir_pos(file, ctx) = pos + 1;
 	}

 out:
-	if (page)
-		__free_page(page);
+	scoutfs_unlock(sb, dir_lock, SCOUTFS_LOCK_READ);
+
+	kfree(dent);
 	return ret;
 }

@@ -750,9 +703,8 @@ out_unlock:
 	return inode;
 }

-static int scoutfs_mknod(KC_VFS_NS_DEF
-			 struct inode *dir,
-			 struct dentry *dentry, umode_t mode, dev_t rdev)
+static int scoutfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
+		       dev_t rdev)
 {
 	struct super_block *sb = dir->i_sb;
 	struct inode *inode = NULL;
@@ -821,20 +773,15 @@ out:
 }

 /* XXX hmm, do something with excl? */
-static int scoutfs_create(KC_VFS_NS_DEF
-			  struct inode *dir,
-			  struct dentry *dentry, umode_t mode, bool excl)
+static int scoutfs_create(struct inode *dir, struct dentry *dentry,
+			  umode_t mode, bool excl)
 {
-	return scoutfs_mknod(KC_VFS_NS
-			     dir, dentry, mode | S_IFREG, 0);
+	return scoutfs_mknod(dir, dentry, mode | S_IFREG, 0);
 }

-static int scoutfs_mkdir(KC_VFS_NS_DEF
-			 struct inode *dir,
-			 struct dentry *dentry, umode_t mode)
+static int scoutfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 {
-	return scoutfs_mknod(KC_VFS_NS
-			     dir, dentry, mode | S_IFDIR, 0);
+	return scoutfs_mknod(dir, dentry, mode | S_IFDIR, 0);
 }

 static int scoutfs_link(struct dentry *old_dentry,
@@ -1229,8 +1176,7 @@ static const char *scoutfs_get_link(struct dentry *dentry, struct inode *inode,
 * Symlink target paths can be annoyingly large.  We store relatively
 * rare large paths in multiple items.
 */
-static int scoutfs_symlink(KC_VFS_NS_DEF
-			   struct inode *dir, struct dentry *dentry,
+static int scoutfs_symlink(struct inode *dir, struct dentry *dentry,
 			   const char *symname)
 {
 	struct super_block *sb = dir->i_sb;
@@ -1617,8 +1563,7 @@ static int verify_ancestors(struct super_block *sb, u64 p1, u64 p2,
 * from using parent/child locking orders as two groups can have both
 * parent and child relationships to each other.
 */
-static int scoutfs_rename_common(KC_VFS_NS_DEF
-				 struct inode *old_dir,
+static int scoutfs_rename_common(struct inode *old_dir,
 				 struct dentry *old_dentry, struct inode *new_dir,
 				 struct dentry *new_dentry, unsigned int flags)
 {
@@ -1812,7 +1757,7 @@ retry:
 	}
 	old_inode->i_ctime = now;
 	if (new_inode)
-		new_inode->i_ctime = now;
+		old_inode->i_ctime = now;

 	inode_inc_iversion(old_dir);
 	inode_inc_iversion(old_inode);
@@ -1895,21 +1840,18 @@ 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);
+	return scoutfs_rename_common(old_dir, old_dentry, new_dir, new_dentry, 0);
 }
 #endif

-static int scoutfs_rename2(KC_VFS_NS_DEF
-			  struct inode *old_dir,
+static int scoutfs_rename2(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);
+	return scoutfs_rename_common(old_dir, old_dentry, new_dir, new_dentry, flags);
 }

 #ifdef KC_FMODE_KABI_ITERATE
@@ -1921,18 +1863,8 @@ static int scoutfs_dir_open(struct inode *inode, struct file *file)
 }
 #endif

-static int scoutfs_tmpfile(KC_VFS_NS_DEF
-			   struct inode *dir,
-#ifdef KC_D_TMPFILE_DENTRY
-			   struct dentry *dentry,
-#else
-			   struct file *file,
-#endif
-			   umode_t mode)
+static int scoutfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 {
-#ifndef KC_D_TMPFILE_DENTRY
-	struct dentry *dentry = file->f_path.dentry;
-#endif
 	struct super_block *sb = dir->i_sb;
 	struct inode *inode = NULL;
 	struct scoutfs_lock *dir_lock = NULL;
@@ -1959,11 +1891,7 @@ static int scoutfs_tmpfile(KC_VFS_NS_DEF
 	si->crtime = inode->i_mtime;
 	insert_inode_hash(inode);
 	ihold(inode); /* need to update inode modifications in d_tmpfile */
-#ifdef KC_D_TMPFILE_DENTRY
 	d_tmpfile(dentry, inode);
-#else
-	d_tmpfile(file, inode);
-#endif
 	inode_inc_iversion(inode);
 	scoutfs_forest_inc_inode_count(sb);

@@ -1971,10 +1899,6 @@ static int scoutfs_tmpfile(KC_VFS_NS_DEF
 	scoutfs_update_inode_item(dir, dir_lock, &ind_locks);
 	scoutfs_inode_index_unlock(sb, &ind_locks);

-#ifndef KC_D_TMPFILE_DENTRY
-	ret = finish_open_simple(file, 0);
-#endif
-
 out:
 	scoutfs_release_trans(sb);
 	scoutfs_inode_index_unlock(sb, &ind_locks);
@@ -2020,7 +1944,7 @@ const struct inode_operations scoutfs_symlink_iops = {
 };

 const struct file_operations scoutfs_dir_fops = {
-	.iterate	= scoutfs_readdir,
+	.KC_FOP_READDIR	= scoutfs_readdir,
 #ifdef KC_FMODE_KABI_ITERATE
 	.open		= scoutfs_dir_open,
 #endif
@@ -2053,9 +1977,6 @@ const struct inode_operations scoutfs_dir_iops = {
 #endif
 	.listxattr	= scoutfs_listxattr,
 	.get_acl	= scoutfs_get_acl,
-#ifdef KC_GET_ACL_DENTRY
-	.set_acl	= scoutfs_set_acl,
-#endif
 	.symlink	= scoutfs_symlink,
 	.permission	= scoutfs_permission,
 #ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
--- a/kmod/src/fence.c
+++ b/kmod/src/fence.c
@@ -105,12 +105,12 @@ static ssize_t elapsed_secs_show(struct kobject *kobj,
 {
 	DECLARE_FENCE_FROM_KOBJ(fence, kobj);
 	ktime_t now = ktime_get();
-	ktime_t t = ns_to_ktime(0);
+	struct timeval tv = { 0, };

 	if (ktime_after(now, fence->start_kt))
-		t = ktime_sub(now, fence->start_kt);
+		tv = ktime_to_timeval(ktime_sub(now, fence->start_kt));

-	return snprintf(buf, PAGE_SIZE, "%llu", (long long)ktime_divns(t, NSEC_PER_SEC));
+	return snprintf(buf, PAGE_SIZE, "%llu", (long long)tv.tv_sec);
 }
 SCOUTFS_ATTR_RO(elapsed_secs);

--- a/kmod/src/file.c
+++ b/kmod/src/file.c
@@ -267,8 +267,7 @@ out:
 }
 #endif

-int scoutfs_permission(KC_VFS_NS_DEF
-		       struct inode *inode, int mask)
+int scoutfs_permission(struct inode *inode, int mask)
 {
 	struct super_block *sb = inode->i_sb;
 	struct scoutfs_lock *inode_lock = NULL;
@@ -282,8 +281,7 @@ int scoutfs_permission(KC_VFS_NS_DEF
 	if (ret)
 		return ret;

-	ret = generic_permission(KC_VFS_INIT_NS
-				 inode, mask);
+	ret = generic_permission(inode, mask);

 	scoutfs_unlock(sb, inode_lock, SCOUTFS_LOCK_READ);

--- a/kmod/src/file.h
+++ b/kmod/src/file.h
@@ -10,8 +10,7 @@ ssize_t scoutfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 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);
+int scoutfs_permission(struct inode *inode, int mask);
 loff_t scoutfs_file_llseek(struct file *file, loff_t offset, int whence);

 #endif	/* _SCOUTFS_FILE_H_ */
--- a/kmod/src/format.h
+++ b/kmod/src/format.h
@@ -470,7 +470,7 @@ struct scoutfs_srch_compact {
 * @get_trans_seq, @commit_trans_seq: These pair of sequence numbers
 * determine if a transaction is currently open for the mount that owns
 * the log_trees struct.  get_trans_seq is advanced by the server as the
- * transaction is opened.   The server sets commit_trans_seq equal to
+ * transaction is opened.   The server sets comimt_trans_seq equal to
 * get_ as the transaction is committed.
 */
 struct scoutfs_log_trees {
@@ -1091,8 +1091,7 @@ enum scoutfs_net_cmd {
 	EXPAND_NET_ERRNO(ENOMEM)	\
 	EXPAND_NET_ERRNO(EIO)		\
 	EXPAND_NET_ERRNO(ENOSPC)	\
-	EXPAND_NET_ERRNO(EINVAL)	\
-	EXPAND_NET_ERRNO(ENOLINK)
+	EXPAND_NET_ERRNO(EINVAL)

 #undef EXPAND_NET_ERRNO
 #define EXPAND_NET_ERRNO(which) SCOUTFS_NET_ERR_##which,
--- a/kmod/src/inode.c
+++ b/kmod/src/inode.c
@@ -150,9 +150,6 @@ static const struct inode_operations scoutfs_file_iops = {
 #endif
 	.listxattr	= scoutfs_listxattr,
 	.get_acl	= scoutfs_get_acl,
-#ifdef KC_GET_ACL_DENTRY
-	.set_acl	= scoutfs_set_acl,
-#endif
 	.fiemap		= scoutfs_data_fiemap,
 };

@@ -166,9 +163,6 @@ static const struct inode_operations scoutfs_special_iops = {
 #endif
 	.listxattr	= scoutfs_listxattr,
 	.get_acl	= scoutfs_get_acl,
-#ifdef KC_GET_ACL_DENTRY
-	.set_acl	= scoutfs_set_acl,
-#endif
 };

 /*
@@ -379,8 +373,7 @@ int scoutfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
 {
 	struct inode *inode = dentry->d_inode;
 #else
-int scoutfs_getattr(KC_VFS_NS_DEF
-		    const struct path *path, struct kstat *stat,
+int scoutfs_getattr(const struct path *path, struct kstat *stat,
 		    u32 request_mask, unsigned int query_flags)
 {
 	struct inode *inode = d_inode(path->dentry);
@@ -392,8 +385,7 @@ int scoutfs_getattr(KC_VFS_NS_DEF
 	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ,
 				 SCOUTFS_LKF_REFRESH_INODE, inode, &lock);
 	if (ret == 0) {
-		generic_fillattr(KC_VFS_INIT_NS
-				 inode, stat);
+		generic_fillattr(inode, stat);
 		scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);
 	}
 	return ret;
@@ -491,8 +483,7 @@ int scoutfs_complete_truncate(struct inode *inode, struct scoutfs_lock *lock)
 * re-acquire it.  Ideally we'd fix this so that we can acquire the lock
 * instead of the caller.
 */
-int scoutfs_setattr(KC_VFS_NS_DEF
-		    struct dentry *dentry, struct iattr *attr)
+int scoutfs_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = dentry->d_inode;
 	struct super_block *sb = inode->i_sb;
@@ -510,8 +501,7 @@ retry:
 				 SCOUTFS_LKF_REFRESH_INODE, inode, &lock);
 	if (ret)
 		return ret;
-	ret = setattr_prepare(KC_VFS_INIT_NS
-			      dentry, attr);
+	ret = setattr_prepare(dentry, attr);
 	if (ret)
 		goto out;

@@ -575,8 +565,7 @@ retry:
 	if (ret < 0)
 		goto release;

-	setattr_copy(KC_VFS_INIT_NS
-		     inode, attr);
+	setattr_copy(inode, attr);
 	inode_inc_iversion(inode);
 	scoutfs_update_inode_item(inode, lock, &ind_locks);

@@ -990,10 +979,10 @@ static bool inode_has_index(umode_t mode, u8 type)
 	}
 }

-static int cmp_index_lock(void *priv, KC_LIST_CMP_CONST struct list_head *A, KC_LIST_CMP_CONST struct list_head *B)
+static int cmp_index_lock(void *priv, struct list_head *A, struct list_head *B)
 {
-	KC_LIST_CMP_CONST struct index_lock *a = list_entry(A, KC_LIST_CMP_CONST struct index_lock, head);
-	KC_LIST_CMP_CONST struct index_lock *b = list_entry(B, KC_LIST_CMP_CONST struct index_lock, head);
+	struct index_lock *a = list_entry(A, struct index_lock, head);
+	struct index_lock *b = list_entry(B, struct index_lock, head);

 	return ((int)a->type - (int)b->type) ?:
 	       scoutfs_cmp_u64s(a->major, b->major) ?:
@@ -1482,6 +1471,12 @@ static int remove_index_items(struct super_block *sb, u64 ino,
 * Return an allocated and unused inode number.  Returns -ENOSPC if
 * we're out of inode.
 *
+ * Each parent directory has its own pool of free inode numbers.  Items
+ * are sorted by their inode numbers as they're stored in segments.
+ * This will tend to group together files that are created in a
+ * directory at the same time in segments.  Concurrent creation across
+ * different directories will be stored in their own regions.
+ *
 * Inode numbers are never reclaimed.  If the inode is evicted or we're
 * unmounted the pending inode numbers will be lost.  Asking for a
 * relatively small number from the server each time will tend to
@@ -1491,18 +1486,12 @@ static int remove_index_items(struct super_block *sb, u64 ino,
 int scoutfs_alloc_ino(struct super_block *sb, bool is_dir, u64 *ino_ret)
 {
 	DECLARE_INODE_SB_INFO(sb, inf);
-	struct scoutfs_mount_options opts;
 	struct inode_allocator *ia;
 	u64 ino;
 	u64 nr;
 	int ret;

-	scoutfs_options_read(sb, &opts);
-
-	if (is_dir && opts.ino_alloc_per_lock == SCOUTFS_LOCK_INODE_GROUP_NR)
-		ia = &inf->dir_ino_alloc;
-	else
-		ia = &inf->ino_alloc;
+	ia = is_dir ? &inf->dir_ino_alloc : &inf->ino_alloc;

 	spin_lock(&ia->lock);

@@ -1523,17 +1512,6 @@ int scoutfs_alloc_ino(struct super_block *sb, bool is_dir, u64 *ino_ret)
 	*ino_ret = ia->ino++;
 	ia->nr--;

-	if (opts.ino_alloc_per_lock != SCOUTFS_LOCK_INODE_GROUP_NR) {
-		nr = ia->ino & SCOUTFS_LOCK_INODE_GROUP_MASK;
-		if (nr >= opts.ino_alloc_per_lock) {
-			nr = SCOUTFS_LOCK_INODE_GROUP_NR - nr;
-			if (nr > ia->nr)
-				nr = ia->nr;
-			ia->ino += nr;
-			ia->nr -= nr;
-		}
-	}
-
 	spin_unlock(&ia->lock);
 	ret = 0;
 out:
@@ -1584,8 +1562,7 @@ int scoutfs_new_inode(struct super_block *sb, struct inode *dir, umode_t mode, d
 	scoutfs_inode_set_data_seq(inode);

 	inode->i_ino = ino; /* XXX overflow */
-	inode_init_owner(KC_VFS_INIT_NS
-			 inode, dir, mode);
+	inode_init_owner(inode, dir, mode);
 	inode_set_bytes(inode, 0);
 	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
 	inode->i_rdev = rdev;
@@ -1637,14 +1614,10 @@ int scoutfs_inode_orphan_delete(struct super_block *sb, u64 ino, struct scoutfs_
 				struct scoutfs_lock *primary)
 {
 	struct scoutfs_key key;
-	int ret;

 	init_orphan_key(&key, ino);

-	ret = scoutfs_item_delete_force(sb, &key, lock, primary);
-	trace_scoutfs_inode_orphan_delete(sb, ino, ret);
-
-	return ret;
+	return scoutfs_item_delete_force(sb, &key, lock, primary);
 }

 /*
@@ -1726,8 +1699,6 @@ out:
 		scoutfs_release_trans(sb);
 	scoutfs_inode_index_unlock(sb, &ind_locks);

-	trace_scoutfs_delete_inode_end(sb, ino, mode, size, ret);
-
 	return ret;
 }

@@ -1823,9 +1794,6 @@ out:
 * they've checked that the inode could really be deleted.  We serialize
 * on a bit in the lock data so that we only have one deletion attempt
 * per inode under this mount's cluster lock.
- *
- * Returns -EAGAIN if we either did some cleanup work or are unable to finish
- * cleaning up this inode right now.
 */
 static int try_delete_inode_items(struct super_block *sb, u64 ino)
 {
@@ -1839,8 +1807,6 @@ static int try_delete_inode_items(struct super_block *sb, u64 ino)
 	int bit_nr;
 	int ret;

-	trace_scoutfs_try_delete(sb, ino);
-
 	ret = scoutfs_lock_ino(sb, SCOUTFS_LOCK_WRITE, 0, ino, &lock);
 	if (ret < 0)
 		goto out;
@@ -1853,32 +1819,27 @@ static int try_delete_inode_items(struct super_block *sb, u64 ino)

 	/* only one local attempt per inode at a time */
 	if (test_and_set_bit(bit_nr, ldata->trying)) {
-		trace_scoutfs_try_delete_local_busy(sb, ino);
-		ret = -EAGAIN;
+		ret = 0;
 		goto out;
 	}
 	clear_trying = true;

 	/* can't delete if it's cached in local or remote mounts */
 	if (scoutfs_omap_test(sb, ino) || test_bit_le(bit_nr, ldata->map.bits)) {
-		trace_scoutfs_try_delete_cached(sb, ino);
-		ret = -EAGAIN;
+		ret = 0;
 		goto out;
 	}

 	scoutfs_inode_init_key(&key, ino);
 	ret = lookup_inode_item(sb, &key, &sinode, lock);
 	if (ret < 0) {
-		if (ret == -ENOENT) {
-			trace_scoutfs_try_delete_no_item(sb, ino);
+		if (ret == -ENOENT)
 			ret = 0;
-		}
 		goto out;
 	}

 	if (le32_to_cpu(sinode.nlink) > 0) {
-		trace_scoutfs_try_delete_has_links(sb, ino, le32_to_cpu(sinode.nlink));
-		ret = -EAGAIN;
+		ret = 0;
 		goto out;
 	}

@@ -1887,11 +1848,6 @@ static int try_delete_inode_items(struct super_block *sb, u64 ino)
 		goto out;

 	ret = delete_inode_items(sb, ino, &sinode, lock, orph_lock);
-	if (ret == 0) {
-		ret = -EAGAIN;
-		scoutfs_inc_counter(sb, inode_deleted);
-	}
-
 out:
 	if (clear_trying)
 		clear_bit(bit_nr, ldata->trying);
@@ -2000,8 +1956,6 @@ static void iput_worker(struct work_struct *work)
 		while (count-- > 0)
 			iput(inode);

-		cond_resched();
-
 		/* can't touch inode after final iput */

 		spin_lock(&inf->iput_lock);
@@ -2092,10 +2046,6 @@ void scoutfs_inode_schedule_orphan_dwork(struct super_block *sb)
 * a locally cached inode.  Then we ask the server for the open map
 * containing the inode.  Only if we don't see any cached users do we do
 * the expensive work of acquiring locks to try and delete the items.
- *
- * We need to track whether there is any orphan cleanup work remaining so
- * that tests such as inode-deletion can watch the orphan_scan_empty counter
- * to determine when inode cleanup from open-unlink scenarios is complete.
 */
 static void inode_orphan_scan_worker(struct work_struct *work)
 {
@@ -2107,14 +2057,11 @@ static void inode_orphan_scan_worker(struct work_struct *work)
 	SCOUTFS_BTREE_ITEM_REF(iref);
 	struct scoutfs_key last;
 	struct scoutfs_key key;
-	bool work_todo = false;
 	u64 group_nr;
 	int bit_nr;
 	u64 ino;
 	int ret;

-	trace_scoutfs_orphan_scan_start(sb);
-
 	scoutfs_inc_counter(sb, orphan_scan);

 	init_orphan_key(&last, U64_MAX);
@@ -2134,10 +2081,8 @@ static void inode_orphan_scan_worker(struct work_struct *work)
 		init_orphan_key(&key, ino);
 		ret = scoutfs_btree_next(sb, &roots.fs_root, &key, &iref);
 		if (ret < 0) {
-			if (ret == -ENOENT) {
-				trace_scoutfs_orphan_scan_work(sb, 0);
+			if (ret == -ENOENT)
 				break;
-			}
 			goto out;
 		}

@@ -2152,7 +2097,6 @@ static void inode_orphan_scan_worker(struct work_struct *work)

 		/* locally cached inodes will try to delete as they evict */
 		if (scoutfs_omap_test(sb, ino)) {
-			work_todo = true;
 			scoutfs_inc_counter(sb, orphan_scan_cached);
 			continue;
 		}
@@ -2168,22 +2112,13 @@ static void inode_orphan_scan_worker(struct work_struct *work)

 		/* remote cached inodes will also try to delete */
 		if (test_bit_le(bit_nr, omap.bits)) {
-			work_todo = true;
 			scoutfs_inc_counter(sb, orphan_scan_omap_set);
 			continue;
 		}

 		/* seemingly orphaned and unused, get locks and check for sure */
 		scoutfs_inc_counter(sb, orphan_scan_attempts);
-		trace_scoutfs_orphan_scan_work(sb, ino);
-
 		ret = try_delete_inode_items(sb, ino);
-		if (ret == -EAGAIN) {
-			work_todo = true;
-			ret = 0;
-		}
-
-		trace_scoutfs_orphan_scan_end(sb, ino, ret);
 	}

 	ret = 0;
@@ -2192,11 +2127,6 @@ out:
 	if (ret < 0)
 		scoutfs_inc_counter(sb, orphan_scan_error);

-	if (!work_todo)
-		scoutfs_inc_counter(sb, orphan_scan_empty);
-
-	trace_scoutfs_orphan_scan_stop(sb, work_todo);
-
 	scoutfs_inode_schedule_orphan_dwork(sb);
 }

@@ -2247,7 +2177,7 @@ int scoutfs_inode_walk_writeback(struct super_block *sb, bool write)
 	struct scoutfs_inode_info *si;
 	struct scoutfs_inode_info *tmp;
 	struct inode *inode;
-	int ret = 0;
+	int ret;

 	spin_lock(&inf->writeback_lock);

--- a/kmod/src/inode.h
+++ b/kmod/src/inode.h
@@ -135,12 +135,10 @@ int scoutfs_inode_refresh(struct inode *inode, struct scoutfs_lock *lock);
 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,
+int scoutfs_getattr(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);
+int scoutfs_setattr(struct dentry *dentry, struct iattr *attr);

 int scoutfs_inode_orphan_create(struct super_block *sb, u64 ino, struct scoutfs_lock *lock,
 				struct scoutfs_lock *primary);
--- a/kmod/src/ioctl.c
+++ b/kmod/src/ioctl.c
@@ -23,7 +23,6 @@
 #include <linux/aio.h>
 #include <linux/list_sort.h>
 #include <linux/backing-dev.h>
-#include <linux/overflow.h>

 #include "format.h"
 #include "key.h"
@@ -48,7 +47,6 @@
 #include "wkic.h"
 #include "quota.h"
 #include "scoutfs_trace.h"
-#include "util.h"

 /*
 * We make inode index items coherent by locking fixed size regions of
@@ -58,23 +56,25 @@
 * key space after we find no items in a given lock region.  This is
 * relatively cheap because reading is going to check the segments
 * anyway.
+ *
+ * This is copying to userspace while holding a read lock.  This is safe
+ * because faulting can send a request for a write lock while the read
+ * lock is being used.  The cluster locks don't block tasks in a node,
+ * they match and the tasks fall back to local locking.  In this case
+ * the spin locks around the item cache.
 */
 static long scoutfs_ioc_walk_inodes(struct file *file, unsigned long arg)
 {
 	struct super_block *sb = file_inode(file)->i_sb;
 	struct scoutfs_ioctl_walk_inodes __user *uwalk = (void __user *)arg;
 	struct scoutfs_ioctl_walk_inodes walk;
-	struct scoutfs_ioctl_walk_inodes_entry *ent = NULL;
-	struct scoutfs_ioctl_walk_inodes_entry *end;
+	struct scoutfs_ioctl_walk_inodes_entry ent;
 	struct scoutfs_key next_key;
 	struct scoutfs_key last_key;
 	struct scoutfs_key key;
 	struct scoutfs_lock *lock;
-	struct page *page = NULL;
 	u64 last_seq;
-	u64 entries = 0;
 	int ret = 0;
-	int complete = 0;
 	u32 nr = 0;
 	u8 type;

@@ -105,10 +105,6 @@ static long scoutfs_ioc_walk_inodes(struct file *file, unsigned long arg)
 		}
 	}

-	page = alloc_page(GFP_KERNEL);
-	if (!page)
-		return -ENOMEM;
-
 	scoutfs_inode_init_index_key(&key, type, walk.first.major,
 				     walk.first.minor, walk.first.ino);
 	scoutfs_inode_init_index_key(&last_key, type, walk.last.major,
@@ -117,107 +113,77 @@ static long scoutfs_ioc_walk_inodes(struct file *file, unsigned long arg)
 	/* cap nr to the max the ioctl can return to a compat task */
 	walk.nr_entries = min_t(u64, walk.nr_entries, INT_MAX);

-	end = page_address(page) + PAGE_SIZE;
+	ret = scoutfs_lock_inode_index(sb, SCOUTFS_LOCK_READ, type,
+				       walk.first.major, walk.first.ino,
+				       &lock);
+	if (ret < 0)
+		goto out;

-	/* outer loop */
-	for (nr = 0;;) {
-		ent = page_address(page);
-		/* make sure _pad and minor are zeroed */
-		memset(ent, 0, PAGE_SIZE);
+	for (nr = 0; nr < walk.nr_entries; ) {

-		ret = scoutfs_lock_inode_index(sb, SCOUTFS_LOCK_READ, type,
-					       le64_to_cpu(key.skii_major),
-					       le64_to_cpu(key.skii_ino),
-					       &lock);
-		if (ret)
+		ret = scoutfs_item_next(sb, &key, &last_key, NULL, 0, lock);
+		if (ret < 0 && ret != -ENOENT)
 			break;

-		/* inner loop 1 */
-		while (ent + 1 < end) {
-			ret = scoutfs_item_next(sb, &key, &last_key, NULL, 0, lock);
-			if (ret < 0 && ret != -ENOENT)
+		if (ret == -ENOENT) {
+
+			/* done if lock covers last iteration key */
+			if (scoutfs_key_compare(&last_key, &lock->end) <= 0) {
+				ret = 0;
 				break;
-
-			if (ret == -ENOENT) {
-				/* done if lock covers last iteration key */
-				if (scoutfs_key_compare(&last_key, &lock->end) <= 0) {
-					ret = 0;
-					complete = 1;
-					break;
-				}
-
-				/* continue iterating after locked empty region */
-				key = lock->end;
-				scoutfs_key_inc(&key);
-
-				scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);
-				/* avoid double-unlocking here after break */
-				lock = NULL;
-
-				ret = scoutfs_forest_next_hint(sb, &key, &next_key);
-				if (ret < 0 && ret != -ENOENT)
-					break;
-
-				if (ret == -ENOENT ||
-				    scoutfs_key_compare(&next_key, &last_key) > 0) {
-					ret = 0;
-					complete = 1;
-					break;
-				}
-
-				key = next_key;
-
-				ret = scoutfs_lock_inode_index(sb, SCOUTFS_LOCK_READ,
-							type,
-							le64_to_cpu(key.skii_major),
-							le64_to_cpu(key.skii_ino),
-							&lock);
-				if (ret)
-					break;
-
-				continue;
 			}

-			ent->major = le64_to_cpu(key.skii_major);
-			ent->ino = le64_to_cpu(key.skii_ino);
-
+			/* continue iterating after locked empty region */
+			key = lock->end;
 			scoutfs_key_inc(&key);

-			ent++;
-			entries++;
+			scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);

-			if (nr + entries >= walk.nr_entries) {
-				complete = 1;
-				break;
-			}
-		}
+			ret = scoutfs_forest_next_hint(sb, &key, &next_key);
+			if (ret < 0 && ret != -ENOENT)
+				goto out;

-		scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);
-		if (ret < 0)
-			break;
-
-		/* inner loop 2 */
-		ent = page_address(page);
-		for (; entries > 0; entries--) {
-			if (copy_to_user((void __user *)walk.entries_ptr, ent,
-					 sizeof(struct scoutfs_ioctl_walk_inodes_entry))) {
-				ret = -EFAULT;
+			if (ret == -ENOENT ||
+			    scoutfs_key_compare(&next_key, &last_key) > 0) {
+				ret = 0;
 				goto out;
 			}
-			walk.entries_ptr += sizeof(struct scoutfs_ioctl_walk_inodes_entry);
-			ent++;
-			nr++;
+
+			key = next_key;
+
+			ret = scoutfs_lock_inode_index(sb, SCOUTFS_LOCK_READ,
+						key.sk_type,
+						le64_to_cpu(key.skii_major),
+						le64_to_cpu(key.skii_ino),
+						&lock);
+			if (ret < 0)
+				goto out;
+
+			continue;
 		}

-		if (complete)
+		ent.major = le64_to_cpu(key.skii_major);
+		ent.minor = 0;
+		ent.ino = le64_to_cpu(key.skii_ino);
+
+		if (copy_to_user((void __user *)walk.entries_ptr, &ent,
+				 sizeof(ent))) {
+			ret = -EFAULT;
 			break;
+		}
+
+		nr++;
+		walk.entries_ptr += sizeof(ent);
+
+		scoutfs_key_inc(&key);
 	}

+	scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);
+
 out:
-	if (page)
-		__free_page(page);
 	if (nr > 0)
 		ret = nr;
+
 	return ret;
 }

@@ -322,7 +288,6 @@ static long scoutfs_ioc_release(struct file *file, unsigned long arg)
 	u64 online;
 	u64 offline;
 	u64 isize;
-	__u64 tmp;
 	int ret;

 	if (copy_from_user(&args, (void __user *)arg, sizeof(args)))
@@ -332,11 +297,12 @@ static long scoutfs_ioc_release(struct file *file, unsigned long arg)

 	if (args.length == 0)
 		return 0;
-	if ((check_add_overflow(args.offset, args.length - 1, &tmp)) ||
+	if (((args.offset + args.length) < args.offset) ||
 	    (args.offset & SCOUTFS_BLOCK_SM_MASK) ||
 	    (args.length & SCOUTFS_BLOCK_SM_MASK))
 		return -EINVAL;

+
 	ret = mnt_want_write_file(file);
 	if (ret)
 		return ret;
@@ -441,6 +407,8 @@ static long scoutfs_ioc_data_wait_err(struct file *file, unsigned long arg)

 	if (!S_ISREG(inode->i_mode)) {
 		ret = -EINVAL;
+	} else if (scoutfs_inode_data_version(inode) != args.data_version) {
+		ret = -ESTALE;
 	} else {
 		ret = scoutfs_data_wait_err(inode, sblock, eblock, args.op,
 					    args.err);
@@ -554,9 +522,7 @@ static long scoutfs_ioc_stage(struct file *file, unsigned long arg)
 	}

 	si->staging = true;
-#ifdef KC_CURRENT_BACKING_DEV_INFO
 	current->backing_dev_info = inode_to_bdi(inode);
-#endif

 	pos = args.offset;
 	written = 0;
@@ -569,9 +535,7 @@ static long scoutfs_ioc_stage(struct file *file, unsigned long arg)
 	} while (ret > 0 && written < args.length);

 	si->staging = false;
-#ifdef KC_CURRENT_BACKING_DEV_INFO
 	current->backing_dev_info = NULL;
-#endif
 out:
 	scoutfs_per_task_del(&si->pt_data_lock, &pt_ent);
 	scoutfs_unlock(sb, lock, SCOUTFS_LOCK_WRITE);
@@ -710,8 +674,8 @@ static long scoutfs_ioc_setattr_more(struct file *file, unsigned long arg)
 		goto out;
 	}

-	iax->x_mask = SCOUTFS_IOC_IAX_CTIME | SCOUTFS_IOC_IAX_CRTIME |
-		      SCOUTFS_IOC_IAX_SIZE;
+	iax->x_mask = SCOUTFS_IOC_IAX_DATA_VERSION | SCOUTFS_IOC_IAX_CTIME |
+		      SCOUTFS_IOC_IAX_CRTIME | SCOUTFS_IOC_IAX_SIZE;
 	iax->data_version = sm.data_version;
 	iax->ctime_sec = sm.ctime_sec;
 	iax->ctime_nsec = sm.ctime_nsec;
@@ -722,9 +686,6 @@ static long scoutfs_ioc_setattr_more(struct file *file, unsigned long arg)
 	if (sm.flags & SCOUTFS_IOC_SETATTR_MORE_OFFLINE)
 		iax->x_flags |= SCOUTFS_IOC_IAX_F_SIZE_OFFLINE;

-	if (sm.data_version != 0)
-		iax->x_mask |= SCOUTFS_IOC_IAX_DATA_VERSION;
-
 	ret = mnt_want_write_file(file);
 	if (ret < 0)
 		goto out;
@@ -752,8 +713,7 @@ static long scoutfs_ioc_listxattr_hidden(struct file *file, unsigned long arg)
 	int total = 0;
 	int ret;

-	ret = inode_permission(KC_VFS_INIT_NS
-			       inode, MAY_READ);
+	ret = inode_permission(inode, MAY_READ);
 	if (ret < 0)
 		goto out;

@@ -952,9 +912,6 @@ static int copy_alloc_detail_to_user(struct super_block *sb, void *arg,
 	if (args->copied == args->nr)
 		return -EOVERFLOW;

-	/* .type and .pad need clearing */
-	memset(&ade, 0, sizeof(struct scoutfs_ioctl_alloc_detail_entry));
-
 	ade.blocks = blocks;
 	ade.id = id;
 	ade.meta = !!meta;
@@ -994,7 +951,6 @@ static long scoutfs_ioc_move_blocks(struct file *file, unsigned long arg)
 	struct scoutfs_ioctl_move_blocks mb;
 	struct file *from_file;
 	struct inode *from;
-	u64 tmp;
 	int ret;

 	if (copy_from_user(&mb, umb, sizeof(mb)))
@@ -1003,8 +959,8 @@ static long scoutfs_ioc_move_blocks(struct file *file, unsigned long arg)
 	if (mb.len == 0)
 		return 0;

-	if ((check_add_overflow(mb.from_off, mb.len - 1, &tmp)) ||
-	    (check_add_overflow(mb.to_off, mb.len - 1, &tmp)))
+	if (mb.from_off + mb.len < mb.from_off ||
+	    mb.to_off + mb.len < mb.to_off)
 		return -EOVERFLOW;

 	from_file = fget(mb.from_fd);
@@ -1196,15 +1152,11 @@ static long scoutfs_ioc_get_allocated_inos(struct file *file, unsigned long arg)
 	struct scoutfs_lock *lock = NULL;
 	struct scoutfs_key key;
 	struct scoutfs_key end;
-	struct page *page = NULL;
 	u64 __user *uinos;
 	u64 bytes;
-	u64 *ino;
-	u64 *ino_end;
-	int entries = 0;
+	u64 ino;
 	int nr;
 	int ret;
-	int complete = 0;

 	if (!(file->f_mode & FMODE_READ)) {
 		ret = -EBADF;
@@ -1226,83 +1178,47 @@ static long scoutfs_ioc_get_allocated_inos(struct file *file, unsigned long arg)
 		goto out;
 	}

-	page = alloc_page(GFP_KERNEL);
-	if (!page) {
-		ret = -ENOMEM;
-		goto out;
-	}
-	ino_end = page_address(page) + PAGE_SIZE;
-
 	scoutfs_inode_init_key(&key, gai.start_ino);
 	scoutfs_inode_init_key(&end, gai.start_ino | SCOUTFS_LOCK_INODE_GROUP_MASK);
 	uinos = (void __user *)gai.inos_ptr;
 	bytes = gai.inos_bytes;
 	nr = 0;

-	for (;;) {
+	ret = scoutfs_lock_ino(sb, SCOUTFS_LOCK_READ, 0, gai.start_ino, &lock);
+	if (ret < 0)
+		goto out;

-		ret = scoutfs_lock_ino(sb, SCOUTFS_LOCK_READ, 0, gai.start_ino, &lock);
-		if (ret < 0)
-			goto out;
+	while (bytes >= sizeof(*uinos)) {

-		ino = page_address(page);
-		while (ino < ino_end) {
-
-			ret = scoutfs_item_next(sb, &key, &end, NULL, 0, lock);
-			if (ret < 0) {
-				if (ret == -ENOENT) {
-					ret = 0;
-					complete = 1;
-				}
-				break;
-			}
-
-			if (key.sk_zone != SCOUTFS_FS_ZONE) {
+		ret = scoutfs_item_next(sb, &key, &end, NULL, 0, lock);
+		if (ret < 0) {
+			if (ret == -ENOENT)
 				ret = 0;
-				complete = 1;
-				break;
-			}
-
-			/* all fs items are owned by allocated inodes, and _first is always ino */
-			*ino = le64_to_cpu(key._sk_first);
-			scoutfs_inode_init_key(&key, *ino + 1);
-
-			ino++;
-			entries++;
-			nr++;
-
-			bytes -= sizeof(*uinos);
-			if (bytes < sizeof(*uinos)) {
-				complete = 1;
-				break;
-			}
-
-			if (nr == INT_MAX) {
-				complete = 1;
-				break;
-			}
+			break;
 		}

-		scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);
-
-		if (ret < 0)
+		if (key.sk_zone != SCOUTFS_FS_ZONE) {
+			ret = 0;
 			break;
+		}

-		ino = page_address(page);
-		if (copy_to_user(uinos, ino, entries * sizeof(*uinos))) {
+		/* all fs items are owned by allocated inodes, and _first is always ino */
+		ino = le64_to_cpu(key._sk_first);
+		if (put_user(ino, uinos)) {
 			ret = -EFAULT;
-			goto out;
+			break;
 		}

-		uinos += entries;
-		entries = 0;
-
-		if (complete)
+		uinos++;
+		bytes -= sizeof(*uinos);
+		if (++nr == INT_MAX)
 			break;
+
+		scoutfs_inode_init_key(&key, ino + 1);
 	}
+
+	scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);
 out:
-	if (page)
-		__free_page(page);
 	return ret ?: nr;
 }

@@ -1370,7 +1286,7 @@ static long scoutfs_ioc_get_referring_entries(struct file *file, unsigned long a
 			ent.d_type = bref->d_type;
 			ent.name_len = name_len;

-			if (copy_to_user(uent, &ent, offsetof(struct scoutfs_ioctl_dirent, name[0])) ||
+			if (copy_to_user(uent, &ent, sizeof(struct scoutfs_ioctl_dirent)) ||
 			    copy_to_user(&uent->name[0], bref->dent.name, name_len) ||
 			    put_user('\0', &uent->name[name_len])) {
 				ret = -EFAULT;
--- a/kmod/src/ioctl.h
+++ b/kmod/src/ioctl.h
@@ -366,15 +366,10 @@ struct scoutfs_ioctl_statfs_more {
 *
 * Find current waiters that match the inode, op, and block range to wake
 * up and return an error.
- *
- * (*) ca. v1.25 and earlier required that the data_version passed match
- * that of the waiter, but this check is removed. It was never needed
- * because no data is modified during this ioctl. Any data_version value
- * here is thus since then ignored.
 */
 struct scoutfs_ioctl_data_wait_err {
 	__u64 ino;
-	__u64 data_version; /* Ignored, see above (*) */
+	__u64 data_version;
 	__u64 offset;
 	__u64 count;
 	__u64 op;
--- a/kmod/src/item.c
+++ b/kmod/src/item.c
@@ -86,8 +86,6 @@ struct item_cache_info {
 	/* often walked, but per-cpu refs are fast path */
 	rwlock_t rwlock;
 	struct rb_root pg_root;
-	/* stop readers from caching stale items behind reclaimed cleaned written items */
-	u64 read_dirty_barrier;

 	/* page-granular modification by writers, then exclusive to commit */
 	spinlock_t dirty_lock;
@@ -98,6 +96,10 @@ struct item_cache_info {
 	spinlock_t lru_lock;
 	struct list_head lru_list;
 	unsigned long lru_pages;
+
+	/* written by page readers, read by shrink */
+	spinlock_t active_lock;
+	struct list_head active_list;
 };

 #define DECLARE_ITEM_CACHE_INFO(sb, name) \
@@ -1283,6 +1285,78 @@ static int cache_empty_page(struct super_block *sb,
 	return 0;
 }

+/*
+ * Readers operate independently from dirty items and transactions.
+ * They read a set of persistent items and insert them into the cache
+ * when there aren't already pages whose key range contains the items.
+ * This naturally prefers cached dirty items over stale read items.
+ *
+ * We have to deal with the case where dirty items are written and
+ * invalidated while a read is in flight.   The reader won't have seen
+ * the items that were dirty in their persistent roots as they started
+ * reading.  By the time they insert their read pages the previously
+ * dirty items have been reclaimed and are not in the cache.  The old
+ * stale items will be inserted in their place, effectively corrupting
+ * by having the dirty items disappear.
+ *
+ * We fix this by tracking the max seq of items in pages.  As readers
+ * start they record the current transaction seq.  Invalidation skips
+ * pages with a max seq greater than the first reader seq because the
+ * items in the page have to stick around to prevent the readers stale
+ * items from being inserted.
+ *
+ * This naturally only affects a small set of pages with items that were
+ * written relatively recently.  If we're in memory pressure then we
+ * probably have a lot of pages and they'll naturally have items that
+ * were visible to any raders.  We don't bother with the complicated and
+ * expensive further refinement of tracking the ranges that are being
+ * read and comparing those with pages to invalidate.
+ */
+struct active_reader {
+	struct list_head head;
+	u64 seq;
+};
+
+#define INIT_ACTIVE_READER(rdr) \
+	struct active_reader rdr = { .head = LIST_HEAD_INIT(rdr.head) }
+
+static void add_active_reader(struct super_block *sb, struct active_reader *active)
+{
+	DECLARE_ITEM_CACHE_INFO(sb, cinf);
+
+	BUG_ON(!list_empty(&active->head));
+
+	active->seq = scoutfs_trans_sample_seq(sb);
+
+	spin_lock(&cinf->active_lock);
+	list_add_tail(&active->head, &cinf->active_list);
+	spin_unlock(&cinf->active_lock);
+}
+
+static u64 first_active_reader_seq(struct item_cache_info *cinf)
+{
+	struct active_reader *active;
+	u64 first;
+
+	/* only the calling task adds or deletes this active */
+	spin_lock(&cinf->active_lock);
+	active = list_first_entry_or_null(&cinf->active_list, struct active_reader, head);
+	first = active ? active->seq : U64_MAX;
+	spin_unlock(&cinf->active_lock);
+
+	return first;
+}
+
+static void del_active_reader(struct item_cache_info *cinf, struct active_reader *active)
+{
+	/* only the calling task adds or deletes this active */
+	if (!list_empty(&active->head)) {
+		spin_lock(&cinf->active_lock);
+		list_del_init(&active->head);
+		spin_unlock(&cinf->active_lock);
+	}
+}
+
 /*
 * Add a newly read item to the pages that we're assembling for
 * insertion into the cache.   These pages are private, they only exist
@@ -1376,34 +1450,24 @@ static int read_page_item(struct super_block *sb, struct scoutfs_key *key, u64 s
 * and duplicates, we insert any resulting pages which don't overlap
 * with existing cached pages.
 *
- * The forest item reader is reading stable trees that could be
- * overwritten.  It can return -ESTALE which we return to the caller who
- * will retry the operation and work with a new set of more recent
- * btrees.
- *
 * We only insert uncached regions because this is called with cluster
 * locks held, but without locking the cache.  The regions we read can
 * be stale with respect to the current cache, which can be read and
 * dirtied by other cluster lock holders on our node, but the cluster
- * locks protect the stable items we read.
+ * locks protect the stable items we read.  Invalidation is careful not
+ * to drop pages that have items that we couldn't see because they were
+ * dirty when we started reading.
 *
- * Using the presence of locally written dirty pages to override stale
- * read pages only works if, well, the more recent locally written pages
- * are still present.  Readers are totally decoupled from writers and
- * can have a set of items that is very old indeed.  In the mean time
- * more recent items would have been dirtied locally, committed,
- * cleaned, and reclaimed.  We have a coarse barrier which ensures that
- * readers can't insert items read from old roots from before local data
- * was written.  If a write completes while a read is in progress the
- * read will have to retry.  The retried read can use cached blocks so
- * we're relying on reads being much faster than writes to reduce the
- * overhead to mostly cpu work of recollecting the items from cached
- * blocks via a more recent root from the server.
+ * The forest item reader is reading stable trees that could be
+ * overwritten.  It can return -ESTALE which we return to the caller who
+ * will retry the operation and work with a new set of more recent
+ * btrees.
 */
 static int read_pages(struct super_block *sb, struct item_cache_info *cinf,
 		      struct scoutfs_key *key, struct scoutfs_lock *lock)
 {
 	struct rb_root root = RB_ROOT;
+	INIT_ACTIVE_READER(active);
 	struct cached_page *right = NULL;
 	struct cached_page *pg;
 	struct cached_page *rd;
@@ -1416,7 +1480,6 @@ static int read_pages(struct super_block *sb, struct item_cache_info *cinf,
 	struct rb_node *par;
 	struct rb_node *pg_tmp;
 	struct rb_node *item_tmp;
-	u64 rdbar;
 	int pgi;
 	int ret;

@@ -1430,9 +1493,8 @@ static int read_pages(struct super_block *sb, struct item_cache_info *cinf,
 	pg->end = lock->end;
 	rbtree_insert(&pg->node, NULL, &root.rb_node, &root);

-	read_lock(&cinf->rwlock);
-	rdbar = cinf->read_dirty_barrier;
-	read_unlock(&cinf->rwlock);
+	/* set active reader seq before reading persistent roots */
+	add_active_reader(sb, &active);

 	start = lock->start;
 	end = lock->end;
@@ -1471,13 +1533,6 @@ static int read_pages(struct super_block *sb, struct item_cache_info *cinf,
 retry:
 	write_lock(&cinf->rwlock);

-	/* can't insert if write has cleaned since we read */
-	if (cinf->read_dirty_barrier != rdbar) {
-		scoutfs_inc_counter(sb, item_read_pages_barrier);
-		ret = -ESTALE;
-		goto unlock;
-	}
-
 	while ((rd = first_page(&root))) {

 		pg = page_rbtree_walk(sb, &cinf->pg_root, &rd->start, &rd->end,
@@ -1515,12 +1570,12 @@ retry:
 		}
 	}

-	ret = 0;
-
-unlock:
 	write_unlock(&cinf->rwlock);

+	ret = 0;
 out:
+	del_active_reader(cinf, &active);
+
 	/* free any pages we left dangling on error */
 	for_each_page_safe(&root, rd, pg_tmp) {
 		rbtree_erase(&rd->node, &root);
@@ -1580,7 +1635,6 @@ retry:
 			ret = read_pages(sb, cinf, key, lock);
 		if (ret < 0 && ret != -ESTALE)
 			goto out;
-		scoutfs_inc_counter(sb, item_read_pages_retry);
 		goto retry;
 	}

@@ -2187,18 +2241,18 @@ u64 scoutfs_item_dirty_pages(struct super_block *sb)
 	return (u64)atomic_read(&cinf->dirty_pages);
 }

-static int cmp_pg_start(void *priv, KC_LIST_CMP_CONST struct list_head *A, KC_LIST_CMP_CONST struct list_head *B)
+static int cmp_pg_start(void *priv, struct list_head *A, struct list_head *B)
 {
-	KC_LIST_CMP_CONST struct cached_page *a = list_entry(A, KC_LIST_CMP_CONST struct cached_page, dirty_head);
-	KC_LIST_CMP_CONST struct cached_page *b = list_entry(B, KC_LIST_CMP_CONST struct cached_page, dirty_head);
+	struct cached_page *a = list_entry(A, struct cached_page, dirty_head);
+	struct cached_page *b = list_entry(B, struct cached_page, dirty_head);

 	return scoutfs_key_compare(&a->start, &b->start);
 }

-static int cmp_item_key(void *priv, KC_LIST_CMP_CONST struct list_head *A, KC_LIST_CMP_CONST struct list_head *B)
+static int cmp_item_key(void *priv, struct list_head *A, struct list_head *B)
 {
-	KC_LIST_CMP_CONST struct cached_item *a = list_entry(A, KC_LIST_CMP_CONST struct cached_item, dirty_head);
-	KC_LIST_CMP_CONST struct cached_item *b = list_entry(B, KC_LIST_CMP_CONST struct cached_item, dirty_head);
+	struct cached_item *a = list_entry(A, struct cached_item, dirty_head);
+	struct cached_item *b = list_entry(B, struct cached_item, dirty_head);

 	return scoutfs_key_compare(&a->key, &b->key);
 }
@@ -2347,12 +2401,6 @@ out:
 * The caller has successfully committed all the dirty btree blocks that
 * contained the currently dirty items.  Clear all the dirty items and
 * pages.
- *
- * This strange lock/trylock loop comes from sparse issuing spurious
- * mismatched context warnings if we do anything (like unlock and relax)
- * in the else branch of the failed trylock.  We're jumping through
- * hoops to not use the else but still drop and reacquire the dirty_lock
- * if the trylock fails.
 */
 int scoutfs_item_write_done(struct super_block *sb)
 {
@@ -2361,35 +2409,40 @@ int scoutfs_item_write_done(struct super_block *sb)
 	struct cached_item *tmp;
 	struct cached_page *pg;

-	/* don't let read_pages miss written+cleaned items */
-	write_lock(&cinf->rwlock);
-	cinf->read_dirty_barrier++;
-	write_unlock(&cinf->rwlock);
-
+retry:
 	spin_lock(&cinf->dirty_lock);
-	while ((pg = list_first_entry_or_null(&cinf->dirty_list, struct cached_page, dirty_head))) {
-		if (write_trylock(&pg->rwlock)) {
+
+	while ((pg = list_first_entry_or_null(&cinf->dirty_list,
+					      struct cached_page,
+					      dirty_head))) {
+
+		if (!write_trylock(&pg->rwlock)) {
 			spin_unlock(&cinf->dirty_lock);
-			list_for_each_entry_safe(item, tmp, &pg->dirty_list,
-						 dirty_head) {
-				clear_item_dirty(sb, cinf, pg, item);
-
-				if (item->delta)
-					scoutfs_inc_counter(sb, item_delta_written);
-
-				/* free deletion items */
-				if (item->deletion || item->delta)
-					erase_item(pg, item);
-				else
-					item->persistent = 1;
-			}
-
-			write_unlock(&pg->rwlock);
-			spin_lock(&cinf->dirty_lock);
+			cpu_relax();
+			goto retry;
 		}
+
 		spin_unlock(&cinf->dirty_lock);
+
+		list_for_each_entry_safe(item, tmp, &pg->dirty_list,
+					 dirty_head) {
+			clear_item_dirty(sb, cinf, pg, item);
+
+			if (item->delta)
+				scoutfs_inc_counter(sb, item_delta_written);
+
+			/* free deletion items */
+			if (item->deletion || item->delta)
+				erase_item(pg, item);
+			else
+				item->persistent = 1;
+		}
+
+		write_unlock(&pg->rwlock);
+
 		spin_lock(&cinf->dirty_lock);
-	} while (pg);
+	}
+
 	spin_unlock(&cinf->dirty_lock);

 	return 0;
@@ -2544,15 +2597,24 @@ static unsigned long item_cache_scan_objects(struct shrinker *shrink,
 	struct cached_page *tmp;
 	struct cached_page *pg;
 	unsigned long freed = 0;
+	u64 first_reader_seq;
 	int nr = sc->nr_to_scan;

 	scoutfs_inc_counter(sb, item_cache_scan_objects);

+	/* can't invalidate pages with items that weren't visible to first reader */
+	first_reader_seq = first_active_reader_seq(cinf);
+
 	write_lock(&cinf->rwlock);
 	spin_lock(&cinf->lru_lock);

 	list_for_each_entry_safe(pg, tmp, &cinf->lru_list, lru_head) {

+		if (first_reader_seq <= pg->max_seq) {
+			scoutfs_inc_counter(sb, item_shrink_page_reader);
+			continue;
+		}
+
 		if (!write_trylock(&pg->rwlock)) {
 			scoutfs_inc_counter(sb, item_shrink_page_trylock);
 			continue;
@@ -2619,6 +2681,8 @@ int scoutfs_item_setup(struct super_block *sb)
 	atomic_set(&cinf->dirty_pages, 0);
 	spin_lock_init(&cinf->lru_lock);
 	INIT_LIST_HEAD(&cinf->lru_list);
+	spin_lock_init(&cinf->active_lock);
+	INIT_LIST_HEAD(&cinf->active_list);

 	cinf->pcpu_pages = alloc_percpu(struct item_percpu_pages);
 	if (!cinf->pcpu_pages)
@@ -2629,7 +2693,7 @@ 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));
+	KC_REGISTER_SHRINKER(&cinf->shrinker);
 #ifdef KC_CPU_NOTIFIER
        cinf->notifier.notifier_call = item_cpu_callback;
        register_hotcpu_notifier(&cinf->notifier);
@@ -2651,6 +2715,8 @@ void scoutfs_item_destroy(struct super_block *sb)
 	int cpu;

 	if (cinf) {
+		BUG_ON(!list_empty(&cinf->active_list));
+
 #ifdef KC_CPU_NOTIFIER
 		unregister_hotcpu_notifier(&cinf->notifier);
 #endif
--- a/kmod/src/kernelcompat.c
+++ b/kmod/src/kernelcompat.c
@@ -67,11 +67,12 @@ 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)
 {
+	struct file *file = iocb->ki_filp;
 	ssize_t status;
 	struct iov_iter i;

 	iov_iter_init(&i, WRITE, iov, nr_segs, count);
-	status = kc_generic_perform_write(iocb, &i, pos);
+	status = generic_perform_write(file, &i, pos);

 	if (likely(status >= 0)) {
 		written += status;
@@ -81,69 +82,3 @@ kc_generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
 	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)
-{
-	struct kc_isolate_args *args = cb_arg;
-
-	return args->isolate(item, list, 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
--- a/kmod/src/kernelcompat.h
+++ b/kmod/src/kernelcompat.h
@@ -29,6 +29,50 @@ do {						\
 })
 #endif

+#ifndef KC_ITERATE_DIR_CONTEXT
+typedef filldir_t kc_readdir_ctx_t;
+#define KC_DECLARE_READDIR(name, file, dirent, ctx) name(file, dirent, ctx)
+#define KC_FOP_READDIR readdir
+#define kc_readdir_pos(filp, ctx) (filp)->f_pos
+#define kc_dir_emit_dots(file, dirent, ctx) dir_emit_dots(file, dirent, ctx)
+#define kc_dir_emit(ctx, dirent, name, name_len, pos, ino, dt) \
+	(ctx(dirent, name, name_len, pos, ino, dt) == 0)
+#else
+typedef struct dir_context * kc_readdir_ctx_t;
+#define KC_DECLARE_READDIR(name, file, dirent, ctx) name(file, ctx)
+#define KC_FOP_READDIR iterate
+#define kc_readdir_pos(filp, ctx) (ctx)->pos
+#define kc_dir_emit_dots(file, dirent, ctx) dir_emit_dots(file, ctx)
+#define kc_dir_emit(ctx, dirent, name, name_len, pos, ino, dt) \
+	dir_emit(ctx, name, name_len, ino, dt)
+#endif
+
+#ifndef KC_DIR_EMIT_DOTS
+/*
+ * Kernels before ->iterate and don't have dir_emit_dots so we give them
+ * one that works with the ->readdir() filldir() method.
+ */
+static inline int dir_emit_dots(struct file *file, void *dirent,
+				filldir_t filldir)
+{
+	if (file->f_pos == 0) {
+		if (filldir(dirent, ".", 1, 1,
+			    file->f_path.dentry->d_inode->i_ino, DT_DIR))
+			return 0;
+		file->f_pos = 1;
+	}
+
+	if (file->f_pos == 1) {
+		if (filldir(dirent, "..", 2, 1,
+			    parent_ino(file->f_path.dentry), DT_DIR))
+			return 0;
+		file->f_pos = 2;
+	}
+
+	return 1;
+}
+#endif
+
 #ifdef KC_POSIX_ACL_VALID_USER_NS
 #define kc_posix_acl_valid(user_ns, acl) posix_acl_valid(user_ns, acl)
 #else
@@ -153,11 +197,7 @@ struct timespec64 kc_current_time(struct inode *inode);
 } while (0)

 #define KC_SHRINKER_CONTAINER_OF(ptr, type) container_of(ptr, type, shrinker)
-#ifdef KC_SHRINKER_NAME
-#define KC_REGISTER_SHRINKER register_shrinker
-#else
-#define KC_REGISTER_SHRINKER(ptr, fmt, ...) (register_shrinker(ptr))
-#endif /* KC_SHRINKER_NAME */
+#define KC_REGISTER_SHRINKER(ptr) (register_shrinker(ptr))
 #define KC_UNREGISTER_SHRINKER(ptr) (unregister_shrinker(ptr))
 #define KC_SHRINKER_FN(ptr) (ptr)
 #else
@@ -184,7 +224,7 @@ struct kc_shrinker_wrapper {
 	_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_REGISTER_SHRINKER(ptr) (register_shrinker(ptr.shrink))
 #define KC_UNREGISTER_SHRINKER(ptr) (unregister_shrinker(ptr.shrink))
 #define KC_SHRINKER_FN(ptr) (ptr.shrink)

@@ -231,262 +271,6 @@ ssize_t kc_generic_file_buffered_write(struct kiocb *iocb, const struct iovec *i
               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)
-{
-	iocb->ki_pos = pos;
-	return generic_perform_write(iocb, iter);
-}
-#else
-static inline int kc_generic_perform_write(struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
-{
-	struct file *file = iocb->ki_filp;
-	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; */
-typedef unsigned int blk_opf_t;
-#endif
-
-#ifdef KC_LIST_CMP_CONST_ARG_LIST_HEAD
-#define KC_LIST_CMP_CONST const
-#else
-#define KC_LIST_CMP_CONST
-#endif
-
-#ifdef KC_VMALLOC_PGPROT_T
-#define kc__vmalloc(size, gfp_mask) __vmalloc(size, gfp_mask, PAGE_KERNEL)
-#else
-#define kc__vmalloc __vmalloc
-#endif
-
-#ifdef KC_VFS_METHOD_MNT_IDMAP_ARG
-#define KC_VFS_NS_DEF struct mnt_idmap *mnt_idmap,
-#define KC_VFS_NS mnt_idmap,
-#define KC_VFS_INIT_NS &nop_mnt_idmap,
-#else
-#ifdef KC_VFS_METHOD_USER_NAMESPACE_ARG
-#define KC_VFS_NS_DEF struct user_namespace *mnt_user_ns,
-#define KC_VFS_NS mnt_user_ns,
-#define KC_VFS_INIT_NS &init_user_ns,
-#else
-#define KC_VFS_NS_DEF
-#define KC_VFS_NS
-#define KC_VFS_INIT_NS
-#endif
-#endif /* KC_VFS_METHOD_MNT_IDMAP_ARG */
-
-#ifdef KC_BIO_ALLOC_DEV_OPF_ARGS
-#define kc_bio_alloc bio_alloc
-#else
-#include <linux/bio.h>
-static inline struct bio *kc_bio_alloc(struct block_device *bdev, unsigned short nr_vecs,
-				       blk_opf_t opf, gfp_t gfp_mask)
-{
-	struct bio *b = bio_alloc(gfp_mask, nr_vecs);
-	if (b) {
-		kc_bio_set_opf(b, opf);
-		bio_set_dev(b, bdev);
-	}
-	return b;
-}
-#endif
-
-#ifndef KC_FIEMAP_PREP
-#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)
-{
-	sock_set_sndtimeo(sock->sk, secs);
-	return 0;
-}
-static inline int kc_tcp_sock_set_rcvtimeo(struct socket *sock, ktime_t to)
-{
-	struct __kernel_old_timeval tv;
-	sockptr_t kopt;
-
-	tv = ns_to_kernel_old_timeval(to);
-
-	kopt = KERNEL_SOCKPTR(&tv);
-
-	return sock_setsockopt(sock, SOL_SOCKET, SO_RCVTIMEO_NEW,
-			       kopt, sizeof(tv));
-}
-#else
-#include <net/sock.h>
-static inline int kc_sock_set_sndtimeo(struct socket *sock, s64 secs)
-{
-	struct timeval tv = { .tv_sec = secs, .tv_usec = 0 };
-	return kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO,
-				 (char *)&tv, sizeof(tv));
-}
-static inline int kc_tcp_sock_set_rcvtimeo(struct socket *sock, ktime_t to)
-{
-	struct __kernel_old_timeval tv;
-
-	tv = ns_to_kernel_old_timeval(to);
-	return kernel_setsockopt(sock, SOL_SOCKET, SO_RCVTIMEO,
-				 (char *)&tv, sizeof(tv));
-}
-#endif
-
-#ifdef KC_SETSOCKOPT_SOCKPTR_T
-static inline int kc_sock_setsockopt(struct socket *sock, int level, int op, int *optval, unsigned int optlen)
-{
-	sockptr_t kopt = KERNEL_SOCKPTR(optval);
-	return sock_setsockopt(sock, level, op, kopt, sizeof(optval));
-}
-#else
-static inline int kc_sock_setsockopt(struct socket *sock, int level, int op, int *optval, unsigned int optlen)
-{
-	return kernel_setsockopt(sock, level, op, (char *)optval, sizeof(optval));
-}
-#endif
-
-#ifdef KC_HAVE_TCP_SET_SOCKFN
-#include <linux/net.h>
-#include <net/tcp.h>
-static inline int kc_tcp_sock_set_keepintvl(struct socket *sock, int val)
-{
-	return tcp_sock_set_keepintvl(sock->sk, val);
-}
-static inline int kc_tcp_sock_set_keepidle(struct socket *sock, int val)
-{
-	return tcp_sock_set_keepidle(sock->sk, val);
-}
-static inline int kc_tcp_sock_set_user_timeout(struct socket *sock, int val)
-{
-	tcp_sock_set_user_timeout(sock->sk, val);
-	return 0;
-}
-static inline int kc_tcp_sock_set_nodelay(struct socket *sock)
-{
-	tcp_sock_set_nodelay(sock->sk);
-	return 0;
-}
-#else
-#include <linux/net.h>
-#include <net/tcp.h>
-static inline int kc_tcp_sock_set_keepintvl(struct socket *sock, int val)
-{
-	int optval = val;
-	return kernel_setsockopt(sock, SOL_TCP, TCP_KEEPINTVL, (char *)&optval, sizeof(optval));
-}
-static inline int kc_tcp_sock_set_keepidle(struct socket *sock, int val)
-{
-	int optval = val;
-	return kernel_setsockopt(sock, SOL_TCP, TCP_KEEPIDLE, (char *)&optval, sizeof(optval));
-}
-static inline int kc_tcp_sock_set_user_timeout(struct socket *sock, int val)
-{
-	int optval = val;
-	return kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT, (char *)&optval, sizeof(optval));
-}
-static inline int kc_tcp_sock_set_nodelay(struct socket *sock)
-{
-	int optval = 1;
-	return kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char *)&optval, sizeof(optval));
-}
-#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)
-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);
-struct kc_isolate_args {
-	kc_list_lru_walk_cb_t isolate;
-	void *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);
-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);
-#else
-#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);
-}
 #endif

 #endif
--- a/kmod/src/key.h
+++ b/kmod/src/key.h
@@ -125,8 +125,8 @@ static inline bool scoutfs_key_is_ones(struct scoutfs_key *key)
 * other alternatives across keys that first differ in any of the
 * values.  Say maybe 20% faster than memcmp.
 */
-static inline int scoutfs_key_compare(const struct scoutfs_key *a,
-				      const struct scoutfs_key *b)
+static inline int scoutfs_key_compare(struct scoutfs_key *a,
+				      struct scoutfs_key *b)
 {
 	return scoutfs_cmp(a->sk_zone, b->sk_zone) ?:
 	  scoutfs_cmp(le64_to_cpu(a->_sk_first), le64_to_cpu(b->_sk_first)) ?:
@@ -142,10 +142,10 @@ static inline int scoutfs_key_compare(const struct scoutfs_key *a,
 *       1: a_start > b_end
 *  else 0: ranges overlap
 */
-static inline int scoutfs_key_compare_ranges(const struct scoutfs_key *a_start,
-				             const struct scoutfs_key *a_end,
-				             const struct scoutfs_key *b_start,
-				             const struct scoutfs_key *b_end)
+static inline int scoutfs_key_compare_ranges(struct scoutfs_key *a_start,
+				             struct scoutfs_key *a_end,
+				             struct scoutfs_key *b_start,
+				             struct scoutfs_key *b_end)
 {
 	return scoutfs_key_compare(a_end, b_start) < 0 ? -1 :
 	       scoutfs_key_compare(a_start, b_end) > 0 ? 1 :
--- a/kmod/src/lock.c
+++ b/kmod/src/lock.c
@@ -53,10 +53,8 @@
 * all access to the lock (by revoking it down to a null mode) then the
 * lock is freed.
 *
- * Each client has a configurable number of locks that are allowed to
- * remain idle after being granted, for use by future tasks.  Past the
- * limit locks are freed by requesting a null mode from the server,
- * governed by a LRU.
+ * Memory pressure on the client can cause the client to request a null
+ * mode from the server so that once its granted the lock can be freed.
 *
 * So far we've only needed a minimal trylock.  We return -EAGAIN if a
 * lock attempt can't immediately match an existing granted lock.  This
@@ -81,11 +79,14 @@ struct lock_info {
 	bool unmounting;
 	struct rb_root lock_tree;
 	struct rb_root lock_range_tree;
-	u64 nr_locks;
+	KC_DEFINE_SHRINKER(shrinker);
 	struct list_head lru_list;
+	unsigned long long lru_nr;
 	struct workqueue_struct *workq;
 	struct work_struct inv_work;
 	struct list_head inv_list;
+	struct work_struct shrink_work;
+	struct list_head shrink_list;
 	atomic64_t next_refresh_gen;

 	struct dentry *tseq_dentry;
@@ -167,6 +168,7 @@ static int lock_invalidate(struct super_block *sb, struct scoutfs_lock *lock,
 			   enum scoutfs_lock_mode prev, enum scoutfs_lock_mode mode)
 {
 	struct scoutfs_lock_coverage *cov;
+	struct scoutfs_lock_coverage *tmp;
 	u64 ino, last;
 	int ret = 0;

@@ -190,22 +192,19 @@ static int lock_invalidate(struct super_block *sb, struct scoutfs_lock *lock,

 	/* have to invalidate if we're not in the only usable case */
 	if (!(prev == SCOUTFS_LOCK_WRITE && mode == SCOUTFS_LOCK_READ)) {
-		/*
-		 * Remove cov items to tell users that their cache is
-		 * stale.  The unlock pattern comes from avoiding bad
-		 * sparse warnings when taking else in a failed trylock.
-		 */
+retry:
+		/* remove cov items to tell users that their cache is stale */
 		spin_lock(&lock->cov_list_lock);
-		while ((cov = list_first_entry_or_null(&lock->cov_list,
-						       struct scoutfs_lock_coverage, head))) {
-			if (spin_trylock(&cov->cov_lock)) {
-				list_del_init(&cov->head);
-				cov->lock = NULL;
-				spin_unlock(&cov->cov_lock);
-				scoutfs_inc_counter(sb, lock_invalidate_coverage);
+		list_for_each_entry_safe(cov, tmp, &lock->cov_list, head) {
+			if (!spin_trylock(&cov->cov_lock)) {
+				spin_unlock(&lock->cov_list_lock);
+				cpu_relax();
+				goto retry;
 			}
-			spin_unlock(&lock->cov_list_lock);
-			spin_lock(&lock->cov_list_lock);
+			list_del_init(&cov->head);
+			cov->lock = NULL;
+			spin_unlock(&cov->cov_lock);
+			scoutfs_inc_counter(sb, lock_invalidate_coverage);
 		}
 		spin_unlock(&lock->cov_list_lock);

@@ -248,6 +247,7 @@ static void lock_free(struct lock_info *linfo, struct scoutfs_lock *lock)
 	BUG_ON(!RB_EMPTY_NODE(&lock->range_node));
 	BUG_ON(!list_empty(&lock->lru_head));
 	BUG_ON(!list_empty(&lock->inv_head));
+	BUG_ON(!list_empty(&lock->shrink_head));
 	BUG_ON(!list_empty(&lock->cov_list));

 	kfree(lock->inode_deletion_data);
@@ -275,6 +275,7 @@ static struct scoutfs_lock *lock_alloc(struct super_block *sb,
 	INIT_LIST_HEAD(&lock->lru_head);
 	INIT_LIST_HEAD(&lock->inv_head);
 	INIT_LIST_HEAD(&lock->inv_list);
+	INIT_LIST_HEAD(&lock->shrink_head);
 	spin_lock_init(&lock->cov_list_lock);
 	INIT_LIST_HEAD(&lock->cov_list);

@@ -301,7 +302,6 @@ static void lock_inc_count(unsigned int *counts, enum scoutfs_lock_mode mode)
 static void lock_dec_count(unsigned int *counts, enum scoutfs_lock_mode mode)
 {
 	BUG_ON(mode < 0 || mode >= SCOUTFS_LOCK_NR_MODES);
-	BUG_ON(counts[mode] == 0);
 	counts[mode]--;
 }

@@ -407,7 +407,6 @@ static bool lock_insert(struct super_block *sb, struct scoutfs_lock *ins)
 	rb_link_node(&ins->node, parent, node);
 	rb_insert_color(&ins->node, &linfo->lock_tree);

-	linfo->nr_locks++;
 	scoutfs_tseq_add(&linfo->tseq_tree, &ins->tseq_entry);

 	return true;
@@ -422,7 +421,6 @@ static void lock_remove(struct lock_info *linfo, struct scoutfs_lock *lock)
 	rb_erase(&lock->range_node, &linfo->lock_range_tree);
 	RB_CLEAR_NODE(&lock->range_node);

-	linfo->nr_locks--;
 	scoutfs_tseq_del(&linfo->tseq_tree, &lock->tseq_entry);
 }

@@ -462,8 +460,10 @@ static void __lock_del_lru(struct lock_info *linfo, struct scoutfs_lock *lock)
 {
 	assert_spin_locked(&linfo->lock);

-	if (!list_empty(&lock->lru_head))
+	if (!list_empty(&lock->lru_head)) {
 		list_del_init(&lock->lru_head);
+		linfo->lru_nr--;
+	}
 }

 /*
@@ -522,16 +522,14 @@ static struct scoutfs_lock *create_lock(struct super_block *sb,
 * indicate that the lock wasn't idle.  If it really is idle then we
 * either free it if it's null or put it back on the lru.
 */
-static void __put_lock(struct lock_info *linfo, struct scoutfs_lock *lock, bool tail)
+static void put_lock(struct lock_info *linfo,struct scoutfs_lock *lock)
 {
 	assert_spin_locked(&linfo->lock);

 	if (lock_idle(lock)) {
 		if (lock->mode != SCOUTFS_LOCK_NULL) {
-			if (tail)
-				list_add_tail(&lock->lru_head, &linfo->lru_list);
-			else
-				list_add(&lock->lru_head, &linfo->lru_list);
+			list_add_tail(&lock->lru_head, &linfo->lru_list);
+			linfo->lru_nr++;
 		} else {
 			lock_remove(linfo, lock);
 			lock_free(linfo, lock);
@@ -539,11 +537,6 @@ static void __put_lock(struct lock_info *linfo, struct scoutfs_lock *lock, bool
 	}
 }

-static inline void put_lock(struct lock_info *linfo, struct scoutfs_lock *lock)
-{
-	__put_lock(linfo, lock, true);
-}
-
 /*
 * The caller has made a change (set a lock mode) which can let one of the
 * invalidating locks make forward progress.
@@ -717,14 +710,14 @@ static void lock_invalidate_worker(struct work_struct *work)
 		/* only lock protocol, inv can't call subsystems after shutdown */
 		if (!linfo->shutdown) {
 			ret = lock_invalidate(sb, lock, nl->old_mode, nl->new_mode);
-			BUG_ON(ret < 0 && ret != -ENOLINK);
+			BUG_ON(ret);
 		}

 		/* respond with the key and modes from the request, server might have died */
 		ret = scoutfs_client_lock_response(sb, ireq->net_id, nl);
 		if (ret == -ENOTCONN)
 			ret = 0;
-		BUG_ON(ret < 0 && ret != -ENOLINK);
+		BUG_ON(ret);

 		scoutfs_inc_counter(sb, lock_invalidate_response);
 	}
@@ -879,69 +872,6 @@ int scoutfs_lock_recover_request(struct super_block *sb, u64 net_id,
 	return ret;
 }

-/*
- * This is called on every _lock call to try and keep the number of
- * locks under the idle count.  We're intentionally trying to throttle
- * shrinking bursts by tying its frequency to lock use.  It will only
- * send requests to free unused locks, though, so it's always possible
- * to exceed the high water mark under heavy load.
- *
- * We send a null request and the lock will be freed by the response
- * once all users drain.  If this races with invalidation then the
- * server will only send the grant response once the invalidation is
- * finished.
- */
-static bool try_shrink_lock(struct super_block *sb, struct lock_info *linfo, bool force)
-{
-	struct scoutfs_mount_options opts;
-	struct scoutfs_lock *lock = NULL;
-	struct scoutfs_net_lock nl;
-	int ret = 0;
-
-	scoutfs_options_read(sb, &opts);
-
-	/* avoiding lock contention with unsynchronized test, don't mind temp false results */
-	if (!force && (list_empty(&linfo->lru_list) ||
-	               READ_ONCE(linfo->nr_locks) <= opts.lock_idle_count))
-		return false;
-
-	spin_lock(&linfo->lock);
-
-	lock = list_first_entry_or_null(&linfo->lru_list, struct scoutfs_lock, lru_head);
-	if (lock && (force || (linfo->nr_locks > opts.lock_idle_count))) {
-		__lock_del_lru(linfo, lock);
-		lock->request_pending = 1;
-
-		nl.key = lock->start;
-		nl.old_mode = lock->mode;
-		nl.new_mode = SCOUTFS_LOCK_NULL;
-	} else {
-		lock = NULL;
-	}
-
-	spin_unlock(&linfo->lock);
-
-	if (lock) {
-		ret = scoutfs_client_lock_request(sb, &nl);
-		if (ret < 0) {
-			scoutfs_inc_counter(sb, lock_shrink_request_failed);
-
-			spin_lock(&linfo->lock);
-
-			lock->request_pending = 0;
-			wake_up(&lock->waitq);
-			__put_lock(linfo, lock, false);
-
-			spin_unlock(&linfo->lock);
-		} else {
-			scoutfs_inc_counter(sb, lock_shrink_attempted);
-			trace_scoutfs_lock_shrink(sb, lock);
-		}
-	}
-
-	return lock && ret == 0;
-}
-
 static bool lock_wait_cond(struct super_block *sb, struct scoutfs_lock *lock,
 			   enum scoutfs_lock_mode mode)
 {
@@ -1004,8 +934,6 @@ static int lock_key_range(struct super_block *sb, enum scoutfs_lock_mode mode, i
 	if (WARN_ON_ONCE(scoutfs_trans_held()))
 		return -EDEADLK;

-	try_shrink_lock(sb, linfo, false);
-
 	spin_lock(&linfo->lock);

 	/* drops and re-acquires lock if it allocates */
@@ -1449,12 +1377,134 @@ bool scoutfs_lock_protected(struct scoutfs_lock *lock, struct scoutfs_key *key,
 					  &lock->start, &lock->end) == 0;
 }

+/*
+ * The shrink callback got the lock, marked it request_pending, and put
+ * it on the shrink list.  We send a null request and the lock will be
+ * freed by the response once all users drain.  If this races with
+ * invalidation then the server will only send the grant response once
+ * the invalidation is finished.
+ */
+static void lock_shrink_worker(struct work_struct *work)
+{
+	struct lock_info *linfo = container_of(work, struct lock_info,
+					       shrink_work);
+	struct super_block *sb = linfo->sb;
+	struct scoutfs_net_lock nl;
+	struct scoutfs_lock *lock;
+	struct scoutfs_lock *tmp;
+	LIST_HEAD(list);
+	int ret;
+
+	scoutfs_inc_counter(sb, lock_shrink_work);
+
+	spin_lock(&linfo->lock);
+	list_splice_init(&linfo->shrink_list, &list);
+	spin_unlock(&linfo->lock);
+
+	list_for_each_entry_safe(lock, tmp, &list, shrink_head) {
+		list_del_init(&lock->shrink_head);
+
+		/* unlocked lock access, but should be stable since we queued */
+		nl.key = lock->start;
+		nl.old_mode = lock->mode;
+		nl.new_mode = SCOUTFS_LOCK_NULL;
+
+		ret = scoutfs_client_lock_request(sb, &nl);
+		if (ret) {
+			/* oh well, not freeing */
+			scoutfs_inc_counter(sb, lock_shrink_aborted);
+
+			spin_lock(&linfo->lock);
+
+			lock->request_pending = 0;
+			wake_up(&lock->waitq);
+			put_lock(linfo, lock);
+
+			spin_unlock(&linfo->lock);
+		}
+	}
+}
+
+static unsigned long lock_count_objects(struct shrinker *shrink,
+					struct shrink_control *sc)
+{
+	struct lock_info *linfo = KC_SHRINKER_CONTAINER_OF(shrink, struct lock_info);
+	struct super_block *sb = linfo->sb;
+
+	scoutfs_inc_counter(sb, lock_count_objects);
+
+	return shrinker_min_long(linfo->lru_nr);
+}
+
+/*
+ * Start the shrinking process for locks on the lru.  If a lock is on
+ * the lru then it can't have any active users.  We don't want to block
+ * or allocate here so all we do is get the lock, mark it request
+ * pending, and kick off the work.  The work sends a null request and
+ * eventually the lock is freed by its response.
+ *
+ * Only a racing lock attempt that isn't matched can prevent the lock
+ * from being freed.  It'll block waiting to send its request for its
+ * mode which will prevent the lock from being freed when the null
+ * response arrives.
+ */
+static unsigned long lock_scan_objects(struct shrinker *shrink,
+				       struct shrink_control *sc)
+{
+	struct lock_info *linfo = KC_SHRINKER_CONTAINER_OF(shrink, struct lock_info);
+	struct super_block *sb = linfo->sb;
+	struct scoutfs_lock *lock;
+	struct scoutfs_lock *tmp;
+	unsigned long freed = 0;
+	unsigned long nr = sc->nr_to_scan;
+	bool added = false;
+
+	scoutfs_inc_counter(sb, lock_scan_objects);
+
+	spin_lock(&linfo->lock);
+
+restart:
+	list_for_each_entry_safe(lock, tmp, &linfo->lru_list, lru_head) {
+
+		BUG_ON(!lock_idle(lock));
+		BUG_ON(lock->mode == SCOUTFS_LOCK_NULL);
+		BUG_ON(!list_empty(&lock->shrink_head));
+
+		if (nr-- == 0)
+			break;
+
+		__lock_del_lru(linfo, lock);
+		lock->request_pending = 1;
+		list_add_tail(&lock->shrink_head, &linfo->shrink_list);
+		added = true;
+		freed++;
+
+		scoutfs_inc_counter(sb, lock_shrink_attempted);
+		trace_scoutfs_lock_shrink(sb, lock);
+
+		/* could have bazillions of idle locks */
+		if (cond_resched_lock(&linfo->lock))
+			goto restart;
+	}
+
+	spin_unlock(&linfo->lock);
+
+	if (added)
+		queue_work(linfo->workq, &linfo->shrink_work);
+
+	trace_scoutfs_lock_shrink_exit(sb, sc->nr_to_scan, freed);
+	return freed;
+}
+
 void scoutfs_free_unused_locks(struct super_block *sb)
 {
-	DECLARE_LOCK_INFO(sb, linfo);
+	struct lock_info *linfo = SCOUTFS_SB(sb)->lock_info;
+	struct shrink_control sc = {
+		.gfp_mask = GFP_NOFS,
+		.nr_to_scan = INT_MAX,
+	};

-	while (try_shrink_lock(sb, linfo, true))
-		cond_resched();
+	lock_scan_objects(KC_SHRINKER_FN(&linfo->shrinker), &sc);
 }

 static void lock_tseq_show(struct seq_file *m, struct scoutfs_tseq_entry *ent)
@@ -1537,10 +1587,10 @@ u64 scoutfs_lock_ino_refresh_gen(struct super_block *sb, u64 ino)
 * transitions and sending requests.   We set the shutdown flag to catch
 * anyone who breaks this rule.
 *
- * With no more lock callers, we'll no longer try to shrink the pool of
- * granted locks.  We'll free all of them as _destroy() is called after
- * the farewell response indicates that the server tore down all our
- * lock state.
+ * We unregister the shrinker so that we won't try and send null
+ * requests in response to memory pressure.  The locks will all be
+ * unceremoniously dropped once we get a farewell response from the
+ * server which indicates that they destroyed our locking state.
 *
 * We will still respond to invalidation requests that have to be
 * processed to let unmount in other mounts acquire locks and make
@@ -1560,6 +1610,10 @@ void scoutfs_lock_shutdown(struct super_block *sb)

 	trace_scoutfs_lock_shutdown(sb, linfo);

+	/* stop the shrinker from queueing work */
+	KC_UNREGISTER_SHRINKER(&linfo->shrinker);
+	flush_work(&linfo->shrink_work);
+
 	/* cause current and future lock calls to return errors */
 	spin_lock(&linfo->lock);
 	linfo->shutdown = true;
@@ -1650,6 +1704,8 @@ void scoutfs_lock_destroy(struct super_block *sb)
 			list_del_init(&lock->inv_head);
 			lock->invalidate_pending = 0;
 		}
+		if (!list_empty(&lock->shrink_head))
+			list_del_init(&lock->shrink_head);
 		lock_remove(linfo, lock);
 		lock_free(linfo, lock);
 	}
@@ -1674,9 +1730,14 @@ int scoutfs_lock_setup(struct super_block *sb)
 	spin_lock_init(&linfo->lock);
 	linfo->lock_tree = RB_ROOT;
 	linfo->lock_range_tree = RB_ROOT;
+	KC_INIT_SHRINKER_FUNCS(&linfo->shrinker, lock_count_objects,
+			       lock_scan_objects);
+	KC_REGISTER_SHRINKER(&linfo->shrinker);
 	INIT_LIST_HEAD(&linfo->lru_list);
 	INIT_WORK(&linfo->inv_work, lock_invalidate_worker);
 	INIT_LIST_HEAD(&linfo->inv_list);
+	INIT_WORK(&linfo->shrink_work, lock_shrink_worker);
+	INIT_LIST_HEAD(&linfo->shrink_list);
 	atomic64_set(&linfo->next_refresh_gen, 0);
 	scoutfs_tseq_tree_init(&linfo->tseq_tree, lock_tseq_show);

--- a/kmod/src/lock_server.c
+++ b/kmod/src/lock_server.c
@@ -202,48 +202,21 @@ static u8 invalidation_mode(u8 granted, u8 requested)

 /*
 * Return true of the client lock instances described by the entries can
- * be granted at the same time.  There's only three cases where this is
- * true.
- *
- * First, the two locks are both of the same mode that allows full
- * sharing -- read and write only.  The only point of these modes is
- * that everyone can share them.
- *
- * Second, a write lock gives the client permission to read as well.
- * This means that a client can upgrade its read lock to a write lock
- * without having to invalidate the existing read and drop caches.
- *
- * Third, null locks are always compatible between clients.  It's as
- * though the client with the null lock has no lock at all.  But it's
- * never compatible with all locks on the client requesting null.
- * Sending invalidations for existing locks on a client when we get a
- * null request is how we resolve races in shrinking locks -- we turn it
- * into the unsolicited remote invalidation case.
- *
- * All other mode and client combinations can not be shared, most
- * typically a write lock invalidating all other non-write holders to
- * drop caches and force a read after the write has completed.
+ * be granted at the same time.  Typically this only means they're both
+ * modes that are compatible between nodes. In addition there's the
+ * special case where a read lock on a client is compatible with a write
+ * lock on the same client because the client's cache covered by the
+ * read lock is still valid if they get a write lock.
 */
 static bool client_entries_compatible(struct client_lock_entry *granted,
 				      struct client_lock_entry *requested)
 {
-	/* only read and write_only can be full shared */
-	if ((granted->mode == requested->mode) &&
-	    (granted->mode == SCOUTFS_LOCK_READ || granted->mode == SCOUTFS_LOCK_WRITE_ONLY))
-		return true;
-
-	/* _write includes reading, so a client can upgrade its read to write */
-	if (granted->rid == requested->rid &&
-	    granted->mode == SCOUTFS_LOCK_READ &&
-	    requested->mode == SCOUTFS_LOCK_WRITE)
-		return true;
-
-	/* null is always compatible across clients, never within a client */
-	if ((granted->rid != requested->rid) &&
-	    (granted->mode == SCOUTFS_LOCK_NULL || requested->mode == SCOUTFS_LOCK_NULL))
-		return true;
-
-	return false;
+	return (granted->mode == requested->mode &&
+		(granted->mode == SCOUTFS_LOCK_READ ||
+		 granted->mode == SCOUTFS_LOCK_WRITE_ONLY)) ||
+	       (granted->rid == requested->rid &&
+		granted->mode == SCOUTFS_LOCK_READ &&
+		requested->mode == SCOUTFS_LOCK_WRITE);
 }

 /*
@@ -344,18 +317,16 @@ static void put_server_lock(struct lock_server_info *inf,

 	BUG_ON(!mutex_is_locked(&snode->mutex));

-	spin_lock(&inf->lock);
-
 	if (atomic_dec_and_test(&snode->refcount) &&
 	    list_empty(&snode->granted) &&
 	    list_empty(&snode->requested) &&
 	    list_empty(&snode->invalidated)) {
+		spin_lock(&inf->lock);
 		rb_erase(&snode->node, &inf->locks_root);
+		spin_unlock(&inf->lock);
 		should_free = true;
 	}

-	spin_unlock(&inf->lock);
-
 	mutex_unlock(&snode->mutex);

 	if (should_free) {
@@ -506,19 +477,6 @@ out:
 * because we don't know which locks they'll hold.  Once recover
 * finishes the server calls us to kick all the locks that were waiting
 * during recovery.
- *
- * The calling server shuts down if we return errors indicating that we
- * weren't able to ensure forward progress in the lock state machine.
- *
- * Failure to send to a disconnected client is not a fatal error.
- * During normal disconnection the client's state is removed before
- * their connection is destroyed.  We can't use state to try and send to
- * a non-existing connection.  But a client that fails to reconnect is
- * disconnected before being fenced.  If we have multiple disconnected
- * clients we can try to send to one while cleaning up another.  If
- * they've uncleanly disconnected their locks are going to be removed
- * and the lock can make forward progress again.  Or we'll shutdown for
- * failure to fence.
 */
 static int process_waiting_requests(struct super_block *sb,
 				    struct server_lock_node *snode)
@@ -610,10 +568,6 @@ static int process_waiting_requests(struct super_block *sb,
 out:
 	put_server_lock(inf, snode);

-	/* disconnected clients will be fenced, trying to send to them isn't fatal */
-	if (ret == -ENOTCONN)
-		ret = 0;
-
 	return ret;
 }

--- a/kmod/src/msg.h
+++ b/kmod/src/msg.h
@@ -35,12 +35,6 @@ do {									\
 	}								\
 } while (0)								\

-#define scoutfs_bug_on_err(sb, err, fmt, args...) \
-do { \
-	__typeof__(err) _err = (err); \
-	scoutfs_bug_on(sb, _err < 0 && _err != -ENOLINK, fmt, ##args); \
-} while (0)
-
 /*
 * Each message is only generated once per volume.  Remounting resets
 * the messages.
--- a/kmod/src/net.c
+++ b/kmod/src/net.c
@@ -20,8 +20,6 @@
 #include <net/sock.h>
 #include <net/tcp.h>
 #include <linux/log2.h>
-#include <linux/jhash.h>
-#include <linux/rbtree.h>

 #include "format.h"
 #include "counters.h"
@@ -33,7 +31,6 @@
 #include "endian_swap.h"
 #include "tseq.h"
 #include "fence.h"
-#include "options.h"

 /*
 * scoutfs networking delivers requests and responses between nodes.
@@ -126,7 +123,6 @@ struct message_send {
 	unsigned long dead:1;
 	struct list_head head;
 	scoutfs_net_response_t resp_func;
-	struct rb_node node;
 	void *resp_data;
 	struct scoutfs_net_header nh;
 };
@@ -138,7 +134,6 @@ struct message_send {
 struct message_recv {
 	struct scoutfs_tseq_entry tseq_entry;
 	struct work_struct proc_work;
-	struct list_head ordered_head;
 	struct scoutfs_net_connection *conn;
 	struct scoutfs_net_header nh;
 };
@@ -163,118 +158,49 @@ static bool nh_is_request(struct scoutfs_net_header *nh)
 	return !nh_is_response(nh);
 }

-static int cmp_sorted_msend(u64 pos, struct message_send *msend)
-{
-	if (nh_is_request(&msend->nh))
-		return pos < le64_to_cpu(msend->nh.id) ? -1 :
-		       pos > le64_to_cpu(msend->nh.id) ? 1 : 0;
-	else
-		return pos < le64_to_cpu(msend->nh.seq) ? -1 :
-		       pos > le64_to_cpu(msend->nh.seq) ? 1 : 0;
-}
-
-static struct message_send *search_sorted_msends(struct rb_root *root, u64 pos, struct rb_node *ins)
-{
-	struct rb_node **node = &root->rb_node;
-	struct rb_node *parent = NULL;
-	struct message_send *msend = NULL;
-	struct message_send *next = NULL;
-	int cmp = -1;
-
-	while (*node) {
-		parent = *node;
-		msend = container_of(*node, struct message_send, node);
-
-		cmp = cmp_sorted_msend(pos, msend);
-		if (cmp < 0) {
-			next = msend;
-			node = &(*node)->rb_left;
-		} else if (cmp > 0) {
-			node = &(*node)->rb_right;
-		} else {
-			next = msend;
-			break;
-		}
-	}
-
-	BUG_ON(cmp == 0 && ins);
-
-	if (ins) {
-		rb_link_node(ins, parent, node);
-		rb_insert_color(ins, root);
-	}
-
-	return next;
-}
-
-static struct message_send *next_sorted_msend(struct message_send *msend)
-{
-	struct rb_node *node = rb_next(&msend->node);
-
-	return node ? rb_entry(node, struct message_send, node) : NULL;
-}
-
-#define for_each_sorted_msend(MSEND_, TMP_, ROOT_, POS_) \
-	for (MSEND_ = search_sorted_msends(ROOT_, POS_, NULL); \
-	     MSEND_ != NULL && ({ TMP_ = next_sorted_msend(MSEND_); true; }); \
-	     MSEND_ = TMP_)
-
-static void insert_sorted_msend(struct scoutfs_net_connection *conn, struct message_send *msend)
-{
-	BUG_ON(!RB_EMPTY_NODE(&msend->node));
-
-	if (nh_is_request(&msend->nh))
-		search_sorted_msends(&conn->req_root, le64_to_cpu(msend->nh.id), &msend->node);
-	else
-		search_sorted_msends(&conn->resp_root, le64_to_cpu(msend->nh.seq), &msend->node);
-}
-
-static void erase_sorted_msend(struct scoutfs_net_connection *conn, struct message_send *msend)
-{
-	if (!RB_EMPTY_NODE(&msend->node)) {
-		if (nh_is_request(&msend->nh))
-			rb_erase(&msend->node, &conn->req_root);
-		else
-			rb_erase(&msend->node, &conn->resp_root);
-		RB_CLEAR_NODE(&msend->node);
-	}
-}
-
-static void move_sorted_msends(struct scoutfs_net_connection *dst_conn, struct rb_root *dst_root,
-			       struct scoutfs_net_connection *src_conn, struct rb_root *src_root)
-{
-	struct message_send *msend;
-	struct message_send *tmp;
-
-	for_each_sorted_msend(msend, tmp, src_root, 0) {
-		erase_sorted_msend(src_conn, msend);
-		insert_sorted_msend(dst_conn, msend);
-	}
-}
-
 /*
- * Pending requests are uniquely identified by the id they were assigned
- * as they were first put on the send queue.
+ * We return dead requests so that the caller can stop searching other
+ * lists for the dead request that we found.
 */
-static struct message_send *find_request(struct scoutfs_net_connection *conn, u8 cmd, u64 id)
+static struct message_send *search_list(struct scoutfs_net_connection *conn,
+					struct list_head *list,
+					u8 cmd, u64 id)
 {
 	struct message_send *msend;

 	assert_spin_locked(&conn->lock);

-	msend = search_sorted_msends(&conn->req_root, id, NULL);
-	if (msend && !(msend->nh.cmd == cmd && le64_to_cpu(msend->nh.id) == id))
-		msend = NULL;
+	list_for_each_entry(msend, list, head) {
+		if (nh_is_request(&msend->nh) && msend->nh.cmd == cmd &&
+		    le64_to_cpu(msend->nh.id) == id)
+			return msend;
+	}

+	return NULL;
+}
+
+/*
+ * Find an active send request on the lists.  It's almost certainly
+ * waiting on the resend queue but it could be actively being sent.
+ */
+static struct message_send *find_request(struct scoutfs_net_connection *conn,
+					 u8 cmd, u64 id)
+{
+	struct message_send *msend;
+
+	msend = search_list(conn, &conn->resend_queue, cmd, id) ?:
+		search_list(conn, &conn->send_queue, cmd, id);
+	if (msend && msend->dead)
+		msend = NULL;
 	return msend;
 }

 /*
- * Free a send message by moving it to the send queue and marking it
- * dead.  It is removed from the sorted rb roots so it won't be visible
- * as a request for response processing.
+ * Complete a send message by moving it to the send queue and marking it
+ * to be freed.  It won't be visible to callers trying to find sends.
 */
-static void queue_dead_free(struct scoutfs_net_connection *conn, struct message_send *msend)
+static void complete_send(struct scoutfs_net_connection *conn,
+			  struct message_send *msend)
 {
 	assert_spin_locked(&conn->lock);

@@ -284,7 +210,6 @@ static void queue_dead_free(struct scoutfs_net_connection *conn, struct message_

 	msend->dead = 1;
 	list_move(&msend->head, &conn->send_queue);
-	erase_sorted_msend(conn, msend);
 	queue_work(conn->workq, &conn->send_work);
 }

@@ -407,7 +332,7 @@ static int submit_send(struct super_block *sb,
 		return -EINVAL;

 	if (scoutfs_forcing_unmount(sb))
-		return -ENOLINK;
+		return -EIO;

 	msend = kmalloc(offsetof(struct message_send,
 				 nh.data[data_len]), GFP_NOFS);
@@ -442,7 +367,6 @@ static int submit_send(struct super_block *sb,
 	msend->resp_func = resp_func;
 	msend->resp_data = resp_data;
 	msend->dead = 0;
-	RB_CLEAR_NODE(&msend->node);

 	msend->nh.seq = cpu_to_le64(seq);
 	msend->nh.recv_seq = 0;  /* set when sent, not when queued */
@@ -463,7 +387,6 @@ static int submit_send(struct super_block *sb,
 	} else {
 		list_add_tail(&msend->head, &conn->resend_queue);
 	}
-	insert_sorted_msend(conn, msend);

 	if (id_ret)
 		*id_ret = le64_to_cpu(msend->nh.id);
@@ -533,7 +456,7 @@ static int process_response(struct scoutfs_net_connection *conn,
 	if (msend) {
 		resp_func = msend->resp_func;
 		resp_data = msend->resp_data;
-		queue_dead_free(conn, msend);
+		complete_send(conn, msend);
 	} else {
 		scoutfs_inc_counter(sb, net_dropped_response);
 	}
@@ -575,83 +498,76 @@ static void scoutfs_net_proc_worker(struct work_struct *work)
 	trace_scoutfs_net_proc_work_exit(sb, 0, ret);
 }

-static void scoutfs_net_ordered_proc_worker(struct work_struct *work)
-{
-	struct scoutfs_work_list *wlist = container_of(work, struct scoutfs_work_list, work);
-	struct message_recv *mrecv;
-	struct message_recv *mrecv__;
-	LIST_HEAD(list);
-
-	spin_lock(&wlist->lock);
-	list_splice_init(&wlist->list, &list);
-	spin_unlock(&wlist->lock);
-
-	list_for_each_entry_safe(mrecv, mrecv__, &list, ordered_head) {
-		list_del_init(&mrecv->ordered_head);
-		scoutfs_net_proc_worker(&mrecv->proc_work);
-	}
-}
-
-/*
- * Some messages require in-order processing.  But the scope of the
- * ordering isn't global.  In the case of lock messages, it's per lock.
- * So for these messages we hash them to a number of ordered workers who
- * walk a list and call the usual work function in order.  This replaced
- * first the proc work detecting OOO and re-ordering, and then only
- * calling proc from the one recv work context.
- */
-static void queue_ordered_proc(struct scoutfs_net_connection *conn, struct message_recv *mrecv)
-{
-	struct scoutfs_work_list *wlist;
-	struct scoutfs_net_lock *nl;
-	u32 h;
-
-	if (WARN_ON_ONCE(mrecv->nh.cmd != SCOUTFS_NET_CMD_LOCK ||
-		         le16_to_cpu(mrecv->nh.data_len) != sizeof(struct scoutfs_net_lock)))
-		return scoutfs_net_proc_worker(&mrecv->proc_work);
-
-	nl = (void *)mrecv->nh.data;
-	h = jhash(&nl->key, sizeof(struct scoutfs_key), 0x6fdd3cd5);
-	wlist = &conn->ordered_proc_wlists[h % conn->ordered_proc_nr];
-
-	spin_lock(&wlist->lock);
-	list_add_tail(&mrecv->ordered_head, &wlist->list);
-	spin_unlock(&wlist->lock);
-	queue_work(conn->workq, &wlist->work);
-}
-
 /*
 * Free live responses up to and including the seq by marking them dead
 * and moving them to the send queue to be freed.
 */
-static void free_acked_responses(struct scoutfs_net_connection *conn, u64 seq)
+static int move_acked_responses(struct scoutfs_net_connection *conn,
+				struct list_head *list, u64 seq)
 {
 	struct message_send *msend;
 	struct message_send *tmp;
+	int ret = 0;
+
+	assert_spin_locked(&conn->lock);
+
+	list_for_each_entry_safe(msend, tmp, list, head) {
+		if (le64_to_cpu(msend->nh.seq) > seq)
+			break;
+		if (!nh_is_response(&msend->nh) || msend->dead)
+			continue;
+
+		msend->dead = 1;
+		list_move(&msend->head, &conn->send_queue);
+		ret = 1;
+	}
+
+	return ret;
+}
+
+/* acks are processed inline in the recv worker */
+static void free_acked_responses(struct scoutfs_net_connection *conn, u64 seq)
+{
+	int moved;

 	spin_lock(&conn->lock);

-	for_each_sorted_msend(msend, tmp, &conn->resp_root, 0) {
-		if (le64_to_cpu(msend->nh.seq) > seq)
-			break;
-
-		queue_dead_free(conn, msend);
-	}
+	moved = move_acked_responses(conn, &conn->send_queue, seq) +
+		move_acked_responses(conn, &conn->resend_queue, seq);

 	spin_unlock(&conn->lock);
+
+	if (moved)
+		queue_work(conn->workq, &conn->send_work);
 }

-static int k_recvmsg(struct socket *sock, void *buf, unsigned len)
+static int recvmsg_full(struct socket *sock, void *buf, unsigned len)
 {
-	struct kvec kv = {
-		.iov_base = buf,
-		.iov_len = len,
-	};
-	struct msghdr msg = {
-		.msg_flags = MSG_NOSIGNAL,
-	};
+	struct msghdr msg;
+	struct kvec kv;
+	int ret;

-	return kernel_recvmsg(sock, &msg, &kv, 1, len, msg.msg_flags);
+	while (len) {
+		memset(&msg, 0, sizeof(msg));
+		msg.msg_flags = MSG_NOSIGNAL;
+		kv.iov_base = buf;
+		kv.iov_len = len;
+
+#ifndef KC_MSGHDR_STRUCT_IOV_ITER
+		msg.msg_iov = (struct iovec *)&kv;
+		msg.msg_iovlen = 1;
+#else
+		iov_iter_init(&msg.msg_iter, READ, (struct iovec *)&kv, len, 1);
+#endif
+		ret = kernel_recvmsg(sock, &msg, &kv, 1, len, msg.msg_flags);
+		if (ret <= 0)
+			return -ECONNABORTED;
+
+		len -= ret;
+		buf += ret;
+	}
+
+	return 0;
 }

 static bool invalid_message(struct scoutfs_net_connection *conn,
@@ -688,72 +604,6 @@ static bool invalid_message(struct scoutfs_net_connection *conn,
 	return false;
 }

-static int recv_one_message(struct super_block *sb, struct net_info *ninf,
-			    struct scoutfs_net_connection *conn, struct scoutfs_net_header *nh,
-			    unsigned int data_len)
-{
-	struct message_recv *mrecv;
-	int ret;
-
-	scoutfs_inc_counter(sb, net_recv_messages);
-	scoutfs_add_counter(sb, net_recv_bytes, nh_bytes(data_len));
-	trace_scoutfs_net_recv_message(sb, &conn->sockname, &conn->peername, nh);
-
-	/* caller's invalid message checked data len */
-	mrecv = kmalloc(offsetof(struct message_recv, nh.data[data_len]), GFP_NOFS);
-	if (!mrecv) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	mrecv->conn = conn;
-	INIT_WORK(&mrecv->proc_work, scoutfs_net_proc_worker);
-	INIT_LIST_HEAD(&mrecv->ordered_head);
-	mrecv->nh = *nh;
-	if (data_len)
-		memcpy(mrecv->nh.data, (nh + 1), data_len);
-
-	if (nh->cmd == SCOUTFS_NET_CMD_GREETING) {
-		/* greetings are out of band, no seq mechanics */
-		set_conn_fl(conn, saw_greeting);
-
-	} else if (le64_to_cpu(nh->seq) <=
-		   atomic64_read(&conn->recv_seq)) {
-		/* drop any resent duplicated messages */
-		scoutfs_inc_counter(sb, net_recv_dropped_duplicate);
-		kfree(mrecv);
-		ret = 0;
-		goto out;
-
-	} else {
-		/* record that we've received sender's seq */
-		atomic64_set(&conn->recv_seq, le64_to_cpu(nh->seq));
-		/* and free our responses that sender has received */
-		free_acked_responses(conn, le64_to_cpu(nh->recv_seq));
-	}
-
-	scoutfs_tseq_add(&ninf->msg_tseq_tree, &mrecv->tseq_entry);
-
-	/*
-	 * Initial received greetings are processed inline
-	 * before any other incoming messages.
-	 *
-	 * Incoming requests or responses to the lock client
-	 * can't handle re-ordering, so they're queued to
-	 * ordered receive processing work.
-	 */
-	if (nh->cmd == SCOUTFS_NET_CMD_GREETING)
-		scoutfs_net_proc_worker(&mrecv->proc_work);
-	else if (nh->cmd == SCOUTFS_NET_CMD_LOCK && !conn->listening_conn)
-		queue_ordered_proc(conn, mrecv);
-	else
-		queue_work(conn->workq, &mrecv->proc_work);
-	ret = 0;
-
-out:
-	return ret;
-}
-
 /*
 * Always block receiving from the socket.  Errors trigger shutting down
 * the connection.
@@ -764,72 +614,86 @@ static void scoutfs_net_recv_worker(struct work_struct *work)
 	struct super_block *sb = conn->sb;
 	struct net_info *ninf = SCOUTFS_SB(sb)->net_info;
 	struct socket *sock = conn->sock;
-	struct scoutfs_net_header *nh;
-	struct page *page = NULL;
+	struct scoutfs_net_header nh;
+	struct message_recv *mrecv;
 	unsigned int data_len;
-	int hdr_off;
-	int rx_off;
-	int size;
 	int ret;

 	trace_scoutfs_net_recv_work_enter(sb, 0, 0);

-	page = alloc_page(GFP_NOFS);
-	if (!page) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	hdr_off = 0;
-	rx_off = 0;
-
 	for (;;) {
 		/* receive the header */
-		ret = k_recvmsg(sock, page_address(page) + rx_off, PAGE_SIZE - rx_off);
-		if (ret <= 0) {
-			ret = -ECONNABORTED;
-			goto out;
+		ret = recvmsg_full(sock, &nh, sizeof(nh));
+		if (ret)
+			break;
+
+		/* receiving an invalid message breaks the connection */
+		if (invalid_message(conn, &nh)) {
+			scoutfs_inc_counter(sb, net_recv_invalid_message);
+			ret = -EBADMSG;
+			break;
 		}

-		rx_off += ret;
+		data_len = le16_to_cpu(nh.data_len);

-		for (;;) {
-			size = rx_off - hdr_off;
-			if (size < sizeof(struct scoutfs_net_header))
-				break;
+		scoutfs_inc_counter(sb, net_recv_messages);
+		scoutfs_add_counter(sb, net_recv_bytes, nh_bytes(data_len));
+		trace_scoutfs_net_recv_message(sb, &conn->sockname,
+					       &conn->peername, &nh);

-			nh = page_address(page) + hdr_off;
-
-			/* receiving an invalid message breaks the connection */
-			if (invalid_message(conn, nh)) {
-				scoutfs_inc_counter(sb, net_recv_invalid_message);
-				ret = -EBADMSG;
-				break;
-			}
-
-			data_len = le16_to_cpu(nh->data_len);
-			if (sizeof(struct scoutfs_net_header) + data_len > size)
-				break;
-
-			ret = recv_one_message(sb, ninf, conn, nh, data_len);
-			if (ret < 0)
-				goto out;
-
-			hdr_off += sizeof(struct scoutfs_net_header) + data_len;
+		/* invalid message checked data len */
+		mrecv = kmalloc(offsetof(struct message_recv,
+					 nh.data[data_len]), GFP_NOFS);
+		if (!mrecv) {
+			ret = -ENOMEM;
+			break;
 		}

-		if ((PAGE_SIZE - rx_off) <
-		    (sizeof(struct scoutfs_net_header) + SCOUTFS_NET_MAX_DATA_LEN)) {
-			if (size)
-				memmove(page_address(page), page_address(page) + hdr_off, size);
-			hdr_off = 0;
-			rx_off = size;
+		mrecv->conn = conn;
+		INIT_WORK(&mrecv->proc_work, scoutfs_net_proc_worker);
+		mrecv->nh = nh;
+
+		/* receive the data payload */
+		ret = recvmsg_full(sock, mrecv->nh.data, data_len);
+		if (ret) {
+			kfree(mrecv);
+			break;
 		}
+
+		if (nh.cmd == SCOUTFS_NET_CMD_GREETING) {
+			/* greetings are out of band, no seq mechanics */
+			set_conn_fl(conn, saw_greeting);
+
+		} else if (le64_to_cpu(nh.seq) <=
+			   atomic64_read(&conn->recv_seq)) {
+			/* drop any resent duplicated messages */
+			scoutfs_inc_counter(sb, net_recv_dropped_duplicate);
+			kfree(mrecv);
+			continue;
+
+		} else {
+			/* record that we've received sender's seq */
+			atomic64_set(&conn->recv_seq, le64_to_cpu(nh.seq));
+			/* and free our responses that sender has received */
+			free_acked_responses(conn, le64_to_cpu(nh.recv_seq));
+		}
+
+		scoutfs_tseq_add(&ninf->msg_tseq_tree, &mrecv->tseq_entry);
+
+		/*
+		 * Initial received greetings are processed
+		 * synchronously before any other incoming messages.
+		 *
+		 * Incoming requests or responses to the lock client are
+		 * called synchronously to avoid reordering.
+		 */
+		if (nh.cmd == SCOUTFS_NET_CMD_GREETING ||
+		    (nh.cmd == SCOUTFS_NET_CMD_LOCK && !conn->listening_conn))
+			scoutfs_net_proc_worker(&mrecv->proc_work);
+		else
+			queue_work(conn->workq, &mrecv->proc_work);
 	}

-out:
-	__free_page(page);
-
 	if (ret)
 		scoutfs_inc_counter(sb, net_recv_error);

@@ -839,48 +703,38 @@ out:
 	trace_scoutfs_net_recv_work_exit(sb, 0, ret);
 }

-/*
- * This consumes the kvec.
- */
-static int k_sendmsg_full(struct socket *sock, struct kvec *kv, unsigned long nr_segs, size_t count)
+static int sendmsg_full(struct socket *sock, void *buf, unsigned len)
 {
-	int ret = 0;
+	struct msghdr msg;
+	struct kvec kv;
+	int ret;

-	while (count > 0) {
-		struct msghdr msg = {
-			.msg_flags = MSG_NOSIGNAL,
-		};
+	while (len) {
+		memset(&msg, 0, sizeof(msg));
+		msg.msg_flags = MSG_NOSIGNAL;
+		kv.iov_base = buf;
+		kv.iov_len = len;

-		ret = kernel_sendmsg(sock, &msg, kv, nr_segs, count);
-		if (ret <= 0) {
-			ret = -ECONNABORTED;
-			break;
-		}
+#ifndef KC_MSGHDR_STRUCT_IOV_ITER
+		msg.msg_iov = (struct iovec *)&kv;
+		msg.msg_iovlen = 1;
+#else
+		iov_iter_init(&msg.msg_iter, WRITE, (struct iovec *)&kv, len, 1);
+#endif
+		ret = kernel_sendmsg(sock, &msg, &kv, 1, len);
+		if (ret <= 0)
+			return -ECONNABORTED;

-		count -= ret;
-		if (count) {
-			while (nr_segs > 0 && ret >= kv->iov_len) {
-				ret -= kv->iov_len;
-				kv++;
-				nr_segs--;
-			}
-			if (nr_segs > 0 && ret > 0) {
-				kv->iov_base += ret;
-				kv->iov_len -= ret;
-			}
-			BUG_ON(nr_segs == 0);
-		}
-		ret = 0;
+		len -= ret;
+		buf += ret;
 	}
-	
-	return ret;
+
+	return 0;
 }

-static void free_msend(struct net_info *ninf, struct scoutfs_net_connection *conn,
-		       struct message_send *msend)
+static void free_msend(struct net_info *ninf, struct message_send *msend)
 {
 	list_del_init(&msend->head);
-	erase_sorted_msend(conn, msend);
 	scoutfs_tseq_del(&ninf->msg_tseq_tree, &msend->tseq_entry);
 	kfree(msend);
 }
@@ -906,74 +760,54 @@ static void scoutfs_net_send_worker(struct work_struct *work)
 	struct super_block *sb = conn->sb;
 	struct net_info *ninf = SCOUTFS_SB(sb)->net_info;
 	struct message_send *msend;
-	struct message_send *_msend_;
-	struct kvec kv[16];
-	unsigned long nr_segs;
-	size_t count;
+	int ret = 0;
 	int len;
-	int ret;

 	trace_scoutfs_net_send_work_enter(sb, 0, 0);

-	for (;;) {
-		nr_segs = 0;
-		count = 0;
+	spin_lock(&conn->lock);
+
+	while ((msend = list_first_entry_or_null(&conn->send_queue,
+						 struct message_send, head))) {
+
+		if (msend->dead) {
+			free_msend(ninf, msend);
+			continue;
+		}
+
+		if ((msend->nh.cmd == SCOUTFS_NET_CMD_FAREWELL) &&
+		    nh_is_response(&msend->nh)) {
+			set_conn_fl(conn, saw_farewell);
+		}
+
+		msend->nh.recv_seq =
+			cpu_to_le64(atomic64_read(&conn->recv_seq));
+
+		spin_unlock(&conn->lock);
+
+		len = nh_bytes(le16_to_cpu(msend->nh.data_len));
+
+		scoutfs_inc_counter(sb, net_send_messages);
+		scoutfs_add_counter(sb, net_send_bytes, len);
+		trace_scoutfs_net_send_message(sb, &conn->sockname,
+					       &conn->peername, &msend->nh);
+
+		ret = sendmsg_full(conn->sock, &msend->nh, len);

 		spin_lock(&conn->lock);

-		list_for_each_entry_safe(msend, _msend_, &conn->send_queue, head) {
-			if (msend->dead) {
-				free_msend(ninf, conn, msend);
-				continue;
-			}
+		msend->nh.recv_seq = 0;

-			len = nh_bytes(le16_to_cpu(msend->nh.data_len));
+		if (ret)
+			break;

-			if ((msend->nh.cmd == SCOUTFS_NET_CMD_FAREWELL) &&
-			    nh_is_response(&msend->nh)) {
-				set_conn_fl(conn, saw_farewell);
-			}
-
-			msend->nh.recv_seq = cpu_to_le64(atomic64_read(&conn->recv_seq));
-
-			scoutfs_inc_counter(sb, net_send_messages);
-			scoutfs_add_counter(sb, net_send_bytes, len);
-			trace_scoutfs_net_send_message(sb, &conn->sockname,
-						       &conn->peername, &msend->nh);
-
-			count += len;
-			kv[nr_segs].iov_base = &msend->nh;
-			kv[nr_segs].iov_len = len;
-			if (++nr_segs == ARRAY_SIZE(kv))
-				break;
-
-		}
-		spin_unlock(&conn->lock);
-
-		if (nr_segs == 0) {
-			ret = 0;
-			goto out;
-		}
-
-		ret = k_sendmsg_full(conn->sock, kv, nr_segs, count);
-		if (ret < 0)
-			goto out;
-
-		spin_lock(&conn->lock);
-		list_for_each_entry_safe(msend, _msend_, &conn->send_queue, head) {
-			msend->nh.recv_seq = 0;
-
-			/* resend if it wasn't freed while we sent */
-			if (!msend->dead)
-				list_move_tail(&msend->head, &conn->resend_queue);
-
-			if (--nr_segs == 0)
-				break;
-		}
-		spin_unlock(&conn->lock);
+		/* resend if it wasn't freed while we sent */
+		if (!msend->dead)
+			list_move_tail(&msend->head, &conn->resend_queue);
 	}

-out:
+	spin_unlock(&conn->lock);
+
 	if (ret) {
 		scoutfs_inc_counter(sb, net_send_error);
 		shutdown_conn(conn);
@@ -1012,7 +846,7 @@ static void scoutfs_net_destroy_worker(struct work_struct *work)

 	list_splice_init(&conn->resend_queue, &conn->send_queue);
 	list_for_each_entry_safe(msend, tmp, &conn->send_queue, head)
-		free_msend(ninf, conn, msend);
+		free_msend(ninf, msend);

 	/* accepted sockets are removed from their listener's list */
 	if (conn->listening_conn) {
@@ -1028,7 +862,6 @@ static void scoutfs_net_destroy_worker(struct work_struct *work)
 	destroy_workqueue(conn->workq);
 	scoutfs_tseq_del(&ninf->conn_tseq_tree, &conn->tseq_entry);
 	kfree(conn->info);
-	kfree(conn->ordered_proc_wlists);
 	trace_scoutfs_conn_destroy_free(conn);
 	kfree(conn);

@@ -1054,7 +887,7 @@ static void destroy_conn(struct scoutfs_net_connection *conn)
 * The TCP_KEEP* and TCP_USER_TIMEOUT option interaction is subtle.
 * TCP_USER_TIMEOUT only applies if there is unacked written data in the
 * send queue.  It doesn't work if the connection is idle.  Adding
- * keepalive probes with user_timeout set changes how the keepalive
+ * keepalice probes with user_timeout set changes how the keepalive
 * timeout is calculated.   CNT no longer matters.   Each time
 * additional probes (not the first) are sent the user timeout is
 * checked against the last time data was received.  If none of the
@@ -1066,50 +899,58 @@ static void destroy_conn(struct scoutfs_net_connection *conn)
 * elapses during the probe timer processing after the unsuccessful
 * probes.
 */
-static int sock_opts_and_names(struct super_block *sb,
-			       struct scoutfs_net_connection *conn,
+#define UNRESPONSIVE_TIMEOUT_SECS 10
+#define UNRESPONSIVE_PROBES 3
+static int sock_opts_and_names(struct scoutfs_net_connection *conn,
 			       struct socket *sock)
 {
-	struct scoutfs_mount_options opts;
+	struct timeval tv;
 	int optval;
 	int ret;

-	scoutfs_options_read(sb, &opts);
-
 	/* we use a keepalive timeout instead of send timeout */
-	ret = kc_sock_set_sndtimeo(sock, 0);
+	tv.tv_sec = 0;
+	tv.tv_usec = 0;
+	ret = kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO,
+				(char *)&tv, sizeof(tv));
 	if (ret)
 		goto out;

 	/* not checked when user_timeout != 0, but for clarity */
 	optval = UNRESPONSIVE_PROBES;
-	ret = kc_sock_setsockopt(sock, SOL_TCP, TCP_KEEPCNT,
-				&optval, sizeof(optval));
+	ret = kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT,
+				(char *)&optval, sizeof(optval));
 	if (ret)
 		goto out;

-	optval = (opts.tcp_keepalive_timeout_ms / MSEC_PER_SEC) - UNRESPONSIVE_PROBES;
-	ret = kc_tcp_sock_set_keepidle(sock, optval);
+	BUILD_BUG_ON(UNRESPONSIVE_PROBES >= UNRESPONSIVE_TIMEOUT_SECS);
+	optval = UNRESPONSIVE_TIMEOUT_SECS - (UNRESPONSIVE_PROBES);
+	ret = kernel_setsockopt(sock, SOL_TCP, TCP_KEEPIDLE,
+				(char *)&optval, sizeof(optval));
 	if (ret)
 		goto out;

 	optval = 1;
-	ret = kc_tcp_sock_set_keepintvl(sock, optval);
+	ret = kernel_setsockopt(sock, SOL_TCP, TCP_KEEPINTVL,
+				(char *)&optval, sizeof(optval));
 	if (ret)
 		goto out;

-	optval = opts.tcp_keepalive_timeout_ms;
-	ret = kc_tcp_sock_set_user_timeout(sock, optval);
+	optval = UNRESPONSIVE_TIMEOUT_SECS * MSEC_PER_SEC;
+	ret = kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT,
+				(char *)&optval, sizeof(optval));
 	if (ret)
 		goto out;

 	optval = 1;
-	ret = kc_sock_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
-				&optval, sizeof(optval));
+	ret = kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
+				(char *)&optval, sizeof(optval));
 	if (ret)
 		goto out;

-	ret = kc_tcp_sock_set_nodelay(sock);
+	optval = 1;
+	ret = kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY,
+				(char *)&optval, sizeof(optval));
 	if (ret)
 		goto out;

@@ -1160,19 +1001,13 @@ static void scoutfs_net_listen_worker(struct work_struct *work)
 						  conn->notify_down,
 						  conn->info_size,
 						  conn->req_funcs, "accepted");
-		/*
-		 * scoutfs_net_alloc_conn() can fail due to ENOMEM. If this
-		 * is the only thing that does so, there's no harm in trying
-		 * to see if kernel_accept() can get enough memory to try accepting
-		 * a new connection again. If that then fails with ENOMEM, it'll
-		 * shut down the conn anyway. So just retry here.
-		 */
 		if (!acc_conn) {
 			sock_release(acc_sock);
+			ret = -ENOMEM;
 			continue;
 		}

-		ret = sock_opts_and_names(sb, acc_conn, acc_sock);
+		ret = sock_opts_and_names(acc_conn, acc_sock);
 		if (ret) {
 			sock_release(acc_sock);
 			destroy_conn(acc_conn);
@@ -1214,6 +1049,7 @@ static void scoutfs_net_connect_worker(struct work_struct *work)
 	DEFINE_CONN_FROM_WORK(conn, work, connect_work);
 	struct super_block *sb = conn->sb;
 	struct socket *sock;
+	struct timeval tv;
 	int ret;

 	trace_scoutfs_net_connect_work_enter(sb, 0, 0);
@@ -1224,8 +1060,11 @@ static void scoutfs_net_connect_worker(struct work_struct *work)

 	sock->sk->sk_allocation = GFP_NOFS;

-	/* caller specified connect timeout, defaults to 1 sec */
-	ret = kc_sock_set_sndtimeo(sock, conn->connect_timeout_ms / MSEC_PER_SEC);
+	/* caller specified connect timeout */
+	tv.tv_sec = conn->connect_timeout_ms / MSEC_PER_SEC;
+	tv.tv_usec = (conn->connect_timeout_ms % MSEC_PER_SEC) * USEC_PER_MSEC;
+	ret = kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO,
+				(char *)&tv, sizeof(tv));
 	if (ret) {
 		sock_release(sock);
 		goto out;
@@ -1243,7 +1082,7 @@ static void scoutfs_net_connect_worker(struct work_struct *work)
 	if (ret)
 		goto out;

-	ret = sock_opts_and_names(sb, conn, sock);
+	ret = sock_opts_and_names(conn, sock);
 	if (ret)
 		goto out;

@@ -1358,7 +1197,7 @@ static void scoutfs_net_shutdown_worker(struct work_struct *work)
 							struct message_send, head))) {
 			resp_func = msend->resp_func;
 			resp_data = msend->resp_data;
-			free_msend(ninf, conn, msend);
+			free_msend(ninf, msend);
 			spin_unlock(&conn->lock);

 			call_resp_func(sb, conn, resp_func, resp_data, NULL, 0, -ECONNABORTED);
@@ -1374,7 +1213,7 @@ static void scoutfs_net_shutdown_worker(struct work_struct *work)
 	list_splice_tail_init(&conn->send_queue, &conn->resend_queue);
 	list_for_each_entry_safe(msend, tmp, &conn->resend_queue, head) {
 		if (msend->nh.cmd == SCOUTFS_NET_CMD_GREETING)
-			free_msend(ninf, conn, msend);
+			free_msend(ninf, msend);
 	}

 	clear_conn_fl(conn, saw_greeting);
@@ -1504,30 +1343,25 @@ scoutfs_net_alloc_conn(struct super_block *sb,
 {
 	struct net_info *ninf = SCOUTFS_SB(sb)->net_info;
 	struct scoutfs_net_connection *conn;
-	unsigned int nr;
-	unsigned int i;
-
-	nr = min_t(unsigned int, num_possible_cpus(),
-		   PAGE_SIZE / sizeof(struct scoutfs_work_list));

 	conn = kzalloc(sizeof(struct scoutfs_net_connection), GFP_NOFS);
-	if (conn) {
-		if (info_size)
-			conn->info = kzalloc(info_size, GFP_NOFS);
-		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);
-	}
-	if (!conn || (info_size && !conn->info) || !conn->workq || !conn->ordered_proc_wlists) {
-		if (conn) {
-			kfree(conn->info);
-			kfree(conn->ordered_proc_wlists);
-			if (conn->workq)
-				destroy_workqueue(conn->workq);
+	if (!conn)
+		return NULL;
+
+	if (info_size) {
+		conn->info = kzalloc(info_size, GFP_NOFS);
+		if (!conn->info) {
 			kfree(conn);
+			return NULL;
 		}
+	}
+
+	conn->workq = alloc_workqueue("scoutfs_net_%s",
+				      WQ_UNBOUND | WQ_NON_REENTRANT, 0,
+				      name_suffix);
+	if (!conn->workq) {
+		kfree(conn->info);
+		kfree(conn);
 		return NULL;
 	}

@@ -1548,8 +1382,6 @@ scoutfs_net_alloc_conn(struct super_block *sb,
 	atomic64_set(&conn->recv_seq, 0);
 	INIT_LIST_HEAD(&conn->send_queue);
 	INIT_LIST_HEAD(&conn->resend_queue);
-	conn->req_root = RB_ROOT;
-	conn->resp_root = RB_ROOT;
 	INIT_WORK(&conn->listen_work, scoutfs_net_listen_worker);
 	INIT_WORK(&conn->connect_work, scoutfs_net_connect_worker);
 	INIT_WORK(&conn->send_work, scoutfs_net_send_worker);
@@ -1559,13 +1391,6 @@ scoutfs_net_alloc_conn(struct super_block *sb,
 	INIT_DELAYED_WORK(&conn->reconn_free_dwork,
 			  scoutfs_net_reconn_free_worker);

-	conn->ordered_proc_nr = nr;
-	for (i = 0; i < nr; i++) {
-		INIT_WORK(&conn->ordered_proc_wlists[i].work, scoutfs_net_ordered_proc_worker);
-		spin_lock_init(&conn->ordered_proc_wlists[i].lock);
-		INIT_LIST_HEAD(&conn->ordered_proc_wlists[i].list);
-	}
-
 	scoutfs_tseq_add(&ninf->conn_tseq_tree, &conn->tseq_entry);
 	trace_scoutfs_conn_alloc(conn);

@@ -1637,8 +1462,8 @@ int scoutfs_net_bind(struct super_block *sb,
 	sock->sk->sk_allocation = GFP_NOFS;

 	optval = 1;
-	ret = kc_sock_setsockopt(sock, SOL_SOCKET, SO_REUSEADDR,
-				&optval, sizeof(optval));
+	ret = kernel_setsockopt(sock, SOL_SOCKET, SO_REUSEADDR,
+				(char *)&optval, sizeof(optval));
 	if (ret)
 		goto out;

@@ -1762,7 +1587,7 @@ void scoutfs_net_client_greeting(struct super_block *sb,
 		atomic64_set(&conn->recv_seq, 0);
 		list_for_each_entry_safe(msend, tmp, &conn->resend_queue, head){
 			if (nh_is_response(&msend->nh))
-				free_msend(ninf, conn, msend);
+				free_msend(ninf, msend);
 		}
 	}

@@ -1865,8 +1690,6 @@ restart:
 		BUG_ON(!list_empty(&reconn->send_queue));
 		/* queued greeting response is racing, can be in send or resend queue */
 		list_splice_tail_init(&reconn->resend_queue, &conn->resend_queue);
-		move_sorted_msends(conn, &conn->req_root, reconn, &reconn->req_root);
-		move_sorted_msends(conn, &conn->resp_root, reconn, &reconn->resp_root);

 		/* new conn info is unused, swap, old won't call down */
 		swap(conn->info, reconn->info);
--- a/kmod/src/net.h
+++ b/kmod/src/net.h
@@ -1,18 +1,10 @@
 #ifndef _SCOUTFS_NET_H_
 #define _SCOUTFS_NET_H_

-#include <linux/spinlock.h>
-#include <linux/list.h>
 #include <linux/in.h>
 #include "endian_swap.h"
 #include "tseq.h"

-struct scoutfs_work_list {
-	struct work_struct work;
-	spinlock_t lock;
-	struct list_head list;
-};
-
 struct scoutfs_net_connection;

 /* These are called in their own blocking context */
@@ -67,12 +59,8 @@ struct scoutfs_net_connection {
 	u64 next_send_id;
 	struct list_head send_queue;
 	struct list_head resend_queue;
-	struct rb_root req_root;
-	struct rb_root resp_root;

 	atomic64_t recv_seq;
-	unsigned int ordered_proc_nr;
-	struct scoutfs_work_list *ordered_proc_wlists;

 	struct workqueue_struct *workq;
 	struct work_struct listen_work;
--- a/kmod/src/omap.c
+++ b/kmod/src/omap.c
@@ -592,7 +592,7 @@ static int handle_request(struct super_block *sb, struct omap_request *req)
 	ret = 0;
 out:
 	free_rids(&priv_rids);
-	if ((ret < 0) && (req != NULL)) {
+	if (ret < 0) {
 		ret = scoutfs_server_send_omap_response(sb, req->client_rid, req->client_id,
 							NULL, ret);
 		free_req(req);
--- a/kmod/src/options.c
+++ b/kmod/src/options.c
@@ -33,15 +33,12 @@ enum {
 	Opt_acl,
 	Opt_data_prealloc_blocks,
 	Opt_data_prealloc_contig_only,
-	Opt_ino_alloc_per_lock,
-	Opt_lock_idle_count,
 	Opt_log_merge_wait_timeout_ms,
 	Opt_metadev_path,
 	Opt_noacl,
 	Opt_orphan_scan_delay_ms,
 	Opt_quorum_heartbeat_timeout_ms,
 	Opt_quorum_slot_nr,
-	Opt_tcp_keepalive_timeout_ms,
 	Opt_err,
 };

@@ -49,15 +46,12 @@ static const match_table_t tokens = {
 	{Opt_acl, "acl"},
 	{Opt_data_prealloc_blocks, "data_prealloc_blocks=%s"},
 	{Opt_data_prealloc_contig_only, "data_prealloc_contig_only=%s"},
-	{Opt_ino_alloc_per_lock, "ino_alloc_per_lock=%s"},
-	{Opt_lock_idle_count, "lock_idle_count=%s"},
 	{Opt_log_merge_wait_timeout_ms, "log_merge_wait_timeout_ms=%s"},
 	{Opt_metadev_path, "metadev_path=%s"},
 	{Opt_noacl, "noacl"},
 	{Opt_orphan_scan_delay_ms, "orphan_scan_delay_ms=%s"},
 	{Opt_quorum_heartbeat_timeout_ms, "quorum_heartbeat_timeout_ms=%s"},
 	{Opt_quorum_slot_nr, "quorum_slot_nr=%s"},
-	{Opt_tcp_keepalive_timeout_ms, "tcp_keepalive_timeout_ms=%s"},
 	{Opt_err, NULL}
 };

@@ -121,10 +115,6 @@ static void free_options(struct scoutfs_mount_options *opts)
 	kfree(opts->metadev_path);
 }

-#define MIN_LOCK_IDLE_COUNT	32
-#define DEFAULT_LOCK_IDLE_COUNT	(10 * 1000)
-#define MAX_LOCK_IDLE_COUNT	(100 * 1000)
-
 #define MIN_LOG_MERGE_WAIT_TIMEOUT_MS		100UL
 #define DEFAULT_LOG_MERGE_WAIT_TIMEOUT_MS	500
 #define MAX_LOG_MERGE_WAIT_TIMEOUT_MS		(60 * MSEC_PER_SEC)
@@ -136,36 +126,16 @@ static void free_options(struct scoutfs_mount_options *opts)
 #define MIN_DATA_PREALLOC_BLOCKS	1ULL
 #define MAX_DATA_PREALLOC_BLOCKS	((unsigned long long)SCOUTFS_BLOCK_SM_MAX)

-#define DEFAULT_TCP_KEEPALIVE_TIMEOUT_MS	(60 * MSEC_PER_SEC)
-
 static void init_default_options(struct scoutfs_mount_options *opts)
 {
 	memset(opts, 0, sizeof(*opts));

 	opts->data_prealloc_blocks = SCOUTFS_DATA_PREALLOC_DEFAULT_BLOCKS;
 	opts->data_prealloc_contig_only = 1;
-	opts->ino_alloc_per_lock = SCOUTFS_LOCK_INODE_GROUP_NR;
-	opts->lock_idle_count = DEFAULT_LOCK_IDLE_COUNT;
 	opts->log_merge_wait_timeout_ms = DEFAULT_LOG_MERGE_WAIT_TIMEOUT_MS;
 	opts->orphan_scan_delay_ms = -1;
 	opts->quorum_heartbeat_timeout_ms = SCOUTFS_QUORUM_DEF_HB_TIMEO_MS;
 	opts->quorum_slot_nr = -1;
-	opts->tcp_keepalive_timeout_ms = DEFAULT_TCP_KEEPALIVE_TIMEOUT_MS;
-}
-
-static int verify_lock_idle_count(struct super_block *sb, int ret, int val)
-{
-	if (ret < 0) {
-		scoutfs_err(sb, "failed to parse lock_idle_count value");
-		return -EINVAL;
-	}
-	if (val < MIN_LOCK_IDLE_COUNT || val > MAX_LOCK_IDLE_COUNT) {
-		scoutfs_err(sb, "invalid lock_idle_count value %d, must be between %u and %u",
-			    val, MIN_LOCK_IDLE_COUNT, MAX_LOCK_IDLE_COUNT);
-		return -EINVAL;
-	}
-
-	return 0;
 }

 static int verify_log_merge_wait_timeout_ms(struct super_block *sb, int ret, int val)
@@ -198,21 +168,6 @@ static int verify_quorum_heartbeat_timeout_ms(struct super_block *sb, int ret, u
 	return 0;
 }

-static int verify_tcp_keepalive_timeout_ms(struct super_block *sb, int ret, int val)
-{
-	if (ret < 0) {
-		scoutfs_err(sb, "failed to parse tcp_keepalive_timeout_ms value");
-		return -EINVAL;
-	}
-	if (val <= (UNRESPONSIVE_PROBES * MSEC_PER_SEC)) {
-		scoutfs_err(sb, "invalid tcp_keepalive_timeout_ms value %d, must be larger than %lu",
-			    val, (UNRESPONSIVE_PROBES * MSEC_PER_SEC));
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 /*
 * Parse the option string into our options struct.   This can allocate
 * memory in the struct.  The caller is responsible for always calling
@@ -263,34 +218,6 @@ static int parse_options(struct super_block *sb, char *options, struct scoutfs_m
 			opts->data_prealloc_contig_only = nr;
 			break;

-		case Opt_ino_alloc_per_lock:
-			ret = match_int(args, &nr);
-			if (ret < 0 || nr < 1 || nr > SCOUTFS_LOCK_INODE_GROUP_NR) {
-				scoutfs_err(sb, "invalid ino_alloc_per_lock option, must be between 1 and %u",
-					    SCOUTFS_LOCK_INODE_GROUP_NR);
-				if (ret == 0)
-					ret = -EINVAL;
-				return ret;
-			}
-			opts->ino_alloc_per_lock = nr;
-			break;
-
-		case Opt_tcp_keepalive_timeout_ms:
-			ret = match_int(args, &nr);
-			ret = verify_tcp_keepalive_timeout_ms(sb, ret, nr);
-			if (ret < 0)
-				return ret;
-			opts->tcp_keepalive_timeout_ms = nr;
-			break;
-
-		case Opt_lock_idle_count:
-			ret = match_int(args, &nr);
-			ret = verify_lock_idle_count(sb, ret, nr);
-			if (ret < 0)
-				return ret;
-			opts->lock_idle_count = nr;
-			break;
-
 		case Opt_log_merge_wait_timeout_ms:
 			ret = match_int(args, &nr);
 			ret = verify_log_merge_wait_timeout_ms(sb, ret, nr);
@@ -438,14 +365,12 @@ int scoutfs_options_show(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, ",acl");
 	seq_printf(seq, ",data_prealloc_blocks=%llu", opts.data_prealloc_blocks);
 	seq_printf(seq, ",data_prealloc_contig_only=%u", opts.data_prealloc_contig_only);
-	seq_printf(seq, ",ino_alloc_per_lock=%u", opts.ino_alloc_per_lock);
 	seq_printf(seq, ",metadev_path=%s", opts.metadev_path);
 	if (!is_acl)
 		seq_puts(seq, ",noacl");
 	seq_printf(seq, ",orphan_scan_delay_ms=%u", opts.orphan_scan_delay_ms);
 	if (opts.quorum_slot_nr >= 0)
 		seq_printf(seq, ",quorum_slot_nr=%d", opts.quorum_slot_nr);
-	seq_printf(seq, ",tcp_keepalive_timeout_ms=%d", opts.tcp_keepalive_timeout_ms);

 	return 0;
 }
@@ -527,82 +452,6 @@ static ssize_t data_prealloc_contig_only_store(struct kobject *kobj, struct kobj
 }
 SCOUTFS_ATTR_RW(data_prealloc_contig_only);

-static ssize_t ino_alloc_per_lock_show(struct kobject *kobj, struct kobj_attribute *attr,
-					 char *buf)
-{
-	struct super_block *sb = SCOUTFS_SYSFS_ATTRS_SB(kobj);
-	struct scoutfs_mount_options opts;
-
-	scoutfs_options_read(sb, &opts);
-
-	return snprintf(buf, PAGE_SIZE, "%u", opts.ino_alloc_per_lock);
-}
-static ssize_t ino_alloc_per_lock_store(struct kobject *kobj, struct kobj_attribute *attr,
-					  const char *buf, size_t count)
-{
-	struct super_block *sb = SCOUTFS_SYSFS_ATTRS_SB(kobj);
-	DECLARE_OPTIONS_INFO(sb, optinf);
-	char nullterm[20]; /* more than enough for octal -U32_MAX */
-	long val;
-	int len;
-	int ret;
-
-	len = min(count, sizeof(nullterm) - 1);
-	memcpy(nullterm, buf, len);
-	nullterm[len] = '\0';
-
-	ret = kstrtol(nullterm, 0, &val);
-	if (ret < 0 || val < 1 || val > SCOUTFS_LOCK_INODE_GROUP_NR) {
-		scoutfs_err(sb, "invalid ino_alloc_per_lock option, must be between 1 and %u",
-			    SCOUTFS_LOCK_INODE_GROUP_NR);
-		return -EINVAL;
-	}
-
-	write_seqlock(&optinf->seqlock);
-	optinf->opts.ino_alloc_per_lock = val;
-	write_sequnlock(&optinf->seqlock);
-
-	return count;
-}
-SCOUTFS_ATTR_RW(ino_alloc_per_lock);
-
-static ssize_t lock_idle_count_show(struct kobject *kobj, struct kobj_attribute *attr,
-						char *buf)
-{
-	struct super_block *sb = SCOUTFS_SYSFS_ATTRS_SB(kobj);
-	struct scoutfs_mount_options opts;
-
-	scoutfs_options_read(sb, &opts);
-
-	return snprintf(buf, PAGE_SIZE, "%u", opts.lock_idle_count);
-}
-static ssize_t lock_idle_count_store(struct kobject *kobj, struct kobj_attribute *attr,
-						 const char *buf, size_t count)
-{
-	struct super_block *sb = SCOUTFS_SYSFS_ATTRS_SB(kobj);
-	DECLARE_OPTIONS_INFO(sb, optinf);
-	char nullterm[30]; /* more than enough for octal -U64_MAX */
-	int val;
-	int len;
-	int ret;
-
-	len = min(count, sizeof(nullterm) - 1);
-	memcpy(nullterm, buf, len);
-	nullterm[len] = '\0';
-
-	ret = kstrtoint(nullterm, 0, &val);
-	ret = verify_lock_idle_count(sb, ret, val);
-	if (ret == 0) {
-		write_seqlock(&optinf->seqlock);
-		optinf->opts.lock_idle_count = val;
-		write_sequnlock(&optinf->seqlock);
-		ret = count;
-	}
-
-	return ret;
-}
-SCOUTFS_ATTR_RW(lock_idle_count);
-
 static ssize_t log_merge_wait_timeout_ms_show(struct kobject *kobj, struct kobj_attribute *attr,
 						char *buf)
 {
@@ -743,8 +592,6 @@ SCOUTFS_ATTR_RO(quorum_slot_nr);
 static struct attribute *options_attrs[] = {
 	SCOUTFS_ATTR_PTR(data_prealloc_blocks),
 	SCOUTFS_ATTR_PTR(data_prealloc_contig_only),
-	SCOUTFS_ATTR_PTR(ino_alloc_per_lock),
-	SCOUTFS_ATTR_PTR(lock_idle_count),
 	SCOUTFS_ATTR_PTR(log_merge_wait_timeout_ms),
 	SCOUTFS_ATTR_PTR(metadev_path),
 	SCOUTFS_ATTR_PTR(orphan_scan_delay_ms),
--- a/kmod/src/options.h
+++ b/kmod/src/options.h
@@ -8,18 +8,13 @@
 struct scoutfs_mount_options {
 	u64 data_prealloc_blocks;
 	bool data_prealloc_contig_only;
-	unsigned int ino_alloc_per_lock;
-	int lock_idle_count;
 	unsigned int log_merge_wait_timeout_ms;
 	char *metadev_path;
 	unsigned int orphan_scan_delay_ms;
 	int quorum_slot_nr;
 	u64 quorum_heartbeat_timeout_ms;
-	int tcp_keepalive_timeout_ms;
 };

-#define UNRESPONSIVE_PROBES	3
-
 void scoutfs_options_read(struct super_block *sb, struct scoutfs_mount_options *opts);
 int scoutfs_options_show(struct seq_file *seq, struct dentry *root);

--- a/kmod/src/quorum.c
+++ b/kmod/src/quorum.c
@@ -243,6 +243,10 @@ static int send_msg_members(struct super_block *sb, int type, u64 term, int only
 	};
 	struct sockaddr_in sin;
 	struct msghdr mh = {
+#ifndef KC_MSGHDR_STRUCT_IOV_ITER
+		.msg_iov = (struct iovec *)&kv,
+		.msg_iovlen = 1,
+#endif
 		.msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL,
 		.msg_name = &sin,
 		.msg_namelen = sizeof(sin),
@@ -264,7 +268,9 @@ static int send_msg_members(struct super_block *sb, int type, u64 term, int only

 		scoutfs_quorum_slot_sin(&qinf->qconf, i, &sin);
 		now = ktime_get();
-
+#ifdef KC_MSGHDR_STRUCT_IOV_ITER
+		iov_iter_init(&mh.msg_iter, WRITE, (struct iovec *)&kv, sizeof(qmes), 1);
+#endif
 		ret = kernel_sendmsg(qinf->sock, &mh, &kv, 1, kv.iov_len);
 		if (ret != kv.iov_len)
 			failed++;
@@ -297,6 +303,7 @@ static int recv_msg(struct super_block *sb, struct quorum_host_msg *msg,
 	DECLARE_QUORUM_INFO(sb, qinf);
 	struct scoutfs_sb_info *sbi = SCOUTFS_SB(sb);
 	struct scoutfs_quorum_message qmes;
+	struct timeval tv;
 	ktime_t rel_to;
 	ktime_t now;
 	int ret;
@@ -306,6 +313,10 @@ static int recv_msg(struct super_block *sb, struct quorum_host_msg *msg,
 		.iov_len = sizeof(struct scoutfs_quorum_message),
 	};
 	struct msghdr mh = {
+#ifndef KC_MSGHDR_STRUCT_IOV_ITER
+		.msg_iov = (struct iovec *)&kv,
+		.msg_iovlen = 1,
+#endif
 		.msg_flags = MSG_NOSIGNAL,
 	};

@@ -317,12 +328,19 @@ static int recv_msg(struct super_block *sb, struct quorum_host_msg *msg,
 	else
 		rel_to = ns_to_ktime(0);

-	if (ktime_compare(rel_to, ns_to_ktime(NSEC_PER_USEC)) <= 0) {
+	tv = ktime_to_timeval(rel_to);
+	if (tv.tv_sec == 0 && tv.tv_usec == 0) {
 		mh.msg_flags |= MSG_DONTWAIT;
 	} else {
-		ret = kc_tcp_sock_set_rcvtimeo(qinf->sock, rel_to);
+		ret = kernel_setsockopt(qinf->sock, SOL_SOCKET, SO_RCVTIMEO,
+					(char *)&tv, sizeof(tv));
+		if (ret < 0)
+			return ret;
 	}

+#ifdef KC_MSGHDR_STRUCT_IOV_ITER
+	iov_iter_init(&mh.msg_iter, READ, (struct iovec *)&kv, sizeof(struct scoutfs_quorum_message), 1);
+#endif
 	ret = kernel_recvmsg(qinf->sock, &mh, &kv, 1, kv.iov_len, mh.msg_flags);
 	if (ret < 0)
 		return ret;
@@ -468,7 +486,7 @@ static void set_quorum_block_event(struct super_block *sb, struct scoutfs_quorum
 	if (WARN_ON_ONCE(event < 0 || event >= SCOUTFS_QUORUM_EVENT_NR))
 		return;

-	ktime_get_ts64(&ts);
+	getnstimeofday64(&ts);
 	le64_add_cpu(&blk->write_nr, 1);

 	ev = &blk->events[event];
@@ -507,10 +525,10 @@ static int update_quorum_block(struct super_block *sb, int event, u64 term, bool
 		set_quorum_block_event(sb, &blk, event, term);
 		ret = write_quorum_block(sb, blkno, &blk);
 		if (ret < 0)
-			scoutfs_err(sb, "error %d writing quorum block %llu after updating event %d term %llu",
+			scoutfs_err(sb, "error %d reading quorum block %llu to update event %d term %llu",
 				    ret, blkno, event, term);
 	} else {
-		scoutfs_err(sb, "error %d reading quorum block %llu to update event %d term %llu",
+		scoutfs_err(sb, "error %d writing quorum block %llu after updating event %d term %llu",
 			    ret, blkno, event, term);
 	}

@@ -809,7 +827,6 @@ static void scoutfs_quorum_worker(struct work_struct *work)

 		/* followers and candidates start new election on timeout */
 		if (qst.role != LEADER &&
-		    msg.type == SCOUTFS_QUORUM_MSG_INVALID &&
 		    ktime_after(ktime_get(), qst.timeout)) {
 			/* .. but only if their server has stopped */
 			if (!scoutfs_server_is_down(sb)) {
@@ -970,10 +987,7 @@ static void scoutfs_quorum_worker(struct work_struct *work)
 	}

 	/* record that this slot no longer has an active quorum */
-	err = update_quorum_block(sb, SCOUTFS_QUORUM_EVENT_END, qst.term, true);
-	if (err < 0 && ret == 0)
-		ret = err;
-
+	update_quorum_block(sb, SCOUTFS_QUORUM_EVENT_END, qst.term, true);
 out:
 	if (ret < 0) {
 		scoutfs_err(sb, "quorum service saw error %d, shutting down.  This mount is no longer participating in quorum.  It should be remounted to restore service.",
@@ -1062,7 +1076,7 @@ static char *role_str(int role)
 		[LEADER] = "leader",
 	};

-	if (role < 0 || role >= ARRAY_SIZE(roles) || !roles[role])
+	if (role < 0 || role > ARRAY_SIZE(roles) || !roles[role])
 		return "invalid";

 	return roles[role];
@@ -1311,8 +1325,8 @@ int scoutfs_quorum_setup(struct super_block *sb)
 	qinf = kzalloc(sizeof(struct quorum_info), GFP_KERNEL);
 	super = kmalloc(sizeof(struct scoutfs_super_block), GFP_KERNEL);
 	if (qinf)
-		qinf->hb_delay = kc__vmalloc(HB_DELAY_NR * sizeof(struct count_recent),
-					   GFP_KERNEL | __GFP_ZERO);
+		qinf->hb_delay = __vmalloc(HB_DELAY_NR * sizeof(struct count_recent),
+					   GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL);
 	if (!qinf || !super || !qinf->hb_delay) {
 		if (qinf)
 			vfree(qinf->hb_delay);
--- a/kmod/src/quota.c
+++ b/kmod/src/quota.c
@@ -1226,7 +1226,7 @@ int scoutfs_quota_setup(struct super_block *sb)
 	init_waitqueue_head(&qtinf->waitq);

 	KC_INIT_SHRINKER_FUNCS(&qtinf->shrinker, count_cached_checks, scan_cached_checks);
-	KC_REGISTER_SHRINKER(&qtinf->shrinker, "scoutfs-quota:" SCSBF, SCSB_ARGS(sb));
+	KC_REGISTER_SHRINKER(&qtinf->shrinker);

 	sbi->squota_info = qtinf;

--- a/kmod/src/recov.c
+++ b/kmod/src/recov.c
@@ -76,10 +76,10 @@ static struct recov_pending *lookup_pending(struct recov_info *recinf, u64 rid,
 * We keep the pending list sorted by rid so that we can iterate over
 * them.  The list should be small and shouldn't be used often.
 */
-static int cmp_pending_rid(void *priv, KC_LIST_CMP_CONST struct list_head *A, KC_LIST_CMP_CONST struct list_head *B)
+static int cmp_pending_rid(void *priv, struct list_head *A, struct list_head *B)
 {
-	KC_LIST_CMP_CONST struct recov_pending *a = list_entry(A, KC_LIST_CMP_CONST struct recov_pending, head);
-	KC_LIST_CMP_CONST struct recov_pending *b = list_entry(B, KC_LIST_CMP_CONST struct recov_pending, head);
+	struct recov_pending *a = list_entry(A, struct recov_pending, head);
+	struct recov_pending *b = list_entry(B, struct recov_pending, head);

 	return scoutfs_cmp_u64s(a->rid, b->rid);
 }
--- a/kmod/src/scoutfs_trace.h
+++ b/kmod/src/scoutfs_trace.h
@@ -24,6 +24,7 @@

 #include <linux/tracepoint.h>
 #include <linux/in.h>
+#include <linux/unaligned/access_ok.h>

 #include "key.h"
 #include "format.h"
@@ -286,52 +287,6 @@ TRACE_EVENT(scoutfs_data_alloc_block_enter,
 		  STE_ENTRY_ARGS(ext))
 );

-TRACE_EVENT(scoutfs_data_page_mkwrite,
-	TP_PROTO(struct super_block *sb, __u64 ino, __u64 pos, __u32 ret),
-
-	TP_ARGS(sb, ino, pos, ret),
-
-	TP_STRUCT__entry(
-		SCSB_TRACE_FIELDS
-		__field(__u64, ino)
-		__field(__u64, pos)
-		__field(__u32, ret)
-	),
-
-	TP_fast_assign(
-		SCSB_TRACE_ASSIGN(sb);
-		__entry->ino = ino;
-		__entry->pos = pos;
-		__entry->ret = ret;
-	),
-
-	TP_printk(SCSBF" ino %llu pos %llu ret %u ",
-		  SCSB_TRACE_ARGS, __entry->ino, __entry->pos, __entry->ret)
-);
-
-TRACE_EVENT(scoutfs_data_filemap_fault,
-	TP_PROTO(struct super_block *sb, __u64 ino, __u64 pos, __u32 ret),
-
-	TP_ARGS(sb, ino, pos, ret),
-
-	TP_STRUCT__entry(
-		SCSB_TRACE_FIELDS
-		__field(__u64, ino)
-		__field(__u64, pos)
-		__field(__u32, ret)
-	),
-
-	TP_fast_assign(
-		SCSB_TRACE_ASSIGN(sb);
-		__entry->ino = ino;
-		__entry->pos = pos;
-		__entry->ret = ret;
-	),
-
-	TP_printk(SCSBF" ino %llu pos %llu ret %u ",
-		  SCSB_TRACE_ARGS, __entry->ino, __entry->pos, __entry->ret)
-);
-
 DECLARE_EVENT_CLASS(scoutfs_data_file_extent_class,
 	TP_PROTO(struct super_block *sb, __u64 ino, struct scoutfs_extent *ext),

@@ -789,80 +744,6 @@ TRACE_EVENT(scoutfs_inode_walk_writeback,
 		  __entry->ino, __entry->write, __entry->ret)
 );

-TRACE_EVENT(scoutfs_orphan_scan_start,
-	TP_PROTO(struct super_block *sb),
-
-	TP_ARGS(sb),
-
-	TP_STRUCT__entry(
-		SCSB_TRACE_FIELDS
-	),
-
-	TP_fast_assign(
-		SCSB_TRACE_ASSIGN(sb);
-	),
-
-	TP_printk(SCSBF, SCSB_TRACE_ARGS)
-);
-
-TRACE_EVENT(scoutfs_orphan_scan_stop,
-	TP_PROTO(struct super_block *sb, bool work_todo),
-
-	TP_ARGS(sb, work_todo),
-
-	TP_STRUCT__entry(
-		SCSB_TRACE_FIELDS
-		__field(bool, work_todo)
-	),
-
-	TP_fast_assign(
-		SCSB_TRACE_ASSIGN(sb);
-		__entry->work_todo = work_todo;
-	),
-
-	TP_printk(SCSBF" work_todo %d", SCSB_TRACE_ARGS, __entry->work_todo)
-);
-
-TRACE_EVENT(scoutfs_orphan_scan_work,
-	TP_PROTO(struct super_block *sb, __u64 ino),
-
-	TP_ARGS(sb, ino),
-
-	TP_STRUCT__entry(
-		SCSB_TRACE_FIELDS
-		__field(__u64, ino)
-	),
-
-	TP_fast_assign(
-		SCSB_TRACE_ASSIGN(sb);
-		__entry->ino = ino;
-	),
-
-	TP_printk(SCSBF" ino %llu", SCSB_TRACE_ARGS,
-		  __entry->ino)
-);
-
-TRACE_EVENT(scoutfs_orphan_scan_end,
-	TP_PROTO(struct super_block *sb, __u64 ino, int ret),
-
-	TP_ARGS(sb, ino, ret),
-
-	TP_STRUCT__entry(
-		SCSB_TRACE_FIELDS
-		__field(__u64, ino)
-		__field(int, ret)
-	),
-
-	TP_fast_assign(
-		SCSB_TRACE_ASSIGN(sb);
-		__entry->ino = ino;
-		__entry->ret = ret;
-	),
-
-	TP_printk(SCSBF" ino %llu ret %d", SCSB_TRACE_ARGS,
-		  __entry->ino, __entry->ret)
-);
-
 DECLARE_EVENT_CLASS(scoutfs_lock_info_class,
 	TP_PROTO(struct super_block *sb, struct lock_info *linfo),

@@ -897,14 +778,13 @@ DEFINE_EVENT(scoutfs_lock_info_class, scoutfs_lock_destroy,
 );

 TRACE_EVENT(scoutfs_xattr_set,
-	TP_PROTO(struct super_block *sb, __u64 ino, size_t name_len,
-		 const void *value, size_t size, int flags),
+	TP_PROTO(struct super_block *sb, size_t name_len, const void *value,
+		 size_t size, int flags),

-	TP_ARGS(sb, ino, name_len, value, size, flags),
+	TP_ARGS(sb, name_len, value, size, flags),

 	TP_STRUCT__entry(
 		SCSB_TRACE_FIELDS
-		__field(__u64, ino)
 		__field(size_t, name_len)
 		__field(const void *, value)
 		__field(size_t, size)
@@ -913,16 +793,15 @@ TRACE_EVENT(scoutfs_xattr_set,

 	TP_fast_assign(
 		SCSB_TRACE_ASSIGN(sb);
-		__entry->ino = ino;
 		__entry->name_len = name_len;
 		__entry->value = value;
 		__entry->size = size;
 		__entry->flags = flags;
 	),

-	TP_printk(SCSBF" ino %llu name_len %zu value %p size %zu flags 0x%x",
-		  SCSB_TRACE_ARGS, __entry->ino,  __entry->name_len,
-		  __entry->value, __entry->size, __entry->flags)
+	TP_printk(SCSBF" name_len %zu value %p size %zu flags 0x%x",
+		  SCSB_TRACE_ARGS, __entry->name_len, __entry->value,
+		  __entry->size, __entry->flags)
 );

 TRACE_EVENT(scoutfs_advance_dirty_super,
@@ -1110,82 +989,6 @@ TRACE_EVENT(scoutfs_orphan_inode,
 		  MINOR(__entry->dev), __entry->ino)
 );

-DECLARE_EVENT_CLASS(scoutfs_try_delete_class,
-        TP_PROTO(struct super_block *sb, u64 ino),
-        TP_ARGS(sb, ino),
-        TP_STRUCT__entry(
-		SCSB_TRACE_FIELDS
-		__field(__u64, ino)
-        ),
-        TP_fast_assign(
-		SCSB_TRACE_ASSIGN(sb);
-		__entry->ino = ino;
-        ),
-	TP_printk(SCSBF" ino %llu", SCSB_TRACE_ARGS, __entry->ino)
-);
-
-DEFINE_EVENT(scoutfs_try_delete_class, scoutfs_try_delete,
-        TP_PROTO(struct super_block *sb, u64 ino),
-        TP_ARGS(sb, ino)
-);
-
-DEFINE_EVENT(scoutfs_try_delete_class, scoutfs_try_delete_local_busy,
-        TP_PROTO(struct super_block *sb, u64 ino),
-        TP_ARGS(sb, ino)
-);
-
-DEFINE_EVENT(scoutfs_try_delete_class, scoutfs_try_delete_cached,
-        TP_PROTO(struct super_block *sb, u64 ino),
-        TP_ARGS(sb, ino)
-);
-
-DEFINE_EVENT(scoutfs_try_delete_class, scoutfs_try_delete_no_item,
-        TP_PROTO(struct super_block *sb, u64 ino),
-        TP_ARGS(sb, ino)
-);
-
-TRACE_EVENT(scoutfs_try_delete_has_links,
-	TP_PROTO(struct super_block *sb, u64 ino, unsigned int nlink),
-
-	TP_ARGS(sb, ino, nlink),
-
-	TP_STRUCT__entry(
-		SCSB_TRACE_FIELDS
-		__field(__u64, ino)
-		__field(unsigned int, nlink)
-	),
-
-	TP_fast_assign(
-		SCSB_TRACE_ASSIGN(sb);
-		__entry->ino = ino;
-		__entry->nlink = nlink;
-	),
-
-	TP_printk(SCSBF" ino %llu nlink %u", SCSB_TRACE_ARGS, __entry->ino,
-		  __entry->nlink)
-);
-
-TRACE_EVENT(scoutfs_inode_orphan_delete,
-	TP_PROTO(struct super_block *sb, u64 ino, int ret),
-
-	TP_ARGS(sb, ino, ret),
-
-	TP_STRUCT__entry(
-		SCSB_TRACE_FIELDS
-		__field(__u64, ino)
-		__field(int, ret)
-	),
-
-	TP_fast_assign(
-		SCSB_TRACE_ASSIGN(sb);
-		__entry->ino = ino;
-		__entry->ret = ret;
-	),
-
-	TP_printk(SCSBF" ino %llu ret %d", SCSB_TRACE_ARGS, __entry->ino,
-		__entry->ret)
-);
-
 TRACE_EVENT(scoutfs_delete_inode,
 	TP_PROTO(struct super_block *sb, u64 ino, umode_t mode, u64 size),

@@ -1210,32 +1013,6 @@ TRACE_EVENT(scoutfs_delete_inode,
 		  __entry->mode, __entry->size)
 );

-TRACE_EVENT(scoutfs_delete_inode_end,
-	TP_PROTO(struct super_block *sb, u64 ino, umode_t mode, u64 size, int ret),
-
-	TP_ARGS(sb, ino, mode, size, ret),
-
-	TP_STRUCT__entry(
-		__field(dev_t, dev)
-		__field(__u64, ino)
-		__field(umode_t, mode)
-		__field(__u64, size)
-		__field(int, ret)
-	),
-
-	TP_fast_assign(
-		__entry->dev = sb->s_dev;
-		__entry->ino = ino;
-		__entry->mode = mode;
-		__entry->size = size;
-		__entry->ret = ret;
-	),
-
-	TP_printk("dev %d,%d ino %llu, mode 0x%x size %llu, ret %d",
-		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino,
-		  __entry->mode, __entry->size, __entry->ret)
-);
-
 DECLARE_EVENT_CLASS(scoutfs_key_class,
        TP_PROTO(struct super_block *sb, struct scoutfs_key *key),
        TP_ARGS(sb, key),
@@ -1270,12 +1047,9 @@ DECLARE_EVENT_CLASS(scoutfs_lock_class,
 		sk_trace_define(start)
 		sk_trace_define(end)
 		__field(u64, refresh_gen)
-		__field(u64, write_seq)
-		__field(u64, dirty_trans_seq)
 		__field(unsigned char, request_pending)
 		__field(unsigned char, invalidate_pending)
 		__field(int, mode)
-		__field(int, invalidating_mode)
 		__field(unsigned int, waiters_cw)
 		__field(unsigned int, waiters_pr)
 		__field(unsigned int, waiters_ex)
@@ -1288,12 +1062,9 @@ DECLARE_EVENT_CLASS(scoutfs_lock_class,
 		sk_trace_assign(start, &lck->start);
 		sk_trace_assign(end, &lck->end);
 		__entry->refresh_gen = lck->refresh_gen;
-		__entry->write_seq = lck->write_seq;
-		__entry->dirty_trans_seq = lck->dirty_trans_seq;
 		__entry->request_pending = lck->request_pending;
 		__entry->invalidate_pending = lck->invalidate_pending;
 		__entry->mode = lck->mode;
-		__entry->invalidating_mode = lck->invalidating_mode;
 		__entry->waiters_pr = lck->waiters[SCOUTFS_LOCK_READ];
 		__entry->waiters_ex = lck->waiters[SCOUTFS_LOCK_WRITE];
 		__entry->waiters_cw = lck->waiters[SCOUTFS_LOCK_WRITE_ONLY];
@@ -1301,11 +1072,10 @@ DECLARE_EVENT_CLASS(scoutfs_lock_class,
 		__entry->users_ex = lck->users[SCOUTFS_LOCK_WRITE];
 		__entry->users_cw = lck->users[SCOUTFS_LOCK_WRITE_ONLY];
        ),
-        TP_printk(SCSBF" start "SK_FMT" end "SK_FMT" mode %u invmd %u reqp %u invp %u refg %llu wris %llu dts %llu waiters: pr %u ex %u cw %u users: pr %u ex %u cw %u",
+        TP_printk(SCSBF" start "SK_FMT" end "SK_FMT" mode %u reqpnd %u invpnd %u rfrgen %llu waiters: pr %u ex %u cw %u users: pr %u ex %u cw %u",
 		  SCSB_TRACE_ARGS, sk_trace_args(start), sk_trace_args(end),
-		  __entry->mode, __entry->invalidating_mode, __entry->request_pending,
-		  __entry->invalidate_pending, __entry->refresh_gen, __entry->write_seq,
-		  __entry->dirty_trans_seq,
+		  __entry->mode, __entry->request_pending,
+		  __entry->invalidate_pending, __entry->refresh_gen,
 		  __entry->waiters_pr, __entry->waiters_ex, __entry->waiters_cw,
 		  __entry->users_pr, __entry->users_ex, __entry->users_cw)
 );
@@ -1619,6 +1389,28 @@ DEFINE_EVENT(scoutfs_work_class, scoutfs_data_return_server_extents_exit,
        TP_ARGS(sb, data, ret)
 );

+DECLARE_EVENT_CLASS(scoutfs_shrink_exit_class,
+        TP_PROTO(struct super_block *sb, unsigned long nr_to_scan, int ret),
+        TP_ARGS(sb, nr_to_scan, ret),
+        TP_STRUCT__entry(
+		__field(void *, sb)
+		__field(unsigned long, nr_to_scan)
+		__field(int, ret)
+        ),
+        TP_fast_assign(
+		__entry->sb = sb;
+		__entry->nr_to_scan = nr_to_scan;
+		__entry->ret = ret;
+        ),
+        TP_printk("sb %p nr_to_scan %lu ret %d",
+		  __entry->sb, __entry->nr_to_scan, __entry->ret)
+);
+
+DEFINE_EVENT(scoutfs_shrink_exit_class, scoutfs_lock_shrink_exit,
+        TP_PROTO(struct super_block *sb, unsigned long nr_to_scan, int ret),
+        TP_ARGS(sb, nr_to_scan, ret)
+);
+
 TRACE_EVENT(scoutfs_rename,
 	TP_PROTO(struct super_block *sb, struct inode *old_dir,
 		 struct dentry *old_dentry, struct inode *new_dir,
@@ -2122,17 +1914,15 @@ DEFINE_EVENT(scoutfs_server_client_count_class, scoutfs_server_client_down,
 );

 DECLARE_EVENT_CLASS(scoutfs_server_commit_users_class,
-        TP_PROTO(struct super_block *sb, int holding, int applying,
-		 int nr_holders, u32 budget,
-		 u32 avail_before, u32 freed_before,
-		 int committing, int exceeded),
-        TP_ARGS(sb, holding, applying, nr_holders, budget, avail_before, freed_before, committing, exceeded),
+        TP_PROTO(struct super_block *sb, int holding, int applying, int nr_holders,
+		 u32 avail_before, u32 freed_before, int committing, int exceeded),
+        TP_ARGS(sb, holding, applying, nr_holders, avail_before, freed_before, committing,
+		exceeded),
        TP_STRUCT__entry(
 		SCSB_TRACE_FIELDS
 		__field(int, holding)
 		__field(int, applying)
 		__field(int, nr_holders)
-		__field(u32, budget)
 		__field(__u32, avail_before)
 		__field(__u32, freed_before)
 		__field(int, committing)
@@ -2143,45 +1933,35 @@ DECLARE_EVENT_CLASS(scoutfs_server_commit_users_class,
 		__entry->holding = !!holding;
 		__entry->applying = !!applying;
 		__entry->nr_holders = nr_holders;
-		__entry->budget = budget;
 		__entry->avail_before = avail_before;
 		__entry->freed_before = freed_before;
 		__entry->committing = !!committing;
 		__entry->exceeded = !!exceeded;
        ),
-	TP_printk(SCSBF" holding %u applying %u nr %u budget %u avail_before %u freed_before %u committing %u exceeded %u",
-		  SCSB_TRACE_ARGS, __entry->holding, __entry->applying,
-		  __entry->nr_holders, __entry->budget,
-		  __entry->avail_before, __entry->freed_before,
-		  __entry->committing, __entry->exceeded)
+	TP_printk(SCSBF" holding %u applying %u nr %u avail_before %u freed_before %u committing %u exceeded %u",
+		  SCSB_TRACE_ARGS, __entry->holding, __entry->applying, __entry->nr_holders,
+		  __entry->avail_before, __entry->freed_before, __entry->committing,
+		  __entry->exceeded)
 );
 DEFINE_EVENT(scoutfs_server_commit_users_class, scoutfs_server_commit_hold,
-        TP_PROTO(struct super_block *sb, int holding, int applying,
-		 int nr_holders, u32 budget,
-		 u32 avail_before, u32 freed_before,
-		 int committing, int exceeded),
-        TP_ARGS(sb, holding, applying, nr_holders, budget, avail_before, freed_before, committing, exceeded)
+        TP_PROTO(struct super_block *sb, int holding, int applying, int nr_holders,
+		 u32 avail_before, u32 freed_before, int committing, int exceeded),
+        TP_ARGS(sb, holding, applying, nr_holders, avail_before, freed_before, committing, exceeded)
 );
 DEFINE_EVENT(scoutfs_server_commit_users_class, scoutfs_server_commit_apply,
-        TP_PROTO(struct super_block *sb, int holding, int applying,
-		 int nr_holders, u32 budget,
-		 u32 avail_before, u32 freed_before,
-		 int committing, int exceeded),
-        TP_ARGS(sb, holding, applying, nr_holders, budget, avail_before, freed_before, committing, exceeded)
+        TP_PROTO(struct super_block *sb, int holding, int applying, int nr_holders,
+		 u32 avail_before, u32 freed_before, int committing, int exceeded),
+        TP_ARGS(sb, holding, applying, nr_holders, avail_before, freed_before, committing, exceeded)
 );
 DEFINE_EVENT(scoutfs_server_commit_users_class, scoutfs_server_commit_start,
-        TP_PROTO(struct super_block *sb, int holding, int applying,
-		 int nr_holders, u32 budget,
-		 u32 avail_before, u32 freed_before,
-		 int committing, int exceeded),
-        TP_ARGS(sb, holding, applying, nr_holders, budget, avail_before, freed_before, committing, exceeded)
+        TP_PROTO(struct super_block *sb, int holding, int applying, int nr_holders,
+		 u32 avail_before, u32 freed_before, int committing, int exceeded),
+        TP_ARGS(sb, holding, applying, nr_holders, avail_before, freed_before, committing, exceeded)
 );
 DEFINE_EVENT(scoutfs_server_commit_users_class, scoutfs_server_commit_end,
-        TP_PROTO(struct super_block *sb, int holding, int applying,
-		 int nr_holders, u32 budget,
-		 u32 avail_before, u32 freed_before,
-		 int committing, int exceeded),
-        TP_ARGS(sb, holding, applying, nr_holders, budget, avail_before, freed_before, committing, exceeded)
+        TP_PROTO(struct super_block *sb, int holding, int applying, int nr_holders,
+		 u32 avail_before, u32 freed_before, int committing, int exceeded),
+        TP_ARGS(sb, holding, applying, nr_holders, avail_before, freed_before, committing, exceeded)
 );

 #define slt_symbolic(mode)						\
@@ -2619,151 +2399,6 @@ TRACE_EVENT(scoutfs_block_dirty_ref,
 		  __entry->block_blkno, __entry->block_seq)
 );

-TRACE_EVENT(scoutfs_get_file_block,
-	TP_PROTO(struct super_block *sb, u64 blkno, int flags,
-		 struct scoutfs_srch_block *srb),
-
-	TP_ARGS(sb, blkno, flags, srb),
-
-	TP_STRUCT__entry(
-		SCSB_TRACE_FIELDS
-		__field(__u64, blkno)
-		__field(__u32, entry_nr)
-		__field(__u32, entry_bytes)
-		__field(int, flags)
-		__field(__u64, first_hash)
-		__field(__u64, first_ino)
-		__field(__u64, first_id)
-		__field(__u64, last_hash)
-		__field(__u64, last_ino)
-		__field(__u64, last_id)
-	),
-
-	TP_fast_assign(
-		SCSB_TRACE_ASSIGN(sb);
-		__entry->blkno = blkno;
-		__entry->entry_nr = __le32_to_cpu(srb->entry_nr);
-		__entry->entry_bytes = __le32_to_cpu(srb->entry_bytes);
-		__entry->flags = flags;
-		__entry->first_hash = __le64_to_cpu(srb->first.hash);
-		__entry->first_ino = __le64_to_cpu(srb->first.ino);
-		__entry->first_id = __le64_to_cpu(srb->first.id);
-		__entry->last_hash = __le64_to_cpu(srb->last.hash);
-		__entry->last_ino = __le64_to_cpu(srb->last.ino);
-		__entry->last_id = __le64_to_cpu(srb->last.id);
-	),
-
-	TP_printk(SCSBF" blkno %llu nr %u bytes %u flags 0x%x first_hash 0x%llx first_ino %llu first_id 0x%llx last_hash 0x%llx last_ino %llu last_id 0x%llx",
-		  SCSB_TRACE_ARGS, __entry->blkno, __entry->entry_nr,
-		  __entry->entry_bytes, __entry->flags,
-		  __entry->first_hash, __entry->first_ino, __entry->first_id,
-		  __entry->last_hash, __entry->last_ino, __entry->last_id)
-);
-
-TRACE_EVENT(scoutfs_srch_new_merge,
-	TP_PROTO(struct super_block *sb),
-
-	TP_ARGS(sb),
-
-	TP_STRUCT__entry(
-		SCSB_TRACE_FIELDS
-	),
-
-	TP_fast_assign(
-		SCSB_TRACE_ASSIGN(sb);
-	),
-
-	TP_printk(SCSBF, SCSB_TRACE_ARGS)
-);
-
-TRACE_EVENT(scoutfs_srch_emit_entry,
-	TP_PROTO(struct super_block *sb, struct scoutfs_srch_entry *sre,
-		 struct scoutfs_srch_block *srb, u64 blkno),
-
-	TP_ARGS(sb, sre, srb, blkno),
-
-	TP_STRUCT__entry(
-		SCSB_TRACE_FIELDS
-		__field(__u32, entry_nr)
-		__field(__u64, blkno)
-		__field(__u64, hash)
-		__field(__u64, ino)
-		__field(__u64, id)
-	),
-
-	TP_fast_assign(
-		SCSB_TRACE_ASSIGN(sb);
-		__entry->entry_nr = __le32_to_cpu(srb->entry_nr);
-		__entry->blkno = blkno;
-		__entry->hash = __le64_to_cpu(sre->hash);
-		__entry->ino = __le64_to_cpu(sre->ino);
-		__entry->id = __le64_to_cpu(sre->id);
-	),
-
-	TP_printk(SCSBF" nr %u blkno %llu hash 0x%llx ino %llu id 0x%llx",
-		  SCSB_TRACE_ARGS, __entry->entry_nr, __entry->blkno,
-		  __entry->hash, __entry->ino, __entry->id)
-);
-
-TRACE_EVENT(scoutfs_srch_clr_tmp,
-	TP_PROTO(struct super_block *sb, struct scoutfs_srch_entry *tmp),
-
-	TP_ARGS(sb, tmp),
-
-	TP_STRUCT__entry(
-		SCSB_TRACE_FIELDS
-		__field(__u64, tmp_hash)
-		__field(__u64, tmp_ino)
-		__field(__u64, tmp_id)
-	),
-
-	TP_fast_assign(
-		SCSB_TRACE_ASSIGN(sb);
-		__entry->tmp_hash = __le64_to_cpu(tmp->hash);
-		__entry->tmp_ino = __le64_to_cpu(tmp->ino);
-		__entry->tmp_id = __le64_to_cpu(tmp->id);
-	),
-
-	TP_printk(SCSBF" tmp hash 0x%llx tmp ino %llu tmp hash 0x%llx",
-		  SCSB_TRACE_ARGS,
-		  __entry->tmp_hash, __entry->tmp_ino, __entry->tmp_id)
-);
-
-TRACE_EVENT(scoutfs_srch_cmp,
-	TP_PROTO(struct super_block *sb, struct scoutfs_srch_entry *root,
-		 struct scoutfs_srch_entry *tmp, void *bl),
-
-	TP_ARGS(sb, root, tmp, bl),
-
-	TP_STRUCT__entry(
-		SCSB_TRACE_FIELDS
-		__field(__u64, root_hash)
-		__field(__u64, root_ino)
-		__field(__u64, root_id)
-		__field(__u64, tmp_hash)
-		__field(__u64, tmp_ino)
-		__field(__u64, tmp_id)
-		__field(void *, bl)
-	),
-
-	TP_fast_assign(
-		SCSB_TRACE_ASSIGN(sb);
-		__entry->root_hash = __le64_to_cpu(root->hash);
-		__entry->root_ino = __le64_to_cpu(root->ino);
-		__entry->root_id = __le64_to_cpu(root->id);
-		__entry->tmp_hash = __le64_to_cpu(tmp->hash);
-		__entry->tmp_ino = __le64_to_cpu(tmp->ino);
-		__entry->tmp_id = __le64_to_cpu(tmp->id);
-		__entry->bl = bl;
-	),
-
-	TP_printk(SCSBF" root hash 0x%llx root ino %llu root id 0x%llx tmp hash 0x%llx tmp ino %llu tmp hash 0x%llx, bl %p",
-		  SCSB_TRACE_ARGS,
-		  __entry->root_hash, __entry->root_ino, __entry->root_id,
-		  __entry->tmp_hash, __entry->tmp_ino, __entry->tmp_id,
-		  __entry->bl)
-);
-
 TRACE_EVENT(scoutfs_block_stale,
 	TP_PROTO(struct super_block *sb, struct scoutfs_block_ref *ref,
 		 struct scoutfs_block_header *hdr, u32 magic, u32 crc),
@@ -2804,8 +2439,8 @@ TRACE_EVENT(scoutfs_block_stale,

 DECLARE_EVENT_CLASS(scoutfs_block_class,
 	TP_PROTO(struct super_block *sb, void *bp, u64 blkno, int refcount, int io_count,
-		 unsigned long bits),
-	TP_ARGS(sb, bp, blkno, refcount, io_count, bits),
+		 unsigned long bits, __u64 accessed),
+	TP_ARGS(sb, bp, blkno, refcount, io_count, bits, accessed),
 	TP_STRUCT__entry(
 		SCSB_TRACE_FIELDS
 		__field(void *, bp)
@@ -2813,6 +2448,7 @@ DECLARE_EVENT_CLASS(scoutfs_block_class,
 		__field(int, refcount)
 		__field(int, io_count)
 		__field(long, bits)
+		__field(__u64, accessed)
 	),
 	TP_fast_assign(
 		SCSB_TRACE_ASSIGN(sb);
@@ -2821,65 +2457,71 @@ DECLARE_EVENT_CLASS(scoutfs_block_class,
 		__entry->refcount = refcount;
 		__entry->io_count = io_count;
 		__entry->bits = bits;
+		__entry->accessed = accessed;
 	),
-	TP_printk(SCSBF" bp %p blkno %llu refcount %x io_count %d bits 0x%lx",
+	TP_printk(SCSBF" bp %p blkno %llu refcount %d io_count %d bits 0x%lx accessed %llu",
 		  SCSB_TRACE_ARGS, __entry->bp, __entry->blkno, __entry->refcount,
-		  __entry->io_count, __entry->bits)
+		  __entry->io_count, __entry->bits, __entry->accessed)
 );
 DEFINE_EVENT(scoutfs_block_class, scoutfs_block_allocate,
 	TP_PROTO(struct super_block *sb, void *bp, u64 blkno,
-		 int refcount, int io_count, unsigned long bits),
-	TP_ARGS(sb, bp, blkno, refcount, io_count, bits)
+		 int refcount, int io_count, unsigned long bits,
+		 __u64 accessed),
+	TP_ARGS(sb, bp, blkno, refcount, io_count, bits, accessed)
 );
 DEFINE_EVENT(scoutfs_block_class, scoutfs_block_free,
 	TP_PROTO(struct super_block *sb, void *bp, u64 blkno,
-		 int refcount, int io_count, unsigned long bits),
-	TP_ARGS(sb, bp, blkno, refcount, io_count, bits)
+		 int refcount, int io_count, unsigned long bits,
+		 __u64 accessed),
+	TP_ARGS(sb, bp, blkno, refcount, io_count, bits, accessed)
 );
 DEFINE_EVENT(scoutfs_block_class, scoutfs_block_insert,
 	TP_PROTO(struct super_block *sb, void *bp, u64 blkno,
-		 int refcount, int io_count, unsigned long bits),
-	TP_ARGS(sb, bp, blkno, refcount, io_count, bits)
+		 int refcount, int io_count, unsigned long bits,
+		 __u64 accessed),
+	TP_ARGS(sb, bp, blkno, refcount, io_count, bits, accessed)
 );
 DEFINE_EVENT(scoutfs_block_class, scoutfs_block_remove,
 	TP_PROTO(struct super_block *sb, void *bp, u64 blkno,
-		 int refcount, int io_count, unsigned long bits),
-	TP_ARGS(sb, bp, blkno, refcount, io_count, bits)
+		 int refcount, int io_count, unsigned long bits,
+		 __u64 accessed),
+	TP_ARGS(sb, bp, blkno, refcount, io_count, bits, accessed)
 );
 DEFINE_EVENT(scoutfs_block_class, scoutfs_block_end_io,
 	TP_PROTO(struct super_block *sb, void *bp, u64 blkno,
-		 int refcount, int io_count, unsigned long bits),
-	TP_ARGS(sb, bp, blkno, refcount, io_count, bits)
+		 int refcount, int io_count, unsigned long bits,
+		 __u64 accessed),
+	TP_ARGS(sb, bp, blkno, refcount, io_count, bits, accessed)
 );
 DEFINE_EVENT(scoutfs_block_class, scoutfs_block_submit,
 	TP_PROTO(struct super_block *sb, void *bp, u64 blkno,
-		 int refcount, int io_count, unsigned long bits),
-	TP_ARGS(sb, bp, blkno, refcount, io_count, bits)
+		 int refcount, int io_count, unsigned long bits,
+		 __u64 accessed),
+	TP_ARGS(sb, bp, blkno, refcount, io_count, bits, accessed)
 );
 DEFINE_EVENT(scoutfs_block_class, scoutfs_block_invalidate,
 	TP_PROTO(struct super_block *sb, void *bp, u64 blkno,
-		 int refcount, int io_count, unsigned long bits),
-	TP_ARGS(sb, bp, blkno, refcount, io_count, bits)
+		 int refcount, int io_count, unsigned long bits,
+		 __u64 accessed),
+	TP_ARGS(sb, bp, blkno, refcount, io_count, bits, accessed)
 );
 DEFINE_EVENT(scoutfs_block_class, scoutfs_block_mark_dirty,
 	TP_PROTO(struct super_block *sb, void *bp, u64 blkno,
-		 int refcount, int io_count, unsigned long bits),
-	TP_ARGS(sb, bp, blkno, refcount, io_count, bits)
+		 int refcount, int io_count, unsigned long bits,
+		 __u64 accessed),
+	TP_ARGS(sb, bp, blkno, refcount, io_count, bits, accessed)
 );
 DEFINE_EVENT(scoutfs_block_class, scoutfs_block_forget,
 	TP_PROTO(struct super_block *sb, void *bp, u64 blkno,
-		 int refcount, int io_count, unsigned long bits),
-	TP_ARGS(sb, bp, blkno, refcount, io_count, bits)
+		 int refcount, int io_count, unsigned long bits,
+		 __u64 accessed),
+	TP_ARGS(sb, bp, blkno, refcount, io_count, bits, accessed)
 );
 DEFINE_EVENT(scoutfs_block_class, scoutfs_block_shrink,
 	TP_PROTO(struct super_block *sb, void *bp, u64 blkno,
-		 int refcount, int io_count, unsigned long bits),
-	TP_ARGS(sb, bp, blkno, refcount, io_count, bits)
-);
-DEFINE_EVENT(scoutfs_block_class, scoutfs_block_isolate,
-	TP_PROTO(struct super_block *sb, void *bp, u64 blkno,
-		 int refcount, int io_count, unsigned long bits),
-	TP_ARGS(sb, bp, blkno, refcount, io_count, bits)
+		 int refcount, int io_count, unsigned long bits,
+		 __u64 accessed),
+	TP_ARGS(sb, bp, blkno, refcount, io_count, bits, accessed)
 );

 DECLARE_EVENT_CLASS(scoutfs_ext_next_class,
@@ -3354,45 +2996,6 @@ DEFINE_EVENT(scoutfs_srch_compact_class, scoutfs_srch_compact_client_recv,
 	TP_ARGS(sb, sc)
 );

-TRACE_EVENT(scoutfs_ioc_search_xattrs,
-	TP_PROTO(struct super_block *sb, u64 ino, u64 last_ino),
-
-	TP_ARGS(sb, ino, last_ino),
-
-	TP_STRUCT__entry(
-		SCSB_TRACE_FIELDS
-		__field(u64, ino)
-		__field(u64, last_ino)
-	),
-
-	TP_fast_assign(
-		SCSB_TRACE_ASSIGN(sb);
-		__entry->ino = ino;
-		__entry->last_ino = last_ino;
-	),
-
-	TP_printk(SCSBF" ino %llu last_ino %llu", SCSB_TRACE_ARGS,
-		  __entry->ino, __entry->last_ino)
-);
-
-TRACE_EVENT(scoutfs_trigger_fired,
-	TP_PROTO(struct super_block *sb, const char *name),
-
-	TP_ARGS(sb, name),
-
-	TP_STRUCT__entry(
-		SCSB_TRACE_FIELDS
-		__field(const char *, name)
-	),
-
-	TP_fast_assign(
-		SCSB_TRACE_ASSIGN(sb);
-		__entry->name = name;
-	),
-
-	TP_printk(SCSBF" %s", SCSB_TRACE_ARGS, __entry->name)
-);
-
 #endif /* _TRACE_SCOUTFS_H */

 /* This part must be outside protection */
--- a/kmod/src/server.c
+++ b/kmod/src/server.c
@@ -41,7 +41,6 @@
 #include "recov.h"
 #include "omap.h"
 #include "fence.h"
-#include "triggers.h"

 /*
 * Every active mount can act as the server that listens on a net
@@ -66,7 +65,6 @@ struct commit_users {
 	struct list_head holding;
 	struct list_head applying;
 	unsigned int nr_holders;
-	u32 budget;
 	u32 avail_before;
 	u32 freed_before;
 	bool committing;
@@ -86,9 +84,8 @@ static void init_commit_users(struct commit_users *cusers)
 do {												\
 	__typeof__(cusers) _cusers = (cusers);							\
 	trace_scoutfs_server_commit_##which(sb, !list_empty(&_cusers->holding),			\
-		!list_empty(&_cusers->applying), _cusers->nr_holders, _cusers->budget,		\
-		_cusers->avail_before, _cusers->freed_before, _cusers->committing,		\
-		_cusers->exceeded);								\
+		!list_empty(&_cusers->applying), _cusers->nr_holders, _cusers->avail_before,	\
+		_cusers->freed_before, _cusers->committing, _cusers->exceeded);			\
 } while (0)

 struct server_info {
@@ -301,11 +298,12 @@ static void check_holder_budget(struct super_block *sb, struct server_info *serv
 {
 	static bool exceeded_once = false;
 	struct commit_hold *hold;
-	struct timespec64 ts;
+	struct timespec ts;
 	u32 avail_used;
 	u32 freed_used;
 	u32 avail_now;
 	u32 freed_now;
+	u32 budget;

 	assert_spin_locked(&cusers->lock);

@@ -320,18 +318,19 @@ static void check_holder_budget(struct super_block *sb, struct server_info *serv
 	else
 		freed_used = SCOUTFS_ALLOC_LIST_MAX_BLOCKS - freed_now;

-	if (avail_used <= cusers->budget && freed_used <= cusers->budget)
+	budget = cusers->nr_holders * COMMIT_HOLD_ALLOC_BUDGET;
+	if (avail_used <= budget && freed_used <= budget)
 		return;

 	exceeded_once = true;
 	cusers->exceeded = cusers->nr_holders;

-	scoutfs_err(sb, "holders exceeded alloc budget %u av: bef %u now %u, fr: bef %u now %u",
-		    cusers->budget, cusers->avail_before, avail_now,
+	scoutfs_err(sb, "%u holders exceeded alloc budget av: bef %u now %u, fr: bef %u now %u",
+		    cusers->nr_holders, cusers->avail_before, avail_now,
 		    cusers->freed_before, freed_now);

 	list_for_each_entry(hold, &cusers->holding, entry) {
-		ts = ktime_to_timespec64(hold->start);
+		ts = ktime_to_timespec(hold->start);
 		scoutfs_err(sb, "exceeding hold start %llu.%09llu av %u fr %u",
 			    (u64)ts.tv_sec, (u64)ts.tv_nsec, hold->avail, hold->freed);
 		hold->exceeded = true;
@@ -350,7 +349,7 @@ static bool hold_commit(struct super_block *sb, struct server_info *server,
 {
 	bool has_room;
 	bool held;
-	u32 new_budget;
+	u32 budget;
 	u32 av;
 	u32 fr;

@@ -368,8 +367,8 @@ static bool hold_commit(struct super_block *sb, struct server_info *server,
 	}

 	/* +2 for our additional hold and then for the final commit work the server does */
-	new_budget = max(cusers->budget, (cusers->nr_holders + 2) * COMMIT_HOLD_ALLOC_BUDGET);
-	has_room = av >= new_budget && fr >= new_budget;
+	budget = (cusers->nr_holders + 2) * COMMIT_HOLD_ALLOC_BUDGET;
+	has_room = av >= budget && fr >= budget;
 	/* checking applying so holders drain once an apply caller starts waiting */
 	held = !cusers->committing && has_room && list_empty(&cusers->applying);

@@ -389,7 +388,6 @@ static bool hold_commit(struct super_block *sb, struct server_info *server,
 		list_add_tail(&hold->entry, &cusers->holding);

 		cusers->nr_holders++;
-		cusers->budget = new_budget;

 	} else if (!has_room && cusers->nr_holders == 0 && !cusers->committing) {
 		cusers->committing = true;
@@ -447,7 +445,7 @@ static int server_apply_commit(struct super_block *sb, struct commit_hold *hold,
 {
 	DECLARE_SERVER_INFO(sb, server);
 	struct commit_users *cusers = &server->cusers;
-	struct timespec64 ts;
+	struct timespec ts;

 	spin_lock(&cusers->lock);

@@ -456,7 +454,7 @@ static int server_apply_commit(struct super_block *sb, struct commit_hold *hold,
 	check_holder_budget(sb, server, cusers);

 	if (hold->exceeded) {
-		ts = ktime_to_timespec64(hold->start);
+		ts = ktime_to_timespec(hold->start);
 		scoutfs_err(sb, "exceeding hold start %llu.%09llu stack:",
 			    (u64)ts.tv_sec, (u64)ts.tv_nsec);
 		dump_stack();
@@ -518,7 +516,6 @@ static void commit_end(struct super_block *sb, struct commit_users *cusers, int
 	list_for_each_entry_safe(hold, tmp, &cusers->applying, entry)
 		list_del_init(&hold->entry);
 	cusers->committing = false;
-	cusers->budget = 0;
 	spin_unlock(&cusers->lock);

 	wake_up(&cusers->waitq);
@@ -611,7 +608,7 @@ static void scoutfs_server_commit_func(struct work_struct *work)
 		goto out;

 	if (scoutfs_forcing_unmount(sb)) {
-		ret = -ENOLINK;
+		ret = -EIO;
 		goto out;
 	}

@@ -995,11 +992,10 @@ static int for_each_rid_last_lt(struct super_block *sb, struct scoutfs_btree_roo
 }

 /*
- * Log merge range items are stored at the starting fs key of the range
- * with the zone overwritten to indicate the log merge item type.  This
- * day0 mistake loses sorting information for items in the different
- * zones in the fs root, so the range items aren't strictly sorted by
- * the starting key of their range.
+ * Log merge range items are stored at the starting fs key of the range.
+ * The only fs key field that doesn't hold information is the zone, so
+ * we use the zone to differentiate all types that we store in the log
+ * merge tree.
 */
 static void init_log_merge_key(struct scoutfs_key *key, u8 zone, u64 first,
 			       u64 second)
@@ -1031,51 +1027,6 @@ static int next_log_merge_item_key(struct super_block *sb, struct scoutfs_btree_
 	return ret;
 }

-/*
- * The range items aren't sorted by their range.start because
- * _RANGE_ZONE clobbers the range's zone.  We sweep all the items and
- * find the range with the next least starting key that's greater than
- * the caller's starting key.  We have to be careful to iterate over the
- * log_merge tree keys because the ranges can overlap as they're mapped
- * to the log_merge keys by clobbering their zone.
- */
-static int next_log_merge_range(struct super_block *sb, struct scoutfs_btree_root *root,
-				struct scoutfs_key *start, struct scoutfs_log_merge_range *rng)
-{
-	struct scoutfs_log_merge_range *next;
-	SCOUTFS_BTREE_ITEM_REF(iref);
-	struct scoutfs_key key;
-	int ret;
-
-	key = *start;
-	key.sk_zone = SCOUTFS_LOG_MERGE_RANGE_ZONE;
-	scoutfs_key_set_ones(&rng->start);
-
-	do {
-		ret = scoutfs_btree_next(sb, root, &key, &iref);
-		if (ret == 0) {
-			if (iref.key->sk_zone != SCOUTFS_LOG_MERGE_RANGE_ZONE) {
-				ret = -ENOENT;
-			} else if (iref.val_len != sizeof(struct scoutfs_log_merge_range)) {
-				ret = -EIO;
-			} else {
-				next = iref.val;
-				if (scoutfs_key_compare(&next->start, &rng->start) < 0 &&
-				    scoutfs_key_compare(&next->start, start) >= 0)
-					*rng = *next;
-				key = *iref.key;
-				scoutfs_key_inc(&key);
-			}
-			scoutfs_btree_put_iref(&iref);
-		}
-	} while (ret == 0);
-
-	if (ret == -ENOENT && !scoutfs_key_is_ones(&rng->start))
-		ret = 0;
-
-	return ret;
-}
-
 static int next_log_merge_item(struct super_block *sb,
 			       struct scoutfs_btree_root *root,
 			       u8 zone, u64 first, u64 second,
@@ -1087,101 +1038,6 @@ static int next_log_merge_item(struct super_block *sb,
 	return next_log_merge_item_key(sb, root, zone, &key, val, val_len);
 }

-static int do_finalize_ours(struct super_block *sb,
-			    struct scoutfs_log_trees *lt,
-			    struct commit_hold *hold)
-{
-	struct server_info *server = SCOUTFS_SB(sb)->server_info;
-	struct scoutfs_super_block *super = DIRTY_SUPER_SB(sb);
-	struct scoutfs_key key;
-	char *err_str = NULL;
-	u64 rid = le64_to_cpu(lt->rid);
-	bool more;
-	int ret;
-	int err;
-
-	mutex_lock(&server->srch_mutex);
-	ret = scoutfs_srch_rotate_log(sb, &server->alloc, &server->wri,
-				      &super->srch_root, &lt->srch_file, true);
-	mutex_unlock(&server->srch_mutex);
-	if (ret < 0) {
-		scoutfs_err(sb, "error rotating srch log for rid %016llx: %d",
-			    rid, ret);
-		return ret;
-        }
-
-	do {
-		more = false;
-
-		/*
-		 * All of these can return errors, perhaps indicating successful
-		 * partial progress, after having modified the allocator trees.
-		 * We always have to update the roots in the log item.
-		 */
-		mutex_lock(&server->alloc_mutex);
-		ret = (err_str = "splice meta_freed to other_freed",
-				scoutfs_alloc_splice_list(sb, &server->alloc,
-					&server->wri, server->other_freed,
-					&lt->meta_freed)) ?:
-			(err_str = "splice meta_avail",
-			 scoutfs_alloc_splice_list(sb, &server->alloc,
-					&server->wri, server->other_freed,
-					&lt->meta_avail)) ?:
-			(err_str = "empty data_avail",
-			 alloc_move_empty(sb, &super->data_alloc,
-					  &lt->data_avail,
-					  COMMIT_HOLD_ALLOC_BUDGET / 2)) ?:
-			(err_str = "empty data_freed",
-			 alloc_move_empty(sb, &super->data_alloc,
-					  &lt->data_freed,
-					  COMMIT_HOLD_ALLOC_BUDGET / 2));
-		mutex_unlock(&server->alloc_mutex);
-
-		/*
-		 * only finalize, allowing merging, once the allocators are
-		 * fully freed
-		 */
-		if (ret == 0) {
-			/* the transaction is no longer open */
-			le64_add_cpu(&lt->flags, SCOUTFS_LOG_TREES_FINALIZED);
-			lt->finalize_seq = cpu_to_le64(scoutfs_server_next_seq(sb));
-		}
-
-		scoutfs_key_init_log_trees(&key, rid, le64_to_cpu(lt->nr));
-
-		err = scoutfs_btree_update(sb, &server->alloc, &server->wri,
-					   &super->logs_root, &key, lt,
-					   sizeof(*lt));
-		BUG_ON(err != 0); /* alloc, log, srch items out of sync */
-
-		if (ret == -EINPROGRESS) {
-			more = true;
-			mutex_unlock(&server->logs_mutex);
-			ret = server_apply_commit(sb, hold, 0);
-			if (ret < 0)
-				WARN_ON_ONCE(ret < 0);
-			server_hold_commit(sb, hold);
-			mutex_lock(&server->logs_mutex);
-		} else if (ret == 0) {
-			memset(&lt->item_root, 0, sizeof(lt->item_root));
-			memset(&lt->bloom_ref, 0, sizeof(lt->bloom_ref));
-			lt->inode_count_delta = 0;
-			lt->max_item_seq = 0;
-			lt->finalize_seq = 0;
-			le64_add_cpu(&lt->nr, 1);
-			lt->flags = 0;
-		}
-	} while (more);
-
-	if (ret < 0) {
-		scoutfs_err(sb,
-			    "error %d finalizing log trees for rid %016llx: %s",
-			    ret, rid, err_str);
-	}
-
-	return ret;
-}
-
 /*
 * Finalizing the log btrees for merging needs to be done carefully so
 * that items don't appear to go backwards in time.
@@ -1233,6 +1089,7 @@ static int finalize_and_start_log_merge(struct super_block *sb, struct scoutfs_l
 	struct scoutfs_log_merge_range rng;
 	struct scoutfs_mount_options opts;
 	struct scoutfs_log_trees each_lt;
+	struct scoutfs_log_trees fin;
 	unsigned int delay_ms;
 	unsigned long timeo;
 	bool saw_finalized;
@@ -1292,13 +1149,9 @@ static int finalize_and_start_log_merge(struct super_block *sb, struct scoutfs_l
 		 * meta was low so that deleted items are merged
 		 * promptly and freed blocks can bring the client out of
 		 * enospc.
-		 *
-		 * The trigger can be used to force a log merge in cases where
-		 * a test only generates small amounts of change.
 		 */
 		finalize_ours = (lt->item_root.height > 2) ||
-				(le32_to_cpu(lt->meta_avail.flags) & SCOUTFS_ALLOC_FLAG_LOW) ||
-				scoutfs_trigger(sb, LOG_MERGE_FORCE_FINALIZE_OURS);
+				(le32_to_cpu(lt->meta_avail.flags) & SCOUTFS_ALLOC_FLAG_LOW);

 		trace_scoutfs_server_finalize_decision(sb, rid, saw_finalized, others_active,
 						       ours_visible, finalize_ours, delay_ms,
@@ -1307,7 +1160,6 @@ static int finalize_and_start_log_merge(struct super_block *sb, struct scoutfs_l
 		/* done if we're not finalizing and there's no finalized */
 		if (!finalize_ours && !saw_finalized) {
 			ret = 0;
-			scoutfs_inc_counter(sb, log_merge_no_finalized);
 			break;
 		}

@@ -1342,11 +1194,32 @@ static int finalize_and_start_log_merge(struct super_block *sb, struct scoutfs_l

 		/* Finalize ours if it's visible to others */
 		if (ours_visible) {
-			ret = do_finalize_ours(sb, lt, hold);
+			fin = *lt;
+			memset(&fin.meta_avail, 0, sizeof(fin.meta_avail));
+			memset(&fin.meta_freed, 0, sizeof(fin.meta_freed));
+			memset(&fin.data_avail, 0, sizeof(fin.data_avail));
+			memset(&fin.data_freed, 0, sizeof(fin.data_freed));
+			memset(&fin.srch_file, 0, sizeof(fin.srch_file));
+			le64_add_cpu(&fin.flags, SCOUTFS_LOG_TREES_FINALIZED);
+			fin.finalize_seq = cpu_to_le64(scoutfs_server_next_seq(sb));
+
+			scoutfs_key_init_log_trees(&key, le64_to_cpu(fin.rid),
+						   le64_to_cpu(fin.nr));
+			ret = scoutfs_btree_update(sb, &server->alloc, &server->wri,
+						   &super->logs_root, &key, &fin,
+						   sizeof(fin));
 			if (ret < 0) {
-				err_str = "finalizing ours";
+				err_str = "updating finalized log_trees";
 				break;
 			}
+
+			memset(&lt->item_root, 0, sizeof(lt->item_root));
+			memset(&lt->bloom_ref, 0, sizeof(lt->bloom_ref));
+			lt->inode_count_delta = 0;
+			lt->max_item_seq = 0;
+			lt->finalize_seq = 0;
+			le64_add_cpu(&lt->nr, 1);
+			lt->flags = 0;
 		}

 		/* wait a bit for mounts to arrive */
@@ -1407,8 +1280,6 @@ static int finalize_and_start_log_merge(struct super_block *sb, struct scoutfs_l
 			BUG_ON(err); /* inconsistent */
 		}

-		scoutfs_inc_counter(sb, log_merge_start);
-
 		/* we're done, caller can make forward progress */
 		break;
 	}
@@ -1428,10 +1299,12 @@ static int finalize_and_start_log_merge(struct super_block *sb, struct scoutfs_l
 * is nested inside holding commits so we recheck the persistent item
 * each time we commit to make sure it's still what we think.   The
 * caller is still going to send the item to the client so we update the
- * caller's each time we make progress.  If we hit an error applying the
- * changes we make then we can't send the log_trees to the client.
+ * caller's each time we make progress.  This is a best-effort attempt
+ * to clean up and it's valid to leave extents in data_freed we don't
+ * return errors to the caller.  The client will continue the work later
+ * in get_log_trees or as the rid is reclaimed.
 */
-static int try_drain_data_freed(struct super_block *sb, struct scoutfs_log_trees *lt)
+static void try_drain_data_freed(struct super_block *sb, struct scoutfs_log_trees *lt)
 {
 	DECLARE_SERVER_INFO(sb, server);
 	struct scoutfs_super_block *super = DIRTY_SUPER_SB(sb);
@@ -1440,7 +1313,6 @@ static int try_drain_data_freed(struct super_block *sb, struct scoutfs_log_trees
 	struct scoutfs_log_trees drain;
 	struct scoutfs_key key;
 	COMMIT_HOLD(hold);
-	bool apply = false;
 	int ret = 0;
 	int err;

@@ -1449,27 +1321,22 @@ static int try_drain_data_freed(struct super_block *sb, struct scoutfs_log_trees
 	while (lt->data_freed.total_len != 0) {
 		server_hold_commit(sb, &hold);
 		mutex_lock(&server->logs_mutex);
-		apply = true;

 		ret = find_log_trees_item(sb, &super->logs_root, false, rid, U64_MAX, &drain);
-		if (ret < 0) {
-			ret = 0;
+		if (ret < 0)
 			break;
-		}

 		/* careful to only keep draining the caller's specific open trans */
 		if (drain.nr != lt->nr || drain.get_trans_seq != lt->get_trans_seq ||
 		    drain.commit_trans_seq != lt->commit_trans_seq || drain.flags != lt->flags) {
-			ret = 0;
+			ret = -ENOENT;
 			break;
 		}

 		ret = scoutfs_btree_dirty(sb, &server->alloc, &server->wri,
 					  &super->logs_root, &key);
-		if (ret < 0) {
-			ret = 0;
+		if (ret < 0)
 			break;
-		}

 		/* moving can modify and return errors, always update caller and item */
 		mutex_lock(&server->alloc_mutex);
@@ -1485,19 +1352,19 @@ static int try_drain_data_freed(struct super_block *sb, struct scoutfs_log_trees
 		BUG_ON(err < 0); /* dirtying must guarantee success */

 		mutex_unlock(&server->logs_mutex);
+
 		ret = server_apply_commit(sb, &hold, ret);
-		apply = false;
-
-		if (ret < 0)
+		if (ret < 0) {
+			ret = 0; /* don't try to abort, ignoring ret */
 			break;
+		}
 	}

-	if (apply) {
+	/* try to cleanly abort and write any partial dirty btree blocks, but ignore result */
+	if (ret < 0) {
 		mutex_unlock(&server->logs_mutex);
-		server_apply_commit(sb, &hold, ret);
+		server_apply_commit(sb, &hold, 0);
 	}
-
-	return ret;
 }

 /*
@@ -1625,8 +1492,7 @@ static int server_get_log_trees(struct super_block *sb,
 		goto update;
 	}

-	ret = alloc_move_empty(sb, &super->data_alloc, &lt.data_freed,
-			       COMMIT_HOLD_ALLOC_BUDGET / 2);
+	ret = alloc_move_empty(sb, &super->data_alloc, &lt.data_freed, 100);
 	if (ret == -EINPROGRESS)
 		ret = 0;
 	if (ret < 0) {
@@ -1706,9 +1572,9 @@ out:
 		scoutfs_err(sb, "error %d getting log trees for rid %016llx: %s",
 			    ret, rid, err_str);

-	/* try to drain excessive data_freed with additional commits, if needed */
+	/* try to drain excessive data_freed with additional commits, if needed, ignoring err */
 	if (ret == 0)
-		ret = try_drain_data_freed(sb, &lt);
+		try_drain_data_freed(sb, &lt);

 	return scoutfs_net_response(sb, conn, cmd, id, ret, &lt, sizeof(lt));
 }
@@ -1736,7 +1602,6 @@ static int server_commit_log_trees(struct super_block *sb,
 	int ret;

 	if (arg_len != sizeof(struct scoutfs_log_trees)) {
-		err_str = "invalid message log_trees size";
 		ret = -EINVAL;
 		goto out;
 	}
@@ -1800,7 +1665,7 @@ static int server_commit_log_trees(struct super_block *sb,

 	ret = scoutfs_btree_update(sb, &server->alloc, &server->wri,
 				   &super->logs_root, &key, &lt, sizeof(lt));
-	BUG_ON(ret < 0); /* dirtying should have guaranteed success, srch item inconsistent */
+	BUG_ON(ret < 0); /* dirtying should have guaranteed success */
 	if (ret < 0)
 		err_str = "updating log trees item";

@@ -1808,10 +1673,11 @@ unlock:
 	mutex_unlock(&server->logs_mutex);

 	ret = server_apply_commit(sb, &hold, ret);
-out:
 	if (ret < 0)
-		scoutfs_err(sb, "server error %d committing client logs for rid %016llx, nr %llu: %s",
-			    ret, rid, le64_to_cpu(lt.nr), err_str);
+		scoutfs_err(sb, "server error %d committing client logs for rid %016llx: %s",
+			    ret, rid, err_str);
+out:
+	WARN_ON_ONCE(ret < 0);
 	return scoutfs_net_response(sb, conn, cmd, id, ret, NULL, 0);
 }

@@ -1921,11 +1787,9 @@ static int reclaim_open_log_tree(struct super_block *sb, u64 rid)
 	       scoutfs_alloc_splice_list(sb, &server->alloc, &server->wri, server->other_freed,
 					 &lt.meta_avail)) ?:
 	      (err_str = "empty data_avail",
-	       alloc_move_empty(sb, &super->data_alloc, &lt.data_avail,
-				COMMIT_HOLD_ALLOC_BUDGET / 2)) ?:
+	       alloc_move_empty(sb, &super->data_alloc, &lt.data_avail, 100)) ?:
 	      (err_str = "empty data_freed",
-	       alloc_move_empty(sb, &super->data_alloc, &lt.data_freed,
-				COMMIT_HOLD_ALLOC_BUDGET / 2));
+	       alloc_move_empty(sb, &super->data_alloc, &lt.data_freed, 100));
 	mutex_unlock(&server->alloc_mutex);

 	/* only finalize, allowing merging, once the allocators are fully freed */
@@ -1946,9 +1810,6 @@ static int reclaim_open_log_tree(struct super_block *sb, u64 rid)
 out:
 	mutex_unlock(&server->logs_mutex);

-	if (ret == 0)
-		scoutfs_inc_counter(sb, reclaimed_open_logs);
-
 	if (ret < 0 && ret != -EINPROGRESS)
 		scoutfs_err(sb, "server error %d reclaiming log trees for rid %016llx: %s",
 			    ret, rid, err_str);
@@ -2150,7 +2011,7 @@ static int server_srch_get_compact(struct super_block *sb,

 apply:
 	ret = server_apply_commit(sb, &hold, ret);
-	WARN_ON_ONCE(ret < 0 && ret != -ENOENT && ret != -ENOLINK); /* XXX leaked busy item */
+	WARN_ON_ONCE(ret < 0 && ret != -ENOENT); /* XXX leaked busy item */
 out:
 	ret = scoutfs_net_response(sb, conn, cmd, id, ret,
 				   sc, sizeof(struct scoutfs_srch_compact));
@@ -2190,7 +2051,7 @@ static int server_srch_commit_compact(struct super_block *sb,
 					  &super->srch_root, rid, sc,
 					  &av, &fr);
 	mutex_unlock(&server->srch_mutex);
-	if (ret < 0)
+	if (ret < 0) /* XXX very bad, leaks allocators */
 		goto apply;

 	/* reclaim allocators if they were set by _srch_commit_ */
@@ -2200,10 +2061,10 @@ static int server_srch_commit_compact(struct super_block *sb,
 	      scoutfs_alloc_splice_list(sb, &server->alloc, &server->wri,
 					server->other_freed, &fr);
 	mutex_unlock(&server->alloc_mutex);
-	WARN_ON(ret < 0); /* XXX leaks allocators */
 apply:
 	ret = server_apply_commit(sb, &hold, ret);
 out:
+	WARN_ON(ret < 0); /* XXX leaks allocators */
 	return scoutfs_net_response(sb, conn, cmd, id, ret, NULL, 0);
 }

@@ -2516,8 +2377,6 @@ static int splice_log_merge_completions(struct super_block *sb,
 		queue_work(server->wq, &server->log_merge_free_work);
 	else
 		err_str = "deleting merge status item";
-
-	scoutfs_inc_counter(sb, log_merge_complete);
 out:
 	if (upd_stat) {
 		init_log_merge_key(&key, SCOUTFS_LOG_MERGE_STATUS_ZONE, 0, 0);
@@ -2530,9 +2389,10 @@ out:
 		}
 	}

-	/* inconsistent */
-	scoutfs_bug_on_err(sb, ret,
-			   "server error %d splicing log merge completion: %s", ret, err_str);
+	if (ret < 0)
+		scoutfs_err(sb, "server error %d splicing log merge completion: %s", ret, err_str);
+
+	BUG_ON(ret); /* inconsistent */

 	return ret ?: einprogress;
 }
@@ -2667,7 +2527,7 @@ static void server_log_merge_free_work(struct work_struct *work)

 		ret = scoutfs_btree_free_blocks(sb, &server->alloc,
 						&server->wri, &fr.key,
-						&fr.root, COMMIT_HOLD_ALLOC_BUDGET / 8);
+						&fr.root, COMMIT_HOLD_ALLOC_BUDGET / 2);
 		if (ret < 0) {
 			err_str = "freeing log btree";
 			break;
@@ -2686,7 +2546,7 @@ static void server_log_merge_free_work(struct work_struct *work)
 		/* freed blocks are in allocator, we *have* to update fr */
 		BUG_ON(ret < 0);

-		if (server_hold_alloc_used_since(sb, &hold) >= (COMMIT_HOLD_ALLOC_BUDGET * 3) / 4) {
+		if (server_hold_alloc_used_since(sb, &hold) >= COMMIT_HOLD_ALLOC_BUDGET / 2) {
 			mutex_unlock(&server->logs_mutex);
 			ret = server_apply_commit(sb, &hold, ret);
 			commit = false;
@@ -2777,7 +2637,10 @@ restart:

 	/* find the next range, always checking for splicing */
 	for (;;) {
-		ret = next_log_merge_range(sb, &super->log_merge, &stat.next_range_key, &rng);
+		key = stat.next_range_key;
+		key.sk_zone = SCOUTFS_LOG_MERGE_RANGE_ZONE;
+		ret = next_log_merge_item_key(sb, &super->log_merge, SCOUTFS_LOG_MERGE_RANGE_ZONE,
+					      &key, &rng, sizeof(rng));
 		if (ret < 0 && ret != -ENOENT) {
 			err_str = "finding merge range item";
 			goto out;
@@ -3048,13 +2911,7 @@ static int server_commit_log_merge(struct super_block *sb,
 				  SCOUTFS_LOG_MERGE_STATUS_ZONE, 0, 0,
 				  &stat, sizeof(stat));
 	if (ret < 0) {
-		/*
-		 * During a retransmission, it's possible that the server
-		 * already committed and resolved this log merge. ENOENT
-		 * is expected in that case.
-		 */
-		if (ret != -ENOENT)
-			err_str = "getting merge status item";
+		err_str = "getting merge status item";
 		goto out;
 	}

@@ -4292,7 +4149,7 @@ static void fence_pending_recov_worker(struct work_struct *work)
 	struct server_info *server = container_of(work, struct server_info,
 						  fence_pending_recov_work);
 	struct super_block *sb = server->sb;
-	union scoutfs_inet_addr addr = {{0,}};
+	union scoutfs_inet_addr addr;
 	u64 rid = 0;
 	int ret = 0;

--- a/kmod/src/sparse-filtered.sh
+++ b/kmod/src/sparse-filtered.sh
@@ -1,45 +0,0 @@
-#!/bin/bash
-
-#
-# Unfortunately, kernels can ship which contain sparse errors that are
-# unrelated to us.
-#
-# The exit status of this filtering wrapper will indicate an error if
-# sparse wasn't found or if there were any unfiltered output lines.  It
-# can hide error exit status from sparse or grep if they don't produce
-# output that makes it past the filters.
-#
-
-# must have sparse.  Fail with error message, mask success path.
-which sparse > /dev/null || exit 1
-
-# initial unmatchable, additional added as RE+="|..."
-RE="$^"
-
-#
-# Darn.  sparse has multi-line error messages, and I'd rather not bother
-# with multi-line filters.  So we'll just drop this context.
-#
-# command-line: note: in included file (through include/linux/netlink.h, include/linux/ethtool.h, include/linux/netdevice.h, include/net/sock.h, /root/scoutfs/kmod/src/kernelcompat.h, builtin): 
-#         fprintf(stderr, "%s: note: in included file%s:\n",
-#
-RE+="|: note: in included file"
-
-# 3.10.0-1160.119.1.el7.x86_64.debug
-# include/linux/posix_acl.h:138:9: warning: incorrect type in assignment (different address spaces)
-# include/linux/posix_acl.h:138:9:    expected struct posix_acl *<noident>
-# include/linux/posix_acl.h:138:9:    got struct posix_acl [noderef] <asn:4>*<noident>
-RE+="|include/linux/posix_acl.h:"
-
-# 3.10.0-1160.119.1.el7.x86_64.debug
-#include/uapi/linux/perf_event.h:146:56: warning: cast truncates bits from constant value (8000000000000000 becomes 0)
-RE+="|include/uapi/linux/perf_event.h:"
-
-# 4.18.0-513.24.1.el8_9.x86_64+debug'
-#./include/linux/skbuff.h:824:1: warning: directive in macro's argument list
-RE+="|include/linux/skbuff.h:"
-
-sparse "$@" |& \
-	grep -E -v "($RE)" |& \
-	awk '{ print $0 } END { exit NR > 0 }'
-exit $?
--- a/kmod/src/srch.c
+++ b/kmod/src/srch.c
@@ -18,7 +18,6 @@
 #include <linux/pagemap.h>
 #include <linux/vmalloc.h>
 #include <linux/sort.h>
-#include <asm/unaligned.h>

 #include "super.h"
 #include "format.h"
@@ -62,7 +61,7 @@
 * re-allocated and re-written.  Search can restart by checking the
 * btree for the current set of files.  Compaction reads log files which
 * are protected from other compactions by the persistent busy items
- * created by the server.  Compaction won't see its blocks reused out
+ * created by the server.  Compaction won't see it's blocks reused out
 * from under it, but it can encounter stale cached blocks that need to
 * be invalidated.
 */
@@ -442,10 +441,6 @@ out:
 	if (ret == 0 && (flags & GFB_INSERT) && blk >= le64_to_cpu(sfl->blocks))
 		sfl->blocks = cpu_to_le64(blk + 1);

-	if (bl) {
-		trace_scoutfs_get_file_block(sb, bl->blkno, flags, bl->data);
-	}
-
 	*bl_ret = bl;
 	return ret;
 }
@@ -537,35 +532,23 @@ out:
 * the pairs cancel each other out by all readers (the second encoding
 * looks like deletion) so they aren't visible to the first/last bounds of
 * the block or file.
- *
- * We use the same entry repeatedly, so the diff between them will be empty.
- * This lets us just emit the two-byte count word, leaving the other bytes
- * as zero.
- *
- * Split the desired total len into two pieces, adding any remainder to the
- * first four-bit value.
 */
-static void append_padded_entry(struct scoutfs_srch_file *sfl,
-				struct scoutfs_srch_block *srb,
-				int len)
+static int append_padded_entry(struct scoutfs_srch_file *sfl, u64 blk,
+			       struct scoutfs_srch_block *srb, struct scoutfs_srch_entry *sre)
 {
-	int each;
-	int rem;
-	u16 lengths = 0;
-	u8 *buf = srb->entries + le32_to_cpu(srb->entry_bytes);
+	int ret;

-	each = (len - 2) >> 1;
-	rem = (len - 2) & 1;
+	ret = encode_entry(srb->entries + le32_to_cpu(srb->entry_bytes),
+			   sre, &srb->tail);
+	if (ret > 0) {
+		srb->tail = *sre;
+		le32_add_cpu(&srb->entry_nr, 1);
+		le32_add_cpu(&srb->entry_bytes, ret);
+		le64_add_cpu(&sfl->entries, 1);
+		ret = 0;
+	}

-	lengths |= each + rem;
-	lengths |= each << 4;
-
-	memset(buf, 0, len);
-	put_unaligned_le16(lengths, buf);
-
-	le32_add_cpu(&srb->entry_nr, 1);
-	le32_add_cpu(&srb->entry_bytes, len);
-	le64_add_cpu(&sfl->entries, 1);
+	return ret;
 }

 /*
@@ -576,41 +559,61 @@ static void append_padded_entry(struct scoutfs_srch_file *sfl,
 * This is called when there is a single existing entry in the block.
 * We have the entire block to work with.  We encode pairs of matching
 * entries.  This hides them from readers (both searches and merging) as
- * they're interpreted as creation and deletion and are deleted.
+ * they're interpreted as creation and deletion and are deleted.  We use
+ * the existing hash value of the first entry in the block but then set
+ * the inode to an impossibly large number so it doesn't interfere with
+ * anything.
 *
- * For simplicity and to maintain sort ordering within the block, we reuse
- * the existing entry. This lets us skip the encoding step, because we know
- * the diff will be zero. We can zero-pad the resulting entries to hit the
- * target offset exactly.
+ * To hit the specific offset we very carefully manage the amount of
+ * bytes of change between fields in the entry.  We know that if we
+ * change all the byte of the ino and id we end up with a 20 byte
+ * (2+8+8,2) encoding of the pair of entries.  To have the last entry
+ * start at the _SAFE_POS offset we know that the final 20 byte pair
+ * encoding needs to end at 2 bytes (second entry encoding) after the
+ * _SAFE_POS offset.
 *
- * Because we can't predict the exact number of entry_bytes when we start,
- * we adjust the byte count of subsequent entries until we wind up at a
- * multiple of 20 bytes away from our goal and then use that length for
- * the remaining entries.
- *
- * We could just use a single pair of unnaturally large entries to consume
- * the needed space, adjusting for an odd number of entry_bytes if necessary.
- * The use of 19 or 20 bytes for the entry pair matches what we would see with
- * real (non-zero) entries that vary from the existing entry.
+ * So as we encode pairs we watch the delta of our current offset from
+ * that desired final offset of 2 past _SAFE_POS.  If we're a multiple
+ * of 20 away then we encode the full 20 byte pairs.  If we're not, then
+ * we drop a byte to encode 19 bytes.  That'll slowly change the offset
+ * to be a multiple of 20 again while encoding large entries.
 */
-static void pad_entries_at_safe(struct scoutfs_srch_file *sfl,
+static void pad_entries_at_safe(struct scoutfs_srch_file *sfl, u64 blk,
 				struct scoutfs_srch_block *srb)
 {
+	struct scoutfs_srch_entry sre;
 	u32 target;
 	s32 diff;
+	u64 hash;
+	u64 ino;
+	u64 id;
+	int ret;
+
+	hash = le64_to_cpu(srb->tail.hash);
+	ino = le64_to_cpu(srb->tail.ino) | (1ULL << 62);
+	id = le64_to_cpu(srb->tail.id);

 	target = SCOUTFS_SRCH_BLOCK_SAFE_BYTES + 2;

 	while ((diff = target - le32_to_cpu(srb->entry_bytes)) > 0) {
-		append_padded_entry(sfl, srb, 10);
+		ino ^= 1ULL << (7 * 8);
 		if (diff % 20 == 0) {
-			append_padded_entry(sfl, srb, 10);
+			id ^= 1ULL << (7 * 8);
 		} else {
-			append_padded_entry(sfl, srb, 9);
+			id ^= 1ULL << (6 * 8);
 		}
-	}

-	WARN_ON_ONCE(diff != 0);
+		sre.hash = cpu_to_le64(hash);
+		sre.ino = cpu_to_le64(ino);
+		sre.id = cpu_to_le64(id);
+
+		ret = append_padded_entry(sfl, blk, srb, &sre);
+		if (ret == 0)
+			ret = append_padded_entry(sfl, blk, srb, &sre);
+		BUG_ON(ret != 0);
+
+		diff = target - le32_to_cpu(srb->entry_bytes);
+	}
 }

 /*
@@ -745,14 +748,14 @@ static int search_log_file(struct super_block *sb,
 		for (i = 0; i < le32_to_cpu(srb->entry_nr); i++) {
 			if (pos > SCOUTFS_SRCH_BLOCK_SAFE_BYTES) {
 				/* can only be inconsistency :/ */
-				ret = -EIO;
+				ret = EIO;
 				break;
 			}

 			ret = decode_entry(srb->entries + pos, &sre, &prev);
 			if (ret <= 0) {
 				/* can only be inconsistency :/ */
-				ret = -EIO;
+				ret = EIO;
 				break;
 			}
 			pos += ret;
@@ -855,15 +858,15 @@ static int search_sorted_file(struct super_block *sb,

 		if (pos > SCOUTFS_SRCH_BLOCK_SAFE_BYTES) {
 			/* can only be inconsistency :/ */
-			ret = -EIO;
-			goto out;
+			ret = EIO;
+			break;
 		}

 		ret = decode_entry(srb->entries + pos, &sre, &prev);
 		if (ret <= 0) {
 			/* can only be inconsistency :/ */
-			ret = -EIO;
-			goto out;
+			ret = EIO;
+			break;
 		}
 		pos += ret;
 		prev = sre;
@@ -968,8 +971,6 @@ int scoutfs_srch_search_xattrs(struct super_block *sb,

 	scoutfs_inc_counter(sb, srch_search_xattrs);

-	trace_scoutfs_ioc_search_xattrs(sb, ino, last_ino);
-
 	*done = false;
 	srch_init_rb_root(sroot);

@@ -1406,7 +1407,7 @@ int scoutfs_srch_commit_compact(struct super_block *sb,
 			ret = -EIO;
 		scoutfs_btree_put_iref(&iref);
 	}
-	if (ret < 0)
+	if (ret < 0) /* XXX leaks allocators */
 		goto out;

 	/* restore busy to pending if the operation failed */
@@ -1426,8 +1427,10 @@ int scoutfs_srch_commit_compact(struct super_block *sb,
 	/* update file references if we finished compaction (!deleting) */
 	if (!(res->flags & SCOUTFS_SRCH_COMPACT_FLAG_DELETE)) {
 		ret = commit_files(sb, alloc, wri, root, res);
-		if (ret < 0)
+		if (ret < 0) {
+			/* XXX we can't commit, shutdown? */
 			goto out;
+		}

 		/* transition flags for deleting input files */
 		for (i = 0; i < res->nr; i++) {
@@ -1454,7 +1457,7 @@ update:
 			      le64_to_cpu(pending->id), 0);
 		ret = scoutfs_btree_insert(sb, alloc, wri, root, &key,
 					   pending, sizeof(*pending));
-		if (WARN_ON_ONCE(ret < 0)) /* XXX inconsistency */
+		if (ret < 0)
 			goto out;
 	}

@@ -1467,6 +1470,7 @@ update:
 		BUG_ON(err); /* both busy and pending present */
 	}
 out:
+	WARN_ON_ONCE(ret < 0); /* XXX inconsistency */
 	kfree(busy);
 	return ret;
 }
@@ -1525,66 +1529,6 @@ static bool should_commit(struct super_block *sb, struct scoutfs_alloc *alloc,
 		scoutfs_alloc_meta_low(sb, alloc, nr);
 }

-static int alloc_srch_block(struct super_block *sb, struct scoutfs_alloc *alloc,
-			    struct scoutfs_block_writer *wri,
-			    struct scoutfs_srch_file *sfl,
-			    struct scoutfs_block **bl,
-			    u64 blk)
-{
-	DECLARE_SRCH_INFO(sb, srinf);
-	int ret;
-
-	if (atomic_read(&srinf->shutdown))
-		return -ESHUTDOWN;
-
-	/* could grow and dirty to a leaf */
-	if (should_commit(sb, alloc, wri, sfl->height + 1))
-		return -EAGAIN;
-
-	ret = get_file_block(sb, alloc, wri, sfl, GFB_INSERT | GFB_DIRTY,
-			     blk, bl);
-	if (ret < 0)
-		return ret;
-
-	scoutfs_inc_counter(sb, srch_compact_dirty_block);
-
-	return 0;
-}
-
-static int emit_srch_entry(struct super_block *sb,
-			   struct scoutfs_srch_file *sfl,
-			   struct scoutfs_srch_block *srb,
-			   struct scoutfs_srch_entry *sre,
-			   u64 blk)
-{
-	int ret;
-
-	ret = encode_entry(srb->entries + le32_to_cpu(srb->entry_bytes),
-			   sre, &srb->tail);
-	if (WARN_ON_ONCE(ret <= 0)) {
-		/* shouldn't happen */
-		return -EIO;
-	}
-
-	if (srb->entry_bytes == 0) {
-		if (blk == 0)
-			sfl->first = *sre;
-		srb->first = *sre;
-	}
-
-	le32_add_cpu(&srb->entry_nr, 1);
-	le32_add_cpu(&srb->entry_bytes, ret);
-	srb->last = *sre;
-	srb->tail = *sre;
-	sfl->last = *sre;
-	le64_add_cpu(&sfl->entries, 1);
-
-	scoutfs_inc_counter(sb, srch_compact_entry);
-	trace_scoutfs_srch_emit_entry(sb, sre, srb, blk);
-
-	return 0;
-}
-
 struct tourn_node {
 	struct scoutfs_srch_entry sre;
 	int ind;
@@ -1619,18 +1563,20 @@ static int kway_merge(struct super_block *sb,
 		      kway_get_t kway_get, kway_advance_t kway_adv,
 		      void **args, int nr, bool logs_input)
 {
+	DECLARE_SRCH_INFO(sb, srinf);
 	struct scoutfs_srch_block *srb = NULL;
-	struct scoutfs_srch_entry tmp_entry = {0};
+	struct scoutfs_srch_entry last_tail;
 	struct scoutfs_block *bl = NULL;
 	struct tourn_node *tnodes;
 	struct tourn_node *leaves;
 	struct tourn_node *root;
 	struct tourn_node *tn;
-	bool have_tmp = false;
+	int last_bytes = 0;
 	int nr_parents;
 	int nr_nodes;
 	int empty = 0;
 	int ret = 0;
+	int diff;
 	u64 blk;
 	int ind;
 	int i;
@@ -1642,7 +1588,8 @@ static int kway_merge(struct super_block *sb,
 	nr_parents = max_t(unsigned long, 1, roundup_pow_of_two(nr) - 1);
 	/* root at [1] for easy sib/parent index calc, final pad for odd sib */
 	nr_nodes = 1 + nr_parents + nr + 1;
-	tnodes = kc__vmalloc(nr_nodes * sizeof(struct tourn_node), GFP_NOFS);
+	tnodes = __vmalloc(nr_nodes * sizeof(struct tourn_node),
+			   GFP_NOFS, PAGE_KERNEL);
 	if (!tnodes)
 		return -ENOMEM;

@@ -1664,73 +1611,97 @@ static int kway_merge(struct super_block *sb,
 		}
 	}

-	trace_scoutfs_srch_new_merge(sb);
-
 	/* always append new blocks */
 	blk = le64_to_cpu(sfl->blocks);
 	while (empty < nr) {
-		trace_scoutfs_srch_cmp(sb, &root->sre, &tmp_entry, bl);
-
-		if (sre_cmp(&root->sre, &tmp_entry) != 0) {
-			if (have_tmp) {
-				if (bl == NULL) {
-					ret = alloc_srch_block(sb, alloc, wri,
-							       sfl, &bl, blk);
-					if (ret < 0) {
-						if (ret == -EAGAIN)
-							ret = 0;
-						goto out;
-					}
-					srb = bl->data;
-				}
-
-				ret = emit_srch_entry(sb, sfl, srb, &tmp_entry,
-						      blk);
-				if (ret < 0)
-					goto out;
-
-				if (le32_to_cpu(srb->entry_bytes) >
-						SCOUTFS_SRCH_BLOCK_SAFE_BYTES) {
-					scoutfs_block_put(sb, bl);
-					bl = NULL;
-					blk++;
-					memset(&tmp_entry, 0, sizeof(tmp_entry));
-					have_tmp = false;
-					continue;
-				}
-
-				/*
-				 * end sorted block on _SAFE offset for
-				 * testing
-				 */
-				if (bl && le32_to_cpu(srb->entry_nr) == 1 &&
-				    logs_input &&
-				    scoutfs_trigger(sb, SRCH_COMPACT_LOGS_PAD_SAFE)) {
-					pad_entries_at_safe(sfl, srb);
-					scoutfs_block_put(sb, bl);
-					bl = NULL;
-					blk++;
-
-					memset(&tmp_entry, 0, sizeof(tmp_entry));
-					have_tmp = false;
-					continue;
-				}
+		if (bl == NULL) {
+			if (atomic_read(&srinf->shutdown)) {
+				ret = -ESHUTDOWN;
+				goto out;
 			}

-			tmp_entry = root->sre;
-			have_tmp = true;
+			/* could grow and dirty to a leaf */
+			if (should_commit(sb, alloc, wri, sfl->height + 1)) {
+				ret = 0;
+				goto out;
+			}
+
+			ret = get_file_block(sb, alloc, wri, sfl,
+					     GFB_INSERT | GFB_DIRTY, blk, &bl);
+			if (ret < 0)
+				goto out;
+			srb = bl->data;
+			scoutfs_inc_counter(sb, srch_compact_dirty_block);
+		}
+
+		if (sre_cmp(&root->sre, &srb->last) != 0) {
+			last_bytes = le32_to_cpu(srb->entry_bytes);
+			last_tail = srb->last;
+			ret = encode_entry(srb->entries +
+					   le32_to_cpu(srb->entry_bytes),
+					   &root->sre, &srb->tail);
+			if (WARN_ON_ONCE(ret <= 0)) {
+				/* shouldn't happen */
+				ret = -EIO;
+				goto out;
+			}
+
+			if (srb->entry_bytes == 0) {
+				if (blk == 0)
+					sfl->first = root->sre;
+				srb->first = root->sre;
+			}
+			le32_add_cpu(&srb->entry_nr, 1);
+			le32_add_cpu(&srb->entry_bytes, ret);
+			srb->last = root->sre;
+			srb->tail = root->sre;
+			sfl->last = root->sre;
+			le64_add_cpu(&sfl->entries, 1);
+			ret = 0;
+
+			if (le32_to_cpu(srb->entry_bytes) >
+			    SCOUTFS_SRCH_BLOCK_SAFE_BYTES) {
+				scoutfs_block_put(sb, bl);
+				bl = NULL;
+				blk++;
+			}
+
+			/* end sorted block on _SAFE offset for testing */
+			if (bl && le32_to_cpu(srb->entry_nr) == 1 && logs_input &&
+			    scoutfs_trigger(sb, SRCH_COMPACT_LOGS_PAD_SAFE)) {
+				pad_entries_at_safe(sfl, blk, srb);
+				scoutfs_block_put(sb, bl);
+				bl = NULL;
+				blk++;
+			}
+
+			scoutfs_inc_counter(sb, srch_compact_entry);
+
 		} else {
 			/*
 			 * Duplicate entries indicate deletion so we
-			 * undo the previously cached tmp entry and ignore
+			 * undo the previously encoded entry and ignore
 			 * this entry.  This only happens within each
 			 * block.  Deletions can span block boundaries
 			 * and will be filtered out by search and
 			 * hopefully removed in future compactions.
 			 */
-			trace_scoutfs_srch_clr_tmp(sb, &tmp_entry);
-			memset(&tmp_entry, 0, sizeof(tmp_entry));
-			have_tmp = false;
+			diff = le32_to_cpu(srb->entry_bytes) - last_bytes;
+			if (diff) {
+				memset(srb->entries + last_bytes, 0, diff);
+				if (srb->entry_bytes == 0) {
+					/* last_tail will be 0 */
+					if (blk == 0)
+						sfl->first = last_tail;
+					srb->first = last_tail;
+				}
+				le32_add_cpu(&srb->entry_nr, -1);
+				srb->entry_bytes = cpu_to_le32(last_bytes);
+				srb->last = last_tail;
+				srb->tail = last_tail;
+				sfl->last = last_tail;
+				le64_add_cpu(&sfl->entries, -1);
+			}

 			scoutfs_inc_counter(sb, srch_compact_removed_entry);
 		}
@@ -1773,22 +1744,6 @@ static int kway_merge(struct super_block *sb,
 	/* could stream a final index.. arguably a small portion of work */

 out:
-	if (have_tmp) {
-		bool emit = true;
-
-		if (bl == NULL) {
-			ret = alloc_srch_block(sb, alloc, wri, sfl, &bl, blk);
-			if (ret) {
-				emit = false;
-				if (ret == -EAGAIN)
-					ret = 0;
-			}
-		}
-
-		if (emit)
-			ret = emit_srch_entry(sb, sfl, srb, &tmp_entry, blk);
-	}
-
 	scoutfs_block_put(sb, bl);
 	vfree(tnodes);
 	return ret;
@@ -1847,7 +1802,7 @@ static void swap_page_sre(void *A, void *B, int size)
 * typically, ~10x worst case).
 *
 * Because we read and sort all the input files we must perform the full
- * compaction in one operation.  The server must have given us
+ * compaction in one operation.  The server must have given us a
 * sufficiently large avail/freed lists, otherwise we'll return ENOSPC.
 */
 static int compact_logs(struct super_block *sb,
@@ -1911,14 +1866,14 @@ static int compact_logs(struct super_block *sb,

 		if (pos > SCOUTFS_SRCH_BLOCK_SAFE_BYTES) {
 			/* can only be inconsistency :/ */
-			ret = -EIO;
-			goto out;
+			ret = EIO;
+			break;
 		}

 		ret = decode_entry(srb->entries + pos, sre, &prev);
 		if (ret <= 0) {
 			/* can only be inconsistency :/ */
-			ret = -EIO;
+			ret = EIO;
 			goto out;
 		}
 		prev = *sre;
@@ -2032,11 +1987,6 @@ static int kway_get_reader(struct super_block *sb,
 	    rdr->skip > SCOUTFS_SRCH_BLOCK_SAFE_BYTES ||
 	    rdr->skip >= le32_to_cpu(srb->entry_bytes)) {
 		/* XXX inconsistency */
-		scoutfs_err(sb, "blkno %llu pos %u vs %ld, skip %u, bytes %u",
-			__le64_to_cpu(srb->hdr.blkno),
-			rdr->pos, SCOUTFS_SRCH_BLOCK_SAFE_BYTES,
-			rdr->skip,
-			le32_to_cpu(srb->entry_bytes));
 		return -EIO;
 	}

@@ -2331,11 +2281,12 @@ static void scoutfs_srch_compact_worker(struct work_struct *work)
 	} else {
 		ret = -EINVAL;
 	}
+	if (ret < 0)
+		goto commit;

-	scoutfs_alloc_prepare_commit(sb, &alloc, &wri);
-	if (ret == 0)
+	ret = scoutfs_alloc_prepare_commit(sb, &alloc, &wri) ?:
 	      scoutfs_block_writer_write(sb, &wri);
-
+commit:
 	/* the server won't use our partial compact if _ERROR is set */
 	sc->meta_avail = alloc.avail;
 	sc->meta_freed = alloc.freed;
@@ -2352,7 +2303,7 @@ out:
 		scoutfs_inc_counter(sb, srch_compact_error);

 	scoutfs_block_writer_forget_all(sb, &wri);
-	queue_compact_work(srinf, sc != NULL && sc->nr > 0 && ret == 0);
+	queue_compact_work(srinf, sc->nr > 0 && ret == 0);

 	kfree(sc);
 }
--- a/kmod/src/super.c
+++ b/kmod/src/super.c
@@ -160,17 +160,7 @@ static void scoutfs_metadev_close(struct super_block *sb)
 		 * from kill_sb->put_super.
 		 */
 		lockdep_off();
-
-#ifdef KC_BDEV_FILE_OPEN_BY_PATH
-		bdev_fput(sbi->meta_bdev_file);
-#else
-#ifdef KC_BLKDEV_PUT_HOLDER_ARG
-		blkdev_put(sbi->meta_bdev, sb);
-#else
 		blkdev_put(sbi->meta_bdev, SCOUTFS_META_BDEV_MODE);
-#endif
-#endif
-
 		lockdep_on();
 		sbi->meta_bdev = NULL;
 	}
@@ -487,11 +477,7 @@ out:
 static int scoutfs_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct scoutfs_mount_options opts;
-#ifdef KC_BDEV_FILE_OPEN_BY_PATH
-	struct file *meta_bdev_file;
-#else
 	struct block_device *meta_bdev;
-#endif
 	struct scoutfs_sb_info *sbi;
 	struct inode *inode;
 	int ret;
@@ -512,9 +498,9 @@ static int scoutfs_fill_super(struct super_block *sb, void *data, int silent)

 	sbi = kzalloc(sizeof(struct scoutfs_sb_info), GFP_KERNEL);
 	sb->s_fs_info = sbi;
+	sbi->sb = sb;
 	if (!sbi)
 		return -ENOMEM;
-	sbi->sb = sb;

 	ret = assign_random_id(sbi);
 	if (ret < 0)
@@ -537,27 +523,7 @@ static int scoutfs_fill_super(struct super_block *sb, void *data, int silent)
 		goto out;
 	}

-#ifdef KC_BDEV_FILE_OPEN_BY_PATH
-	/*
-	 * pass sbi as holder, since dev_mount already passes sb, which triggers a
-	 * WARN_ON because dev_mount also passes non-NULL hops. By passing sbi
-	 * here we just get a simple error in our test cases.
-	 */
-	meta_bdev_file = bdev_file_open_by_path(opts.metadev_path, SCOUTFS_META_BDEV_MODE, sbi, NULL);
-	if (IS_ERR(meta_bdev_file)) {
-		scoutfs_err(sb, "could not open metadev: error %ld",
-			    PTR_ERR(meta_bdev_file));
-		ret = PTR_ERR(meta_bdev_file);
-		goto out;
-	}
-	sbi->meta_bdev_file = meta_bdev_file;
-	sbi->meta_bdev = file_bdev(meta_bdev_file);
-#else
-#ifdef KC_BLKDEV_PUT_HOLDER_ARG
-	meta_bdev = blkdev_get_by_path(opts.metadev_path, SCOUTFS_META_BDEV_MODE, sb, NULL);
-#else
 	meta_bdev = blkdev_get_by_path(opts.metadev_path, SCOUTFS_META_BDEV_MODE, sb);
-#endif
 	if (IS_ERR(meta_bdev)) {
 		scoutfs_err(sb, "could not open metadev: error %ld",
 			    PTR_ERR(meta_bdev));
@@ -565,8 +531,6 @@ static int scoutfs_fill_super(struct super_block *sb, void *data, int silent)
 		goto out;
 	}
 	sbi->meta_bdev = meta_bdev;
-#endif
-
 	ret = set_blocksize(sbi->meta_bdev, SCOUTFS_BLOCK_SM_SIZE);
 	if (ret != 0) {
 		scoutfs_err(sb, "failed to set metadev blocksize, returned %d",
--- a/kmod/src/super.h
+++ b/kmod/src/super.h
@@ -42,9 +42,6 @@ struct scoutfs_sb_info {
 	u64 fmt_vers;

 	struct block_device *meta_bdev;
-#ifdef KC_BDEV_FILE_OPEN_BY_PATH
-	struct file *meta_bdev_file;
-#endif

 	spinlock_t next_ino_lock;

@@ -104,11 +101,7 @@ static inline bool SCOUTFS_IS_META_BDEV(struct scoutfs_super_block *super_block)
 	return !!(le64_to_cpu(super_block->flags) & SCOUTFS_FLAG_IS_META_BDEV);
 }

-#ifdef KC_HAVE_BLK_MODE_T
-#define SCOUTFS_META_BDEV_MODE (BLK_OPEN_READ | BLK_OPEN_WRITE | BLK_OPEN_EXCL)
-#else
 #define SCOUTFS_META_BDEV_MODE (FMODE_READ | FMODE_WRITE | FMODE_EXCL)
-#endif

 static inline bool scoutfs_forcing_unmount(struct super_block *sb)
 {
--- a/kmod/src/sysfs.c
+++ b/kmod/src/sysfs.c
@@ -13,7 +13,6 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/fs.h>
-#include <linux/blkdev.h>

 #include "super.h"
 #include "sysfs.h"
--- a/kmod/src/trans.c
+++ b/kmod/src/trans.c
@@ -159,58 +159,6 @@ static bool drained_holders(struct trans_info *tri)
 	return holders == 0;
 }

-static int commit_current_log_trees(struct super_block *sb, char **str)
-{
-	DECLARE_TRANS_INFO(sb, tri);
-
-	return (*str = "data submit", scoutfs_inode_walk_writeback(sb, true)) ?:
-	       (*str = "item dirty", scoutfs_item_write_dirty(sb))  ?:
-	       (*str = "data prepare", scoutfs_data_prepare_commit(sb))  ?:
-	       (*str = "alloc prepare", scoutfs_alloc_prepare_commit(sb, &tri->alloc, &tri->wri)) ?:
-	       (*str = "meta write", scoutfs_block_writer_write(sb, &tri->wri))  ?:
-	       (*str = "data wait", scoutfs_inode_walk_writeback(sb, false)) ?:
-	       (*str = "commit log trees", commit_btrees(sb)) ?:
-	       scoutfs_item_write_done(sb);
-}
-
-static int get_next_log_trees(struct super_block *sb, char **str)
-{
-	return (*str = "get log trees", scoutfs_trans_get_log_trees(sb));
-}
-
-static int retry_forever(struct super_block *sb, int (*func)(struct super_block *sb, char **str))
-{
-	bool retrying = false;
-	char *str;
-	int ret;
-
-	do {
-		str = NULL;
-
-		ret = func(sb, &str);
-		if (ret < 0) {
-			if (!retrying) {
-				scoutfs_warn(sb, "critical transaction commit failure: %s = %d, retrying",
-					    str, ret);
-				retrying = true;
-			}
-
-			if (scoutfs_forcing_unmount(sb)) {
-				ret = -ENOLINK;
-				break;
-			}
-
-			msleep(2 * MSEC_PER_SEC);
-
-		} else if (retrying) {
-			scoutfs_info(sb, "retried transaction commit succeeded");
-		}
-
-	} while (ret < 0);
-
-	return ret;
-}
-
 /*
 * This work func is responsible for writing out all the dirty blocks
 * that make up the current dirty transaction.  It prevents writers from
@@ -236,6 +184,8 @@ void scoutfs_trans_write_func(struct work_struct *work)
 	struct trans_info *tri = container_of(work, struct trans_info, write_work.work);
 	struct super_block *sb = tri->sb;
 	struct scoutfs_sb_info *sbi = SCOUTFS_SB(sb);
+	bool retrying = false;
+	char *s = NULL;
 	int ret = 0;

 	tri->task = current;
@@ -252,7 +202,7 @@ void scoutfs_trans_write_func(struct work_struct *work)
 	}

 	if (scoutfs_forcing_unmount(sb)) {
-		ret = -ENOLINK;
+		ret = -EIO;
 		goto out;
 	}

@@ -264,9 +214,37 @@ void scoutfs_trans_write_func(struct work_struct *work)

 	scoutfs_inc_counter(sb, trans_commit_written);

-	/* retry {commit,get}_log_trees until they succeeed, can only fail when forcing unmount */
-	ret = retry_forever(sb, commit_current_log_trees) ?:
-	      retry_forever(sb, get_next_log_trees);
+	do {
+		ret = (s = "data submit", scoutfs_inode_walk_writeback(sb, true)) ?:
+		      (s = "item dirty", scoutfs_item_write_dirty(sb))  ?:
+		      (s = "data prepare", scoutfs_data_prepare_commit(sb))  ?:
+		      (s = "alloc prepare", scoutfs_alloc_prepare_commit(sb, &tri->alloc,
+									 &tri->wri))  ?:
+		      (s = "meta write", scoutfs_block_writer_write(sb, &tri->wri))  ?:
+		      (s = "data wait", scoutfs_inode_walk_writeback(sb, false)) ?:
+		      (s = "commit log trees", commit_btrees(sb)) ?:
+		      scoutfs_item_write_done(sb) ?:
+		      (s = "get log trees", scoutfs_trans_get_log_trees(sb));
+		if (ret < 0) {
+			if (!retrying) {
+				scoutfs_warn(sb, "critical transaction commit failure: %s = %d, retrying",
+					    s, ret);
+				retrying = true;
+			}
+
+			if (scoutfs_forcing_unmount(sb)) {
+				ret = -EIO;
+				break;
+			}
+
+			msleep(2 * MSEC_PER_SEC);
+
+		} else if (retrying) {
+			scoutfs_info(sb, "retried transaction commit succeeded");
+		}
+
+	} while (ret < 0);
+
 out:
 	spin_lock(&tri->write_lock);
 	tri->write_count++;
--- a/kmod/src/triggers.c
+++ b/kmod/src/triggers.c
@@ -18,7 +18,6 @@

 #include "super.h"
 #include "triggers.h"
-#include "scoutfs_trace.h"

 /*
 * We have debugfs files we can write to which arm triggers which
@@ -40,7 +39,6 @@ struct scoutfs_triggers {

 static char *names[] = {
 	[SCOUTFS_TRIGGER_BLOCK_REMOVE_STALE] = "block_remove_stale",
-	[SCOUTFS_TRIGGER_LOG_MERGE_FORCE_FINALIZE_OURS] = "log_merge_force_finalize_ours",
 	[SCOUTFS_TRIGGER_SRCH_COMPACT_LOGS_PAD_SAFE] = "srch_compact_logs_pad_safe",
 	[SCOUTFS_TRIGGER_SRCH_FORCE_LOG_ROTATE] = "srch_force_log_rotate",
 	[SCOUTFS_TRIGGER_SRCH_MERGE_STOP_SAFE] = "srch_merge_stop_safe",
@@ -53,7 +51,6 @@ bool scoutfs_trigger_test_and_clear(struct super_block *sb, unsigned int t)
 	atomic_t *atom;
 	int old;
 	int mem;
-	bool fired;

 	BUG_ON(t >= SCOUTFS_TRIGGER_NR);
 	atom = &triggers->atomics[t];
@@ -67,12 +64,7 @@ bool scoutfs_trigger_test_and_clear(struct super_block *sb, unsigned int t)
 		mem = atomic_cmpxchg(atom, old, 0);
 	} while (mem && mem != old);

-	fired = !!mem;
-
-	if (fired)
-		trace_scoutfs_trigger_fired(sb, names[t]);
-
-	return fired;
+	return !!mem;
 }

 int scoutfs_setup_triggers(struct super_block *sb)
@@ -101,9 +93,13 @@ int scoutfs_setup_triggers(struct super_block *sb)
 		goto out;
 	}

-	for (i = 0; i < ARRAY_SIZE(triggers->atomics); i++)
-		debugfs_create_atomic_t(names[i], 0644, triggers->dir,
-					&triggers->atomics[i]);
+	for (i = 0; i < ARRAY_SIZE(triggers->atomics); i++) {
+		if (!debugfs_create_atomic_t(names[i], 0644, triggers->dir,
+					     &triggers->atomics[i])) {
+			ret = -ENOMEM;
+			goto out;
+		}
+	}

 	ret = 0;
 out:
--- a/kmod/src/triggers.h
+++ b/kmod/src/triggers.h
@@ -3,7 +3,6 @@

 enum scoutfs_trigger {
 	SCOUTFS_TRIGGER_BLOCK_REMOVE_STALE,
-	SCOUTFS_TRIGGER_LOG_MERGE_FORCE_FINALIZE_OURS,
 	SCOUTFS_TRIGGER_SRCH_COMPACT_LOGS_PAD_SAFE,
 	SCOUTFS_TRIGGER_SRCH_FORCE_LOG_ROTATE,
 	SCOUTFS_TRIGGER_SRCH_MERGE_STOP_SAFE,
--- a/kmod/src/tseq.c
+++ b/kmod/src/tseq.c
@@ -183,13 +183,6 @@ static void *scoutfs_tseq_seq_next(struct seq_file *m, void *v, loff_t *pos)
 	ent = tseq_rb_next(ent);
 	if (ent)
 		*pos = ent->pos;
-	else
-		/*
-		 * once we hit the end, *pos is never used, but it has to
-		 * be updated to avoid an error in bpf_seq_read()
-		 */
-		(*pos)++;
-
 	return ent;
 }

--- a/kmod/src/wkic.c
+++ b/kmod/src/wkic.c
@@ -1113,7 +1113,7 @@ int scoutfs_wkic_setup(struct super_block *sb)

 	winf->sb = sb;
 	KC_INIT_SHRINKER_FUNCS(&winf->shrinker, wkic_shrink_count, wkic_shrink_scan);
-	KC_REGISTER_SHRINKER(&winf->shrinker, "scoutfs-weak_item:" SCSBF, SCSB_ARGS(sb));
+	KC_REGISTER_SHRINKER(&winf->shrinker);

 	sbi->wkic_info = winf;
 	return 0;
--- a/kmod/src/xattr.c
+++ b/kmod/src/xattr.c
@@ -742,7 +742,7 @@ int scoutfs_xattr_set_locked(struct inode *inode, const char *name, size_t name_
 	int ret;
 	int err;

-	trace_scoutfs_xattr_set(sb, ino, name_len, value, size, flags);
+	trace_scoutfs_xattr_set(sb, name_len, value, size, flags);

 	if (WARN_ON_ONCE(tgs->totl && tgs->indx) ||
 	    WARN_ON_ONCE((tgs->totl | tgs->indx) && !tag_lock))
@@ -1026,9 +1026,7 @@ static int scoutfs_xattr_get_handler

 static int scoutfs_xattr_set_handler
 #ifdef KC_XATTR_STRUCT_XATTR_HANDLER
-		(const struct xattr_handler *handler,
-		 KC_VFS_NS_DEF
-		 struct dentry *dentry,
+		(const struct xattr_handler *handler, struct dentry *dentry,
 		 struct inode *inode, const char *name, const void *value,
 		 size_t size, int flags)
 {
--- a/tests/.gitignore
+++ b/tests/.gitignore
@@ -10,5 +10,3 @@ src/stage_tmpfile
 src/create_xattr_loop
 src/o_tmpfile_umask
 src/o_tmpfile_linkat
-src/mmap_stress
-src/mmap_validate
--- a/tests/.xfstests-branch
+++ b/tests/.xfstests-branch
@@ -1 +0,0 @@
-v2022.05.01-2-g787cd20
--- a/tests/Makefile
+++ b/tests/Makefile
@@ -13,9 +13,7 @@ BIN := src/createmany			\
 	src/create_xattr_loop		\
 	src/fragmented_data_extents	\
 	src/o_tmpfile_umask		\
-	src/o_tmpfile_linkat		\
-	src/mmap_stress			\
-	src/mmap_validate
+	src/o_tmpfile_linkat

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

@@ -25,10 +23,8 @@ ifneq ($(DEPS),)
 -include $(DEPS)
 endif

-src/mmap_stress: LIBS+=-lpthread
-
 $(BIN): %: %.c Makefile
-	gcc $(CFLAGS) -MD -MP -MF $*.d $< -o $@ $(LIBS)
+	gcc $(CFLAGS) -MD -MP -MF $*.d $< -o $@

 .PHONY: clean
 clean:
--- a/tests/README.md
+++ b/tests/README.md
@@ -117,7 +117,6 @@ used during the test.
 | T\_NR\_MOUNTS    | number of mounts     | -n              | 3                 |
 | T\_O[0-9]        | mount options        | created per run | -o server\_addr=  |
 | T\_QUORUM        | quorum count         | -q              | 2                 |
-| T\_EXTRA         | per-test file dir    | revision ctled  | tests/extra/t     |
 | T\_TMP           | per-test tmp prefix  | made for test   | results/tmp/t/tmp |
 | T\_TMPDIR        | per-test tmp dir dir | made for test   | results/tmp/t     |

--- a/tests/extra/xfstests/expected-results
+++ b/tests/extra/xfstests/expected-results
@@ -1,882 +0,0 @@
-Ran:
-generic/001
-generic/002
-generic/004
-generic/005
-generic/006
-generic/007
-generic/008
-generic/009
-generic/011
-generic/012
-generic/013
-generic/014
-generic/015
-generic/016
-generic/018
-generic/020
-generic/021
-generic/022
-generic/023
-generic/024
-generic/025
-generic/026
-generic/028
-generic/029
-generic/030
-generic/031
-generic/032
-generic/033
-generic/034
-generic/035
-generic/037
-generic/039
-generic/040
-generic/041
-generic/050
-generic/052
-generic/053
-generic/056
-generic/057
-generic/058
-generic/059
-generic/060
-generic/061
-generic/062
-generic/063
-generic/064
-generic/065
-generic/066
-generic/067
-generic/069
-generic/070
-generic/071
-generic/073
-generic/076
-generic/078
-generic/079
-generic/080
-generic/081
-generic/082
-generic/084
-generic/086
-generic/087
-generic/088
-generic/090
-generic/091
-generic/092
-generic/094
-generic/096
-generic/097
-generic/098
-generic/099
-generic/101
-generic/104
-generic/105
-generic/106
-generic/107
-generic/110
-generic/111
-generic/113
-generic/114
-generic/115
-generic/116
-generic/117
-generic/118
-generic/119
-generic/120
-generic/121
-generic/122
-generic/123
-generic/124
-generic/126
-generic/128
-generic/129
-generic/130
-generic/131
-generic/134
-generic/135
-generic/136
-generic/138
-generic/139
-generic/140
-generic/141
-generic/142
-generic/143
-generic/144
-generic/145
-generic/146
-generic/147
-generic/148
-generic/149
-generic/150
-generic/151
-generic/152
-generic/153
-generic/154
-generic/155
-generic/156
-generic/157
-generic/158
-generic/159
-generic/160
-generic/161
-generic/162
-generic/163
-generic/169
-generic/171
-generic/172
-generic/173
-generic/174
-generic/177
-generic/178
-generic/179
-generic/180
-generic/181
-generic/182
-generic/183
-generic/184
-generic/185
-generic/188
-generic/189
-generic/190
-generic/191
-generic/193
-generic/194
-generic/195
-generic/196
-generic/197
-generic/198
-generic/199
-generic/200
-generic/201
-generic/202
-generic/203
-generic/205
-generic/206
-generic/207
-generic/210
-generic/211
-generic/212
-generic/214
-generic/215
-generic/216
-generic/217
-generic/218
-generic/219
-generic/220
-generic/221
-generic/222
-generic/223
-generic/225
-generic/227
-generic/228
-generic/229
-generic/230
-generic/235
-generic/236
-generic/237
-generic/238
-generic/240
-generic/244
-generic/245
-generic/246
-generic/247
-generic/248
-generic/249
-generic/250
-generic/252
-generic/253
-generic/254
-generic/255
-generic/256
-generic/257
-generic/258
-generic/259
-generic/260
-generic/261
-generic/262
-generic/263
-generic/264
-generic/265
-generic/266
-generic/267
-generic/268
-generic/271
-generic/272
-generic/276
-generic/277
-generic/278
-generic/279
-generic/281
-generic/282
-generic/283
-generic/284
-generic/286
-generic/287
-generic/288
-generic/289
-generic/290
-generic/291
-generic/292
-generic/293
-generic/294
-generic/295
-generic/296
-generic/301
-generic/302
-generic/303
-generic/304
-generic/305
-generic/306
-generic/307
-generic/308
-generic/309
-generic/312
-generic/313
-generic/314
-generic/315
-generic/316
-generic/317
-generic/319
-generic/322
-generic/324
-generic/325
-generic/326
-generic/327
-generic/328
-generic/329
-generic/330
-generic/331
-generic/332
-generic/335
-generic/336
-generic/337
-generic/341
-generic/342
-generic/343
-generic/346
-generic/348
-generic/353
-generic/355
-generic/358
-generic/359
-generic/360
-generic/361
-generic/362
-generic/363
-generic/364
-generic/365
-generic/366
-generic/367
-generic/368
-generic/369
-generic/370
-generic/371
-generic/372
-generic/373
-generic/374
-generic/375
-generic/376
-generic/377
-generic/378
-generic/379
-generic/380
-generic/381
-generic/382
-generic/383
-generic/384
-generic/385
-generic/386
-generic/389
-generic/391
-generic/392
-generic/393
-generic/394
-generic/395
-generic/396
-generic/397
-generic/398
-generic/400
-generic/401
-generic/402
-generic/403
-generic/404
-generic/406
-generic/407
-generic/408
-generic/412
-generic/413
-generic/414
-generic/417
-generic/419
-generic/420
-generic/421
-generic/422
-generic/424
-generic/425
-generic/426
-generic/427
-generic/428
-generic/436
-generic/437
-generic/439
-generic/440
-generic/443
-generic/445
-generic/446
-generic/448
-generic/449
-generic/450
-generic/451
-generic/452
-generic/453
-generic/454
-generic/456
-generic/458
-generic/460
-generic/462
-generic/463
-generic/465
-generic/466
-generic/468
-generic/469
-generic/470
-generic/471
-generic/474
-generic/477
-generic/478
-generic/479
-generic/480
-generic/481
-generic/483
-generic/485
-generic/486
-generic/487
-generic/488
-generic/489
-generic/490
-generic/491
-generic/492
-generic/498
-generic/499
-generic/501
-generic/502
-generic/503
-generic/504
-generic/505
-generic/506
-generic/507
-generic/508
-generic/509
-generic/510
-generic/511
-generic/512
-generic/513
-generic/514
-generic/515
-generic/516
-generic/517
-generic/518
-generic/519
-generic/520
-generic/523
-generic/524
-generic/525
-generic/526
-generic/527
-generic/528
-generic/529
-generic/530
-generic/531
-generic/533
-generic/534
-generic/535
-generic/536
-generic/537
-generic/538
-generic/539
-generic/540
-generic/541
-generic/542
-generic/543
-generic/544
-generic/545
-generic/546
-generic/547
-generic/548
-generic/549
-generic/550
-generic/552
-generic/553
-generic/555
-generic/556
-generic/557
-generic/566
-generic/567
-generic/571
-generic/572
-generic/573
-generic/574
-generic/575
-generic/576
-generic/577
-generic/578
-generic/580
-generic/581
-generic/582
-generic/583
-generic/584
-generic/586
-generic/587
-generic/588
-generic/591
-generic/592
-generic/593
-generic/594
-generic/595
-generic/596
-generic/597
-generic/598
-generic/599
-generic/600
-generic/601
-generic/602
-generic/603
-generic/604
-generic/605
-generic/606
-generic/607
-generic/608
-generic/609
-generic/610
-generic/611
-generic/612
-generic/613
-generic/614
-generic/618
-generic/621
-generic/623
-generic/624
-generic/625
-generic/626
-generic/628
-generic/629
-generic/630
-generic/632
-generic/634
-generic/635
-generic/637
-generic/638
-generic/639
-generic/640
-generic/644
-generic/645
-generic/646
-generic/647
-generic/651
-generic/652
-generic/653
-generic/654
-generic/655
-generic/657
-generic/658
-generic/659
-generic/660
-generic/661
-generic/662
-generic/663
-generic/664
-generic/665
-generic/666
-generic/667
-generic/668
-generic/669
-generic/673
-generic/674
-generic/675
-generic/676
-generic/677
-generic/678
-generic/679
-generic/680
-generic/681
-generic/682
-generic/683
-generic/684
-generic/685
-generic/686
-generic/687
-generic/688
-generic/689
-shared/002
-shared/032
-Not
-run:
-generic/008
-generic/009
-generic/012
-generic/015
-generic/016
-generic/018
-generic/021
-generic/022
-generic/025
-generic/026
-generic/031
-generic/033
-generic/050
-generic/052
-generic/058
-generic/059
-generic/060
-generic/061
-generic/063
-generic/064
-generic/078
-generic/079
-generic/081
-generic/082
-generic/091
-generic/094
-generic/096
-generic/110
-generic/111
-generic/113
-generic/114
-generic/115
-generic/116
-generic/118
-generic/119
-generic/121
-generic/122
-generic/123
-generic/128
-generic/130
-generic/134
-generic/135
-generic/136
-generic/138
-generic/139
-generic/140
-generic/142
-generic/143
-generic/144
-generic/145
-generic/146
-generic/147
-generic/148
-generic/149
-generic/150
-generic/151
-generic/152
-generic/153
-generic/154
-generic/155
-generic/156
-generic/157
-generic/158
-generic/159
-generic/160
-generic/161
-generic/162
-generic/163
-generic/171
-generic/172
-generic/173
-generic/174
-generic/177
-generic/178
-generic/179
-generic/180
-generic/181
-generic/182
-generic/183
-generic/185
-generic/188
-generic/189
-generic/190
-generic/191
-generic/193
-generic/194
-generic/195
-generic/196
-generic/197
-generic/198
-generic/199
-generic/200
-generic/201
-generic/202
-generic/203
-generic/205
-generic/206
-generic/207
-generic/210
-generic/211
-generic/212
-generic/214
-generic/216
-generic/217
-generic/218
-generic/219
-generic/220
-generic/222
-generic/223
-generic/225
-generic/227
-generic/229
-generic/230
-generic/235
-generic/238
-generic/240
-generic/244
-generic/250
-generic/252
-generic/253
-generic/254
-generic/255
-generic/256
-generic/259
-generic/260
-generic/261
-generic/262
-generic/263
-generic/264
-generic/265
-generic/266
-generic/267
-generic/268
-generic/271
-generic/272
-generic/276
-generic/277
-generic/278
-generic/279
-generic/281
-generic/282
-generic/283
-generic/284
-generic/287
-generic/288
-generic/289
-generic/290
-generic/291
-generic/292
-generic/293
-generic/295
-generic/296
-generic/301
-generic/302
-generic/303
-generic/304
-generic/305
-generic/312
-generic/314
-generic/316
-generic/317
-generic/324
-generic/326
-generic/327
-generic/328
-generic/329
-generic/330
-generic/331
-generic/332
-generic/353
-generic/355
-generic/358
-generic/359
-generic/361
-generic/362
-generic/363
-generic/364
-generic/365
-generic/366
-generic/367
-generic/368
-generic/369
-generic/370
-generic/371
-generic/372
-generic/373
-generic/374
-generic/378
-generic/379
-generic/380
-generic/381
-generic/382
-generic/383
-generic/384
-generic/385
-generic/386
-generic/391
-generic/392
-generic/395
-generic/396
-generic/397
-generic/398
-generic/400
-generic/402
-generic/404
-generic/406
-generic/407
-generic/408
-generic/412
-generic/413
-generic/414
-generic/417
-generic/419
-generic/420
-generic/421
-generic/422
-generic/424
-generic/425
-generic/427
-generic/439
-generic/440
-generic/446
-generic/449
-generic/450
-generic/451
-generic/453
-generic/454
-generic/456
-generic/458
-generic/462
-generic/463
-generic/465
-generic/466
-generic/468
-generic/469
-generic/470
-generic/471
-generic/474
-generic/485
-generic/487
-generic/488
-generic/491
-generic/492
-generic/499
-generic/501
-generic/503
-generic/505
-generic/506
-generic/507
-generic/508
-generic/511
-generic/513
-generic/514
-generic/515
-generic/516
-generic/517
-generic/518
-generic/519
-generic/520
-generic/528
-generic/530
-generic/536
-generic/537
-generic/538
-generic/539
-generic/540
-generic/541
-generic/542
-generic/543
-generic/544
-generic/545
-generic/546
-generic/548
-generic/549
-generic/550
-generic/552
-generic/553
-generic/555
-generic/556
-generic/566
-generic/567
-generic/572
-generic/573
-generic/574
-generic/575
-generic/576
-generic/577
-generic/578
-generic/580
-generic/581
-generic/582
-generic/583
-generic/584
-generic/586
-generic/587
-generic/588
-generic/591
-generic/592
-generic/593
-generic/594
-generic/595
-generic/596
-generic/597
-generic/598
-generic/599
-generic/600
-generic/601
-generic/602
-generic/603
-generic/605
-generic/606
-generic/607
-generic/608
-generic/609
-generic/610
-generic/612
-generic/613
-generic/621
-generic/623
-generic/624
-generic/625
-generic/626
-generic/628
-generic/629
-generic/630
-generic/635
-generic/644
-generic/645
-generic/646
-generic/647
-generic/651
-generic/652
-generic/653
-generic/654
-generic/655
-generic/657
-generic/658
-generic/659
-generic/660
-generic/661
-generic/662
-generic/663
-generic/664
-generic/665
-generic/666
-generic/667
-generic/668
-generic/669
-generic/673
-generic/674
-generic/675
-generic/677
-generic/678
-generic/679
-generic/680
-generic/681
-generic/682
-generic/683
-generic/684
-generic/685
-generic/686
-generic/687
-generic/688
-generic/689
-shared/002
-shared/032
-Passed all 512 tests
--- a/tests/extra/xfstests/local.exclude
+++ b/tests/extra/xfstests/local.exclude
@@ -1,44 +0,0 @@
-generic/003	# missing atime update in buffered read
-generic/075	# file content mismatch failures (fds, etc)
-generic/103	# enospc causes trans commit failures
-generic/108	# mount fails on failing device?
-generic/112	# file content mismatch failures (fds, etc)
-generic/213	# enospc causes trans commit failures
-generic/318	# can't support user namespaces until v5.11
-generic/321	# requires selinux enabled for '+' in ls?
-generic/338	# BUG_ON update inode error handling
-generic/347	# _dmthin_mount doesn't work?
-generic/356	# swap
-generic/357	# swap
-generic/409	# bind mounts not scripted yet
-generic/410	# bind mounts not scripted yet
-generic/411	# bind mounts not scripted yet
-generic/423	# symlink inode size is strlen() + 1 on scoutfs
-generic/430	# xfs_io copy_range missing in el7
-generic/431	# xfs_io copy_range missing in el7
-generic/432	# xfs_io copy_range missing in el7
-generic/433	# xfs_io copy_range missing in el7
-generic/434	# xfs_io copy_range missing in el7
-generic/441	# dm-mapper
-generic/444	# el9's posix_acl_update_mode is buggy ?
-generic/467	# open_by_handle ESTALE
-generic/472	# swap
-generic/484	# dm-mapper
-generic/493	# swap
-generic/494	# swap
-generic/495	# swap
-generic/496	# swap
-generic/497	# swap
-generic/532	# xfs_io statx attrib_mask missing in el7
-generic/554	# swap
-generic/563	# cgroup+loopdev
-generic/564	# xfs_io copy_range missing in el7
-generic/565	# xfs_io copy_range missing in el7
-generic/568	# falloc not resulting in block count increase
-generic/569	# swap
-generic/570	# swap
-generic/620	# dm-hugedisk
-generic/633	# id-mapped mounts missing in el7
-generic/636	# swap
-generic/641	# swap
-generic/643	# swap
--- a/tests/fenced-local-force-unmount.sh
+++ b/tests/fenced-local-force-unmount.sh
@@ -8,33 +8,36 @@

 echo "$0 running rid '$SCOUTFS_FENCED_REQ_RID' ip '$SCOUTFS_FENCED_REQ_IP' args '$@'"

-echo_fail() {
-	echo "$@" >&2
+log() {
+	echo "$@" > /dev/stderr
 	exit 1
 }

-# silence error messages
-quiet_cat()
-{
-	cat "$@" 2>/dev/null
+echo_fail() {
+	echo "$@" > /dev/stderr
+	exit 1
 }

 rid="$SCOUTFS_FENCED_REQ_RID"

-shopt -s nullglob
 for fs in /sys/fs/scoutfs/*; do
-	fs_rid="$(quiet_cat $fs/rid)"
-	nr="$(quiet_cat $fs/data_device_maj_min)"
-	[ ! -d "$fs" -o "$fs_rid" != "$rid" ] && continue
+	[ ! -d "$fs" ] && continue

-	mnt=$(findmnt -l -n -t scoutfs -o TARGET -S $nr)
-	[ -z "$mnt" ] && continue
-
-	if ! umount -qf "$mnt"; then
-		if [ -d "$fs" ]; then
-			echo_fail "umount -qf $mnt failed"
-		fi
+	fs_rid="$(cat $fs/rid)" || \
+		echo_fail "failed to get rid in $fs"
+	if [ "$fs_rid" != "$rid" ]; then
+		continue
 	fi
+
+	nr="$(cat $fs/data_device_maj_min)" || \
+		echo_fail "failed to get data device major:minor in $fs"
+
+	mnts=$(findmnt -l -n -t scoutfs -o TARGET -S $nr) || \
+		echo_fail "findmnt -t scoutfs -S $nr failed"
+	for mnt in $mnts; do
+		umount -f "$mnt" || \
+			echo_fail "umout -f $mnt failed"
+	done
 done

 exit 0
--- a/tests/funcs/exec.sh
+++ b/tests/funcs/exec.sh
@@ -7,9 +7,8 @@ t_status_msg()
 export T_PASS_STATUS=100
 export T_SKIP_STATUS=101
 export T_FAIL_STATUS=102
-export T_SKIP_PERMITTED_STATUS=103
 export T_FIRST_STATUS="$T_PASS_STATUS"
-export T_LAST_STATUS="$T_SKIP_PERMITTED_STATUS"
+export T_LAST_STATUS="$T_FAIL_STATUS"

 t_pass()
 {
@@ -22,17 +21,6 @@ t_skip()
 	exit $T_SKIP_STATUS
 }

-#
-# This exit code is *reserved* for tests that are up-front never going to work
-# in certain cases. This should be expressly documented per-case and made
-# abundantly clear before merging. The test itself should document its case.
-#
-t_skip_permitted()
-{
-	t_status_msg "$@"
-	exit $T_SKIP_PERMITTED_STATUS
-}
-
 t_fail()
 {
 	t_status_msg "$@"
@@ -64,37 +52,19 @@ t_rc()
 }

 #
-# As run, stdout/err are redirected to a file that will be compared with
-# the stored expected golden output of the test.  This redirects
-# stdout/err in the script to stdout of the invoking run-test.  It's
-# intended to give visible output of tests without being included in the
-# golden output.
+# redirect test output back to the output of the invoking script intead
+# of the compared output.
 #
-# (see the goofy "exec" fd manipulation in the main run-tests as it runs
-# each test)
-#
-t_stdout_invoked()
+t_restore_output()
 {
 	exec >&6 2>&1
 }

 #
-# This undoes t_stdout_invokved, returning the test's stdout/err to the
-# output file as it was when it was launched.
+# redirect a command's output back to the compared output after the
+# test has restored its output
 #
-t_stdout_compare()
+t_compare_output()
 {
-	exec >&7 2>&1
-}
-
-#
-# usually bash prints an annoying output message when jobs
-# are killed.  We can avoid that by redirecting stderr for
-# the bash process when it reaps the jobs that are killed.
-#
-t_silent_kill() {
-	exec {ERR}>&2 2>/dev/null
-	kill "$@"
-	wait "$@"
-	exec 2>&$ERR {ERR}>&-
+	"$@" >&7 2>&1
 }
--- a/tests/funcs/filter.sh
+++ b/tests/funcs/filter.sh
@@ -121,7 +121,6 @@ t_filter_dmesg()

 	# in debugging kernels we can slow things down a bit
 	re="$re|hrtimer: interrupt took .*"
-	re="$re|clocksource: Long readout interval"

 	# fencing tests force unmounts and trigger timeouts
 	re="$re|scoutfs .* forcing unmount"
@@ -141,38 +140,17 @@ t_filter_dmesg()
 	re="$re|scoutfs .* error.*server failed to bind to.*"
 	re="$re|scoutfs .* critical transaction commit failure.*"

-	# ENOLINK (-67) indicates an expected forced unmount error
-	re="$re|scoutfs .* error -67 .*"
-
 	# change-devices causes loop device resizing
 	re="$re|loop: module loaded"
 	re="$re|loop[0-9].* detected capacity change from.*"
-	re="$re|dm-[0-9].* detected capacity change from.*"

 	# ignore systemd-journal rotating
 	re="$re|systemd-journald.*"

-	# process accounting can be noisy
-	re="$re|Process accounting resumed.*"
-
 	# format vers back/compat tries bad mounts
 	re="$re|scoutfs .* error.*outside of supported version.*"
 	re="$re|scoutfs .* error.*could not get .*super.*"

-	# ignore "unsafe core pattern" when xfstests tries to disable cores"
-	re="$re|Unsafe core_pattern used with fs.suid_dumpable=2.*"
-	re="$re|Pipe handler or fully qualified core dump path required.*"
-	re="$re|Set kernel.core_pattern before fs.suid_dumpable.*"
-
-	# perf warning that it adjusted sample rate
-	re="$re|perf: interrupt took too long.*lowering kernel.perf_event_max_sample_rate.*"
-
-	# some ci test guests are unresponsive
-	re="$re|longest quorum heartbeat .* delay"
-
-	# creating block devices may trigger this
-	re="$re|block device autoloading is deprecated and will be removed."
-
 	egrep -v "($re)" | \
 		ignore_harmless_unwind_kasan_stack_oob
 }
--- a/tests/funcs/fs.sh
+++ b/tests/funcs/fs.sh
@@ -498,121 +498,3 @@ t_restore_all_sysfs_mount_options() {
 		t_set_sysfs_mount_option $i $name "${_saved_opts[$ind]}"
 	done
 }
-
-t_force_log_merge() {
-	local sv=$(t_server_nr)
-	local merges_started
-	local last_merges_started
-	local merges_completed
-	local last_merges_completed
-
-	while true; do
-		last_merges_started=$(t_counter log_merge_start $sv)
-		last_merges_completed=$(t_counter log_merge_complete $sv)
-
-		t_trigger_arm_silent log_merge_force_finalize_ours $sv
-
-		t_sync_seq_index
-
-		while test "$(t_trigger_get log_merge_force_finalize_ours $sv)" == "1"; do
-			sleep .5
-		done
-
-		merges_started=$(t_counter log_merge_start $sv)
-
-		if (( merges_started > last_merges_started )); then
-			merges_completed=$(t_counter log_merge_complete $sv)
-
-			while (( merges_completed == last_merges_completed )); do
-				sleep .5
-				merges_completed=$(t_counter log_merge_complete $sv)
-			done
-			break
-		fi
-	done
-}
-
-declare -A _last_scan
-t_get_orphan_scan_runs() {
-	local i
-
-	for i in $(t_fs_nrs); do
-		_last_scan[$i]=$(t_counter orphan_scan $i)
-	done
-}
-
-t_wait_for_orphan_scan_runs() {
-	local i
-	local scan
-
-	t_get_orphan_scan_runs
-
-	for i in $(t_fs_nrs); do
-		while true; do
-			scan=$(t_counter orphan_scan $i)
-			if (( scan != _last_scan[$i] )); then
-				break
-			fi
-			sleep .5
-		done
-	done
-}
-
-declare -A _last_empty
-t_get_orphan_scan_empty() {
-	local i
-
-	for i in $(t_fs_nrs); do
-		_last_empty[$i]=$(t_counter orphan_scan_empty $i)
-	done
-}
-
-t_wait_for_no_orphans() {
-	local i;
-	local working;
-	local empty;
-
-	t_get_orphan_scan_empty
-
-	while true; do
-		working=0
-
-		t_wait_for_orphan_scan_runs
-
-		for i in $(t_fs_nrs); do
-			empty=$(t_counter orphan_scan_empty $i)
-			if (( empty == _last_empty[$i] )); then
-				(( working++ ))
-			else
-				(( _last_empty[$i] = empty ))
-			fi
-		done
-
-		if (( working == 0 )); then
-			break
-		fi
-
-		sleep 1
-	done
-}
-
-#
-# Repeatedly run the arguments as a command, sleeping in between, until
-# it returns success.  The first argument is a relative timeout in
-# seconds.  The remaining arguments are the command and its arguments.
-#
-# If the timeout expires without the command returning 0 then the test
-# fails.
-#
-t_wait_until_timeout() {
-	local relative="$1"
-	local expire="$((SECONDS + relative))"
-	shift
-
-	while (( SECONDS < expire )); do
-		"$@" && return
-		sleep 1
-	done
-
-	t_fail "command failed for $relative sec: $@"
-}
--- a/tests/funcs/tap.sh
+++ b/tests/funcs/tap.sh
@@ -1,101 +0,0 @@
-
-#
-# Generate TAP format test results
-#
-
-t_tap_header()
-{
-	local runid=$1
-	local sequence=( $(echo $tests) )
-	local count=${#sequence[@]}
-
-	# avoid recreating the same TAP result over again - harness sets this
-	[[ -z "$runid" ]] && runid="*test*"
-
-	cat > $T_RESULTS/scoutfs.tap <<TAPEOF
-TAP version 14
-1..${count}
-#
-# TAP results for run ${runid}
-#
-# host/run info:
-#
-#   hostname: ${HOSTNAME}
-#   test start time: $(date --utc)
-#   uname -r: $(uname -r)
-#   scoutfs commit id: $(git describe --tags)
-#
-# sequence for this run:
-#
-TAPEOF
-
-	# Sequence
-	for t in ${tests}; do
-		 echo ${t/.sh/}
-	done | cat -n | expand | column -c 120 | expand | sed 's/^ /#/' >> $T_RESULTS/scoutfs.tap
-	echo "#" >> $T_RESULTS/scoutfs.tap
-}
-
-t_tap_progress()
-{
-(
-	local i=$(( testcount + 1 ))
-	local testname=$1
-	local result=$2
-
-	local stmsg=""
-	local diff=""
-	local dmsg=""
-
-	if [[ -s $T_RESULTS/tmp/${testname}/status.msg ]]; then
-		stmsg="1"
-	fi
-
-	if [[ -s "$T_RESULTS/tmp/${testname}/dmesg.new" ]]; then
-		dmsg="1"
-	fi
-
-	if ! cmp -s golden/${testname} $T_RESULTS/output/${testname}; then
-		diff="1"
-	fi
-
-	if [[ "${result}" == "100" ]] && [[ -z "${dmsg}" ]] && [[ -z "${diff}" ]]; then
-		echo "ok ${i} - ${testname}"
-	elif [[ "${result}" == "103" ]]; then
-		echo "ok ${i} - ${testname}"
-		echo "# ${testname} ** skipped - permitted **"
-	else
-		echo "not ok ${i} - ${testname}"
-
-		case ${result} in
-		101)
-			echo "# ${testname} ** skipped **"
-			;;
-		102)
-			echo "# ${testname} ** failed **"
-			;;
-		esac
-
-		if [[ -n "${stmsg}" ]]; then
-			echo "#"
-			echo "# status:"
-			echo "#"
-			cat $T_RESULTS/tmp/${testname}/status.msg | sed 's/^/# - /'
-		fi
-
-		if [[ -n "${diff}" ]]; then
-			echo "#"
-			echo "# diff:"
-			echo "#"
-			diff -u golden/${testname} $T_RESULTS/output/${testname} | expand | sed 's/^/#   /'
-		fi
-
-		if [[ -n "${dmsg}" ]]; then
-			echo "#"
-			echo "# dmesg:"
-			echo "#"
-			cat "$T_RESULTS/tmp/${testname}/dmesg.new" | sed 's/^/#   /'
-		fi
-	fi
-) >> $T_RESULTS/scoutfs.tap
-}
--- a/tests/golden/basic-posix-acl
+++ b/tests/golden/basic-posix-acl
@@ -41,7 +41,9 @@ group::r-x
 mask::rwx
 other::r-x

+bash: line 0: cd: dir-root: Permission denied
 Failed
+bash: line 0: cd: symlinkdir-root: Permission denied
 Failed
 # file: dir-root
 # owner: root
--- a/tests/golden/data-prealloc
+++ b/tests/golden/data-prealloc
@@ -1,29 +1,29 @@
 == initial writes smaller than prealloc grow to prealloc size
-/mnt/test/test/data-prealloc/file-1: extents: 7
-/mnt/test/test/data-prealloc/file-2: extents: 7
+/mnt/test/test/data-prealloc/file-1: 7 extents found
+/mnt/test/test/data-prealloc/file-2: 7 extents found
 == larger files get full prealloc extents
-/mnt/test/test/data-prealloc/file-1: extents: 9
-/mnt/test/test/data-prealloc/file-2: extents: 9
+/mnt/test/test/data-prealloc/file-1: 9 extents found
+/mnt/test/test/data-prealloc/file-2: 9 extents found
 == non-streaming writes with contig have per-block extents
-/mnt/test/test/data-prealloc/file-1: extents: 32
-/mnt/test/test/data-prealloc/file-2: extents: 32
+/mnt/test/test/data-prealloc/file-1: 32 extents found
+/mnt/test/test/data-prealloc/file-2: 32 extents found
 == 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: 4 extents found
+/mnt/test/test/data-prealloc/file-2: 4 extents found
+/mnt/test/test/data-prealloc/file-1: 4 extents found
+/mnt/test/test/data-prealloc/file-2: 4 extents found
 == 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
-/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: 4 extents found
+/mnt/test/test/data-prealloc/file-2: 4 extents found
+/mnt/test/test/data-prealloc/file-1: 4 extents found
+/mnt/test/test/data-prealloc/file-2: 4 extents found
 == 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: 3
-/mnt/test/test/data-prealloc/file-2: extents: 3
+/mnt/test/test/data-prealloc/file-1: 5 extents found
+/mnt/test/test/data-prealloc/file-2: 5 extents found
+/mnt/test/test/data-prealloc/file-1: 5 extents found
+/mnt/test/test/data-prealloc/file-2: 5 extents found
+/mnt/test/test/data-prealloc/file-1: 3 extents found
+/mnt/test/test/data-prealloc/file-2: 3 extents found
 == block writes into region allocs hole
 wrote blk 24
 wrote blk 32
--- a/tests/golden/inode-deletion
+++ b/tests/golden/inode-deletion
@@ -17,7 +17,7 @@ ino not found in dseq index
 mount 0 contents after mount 1 rm: contents
 ino found in dseq index
 ino found in dseq index
-stat: cannot stat '/mnt/test/test/inode-deletion/badfile': No such file or directory
+stat: cannot stat '/mnt/test/test/inode-deletion/file': No such file or directory
 ino not found in dseq index
 ino not found in dseq index
 == lots of deletions use one open map
--- a/tests/golden/large-fragmented-free
+++ b/tests/golden/large-fragmented-free
@@ -1,3 +1,4 @@
+== setting longer hung task timeout
 == creating fragmented extents
 == unlink file with moved extents to free extents per block
 == cleanup
--- a/tests/golden/lock-shrink-read-race
+++ b/tests/golden/lock-shrink-read-race
@@ -1,2 +0,0 @@
-=== setup
-=== spin reading and shrinking
--- a/tests/golden/mmap
+++ b/tests/golden/mmap
@@ -1,27 +0,0 @@
-== mmap_stress
-thread 0 complete
-thread 1 complete
-thread 2 complete
-thread 3 complete
-thread 4 complete
-== basic mmap/read/write consistency checks
-== mmap read from offline extent
-0: offset: 0 length: 2 flags: O.L
-extents: 1
-1
-00000200:  ea ea ea ea ea ea ea ea ea ea ea ea ea ea ea ea  ................
-0
-0: offset: 0 length: 2 flags: ..L
-extents: 1
-== mmap write to an offline extent
-0: offset: 0 length: 2 flags: O.L
-extents: 1
-1
-0
-0: offset: 0 length: 2 flags: ..L
-extents: 1
-00000000  ea ea ea ea ea ea ea ea  ea ea ea ea ea ea ea ea  |................|
-00000010  11 11 11 11 11 11 11 11  11 11 11 11 11 11 11 11  |................|
-00000020  ea ea ea ea ea ea ea ea  ea ea ea ea ea ea ea ea  |................|
-00000030
-== done
--- a/tests/golden/offline-extent-waiting
+++ b/tests/golden/offline-extent-waiting
@@ -49,7 +49,7 @@ offline wating should be empty:
 0
 == truncating does wait
 truncate should be waiting for first block:
-truncate should no longer be waiting:
+trunate should no longer be waiting:
 0
 == writing waits
 should be waiting for write
--- a/tests/golden/setattr_more
+++ b/tests/golden/setattr_more
@@ -22,8 +22,10 @@ scoutfs: setattr failed: Invalid argument (22)
 == large ctime is set
 1972-02-19 00:06:25.999999999 +0000
 == large offline extents are created
-0: offset: 0 0 length: 10007 flags: O.L
-extents: 1
+Filesystem type is: 554f4353
+File size of /mnt/test/test/setattr_more/file is 40988672 (10007 blocks of 4096 bytes)
+ ext:     logical_offset:        physical_offset: length:   expected: flags:
+   0:        0..   10006:          0..     10006:  10007:             unknown,eof
+/mnt/test/test/setattr_more/file: 1 extent found
 == correct offline extent length
 976563
-== omitting data_version should not fail
--- a/tests/golden/simple-readdir
+++ b/tests/golden/simple-readdir
@@ -1,97 +0,0 @@
-== create content
-== readdir all
-00000000: d_off: 0x00000001 d_reclen: 0x18 d_type: DT_DIR d_name: .
-00000001: d_off: 0x00000002 d_reclen: 0x18 d_type: DT_DIR d_name: ..
-00000002: d_off: 0x00000003 d_reclen: 0x18 d_type: DT_REG d_name: a
-00000003: d_off: 0x00000004 d_reclen: 0x20 d_type: DT_REG d_name: aaaaaaaa
-00000004: d_off: 0x00000005 d_reclen: 0x28 d_type: DT_REG d_name: aaaaaaaaaaaaaaa
-00000005: d_off: 0x00000006 d_reclen: 0x30 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaa
-00000006: d_off: 0x00000007 d_reclen: 0x38 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000007: d_off: 0x00000008 d_reclen: 0x38 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000008: d_off: 0x00000009 d_reclen: 0x40 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000009: d_off: 0x0000000a d_reclen: 0x48 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000000a: d_off: 0x0000000b d_reclen: 0x50 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000000b: d_off: 0x0000000c d_reclen: 0x58 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000000c: d_off: 0x0000000d d_reclen: 0x60 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000000d: d_off: 0x0000000e d_reclen: 0x68 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000000e: d_off: 0x0000000f d_reclen: 0x70 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000000f: d_off: 0x00000010 d_reclen: 0x70 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000010: d_off: 0x00000011 d_reclen: 0x78 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000011: d_off: 0x00000012 d_reclen: 0x80 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000012: d_off: 0x00000013 d_reclen: 0x88 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000013: d_off: 0x00000014 d_reclen: 0x90 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000014: d_off: 0x00000015 d_reclen: 0x98 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000015: d_off: 0x00000016 d_reclen: 0xa0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000016: d_off: 0x00000017 d_reclen: 0xa8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000017: d_off: 0x00000018 d_reclen: 0xa8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000018: d_off: 0x00000019 d_reclen: 0xb0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000019: d_off: 0x0000001a d_reclen: 0xb8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001a: d_off: 0x0000001b d_reclen: 0xc0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001b: d_off: 0x0000001c d_reclen: 0xc8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001c: d_off: 0x0000001d d_reclen: 0xd0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001d: d_off: 0x0000001e d_reclen: 0xd8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001e: d_off: 0x0000001f d_reclen: 0xe0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001f: d_off: 0x00000020 d_reclen: 0xe0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000020: d_off: 0x00000021 d_reclen: 0xe8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000021: d_off: 0x00000022 d_reclen: 0xf0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000022: d_off: 0x00000023 d_reclen: 0xf8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000023: d_off: 0x00000024 d_reclen: 0x100 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000024: d_off: 0x00000025 d_reclen: 0x108 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000025: d_off: 0x00000026 d_reclen: 0x110 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-== readdir offset
-00000014: d_off: 0x00000015 d_reclen: 0x98 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000015: d_off: 0x00000016 d_reclen: 0xa0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000016: d_off: 0x00000017 d_reclen: 0xa8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000017: d_off: 0x00000018 d_reclen: 0xa8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000018: d_off: 0x00000019 d_reclen: 0xb0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000019: d_off: 0x0000001a d_reclen: 0xb8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001a: d_off: 0x0000001b d_reclen: 0xc0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001b: d_off: 0x0000001c d_reclen: 0xc8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001c: d_off: 0x0000001d d_reclen: 0xd0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001d: d_off: 0x0000001e d_reclen: 0xd8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001e: d_off: 0x0000001f d_reclen: 0xe0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001f: d_off: 0x00000020 d_reclen: 0xe0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000020: d_off: 0x00000021 d_reclen: 0xe8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000021: d_off: 0x00000022 d_reclen: 0xf0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000022: d_off: 0x00000023 d_reclen: 0xf8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000023: d_off: 0x00000024 d_reclen: 0x100 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000024: d_off: 0x00000025 d_reclen: 0x108 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000025: d_off: 0x00000026 d_reclen: 0x110 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-== readdir len (bytes)
-00000000: d_off: 0x00000001 d_reclen: 0x18 d_type: DT_DIR d_name: .
-00000001: d_off: 0x00000002 d_reclen: 0x18 d_type: DT_DIR d_name: ..
-00000002: d_off: 0x00000003 d_reclen: 0x18 d_type: DT_REG d_name: a
-00000003: d_off: 0x00000004 d_reclen: 0x20 d_type: DT_REG d_name: aaaaaaaa
-00000004: d_off: 0x00000005 d_reclen: 0x28 d_type: DT_REG d_name: aaaaaaaaaaaaaaa
-00000005: d_off: 0x00000006 d_reclen: 0x30 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaa
-00000006: d_off: 0x00000007 d_reclen: 0x38 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-== introduce gap
-00000000: d_off: 0x00000001 d_reclen: 0x18 d_type: DT_DIR d_name: .
-00000001: d_off: 0x00000002 d_reclen: 0x18 d_type: DT_DIR d_name: ..
-00000002: d_off: 0x00000003 d_reclen: 0x18 d_type: DT_REG d_name: a
-00000003: d_off: 0x00000004 d_reclen: 0x20 d_type: DT_REG d_name: aaaaaaaa
-00000004: d_off: 0x00000005 d_reclen: 0x28 d_type: DT_REG d_name: aaaaaaaaaaaaaaa
-00000005: d_off: 0x00000006 d_reclen: 0x30 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaa
-00000006: d_off: 0x00000007 d_reclen: 0x38 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000007: d_off: 0x00000008 d_reclen: 0x38 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000008: d_off: 0x00000009 d_reclen: 0x40 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000009: d_off: 0x00000014 d_reclen: 0x48 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000014: d_off: 0x00000015 d_reclen: 0x98 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000015: d_off: 0x00000016 d_reclen: 0xa0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000016: d_off: 0x00000017 d_reclen: 0xa8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000017: d_off: 0x00000018 d_reclen: 0xa8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000018: d_off: 0x00000019 d_reclen: 0xb0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000019: d_off: 0x0000001a d_reclen: 0xb8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001a: d_off: 0x0000001b d_reclen: 0xc0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001b: d_off: 0x0000001c d_reclen: 0xc8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001c: d_off: 0x0000001d d_reclen: 0xd0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001d: d_off: 0x0000001e d_reclen: 0xd8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001e: d_off: 0x0000001f d_reclen: 0xe0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-0000001f: d_off: 0x00000020 d_reclen: 0xe0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000020: d_off: 0x00000021 d_reclen: 0xe8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000021: d_off: 0x00000022 d_reclen: 0xf0 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000022: d_off: 0x00000023 d_reclen: 0xf8 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000023: d_off: 0x00000024 d_reclen: 0x100 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000024: d_off: 0x00000025 d_reclen: 0x108 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-00000025: d_off: 0x00000026 d_reclen: 0x110 d_type: DT_REG d_name: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
-== cleanup
--- a/tests/golden/simple-staging
+++ b/tests/golden/simple-staging
@@ -1,9 +1,5 @@
 == create/release/stage single block file
-0: offset: 0 0 length: 1 flags: O.L
-extents: 1
 == create/release/stage larger file
-0: offset: 0 0 length: 4096 flags: O.L
-extents: 1
 == multiple release,drop_cache,stage cycles
 == release+stage shouldn't change stat, data seq or vers
 == stage does change meta_seq
@@ -11,22 +7,16 @@ extents: 1
 stage: must provide file version with --data-version
 Try `stage --help' or `stage --usage' for more information.
 == wrapped region fails
-stage returned -1, not 8192: error Invalid argument (22)
+stage returned -1, not 4096: error Invalid argument (22)
 scoutfs: stage failed: Input/output error (5)
 == non-block aligned offset fails
 stage returned -1, not 4095: error Invalid argument (22)
 scoutfs: stage failed: Input/output error (5)
-0: offset: 0 0 length: 1 flags: O.L
-extents: 1
 == non-block aligned len within block fails
 stage returned -1, not 1024: error Invalid argument (22)
 scoutfs: stage failed: Input/output error (5)
-0: offset: 0 0 length: 1 flags: O.L
-extents: 1
 == partial final block that writes to i_size does work
 == zero length stage doesn't bring blocks online
-0: offset: 0 0 length: 100 flags: O.L
-extents: 1
 == stage of non-regular file fails
 ioctl failed: Inappropriate ioctl for device (25)
 stage: must provide file version with --data-version
--- a/tests/golden/srch-safe-merge-pos
+++ b/tests/golden/srch-safe-merge-pos
@@ -1,7 +1,37 @@
 == initialize per-mount values
 == arm compaction triggers
+trigger srch_compact_logs_pad_safe armed: 1
+trigger srch_merge_stop_safe armed: 1
+trigger srch_compact_logs_pad_safe armed: 1
+trigger srch_merge_stop_safe armed: 1
+trigger srch_compact_logs_pad_safe armed: 1
+trigger srch_merge_stop_safe armed: 1
+trigger srch_compact_logs_pad_safe armed: 1
+trigger srch_merge_stop_safe armed: 1
+trigger srch_compact_logs_pad_safe armed: 1
+trigger srch_merge_stop_safe armed: 1
 == compact more often
 == create padded sorted inputs by forcing log rotation
+trigger srch_force_log_rotate armed: 1
+trigger srch_force_log_rotate armed: 1
+trigger srch_force_log_rotate armed: 1
+trigger srch_force_log_rotate armed: 1
+trigger srch_compact_logs_pad_safe armed: 1
+trigger srch_force_log_rotate armed: 1
+trigger srch_force_log_rotate armed: 1
+trigger srch_force_log_rotate armed: 1
+trigger srch_force_log_rotate armed: 1
+trigger srch_compact_logs_pad_safe armed: 1
+trigger srch_force_log_rotate armed: 1
+trigger srch_force_log_rotate armed: 1
+trigger srch_force_log_rotate armed: 1
+trigger srch_force_log_rotate armed: 1
+trigger srch_compact_logs_pad_safe armed: 1
+trigger srch_force_log_rotate armed: 1
+trigger srch_force_log_rotate armed: 1
+trigger srch_force_log_rotate armed: 1
+trigger srch_force_log_rotate armed: 1
+trigger srch_compact_logs_pad_safe armed: 1
 == compaction of padded should stop at safe
 == verify no compaction errors
 == cleanup
--- a/tests/golden/xfstests
+++ b/tests/golden/xfstests
@@ -0,0 +1,288 @@
+Ran:
+generic/001
+generic/002
+generic/004
+generic/005
+generic/006
+generic/007
+generic/011
+generic/013
+generic/014
+generic/020
+generic/023
+generic/024
+generic/028
+generic/032
+generic/034
+generic/035
+generic/037
+generic/039
+generic/040
+generic/041
+generic/053
+generic/056
+generic/057
+generic/062
+generic/065
+generic/066
+generic/067
+generic/069
+generic/070
+generic/071
+generic/073
+generic/076
+generic/084
+generic/086
+generic/087
+generic/088
+generic/090
+generic/092
+generic/098
+generic/101
+generic/104
+generic/105
+generic/106
+generic/107
+generic/117
+generic/124
+generic/129
+generic/131
+generic/169
+generic/184
+generic/221
+generic/228
+generic/236
+generic/237
+generic/245
+generic/249
+generic/257
+generic/258
+generic/286
+generic/294
+generic/306
+generic/307
+generic/308
+generic/309
+generic/313
+generic/315
+generic/319
+generic/322
+generic/335
+generic/336
+generic/337
+generic/341
+generic/342
+generic/343
+generic/348
+generic/360
+generic/375
+generic/376
+generic/377
+Not
+run:
+generic/008
+generic/009
+generic/012
+generic/015
+generic/016
+generic/018
+generic/021
+generic/022
+generic/025
+generic/026
+generic/031
+generic/033
+generic/050
+generic/052
+generic/058
+generic/059
+generic/060
+generic/061
+generic/063
+generic/064
+generic/078
+generic/079
+generic/081
+generic/082
+generic/091
+generic/094
+generic/096
+generic/110
+generic/111
+generic/113
+generic/114
+generic/115
+generic/116
+generic/118
+generic/119
+generic/121
+generic/122
+generic/123
+generic/128
+generic/130
+generic/134
+generic/135
+generic/136
+generic/138
+generic/139
+generic/140
+generic/142
+generic/143
+generic/144
+generic/145
+generic/146
+generic/147
+generic/148
+generic/149
+generic/150
+generic/151
+generic/152
+generic/153
+generic/154
+generic/155
+generic/156
+generic/157
+generic/158
+generic/159
+generic/160
+generic/161
+generic/162
+generic/163
+generic/171
+generic/172
+generic/173
+generic/174
+generic/177
+generic/178
+generic/179
+generic/180
+generic/181
+generic/182
+generic/183
+generic/185
+generic/188
+generic/189
+generic/190
+generic/191
+generic/193
+generic/194
+generic/195
+generic/196
+generic/197
+generic/198
+generic/199
+generic/200
+generic/201
+generic/202
+generic/203
+generic/205
+generic/206
+generic/207
+generic/210
+generic/211
+generic/212
+generic/214
+generic/216
+generic/217
+generic/218
+generic/219
+generic/220
+generic/222
+generic/223
+generic/225
+generic/227
+generic/229
+generic/230
+generic/235
+generic/238
+generic/240
+generic/244
+generic/250
+generic/252
+generic/253
+generic/254
+generic/255
+generic/256
+generic/259
+generic/260
+generic/261
+generic/262
+generic/263
+generic/264
+generic/265
+generic/266
+generic/267
+generic/268
+generic/271
+generic/272
+generic/276
+generic/277
+generic/278
+generic/279
+generic/281
+generic/282
+generic/283
+generic/284
+generic/287
+generic/288
+generic/289
+generic/290
+generic/291
+generic/292
+generic/293
+generic/295
+generic/296
+generic/301
+generic/302
+generic/303
+generic/304
+generic/305
+generic/312
+generic/314
+generic/316
+generic/317
+generic/324
+generic/326
+generic/327
+generic/328
+generic/329
+generic/330
+generic/331
+generic/332
+generic/353
+generic/355
+generic/356
+generic/357
+generic/358
+generic/359
+generic/361
+generic/362
+generic/363
+generic/364
+generic/365
+generic/366
+generic/367
+generic/368
+generic/369
+generic/370
+generic/371
+generic/372
+generic/373
+generic/374
+generic/378
+generic/379
+generic/380
+generic/381
+generic/382
+generic/383
+generic/384
+generic/385
+generic/386
+shared/001
+shared/002
+shared/003
+shared/004
+shared/032
+shared/051
+shared/289
+Passed all 79 tests
--- a/tests/run-tests.sh
+++ b/tests/run-tests.sh
@@ -56,7 +56,6 @@ $(basename $0) options:
              | only tests matching will be run.  Can be provided multiple
              | times
    -i        | Force removing and inserting the built scoutfs.ko module.
-    -l <nr>   | Loop each test <nr> times while passing, last run counts.
    -M <file> | Specify the filesystem's meta data device path that contains
              | the file system to be tested.  Will be clobbered by -m mkfs.
    -m        | Run mkfs on the device before mounting and running
@@ -70,7 +69,6 @@ $(basename $0) options:
    -r <dir>  | Specify the directory in which to store results of
              | test runs.  The directory will be created if it doesn't
              | exist.  Previous results will be deleted as each test runs.
-    -R        | shuffle the test order randomly using shuf
    -s        | Skip git repo checkouts.
    -t        | Enabled trace events that match the given glob argument.
              | Multiple options enable multiple globbed events.
@@ -90,9 +88,7 @@ done

 # set some T_ defaults
 T_TRACE_DUMP="0"
-T_TRACE_PRINTK=""
-T_PORT_START="19700"
-T_LOOP_ITER="1"
+T_TRACE_PRINTK="0"

 # array declarations to be able to use array ops
 declare -a T_TRACE_GLOB
@@ -133,15 +129,6 @@ while true; do
 	-i)
 		T_INSMOD="1"
 		;;
-	-l)
-	        test -n "$2" || die "-l must have a nr iterations argument"
-		test "$2" -eq "$2" 2>/dev/null || die "-l <nr> argument must be an integer"
-		T_LOOP_ITER="$2"
-
-		# when looping, break after first failure
-		T_ABORT="1"
-		shift
-		;;
 	-M)
 	        test -n "$2" || die "-z must have meta device file argument"
 	        T_META_DEVICE="$2"
@@ -177,9 +164,6 @@ while true; do
 		T_RESULTS="$2"
 		shift
 		;;
-	-R)
-		T_SHUF="1"
-		;;
 	-s)
 	        T_SKIP_CHECKOUT="1"
 		;;
@@ -277,37 +261,13 @@ for e in T_META_DEVICE T_DATA_DEVICE T_EX_META_DEV T_EX_DATA_DEV T_KMOD T_RESULT
 	eval $e=\"$(readlink -f "${!e}")\"
 done

-# try and check ports, but not necessary
-T_TEST_PORT="$T_PORT_START"
-T_SCRATCH_PORT="$((T_PORT_START + 100))"
-T_DEV_PORT="$((T_PORT_START + 200))"
-read local_start local_end < /proc/sys/net/ipv4/ip_local_port_range
-if [ -n "$local_start" -a -n "$local_end" -a "$local_start" -lt "$local_end" ]; then
-	if [ ! "$T_DEV_PORT" -lt "$local_start" -a ! "$T_TEST_PORT" -gt "$local_end" ]; then
-		die "listening port range $T_TEST_PORT - $T_DEV_PORT is within local dynamic port range $local_start - $local_end in /proc/sys/net/ipv4/ip_local_port_range"
-	fi
-fi
-
-# permute sequence?
-T_SEQUENCE=sequence
-if [ -n "$T_SHUF" ]; then
-	msg "shuffling test order"
-	shuf sequence -o sequence.shuf
-	# keep xfstests at the end
-	if grep -q 'xfstests.sh' sequence.shuf ; then
-		sed -i '/xfstests.sh/d' sequence.shuf
-		echo "xfstests.sh" >> sequence.shuf
-	fi
-	T_SEQUENCE=sequence.shuf
-fi
-
 # include everything by default
 test -z "$T_INCLUDE" && T_INCLUDE="-e '.*'"
 # (quickly) exclude nothing by default
 test -z "$T_EXCLUDE" && T_EXCLUDE="-e '\Zx'"

 # eval to strip re ticks but not expand
-tests=$(grep -v "^#" $T_SEQUENCE |
+tests=$(grep -v "^#" sequence |
 	eval grep "$T_INCLUDE" | eval grep -v "$T_EXCLUDE")
 test -z "$tests" && \
 	die "no tests found by including $T_INCLUDE and excluding $T_EXCLUDE"
@@ -386,7 +346,7 @@ fi
 quo=""
 if [ -n "$T_MKFS" ]; then
 	for i in $(seq -0 $((T_QUORUM - 1))); do
-		quo="$quo -Q $i,127.0.0.1,$((T_TEST_PORT + i))"
+		quo="$quo -Q $i,127.0.0.1,$((42000 + i))"
 	done

 	msg "making new filesystem with $T_QUORUM quorum members"
@@ -402,44 +362,30 @@ if [ -n "$T_INSMOD" ]; then
 	cmd insmod "$T_MODULE"
 fi

-start_tracing() {
-	if [ -n "$T_TRACE_MULT" ]; then
-		orig_trace_size=1408
-		mult_trace_size=$((orig_trace_size * T_TRACE_MULT))
-		msg "increasing trace buffer size from $orig_trace_size KiB to $mult_trace_size KiB"
-		echo $mult_trace_size > /sys/kernel/debug/tracing/buffer_size_kb
-	fi
+if [ -n "$T_TRACE_MULT" ]; then
+	orig_trace_size=$(cat /sys/kernel/debug/tracing/buffer_size_kb)
+	mult_trace_size=$((orig_trace_size * T_TRACE_MULT))
+	msg "increasing trace buffer size from $orig_trace_size KiB to $mult_trace_size KiB"
+	echo $mult_trace_size > /sys/kernel/debug/tracing/buffer_size_kb
+fi

-	nr_globs=${#T_TRACE_GLOB[@]}
-	if [ $nr_globs -gt 0 ]; then
-		echo 0 > /sys/kernel/debug/tracing/events/scoutfs/enable
+nr_globs=${#T_TRACE_GLOB[@]}
+if [ $nr_globs -gt 0 ]; then
+	echo 0 > /sys/kernel/debug/tracing/events/scoutfs/enable

-		for g in "${T_TRACE_GLOB[@]}"; do
-			for e in /sys/kernel/debug/tracing/events/scoutfs/$g/enable; do
-				if test -w "$e"; then
-					echo 1 > "$e"
-				else
-					die "-t glob '$g' matched no scoutfs events"
-				fi
-			done
+	for g in "${T_TRACE_GLOB[@]}"; do
+		for e in /sys/kernel/debug/tracing/events/scoutfs/$g/enable; do
+			if test -w "$e"; then
+				echo 1 > "$e"
+			else
+				die "-t glob '$g' matched no scoutfs events"
+			fi
 		done
+	done

-		nr_events=$(cat /sys/kernel/debug/tracing/set_event | wc -l)
-		msg "enabled $nr_events trace events from $nr_globs -t globs"
-	fi
-}
-
-stop_tracing() {
-	if [ -n "$T_TRACE_GLOB" -o -n "$T_TRACE_PRINTK" ]; then
-		msg "saving traces and disabling tracing"
-		echo 0 > /sys/kernel/debug/tracing/events/scoutfs/enable
-		echo 0 > /sys/kernel/debug/tracing/options/trace_printk
-		cat /sys/kernel/debug/tracing/trace | gzip > "$T_RESULTS/traces.gz"
-		if [ -n "$orig_trace_size" ]; then
-			echo $orig_trace_size > /sys/kernel/debug/tracing/buffer_size_kb
-		fi
-	fi
-}
+	nr_events=$(cat /sys/kernel/debug/tracing/set_event | wc -l)
+	msg "enabled $nr_events trace events from $nr_globs -t globs"
+fi

 if [ -n "$T_TRACE_PRINTK" ]; then
 	echo "$T_TRACE_PRINTK" > /sys/kernel/debug/tracing/options/trace_printk
@@ -455,30 +401,6 @@ cmd grep .  /sys/kernel/debug/tracing/options/trace_printk \
 	    /sys/kernel/debug/tracing/buffer_size_kb \
 	    /proc/sys/kernel/ftrace_dump_on_oops

-# we can record pids to kill as we exit, we kill in reverse added order
-atexit_kill_pids=""
-add_atexit_kill_pid()
-{
-	atexit_kill_pids="$1 $atexit_kill_pids"
-}
-atexit_kill()
-{
-	local pid
-
-	# suppress bg function exited messages
-	exec {ERR}>&2 2>/dev/null
-
-	for pid in $atexit_kill_pids; do
-		if test -e "/proc/$pid/status" ; then
-			kill "$pid"
-			wait "$pid"
-		fi
-	done
-
-	exec 2>&$ERR {ERR}>&-
-}
-trap atexit_kill EXIT
-
 #
 # Build a fenced config that runs scripts out of the repository rather
 # than the default system directory
@@ -492,46 +414,26 @@ EOF
 export SCOUTFS_FENCED_CONFIG_FILE="$conf"
 T_FENCED_LOG="$T_RESULTS/fenced.log"

+#
+# Run the agent in the background, log its output, an kill it if we
+# exit
+#
+fenced_log()
+{
+	echo "[$(timestamp)] $*" >> "$T_FENCED_LOG"
+}
+fenced_pid=""
+kill_fenced()
+{
+	if test -n "$fenced_pid" -a -d "/proc/$fenced_pid" ; then
+		fenced_log "killing fenced pid $fenced_pid"
+		kill "$fenced_pid"
+	fi
+}
+trap kill_fenced EXIT
 $T_UTILS/fenced/scoutfs-fenced > "$T_FENCED_LOG" 2>&1 &
 fenced_pid=$!
-add_atexit_kill_pid $fenced_pid
-
-#
-# some critical failures will cause fs operations to hang.  We can watch
-# for evidence of them and cause the system to crash, at least.
-#
-crash_monitor()
-{
-	local bad=0
-
-	while sleep 1; do
-		if dmesg | grep -q "inserting extent.*overlaps existing"; then
-			echo "run-tests monitor saw overlapping extent message"
-			bad=1
-		fi
-
-		if dmesg | grep -q "error indicated by fence action" ; then
-			echo "run-tests monitor saw fence agent error message"
-			bad=1
-		fi
-
-		if [ ! -e "/proc/${fenced_pid}/status" ]; then
-			echo "run-tests monitor didn't see fenced pid $fenced_pid /proc dir"
-			bad=1
-		fi
-
-		if [ "$bad" != 0 ]; then
-			echo "run-tests monitor syncing and triggering crash"
-			# hail mary, the sync could well hang
-			(echo s > /proc/sysrq-trigger) &
-			sleep 5
-			echo c > /proc/sysrq-trigger
-			exit 1
-		fi
-	done
-}
-crash_monitor &
-add_atexit_kill_pid $!
+fenced_log "started fenced pid $fenced_pid in the background"

 # setup dm tables
 echo "0 $(blockdev --getsz $T_META_DEVICE) linear $T_META_DEVICE 0" > \
@@ -604,163 +506,143 @@ fi
 . funcs/filter.sh

 # give tests access to built binaries in src/, prefer over installed
-export PATH="$PWD/src:$PATH"
+PATH="$PWD/src:$PATH"

 msg "running tests"
 > "$T_RESULTS/skip.log"
 > "$T_RESULTS/fail.log"

-# generate a test ID to make sure we can de-duplicate TAP results in aggregation
-. funcs/tap.sh
-t_tap_header $(uuidgen)
-
-testcount=0
 passed=0
 skipped=0
 failed=0
-skipped_permitted=0
-for iter in $(seq 1 $T_LOOP_ITER); do
+for t in $tests; do
+	# tests has basenames from sequence, get path and name
+	t="tests/$t"
+	test_name=$(basename "$t" | sed -e 's/.sh$//')

-	start_tracing
+	# create a temporary dir and file path for the test
+	T_TMPDIR="$T_RESULTS/tmp/$test_name"
+	T_TMP="$T_TMPDIR/tmp"
+	cmd rm -rf "$T_TMPDIR"
+	cmd mkdir -p "$T_TMPDIR"

-	for t in $tests; do
-		# tests has basenames from sequence, get path and name
-		t="tests/$t"
-		test_name=$(basename "$t" | sed -e 's/.sh$//')
+	# create a test name dir in the fs
+	T_DS=""
+	for i in $(seq 0 $((T_NR_MOUNTS - 1))); do
+		dir="${T_M[$i]}/test/$test_name"

-		# get stats from previous pass
-		last="$T_RESULTS/last-passed-test-stats"
-		stats=$(grep -s "^$test_name " "$last" | cut -d " " -f 2-)
-		test -n "$stats" && stats="last: $stats"
-		printf "  %-30s $stats" "$test_name"
+		test $i == 0 && cmd mkdir -p "$dir"

-		# mark in dmesg as to what test we are running
-		echo "run scoutfs test $test_name" > /dev/kmsg
-
-		# let the test get at its extra files
-		T_EXTRA="$T_TESTS/extra/$test_name"
-
-		# create a temporary dir and file path for the test
-		T_TMPDIR="$T_RESULTS/tmp/$test_name"
-		T_TMP="$T_TMPDIR/tmp"
-		cmd rm -rf "$T_TMPDIR"
-		cmd mkdir -p "$T_TMPDIR"
-
-		# create a test name dir in the fs, clean up old data as needed
-		T_DS=""
-		for i in $(seq 0 $((T_NR_MOUNTS - 1))); do
-			dir="${T_M[$i]}/test/$test_name"
-
-			test $i == 0 && (
-				test -d "$dir" && cmd rm -rf "$dir"
-				cmd mkdir -p "$dir"
-			)
-
-			eval T_D$i=$dir
-			T_D[$i]=$dir
-			T_DS+="$dir "
-		done
-
-		# export all our T_ variables
-		for v in ${!T_*}; do
-			eval export $v
-		done
-
-		# prepare to compare output to golden output
-		test -e "$T_RESULTS/output" || cmd mkdir -p "$T_RESULTS/output"
-		out="$T_RESULTS/output/$test_name"
-		> "$T_TMPDIR/status.msg"
-		golden="golden/$test_name"
-
-		# record dmesg before
-		dmesg | t_filter_dmesg > "$T_TMPDIR/dmesg.before"
-
-		# give tests stdout and compared output on specific fds
-		exec 6>&1
-		exec 7>$out
-
-		# run the test with access to our functions
-		start_secs=$SECONDS
-		bash -c "for f in funcs/*.sh; do . \$f; done; . $t" >&7 2>&1
-		sts="$?"
-		log "test $t exited with status $sts"
-		stats="$((SECONDS - start_secs))s"
-
-		# close our weird descriptors
-		exec 6>&-
-		exec 7>&-
-
-		# compare output if the test returned passed status
-		if [ "$sts" == "$T_PASS_STATUS" ]; then
-			if [ ! -e "$golden" ]; then
-				message="no golden output"
-				sts=$T_FAIL_STATUS
-			elif ! cmp -s "$golden" "$out"; then 
-				message="output differs"
-				sts=$T_FAIL_STATUS
-				diff -u "$golden" "$out" >> "$T_RESULTS/fail.log"
-			fi
-		else
-			# get message from t_*() functions
-			message=$(cat "$T_TMPDIR/status.msg")
-		fi
-
-		# see if anything unexpected was added to dmesg
-		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"
-
-			if [ -s "$T_TMPDIR/dmesg.new" ]; then
-				message="unexpected messages in dmesg"
-				sts=$T_FAIL_STATUS
-				cat "$T_TMPDIR/dmesg.new" >> "$T_RESULTS/fail.log"
-			fi
-		fi
-
-		# record unknown exit status
-		if [ "$sts" -lt "$T_FIRST_STATUS" -o "$sts" -gt "$T_LAST_STATUS" ]; then
-			message="unknown status: $sts"
-			sts=$T_FAIL_STATUS
-		fi
-
-		# show and record the result of the test
-		if [ "$sts" == "$T_PASS_STATUS" ]; then
-			echo "  passed: $stats"
-			((passed++))
-			# save stats for passed test
-			grep -s -v "^$test_name " "$last" > "$last.tmp"
-			echo "$test_name $stats" >> "$last.tmp"
-			mv -f "$last.tmp" "$last"
-		elif [ "$sts" == "$T_SKIP_PERMITTED_STATUS" ]; then
-			echo "  [ skipped (permitted): $message ]"
-			echo "$test_name skipped (permitted) $message " >> "$T_RESULTS/skip.log"
-			((skipped_permitted++))
-		elif [ "$sts" == "$T_SKIP_STATUS" ]; then
-			echo "  [ skipped: $message ]"
-			echo "$test_name $message" >> "$T_RESULTS/skip.log"
-			((skipped++))
-		elif [ "$sts" == "$T_FAIL_STATUS" ]; then
-			echo "  [ failed: $message ]"
-			echo "$test_name $message" >> "$T_RESULTS/fail.log"
-			((failed++))
-
-			if [ -n "$T_ABORT" ]; then
-				stop_tracing
-				die "aborting after first failure"
-			fi
-		fi
-
-		# record results for TAP format output
-		t_tap_progress $test_name $sts
-		((testcount++))
+		eval T_D$i=$dir
+		T_D[$i]=$dir
+		T_DS+="$dir "
 	done

-	stop_tracing
+	# export all our T_ variables
+	for v in ${!T_*}; do
+		eval export $v
+	done
+	export PATH # give test access to scoutfs binary
+
+	# prepare to compare output to golden output
+	test -e "$T_RESULTS/output" || cmd mkdir -p "$T_RESULTS/output"
+	out="$T_RESULTS/output/$test_name"
+	> "$T_TMPDIR/status.msg"
+	golden="golden/$test_name"
+
+	# get stats from previous pass
+	last="$T_RESULTS/last-passed-test-stats"
+	stats=$(grep -s "^$test_name " "$last" | cut -d " " -f 2-)
+	test -n "$stats" && stats="last: $stats"
+
+	printf "  %-30s $stats" "$test_name"
+
+	# record dmesg before
+	dmesg | t_filter_dmesg > "$T_TMPDIR/dmesg.before"
+
+	# give tests stdout and compared output on specific fds
+	exec 6>&1
+	exec 7>$out
+
+	# run the test with access to our functions
+	start_secs=$SECONDS
+	bash -c "for f in funcs/*.sh; do . \$f; done; . $t" >&7 2>&1
+	sts="$?"
+	log "test $t exited with status $sts"
+	stats="$((SECONDS - start_secs))s"
+
+	# close our weird descriptors
+	exec 6>&-
+	exec 7>&-
+
+	# compare output if the test returned passed status
+	if [ "$sts" == "$T_PASS_STATUS" ]; then
+		if [ ! -e "$golden" ]; then
+			message="no golden output"
+			sts=$T_FAIL_STATUS
+		elif ! cmp -s "$golden" "$out"; then 
+			message="output differs"
+			sts=$T_FAIL_STATUS
+			diff -u "$golden" "$out" >> "$T_RESULTS/fail.log"
+		fi
+	else
+		# get message from t_*() functions
+		message=$(cat "$T_TMPDIR/status.msg")
+	fi
+
+	# see if anything unexpected was added to dmesg
+	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"
+
+		if [ -s "$T_TMPDIR/dmesg.new" ]; then
+			message="unexpected messages in dmesg"
+			sts=$T_FAIL_STATUS
+			cat "$T_TMPDIR/dmesg.new" >> "$T_RESULTS/fail.log"
+		fi
+	fi
+
+	# record unknown exit status
+	if [ "$sts" -lt "$T_FIRST_STATUS" -o "$sts" -gt "$T_LAST_STATUS" ]; then
+		message="unknown status: $sts"
+		sts=$T_FAIL_STATUS
+	fi
+
+	# show and record the result of the test
+	if [ "$sts" == "$T_PASS_STATUS" ]; then
+		echo "  passed: $stats"
+		((passed++))
+		# save stats for passed test
+		grep -s -v "^$test_name " "$last" > "$last.tmp"
+		echo "$test_name $stats" >> "$last.tmp"
+		mv -f "$last.tmp" "$last"
+	elif [ "$sts" == "$T_SKIP_STATUS" ]; then
+		echo "  [ skipped: $message ]"
+		echo "$test_name $message" >> "$T_RESULTS/skip.log"
+		((skipped++))
+	elif [ "$sts" == "$T_FAIL_STATUS" ]; then
+		echo "  [ failed: $message ]"
+		echo "$test_name $message" >> "$T_RESULTS/fail.log"
+		((failed++))
+
+		test -n "$T_ABORT" && die "aborting after first failure"
+	fi
 done

-msg "all tests run: $passed passed, $skipped skipped, $skipped_permitted skipped (permitted), $failed failed"
+msg "all tests run: $passed passed, $skipped skipped, $failed failed"
+
+
+if [ -n "$T_TRACE_GLOB" -o -n "$T_TRACE_PRINTK" ]; then
+	msg "saving traces and disabling tracing"
+	echo 0 > /sys/kernel/debug/tracing/events/scoutfs/enable
+	echo 0 > /sys/kernel/debug/tracing/options/trace_printk
+	cat /sys/kernel/debug/tracing/trace > "$T_RESULTS/traces"
+	if [ -n "$orig_trace_size" ]; then
+		echo $orig_trace_size > /sys/kernel/debug/tracing/buffer_size_kb
+	fi
+fi

 if [ "$skipped" == 0 -a "$failed" == 0 ]; then
 	msg "all tests passed"
--- a/tests/sequence
+++ b/tests/sequence
@@ -6,7 +6,6 @@ inode-items-updated.sh
 simple-inode-index.sh
 simple-staging.sh
 simple-release-extents.sh
-simple-readdir.sh
 get-referring-entries.sh
 fallocate.sh
 basic-truncate.sh
@@ -18,7 +17,6 @@ projects.sh
 large-fragmented-free.sh
 format-version-forward-back.sh
 enospc.sh
-mmap.sh
 srch-safe-merge-pos.sh
 srch-basic-functionality.sh
 simple-xattr-unit.sh
@@ -27,7 +25,6 @@ totl-xattr-tag.sh
 quota.sh
 lock-refleak.sh
 lock-shrink-consistency.sh
-lock-shrink-read-race.sh
 lock-pr-cw-conflict.sh
 lock-revoke-getcwd.sh
 lock-recover-invalidate.sh
--- a/tests/src/mmap_stress.c
+++ b/tests/src/mmap_stress.c
@@ -1,192 +0,0 @@
-#define _GNU_SOURCE
-/*
- * mmap() stress test for scoutfs
- *
- * This test exercises the scoutfs kernel module's locking by
- * repeatedly reading/writing using mmap and pread/write calls
- * across 5 clients (mounts).
- *
- * Each thread operates on a single thread/client, and performs
- * operations in a random order on the file.
- *
- * The goal is to assure that locking between _page_mkwrite vfs
- * calls and the normal read/write paths do not cause deadlocks.
- *
- * There is no content validation performed. All that is done is
- * assure that the programs continues without errors.
- */
-
-#include <sys/types.h>
-#include <stdio.h>
-#include <sys/stat.h>
-#include <inttypes.h>
-#include <fcntl.h>
-#include <unistd.h>
-#include <stdlib.h>
-#include <string.h>
-#include <stdbool.h>
-#include <sys/mman.h>
-#include <pthread.h>
-#include <errno.h>
-
-static int size = 0;
-static int duration = 0;
-
-struct thread_info {
-	int nr;
-	int fd;
-};
-
-static void *run_test_func(void *ptr)
-{
-	void *buf = NULL;
-	char *addr = NULL;
-	struct thread_info *tinfo = ptr;
-	uint64_t seconds = 0;
-	struct timespec ts;
-	int c = 0;
-	int fd;
-	ssize_t read, written, ret;
-	int preads = 0, pwrites = 0, mreads = 0, mwrites = 0;
-
-	fd = tinfo->fd;
-
-	if (posix_memalign(&buf, 4096, size) != 0) {
-		perror("calloc");
-		exit(-1);
-	}
-
-	addr = mmap(NULL, size, PROT_WRITE | PROT_READ, MAP_SHARED, fd, 0);
-	if (addr == MAP_FAILED) {
-		perror("mmap");
-		exit(-1);
-	}
-
-	usleep(100000); /* 0.1sec to allow all threads to start roughly at the same time */
-
-	clock_gettime(CLOCK_REALTIME, &ts); /* record start time */
-	seconds = ts.tv_sec + duration;
-
-	for (;;) {
-		if (++c % 16 == 0) {
-			clock_gettime(CLOCK_REALTIME, &ts);
-			if (ts.tv_sec >= seconds)
-				break;
-		}
-
-		switch (rand() % 4) {
-		case 0: /* pread */
-			preads++;
-			for (read = 0; read < size;) {
-				ret = pread(fd, buf, size - read, read);
-				if (ret < 0) {
-					perror("pwrite");
-					exit(-1);
-				}
-				read += ret;
-			}
-			break;
-		case 1: /* pwrite */
-			pwrites++;
-			memset(buf, (char)(c & 0xff), size);
-			for (written = 0; written < size;) {
-				ret = pwrite(fd, buf, size - written, written);
-				if (ret < 0) {
-					perror("pwrite");
-					exit(-1);
-				}
-				written += ret;
-			}
-			break;
-		case 2: /* mmap read */
-			mreads++;
-			memcpy(buf, addr, size); /* noerr */
-			break;
-		case 3: /* mmap write */
-			mwrites++;
-			memset(buf, (char)(c & 0xff), size);
-			memcpy(addr, buf, size); /* noerr */
-			break;
-		}
-
-		usleep(10000);
-	}
-
-	munmap(addr, size);
-
-	free(buf);
-
-	printf("thread %u complete: preads %u pwrites %u mreads %u mwrites %u\n", tinfo->nr,
-		mreads, mwrites, preads, pwrites);
-
-	return NULL;
-}
-
-int main(int argc, char **argv)
-{
-	pthread_t thread[5];
-	struct thread_info tinfo[5];
-	int fd[5];
-	int ret;
-	int i;
-
-	if (argc != 8) {
-		fprintf(stderr, "%s requires 7 arguments - size duration file1 file2 file3 file4 file5\n", argv[0]);
-		exit(-1);
-	}
-
-	size = atoi(argv[1]);
-	if (size <= 0) {
-		fprintf(stderr, "invalid size, must be greater than 0\n");
-		exit(-1);
-	}
-
-	duration = atoi(argv[2]);
-	if (duration < 0) {
-		fprintf(stderr, "invalid duration, must be greater than or equal to 0\n");
-		exit(-1);
-	}
-
-	/* create and truncate one fd */
-	fd[0] = open(argv[3], O_RDWR | O_CREAT | O_TRUNC, 00644);
-	if (fd[0] < 0) {
-		perror("open");
-		exit(-1);
-	}
-
-	/* make it the test size */
-	if (posix_fallocate(fd[0], 0, size) != 0) {
-		perror("fallocate");
-		exit(-1);
-	}
-
-	/* now open the rest of the fds */
-	for (i = 1; i < 5; i++) {
-		fd[i] = open(argv[3+i], O_RDWR);
-		if (fd[i] < 0) {
-			perror("open");
-			exit(-1);
-		}
-	}
-
-	/* start threads */
-	for (i = 0; i < 5; i++) {
-		tinfo[i].fd = fd[i];
-		tinfo[i].nr = i;
-		ret = pthread_create(&thread[i], NULL, run_test_func, (void*)&tinfo[i]);
-
-		if (ret) {
-			perror("pthread_create");
-			exit(-1);
-		}
-	}
-
-	/* wait for complete */
-	for (i = 0; i < 5; i++)
-		pthread_join(thread[i], NULL);
-
-	for (i = 0; i < 5; i++)
-		close(fd[i]);
-
-	exit(0);
-}
--- a/tests/src/mmap_validate.c
+++ b/tests/src/mmap_validate.c
@@ -1,159 +0,0 @@
-#define _GNU_SOURCE
-/*
- * mmap() content consistency checking for scoutfs
- *
- * This test program validates that content from memory mappings
- * are consistent across clients, whether written/read with mmap or
- * normal writes/reads.
- *
- * One side of (read/write) will always be memory mapped. It may
- * be that both sides do memory mapped (33% of the time).
- */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <string.h>
-#include <sys/mman.h>
-#include <fcntl.h>
-#include <errno.h>
-
-static int count = 0;
-static int size = 0;
-
-static void run_test_func(int fd1, int fd2)
-{
-	void *buf1 = NULL;
-	void *buf2 = NULL;
-	char *addr1 = NULL;
-	char *addr2 = NULL;
-	int c = 0;
-	ssize_t read, written, ret;
-
-	/* buffers for both sides to compare */
-	if (posix_memalign(&buf1, 4096, size) != 0) {
-		perror("calloc1");
-		exit(-1);
-	}
-
-	if (posix_memalign(&buf2, 4096, size) != 0) {
-		perror("calloc1");
-		exit(-1);
-	}
-
-	/* memory maps for both sides */
-	addr1 = mmap(NULL, size, PROT_WRITE | PROT_READ, MAP_SHARED, fd1, 0);
-	if (addr1 == MAP_FAILED) {
-		perror("mmap1");
-		exit(-1);
-	}
-
-	addr2 = mmap(NULL, size, PROT_WRITE | PROT_READ, MAP_SHARED, fd2, 0);
-	if (addr2 == MAP_FAILED) {
-		perror("mmap2");
-		exit(-1);
-	}
-
-	for (;;) {
-		if (++c > count) /* 10k iterations */
-			break;
-
-		/* put a pattern in buf1 */
-		memset(buf1, c & 0xff, size);
-
-		/* pwrite or mmap write from buf1 */
-		switch (c % 3) {
-		case 0:	/* pwrite */
-			for (written = 0; written < size;) {
-				ret = pwrite(fd1, buf1, size - written, written);
-				if (ret < 0) {
-					perror("pwrite");
-					exit(-1);
-				}
-				written += ret;
-			}
-			break;
-		default: /* mmap write */
-			memcpy(addr1, buf1, size);
-			break;
-		}
-
-		/* pread or mmap read to buf2 */
-		switch (c % 3) {
-		case 2: /* pread */
-			for (read = 0; read < size;) {
-				ret = pread(fd2, buf2, size - read, read);
-				if (ret < 0) {
-					perror("pwrite");
-					exit(-1);
-				}
-				read += ret;
-			}
-			break;
-		default: /* mmap read */
-			memcpy(buf2, addr2, size);
-			break;
-		}
-
-		/* compare bufs */
-		if (memcmp(buf1, buf2, size) != 0) {
-			fprintf(stderr, "memcmp() failed\n");
-			exit(-1);
-		}
-	}
-
-	munmap(addr1, size);
-	munmap(addr2, size);
-
-	free(buf1);
-	free(buf2);
-}
-
-int main(int argc, char **argv)
-{
-	int fd[1];
-
-	if (argc != 5) {
-		fprintf(stderr, "%s requires 4 arguments - size count file1 file2\n", argv[0]);
-		exit(-1);
-	}
-
-	size = atoi(argv[1]);
-	if (size <= 0) {
-		fprintf(stderr, "invalid size, must be greater than 0\n");
-		exit(-1);
-	}
-
-	count = atoi(argv[2]);
-	if (count < 3) {
-		fprintf(stderr, "invalid count, must be greater than 3\n");
-		exit(-1);
-	}
-
-	/* create and truncate one fd */
-	fd[0] = open(argv[3], O_RDWR | O_CREAT | O_TRUNC, 00644);
-	if (fd[0] < 0) {
-		perror("open");
-		exit(-1);
-	}
-
-	fd[1] = open(argv[4], O_RDWR , 00644);
-	if (fd[1] < 0) {
-		perror("open");
-		exit(-1);
-	}
-
-	/* make it the test size */
-	if (posix_fallocate(fd[0], 0, size) != 0) {
-		perror("fallocate");
-		exit(-1);
-	}
-
-	/* run the test function */
-	run_test_func(fd[0], fd[1]);
-
-	close(fd[0]);
-	close(fd[1]);
-
-	exit(0);
-}
--- a/tests/tests/basic-bad-mounts.sh
+++ b/tests/tests/basic-bad-mounts.sh
@@ -15,7 +15,7 @@ echo "== prepare devices, mount point, and logs"
 SCR="$T_TMPDIR/mnt.scratch"
 mkdir -p "$SCR"
 > $T_TMP.mount.out
-scoutfs mkfs -f -Q 0,127.0.0.1,$T_SCRATCH_PORT "$T_EX_META_DEV" "$T_EX_DATA_DEV" > $T_TMP.mkfs.out 2>&1 \
+scoutfs mkfs -f -Q 0,127.0.0.1,53000 "$T_EX_META_DEV" "$T_EX_DATA_DEV" > $T_TMP.mkfs.out 2>&1 \
 	|| t_fail "mkfs failed"

 echo "== bad devices, bad options"
--- a/tests/tests/basic-posix-acl.sh
+++ b/tests/tests/basic-posix-acl.sh
@@ -55,16 +55,16 @@ L dir-root/file-group-write
 L symlinkdir-root/file-group-write

 echo "== directory exec"
-setpriv $SET_UID bash -c "cd dir-root 2>&- && echo Success"
-setpriv $SET_UID bash -c "cd symlinkdir-root 2>&- && echo Success"
+setpriv $SET_UID bash -c "cd dir-root && echo Success"
+setpriv $SET_UID bash -c "cd symlinkdir-root && echo Success"
 setfacl -m u:22222:rw dir-root
 getfacl dir-root
-setpriv $SET_UID bash -c "cd dir-root 2>&- || echo Failed"
-setpriv $SET_UID bash -c "cd symlinkdir-root 2>&- || echo Failed"
+setpriv $SET_UID bash -c "cd dir-root || echo Failed"
+setpriv $SET_UID bash -c "cd symlinkdir-root || echo Failed"
 setfacl -m g:44444:rwx dir-root
 getfacl dir-root
-setpriv $SET_GID bash -c "cd dir-root 2>&- && echo Success"
-setpriv $SET_GID bash -c "cd symlinkdir-root 2>&- && echo Success"
+setpriv $SET_GID bash -c "cd dir-root && echo Success"
+setpriv $SET_GID bash -c "cd symlinkdir-root && echo Success"

 echo "== get/set attr"
 rm -rf file-root
--- a/tests/tests/basic-posix-consistency.sh
+++ b/tests/tests/basic-posix-consistency.sh
@@ -3,13 +3,13 @@
 # operations in one mount and verify the results in another.
 #

-t_require_commands getfattr setfattr dd diff touch stat scoutfs
+t_require_commands getfattr setfattr dd filefrag diff touch stat scoutfs
 t_require_mounts 2

 GETFATTR="getfattr --absolute-names"
 SETFATTR="setfattr"
 DD="dd status=none"
-FIEMAP="scoutfs get-fiemap"
+FILEFRAG="filefrag -v -b4096"

 echo "== root inode updates flow back and forth"
 sleep 1
@@ -55,8 +55,8 @@ for i in $(seq 1 10); do
 		conv=notrunc oflag=append &
 	wait
 done
-$FIEMAP "$T_D0/file" > "$T_TMP.0"
-$FIEMAP "$T_D1/file" > "$T_TMP.1"
+$FILEFRAG "$T_D0/file" | t_filter_fs > "$T_TMP.0"
+$FILEFRAG "$T_D1/file" | t_filter_fs > "$T_TMP.1"
 diff -u "$T_TMP.0" "$T_TMP.1"

 echo "== unlinked file isn't found"
--- a/tests/tests/basic-truncate.sh
+++ b/tests/tests/basic-truncate.sh
@@ -11,7 +11,7 @@ FILE="$T_D0/file"
 # final block as we truncated past it.
 #
 echo "== truncate writes zeroed partial end of file block"
-yes 2>/dev/null | dd of="$FILE" bs=8K count=1 status=none iflag=fullblock
+yes | dd of="$FILE" bs=8K count=1 status=none iflag=fullblock
 sync

 # not passing iflag=fullblock causes the file occasionally to just be
--- a/tests/tests/change-devices.sh
+++ b/tests/tests/change-devices.sh
@@ -11,7 +11,7 @@ truncate -s $sz "$T_TMP.equal"
 truncate -s $large_sz "$T_TMP.large"

 echo "== make scratch fs"
-t_quiet scoutfs mkfs -f -Q 0,127.0.0.1,$T_SCRATCH_PORT "$T_EX_META_DEV" "$T_EX_DATA_DEV"
+t_quiet scoutfs mkfs -f -Q 0,127.0.0.1,53000 "$T_EX_META_DEV" "$T_EX_DATA_DEV"
 SCR="$T_TMPDIR/mnt.scratch"
 mkdir -p "$SCR"

--- a/tests/tests/data-prealloc.sh
+++ b/tests/tests/data-prealloc.sh
@@ -4,16 +4,7 @@
 # merge adjacent consecutive allocations.  (we don't have multiple
 # allocation cursors)
 #
-t_require_commands scoutfs stat dd touch truncate
-
-get_fiemap()
-{
-	scoutfs get-fiemap "$1" | awk '($1 != "extents:") {
-			unwritten = (substr($8, 2, 1) == "U") ? "unwritten" : "";
-			eof = (substr($8, 3, 1) == "L") ? "eof" : "";
-			print $3 ".. " $6 ": " unwritten eof;
-			};'
-}
+t_require_commands scoutfs stat filefrag dd touch truncate

 write_block()
 {
@@ -85,9 +76,26 @@ print_extents_found()
 {
 	local prefix="$1"

-	for f in "$prefix"-*; do
-		echo "$f: $(scoutfs get-fiemap "$f" | tail -n 1)" | t_filter_fs
-	done
+	filefrag "$prefix"* 2>&1 | grep "extent.*found" | t_filter_fs
+}
+
+#
+# print the logical start, len, and flags if they're there.
+#
+print_logical_extents()
+{
+	local file="$1"
+
+	filefrag -v -b4096 "$file" 2>&1 | t_filter_fs | awk '
+		($1 ~ /[0-9]+:/) {
+			if ($NF !~  /[0-9]+:/) {
+				flags=$NF
+			} else {
+				flags=""
+			}
+			print $2, $6, flags
+		}
+	' | sed 's/last,eof/eof/'
 }

 t_save_all_sysfs_mount_options data_prealloc_blocks
@@ -189,7 +197,7 @@ for sides in 0 1 2 3; do
 done

 echo before:
-get_fiemap "$prefix"
+print_logical_extents "$prefix"

 # now write into the first, middle, and last empty block of each
 t_set_sysfs_mount_option 0 data_prealloc_contig_only 0
@@ -215,7 +223,7 @@ for sides in 0 1 2 3; do
 			# mid (both has 6 blocks internally)
 			2) write_block $prefix $((left + 3)) ;;
 		esac
-		get_fiemap "$prefix"
+		print_logical_extents "$prefix"
 		((base+=8))
 	done
 done
--- a/tests/tests/enospc.sh
+++ b/tests/tests/enospc.sh
@@ -57,7 +57,7 @@ test "$before" == "$after" || \
 # XXX this is all pretty manual, would be nice to have helpers
 echo "== make small meta fs"
 # meta device just big enough for reserves and the metadata we'll fill
-scoutfs mkfs -A -f -Q 0,127.0.0.1,$T_SCRATCH_PORT -m 10G "$T_EX_META_DEV" "$T_EX_DATA_DEV" > $T_TMP.mkfs.out 2>&1 || \
+scoutfs mkfs -A -f -Q 0,127.0.0.1,53000 -m 10G "$T_EX_META_DEV" "$T_EX_DATA_DEV" > $T_TMP.mkfs.out 2>&1 || \
 	t_fail "mkfs failed"
 SCR="$T_TMPDIR/mnt.scratch"
 mkdir -p "$SCR"
@@ -88,11 +88,6 @@ rm -rf "$SCR/xattrs"

 echo "== make sure we can create again"
 file="$SCR/file-after"
-C=120
-while (( C-- )); do
-	touch $file 2> /dev/null && break
-	sleep 1
-done
 touch $file
 setfattr -n user.scoutfs-enospc -v 1 "$file"
 sync
--- a/tests/tests/fence-and-reclaim.sh
+++ b/tests/tests/fence-and-reclaim.sh
@@ -5,9 +5,6 @@
 t_require_commands sleep touch grep sync scoutfs
 t_require_mounts 2

-# regularly see ~20/~30s
-VERIFY_TIMEOUT_SECS=90
-
 #
 # Make sure that all mounts can read the results of a write from each
 # mount.
@@ -43,10 +40,8 @@ verify_fenced_run()

 	for rid in $rids; do
 		grep -q ".* running rid '$rid'.* args 'ignored run args'" "$T_FENCED_LOG" || \
-			return 1
+			t_fail "fenced didn't execute RUN script for rid $rid"
 	done
-
-	return 0
 }

 echo "== make sure all mounts can see each other"
@@ -59,7 +54,14 @@ rid=$(t_mount_rid $cl)
 echo "cl $cl sv $sv rid $rid" >> "$T_TMP.log"
 sync
 t_force_umount $cl
-t_wait_until_timeout $VERIFY_TIMEOUT_SECS verify_fenced_run $rid
+# wait for client reconnection to timeout
+while grep -q $rid $(t_debugfs_path $sv)/connections; do
+	sleep .5
+done
+while t_rid_is_fencing $rid; do
+	sleep .5
+done
+verify_fenced_run $rid
 t_mount $cl
 check_read_write

@@ -81,7 +83,15 @@ for cl in $(t_fs_nrs); do
 	t_force_umount $cl
 done

-t_wait_until_timeout $VERIFY_TIMEOUT_SECS verify_fenced_run $rids
+# wait for all client reconnections to timeout
+while egrep -q "($pattern)" $(t_debugfs_path $sv)/connections; do
+	sleep .5
+done
+# wait for all fence requests to complete
+while test -d $(echo /sys/fs/scoutfs/*/fence/* | cut -d " " -f 1); do
+	sleep .5
+done
+verify_fenced_run $rids
 # remount all the clients
 for cl in $(t_fs_nrs); do
 	if [ $cl == $sv ]; then
@@ -97,7 +107,12 @@ rid=$(t_mount_rid $sv)
 echo "sv $sv rid $rid" >> "$T_TMP.log"
 sync
 t_force_umount $sv
-t_wait_until_timeout $VERIFY_TIMEOUT_SECS verify_fenced_run $rid
+t_wait_for_leader
+# wait until new server is done fencing unmounted leader rid
+while t_rid_is_fencing $rid; do
+	sleep .5
+done
+verify_fenced_run $rid
 t_mount $sv
 check_read_write

@@ -112,7 +127,11 @@ for nr in $(t_fs_nrs); do
 	t_force_umount $nr
 done
 t_mount_all
-t_wait_until_timeout $VERIFY_TIMEOUT_SECS verify_fenced_run $rids
+# wait for all fence requests to complete
+while test -d $(echo /sys/fs/scoutfs/*/fence/* | cut -d " " -f 1); do
+	sleep .5
+done
+verify_fenced_run $rids
 check_read_write

 t_pass
--- a/tests/tests/format-version-forward-back.sh
+++ b/tests/tests/format-version-forward-back.sh
@@ -11,11 +11,6 @@
 # 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"
@@ -89,7 +84,7 @@ for vers in $(seq $MIN $((MAX - 1))); do
 	old_module="$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_quiet $old_scoutfs mkfs -f -Q 0,127.0.0.1,53000 "$T_EX_META_DEV" "$T_EX_DATA_DEV" \
 		|| t_fail "mkfs $vers failed"

 	echo "mount $vers with $vers" >> "$T_TMP.log"
--- a/tests/tests/get-referring-entries.sh
+++ b/tests/tests/get-referring-entries.sh
@@ -72,7 +72,7 @@ touch $T_D0/dir/file
 mkdir $T_D0/dir/dir
 ln -s $T_D0/dir/file $T_D0/dir/symlink
 mknod $T_D0/dir/char c 1 3 # null
-mknod $T_D0/dir/block b 42 0 # SAMPLE block dev - nonexistant/demo use only number
+mknod $T_D0/dir/block b 7 0 # loop0
 for name in $(ls -UA $T_D0/dir | sort); do
 	ino=$(stat -c '%i' $T_D0/dir/$name)
 	$GRE $ino | filter_types
--- a/tests/tests/inode-deletion.sh
+++ b/tests/tests/inode-deletion.sh
@@ -61,28 +61,18 @@ rm -f "$T_D1/file"
 check_ino_index "$ino" "$dseq" "$T_M0"
 check_ino_index "$ino" "$dseq" "$T_M1"

-# Hurry along the orphan scanners. If any are currently asleep, we will
-# have to wait at least their current scan interval before they wake up,
-# run, and notice their new interval.
-t_save_all_sysfs_mount_options orphan_scan_delay_ms
-t_set_all_sysfs_mount_options orphan_scan_delay_ms 500
-t_wait_for_orphan_scan_runs
-
 echo "== unlink wait for open on other mount"
-echo "contents" > "$T_D0/badfile"
-ino=$(stat -c "%i" "$T_D0/badfile")
-dseq=$(scoutfs stat -s data_seq "$T_D0/badfile")
-exec {FD}<"$T_D0/badfile"
-rm -f "$T_D1/badfile"
+echo "contents" > "$T_D0/file"
+ino=$(stat -c "%i" "$T_D0/file")
+dseq=$(scoutfs stat -s data_seq "$T_D0/file")
+exec {FD}<"$T_D0/file"
+rm -f "$T_D1/file"
 echo "mount 0 contents after mount 1 rm: $(cat <&$FD)"
 check_ino_index "$ino" "$dseq" "$T_M0"
 check_ino_index "$ino" "$dseq" "$T_M1"
 exec {FD}>&-  # close
 # we know that revalidating will unhash the remote dentry
-stat "$T_D0/badfile" 2>&1 | sed 's/cannot statx/cannot stat/' | t_filter_fs
-t_force_log_merge
-# wait for orphan scanners to pick up the unlinked inode and become idle
-t_wait_for_no_orphans
+stat "$T_D0/file" 2>&1 | sed 's/cannot statx/cannot stat/' | t_filter_fs
 check_ino_index "$ino" "$dseq" "$T_M0"
 check_ino_index "$ino" "$dseq" "$T_M1"

@@ -93,20 +83,16 @@ rm -f "$T_D0/dir"/files-*
 rmdir "$T_D0/dir"

 echo "== open files survive remote scanning orphans"
-echo "contents" > "$T_D0/lastfile"
-ino=$(stat -c "%i" "$T_D0/lastfile")
-dseq=$(scoutfs stat -s data_seq "$T_D0/lastfile")
-exec {FD}<"$T_D0/lastfile"
-rm -f "$T_D0/lastfile"
+echo "contents" > "$T_D0/file"
+ino=$(stat -c "%i" "$T_D0/file")
+dseq=$(scoutfs stat -s data_seq "$T_D0/file")
+exec {FD}<"$T_D0/file"
+rm -f "$T_D0/file"
 t_umount 1
 t_mount 1
 echo "mount 0 contents after mount 1 remounted: $(cat <&$FD)"
 exec {FD}>&-  # close
-t_force_log_merge
-t_wait_for_no_orphans
 check_ino_index "$ino" "$dseq" "$T_M0"
 check_ino_index "$ino" "$dseq" "$T_M1"

-t_restore_all_sysfs_mount_options orphan_scan_delay_ms
-
 t_pass
--- a/tests/tests/large-fragmented-free.sh
+++ b/tests/tests/large-fragmented-free.sh
@@ -10,6 +10,30 @@ EXTENTS_PER_BTREE_BLOCK=600
 EXTENTS_PER_LIST_BLOCK=8192
 FREED_EXTENTS=$((EXTENTS_PER_BTREE_BLOCK * EXTENTS_PER_LIST_BLOCK))

+#
+# This test specifically creates a pathologically sparse file that will
+# be as expensive as possible to free.  This is usually fine on
+# dedicated or reasonable hardware, but trying to run this in
+# virtualized debug kernels can take a very long time.  This test is
+# about making sure that the server doesn't fail, not that the platform
+# can handle the scale of work that our btree formats happen to require
+# while execution is bogged down with use-after-free memory reference
+# tracking.  So we give the test a lot more breathing room before
+# deciding that its hung.
+#
+echo "== setting longer hung task timeout"
+if [ -w /proc/sys/kernel/hung_task_timeout_secs ]; then
+	secs=$(cat /proc/sys/kernel/hung_task_timeout_secs)
+	test "$secs" -gt 0 || \
+		t_fail "confusing value '$secs' from /proc/sys/kernel/hung_task_timeout_secs"
+	restore_hung_task_timeout()
+	{
+		echo "$secs" > /proc/sys/kernel/hung_task_timeout_secs
+	}
+	trap restore_hung_task_timeout EXIT
+	echo "$((secs * 5))" > /proc/sys/kernel/hung_task_timeout_secs
+fi
+
 echo "== creating fragmented extents"
 fragmented_data_extents $FREED_EXTENTS $EXTENTS_PER_BTREE_BLOCK "$T_D0/alloc" "$T_D0/move"

--- a/tests/tests/lock-recover-invalidate.sh
+++ b/tests/tests/lock-recover-invalidate.sh
@@ -38,6 +38,6 @@ while [ "$SECONDS" -lt "$END" ]; do
 done

 echo "== stopping background load"
-t_silent_kill $load_pids
+kill $load_pids

 t_pass
--- a/tests/tests/lock-shrink-read-race.sh
+++ b/tests/tests/lock-shrink-read-race.sh
@@ -1,40 +0,0 @@
-#
-# We had a lock server refcounting bug that could let one thread get a
-# reference on a lock struct that was being freed by another thread.  We
-# were able to reproduce this by having all clients try and produce a
-# lot of read and null requests.
-#
-# This will manfiest as a hung lock and timed out test runs, probably
-# with hung task messages on the console.  Depending on how the race
-# turns out, it can trigger KASAN warnings in
-# process_waiting_requests().
-#
-
-READERS_PER=3
-SECS=30
-
-echo "=== setup"
-touch "$T_D0/file"
-
-echo "=== spin reading and shrinking"
-END=$((SECONDS + SECS))
-for m in $(t_fs_nrs); do
-	eval file="\$T_D${m}/file"
-
-	# lots of tasks reading as fast as they can
-	for t in $(seq 1 $READERS_PER); do
-		(while [ $SECONDS -lt $END ]; do
-			stat $file > /dev/null
-		 done) &
-	done
-	# one task shrinking (triggering null requests) and reading
-	(while [ $SECONDS -lt $END ]; do
-		stat $file > /dev/null
-		t_trigger_arm_silent statfs_lock_purge $m
-		stat -f "$file" > /dev/null
-	 done) &
-done
-
-wait
-
-t_pass
--- a/tests/tests/mmap.sh
+++ b/tests/tests/mmap.sh
@@ -1,54 +0,0 @@
-#
-# test mmap() and normal read/write consistency between different nodes
-#
-
-t_require_commands mmap_stress mmap_validate scoutfs xfs_io
-
-echo "== mmap_stress"
-mmap_stress 8192 30 "$T_D0/mmap_stress" "$T_D0/mmap_stress" "$T_D0/mmap_stress" "$T_D3/mmap_stress" "$T_D3/mmap_stress" | sed 's/:.*//g' | sort
-
-echo "== basic mmap/read/write consistency checks"
-mmap_validate 256 1000 "$T_D0/mmap_val1" "$T_D1/mmap_val1"
-mmap_validate 8192 1000 "$T_D0/mmap_val2" "$T_D1/mmap_val2"
-mmap_validate 88400 1000 "$T_D0/mmap_val3" "$T_D1/mmap_val3"
-
-echo "== mmap read from offline extent"
-F="$T_D0/mmap-offline"
-touch "$F"
-xfs_io -c "pwrite -S 0xEA 0 8192" "$F" > /dev/null
-cp "$F" "${F}-stage"
-vers=$(scoutfs stat -s data_version "$F")
-scoutfs release "$F" -V "$vers" -o 0 -l 8192
-scoutfs get-fiemap -L "$F"
-xfs_io -c "mmap -rwx 0 8192" \
-	-c "mread -v 512 16" "$F" &
-sleep 1
-# should be 1 - data waiting
-jobs | wc -l
-scoutfs stage "${F}-stage" "$F" -V "$vers" -o 0 -l 8192
-# xfs_io thread <here> will output 16 bytes of read data
-sleep 1
-# should be 0 - no more waiting jobs, xfs_io should have exited
-jobs | wc -l
-scoutfs get-fiemap -L "$F"
-
-echo "== mmap write to an offline extent"
-# reuse the same file
-scoutfs release "$F" -V "$vers" -o 0 -l 8192
-scoutfs get-fiemap -L "$F"
-xfs_io -c "mmap -rwx 0 8192" \
-	-c "mwrite -S 0x11 528 16" "$F" &
-sleep 1
-# should be 1 job waiting
-jobs | wc -l
-scoutfs stage "${F}-stage" "$F" -V "$vers" -o 0 -l 8192
-# no output here from write
-sleep 1
-# should be 0 - no more waiting jobs, xfs_io should have exited
-jobs | wc -l
-scoutfs get-fiemap -L "$F"
-# read back contents to assure write changed the file
-dd status=none if="$F" bs=1 count=48 skip=512 | hexdump -C
-
-echo "== done"
-t_pass
--- a/tests/tests/move-blocks.sh
+++ b/tests/tests/move-blocks.sh
@@ -83,9 +83,9 @@ touch "$OTHER"
 ln "$FROM" "$HARD"

 echo "== wrapped offsets should fail"
-HUGE=0xfffffffffffff000
-scoutfs move-blocks "$FROM" -f "$HUGE" -l "8192" "$TO" -t 0 2>&1 | t_filter_fs
-scoutfs move-blocks "$FROM" -f 0 -l "$HUGE" "$TO" -t "8192" 2>&1 | t_filter_fs
+HUGE=0x8000000000000000
+scoutfs move-blocks "$FROM" -f "$HUGE" -l "$HUGE" "$TO" -t 0 2>&1 | t_filter_fs
+scoutfs move-blocks "$FROM" -f 0 -l "$HUGE" "$TO" -t "$HUGE" 2>&1 | t_filter_fs

 echo "== specifying same file fails"
 scoutfs move-blocks "$FROM" -f 0 -l "$BS" "$HARD" -t 0 2>&1 | t_filter_fs
--- a/tests/tests/offline-extent-waiting.sh
+++ b/tests/tests/offline-extent-waiting.sh
@@ -157,7 +157,7 @@ echo "truncate should be waiting for first block:"
 expect_wait "$DIR/file" "change_size" $ino 0
 scoutfs stage "$DIR/golden" "$DIR/file" -V "$vers" -o 0 -l $BYTES
 sleep .1
-echo "truncate should no longer be waiting:"
+echo "trunate should no longer be waiting:"
 scoutfs data-waiting -B 0 -I 0 -p "$DIR" | wc -l
 cat "$DIR/golden" > "$DIR/file"
 vers=$(scoutfs stat -s data_version "$DIR/file")
@@ -168,13 +168,10 @@ scoutfs release "$DIR/file" -V "$vers" -o 0 -l $BYTES
 # overwrite, not truncate+write
 dd if="$DIR/other" of="$DIR/file" \
 	bs=$BS count=$BLOCKS conv=notrunc status=none &
-pid="$!"
 sleep .1
 echo "should be waiting for write"
 expect_wait "$DIR/file" "write" $ino 0
 scoutfs stage "$DIR/golden" "$DIR/file" -V "$vers" -o 0 -l $BYTES
-# wait for the background dd to complete
-wait "$pid" 2> /dev/null
 cmp "$DIR/file" "$DIR/other"

 echo "== cleanup"
--- a/tests/tests/orphan-inodes.sh
+++ b/tests/tests/orphan-inodes.sh
@@ -5,6 +5,18 @@
 t_require_commands sleep touch sync stat handle_cat kill rm
 t_require_mounts 2

+#
+# usually bash prints an annoying output message when jobs
+# are killed.  We can avoid that by redirecting stderr for
+# the bash process when it reaps the jobs that are killed.
+#
+silent_kill() {
+	exec {ERR}>&2 2>/dev/null
+	kill "$@"
+	wait "$@"
+	exec 2>&$ERR {ERR}>&-
+}
+
 #
 # We don't have a great way to test that inode items still exist.   We
 # don't prevent opening handles with nlink 0 today, so we'll use that.
@@ -40,7 +52,7 @@ inode_exists $ino || echo "$ino didn't exist"

 echo "== orphan from failed evict deletion is picked up"
 # pending kill signal stops evict from getting locks and deleting
-t_silent_kill $pid
+silent_kill $pid
 t_set_sysfs_mount_option 0 orphan_scan_delay_ms 1000
 sleep 5
 inode_exists $ino && echo "$ino still exists"
@@ -58,7 +70,7 @@ for nr in $(t_fs_nrs); do
 	rm -f "$path"
 done
 sync
-t_silent_kill $pids
+silent_kill $pids
 for nr in $(t_fs_nrs); do
 	t_force_umount $nr
 done
@@ -67,49 +79,10 @@ t_mount_all
 while test -d $(echo /sys/fs/scoutfs/*/fence/* | cut -d " " -f 1); do
 	sleep .5
 done
-
-
-sv=$(t_server_nr)
-
-# wait for reclaim_open_log_tree() to complete for each mount
-while [ $(t_counter reclaimed_open_logs $sv) -lt $T_NR_MOUNTS ]; do
-	sleep 1
-done
-
-# wait for finalize_and_start_log_merge() to find no active merges in flight
-# and not find any finalized trees
-while [ $(t_counter log_merge_no_finalized $sv) -lt 1 ]; do
-	sleep 1
-done
-
 # wait for orphan scans to run
 t_set_all_sysfs_mount_options orphan_scan_delay_ms 1000
-# wait until we see two consecutive orphan scan attempts without
-# any inode deletion forward progress in each mount
-for nr in $(t_fs_nrs); do
-	C=0
-	LOSA=$(t_counter orphan_scan_attempts $nr)
-	LDOP=$(t_counter inode_deleted $nr)
-
-	while [ $C -lt 2 ]; do
-		sleep 1
-
-		OSA=$(t_counter orphan_scan_attempts $nr)
-		DOP=$(t_counter inode_deleted $nr)
-
-		if [ $OSA != $LOSA ]; then
-			if [ $DOP == $LDOP ]; then
-				(( C++ ))
-			else
-				C=0
-			fi
-		fi
-
-		LOSA=$OSA
-		LDOP=$DOP
-	done
-done
-
+# also have to wait for delayed log merge work from mount
+sleep 15
 for ino in $inos; do
 	inode_exists $ino && echo "$ino still exists"
 done
@@ -158,7 +131,7 @@ while [ $SECONDS -lt $END ]; do
 	done

 	# trigger eviction deletion of each file in each mount
-	t_silent_kill $pids
+	silent_kill $pids

 	wait || t_fail "handle_fsetxattr failed"

--- a/tests/tests/quorum-heartbeat-timeout.sh
+++ b/tests/tests/quorum-heartbeat-timeout.sh
@@ -62,7 +62,7 @@ test_timeout()
 	sleep 1

 	# tear down the current server/leader
-	t_force_umount $sv &
+	t_force_umount $sv

 	# see how long it takes for the next leader to start
 	start=$(time_ms)
@@ -73,7 +73,6 @@ test_timeout()
 	echo "to $to delay $delay" >> $T_TMP.delay

 	# restore the mount that we tore down
-	wait
 	t_mount $sv

 	# make sure the new leader delay was reasonable, allowing for some slack
--- a/tests/tests/quota.sh
+++ b/tests/tests/quota.sh
@@ -22,7 +22,7 @@ reset_all()
 	getfattr --absolute-names -d -m - "$T_D0" | \
 		grep "^scoutfs.totl." | \
 		cut -d '=' -f 1 | \
-		xargs -I'{}'  setfattr -x '{}' "$T_D0"
+		xargs -n 1 -I'{}'  setfattr -x '{}' "$T_D0"
 }

 echo "== prepare dir with write perm for test ids"
--- a/tests/tests/renameat2-noreplace.sh
+++ b/tests/tests/renameat2-noreplace.sh
@@ -8,19 +8,19 @@ t_require_mounts 2
 echo "=== renameat2 noreplace flag test"

 # give each mount their own dir (lock group) to minimize create contention
-mkdir $T_D0/dir0
-mkdir $T_D1/dir1
+mkdir $T_M0/dir0
+mkdir $T_M1/dir1

 echo "=== run two asynchronous calls to renameat2 NOREPLACE"
 for i in $(seq 0 100); do
        # prepare inputs in isolation
-        touch "$T_D0/dir0/old0"
-        touch "$T_D1/dir1/old1"
+        touch "$T_M0/dir0/old0"
+        touch "$T_M1/dir1/old1"

        # race doing noreplace renames, both can't succeed
-        dumb_renameat2 -n "$T_D0/dir0/old0" "$T_D0/dir0/sharednew" 2> /dev/null &
+        dumb_renameat2 -n "$T_M0/dir0/old0" "$T_M0/dir0/sharednew" 2> /dev/null &
        pid0=$!
-        dumb_renameat2 -n "$T_D1/dir1/old1" "$T_D1/dir0/sharednew" 2> /dev/null &
+        dumb_renameat2 -n "$T_M1/dir1/old1" "$T_M1/dir0/sharednew" 2> /dev/null &
        pid1=$!

        wait $pid0
@@ -31,7 +31,7 @@ for i in $(seq 0 100); do
        test "$rc0" == 0 -a "$rc1" == 0 && t_fail "both renames succeeded"

        # blow away possible files for either race outcome
-        rm -f "$T_D0/dir0/old0" "$T_D1/dir1/old1" "$T_D0/dir0/sharednew" "$T_D1/dir1/sharednew"
+        rm -f "$T_M0/dir0/old0" "$T_M1/dir1/old1" "$T_M0/dir0/sharednew" "$T_M1/dir1/sharednew"
 done

 t_pass
--- a/tests/tests/resize-devices.sh
+++ b/tests/tests/resize-devices.sh
@@ -72,7 +72,7 @@ quarter_data=$(echo "$size_data / 4" | bc)

 # XXX this is all pretty manual, would be nice to have helpers
 echo "== make initial small fs"
-scoutfs mkfs -A -f -Q 0,127.0.0.1,$T_SCRATCH_PORT -m $quarter_meta -d $quarter_data \
+scoutfs mkfs -A -f -Q 0,127.0.0.1,53000 -m $quarter_meta -d $quarter_data \
 	"$T_EX_META_DEV" "$T_EX_DATA_DEV" > $T_TMP.mkfs.out 2>&1 || \
 		t_fail "mkfs failed"
 SCR="$T_TMPDIR/mnt.scratch"
--- a/tests/tests/setattr_more.sh
+++ b/tests/tests/setattr_more.sh
@@ -2,7 +2,7 @@
 # Test correctness of the setattr_more ioctl.
 #

-t_require_commands scoutfs touch mkdir rm stat mknod
+t_require_commands filefrag scoutfs touch mkdir rm stat mknod

 FILE="$T_D0/file"

@@ -55,10 +55,17 @@ scoutfs setattr -t 67305985.999999999 -V 1 -s 1 "$FILE" 2>&1 | t_filter_fs
 TZ=GMT stat -c "%z" "$FILE"
 rm "$FILE"

+#
+# With e2fsprogs-v1.42.10-10-g29758d2f, the output of filefrag 'flags' changes
+# significantly. First, the _LAST flag is now output. Second, the 'unknown'
+# flag is now printed out as 'unknown_loc'. To compensate for this, we check
+# and replace the "correct" output for new versions here with the expected
+# value.
+#
 echo "== large offline extents are created"
 touch "$FILE"
 scoutfs setattr -V 1 -o -s $((10007 * 4096)) "$FILE" 2>&1 | t_filter_fs
-scoutfs get-fiemap "$FILE"
+filefrag -v -b4096 "$FILE" 2>&1 | sed 's/last,unknown_loc,eof$/unknown,eof/' | t_filter_fs
 rm "$FILE"

 # had a bug where we were creating extents that were too long
@@ -68,11 +75,4 @@ scoutfs setattr -V 1 -o -s 4000000000 "$FILE" 2>&1 | t_filter_fs
 scoutfs stat -s offline_blocks "$FILE"
 rm "$FILE"

-# Do not fail if data_version is unset - the unset `0` value should not
-# be passed down to attr_x handling code which will -EINVAL on that.
-echo "== omitting data_version should not fail"
-touch "$FILE"
-scoutfs setattr -s 0 -t 1725670311.0 -r 1725670311.0 "$FILE"
-rm "$FILE"
-
 t_pass
--- a/tests/tests/simple-readdir.sh
+++ b/tests/tests/simple-readdir.sh
@@ -1,37 +0,0 @@
-#
-# verify d_off output of xfs_io is consistent.
-#
-
-t_require_commands xfs_io
-
-filt()
-{
-	grep d_off | cut -d ' ' -f 1,4-
-}
-
-echo "== create content"
-for s in $(seq 1 7 250); do
-	f=$(printf '%*s' $s | tr ' ' 'a')
-	touch ${T_D0}/$f
-done
-
-echo "== readdir all"
-xfs_io -c "readdir -v" $T_D0 | filt
-
-echo "== readdir offset"
-xfs_io -c "readdir -v -o 20" $T_D0 | filt
-
-echo "== readdir len (bytes)"
-xfs_io -c "readdir -v -l 193" $T_D0 | filt
-
-echo "== introduce gap"
-for s in $(seq 57 7 120); do
-	f=$(printf '%*s' $s | tr ' ' 'a')
-	rm -f ${T_D0}/$f
-done
-xfs_io -c "readdir -v" $T_D0 | filt
-
-echo "== cleanup"
-rm -rf $T_D0
-
-t_pass
--- a/tests/tests/simple-release-extents.sh
+++ b/tests/tests/simple-release-extents.sh
@@ -7,7 +7,6 @@ t_require_commands xfs_io filefrag scoutfs mknod
 # this test wants to ignore unwritten extents
 fiemap_file() {
 	filefrag -v -b4096 "$1" | grep -v "unwritten"
-	scoutfs get-fiemap "$1" | grep -v 'flags:.*U'
 }

 create_file() {
@@ -62,10 +61,7 @@ echo "== release past i_size is fine"
 release_vers "$FILE" stat 400K 4K

 echo "== wrapped blocks fails"
-# just under!
-release_vers "$FILE" stat $vers 0xfffffffffffff000 4096
-# this goes over
-release_vers "$FILE" stat $vers 0xfffffffffffff000 8192
+release_vers "$FILE" stat $vers 0x8000000000000000 0x8000000000000000

 echo "== releasing non-file fails"
 mknod "$CHAR" c 1 3
@@ -109,20 +105,25 @@ for c in $(seq 0 4); do
 		fi
 	done

+	start=$(fiemap_file "$FILE" | \
+		awk '($1 == "0:"){print substr($4, 0, length($4)- 2)}')
+
 	release_vers "$FILE" stat $(($a * 4))K 4K
 	release_vers "$FILE" stat $(($b * 4))K 4K
 	release_vers "$FILE" stat $(($c * 4))K 4K

 	echo -n "$a $b $c:"

-	scoutfs get-fiemap "$FILE" | \
-		awk 'BEGIN{ORS=""}($1 != "extents:") {
-			off=$3;
-			len=$6;
-			phys=substr($8, 0, 1);
-			phys = (phys == ".") ? off + 100 : 0;
-			print "  (" off, phys, len ")"
-		};'
+	fiemap_file "$FILE" | \
+		awk 'BEGIN{ORS=""}($1 == (NR - 4)":") {
+			off=substr($2, 0, length($2)- 2);
+			phys=substr($4, 0, length($4)- 2);
+			if (phys > 100) {
+				phys = phys - phys + 100 + off;
+			}
+			len=substr($6, 0, length($6)- 1);
+			print "  (" off, phys, len ")";
+		}'
 	echo

 	rm "$FILE"
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Greg Cymbalski	c6ed82f19c	Keep dist suffix	2024-09-26 12:12:03 -07:00
Greg Cymbalski	c122c6823f	Sanitize kversion	2024-09-26 12:09:00 -07:00
Greg Cymbalski	dfa6a8c78b	Add kernel version to package release var	2024-09-26 12:02:51 -07:00