v1.16 Release

Finish the release notes for the 1.16 release.

Signed-off-by: Zach Brown <zab@versity.com>

ReleaseNotes.md

@@ -1,6 +1,225 @@
 Versity ScoutFS Release Notes
 =============================
 
+---
+v1.16
+\
+*Oct 4, 2023*
+
+Fix an issue where the server could hang on startup if its persistent
+allocator structures were left in a specific degraded state by the
+previously active server.
+
+---
+v1.15
+\
+*Jul 17, 2023*
+
+Process log btree merge splicing in multiple commits.  This prevents a
+rare case where pending log merge completions contain more work than can
+be done in a single server commit, causing the server to trigger an
+assert shortly after starting.
+
+Fix spurious EINVAL from data writes when data\_prealloc\_contig\_only was
+set to 0.
+
+---
+v1.14
+\
+*Jun 29, 2023*
+
+Add get\_referring\_entries ioctl for getting directory entries that
+refer to an inode.
+
+Fix excessive CPU use in the move\_blocks interface when moving a large
+number of extents.
+
+Reduce fragmented data allocation when contig\_only prealloc is not in
+use by more consistently allocating multi-block extents within each
+aligned prealloc region.
+
+Avoid rare deadlock in metadata block cache recalim under both heavy
+load and memory pressure.
+
+Fix crash when using quorum\_heartbeat\_timeout\_ms mount option.
+
+---
+v1.13
+\
+*May 19, 2023*
+
+Add the quorum\_heartbeat\_timeout\_ms mount option to set the quorum
+heartbeat timeout.
+
+Change some task prioritization and allocation behavior of the quorum
+agent to help reduce delays in sending and receiving heartbeat messages.
+
+---
+v1.12
+\
+*Apr 17, 2023*
+
+Add the prepare-empty-data-device scoutfs command.  A data device can be
+unused when no files have data blocks, perhaps because they're archived
+and offline.  In this case the data device can be swapped out for
+another device without changes to the metadata device.
+
+Fix an oversight which limited inode timestamps to second granularity
+for some operations.  All operations now record timestamps with full
+nanosecond precision.
+
+Fix spurious ENOENT failures when renaming from other directories into
+the root directory.
+
+---
+v1.11
+\
+*Feb 2, 2023*
+
+Fixed a free extent processing error that could prevent mount from
+proceeding when free data extents were sufficiently fragmented.  It now
+properly handle very fragmented free extent maps.
+
+Fixed a statfs server processing race that could return spurious errors
+and shut down the server.  With the race closed statfs processing is
+reliable.
+
+Fixed a rare livelock in the move\_blocks ioctl.  With the right
+relationship between ioctl arguments and eventual file extent items the
+core loop in the move\_blocks ioctl could get stuck looping on an extent
+item and never return.  The loop exit conditions were fixed and the loop
+will always advance through all extents.
+
+Changed the 'print' scoutfs commands to flush the block cache for the
+devices.  It was inconvenient to expect cache flushing to be a separate
+step to ensure consistency with remote node writes.
+
+---
+v1.10
+\
+*Dec 7, 2022*
+
+Fixed a potential directory entry cache management deadlock that could
+occur when many nodes performed heavy metadata write loads across shared
+directories and their child subdirectories.  The deadlock could halt
+invalidation progress on a node which could then stop use of locks that
+needed invalidation on that node which would result in almost all tasks
+hanging on those locks that would never make progress. 
+
+Fixed a circumstance where metadata change sequence index item
+modification could leave behind old stale metadata sequence items.  The
+duplication case required concurrent metadata updates across mounts with
+particular open transaction patterns so the duplicate items are rare.
+They resulted in a small amount of additional load when walking change
+indexes but had no effect on correctness.
+
+Fixed a rare case where sparse file extension might not write partial
+blocks of zeros which was found in testing.  This required using
+truncate to extend files past file sizes that end in partial blocks
+along with the right transaction commit and memory reclaim patterns.
+This never affected regular non-sparse files nor files prepopulated with
+fallocate.
+
+---
+v1.9
+\
+*Oct 29, 2022*
+
+Fix VFS cached directory entry consistency verification that could cause
+spurious "no such file or directory" (ENOENT) errors from rename over
+NFS under certain conditions.  The problem was only every with the
+consistency of in-memory cached dentry objects, persistent data was
+correct and eventual eviction of the bad cached objects would stop
+generating the errors.
+
+---
+v1.8
+\
+*Oct 18, 2022*
+
+Add support for Linux POSIX Access Control Lists, as described in
+acl(5).  Mount options are added to enable ("acl") and disable ("noacl")
+support.  The default is to support ACLs.  ACLs are stored in the
+existing extended attribute scheme so adding support is does not require
+a format change.
+
+Add options to control data extent preallocation.  The default behavior
+does not change.  The options can relax the limits on preallocation
+which will then trigger under more write patterns and increase the risk
+of preallocated space which is never used.  The options are described in
+scoutfs(5).
+
+---
+v1.7
+\
+*Aug 26, 2022*
+
+* **Fixed possible persistent errors moving freed data extents**
+\
+  Fixed a case where the server could hit persistent errors trying to
+  move a client's freed extents in one commit.  The client had to free
+  a large number of extents that occupied distant positions in the
+  global free extent btree.  Very large fragmented files could cause
+  this.  The server now moves the freed extents in multiple commits and
+  can always ensure forward progress.
+
+* **Fixed possible persistent errors from freed duplicate extents**
+\
+  Background orphan deletion wasn't properly synchronizing with
+  foreground tasks deleting very large files.  If a deletion took long
+  enough then background deletion could also attempt to delete inode items
+  while the deletion was making progress.  This could create duplicate
+  deletions of data extent items which causes the server to abort when
+  it later discovers the duplicate extents as it merges free lists.
+
+---
+v1.6
+\
+*Jul 7, 2022*
+
+* **Fix memory leaks in rare corner cases**
+\
+  Analysis tools found a few corner cases that leaked small structures,
+  generally around error handling or startup and shutdown.
+
+* **Add --skip-likely-huge scoutfs print command option**
+\
+  Add an option to scoutfs print to reduce the size of the output
+  so that it can be used to see system-wide metadata without being
+  overwhelmed by file-level details.
+
+---
+v1.5
+\
+*Jun 21, 2022*
+
+* **Fix persistent error during server startup**
+\
+  Fixed a case where the server would always hit a consistent error on
+  seartup, preventing the system from mounting.  This required a rare
+  but valid state across the clients.
+
+* **Fix a client hang that would lead to fencing**
+\
+  The client module's use of in-kernel networking was missing annotation
+  that could lead to communication hanging.  The server would fence the
+  client when it stopped communicating.  This could be identified by the
+  server fencing a client after it disconnected with no attempt by the
+  client to reconnect.
+
+---
+v1.4
+\
+*May 6, 2022*
+
+* **Fix possible client crash during server failover**
+\
+  Fixed a narrow window during server failover and lock recovery that
+  could cause a client mount to believe that it had an inconsistent item
+  cache and panic.  This required very specific lock state and messaging
+  patterns between multiple mounts and multiple servers which made it
+  unlikely to occur in the field.
+
 ---
 v1.3
 \

kmod/src/Makefile

@@ -8,6 +8,7 @@ CFLAGS_scoutfs_trace.o = -I$(src) # define_trace.h double include
 -include $(src)/Makefile.kernelcompat
  
 scoutfs-y +=			\
+	acl.o			\
 	avl.o			\
 	alloc.o			\
 	block.o			\

kmod/src/Makefile.kernelcompat

@@ -34,3 +34,12 @@ endif
 ifneq (,$(shell grep 'FMODE_KABI_ITERATE' include/linux/fs.h))
 ccflags-y += -DKC_FMODE_KABI_ITERATE
 endif
+
+#
+# v4.7-rc2-23-g0d4d717f2583
+#
+# Added user_ns argument to posix_acl_valid
+#
+ifneq (,$(shell grep 'posix_acl_valid.*user_ns,' include/linux/posix_acl.h))
+ccflags-y += -DKC_POSIX_ACL_VALID_USER_NS
+endif

kmod/src/acl.c

@@ -0,0 +1,355 @@
+/*
+ * Copyright (C) 2022 Versity Software, Inc.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/xattr.h>
+#include <linux/posix_acl.h>
+#include <linux/posix_acl_xattr.h>
+
+#include "format.h"
+#include "super.h"
+#include "scoutfs_trace.h"
+#include "xattr.h"
+#include "acl.h"
+#include "inode.h"
+#include "trans.h"
+
+/*
+ * POSIX draft ACLs are stored as full xattr items with the entries
+ * encoded as the kernel's posix_acl_xattr_{header,entry} value structs.
+ *
+ * They're accessed and modified via user facing synthetic xattrs, iops
+ * calls from the kernel, during inode mode changes, and during inode
+ * creation.
+ *
+ * ACL access devolves into xattr access which is relatively expensive
+ * so we maintain the cached native form in the vfs inode.  We drop the
+ * cache in lock invalidation which means that cached acl access must
+ * always be performed under cluster locking.
+ */
+
+static int acl_xattr_name_len(int type, char **name, size_t *name_len)
+{
+	int ret = 0;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		*name = XATTR_NAME_POSIX_ACL_ACCESS;
+		if (name_len)
+			*name_len = sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1;
+		break;
+	case ACL_TYPE_DEFAULT:
+		*name = XATTR_NAME_POSIX_ACL_DEFAULT;
+		if (name_len)
+			*name_len = sizeof(XATTR_NAME_POSIX_ACL_DEFAULT) - 1;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+struct posix_acl *scoutfs_get_acl_locked(struct inode *inode, int type, struct scoutfs_lock *lock)
+{
+	struct posix_acl *acl;
+	char *value = NULL;
+	char *name;
+	int ret;
+
+	if (!IS_POSIXACL(inode))
+		return NULL;
+
+	acl = get_cached_acl(inode, type);
+	if (acl != ACL_NOT_CACHED)
+		return acl;
+
+	ret = acl_xattr_name_len(type, &name, NULL);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	ret = scoutfs_xattr_get_locked(inode, name, NULL, 0, lock);
+	if (ret > 0) {
+		value = kzalloc(ret, GFP_NOFS);
+		if (!value)
+			ret = -ENOMEM;
+		else
+			ret = scoutfs_xattr_get_locked(inode, name, value, ret, lock);
+	}
+	if (ret > 0) {
+		acl = posix_acl_from_xattr(&init_user_ns, value, ret);
+	} else if (ret == -ENODATA || ret == 0) {
+		acl = NULL;
+	} else {
+		acl = ERR_PTR(ret);
+	}
+
+	/* can set null negative cache */
+	if (!IS_ERR(acl))
+		set_cached_acl(inode, type, acl);
+
+	kfree(value);
+
+	return acl;
+}
+
+struct posix_acl *scoutfs_get_acl(struct inode *inode, int type)
+{
+	struct super_block *sb = inode->i_sb;
+	struct scoutfs_lock *lock = NULL;
+	struct posix_acl *acl;
+	int ret;
+
+	if (!IS_POSIXACL(inode))
+		return NULL;
+
+	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ, 0, inode, &lock);
+	if (ret < 0) {
+		acl = ERR_PTR(ret);
+	} else {
+		acl = scoutfs_get_acl_locked(inode, type, lock);
+		scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);
+	}
+
+	return acl;
+}
+
+/*
+ * The caller has acquired the locks and dirtied the inode, they'll
+ * update the inode item if we return 0.
+ */
+int scoutfs_set_acl_locked(struct inode *inode, struct posix_acl *acl, int type,
+			   struct scoutfs_lock *lock, struct list_head *ind_locks)
+{
+	static const struct scoutfs_xattr_prefix_tags tgs = {0,}; /* never scoutfs. prefix */
+	bool set_mode = false;
+	char *value = NULL;
+	umode_t new_mode;
+	size_t name_len;
+	char *name;
+	int size = 0;
+	int ret;
+
+	ret = acl_xattr_name_len(type, &name, &name_len);
+	if (ret < 0)
+		return ret;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		if (acl) {
+			ret = posix_acl_update_mode(inode, &new_mode, &acl);
+			if (ret < 0)
+				goto out;
+			set_mode = true;
+		}
+		break;
+	case ACL_TYPE_DEFAULT:
+		if (!S_ISDIR(inode->i_mode)) {
+			ret = acl ? -EINVAL : 0;
+			goto out;
+		}
+		break;
+	}
+
+	if (acl) {
+		size = posix_acl_xattr_size(acl->a_count);
+		value = kmalloc(size, GFP_NOFS);
+		if (!value) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		ret = posix_acl_to_xattr(&init_user_ns, acl, value, size);
+		if (ret < 0)
+			goto out;
+	}
+
+	ret = scoutfs_xattr_set_locked(inode, name, name_len, value, size, 0, &tgs,
+				       lock, NULL, ind_locks);
+	if (ret == 0 && set_mode) {
+		inode->i_mode = new_mode;
+		if (!value) {
+			/* can be setting an acl that only affects mode, didn't need xattr */
+			inode_inc_iversion(inode);
+			inode->i_ctime = CURRENT_TIME;
+		}
+	}
+
+out:
+	if (!ret)
+		set_cached_acl(inode, type, acl);
+
+	kfree(value);
+
+	return ret;
+}
+
+int scoutfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+{
+	struct super_block *sb = inode->i_sb;
+	struct scoutfs_lock *lock = NULL;
+	LIST_HEAD(ind_locks);
+	int ret;
+
+	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_WRITE, SCOUTFS_LKF_REFRESH_INODE, inode, &lock) ?:
+	      scoutfs_inode_index_lock_hold(inode, &ind_locks, false, true);
+	if (ret == 0) {
+		ret = scoutfs_dirty_inode_item(inode, lock) ?:
+		      scoutfs_set_acl_locked(inode, acl, type, lock, &ind_locks);
+		if (ret == 0)
+			scoutfs_update_inode_item(inode, lock, &ind_locks);
+
+		scoutfs_release_trans(sb);
+		scoutfs_inode_index_unlock(sb, &ind_locks);
+	}
+
+	scoutfs_unlock(sb, lock, SCOUTFS_LOCK_WRITE);
+	return ret;
+}
+
+int scoutfs_acl_get_xattr(struct dentry *dentry, const char *name, void *value, size_t size,
+			  int type)
+{
+	struct posix_acl *acl;
+	int ret = 0;
+
+	if (!IS_POSIXACL(dentry->d_inode))
+		return -EOPNOTSUPP;
+
+	acl = scoutfs_get_acl(dentry->d_inode, type);
+	if (IS_ERR(acl))
+		return PTR_ERR(acl);
+	if (acl == NULL)
+		return -ENODATA;
+
+	ret = posix_acl_to_xattr(&init_user_ns, acl, value, size);
+	posix_acl_release(acl);
+
+	return ret;
+}
+
+int scoutfs_acl_set_xattr(struct dentry *dentry, const char *name, const void *value, size_t size,
+			  int flags, int type)
+{
+	struct posix_acl *acl = NULL;
+	int ret;
+
+	if (!inode_owner_or_capable(dentry->d_inode))
+		return -EPERM;
+
+	if (!IS_POSIXACL(dentry->d_inode))
+		return -EOPNOTSUPP;
+
+	if (value) {
+		acl = posix_acl_from_xattr(&init_user_ns, value, size);
+		if (IS_ERR(acl))
+			return PTR_ERR(acl);
+
+		if (acl) {
+			ret = kc_posix_acl_valid(&init_user_ns, acl);
+			if (ret)
+				goto out;
+		}
+	}
+
+	ret = scoutfs_set_acl(dentry->d_inode, acl, type);
+out:
+	posix_acl_release(acl);
+
+	return ret;
+}
+
+/*
+ * Apply the parent's default acl to new inodes access acl and inherit
+ * it as the default for new directories.  The caller holds locks and a
+ * transaction.
+ */
+int scoutfs_init_acl_locked(struct inode *inode, struct inode *dir,
+			    struct scoutfs_lock *lock, struct scoutfs_lock *dir_lock,
+			    struct list_head *ind_locks)
+{
+	struct posix_acl *acl = NULL;
+	int ret = 0;
+
+	if (!S_ISLNK(inode->i_mode)) {
+		if (IS_POSIXACL(dir)) {
+			acl = scoutfs_get_acl_locked(dir, ACL_TYPE_DEFAULT, dir_lock);
+			if (IS_ERR(acl))
+				return PTR_ERR(acl);
+		}
+
+		if (!acl)
+			inode->i_mode &= ~current_umask();
+	}
+
+	if (IS_POSIXACL(dir) && acl) {
+		if (S_ISDIR(inode->i_mode)) {
+			ret = scoutfs_set_acl_locked(inode, acl, ACL_TYPE_DEFAULT,
+						     lock, ind_locks);
+			if (ret)
+				goto out;
+		}
+		ret = posix_acl_create(&acl, GFP_NOFS, &inode->i_mode);
+		if (ret < 0)
+			return ret;
+		if (ret > 0)
+			ret = scoutfs_set_acl_locked(inode, acl, ACL_TYPE_ACCESS,
+						     lock, ind_locks);
+	} else {
+		cache_no_acl(inode);
+	}
+out:
+	posix_acl_release(acl);
+	return ret;
+}
+
+/*
+ * Update the access ACL based on a newly set mode.  If we return an
+ * error then the xattr wasn't changed.
+ *
+ * Annoyingly, setattr_copy has logic that transforms the final set mode
+ * that we want to use to update the acl.   But we don't want to modify
+ * the other inode fields while discovering the resulting mode.  We're
+ * relying on acl_chmod not caring about the transformation (currently
+ * just clears sgid).  It would be better if we could get the resulting
+ * mode to give to acl_chmod without modifying the other inode fields.
+ *
+ * The caller has the inode mutex, a cluster lock, transaction, and will
+ * update the inode item if we return success.
+ */
+int scoutfs_acl_chmod_locked(struct inode *inode, struct iattr *attr,
+			     struct scoutfs_lock *lock, struct list_head *ind_locks)
+{
+	struct posix_acl *acl;
+	int ret = 0;
+
+	if (!IS_POSIXACL(inode) || !(attr->ia_valid & ATTR_MODE))
+		return 0;
+
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+
+	acl = scoutfs_get_acl_locked(inode, ACL_TYPE_ACCESS, lock);
+	if (IS_ERR_OR_NULL(acl))
+		return PTR_ERR(acl);
+
+	ret = posix_acl_chmod(&acl, GFP_KERNEL, attr->ia_mode);
+	if (ret)
+		return ret;
+
+	ret = scoutfs_set_acl_locked(inode, acl, ACL_TYPE_ACCESS, lock, ind_locks);
+	posix_acl_release(acl);
+	return ret;
+}

kmod/src/acl.h

@@ -0,0 +1,18 @@
+#ifndef _SCOUTFS_ACL_H_
+#define _SCOUTFS_ACL_H_
+
+struct posix_acl *scoutfs_get_acl(struct inode *inode, int type);
+struct posix_acl *scoutfs_get_acl_locked(struct inode *inode, int type, struct scoutfs_lock *lock);
+int scoutfs_set_acl(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);
+int scoutfs_acl_get_xattr(struct dentry *dentry, const char *name, void *value, size_t size,
+			  int type);
+int scoutfs_acl_set_xattr(struct dentry *dentry, const char *name, const void *value, size_t size,
+			  int flags, int type);
+int scoutfs_acl_chmod_locked(struct inode *inode, struct iattr *attr,
+			     struct scoutfs_lock *lock, struct list_head *ind_locks);
+int scoutfs_init_acl_locked(struct inode *inode, struct inode *dir,
+			    struct scoutfs_lock *lock, struct scoutfs_lock *dir_lock,
+			    struct list_head *ind_locks);
+#endif

kmod/src/alloc.c

@@ -84,6 +84,21 @@ static u64 smallest_order_length(u64 len)
 	return 1ULL << (free_extent_order(len) * 3);
 }
 
+/*
+ * 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) * 2) * 3;
+}
+
 /*
  * Free extents don't have flags and are stored in two indexes sorted by
  * block location and by length order, largest first.  The location key
@@ -877,6 +892,13 @@ static int find_zone_extent(struct super_block *sb, struct scoutfs_alloc_root *r
  * -ENOENT is returned if we run out of extents in the source tree
  * before moving the total.
  *
+ * If meta_budget is non-zero then -EINPROGRESS can be returned if the
+ * the caller's budget is consumed in the allocator during this call
+ * (though not necessarily by us, we don't have per-thread tracking of
+ * allocator consumption :/).  The call can still have made progress and
+ * caller is expected commit the dirty trees and examining the resulting
+ * modified trees to see if they need to continue moving extents.
+ *
  * The caller can specify that extents in the source tree should first
  * be found based on their zone bitmaps.  We'll first try to find
  * extents in the exclusive zones, then vacant zones, and then we'll
@@ -891,7 +913,7 @@ int scoutfs_alloc_move(struct super_block *sb, struct scoutfs_alloc *alloc,
 		       struct scoutfs_block_writer *wri,
 		       struct scoutfs_alloc_root *dst,
 		       struct scoutfs_alloc_root *src, u64 total,
-		       __le64 *exclusive, __le64 *vacant, u64 zone_blocks)
+		       __le64 *exclusive, __le64 *vacant, u64 zone_blocks, u64 meta_budget)
 {
 	struct alloc_ext_args args = {
 		.alloc = alloc,
@@ -899,6 +921,8 @@ int scoutfs_alloc_move(struct super_block *sb, struct scoutfs_alloc *alloc,
 	};
 	struct scoutfs_extent found;
 	struct scoutfs_extent ext;
+	u32 avail_start = 0;
+	u32 freed_start = 0;
 	u64 moved = 0;
 	u64 count;
 	int ret = 0;
@@ -909,6 +933,9 @@ int scoutfs_alloc_move(struct super_block *sb, struct scoutfs_alloc *alloc,
 		vacant = NULL;
 	}
 
+	if (meta_budget != 0)
+		scoutfs_alloc_meta_remaining(alloc, &avail_start, &freed_start);
+
 	while (moved < total) {
 		count = total - moved;
 
@@ -941,6 +968,24 @@ int scoutfs_alloc_move(struct super_block *sb, struct scoutfs_alloc *alloc,
 		if (ret < 0)
 			break;
 
+		if (meta_budget != 0 &&
+		    scoutfs_alloc_meta_low_since(alloc, avail_start, freed_start, meta_budget,
+						 extent_mod_blocks(src->root.height) +
+						 extent_mod_blocks(dst->root.height))) {
+			ret = -EINPROGRESS;
+			break;
+		}
+
+		/* return partial if the server alloc can't dirty any more */
+		if (scoutfs_alloc_meta_low(sb, alloc, 50 + extent_mod_blocks(src->root.height) +
+						      extent_mod_blocks(dst->root.height))) {
+			if (WARN_ON_ONCE(!moved))
+				ret = -ENOSPC;
+			else
+				ret = 0;
+			break;
+		}
+
 		/* searching set start/len, finish initializing alloced extent */
 		ext.map = found.map ? ext.start - found.start + found.map : 0;
 		ext.flags = found.flags;
@@ -1065,15 +1110,6 @@ out:
  * than completely exhausting the avail list or overflowing the freed
  * list.
  *
- * 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.
- *
  * The caller tells us how many extents they're about to modify and how
  * many other additional blocks they may cow manually.  And finally, the
  * caller could be the first to dirty the avail and freed blocks in the
@@ -1082,7 +1118,7 @@ out:
 static bool list_has_blocks(struct super_block *sb, struct scoutfs_alloc *alloc,
 			    struct scoutfs_alloc_root *root, u32 extents, u32 addl_blocks)
 {
-	u32 tree_blocks = (((1 + root->root.height) * 2) * 3) * extents;
+	u32 tree_blocks = extent_mod_blocks(root->root.height) * extents;
 	u32 most = 1 + tree_blocks + addl_blocks;
 
 	if (le32_to_cpu(alloc->avail.first_nr) < most) {
@@ -1329,6 +1365,27 @@ void scoutfs_alloc_meta_remaining(struct scoutfs_alloc *alloc, u32 *avail_total,
 	} while (read_seqretry(&alloc->seqlock, seq));
 }
 
+/*
+ * Returns true if the caller's consumption of nr from either avail or
+ * freed would end up exceeding their budget relative to the starting
+ * remaining snapshot they took.
+ */
+bool scoutfs_alloc_meta_low_since(struct scoutfs_alloc *alloc, u32 avail_start, u32 freed_start,
+				  u32 budget, u32 nr)
+{
+	u32 avail_use;
+	u32 freed_use;
+	u32 avail;
+	u32 freed;
+
+	scoutfs_alloc_meta_remaining(alloc, &avail, &freed);
+
+	avail_use = avail_start - avail;
+	freed_use = freed_start - freed;
+
+	return ((avail_use + nr) > budget) || ((freed_use + nr) > budget);
+}
+
 bool scoutfs_alloc_test_flag(struct super_block *sb,
 			    struct scoutfs_alloc *alloc, u32 flag)
 {
@@ -1525,12 +1582,10 @@ out:
  * call the caller's callback.  This assumes that the super it's reading
  * could be stale and will retry if it encounters stale blocks.
  */
-int scoutfs_alloc_foreach(struct super_block *sb,
-			  scoutfs_alloc_foreach_cb_t cb, void *arg)
+int scoutfs_alloc_foreach(struct super_block *sb, scoutfs_alloc_foreach_cb_t cb, void *arg)
 {
 	struct scoutfs_super_block *super = NULL;
-	struct scoutfs_block_ref stale_refs[2] = {{0,}};
-	struct scoutfs_block_ref refs[2] = {{0,}};
+	DECLARE_SAVED_REFS(saved);
 	int ret;
 
 	super = kmalloc(sizeof(struct scoutfs_super_block), GFP_NOFS);
@@ -1539,26 +1594,18 @@ int scoutfs_alloc_foreach(struct super_block *sb,
 		goto out;
 	}
 
-retry:
-	ret = scoutfs_read_super(sb, super);
-	if (ret < 0)
-		goto out;
+	do {
+		ret = scoutfs_read_super(sb, super);
+		if (ret < 0)
+			goto out;
 
-	refs[0] = super->logs_root.ref;
-	refs[1] = super->srch_root.ref;
+		ret = scoutfs_alloc_foreach_super(sb, super, cb, arg);
+
+		ret = scoutfs_block_check_stale(sb, ret, &saved, &super->logs_root.ref,
+						&super->srch_root.ref);
+	} while (ret == -ESTALE);
 
-	ret = scoutfs_alloc_foreach_super(sb, super, cb, arg);
 out:
-	if (ret == -ESTALE) {
-		if (memcmp(&stale_refs, &refs, sizeof(refs)) == 0) {
-			ret = -EIO;
-		} else {
-			BUILD_BUG_ON(sizeof(stale_refs) != sizeof(refs));
-			memcpy(stale_refs, refs, sizeof(stale_refs));
-			goto retry;
-		}
-	}
-
 	kfree(super);
 	return ret;
 }

kmod/src/alloc.h

@@ -19,14 +19,11 @@
 	(128ULL * 1024 * 1024 >> SCOUTFS_BLOCK_SM_SHIFT)
 
 /*
- * The largest aligned region that we'll try to allocate at the end of
- * the file as it's extended.  This is also limited to the current file
- * size so we can only waste at most twice the total file size when
- * files are less than this.  We try to keep this around the point of
- * diminishing returns in streaming performance of common data devices
- * to limit waste.
+ * The default size that we'll try to preallocate.  This is trying to
+ * hit the limit of large efficient device writes while minimizing
+ * wasted preallocation that is never used.
  */
-#define SCOUTFS_DATA_EXTEND_PREALLOC_LIMIT \
+#define SCOUTFS_DATA_PREALLOC_DEFAULT_BLOCKS \
 	(8ULL * 1024 * 1024 >> SCOUTFS_BLOCK_SM_SHIFT)
 
 /*
@@ -131,7 +128,7 @@ int scoutfs_alloc_move(struct super_block *sb, struct scoutfs_alloc *alloc,
 		       struct scoutfs_block_writer *wri,
 		       struct scoutfs_alloc_root *dst,
 		       struct scoutfs_alloc_root *src, u64 total,
-		       __le64 *exclusive, __le64 *vacant, u64 zone_blocks);
+		       __le64 *exclusive, __le64 *vacant, u64 zone_blocks, u64 meta_budget);
 int scoutfs_alloc_insert(struct super_block *sb, struct scoutfs_alloc *alloc,
 			 struct scoutfs_block_writer *wri, struct scoutfs_alloc_root *root,
 			 u64 start, u64 len);
@@ -159,6 +156,8 @@ int scoutfs_alloc_splice_list(struct super_block *sb,
 bool scoutfs_alloc_meta_low(struct super_block *sb,
 			    struct scoutfs_alloc *alloc, u32 nr);
 void scoutfs_alloc_meta_remaining(struct scoutfs_alloc *alloc, u32 *avail_total, u32 *freed_space);
+bool scoutfs_alloc_meta_low_since(struct scoutfs_alloc *alloc, u32 avail_start, u32 freed_start,
+				  u32 budget, u32 nr);
 bool scoutfs_alloc_test_flag(struct super_block *sb,
 			    struct scoutfs_alloc *alloc, u32 flag);
 

kmod/src/block.c

@@ -677,7 +677,7 @@ out:
 int scoutfs_block_read_ref(struct super_block *sb, struct scoutfs_block_ref *ref, u32 magic,
 			   struct scoutfs_block **bl_ret)
 {
-	struct scoutfs_super_block *super = &SCOUTFS_SB(sb)->super;
+	struct scoutfs_sb_info *sbi = SCOUTFS_SB(sb);
 	struct scoutfs_block_header *hdr;
 	struct block_private *bp = NULL;
 	bool retried = false;
@@ -701,7 +701,7 @@ retry:
 		set_bit(BLOCK_BIT_CRC_VALID, &bp->bits);
 	}
 
-	if (hdr->magic != cpu_to_le32(magic) || hdr->fsid != super->hdr.fsid ||
+	if (hdr->magic != cpu_to_le32(magic) || hdr->fsid != cpu_to_le64(sbi->fsid) ||
 	    hdr->seq != ref->seq || hdr->blkno != ref->blkno) {
 		ret = -ESTALE;
 		goto out;
@@ -728,6 +728,36 @@ out:
 	return ret;
 }
 
+static bool stale_refs_match(struct scoutfs_block_ref *caller, struct scoutfs_block_ref *saved)
+{
+	return !caller || (caller->blkno == saved->blkno && caller->seq == saved->seq);
+}
+
+/*
+ * Check if a read of a reference that gave ESTALE should be retried or
+ * should generate a hard error.  If this is the second time we got
+ * ESTALE from the same refs then we return EIO and the caller should
+ * stop.  As long as we keep seeing different refs we'll return ESTALE
+ * and the caller can keep trying.
+ */
+int scoutfs_block_check_stale(struct super_block *sb, int ret,
+			      struct scoutfs_block_saved_refs *saved,
+			      struct scoutfs_block_ref *a, struct scoutfs_block_ref *b)
+{
+	if (ret == -ESTALE) {
+		if (stale_refs_match(a, &saved->refs[0]) && stale_refs_match(b, &saved->refs[1])){
+			ret = -EIO;
+		} else {
+			if (a)
+				saved->refs[0] = *a;
+			if (b)
+				saved->refs[1] = *b;
+		}
+	}
+
+	return ret;
+}
+
 void scoutfs_block_put(struct super_block *sb, struct scoutfs_block *bl)
 {
 	if (!IS_ERR_OR_NULL(bl))
@@ -797,7 +827,7 @@ int scoutfs_block_dirty_ref(struct super_block *sb, struct scoutfs_alloc *alloc,
 			    u32 magic, struct scoutfs_block **bl_ret,
 			    u64 dirty_blkno, u64 *ref_blkno)
 {
-	struct scoutfs_super_block *super = &SCOUTFS_SB(sb)->super;
+	struct scoutfs_sb_info *sbi = SCOUTFS_SB(sb);
 	struct scoutfs_block *cow_bl = NULL;
 	struct scoutfs_block *bl = NULL;
 	struct block_private *exist_bp = NULL;
@@ -865,7 +895,7 @@ int scoutfs_block_dirty_ref(struct super_block *sb, struct scoutfs_alloc *alloc,
 
 	hdr = bl->data;
 	hdr->magic = cpu_to_le32(magic);
-	hdr->fsid = super->hdr.fsid;
+	hdr->fsid = cpu_to_le64(sbi->fsid);
 	hdr->blkno = cpu_to_le64(bl->blkno);
 	prandom_bytes(&hdr->seq, sizeof(hdr->seq));
 
@@ -1066,6 +1096,7 @@ static int block_shrink(struct shrinker *shrink, struct shrink_control *sc)
 	struct super_block *sb = binf->sb;
 	struct rhashtable_iter iter;
 	struct block_private *bp;
+	bool stop = false;
 	unsigned long nr;
 	u64 recently;
 
@@ -1077,7 +1108,6 @@ static int block_shrink(struct shrinker *shrink, struct shrink_control *sc)
 
 	nr = DIV_ROUND_UP(nr, SCOUTFS_BLOCK_LG_PAGES_PER);
 
-restart:
 	recently = accessed_recently(binf);
 	rhashtable_walk_enter(&binf->ht, &iter);
 	rhashtable_walk_start(&iter);
@@ -1099,12 +1129,15 @@ restart:
 		if (bp == NULL)
 			break;
 		if (bp == ERR_PTR(-EAGAIN)) {
-			/* hard exit to wait for rcu rebalance to finish */
-			rhashtable_walk_stop(&iter);
-			rhashtable_walk_exit(&iter);
-			scoutfs_inc_counter(sb, block_cache_shrink_restart);
-			synchronize_rcu();
-			goto restart;
+			/*
+			 * 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;
 		}
 
 		scoutfs_inc_counter(sb, block_cache_shrink_next);
@@ -1127,8 +1160,11 @@ restart:
 	rhashtable_walk_stop(&iter);
 	rhashtable_walk_exit(&iter);
 out:
-	return min_t(u64, (u64)atomic_read(&binf->total_inserted) * SCOUTFS_BLOCK_LG_PAGES_PER,
-		     INT_MAX);
+	if (stop)
+		return -1;
+	else
+		return min_t(u64, INT_MAX,
+			     (u64)atomic_read(&binf->total_inserted) * SCOUTFS_BLOCK_LG_PAGES_PER);
 }
 
 struct sm_block_completion {

kmod/src/block.h

@@ -13,6 +13,17 @@ struct scoutfs_block {
 	void *priv;
 };
 
+struct scoutfs_block_saved_refs {
+	struct scoutfs_block_ref refs[2];
+};
+
+#define DECLARE_SAVED_REFS(name) \
+	struct scoutfs_block_saved_refs name = {{{0,}}}
+
+int scoutfs_block_check_stale(struct super_block *sb, int ret,
+			      struct scoutfs_block_saved_refs *saved,
+			      struct scoutfs_block_ref *a, struct scoutfs_block_ref *b);
+
 int scoutfs_block_read_ref(struct super_block *sb, struct scoutfs_block_ref *ref, u32 magic,
 			   struct scoutfs_block **bl_ret);
 void scoutfs_block_put(struct super_block *sb, struct scoutfs_block *bl);

kmod/src/client.c

@@ -356,7 +356,6 @@ static int client_greeting(struct super_block *sb,
 {
 	struct scoutfs_sb_info *sbi = SCOUTFS_SB(sb);
 	struct client_info *client = sbi->client_info;
-	struct scoutfs_super_block *super = &SCOUTFS_SB(sb)->super;
 	struct scoutfs_net_greeting *gr = resp;
 	bool new_server;
 	int ret;
@@ -371,9 +370,9 @@ static int client_greeting(struct super_block *sb,
 		goto out;
 	}
 
-	if (gr->fsid != super->hdr.fsid) {
+	if (gr->fsid != cpu_to_le64(sbi->fsid)) {
 		scoutfs_warn(sb, "server greeting response fsid 0x%llx did not match client fsid 0x%llx",
-			     le64_to_cpu(gr->fsid), le64_to_cpu(super->hdr.fsid));
+			     le64_to_cpu(gr->fsid), sbi->fsid);
 		ret = -EINVAL;
 		goto out;
 	}
@@ -476,7 +475,6 @@ static void scoutfs_client_connect_worker(struct work_struct *work)
 						  connect_dwork.work);
 	struct super_block *sb = client->sb;
 	struct scoutfs_sb_info *sbi = SCOUTFS_SB(sb);
-	struct scoutfs_super_block *super = &sbi->super;
 	struct scoutfs_mount_options opts;
 	struct scoutfs_net_greeting greet;
 	struct sockaddr_in sin;
@@ -508,7 +506,7 @@ static void scoutfs_client_connect_worker(struct work_struct *work)
 		goto out;
 
 	/* send a greeting to verify endpoints of each connection */
-	greet.fsid = super->hdr.fsid;
+	greet.fsid = cpu_to_le64(sbi->fsid);
 	greet.fmt_vers = cpu_to_le64(sbi->fmt_vers);
 	greet.server_term = cpu_to_le64(client->server_term);
 	greet.rid = cpu_to_le64(sbi->rid);

kmod/src/counters.h

@@ -34,7 +34,7 @@
 	EXPAND_COUNTER(block_cache_shrink_next)			\
 	EXPAND_COUNTER(block_cache_shrink_recent)		\
 	EXPAND_COUNTER(block_cache_shrink_remove)		\
-	EXPAND_COUNTER(block_cache_shrink_restart)		\
+	EXPAND_COUNTER(block_cache_shrink_stop)			\
 	EXPAND_COUNTER(btree_compact_values)			\
 	EXPAND_COUNTER(btree_compact_values_enomem)		\
 	EXPAND_COUNTER(btree_delete)				\
@@ -75,8 +75,6 @@
 	EXPAND_COUNTER(data_write_begin_enobufs_retry)		\
 	EXPAND_COUNTER(dentry_revalidate_error)			\
 	EXPAND_COUNTER(dentry_revalidate_invalid)		\
-	EXPAND_COUNTER(dentry_revalidate_locked)		\
-	EXPAND_COUNTER(dentry_revalidate_orphan)		\
 	EXPAND_COUNTER(dentry_revalidate_rcu)			\
 	EXPAND_COUNTER(dentry_revalidate_root)			\
 	EXPAND_COUNTER(dentry_revalidate_valid)			\
@@ -168,6 +166,7 @@
 	EXPAND_COUNTER(quorum_recv_resignation)			\
 	EXPAND_COUNTER(quorum_recv_vote)			\
 	EXPAND_COUNTER(quorum_send_heartbeat)			\
+	EXPAND_COUNTER(quorum_send_heartbeat_dropped)		\
 	EXPAND_COUNTER(quorum_send_resignation)			\
 	EXPAND_COUNTER(quorum_send_request)			\
 	EXPAND_COUNTER(quorum_send_vote)			\
@@ -189,8 +188,6 @@
 	EXPAND_COUNTER(srch_search_retry_empty)			\
 	EXPAND_COUNTER(srch_search_sorted)			\
 	EXPAND_COUNTER(srch_search_sorted_block)		\
-	EXPAND_COUNTER(srch_search_stale_eio)			\
-	EXPAND_COUNTER(srch_search_stale_retry)			\
 	EXPAND_COUNTER(srch_search_xattrs)			\
 	EXPAND_COUNTER(srch_read_stale)				\
 	EXPAND_COUNTER(statfs)					\

kmod/src/data.c

@@ -366,27 +366,27 @@ static inline u64 ext_last(struct scoutfs_extent *ext)
 
 /*
  * The caller is writing to a logical iblock that doesn't have an
- * allocated extent.
+ * allocated extent.  The caller has searched for an extent containing
+ * iblock.  If it already existed then it must be unallocated and
+ * offline.
  *
- * We always allocate an extent starting at the logical iblock.  The
- * caller has searched for an extent containing iblock.  If it already
- * existed then it must be unallocated and offline.
+ * We implement two preallocation strategies.  Typically we only
+ * preallocate for simple streaming writes and limit preallocation while
+ * the file is small.   The largest efficient allocation size is
+ * typically large enough that it would be unreasonable to allocate that
+ * much for all small files.
  *
- * Preallocation is used if we're strictly contiguously extending
- * writes.  That is, if the logical block offset equals the number of
- * online blocks.  We try to preallocate the number of blocks existing
- * so that small files don't waste inordinate amounts of space and large
- * files will eventually see large extents.  This only works for
- * contiguous single stream writes or stages of files from the first
- * block.  It doesn't work for concurrent stages, releasing behind
- * staging, sparse files, multi-node writes, etc.  fallocate() is always
- * a better tool to use.
+ * Optionally, we can simply preallocate large empty aligned regions.
+ * This can waste a lot of space for small or sparse files but is
+ * reasonable when a file population is known to be large and dense but
+ * known to be written with non-streaming write patterns.
  */
 static int alloc_block(struct super_block *sb, struct inode *inode,
 		       struct scoutfs_extent *ext, u64 iblock,
 		       struct scoutfs_lock *lock)
 {
 	DECLARE_DATA_INFO(sb, datinf);
+	struct scoutfs_mount_options opts;
 	const u64 ino = scoutfs_ino(inode);
 	struct data_ext_args args = {
 		.ino = ino,
@@ -394,17 +394,22 @@ static int alloc_block(struct super_block *sb, struct inode *inode,
 		.lock = lock,
 	};
 	struct scoutfs_extent found;
-	struct scoutfs_extent pre;
+	struct scoutfs_extent pre = {0,};
+	bool undo_pre = false;
 	u64 blkno = 0;
 	u64 online;
 	u64 offline;
 	u8 flags;
+	u64 start;
 	u64 count;
+	u64 rem;
 	int ret;
 	int err;
 
 	trace_scoutfs_data_alloc_block_enter(sb, ino, iblock, ext);
 
+	scoutfs_options_read(sb, &opts);
+
 	/* can only allocate over existing unallocated offline extent */
 	if (WARN_ON_ONCE(ext->len &&
 			 !(iblock >= ext->start && iblock <= ext_last(ext) &&
@@ -413,66 +418,118 @@ static int alloc_block(struct super_block *sb, struct inode *inode,
 
 	mutex_lock(&datinf->mutex);
 
-	scoutfs_inode_get_onoff(inode, &online, &offline);
+	/* default to single allocation at the written block */
+	start = iblock;
+	count = 1;
+	/* copy existing flags for preallocated regions */
+	flags = ext->len ? ext->flags : 0;
 
 	if (ext->len) {
-		/* limit preallocation to remaining existing (offline) extent */
+		/*
+		 * Assume that offline writers are going to be writing
+		 * all the offline extents and try to preallocate the
+		 * rest of the unwritten extent.
+		 */
 		count = ext->len - (iblock - ext->start);
-		flags = ext->flags;
+
+	} else if (opts.data_prealloc_contig_only) {
+		/*
+		 * Only preallocate when a quick test of the online
+		 * block counts looks like we're a simple streaming
+		 * write.  Try to write until the next extent but limit
+		 * the preallocation size to the number of online
+		 * blocks.
+		 */
+		scoutfs_inode_get_onoff(inode, &online, &offline);
+		if (iblock > 1 && iblock == online) {
+			ret = scoutfs_ext_next(sb, &data_ext_ops, &args,
+					       iblock, 1, &found);
+			if (ret < 0 && ret != -ENOENT)
+				goto out;
+			if (found.len && found.start > iblock)
+				count = found.start - iblock;
+			else
+				count = opts.data_prealloc_blocks;
+
+			count = min(iblock, count);
+		}
+
 	} else {
-		/* otherwise alloc to next extent */
-		ret = scoutfs_ext_next(sb, &data_ext_ops, &args,
-				       iblock, 1, &found);
+		/*
+		 * Preallocation within aligned regions tries to
+		 * allocate an extent to fill the hole in the region
+		 * that contains iblock.  We'd have to add a bit of plumbing
+		 * to find previous extents so we only search for a next
+		 * extent from the front of the region and from iblock.
+		 */
+		div64_u64_rem(iblock, opts.data_prealloc_blocks, &rem);
+		start = iblock - rem;
+		count = opts.data_prealloc_blocks;
+		ret = scoutfs_ext_next(sb, &data_ext_ops, &args, start, 1, &found);
 		if (ret < 0 && ret != -ENOENT)
 			goto out;
-		if (found.len && found.start > iblock)
-			count = found.start - iblock;
-		else
-			count = SCOUTFS_DATA_EXTEND_PREALLOC_LIMIT;
-		flags = 0;
+
+		/* trim count if there's an extent in the region before iblock */
+		if (found.len && found.start < iblock) {
+			count -= iblock - start;
+			start = iblock;
+			/* see if there's also an extent after iblock */
+			ret = scoutfs_ext_next(sb, &data_ext_ops, &args, iblock, 1, &found);
+			if (ret < 0 && ret != -ENOENT)
+				goto out;
+		}
+
+		/* trim count by next extent after iblock */
+		if (found.len && found.start > start && found.start < start + count)
+			count = (found.start - start);
 	}
 
 	/* overall prealloc limit */
-	count = min_t(u64, count, SCOUTFS_DATA_EXTEND_PREALLOC_LIMIT);
-
-	/* only strictly contiguous extending writes will try to preallocate */
-	if (iblock > 1 && iblock == online)
-		count = min(iblock, count);
-	else
-		count = 1;
+	count = min_t(u64, count, opts.data_prealloc_blocks);
 
 	ret = scoutfs_alloc_data(sb, datinf->alloc, datinf->wri,
 				 &datinf->dalloc, count, &blkno, &count);
 	if (ret < 0)
 		goto out;
 
-	ret = scoutfs_ext_set(sb, &data_ext_ops, &args, iblock, 1, blkno, 0);
-	if (ret < 0)
-		goto out;
+	/*
+	 * An aligned prealloc attempt that gets a smaller extent can
+	 * fail to cover iblock, make sure that it does.  This is a
+	 * pathological case so we don't try to move the window past
+	 * iblock.  Just enough to cover it, which we know is safe.
+	 */
+	if (start + count <= iblock)
+		start += (iblock - (start + count) + 1);
 
 	if (count > 1) {
-		pre.start = iblock + 1;
-		pre.len = count - 1;
-		pre.map = blkno + 1;
+		pre.start = start;
+		pre.len = count;
+		pre.map = blkno;
 		pre.flags = flags | SEF_UNWRITTEN;
 		ret = scoutfs_ext_set(sb, &data_ext_ops, &args, pre.start,
 				      pre.len, pre.map, pre.flags);
-		if (ret < 0) {
-			err = scoutfs_ext_set(sb, &data_ext_ops, &args, iblock,
-					      1, 0, flags);
-			BUG_ON(err); /* couldn't restore original */
+		if (ret < 0)
 			goto out;
-		}
+		undo_pre = true;
 	}
 
+	ret = scoutfs_ext_set(sb, &data_ext_ops, &args, iblock, 1, blkno + (iblock - start), 0);
+	if (ret < 0)
+		goto out;
+
 	/* tell the caller we have a single block, could check next? */
 	ext->start = iblock;
 	ext->len = 1;
-	ext->map = blkno;
+	ext->map = blkno + (iblock - start);
 	ext->flags = 0;
 	ret = 0;
 out:
 	if (ret < 0 && blkno > 0) {
+		if (undo_pre) {
+			err = scoutfs_ext_set(sb, &data_ext_ops, &args,
+					      pre.start, pre.len, 0, flags);
+			BUG_ON(err); /* leaked preallocated extent */
+		}
 		err = scoutfs_free_data(sb, datinf->alloc, datinf->wri,
 				        &datinf->data_freed, blkno, count);
 		BUG_ON(err); /* leaked free blocks */
@@ -586,8 +643,8 @@ static int scoutfs_get_block_read(struct inode *inode, sector_t iblock,
 	return ret;
 }
 
-static int scoutfs_get_block_write(struct inode *inode, sector_t iblock,
-				   struct buffer_head *bh, int create)
+int scoutfs_get_block_write(struct inode *inode, sector_t iblock, struct buffer_head *bh,
+			    int create)
 {
 	struct scoutfs_inode_info *si = SCOUTFS_I(inode);
 	int ret;
@@ -1147,9 +1204,9 @@ static void truncate_inode_pages_extent(struct inode *inode, u64 start, u64 len)
  * explained above the move_blocks ioctl argument structure definition.
  *
  * The caller has processed the ioctl args and performed the most basic
- * inode checks, but we perform more detailed inode checks once we have
- * the inode lock and refreshed inodes.  Our job is to safely lock the
- * two files and move the extents.
+ * argument sanity and inode checks, but we perform more detailed inode
+ * checks once we have the inode lock and refreshed inodes.  Our job is
+ * to safely lock the two files and move the extents.
  */
 #define MOVE_DATA_EXTENTS_PER_HOLD 16
 int scoutfs_data_move_blocks(struct inode *from, u64 from_off,
@@ -1208,6 +1265,16 @@ int scoutfs_data_move_blocks(struct inode *from, u64 from_off,
 	from_iblock = from_off >> SCOUTFS_BLOCK_SM_SHIFT;
 	count = (byte_len + SCOUTFS_BLOCK_SM_MASK) >> SCOUTFS_BLOCK_SM_SHIFT;
 	to_iblock = to_off >> SCOUTFS_BLOCK_SM_SHIFT;
+	from_start = from_iblock;
+
+	/* only move extent blocks inside i_size, careful not to wrap */
+	from_size = i_size_read(from);
+	if (from_off >= from_size) {
+		ret = 0;
+		goto out;
+	}
+	if (from_off + byte_len > from_size)
+		count = ((from_size - from_off) + SCOUTFS_BLOCK_SM_MASK) >> SCOUTFS_BLOCK_SM_SHIFT;
 
 	if (S_ISDIR(from->i_mode) || S_ISDIR(to->i_mode)) {
 		ret = -EISDIR;
@@ -1275,7 +1342,7 @@ int scoutfs_data_move_blocks(struct inode *from, u64 from_off,
 
 			/* find the next extent to move */
 			ret = scoutfs_ext_next(sb, &data_ext_ops, &from_args,
-					       from_iblock, 1, &ext);
+					       from_start, 1, &ext);
 			if (ret < 0) {
 				if (ret == -ENOENT) {
 					done = true;
@@ -1284,9 +1351,8 @@ int scoutfs_data_move_blocks(struct inode *from, u64 from_off,
 				break;
 			}
 
-			/* only move extents within count and i_size */
-			if (ext.start >= from_iblock + count ||
-			    ext.start >= i_size_read(from)) {
+			/* done if next extent starts after moving region */
+			if (ext.start >= from_iblock + count) {
 				done = true;
 				ret = 0;
 				break;
@@ -1294,13 +1360,15 @@ int scoutfs_data_move_blocks(struct inode *from, u64 from_off,
 
 			from_start = max(ext.start, from_iblock);
 			map = ext.map + (from_start - ext.start);
-			len = min3(from_iblock + count,
-				   round_up((u64)i_size_read(from),
-					    SCOUTFS_BLOCK_SM_SIZE),
-				   ext.start + ext.len) - from_start;
-
+			len = min(from_iblock + count, ext.start + ext.len) - from_start;
 			to_start = to_iblock + (from_start - from_iblock);
 
+			/* we'd get stuck, shouldn't happen */
+			if (WARN_ON_ONCE(len == 0)) {
+				ret = -EIO;
+				goto out;
+			}
+
 			if (is_stage) {
 				ret = scoutfs_ext_next(sb, &data_ext_ops, &to_args,
 						       to_start, 1, &off_ext);
@@ -1362,6 +1430,12 @@ int scoutfs_data_move_blocks(struct inode *from, u64 from_off,
 							i_size_read(from);
 				i_size_write(to, to_size);
 			}
+
+			/* find next after moved extent, avoiding wrapping */
+			if (from_start + len < from_start)
+				from_start = from_iblock + count + 1;
+			else
+				from_start += len;
 		}
 
 

kmod/src/data.h

@@ -43,6 +43,9 @@ extern const struct file_operations scoutfs_file_fops;
 struct scoutfs_alloc;
 struct scoutfs_block_writer;
 
+int scoutfs_get_block_write(struct inode *inode, sector_t iblock, struct buffer_head *bh,
+			    int create);
+
 int scoutfs_data_truncate_items(struct super_block *sb, struct inode *inode,
 				u64 ino, u64 iblock, u64 last, bool offline,
 				struct scoutfs_lock *lock);

kmod/src/dir.c

@@ -32,6 +32,7 @@
 #include "hash.h"
 #include "omap.h"
 #include "forest.h"
+#include "acl.h"
 #include "counters.h"
 #include "scoutfs_trace.h"
 
@@ -59,8 +60,6 @@
  * All the entries have a dirent struct with the full name in their
  * value.  The dirent struct contains the name hash and readdir position
  * so that any item use can reference all the items for a given entry.
- * This is important for deleting all the items given a dentry that was
- * populated by lookup.
  */
 
 static unsigned int mode_to_type(umode_t mode)
@@ -99,100 +98,12 @@ static unsigned int dentry_type(enum scoutfs_dentry_type type)
 	return DT_UNKNOWN;
 }
 
-/*
- * @lock_cov: tells revalidation that the dentry is still locked and valid.
- *
- * @pos, @hash: lets us remove items on final unlink without having to
- * look them up.
- */
-struct dentry_info {
-	struct scoutfs_lock_coverage lock_cov;
-	u64 hash;
-	u64 pos;
-};
-
-static struct kmem_cache *dentry_info_cache;
-
-static void scoutfs_d_release(struct dentry *dentry)
-{
-	struct super_block *sb = dentry->d_sb;
-	struct dentry_info *di = dentry->d_fsdata;
-
-	if (di) {
-		scoutfs_lock_del_coverage(sb, &di->lock_cov);
-		kmem_cache_free(dentry_info_cache, di);
-		dentry->d_fsdata = NULL;
-	}
-}
-
 static int scoutfs_d_revalidate(struct dentry *dentry, unsigned int flags);
 
-static const struct dentry_operations scoutfs_dentry_ops = {
-	.d_release = scoutfs_d_release,
+const struct dentry_operations scoutfs_dentry_ops = {
 	.d_revalidate = scoutfs_d_revalidate,
 };
 
-static int alloc_dentry_info(struct dentry *dentry)
-{
-	struct dentry_info *di;
-
-	smp_rmb();
-	if (dentry->d_op == &scoutfs_dentry_ops)
-		return 0;
-
-	di = kmem_cache_zalloc(dentry_info_cache, GFP_NOFS);
-	if (!di)
-		return -ENOMEM;
-
-	scoutfs_lock_init_coverage(&di->lock_cov);
-
-	spin_lock(&dentry->d_lock);
-	if (!dentry->d_fsdata) {
-		dentry->d_fsdata = di;
-		smp_wmb();
-		d_set_d_op(dentry, &scoutfs_dentry_ops);
-	}
-	spin_unlock(&dentry->d_lock);
-
-	if (di != dentry->d_fsdata)
-		kmem_cache_free(dentry_info_cache, di);
-
-	return 0;
-}
-
-static void update_dentry_info(struct super_block *sb, struct dentry *dentry,
-			       u64 hash, u64 pos, struct scoutfs_lock *lock)
-{
-	struct dentry_info *di = dentry->d_fsdata;
-
-	if (WARN_ON_ONCE(di == NULL))
-		return;
-
-	scoutfs_lock_add_coverage(sb, lock, &di->lock_cov);
-	di->hash = hash;
-	di->pos = pos;
-}
-
-static u64 dentry_info_hash(struct dentry *dentry)
-{
-	struct dentry_info *di = dentry->d_fsdata;
-
-	if (WARN_ON_ONCE(di == NULL))
-		return 0;
-
-	return di->hash;
-}
-
-static u64 dentry_info_pos(struct dentry *dentry)
-{
-	struct dentry_info *di = dentry->d_fsdata;
-
-	if (WARN_ON_ONCE(di == NULL))
-		return 0;
-
-	return di->pos;
-}
-
 static void init_dirent_key(struct scoutfs_key *key, u8 type, u64 ino,
 			    u64 major, u64 minor)
 {
@@ -317,62 +228,105 @@ out:
 	return ret;
 }
 
-/*
- * Verify that the caller's dentry still precisely matches our dirent
- * items.
- *
- * The caller has a dentry that the vfs revalidated before they acquired
- * their locks.  If the dentry is still covered by a lock we immediately
- * return 0.   If not, we check items and return -ENOENT if a positive
- * dentry no longer matches the items or -EEXIST if a negative entry's
- * name now has an item.
- */
-static int verify_entry(struct super_block *sb, u64 dir_ino, struct dentry *dentry,
-			struct scoutfs_lock *lock)
+static int lookup_dentry_dirent(struct super_block *sb, u64 dir_ino, struct dentry *dentry,
+				struct scoutfs_dirent *dent_ret,
+				struct scoutfs_lock *lock)
 {
-	struct dentry_info *di = dentry->d_fsdata;
+	return lookup_dirent(sb, dir_ino, dentry->d_name.name, dentry->d_name.len,
+			     dirent_name_hash(dentry->d_name.name, dentry->d_name.len),
+			     dent_ret, lock);
+}
+
+static u64 dentry_parent_ino(struct dentry *dentry)
+{
+	struct dentry *parent = NULL;
+	struct inode *dir;
+	u64 dir_ino = 0;
+
+	if ((parent = dget_parent(dentry)) && (dir = parent->d_inode))
+		dir_ino = scoutfs_ino(dir);
+
+	dput(parent);
+	return dir_ino;
+}
+
+/* negative dentries return 0, our root ino is non-zero (1) */
+static u64 dentry_ino(struct dentry *dentry)
+{
+	return dentry->d_inode ? scoutfs_ino(dentry->d_inode) : 0;
+}
+
+static void set_dentry_fsdata(struct dentry *dentry, struct scoutfs_lock *lock)
+{
+	void *now = (void *)(unsigned long)lock->refresh_gen;
+	void *was;
+
+	/* didn't want to alloc :/ */
+	BUILD_BUG_ON(sizeof(dentry->d_fsdata) != sizeof(u64));
+	BUILD_BUG_ON(sizeof(dentry->d_fsdata) != sizeof(long));
+
+	do {
+		was = dentry->d_fsdata;
+	} while (cmpxchg(&dentry->d_fsdata, was, now) != was);
+}
+
+static bool test_dentry_fsdata(struct dentry *dentry, u64 refresh)
+{
+	u64 fsd = (unsigned long)ACCESS_ONCE(dentry->d_fsdata);
+
+	return fsd == refresh;
+}
+
+/*
+ * Validate an operation caller's input dentry argument.  If the fsdata
+ * is valid then the underlying dirent items couldn't have changed and
+ * we return 0.  If fsdata is no longer protected by a lock or its
+ * fields don't match then we check the dirent item.  If the dirent item
+ * doesn't match what the caller expected given their dentry fields then
+ * we return an error.
+ */
+static int validate_dentry(struct super_block *sb, u64 dir_ino, struct dentry *dentry,
+			   struct scoutfs_lock *lock)
+{
+	u64 ino = dentry_ino(dentry);
 	struct scoutfs_dirent dent = {0,};
-	const char *name;
-	u64 dentry_ino;
-	int name_len;
-	u64 hash;
 	int ret;
 
-	if (scoutfs_lock_is_covered(sb, &di->lock_cov))
-		return 0;
+	if (test_dentry_fsdata(dentry, lock->refresh_gen)) {
+		ret = 0;
+		goto out;
+	}
 
-	dentry_ino = dentry->d_inode ? scoutfs_ino(dentry->d_inode) : 0;
-	name = dentry->d_name.name;
-	name_len = dentry->d_name.len;
-	hash = dirent_name_hash(name, name_len);
-
-	ret = lookup_dirent(sb, dir_ino, name, name_len, hash, &dent, lock);
+	ret = lookup_dentry_dirent(sb, dir_ino, dentry, &dent, lock);
 	if (ret < 0 && ret != -ENOENT)
-		return ret;
+		goto out;
 
-	if (dentry_ino != le64_to_cpu(dent.ino) || di->hash != le64_to_cpu(dent.hash) ||
-	    di->pos != le64_to_cpu(dent.pos)) {
-		if (dentry_ino)
-			ret = -ENOENT;
-		else
-			ret = -EEXIST;
+	/* use negative zeroed dent when lookup gave -ENOENT */
+	if (!ino && dent.ino) {
+		/* caller expected negative but there was a dirent */
+		ret = -EEXIST;
+	} else if (ino && !dent.ino) {
+		/* caller expected positive but there was no dirent */
+		ret = -ENOENT;
+	} else if (ino != le64_to_cpu(dent.ino)) {
+		/* name linked to different inode than caller's */
+		ret = -ESTALE;
 	} else {
+		/* dirent ino matches dentry ino */
 		ret = 0;
 	}
 
+out:
+	trace_scoutfs_validate_dentry(sb, dentry, dir_ino, ino, le64_to_cpu(dent.ino),
+				      lock->refresh_gen, ret);
+
 	return ret;
 }
 
 static int scoutfs_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct super_block *sb = dentry->d_sb;
-	struct dentry_info *di = dentry->d_fsdata;
-	struct dentry *parent = dget_parent(dentry);
-	struct scoutfs_lock *lock = NULL;
-	struct scoutfs_dirent dent;
-	bool is_covered = false;
-	struct inode *dir;
-	u64 dentry_ino;
+	u64 dir_ino = dentry_parent_ino(dentry);
 	int ret;
 
 	/* don't think this happens but we can find out */
@@ -394,47 +348,7 @@ static int scoutfs_d_revalidate(struct dentry *dentry, unsigned int flags)
 		goto out;
 	}
 
-	if (WARN_ON_ONCE(di == NULL)) {
-		ret = 0;
-		goto out;
-	}
-
-	is_covered = scoutfs_lock_is_covered(sb, &di->lock_cov);
-	if (is_covered) {
-		scoutfs_inc_counter(sb, dentry_revalidate_locked);
-		ret = 1;
-		goto out;
-	}
-
-	if (!parent || !parent->d_inode) {
-		scoutfs_inc_counter(sb, dentry_revalidate_orphan);
-		ret = 0;
-		goto out;
-	}
-	dir = parent->d_inode;
-
-	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ, 0, dir, &lock);
-	if (ret)
-		goto out;
-
-	ret = lookup_dirent(sb, scoutfs_ino(dir),
-			    dentry->d_name.name, dentry->d_name.len,
-			    dirent_name_hash(dentry->d_name.name,
-					     dentry->d_name.len),
-			    &dent, lock);
-	if (ret == -ENOENT) {
-		dent.ino = 0;
-		dent.hash = 0;
-		dent.pos = 0;
-	} else if (ret < 0) {
-		goto out;
-	}
-
-	dentry_ino = dentry->d_inode ? scoutfs_ino(dentry->d_inode) : 0;
-
-	if ((dentry_ino == le64_to_cpu(dent.ino))) {
-		update_dentry_info(sb, dentry, le64_to_cpu(dent.hash),
-				   le64_to_cpu(dent.pos), lock);
+	if (test_dentry_fsdata(dentry, scoutfs_lock_ino_refresh_gen(sb, dir_ino))) {
 		scoutfs_inc_counter(sb, dentry_revalidate_valid);
 		ret = 1;
 	} else {
@@ -443,10 +357,7 @@ static int scoutfs_d_revalidate(struct dentry *dentry, unsigned int flags)
 	}
 
 out:
-	trace_scoutfs_d_revalidate(sb, dentry, flags, parent, is_covered, ret);
-
-	dput(parent);
-	scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);
+	trace_scoutfs_d_revalidate(sb, dentry, flags, dir_ino, ret);
 
 	if (ret < 0 && ret != -ECHILD)
 		scoutfs_inc_counter(sb, dentry_revalidate_error);
@@ -483,10 +394,6 @@ static struct dentry *scoutfs_lookup(struct inode *dir, struct dentry *dentry,
 		goto out;
 	}
 
-	ret = alloc_dentry_info(dentry);
-	if (ret)
-		goto out;
-
 	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ, 0, dir, &dir_lock);
 	if (ret)
 		goto out;
@@ -500,8 +407,7 @@ static struct dentry *scoutfs_lookup(struct inode *dir, struct dentry *dentry,
 		ino = le64_to_cpu(dent.ino);
 	}
 	if (ret == 0)
-		update_dentry_info(sb, dentry, le64_to_cpu(dent.hash),
-				   le64_to_cpu(dent.pos), dir_lock);
+		set_dentry_fsdata(dentry, dir_lock);
 
 	scoutfs_unlock(sb, dir_lock, SCOUTFS_LOCK_READ);
 
@@ -725,10 +631,6 @@ static struct inode *lock_hold_create(struct inode *dir, struct dentry *dentry,
 	int ret = 0;
 	u64 ino;
 
-	ret = alloc_dentry_info(dentry);
-	if (ret)
-		return ERR_PTR(ret);
-
 	ret = scoutfs_alloc_ino(sb, S_ISDIR(mode), &ino);
 	if (ret)
 		return ERR_PTR(ret);
@@ -765,7 +667,8 @@ retry:
 	if (ret)
 		goto out_unlock;
 
-	ret = scoutfs_new_inode(sb, dir, mode, rdev, ino, *inode_lock, &inode);
+	ret = scoutfs_new_inode(sb, dir, mode, rdev, ino, *inode_lock, &inode) ?:
+	      scoutfs_init_acl_locked(inode, dir, *inode_lock, *dir_lock, ind_locks);
 	if (ret < 0)
 		goto out;
 
@@ -816,7 +719,7 @@ static int scoutfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
 		return PTR_ERR(inode);
 	si = SCOUTFS_I(inode);
 
-	ret = verify_entry(sb, scoutfs_ino(dir), dentry, dir_lock);
+	ret = validate_dentry(sb, scoutfs_ino(dir), dentry, dir_lock);
 	if (ret < 0)
 		goto out;
 
@@ -829,7 +732,7 @@ static int scoutfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
 	if (ret)
 		goto out;
 
-	update_dentry_info(sb, dentry, hash, pos, dir_lock);
+	set_dentry_fsdata(dentry, dir_lock);
 
 	i_size_write(dir, i_size_read(dir) + dentry->d_name.len);
 	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
@@ -903,19 +806,15 @@ static int scoutfs_link(struct dentry *old_dentry,
 	if (ret)
 		return ret;
 
+	ret = validate_dentry(sb, scoutfs_ino(dir), dentry, dir_lock);
+	if (ret < 0)
+		goto out_unlock;
+
 	if (inode->i_nlink >= SCOUTFS_LINK_MAX) {
 		ret = -EMLINK;
 		goto out_unlock;
 	}
 
-	ret = alloc_dentry_info(dentry);
-	if (ret)
-		goto out_unlock;
-
-	ret = verify_entry(sb, scoutfs_ino(dir), dentry, dir_lock);
-	if (ret < 0)
-		goto out_unlock;
-
 	dir_size = i_size_read(dir) + dentry->d_name.len;
 
 	if (inode->i_nlink == 0) {
@@ -941,7 +840,7 @@ retry:
 		goto out;
 
 	if (del_orphan) {
-		ret = scoutfs_inode_orphan_delete(sb, scoutfs_ino(inode), orph_lock);
+		ret = scoutfs_inode_orphan_delete(sb, scoutfs_ino(inode), orph_lock, inode_lock);
 		if (ret)
 			goto out;
 	}
@@ -953,11 +852,11 @@ retry:
 			      scoutfs_ino(inode), inode->i_mode, dir_lock,
 			      inode_lock);
 	if (ret) {
-		err = scoutfs_inode_orphan_create(sb, scoutfs_ino(inode), orph_lock);
+		err = scoutfs_inode_orphan_create(sb, scoutfs_ino(inode), orph_lock, inode_lock);
 		WARN_ON_ONCE(err); /* no orphan, might not scan and delete after crash */
 		goto out;
 	}
-	update_dentry_info(sb, dentry, hash, pos, dir_lock);
+	set_dentry_fsdata(dentry, dir_lock);
 
 	i_size_write(dir, dir_size);
 	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
@@ -1005,9 +904,11 @@ static int scoutfs_unlink(struct inode *dir, struct dentry *dentry)
 	struct scoutfs_lock *inode_lock = NULL;
 	struct scoutfs_lock *orph_lock = NULL;
 	struct scoutfs_lock *dir_lock = NULL;
+	struct scoutfs_dirent dent;
 	LIST_HEAD(ind_locks);
 	u64 ind_seq;
-	int ret = 0;
+	u64 hash;
+	int ret;
 
 	ret = scoutfs_lock_inodes(sb, SCOUTFS_LOCK_WRITE,
 				  SCOUTFS_LKF_REFRESH_INODE,
@@ -1016,11 +917,7 @@ static int scoutfs_unlink(struct inode *dir, struct dentry *dentry)
 	if (ret)
 		return ret;
 
-	ret = alloc_dentry_info(dentry);
-	if (ret)
-		goto unlock;
-
-	ret = verify_entry(sb, scoutfs_ino(dir), dentry, dir_lock);
+	ret = validate_dentry(sb, scoutfs_ino(dir), dentry, dir_lock);
 	if (ret < 0)
 		goto unlock;
 
@@ -1029,6 +926,13 @@ static int scoutfs_unlink(struct inode *dir, struct dentry *dentry)
 		goto unlock;
 	}
 
+	hash = dirent_name_hash(dentry->d_name.name, dentry->d_name.len);
+
+	ret = lookup_dirent(sb, scoutfs_ino(dir), dentry->d_name.name, dentry->d_name.len, hash,
+			    &dent, dir_lock);
+	if (ret < 0)
+		goto out;
+
 	if (should_orphan(inode)) {
 		ret = scoutfs_lock_orphan(sb, SCOUTFS_LOCK_WRITE_ONLY, 0, scoutfs_ino(inode),
 					  &orph_lock);
@@ -1047,21 +951,20 @@ retry:
 		goto unlock;
 
 	if (should_orphan(inode)) {
-		ret = scoutfs_inode_orphan_create(sb, scoutfs_ino(inode), orph_lock);
+		ret = scoutfs_inode_orphan_create(sb, scoutfs_ino(inode), orph_lock, inode_lock);
 		if (ret < 0)
 			goto out;
 	}
 
-	ret = del_entry_items(sb, scoutfs_ino(dir), dentry_info_hash(dentry),
-			      dentry_info_pos(dentry), scoutfs_ino(inode),
-			      dir_lock, inode_lock);
+	ret = del_entry_items(sb, scoutfs_ino(dir), le64_to_cpu(dent.hash), le64_to_cpu(dent.pos),
+			      scoutfs_ino(inode), dir_lock, inode_lock);
 	if (ret) {
-		ret = scoutfs_inode_orphan_delete(sb, scoutfs_ino(inode), orph_lock);
+		ret = scoutfs_inode_orphan_delete(sb, scoutfs_ino(inode), orph_lock, inode_lock);
 		WARN_ON_ONCE(ret); /* should have been dirty */
 		goto out;
 	}
 
-	update_dentry_info(sb, dentry, 0, 0, dir_lock);
+	set_dentry_fsdata(dentry, dir_lock);
 
 	dir->i_ctime = ts;
 	dir->i_mtime = ts;
@@ -1242,10 +1145,11 @@ const struct inode_operations scoutfs_symlink_iops = {
 	.put_link       = scoutfs_put_link,
 	.getattr	= scoutfs_getattr,
 	.setattr	= scoutfs_setattr,
-	.setxattr	= scoutfs_setxattr,
-	.getxattr	= scoutfs_getxattr,
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr	= scoutfs_listxattr,
-	.removexattr	= scoutfs_removexattr,
+	.removexattr	= generic_removexattr,
+	.get_acl	= scoutfs_get_acl,
 };
 
 /*
@@ -1273,17 +1177,13 @@ static int scoutfs_symlink(struct inode *dir, struct dentry *dentry,
 	    name_len > PATH_MAX || name_len > SCOUTFS_SYMLINK_MAX_SIZE)
 		return -ENAMETOOLONG;
 
-	ret = alloc_dentry_info(dentry);
-	if (ret)
-		return ret;
-
 	inode = lock_hold_create(dir, dentry, S_IFLNK|S_IRWXUGO, 0,
 				 &dir_lock, &inode_lock, NULL, &ind_locks);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
 	si = SCOUTFS_I(inode);
 
-	ret = verify_entry(sb, scoutfs_ino(dir), dentry, dir_lock);
+	ret = validate_dentry(sb, scoutfs_ino(dir), dentry, dir_lock);
 	if (ret < 0)
 		goto out;
 
@@ -1301,7 +1201,7 @@ static int scoutfs_symlink(struct inode *dir, struct dentry *dentry,
 	if (ret)
 		goto out;
 
-	update_dentry_info(sb, dentry, hash, pos, dir_lock);
+	set_dentry_fsdata(dentry, dir_lock);
 
 	i_size_write(dir, i_size_read(dir) + dentry->d_name.len);
 	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
@@ -1353,75 +1253,93 @@ int scoutfs_symlink_drop(struct super_block *sb, u64 ino,
 }
 
 /*
- * Find the next link backref key for the given ino starting from the
- * given dir inode and final entry position.  If we find a backref item
- * we add an allocated copy of it to the head of the caller's list.
+ * Find the next link backref items for the given ino starting from the
+ * given dir inode and final entry position.  For each backref item we
+ * add an allocated copy of it to the head of the caller's list.
  *
- * Returns 0 if we added an entry, -ENOENT if we didn't, and -errno for
- * search errors.
+ * Callers who are building a path can add one entry for each parent.
+ * They're left with a list of entries from the root down in list order.
+ *
+ * Callers who are gathering multiple entries for one inode get the
+ * entries in the opposite order that their items are found.
+ *
+ * Returns +ve for number of entries added, -ENOENT if no entries were
+ * found, or -errno on error.  It weirdly won't return 0, but early
+ * callers preferred -ENOENT so we use that for the case of no entries.
  *
  * Callers are comfortable with the race inherent to incrementally
- * building up a path with individual locked backref item lookups.
+ * gathering backrefs across multiple lock acquisitions.
  */
-int scoutfs_dir_add_next_linkref(struct super_block *sb, u64 ino,
-				 u64 dir_ino, u64 dir_pos,
-				 struct list_head *list)
+int scoutfs_dir_add_next_linkrefs(struct super_block *sb, u64 ino, u64 dir_ino, u64 dir_pos,
+				  int count, struct list_head *list)
 {
+	struct scoutfs_link_backref_entry *prev_ent = NULL;
 	struct scoutfs_link_backref_entry *ent = NULL;
 	struct scoutfs_lock *lock = NULL;
 	struct scoutfs_key last_key;
 	struct scoutfs_key key;
+	int nr = 0;
 	int len;
 	int ret;
 
-	ent = kmalloc(offsetof(struct scoutfs_link_backref_entry,
-			       dent.name[SCOUTFS_NAME_LEN]), GFP_KERNEL);
-	if (!ent) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	INIT_LIST_HEAD(&ent->head);
-
 	init_dirent_key(&key, SCOUTFS_LINK_BACKREF_TYPE, ino, dir_ino, dir_pos);
-	init_dirent_key(&last_key, SCOUTFS_LINK_BACKREF_TYPE, ino, U64_MAX,
-			U64_MAX);
+	init_dirent_key(&last_key, SCOUTFS_LINK_BACKREF_TYPE, ino, U64_MAX, U64_MAX);
 
 	ret = scoutfs_lock_ino(sb, SCOUTFS_LOCK_READ, 0, ino, &lock);
 	if (ret)
 		goto out;
 
-	ret = scoutfs_item_next(sb, &key, &last_key, &ent->dent,
-				dirent_bytes(SCOUTFS_NAME_LEN), lock);
-	scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);
-	lock = NULL;
-	if (ret < 0)
-		goto out;
+	while (nr < count) {
+		ent = kmalloc(offsetof(struct scoutfs_link_backref_entry,
+				       dent.name[SCOUTFS_NAME_LEN]), GFP_NOFS);
+		if (!ent) {
+			ret = -ENOMEM;
+			goto out;
+		}
 
-	len = ret - sizeof(struct scoutfs_dirent);
-	if (len < 1 || len > SCOUTFS_NAME_LEN) {
-		scoutfs_corruption(sb, SC_DIRENT_BACKREF_NAME_LEN,
-				   corrupt_dirent_backref_name_len,
-				   "ino %llu dir_ino %llu pos %llu key "SK_FMT" len %d",
-				   ino, dir_ino, dir_pos, SK_ARG(&key), len);
-		ret = -EIO;
-		goto out;
+		INIT_LIST_HEAD(&ent->head);
+
+		ret = scoutfs_item_next(sb, &key, &last_key, &ent->dent,
+					dirent_bytes(SCOUTFS_NAME_LEN), lock);
+		if (ret < 0) {
+			if (ret == -ENOENT && prev_ent)
+				prev_ent->last = true;
+			goto out;
+		}
+
+		len = ret - sizeof(struct scoutfs_dirent);
+		if (len < 1 || len > SCOUTFS_NAME_LEN) {
+			scoutfs_corruption(sb, SC_DIRENT_BACKREF_NAME_LEN,
+					   corrupt_dirent_backref_name_len,
+					   "ino %llu dir_ino %llu pos %llu key "SK_FMT" len %d",
+					   ino, dir_ino, dir_pos, SK_ARG(&key), len);
+			ret = -EIO;
+			goto out;
+		}
+
+		ent->dir_ino = le64_to_cpu(key.skd_major);
+		ent->dir_pos = le64_to_cpu(key.skd_minor);
+		ent->name_len = len;
+		ent->d_type = dentry_type(ent->dent.type);
+		ent->last = false;
+
+		trace_scoutfs_dir_add_next_linkref_found(sb, ino, ent->dir_ino, ent->dir_pos,
+							 ent->name_len);
+
+		list_add(&ent->head, list);
+		prev_ent = ent;
+		ent = NULL;
+		nr++;
+		scoutfs_key_inc(&key);
 	}
 
-	list_add(&ent->head, list);
-	ent->dir_ino = le64_to_cpu(key.skd_major);
-	ent->dir_pos = le64_to_cpu(key.skd_minor);
-	ent->name_len = len;
 	ret = 0;
 out:
-	trace_scoutfs_dir_add_next_linkref(sb, ino, dir_ino, dir_pos, ret,
-					   ent ? ent->dir_ino : 0,
-					   ent ? ent->dir_pos : 0,
-					   ent ? ent->name_len : 0);
+	scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);
+	trace_scoutfs_dir_add_next_linkrefs(sb, ino, dir_ino, dir_pos, count, nr, ret);
 
-	if (ent && list_empty(&ent->head))
-		kfree(ent);
-	return ret;
+	kfree(ent);
+	return nr ?: ret;
 }
 
 static u64 first_backref_dir_ino(struct list_head *list)
@@ -1496,7 +1414,7 @@ retry:
 	}
 
 	/* get the next link name to the given inode */
-	ret = scoutfs_dir_add_next_linkref(sb, ino, dir_ino, dir_pos, list);
+	ret = scoutfs_dir_add_next_linkrefs(sb, ino, dir_ino, dir_pos, 1, list);
 	if (ret < 0)
 		goto out;
 
@@ -1504,7 +1422,7 @@ retry:
 	par_ino = first_backref_dir_ino(list);
 	while (par_ino != SCOUTFS_ROOT_INO) {
 
-		ret = scoutfs_dir_add_next_linkref(sb, par_ino, 0, 0, list);
+		ret = scoutfs_dir_add_next_linkrefs(sb, par_ino, 0, 0, 1, list);
 		if (ret < 0) {
 			if (ret == -ENOENT) {
 				/* restart if there was no parent component */
@@ -1516,6 +1434,8 @@ retry:
 
 		par_ino = first_backref_dir_ino(list);
 	}
+
+	ret = 0;
 out:
 	if (ret < 0)
 		scoutfs_dir_free_backref_path(sb, list);
@@ -1543,6 +1463,11 @@ static int item_d_ancestor(struct super_block *sb, u64 p1, u64 p2, u64 *p_ret)
 
 	*p_ret = 0;
 
+	if (p2 == SCOUTFS_ROOT_INO) {
+		ret = 0;
+		goto out;
+	}
+
 	ret = scoutfs_dir_get_backref_path(sb, p2, 0, 0, &list);
 	if (ret)
 		goto out;
@@ -1631,6 +1556,8 @@ static int scoutfs_rename_common(struct inode *old_dir,
 	struct scoutfs_lock *old_inode_lock = NULL;
 	struct scoutfs_lock *new_inode_lock = NULL;
 	struct scoutfs_lock *orph_lock = NULL;
+	struct scoutfs_dirent new_dent;
+	struct scoutfs_dirent old_dent;
 	struct timespec now;
 	bool ins_new = false;
 	bool del_new = false;
@@ -1678,19 +1605,18 @@ static int scoutfs_rename_common(struct inode *old_dir,
 	if (ret)
 		goto out_unlock;
 
+	/* make sure that the entries assumed by the argument still exist */
+	ret = validate_dentry(sb, scoutfs_ino(old_dir), old_dentry, old_dir_lock) ?:
+	      validate_dentry(sb, scoutfs_ino(new_dir), new_dentry, new_dir_lock);
+	if (ret)
+		goto out_unlock;
+
 	/* test dir i_size now that it's refreshed */
 	if (new_inode && S_ISDIR(new_inode->i_mode) && i_size_read(new_inode)) {
 		ret = -ENOTEMPTY;
 		goto out_unlock;
 	}
 
-	/* make sure that the entries assumed by the argument still exist */
-	ret = alloc_dentry_info(old_dentry) ?:
-	      alloc_dentry_info(new_dentry) ?:
-	      verify_entry(sb, scoutfs_ino(old_dir), old_dentry, old_dir_lock) ?:
-	      verify_entry(sb, scoutfs_ino(new_dir), new_dentry, new_dir_lock);
-	if (ret)
-		goto out_unlock;
 
 	if ((flags & RENAME_NOREPLACE) && (new_inode != NULL)) {
 		ret = -EEXIST;
@@ -1733,10 +1659,12 @@ retry:
 
 	/* remove the new entry if it exists */
 	if (new_inode) {
-		ret = del_entry_items(sb, scoutfs_ino(new_dir),
-				      dentry_info_hash(new_dentry),
-				      dentry_info_pos(new_dentry),
-				      scoutfs_ino(new_inode),
+		ret = lookup_dirent(sb, scoutfs_ino(new_dir), new_dentry->d_name.name,
+				    new_dentry->d_name.len, new_hash, &new_dent, new_dir_lock);
+		if (ret < 0)
+			goto out;
+		ret = del_entry_items(sb, scoutfs_ino(new_dir), le64_to_cpu(new_dent.hash),
+				      le64_to_cpu(new_dent.pos), scoutfs_ino(new_inode),
 				      new_dir_lock, new_inode_lock);
 		if (ret)
 			goto out;
@@ -1752,18 +1680,22 @@ retry:
 		goto out;
 	del_new = true;
 
+	ret = lookup_dirent(sb, scoutfs_ino(old_dir), old_dentry->d_name.name,
+			    old_dentry->d_name.len, old_hash, &old_dent, old_dir_lock);
+	if (ret < 0)
+		goto out;
+
 	/* remove the old entry */
-	ret = del_entry_items(sb, scoutfs_ino(old_dir),
-			      dentry_info_hash(old_dentry),
-			      dentry_info_pos(old_dentry),
-			      scoutfs_ino(old_inode),
+	ret = del_entry_items(sb, scoutfs_ino(old_dir), le64_to_cpu(old_dent.hash),
+			      le64_to_cpu(old_dent.pos), scoutfs_ino(old_inode),
 			      old_dir_lock, old_inode_lock);
 	if (ret)
 		goto out;
 	ins_old = true;
 
 	if (should_orphan(new_inode)) {
-		ret = scoutfs_inode_orphan_create(sb, scoutfs_ino(new_inode), orph_lock);
+		ret = scoutfs_inode_orphan_create(sb, scoutfs_ino(new_inode), orph_lock,
+						  new_inode_lock);
 		if (ret)
 			goto out;
 	}
@@ -1771,7 +1703,7 @@ retry:
 	/* won't fail from here on out, update all the vfs structs */
 
 	/* the caller will use d_move to move the old_dentry into place */
-	update_dentry_info(sb, old_dentry, new_hash, new_pos, new_dir_lock);
+	set_dentry_fsdata(old_dentry, new_dir_lock);
 
        i_size_write(old_dir, i_size_read(old_dir) - old_dentry->d_name.len);
        if (!new_inode)
@@ -1836,8 +1768,8 @@ out:
 		err = 0;
 		if (ins_old)
 			err = add_entry_items(sb, scoutfs_ino(old_dir),
-					      dentry_info_hash(old_dentry),
-					      dentry_info_pos(old_dentry),
+					      le64_to_cpu(old_dent.hash),
+					      le64_to_cpu(old_dent.pos),
 					      old_dentry->d_name.name,
 					      old_dentry->d_name.len,
 					      scoutfs_ino(old_inode),
@@ -1853,8 +1785,8 @@ out:
 
 		if (ins_new && err == 0)
 			err = add_entry_items(sb, scoutfs_ino(new_dir),
-					      dentry_info_hash(new_dentry),
-					      dentry_info_pos(new_dentry),
+					      le64_to_cpu(new_dent.hash),
+					      le64_to_cpu(new_dent.pos),
 					      new_dentry->d_name.name,
 					      new_dentry->d_name.len,
 					      scoutfs_ino(new_inode),
@@ -1925,7 +1857,7 @@ static int scoutfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mod
 		return PTR_ERR(inode);
 	si = SCOUTFS_I(inode);
 
-	ret = scoutfs_inode_orphan_create(sb, scoutfs_ino(inode), orph_lock);
+	ret = scoutfs_inode_orphan_create(sb, scoutfs_ino(inode), orph_lock, inode_lock);
 	if (ret < 0)
 		goto out; /* XXX returning error but items created */
 
@@ -1978,32 +1910,14 @@ const struct inode_operations_wrapper scoutfs_dir_iops = {
 	.rename		= scoutfs_rename,
 	.getattr	= scoutfs_getattr,
 	.setattr	= scoutfs_setattr,
-	.setxattr	= scoutfs_setxattr,
-	.getxattr	= scoutfs_getxattr,
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr	= scoutfs_listxattr,
-	.removexattr	= scoutfs_removexattr,
+	.removexattr	= generic_removexattr,
+	.get_acl	= scoutfs_get_acl,
 	.symlink	= scoutfs_symlink,
 	.permission	= scoutfs_permission,
 	},
 	.tmpfile	= scoutfs_tmpfile,
 	.rename2	= scoutfs_rename2,
 };
-
-void scoutfs_dir_exit(void)
-{
-	if (dentry_info_cache) {
-		kmem_cache_destroy(dentry_info_cache);
-		dentry_info_cache = NULL;
-	}
-}
-
-int scoutfs_dir_init(void)
-{
-	dentry_info_cache = kmem_cache_create("scoutfs_dentry_info",
-					      sizeof(struct dentry_info), 0,
-					      SLAB_RECLAIM_ACCOUNT, NULL);
-	if (!dentry_info_cache)
-		return -ENOMEM;
-
-	return 0;
-}

kmod/src/dir.h

@@ -8,11 +8,15 @@ extern const struct file_operations scoutfs_dir_fops;
 extern const struct inode_operations_wrapper scoutfs_dir_iops;
 extern const struct inode_operations scoutfs_symlink_iops;
 
+extern const struct dentry_operations scoutfs_dentry_ops;
+
 struct scoutfs_link_backref_entry {
 	struct list_head head;
 	u64 dir_ino;
 	u64 dir_pos;
 	u16 name_len;
+	u8 d_type;
+	bool last;
 	struct scoutfs_dirent dent;
 	/* the full name is allocated and stored in dent.name[] */
 };
@@ -22,14 +26,10 @@ int scoutfs_dir_get_backref_path(struct super_block *sb, u64 ino, u64 dir_ino,
 void scoutfs_dir_free_backref_path(struct super_block *sb,
 				   struct list_head *list);
 
-int scoutfs_dir_add_next_linkref(struct super_block *sb, u64 ino,
-				 u64 dir_ino, u64 dir_pos,
-				 struct list_head *list);
+int scoutfs_dir_add_next_linkrefs(struct super_block *sb, u64 ino, u64 dir_ino, u64 dir_pos,
+				  int count, struct list_head *list);
 
 int scoutfs_symlink_drop(struct super_block *sb, u64 ino,
 			 struct scoutfs_lock *lock, u64 i_size);
 
-int scoutfs_dir_init(void);
-void scoutfs_dir_exit(void);
-
 #endif

kmod/src/export.c

@@ -114,8 +114,8 @@ static struct dentry *scoutfs_get_parent(struct dentry *child)
 	int ret;
 	u64 ino;
 
-	ret = scoutfs_dir_add_next_linkref(sb, scoutfs_ino(inode), 0, 0, &list);
-	if (ret)
+	ret = scoutfs_dir_add_next_linkrefs(sb, scoutfs_ino(inode), 0, 0, 1, &list);
+	if (ret < 0)
 		return ERR_PTR(ret);
 
 	ent = list_first_entry(&list, struct scoutfs_link_backref_entry, head);
@@ -138,9 +138,9 @@ static int scoutfs_get_name(struct dentry *parent, char *name,
 	LIST_HEAD(list);
 	int ret;
 
-	ret = scoutfs_dir_add_next_linkref(sb, scoutfs_ino(inode), dir_ino,
-					   0, &list);
-	if (ret)
+	ret = scoutfs_dir_add_next_linkrefs(sb, scoutfs_ino(inode), dir_ino,
+					    0, 1, &list);
+	if (ret < 0)
 		return ret;
 
 	ret = -ENOENT;

kmod/src/forest.c

@@ -78,11 +78,6 @@ struct forest_refs {
 	struct scoutfs_block_ref logs_ref;
 };
 
-/* initialize some refs that initially aren't equal */
-#define DECLARE_STALE_TRACKING_SUPER_REFS(a, b)		\
-	struct forest_refs a = {{cpu_to_le64(0),}};	\
-	struct forest_refs b = {{cpu_to_le64(1),}}
-
 struct forest_bloom_nrs {
 	unsigned int nrs[SCOUTFS_FOREST_BLOOM_NRS];
 };
@@ -136,11 +131,11 @@ static struct scoutfs_block *read_bloom_ref(struct super_block *sb, struct scout
 int scoutfs_forest_next_hint(struct super_block *sb, struct scoutfs_key *key,
 			     struct scoutfs_key *next)
 {
-	DECLARE_STALE_TRACKING_SUPER_REFS(prev_refs, refs);
 	struct scoutfs_net_roots roots;
 	struct scoutfs_btree_root item_root;
 	struct scoutfs_log_trees *lt;
 	SCOUTFS_BTREE_ITEM_REF(iref);
+	DECLARE_SAVED_REFS(saved);
 	struct scoutfs_key found;
 	struct scoutfs_key ltk;
 	bool checked_fs;
@@ -155,8 +150,6 @@ retry:
 		goto out;
 
 	trace_scoutfs_forest_using_roots(sb, &roots.fs_root, &roots.logs_root);
-	refs.fs_ref = roots.fs_root.ref;
-	refs.logs_ref = roots.logs_root.ref;
 
 	scoutfs_key_init_log_trees(&ltk, 0, 0);
 	checked_fs = false;
@@ -212,14 +205,10 @@ retry:
 		}
 	}
 
-	if (ret == -ESTALE) {
-		if (memcmp(&prev_refs, &refs, sizeof(refs)) == 0)
-			return -EIO;
-		prev_refs = refs;
+	ret = scoutfs_block_check_stale(sb, ret, &saved, &roots.fs_root.ref, &roots.logs_root.ref);
+	if (ret == -ESTALE)
 		goto retry;
-	}
 out:
-
 	return ret;
 }
 
@@ -541,9 +530,8 @@ void scoutfs_forest_dec_inode_count(struct super_block *sb)
 
 /*
  * Return the total inode count from the super block and all the
- * log_btrees it references.   This assumes it's working with a block
- * reference hierarchy that should be fully consistent.   If we see
- * ESTALE we've hit persistent corruption.
+ * log_btrees it references.  ESTALE from read blocks is returned to the
+ * caller who is expected to retry or return hard errors.
  */
 int scoutfs_forest_inode_count(struct super_block *sb, struct scoutfs_super_block *super,
 			       u64 *inode_count)
@@ -572,8 +560,6 @@ int scoutfs_forest_inode_count(struct super_block *sb, struct scoutfs_super_bloc
 		if (ret < 0) {
 			if (ret == -ENOENT)
 				ret = 0;
-			else if (ret == -ESTALE)
-				ret = -EIO;
 			break;
 		}
 	}

kmod/src/format.h

@@ -683,16 +683,19 @@ struct scoutfs_xattr_totl_val {
 #define SCOUTFS_QUORUM_ELECT_VAR_MS	100
 
 /*
- * Once a leader is elected they send out heartbeats at regular
- * intervals to force members to wait the much longer heartbeat timeout.
- * Once heartbeat timeout expires without receiving a heartbeat they'll
- * switch over the performing elections.
+ * Once a leader is elected they send heartbeat messages to all quorum
+ * members at regular intervals to force members to wait the much longer
+ * heartbeat timeout.  Once the heartbeat timeout expires without
+ * receiving a heartbeat message a member will start an election.
  *
  * These determine how long it could take members to notice that a
- * leader has gone silent and start to elect a new leader.
+ * leader has gone silent and start to elect a new leader.  The
+ * heartbeat timeout can be changed at run time by options.
  */
 #define SCOUTFS_QUORUM_HB_IVAL_MS	100
-#define SCOUTFS_QUORUM_HB_TIMEO_MS	(5 * MSEC_PER_SEC)
+#define SCOUTFS_QUORUM_MIN_HB_TIMEO_MS	(2 * MSEC_PER_SEC)
+#define SCOUTFS_QUORUM_DEF_HB_TIMEO_MS	(10 * MSEC_PER_SEC)
+#define SCOUTFS_QUORUM_MAX_HB_TIMEO_MS	(60 * MSEC_PER_SEC)
 
 /*
  * A newly elected leader will give fencing some time before giving up and

kmod/src/inode.c

@@ -19,6 +19,8 @@
 #include <linux/pagemap.h>
 #include <linux/sched.h>
 #include <linux/list_sort.h>
+#include <linux/workqueue.h>
+#include <linux/buffer_head.h>
 
 #include "format.h"
 #include "super.h"
@@ -36,6 +38,7 @@
 #include "omap.h"
 #include "forest.h"
 #include "btree.h"
+#include "acl.h"
 
 /*
  * XXX
@@ -66,8 +69,10 @@ struct inode_sb_info {
 
 	struct delayed_work orphan_scan_dwork;
 
+	struct workqueue_struct *iput_workq;
 	struct work_struct iput_work;
-	struct llist_head iput_llist;
+	spinlock_t iput_lock;
+	struct list_head iput_list;
 };
 
 #define DECLARE_INODE_SB_INFO(sb, name) \
@@ -94,7 +99,9 @@ static void scoutfs_inode_ctor(void *obj)
 	init_rwsem(&si->xattr_rwsem);
 	INIT_LIST_HEAD(&si->writeback_entry);
 	scoutfs_lock_init_coverage(&si->ino_lock_cov);
-	atomic_set(&si->iput_count, 0);
+	INIT_LIST_HEAD(&si->iput_head);
+	si->iput_count = 0;
+	si->iput_flags = 0;
 
 	inode_init_once(&si->inode);
 }
@@ -136,20 +143,22 @@ void scoutfs_destroy_inode(struct inode *inode)
 static const struct inode_operations scoutfs_file_iops = {
 	.getattr	= scoutfs_getattr,
 	.setattr	= scoutfs_setattr,
-	.setxattr	= scoutfs_setxattr,
-	.getxattr	= scoutfs_getxattr,
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr	= scoutfs_listxattr,
-	.removexattr	= scoutfs_removexattr,
+	.removexattr	= generic_removexattr,
+	.get_acl	= scoutfs_get_acl,
 	.fiemap		= scoutfs_data_fiemap,
 };
 
 static const struct inode_operations scoutfs_special_iops = {
 	.getattr	= scoutfs_getattr,
 	.setattr	= scoutfs_setattr,
-	.setxattr	= scoutfs_setxattr,
-	.getxattr	= scoutfs_getxattr,
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
 	.listxattr	= scoutfs_listxattr,
-	.removexattr	= scoutfs_removexattr,
+	.removexattr	= generic_removexattr,
+	.get_acl	= scoutfs_get_acl,
 };
 
 /*
@@ -322,7 +331,6 @@ int scoutfs_inode_refresh(struct inode *inode, struct scoutfs_lock *lock)
 			load_inode(inode, &sinode);
 			atomic64_set(&si->last_refreshed, refresh_gen);
 			scoutfs_lock_add_coverage(sb, lock, &si->ino_lock_cov);
-			si->drop_invalidated = false;
 		}
 	} else {
 		ret = 0;
@@ -354,6 +362,7 @@ static int set_inode_size(struct inode *inode, struct scoutfs_lock *lock,
 {
 	struct scoutfs_inode_info *si = SCOUTFS_I(inode);
 	struct super_block *sb = inode->i_sb;
+	SCOUTFS_DECLARE_PER_TASK_ENTRY(pt_ent);
 	LIST_HEAD(ind_locks);
 	int ret;
 
@@ -364,6 +373,13 @@ static int set_inode_size(struct inode *inode, struct scoutfs_lock *lock,
 	if (ret)
 		return ret;
 
+	scoutfs_per_task_add(&si->pt_data_lock, &pt_ent, lock);
+	ret = block_truncate_page(inode->i_mapping, new_size, scoutfs_get_block_write);
+	scoutfs_per_task_del(&si->pt_data_lock, &pt_ent);
+	if (ret < 0)
+		goto unlock;
+	scoutfs_inode_queue_writeback(inode);
+
 	if (new_size != i_size_read(inode))
 		scoutfs_inode_inc_data_version(inode);
 
@@ -375,6 +391,7 @@ static int set_inode_size(struct inode *inode, struct scoutfs_lock *lock,
 	inode_inc_iversion(inode);
 	scoutfs_update_inode_item(inode, lock, &ind_locks);
 
+unlock:
 	scoutfs_release_trans(sb);
 	scoutfs_inode_index_unlock(sb, &ind_locks);
 
@@ -507,10 +524,15 @@ retry:
 	if (ret)
 		goto out;
 
+	ret = scoutfs_acl_chmod_locked(inode, attr, lock, &ind_locks);
+	if (ret < 0)
+		goto release;
+
 	setattr_copy(inode, attr);
 	inode_inc_iversion(inode);
 	scoutfs_update_inode_item(inode, lock, &ind_locks);
 
+release:
 	scoutfs_release_trans(sb);
 	scoutfs_inode_index_unlock(sb, &ind_locks);
 out:
@@ -947,7 +969,8 @@ void scoutfs_inode_init_index_key(struct scoutfs_key *key, u8 type, u64 major,
 static int update_index_items(struct super_block *sb,
 			      struct scoutfs_inode_info *si, u64 ino, u8 type,
 			      u64 major, u32 minor,
-			      struct list_head *lock_list)
+			      struct list_head *lock_list,
+			      struct scoutfs_lock *primary)
 {
 	struct scoutfs_lock *ins_lock;
 	struct scoutfs_lock *del_lock;
@@ -964,7 +987,7 @@ static int update_index_items(struct super_block *sb,
 	scoutfs_inode_init_index_key(&ins, type, major, minor, ino);
 
 	ins_lock = find_index_lock(lock_list, type, major, minor, ino);
-	ret = scoutfs_item_create_force(sb, &ins, NULL, 0, ins_lock);
+	ret = scoutfs_item_create_force(sb, &ins, NULL, 0, ins_lock, primary);
 	if (ret || !will_del_index(si, type, major, minor))
 		return ret;
 
@@ -976,7 +999,7 @@ static int update_index_items(struct super_block *sb,
 
 	del_lock = find_index_lock(lock_list, type, get_item_major(si, type),
 				   get_item_minor(si, type), ino);
-	ret = scoutfs_item_delete_force(sb, &del, del_lock);
+	ret = scoutfs_item_delete_force(sb, &del, del_lock, primary);
 	if (ret) {
 		err = scoutfs_item_delete(sb, &ins, ins_lock);
 		BUG_ON(err);
@@ -988,7 +1011,8 @@ static int update_index_items(struct super_block *sb,
 static int update_indices(struct super_block *sb,
 			  struct scoutfs_inode_info *si, u64 ino, umode_t mode,
 			  struct scoutfs_inode *sinode,
-			  struct list_head *lock_list)
+			  struct list_head *lock_list,
+			  struct scoutfs_lock *primary)
 {
 	struct index_update {
 		u8 type;
@@ -1008,7 +1032,7 @@ static int update_indices(struct super_block *sb,
 			continue;
 
 		ret = update_index_items(sb, si, ino, upd->type, upd->major,
-					 upd->minor, lock_list);
+					 upd->minor, lock_list, primary);
 		if (ret)
 			break;
 	}
@@ -1048,7 +1072,7 @@ void scoutfs_update_inode_item(struct inode *inode, struct scoutfs_lock *lock,
 	/* only race with other inode field stores once */
 	store_inode(&sinode, inode);
 
-	ret = update_indices(sb, si, ino, inode->i_mode, &sinode, lock_list);
+	ret = update_indices(sb, si, ino, inode->i_mode, &sinode, lock_list, lock);
 	BUG_ON(ret);
 
 	scoutfs_inode_init_key(&key, ino);
@@ -1317,7 +1341,7 @@ void scoutfs_inode_index_unlock(struct super_block *sb, struct list_head *list)
 
 /* this is called on final inode cleanup so enoent is fine */
 static int remove_index(struct super_block *sb, u64 ino, u8 type, u64 major,
-			u32 minor, struct list_head *ind_locks)
+			u32 minor, struct list_head *ind_locks, struct scoutfs_lock *primary)
 {
 	struct scoutfs_key key;
 	struct scoutfs_lock *lock;
@@ -1326,7 +1350,7 @@ static int remove_index(struct super_block *sb, u64 ino, u8 type, u64 major,
 	scoutfs_inode_init_index_key(&key, type, major, minor, ino);
 
 	lock = find_index_lock(ind_locks, type, major, minor, ino);
-	ret = scoutfs_item_delete_force(sb, &key, lock);
+	ret = scoutfs_item_delete_force(sb, &key, lock, primary);
 	if (ret == -ENOENT)
 		ret = 0;
 	return ret;
@@ -1343,16 +1367,17 @@ static int remove_index(struct super_block *sb, u64 ino, u8 type, u64 major,
  */
 static int remove_index_items(struct super_block *sb, u64 ino,
 			      struct scoutfs_inode *sinode,
-			      struct list_head *ind_locks)
+			      struct list_head *ind_locks,
+			      struct scoutfs_lock *primary)
 {
 	umode_t mode = le32_to_cpu(sinode->mode);
 	int ret;
 
 	ret = remove_index(sb, ino, SCOUTFS_INODE_INDEX_META_SEQ_TYPE,
-			   le64_to_cpu(sinode->meta_seq), 0, ind_locks);
+			   le64_to_cpu(sinode->meta_seq), 0, ind_locks, primary);
 	if (ret == 0 && S_ISREG(mode))
 		ret = remove_index(sb, ino, SCOUTFS_INODE_INDEX_DATA_SEQ_TYPE,
-				   le64_to_cpu(sinode->data_seq), 0, ind_locks);
+				   le64_to_cpu(sinode->data_seq), 0, ind_locks, primary);
 	return ret;
 }
 
@@ -1442,7 +1467,6 @@ int scoutfs_new_inode(struct super_block *sb, struct inode *dir, umode_t mode, d
 	si->have_item = false;
 	atomic64_set(&si->last_refreshed, lock->refresh_gen);
 	scoutfs_lock_add_coverage(sb, lock, &si->ino_lock_cov);
-	si->drop_invalidated = false;
 	si->flags = 0;
 
 	scoutfs_inode_set_meta_seq(inode);
@@ -1485,22 +1509,24 @@ static void init_orphan_key(struct scoutfs_key *key, u64 ino)
  * zone under a write only lock while the caller has the inode protected
  * by a write lock.
  */
-int scoutfs_inode_orphan_create(struct super_block *sb, u64 ino, struct scoutfs_lock *lock)
+int scoutfs_inode_orphan_create(struct super_block *sb, u64 ino, struct scoutfs_lock *lock,
+				struct scoutfs_lock *primary)
 {
 	struct scoutfs_key key;
 
 	init_orphan_key(&key, ino);
 
-	return scoutfs_item_create_force(sb, &key, NULL, 0, lock);
+	return scoutfs_item_create_force(sb, &key, NULL, 0, lock, primary);
 }
 
-int scoutfs_inode_orphan_delete(struct super_block *sb, u64 ino, struct scoutfs_lock *lock)
+int scoutfs_inode_orphan_delete(struct super_block *sb, u64 ino, struct scoutfs_lock *lock,
+				struct scoutfs_lock *primary)
 {
 	struct scoutfs_key key;
 
 	init_orphan_key(&key, ino);
 
-	return scoutfs_item_delete_force(sb, &key, lock);
+	return scoutfs_item_delete_force(sb, &key, lock, primary);
 }
 
 /*
@@ -1553,7 +1579,7 @@ retry:
 
 	release = true;
 
-	ret = remove_index_items(sb, ino, sinode, &ind_locks);
+	ret = remove_index_items(sb, ino, sinode, &ind_locks, lock);
 	if (ret)
 		goto out;
 
@@ -1568,7 +1594,7 @@ retry:
 	if (ret < 0)
 		goto out;
 
-	ret = scoutfs_inode_orphan_delete(sb, ino, orph_lock);
+	ret = scoutfs_inode_orphan_delete(sb, ino, orph_lock, lock);
 	if (ret < 0)
 		goto out;
 
@@ -1685,6 +1711,7 @@ static int try_delete_inode_items(struct super_block *sb, u64 ino)
 	struct scoutfs_lock *lock = NULL;
 	struct scoutfs_inode sinode;
 	struct scoutfs_key key;
+	bool clear_trying = false;
 	u64 group_nr;
 	int bit_nr;
 	int ret;
@@ -1704,6 +1731,7 @@ static int try_delete_inode_items(struct super_block *sb, u64 ino)
 		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)) {
@@ -1730,7 +1758,7 @@ static int try_delete_inode_items(struct super_block *sb, u64 ino)
 
 	ret = delete_inode_items(sb, ino, &sinode, lock, orph_lock);
 out:
-	if (ldata)
+	if (clear_trying)
 		clear_bit(bit_nr, ldata->trying);
 
 	scoutfs_unlock(sb, lock, SCOUTFS_LOCK_WRITE);
@@ -1740,18 +1768,18 @@ out:
 }
 
 /*
- * As we drop an inode we need to decide to try and delete its items or
- * not, which is expensive.  The two common cases we want to get right
- * both have cluster lock coverage and don't want to delete.   Dropping
- * unused inodes during read lock invalidation has the current lock and
- * sees a nonzero nlink and knows not to delete.  Final iput after a
- * local unlink also has a lock, sees a zero nlink, and tries to perform
- * item deletion in the task that dropped the last link, as users
- * expect. 
+ * As we evicted an inode we need to decide to try and delete its items
+ * or not, which is expensive.  We only try when we have lock coverage
+ * and the inode has been unlinked.  This catches the common case of
+ * regular deletion so deletion will be performed in the final unlink
+ * task.  It also catches open-unlink or o_tmpfile that aren't cached on
+ * other nodes.
  *
- * Evicting an inode outside of cluster locking is the odd slow path
- * that involves lock contention during use the worst cross-mount
- * open-unlink/delete case.
+ * Inodes being evicted outside of lock coverage, by referenced dentries
+ * or inodes that survived the attempt to drop them as their lock was
+ * invalidated, will not try to delete.  This means that cross-mount
+ * open/unlink will almost certainly fall back to the orphan scanner to
+ * perform final deletion.
  */
 void scoutfs_evict_inode(struct inode *inode)
 {
@@ -1767,7 +1795,7 @@ void scoutfs_evict_inode(struct inode *inode)
 		/* clear before trying to delete tests */
 		scoutfs_omap_clear(sb, ino);
 
-		if (!scoutfs_lock_is_covered(sb, &si->ino_lock_cov) || inode->i_nlink == 0)
+		if (scoutfs_lock_is_covered(sb, &si->ino_lock_cov) && inode->i_nlink == 0)
 			try_delete_inode_items(sb, scoutfs_ino(inode));
 	}
 
@@ -1792,30 +1820,56 @@ int scoutfs_drop_inode(struct inode *inode)
 {
 	struct scoutfs_inode_info *si = SCOUTFS_I(inode);
 	struct super_block *sb = inode->i_sb;
+	const bool covered = scoutfs_lock_is_covered(sb, &si->ino_lock_cov);
 
 	trace_scoutfs_drop_inode(sb, scoutfs_ino(inode), inode->i_nlink, inode_unhashed(inode),
-				 si->drop_invalidated);
+				 covered);
 
-	return si->drop_invalidated || !scoutfs_lock_is_covered(sb, &si->ino_lock_cov) ||
-	       generic_drop_inode(inode);
+	return !covered || generic_drop_inode(inode);
 }
 
+
+/*
+ * These iput workers can be concurrent amongst cpus.  This lets us get
+ * some concurrency when these async final iputs end up performing very
+ * expensive inode deletion.  Typically they're dropping linked inodes
+ * that lost lock coverage and the iput will evict without deleting.
+ *
+ * Keep in mind that the dputs in d_prune can ascend into parents and
+ * end up performing the final iput->evict deletion on other inodes.
+ */
 static void iput_worker(struct work_struct *work)
 {
 	struct inode_sb_info *inf = container_of(work, struct inode_sb_info, iput_work);
 	struct scoutfs_inode_info *si;
-	struct scoutfs_inode_info *tmp;
-	struct llist_node *inodes;
-	bool more;
+	struct inode *inode;
+	unsigned long count;
+	unsigned long flags;
 
-	inodes = llist_del_all(&inf->iput_llist);
+	spin_lock(&inf->iput_lock);
+	while ((si = list_first_entry_or_null(&inf->iput_list, struct scoutfs_inode_info,
+					      iput_head))) {
+		list_del_init(&si->iput_head);
+		count = si->iput_count;
+		flags = si->iput_flags;
+		si->iput_count = 0;
+		si->iput_flags = 0;
+		spin_unlock(&inf->iput_lock);
 
-	llist_for_each_entry_safe(si, tmp, inodes, iput_llnode) {
-		do {
-			more = atomic_dec_return(&si->iput_count) > 0;
-			iput(&si->inode);
-		} while (more);
+		inode = &si->inode;
+
+		/* can't touch during unmount, dcache destroys w/o locks */
+		if ((flags & SI_IPUT_FLAG_PRUNE) && !inf->stopped)
+			d_prune_aliases(inode);
+
+		while (count-- > 0)
+			iput(inode);
+
+		/* can't touch inode after final iput */
+
+		spin_lock(&inf->iput_lock);
 	}
+	spin_unlock(&inf->iput_lock);
 }
 
 /*
@@ -1832,15 +1886,21 @@ static void iput_worker(struct work_struct *work)
  * Nothing stops multiple puts of an inode before the work runs so we
  * can track multiple puts in flight.
  */
-void scoutfs_inode_queue_iput(struct inode *inode)
+void scoutfs_inode_queue_iput(struct inode *inode, unsigned long flags)
 {
 	DECLARE_INODE_SB_INFO(inode->i_sb, inf);
 	struct scoutfs_inode_info *si = SCOUTFS_I(inode);
+	bool should_queue;
 
-	if (atomic_inc_return(&si->iput_count) == 1)
-		llist_add(&si->iput_llnode, &inf->iput_llist);
-	smp_wmb(); /* count and list visible before work executes */
-	schedule_work(&inf->iput_work);
+	spin_lock(&inf->iput_lock);
+	si->iput_count++;
+	si->iput_flags |= flags;
+	if ((should_queue = list_empty(&si->iput_head)))
+		list_add_tail(&si->iput_head, &inf->iput_list);
+	spin_unlock(&inf->iput_lock);
+
+	if (should_queue)
+		queue_work(inf->iput_workq, &inf->iput_work);
 }
 
 /*
@@ -2044,7 +2104,7 @@ int scoutfs_inode_walk_writeback(struct super_block *sb, bool write)
 		trace_scoutfs_inode_walk_writeback(sb, scoutfs_ino(inode),
 						   write, ret);
 		if (ret) {
-			scoutfs_inode_queue_iput(inode);
+			scoutfs_inode_queue_iput(inode, 0);
 			goto out;
 		}
 
@@ -2060,7 +2120,7 @@ int scoutfs_inode_walk_writeback(struct super_block *sb, bool write)
 		if (!write)
 			list_del_init(&si->writeback_entry);
 
-		scoutfs_inode_queue_iput(inode);
+		scoutfs_inode_queue_iput(inode, 0);
 	}
 
 	spin_unlock(&inf->writeback_lock);
@@ -2085,7 +2145,15 @@ int scoutfs_inode_setup(struct super_block *sb)
 	spin_lock_init(&inf->ino_alloc.lock);
 	INIT_DELAYED_WORK(&inf->orphan_scan_dwork, inode_orphan_scan_worker);
 	INIT_WORK(&inf->iput_work, iput_worker);
-	init_llist_head(&inf->iput_llist);
+	spin_lock_init(&inf->iput_lock);
+	INIT_LIST_HEAD(&inf->iput_list);
+
+	/* re-entrant, worker locks with itself and queueing */
+	inf->iput_workq = alloc_workqueue("scoutfs_inode_iput", WQ_UNBOUND, 0);
+	if (!inf->iput_workq) {
+		kfree(inf);
+		return -ENOMEM;
+	}
 
 	sbi->inode_sb_info = inf;
 
@@ -2121,14 +2189,18 @@ void scoutfs_inode_flush_iput(struct super_block *sb)
 	DECLARE_INODE_SB_INFO(sb, inf);
 
 	if (inf)
-		flush_work(&inf->iput_work);
+		flush_workqueue(inf->iput_workq);
 }
 
 void scoutfs_inode_destroy(struct super_block *sb)
 {
 	struct inode_sb_info *inf = SCOUTFS_SB(sb)->inode_sb_info;
 
-	kfree(inf);
+	if (inf) {
+		if (inf->iput_workq)
+			destroy_workqueue(inf->iput_workq);
+		kfree(inf);
+	}
 }
 
 void scoutfs_inode_exit(void)

kmod/src/inode.h

@@ -56,14 +56,16 @@ struct scoutfs_inode_info {
 
 	struct scoutfs_lock_coverage ino_lock_cov;
 
-	/* drop if i_count hits 0, allows drop while invalidate holds coverage */
-	bool drop_invalidated;
-	struct llist_node iput_llnode;
-	atomic_t iput_count;
+	struct list_head iput_head;
+	unsigned long iput_count;
+	unsigned long iput_flags;
 
 	struct inode inode;
 };
 
+/* try to prune dcache aliases with queued iput */
+#define SI_IPUT_FLAG_PRUNE	(1 << 0)
+
 static inline struct scoutfs_inode_info *SCOUTFS_I(struct inode *inode)
 {
 	return container_of(inode, struct scoutfs_inode_info, inode);
@@ -78,7 +80,7 @@ struct inode *scoutfs_alloc_inode(struct super_block *sb);
 void scoutfs_destroy_inode(struct inode *inode);
 int scoutfs_drop_inode(struct inode *inode);
 void scoutfs_evict_inode(struct inode *inode);
-void scoutfs_inode_queue_iput(struct inode *inode);
+void scoutfs_inode_queue_iput(struct inode *inode, unsigned long flags);
 
 #define SCOUTFS_IGF_LINKED (1 << 0) /* enoent if nlink == 0 */
 struct inode *scoutfs_iget(struct super_block *sb, u64 ino, int lkf, int igf);
@@ -125,8 +127,10 @@ int scoutfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		    struct kstat *stat);
 int scoutfs_setattr(struct dentry *dentry, struct iattr *attr);
 
-int scoutfs_inode_orphan_create(struct super_block *sb, u64 ino, struct scoutfs_lock *lock);
-int scoutfs_inode_orphan_delete(struct super_block *sb, u64 ino, struct scoutfs_lock *lock);
+int scoutfs_inode_orphan_create(struct super_block *sb, u64 ino, struct scoutfs_lock *lock,
+				struct scoutfs_lock *primary);
+int scoutfs_inode_orphan_delete(struct super_block *sb, u64 ino, struct scoutfs_lock *lock,
+				struct scoutfs_lock *primary);
 void scoutfs_inode_schedule_orphan_dwork(struct super_block *sb);
 
 void scoutfs_inode_queue_writeback(struct inode *inode);

kmod/src/ioctl.c

@@ -1398,6 +1398,110 @@ out:
 	return ret ?: nr;
 }
 
+/*
+ * Copy entries that point to an inode to the user's buffer.  We copy to
+ * userspace from copies of the entries that are acquired under a lock
+ * so that we don't fault while holding cluster locks.  It also gives us
+ * a chance to limit the amount of work under each lock hold.
+ */
+static long scoutfs_ioc_get_referring_entries(struct file *file, unsigned long arg)
+{
+	struct super_block *sb = file_inode(file)->i_sb;
+	struct scoutfs_ioctl_get_referring_entries gre;
+	struct scoutfs_link_backref_entry *bref = NULL;
+	struct scoutfs_link_backref_entry *bref_tmp;
+	struct scoutfs_ioctl_dirent __user *uent;
+	struct scoutfs_ioctl_dirent ent;
+	LIST_HEAD(list);
+	u64 copied;
+	int name_len;
+	int bytes;
+	long nr;
+	int ret;
+
+	if (!capable(CAP_DAC_READ_SEARCH))
+		return -EPERM;
+
+	if (copy_from_user(&gre, (void __user *)arg, sizeof(gre)))
+		return -EFAULT;
+
+	uent = (void __user *)(unsigned long)gre.entries_ptr;
+	copied = 0;
+	nr = 0;
+
+	/* use entry as cursor between calls */
+	ent.dir_ino = gre.dir_ino;
+	ent.dir_pos = gre.dir_pos;
+
+	for (;;) {
+		ret = scoutfs_dir_add_next_linkrefs(sb, gre.ino, ent.dir_ino, ent.dir_pos, 1024,
+						    &list);
+		if (ret < 0) {
+			if (ret == -ENOENT)
+				ret = 0;
+			goto out;
+		}
+
+		/* _add_next adds each entry to the head, _reverse for key order */
+		list_for_each_entry_safe_reverse(bref, bref_tmp, &list, head) {
+			list_del_init(&bref->head);
+
+			name_len = bref->name_len;
+			bytes = ALIGN(offsetof(struct scoutfs_ioctl_dirent, name[name_len + 1]),
+				      16);
+			if (copied + bytes > gre.entries_bytes) {
+				ret = -EINVAL;
+				goto out;
+			}
+
+			ent.dir_ino = bref->dir_ino;
+			ent.dir_pos = bref->dir_pos;
+			ent.ino = gre.ino;
+			ent.entry_bytes = bytes;
+			ent.flags = bref->last ? SCOUTFS_IOCTL_DIRENT_FLAG_LAST : 0;
+			ent.d_type = bref->d_type;
+			ent.name_len = name_len;
+
+			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;
+				goto out;
+			}
+
+			kfree(bref);
+			bref = NULL;
+
+			uent = (void __user *)uent + bytes;
+			copied += bytes;
+			nr++;
+
+			if (nr == LONG_MAX || (ent.flags & SCOUTFS_IOCTL_DIRENT_FLAG_LAST)) {
+				ret = 0;
+				goto out;
+			}
+		}
+
+		/* advance cursor pos from last copied entry */
+		if (++ent.dir_pos == 0) {
+			if (++ent.dir_ino == 0) {
+				ret = 0;
+				goto out;
+			}
+		}
+	}
+
+	ret = 0;
+out:
+	kfree(bref);
+	list_for_each_entry_safe(bref, bref_tmp, &list, head) {
+		list_del_init(&bref->head);
+		kfree(bref);
+	}
+
+	return nr ?: ret;
+}
+
 long scoutfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	switch (cmd) {
@@ -1433,6 +1537,8 @@ long scoutfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		return scoutfs_ioc_read_xattr_totals(file, arg);
 	case SCOUTFS_IOC_GET_ALLOCATED_INOS:
 		return scoutfs_ioc_get_allocated_inos(file, arg);
+	case SCOUTFS_IOC_GET_REFERRING_ENTRIES:
+		return scoutfs_ioc_get_referring_entries(file, arg);
 	}
 
 	return -ENOTTY;

kmod/src/ioctl.h

@@ -559,4 +559,118 @@ struct scoutfs_ioctl_get_allocated_inos {
 #define SCOUTFS_IOC_GET_ALLOCATED_INOS \
 	_IOW(SCOUTFS_IOCTL_MAGIC, 16, struct scoutfs_ioctl_get_allocated_inos)
 
+/*
+ * Get directory entries that refer to a specific inode.
+ *
+ * @ino: The target ino that we're finding referring entries to.
+ * Constant across all the calls that make up an iteration over all the
+ * inode's entries.
+ *
+ * @dir_ino: The inode number of a directory containing the entry to our
+ * inode to search from.  If this parent directory contains no more
+ * entries to our inode then we'll search through other parent directory
+ * inodes in inode order.
+ *
+ * @dir_pos: The position in the dir_ino parent directory of the entry
+ * to our inode to search from.  If there is no entry at this position
+ * then we'll search through other entry positions in increasing order.
+ * If we exhaust the parent directory then we'll search through
+ * additional parent directories in inode order.
+ *
+ * @entries_ptr: A pointer to the buffer where found entries will be
+ * stored.  The pointer must be aligned to 16 bytes.
+ *
+ * @entries_bytes: The size of the buffer that will contain entries.
+ *
+ * To start iterating set the desired target ino, dir_ino to 0, dir_pos
+ * to 0, and set result_ptr and _bytes to a sufficiently large buffer.
+ * Each entry struct that's stored in the buffer adds some overhead so a
+ * large multiple of the largest possible name is a reasonable choice.
+ * (A few multiples of PATH_MAX perhaps.)
+ *
+ * Each call returns the total number of entries that were stored in the
+ * entries buffer.  Zero is returned when the search was successful and
+ * no referring entries were found.  The entries can be iterated over by
+ * advancing each starting struct offset by the total number of bytes in
+ * each entry.  If the _LAST flag is set on an entry then there were no
+ * more entries referring to the inode at the time of the call and
+ * iteration can be stopped.
+ *
+ * To resume iteration set the next call's starting dir_ino and dir_pos
+ * to one past the last entry seen.  Increment the last entry's dir_pos,
+ * and if it wrapped to 0, increment its dir_ino.
+ *
+ * This does not check that the caller has permission to read the
+ * entries found in each containing directory.  It requires
+ * CAP_DAC_READ_SEARCH which bypasses path traversal permissions
+ * checking.
+ *
+ * Entries returned by a single call can reflect any combination of
+ * racing creation and removal of entries.  Each entry existed at the
+ * time it was read though it may have changed in the time it took to
+ * return from the call.  The set of entries returned may no longer
+ * reflect the current set of entries and may not have existed at the
+ * same time.
+ *
+ * This has no knowledge of the life cycle of the inode.  It can return
+ * 0 when there are no referring entries because either the target inode
+ * doesn't exist, it is in the process of being deleted, or because it
+ * is still open while being unlinked.
+ *
+ * On success this returns the number of entries filled in the buffer.
+ * A return of 0 indicates that no entries referred to the inode.
+ *
+ * EINVAL is returned when there is a problem with the buffer.  Either
+ * it was not aligned or it was not large enough for the first entry.
+ *
+ * Many other errnos indicate hard failure to find the next entry.
+ */
+struct scoutfs_ioctl_get_referring_entries {
+	__u64 ino;
+	__u64 dir_ino;
+	__u64 dir_pos;
+	__u64 entries_ptr;
+	__u64 entries_bytes;
+};
+
+/*
+ * @dir_ino: The inode of the directory containing the entry.
+ *
+ * @dir_pos: The readdir f_pos position of the entry within the
+ * directory.
+ *
+ * @ino: The inode number of the target of the entry.
+ *
+ * @flags: Flags associated with this entry.
+ *
+ * @d_type: Inode type as specified with DT_ enum values in readdir(3).
+ *
+ * @entry_bytes: The total bytes taken by the entry in memory, including
+ * the name and any alignment padding.  The start of a following entry
+ * will be found after this number of bytes.
+ *
+ * @name_len: The number of bytes in the name not including the trailing
+ * null, ala strlen(3).
+ *
+ * @name: The null terminated name of the referring entry.  In the
+ * struct definition this array is sized to naturally align the struct.
+ * That number of padded bytes are not necessarily found in the buffer
+ * returned by _get_referring_entries;
+ */
+struct scoutfs_ioctl_dirent {
+	__u64 dir_ino;
+	__u64 dir_pos;
+	__u64 ino;
+	__u16 entry_bytes;
+	__u8  flags;
+	__u8  d_type;
+	__u8  name_len;
+	__u8  name[3];
+};
+
+#define SCOUTFS_IOCTL_DIRENT_FLAG_LAST (1 << 0)
+
+#define SCOUTFS_IOC_GET_REFERRING_ENTRIES \
+	_IOW(SCOUTFS_IOCTL_MAGIC, 17, struct scoutfs_ioctl_get_referring_entries)
+
 #endif

kmod/src/item.c

@@ -1676,6 +1676,14 @@ static int lock_safe(struct scoutfs_lock *lock, struct scoutfs_key *key,
 		return 0;
 }
 
+static int optional_lock_mode_match(struct scoutfs_lock *lock, int mode)
+{
+	if (WARN_ON_ONCE(lock && lock->mode != mode))
+		return -EINVAL;
+	else
+		return 0;
+}
+
 /*
  * Copy the cached item's value into the caller's value.  The number of
  * bytes copied is returned.  A null val returns 0.
@@ -1832,12 +1840,19 @@ out:
  * also increase the seqs.  It lets us limit the inputs of item merging
  * to the last stable seq and ensure that all the items in open
  * transactions and granted locks will have greater seqs.
+ *
+ * This is a little awkward for WRITE_ONLY locks which can have much
+ * older versions than the version of locked primary data that they're
+ * operating on behalf of.  Callers can optionally provide that primary
+ * lock to get the version from.   This ensures that items created under
+ * WRITE_ONLY locks can not have versions less than their primary data.
  */
-static u64 item_seq(struct super_block *sb, struct scoutfs_lock *lock)
+static u64 item_seq(struct super_block *sb, struct scoutfs_lock *lock,
+		    struct scoutfs_lock *primary)
 {
 	struct scoutfs_sb_info *sbi = SCOUTFS_SB(sb);
 
-	return max(sbi->trans_seq, lock->write_seq);
+	return max3(sbi->trans_seq, lock->write_seq, primary ? primary->write_seq : 0);
 }
 
 /*
@@ -1872,7 +1887,7 @@ int scoutfs_item_dirty(struct super_block *sb, struct scoutfs_key *key,
 	if (!item || item->deletion) {
 		ret = -ENOENT;
 	} else {
-		item->seq = item_seq(sb, lock);
+		item->seq = item_seq(sb, lock, NULL);
 		mark_item_dirty(sb, cinf, pg, NULL, item);
 		ret = 0;
 	}
@@ -1889,10 +1904,10 @@ out:
  */
 static int item_create(struct super_block *sb, struct scoutfs_key *key,
 		       void *val, int val_len, struct scoutfs_lock *lock,
-		       int mode, bool force)
+		       struct scoutfs_lock *primary, int mode, bool force)
 {
 	DECLARE_ITEM_CACHE_INFO(sb, cinf);
-	const u64 seq = item_seq(sb, lock);
+	const u64 seq = item_seq(sb, lock, primary);
 	struct cached_item *found;
 	struct cached_item *item;
 	struct cached_page *pg;
@@ -1902,7 +1917,8 @@ static int item_create(struct super_block *sb, struct scoutfs_key *key,
 
 	scoutfs_inc_counter(sb, item_create);
 
-	if ((ret = lock_safe(lock, key, mode)))
+	if ((ret = lock_safe(lock, key, mode)) ||
+	    (ret = optional_lock_mode_match(primary, SCOUTFS_LOCK_WRITE)))
 		goto out;
 
 	ret = scoutfs_forest_set_bloom_bits(sb, lock);
@@ -1943,15 +1959,15 @@ out:
 int scoutfs_item_create(struct super_block *sb, struct scoutfs_key *key,
 			void *val, int val_len, struct scoutfs_lock *lock)
 {
-	return item_create(sb, key, val, val_len, lock,
+	return item_create(sb, key, val, val_len, lock, NULL,
 			   SCOUTFS_LOCK_READ, false);
 }
 
 int scoutfs_item_create_force(struct super_block *sb, struct scoutfs_key *key,
 			      void *val, int val_len,
-			      struct scoutfs_lock *lock)
+			      struct scoutfs_lock *lock, struct scoutfs_lock *primary)
 {
-	return item_create(sb, key, val, val_len, lock,
+	return item_create(sb, key, val, val_len, lock, primary,
 			   SCOUTFS_LOCK_WRITE_ONLY, true);
 }
 
@@ -1965,7 +1981,7 @@ int scoutfs_item_update(struct super_block *sb, struct scoutfs_key *key,
 			void *val, int val_len, struct scoutfs_lock *lock)
 {
 	DECLARE_ITEM_CACHE_INFO(sb, cinf);
-	const u64 seq = item_seq(sb, lock);
+	const u64 seq = item_seq(sb, lock, NULL);
 	struct cached_item *item;
 	struct cached_item *found;
 	struct cached_page *pg;
@@ -2025,12 +2041,16 @@ out:
  * current items so the caller always writes with write only locks.  If
  * combining the current delta item and the caller's item results in a
  * null we can just drop it, we don't have to emit a deletion item.
+ *
+ * Delta items don't have to worry about creating items with old
+ * versions under write_only locks.  The versions don't impact how we
+ * merge two items.
  */
 int scoutfs_item_delta(struct super_block *sb, struct scoutfs_key *key,
 		       void *val, int val_len, struct scoutfs_lock *lock)
 {
 	DECLARE_ITEM_CACHE_INFO(sb, cinf);
-	const u64 seq = item_seq(sb, lock);
+	const u64 seq = item_seq(sb, lock, NULL);
 	struct cached_item *item;
 	struct cached_page *pg;
 	struct rb_node **pnode;
@@ -2099,10 +2119,11 @@ out:
  * deletion item if there isn't one already cached.
  */
 static int item_delete(struct super_block *sb, struct scoutfs_key *key,
-		       struct scoutfs_lock *lock, int mode, bool force)
+		       struct scoutfs_lock *lock, struct scoutfs_lock *primary,
+		       int mode, bool force)
 {
 	DECLARE_ITEM_CACHE_INFO(sb, cinf);
-	const u64 seq = item_seq(sb, lock);
+	const u64 seq = item_seq(sb, lock, primary);
 	struct cached_item *item;
 	struct cached_page *pg;
 	struct rb_node **pnode;
@@ -2111,7 +2132,8 @@ static int item_delete(struct super_block *sb, struct scoutfs_key *key,
 
 	scoutfs_inc_counter(sb, item_delete);
 
-	if ((ret = lock_safe(lock, key, mode)))
+	if ((ret = lock_safe(lock, key, mode)) ||
+	    (ret = optional_lock_mode_match(primary, SCOUTFS_LOCK_WRITE)))
 		goto out;
 
 	ret = scoutfs_forest_set_bloom_bits(sb, lock);
@@ -2161,13 +2183,13 @@ out:
 int scoutfs_item_delete(struct super_block *sb, struct scoutfs_key *key,
 			struct scoutfs_lock *lock)
 {
-	return item_delete(sb, key, lock, SCOUTFS_LOCK_WRITE, false);
+	return item_delete(sb, key, lock, NULL, SCOUTFS_LOCK_WRITE, false);
 }
 
 int scoutfs_item_delete_force(struct super_block *sb, struct scoutfs_key *key,
-			      struct scoutfs_lock *lock)
+			      struct scoutfs_lock *lock, struct scoutfs_lock *primary)
 {
-	return item_delete(sb, key, lock, SCOUTFS_LOCK_WRITE_ONLY, true);
+	return item_delete(sb, key, lock, primary, SCOUTFS_LOCK_WRITE_ONLY, true);
 }
 
 u64 scoutfs_item_dirty_pages(struct super_block *sb)

kmod/src/item.h

@@ -15,16 +15,15 @@ int scoutfs_item_create(struct super_block *sb, struct scoutfs_key *key,
 			void *val, int val_len, struct scoutfs_lock *lock);
 int scoutfs_item_create_force(struct super_block *sb, struct scoutfs_key *key,
 			      void *val, int val_len,
-			      struct scoutfs_lock *lock);
+			      struct scoutfs_lock *lock, struct scoutfs_lock *primary);
 int scoutfs_item_update(struct super_block *sb, struct scoutfs_key *key,
 			void *val, int val_len, struct scoutfs_lock *lock);
 int scoutfs_item_delta(struct super_block *sb, struct scoutfs_key *key,
 		       void *val, int val_len, struct scoutfs_lock *lock);
 int scoutfs_item_delete(struct super_block *sb, struct scoutfs_key *key,
 			  struct scoutfs_lock *lock);
-int scoutfs_item_delete_force(struct super_block *sb,
-				struct scoutfs_key *key,
-				struct scoutfs_lock *lock);
+int scoutfs_item_delete_force(struct super_block *sb, struct scoutfs_key *key,
+			      struct scoutfs_lock *lock, struct scoutfs_lock *primary);
 
 u64 scoutfs_item_dirty_pages(struct super_block *sb);
 int scoutfs_item_write_dirty(struct super_block *sb);

kmod/src/kernelcompat.h

@@ -46,4 +46,10 @@ static inline int dir_emit_dots(struct file *file, void *dirent,
 }
 #endif
 
+#ifdef KC_POSIX_ACL_VALID_USER_NS
+#define kc_posix_acl_valid(user_ns, acl) posix_acl_valid(user_ns, acl)
+#else
+#define kc_posix_acl_valid(user_ns, acl) posix_acl_valid(acl)
+#endif
+
 #endif

kmod/src/lock.c

@@ -18,6 +18,7 @@
 #include <linux/mm.h>
 #include <linux/sort.h>
 #include <linux/ctype.h>
+#include <linux/posix_acl.h>
 
 #include "super.h"
 #include "lock.h"
@@ -129,16 +130,13 @@ static bool lock_modes_match(int granted, int requested)
  * allows deletions to be performed by unlink without having to wait for
  * remote cached inodes to be dropped.
  *
- * If the cached inode was already deferring final inode deletion then
- * we can't perform that inline in invalidation.  The locking alone
- * deadlock, and it might also take multiple transactions to fully
- * delete an inode with significant metadata.  We only perform the iput
- * inline if we know that possible eviction can't perform the final
- * deletion, otherwise we kick it off to async work.
+ * We kick the d_prune and iput off to async work because they can end
+ * up in final iput and inode eviction item deletion which would
+ * deadlock.   d_prune->dput can end up in iput on parents in different
+ * locks entirely.
  */
 static void invalidate_inode(struct super_block *sb, u64 ino)
 {
-	DECLARE_LOCK_INFO(sb, linfo);
 	struct scoutfs_inode_info *si;
 	struct inode *inode;
 
@@ -152,17 +150,9 @@ static void invalidate_inode(struct super_block *sb, u64 ino)
 			scoutfs_data_wait_changed(inode);
 		}
 
-		/* can't touch during unmount, dcache destroys w/o locks */
-		if (!linfo->unmounting)
-			d_prune_aliases(inode);
+		forget_all_cached_acls(inode);
 
-		si->drop_invalidated = true;
-		if (scoutfs_lock_is_covered(sb, &si->ino_lock_cov) && inode->i_nlink > 0) {
-			iput(inode);
-		} else {
-			/* defer iput to work context so we don't evict inodes from invalidation */
-			scoutfs_inode_queue_iput(inode);
-		}
+		scoutfs_inode_queue_iput(inode, SI_IPUT_FLAG_PRUNE);
 	}
 }
 
@@ -198,16 +188,6 @@ 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)) {
 retry:
-		/* invalidate inodes before removing coverage */
-		if (lock->start.sk_zone == SCOUTFS_FS_ZONE) {
-			ino = le64_to_cpu(lock->start.ski_ino);
-			last = le64_to_cpu(lock->end.ski_ino);
-			while (ino <= last) {
-				invalidate_inode(sb, ino);
-				ino++;
-			}
-		}
-
 		/* remove cov items to tell users that their cache is stale */
 		spin_lock(&lock->cov_list_lock);
 		list_for_each_entry_safe(cov, tmp, &lock->cov_list, head) {
@@ -223,6 +203,16 @@ retry:
 		}
 		spin_unlock(&lock->cov_list_lock);
 
+		/* invalidate inodes after removing coverage so drop/evict aren't covered */
+		if (lock->start.sk_zone == SCOUTFS_FS_ZONE) {
+			ino = le64_to_cpu(lock->start.ski_ino);
+			last = le64_to_cpu(lock->end.ski_ino);
+			while (ino <= last) {
+				invalidate_inode(sb, ino);
+				ino++;
+			}
+		}
+
 		scoutfs_item_invalidate(sb, &lock->start, &lock->end);
 	}
 
@@ -289,6 +279,7 @@ static struct scoutfs_lock *lock_alloc(struct super_block *sb,
 	lock->sb = sb;
 	init_waitqueue_head(&lock->waitq);
 	lock->mode = SCOUTFS_LOCK_NULL;
+	lock->invalidating_mode = SCOUTFS_LOCK_NULL;
 
 	atomic64_set(&lock->forest_bloom_nr, 0);
 
@@ -666,7 +657,9 @@ struct inv_req {
  *
  * Before we start invalidating the lock we set the lock to the new
  * mode, preventing further incompatible users of the old mode from
- * using the lock while we're invalidating.
+ * using the lock while we're invalidating.  We record the previously
+ * granted mode so that we can send lock recover responses with the old
+ * granted mode during invalidation.
  */
 static void lock_invalidate_worker(struct work_struct *work)
 {
@@ -691,7 +684,8 @@ static void lock_invalidate_worker(struct work_struct *work)
 		if (!lock_counts_match(nl->new_mode, lock->users))
 			continue;
 
-		/* set the new mode, no incompatible users during inval */
+		/* set the new mode, no incompatible users during inval, recov needs old */
+		lock->invalidating_mode = lock->mode;
 		lock->mode = nl->new_mode;
 
 		/* move everyone that's ready to our private list */
@@ -734,6 +728,8 @@ static void lock_invalidate_worker(struct work_struct *work)
 		list_del(&ireq->head);
 		kfree(ireq);
 
+		lock->invalidating_mode = SCOUTFS_LOCK_NULL;
+
 		if (list_empty(&lock->inv_list)) {
 			/* finish if another request didn't arrive */
 			list_del_init(&lock->inv_head);
@@ -824,6 +820,7 @@ int scoutfs_lock_recover_request(struct super_block *sb, u64 net_id,
 {
 	DECLARE_LOCK_INFO(sb, linfo);
 	struct scoutfs_net_lock_recover *nlr;
+	enum scoutfs_lock_mode mode;
 	struct scoutfs_lock *lock;
 	struct scoutfs_lock *next;
 	struct rb_node *node;
@@ -844,10 +841,15 @@ int scoutfs_lock_recover_request(struct super_block *sb, u64 net_id,
 
 	for (i = 0; lock && i < SCOUTFS_NET_LOCK_MAX_RECOVER_NR; i++) {
 
+		if (lock->invalidating_mode != SCOUTFS_LOCK_NULL)
+			mode = lock->invalidating_mode;
+		else
+			mode = lock->mode;
+
 		nlr->locks[i].key = lock->start;
 		nlr->locks[i].write_seq = cpu_to_le64(lock->write_seq);
-		nlr->locks[i].old_mode = lock->mode;
-		nlr->locks[i].new_mode = lock->mode;
+		nlr->locks[i].old_mode = mode;
+		nlr->locks[i].new_mode = mode;
 
 		node = rb_next(&lock->node);
 		if (node)
@@ -1513,6 +1515,38 @@ void scoutfs_lock_flush_invalidate(struct super_block *sb)
 		flush_work(&linfo->inv_work);
 }
 
+static u64 get_held_lock_refresh_gen(struct super_block *sb, struct scoutfs_key *start)
+{
+	DECLARE_LOCK_INFO(sb, linfo);
+	struct scoutfs_lock *lock;
+	u64 refresh_gen = 0;
+
+	/* this can be called from all manner of places */
+	if (!linfo)
+		return 0;
+
+	spin_lock(&linfo->lock);
+	lock = lock_lookup(sb, start, NULL);
+	if (lock) {
+		if (lock_mode_can_read(lock->mode))
+			refresh_gen = lock->refresh_gen;
+	}
+	spin_unlock(&linfo->lock);
+
+	return refresh_gen;
+}
+
+u64 scoutfs_lock_ino_refresh_gen(struct super_block *sb, u64 ino)
+{
+	struct scoutfs_key start;
+
+	scoutfs_key_set_zeros(&start);
+	start.sk_zone = SCOUTFS_FS_ZONE;
+	start.ski_ino = cpu_to_le64(ino & ~(u64)SCOUTFS_LOCK_INODE_GROUP_MASK);
+
+	return get_held_lock_refresh_gen(sb, &start);
+}
+
 /*
  * The caller is going to be shutting down transactions and the client.
  * We need to make sure that locking won't call either after we return.

kmod/src/lock.h

@@ -39,6 +39,7 @@ struct scoutfs_lock {
 	struct list_head cov_list;
 
 	enum scoutfs_lock_mode mode;
+	enum scoutfs_lock_mode invalidating_mode;
 	unsigned int waiters[SCOUTFS_LOCK_NR_MODES];
 	unsigned int users[SCOUTFS_LOCK_NR_MODES];
 
@@ -99,6 +100,8 @@ void scoutfs_lock_del_coverage(struct super_block *sb,
 bool scoutfs_lock_protected(struct scoutfs_lock *lock, struct scoutfs_key *key,
 			    enum scoutfs_lock_mode mode);
 
+u64 scoutfs_lock_ino_refresh_gen(struct super_block *sb, u64 ino);
+
 void scoutfs_free_unused_locks(struct super_block *sb);
 
 int scoutfs_lock_setup(struct super_block *sb);

kmod/src/net.c

@@ -355,6 +355,7 @@ static int submit_send(struct super_block *sb,
 		}
 		if (rid != 0) {
 			spin_unlock(&conn->lock);
+			kfree(msend);
 			return -ENOTCONN;
 		}
 	}
@@ -991,6 +992,8 @@ static void scoutfs_net_listen_worker(struct work_struct *work)
 		if (ret < 0)
 			break;
 
+		acc_sock->sk->sk_allocation = GFP_NOFS;
+
 		/* inherit accepted request funcs from listening conn */
 		acc_conn = scoutfs_net_alloc_conn(sb, conn->notify_up,
 						  conn->notify_down,
@@ -1053,6 +1056,8 @@ static void scoutfs_net_connect_worker(struct work_struct *work)
 	if (ret)
 		goto out;
 
+	sock->sk->sk_allocation = GFP_NOFS;
+
 	/* 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;
@@ -1341,10 +1346,12 @@ scoutfs_net_alloc_conn(struct super_block *sb,
 	if (!conn)
 		return NULL;
 
-	conn->info = kzalloc(info_size, GFP_NOFS);
-	if (!conn->info) {
-		kfree(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",
@@ -1450,6 +1457,8 @@ int scoutfs_net_bind(struct super_block *sb,
 	if (ret)
 		goto out;
 
+	sock->sk->sk_allocation = GFP_NOFS;
+
 	optval = 1;
 	ret = kernel_setsockopt(sock, SOL_SOCKET, SO_REUSEADDR,
 				(char *)&optval, sizeof(optval));

kmod/src/omap.c

@@ -157,6 +157,15 @@ static int free_rid(struct omap_rid_list *list, struct omap_rid_entry *entry)
 	return nr;
 }
 
+static void free_rid_list(struct omap_rid_list *list)
+{
+	struct omap_rid_entry *entry;
+	struct omap_rid_entry *tmp;
+
+	list_for_each_entry_safe(entry, tmp, &list->head, head)
+		free_rid(list, entry);
+}
+
 static int copy_rids(struct omap_rid_list *to, struct omap_rid_list *from, spinlock_t *from_lock)
 {
 	struct omap_rid_entry *entry;
@@ -804,6 +813,10 @@ void scoutfs_omap_server_shutdown(struct super_block *sb)
 	llist_for_each_entry_safe(req, tmp, requests, llnode)
 		kfree(req);
 
+	spin_lock(&ominf->lock);
+	free_rid_list(&ominf->rids);
+	spin_unlock(&ominf->lock);
+
 	synchronize_rcu();
 }
 
@@ -864,6 +877,10 @@ void scoutfs_omap_destroy(struct super_block *sb)
 		rhashtable_walk_stop(&iter);
 		rhashtable_walk_exit(&iter);
 
+		spin_lock(&ominf->lock);
+		free_rid_list(&ominf->rids);
+		spin_unlock(&ominf->lock);
+
 		rhashtable_destroy(&ominf->group_ht);
 		rhashtable_destroy(&ominf->req_ht);
 		kfree(ominf);

kmod/src/options.c

@@ -27,17 +27,28 @@
 #include "options.h"
 #include "super.h"
 #include "inode.h"
+#include "alloc.h"
 
 enum {
+	Opt_acl,
+	Opt_data_prealloc_blocks,
+	Opt_data_prealloc_contig_only,
 	Opt_metadev_path,
+	Opt_noacl,
 	Opt_orphan_scan_delay_ms,
+	Opt_quorum_heartbeat_timeout_ms,
 	Opt_quorum_slot_nr,
 	Opt_err,
 };
 
 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_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_err, NULL}
 };
@@ -106,11 +117,33 @@ static void free_options(struct scoutfs_mount_options *opts)
 #define DEFAULT_ORPHAN_SCAN_DELAY_MS	(10 * MSEC_PER_SEC)
 #define MAX_ORPHAN_SCAN_DELAY_MS	(60 * MSEC_PER_SEC)
 
+#define MIN_DATA_PREALLOC_BLOCKS	1ULL
+#define MAX_DATA_PREALLOC_BLOCKS	((unsigned long long)SCOUTFS_BLOCK_SM_MAX)
+
 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->orphan_scan_delay_ms = -1;
+	opts->quorum_heartbeat_timeout_ms = SCOUTFS_QUORUM_DEF_HB_TIMEO_MS;
 	opts->quorum_slot_nr = -1;
-	opts->orphan_scan_delay_ms = DEFAULT_ORPHAN_SCAN_DELAY_MS;
+}
+
+static int verify_quorum_heartbeat_timeout_ms(struct super_block *sb, int ret, u64 val)
+{
+	if (ret < 0) {
+		scoutfs_err(sb, "failed to parse quorum_heartbeat_timeout_ms value");
+		return -EINVAL;
+	}
+	if (val < SCOUTFS_QUORUM_MIN_HB_TIMEO_MS || val > SCOUTFS_QUORUM_MAX_HB_TIMEO_MS) {
+		scoutfs_err(sb, "invalid quorum_heartbeat_timeout_ms value %llu, must be between %lu and %lu",
+			    val, SCOUTFS_QUORUM_MIN_HB_TIMEO_MS, SCOUTFS_QUORUM_MAX_HB_TIMEO_MS);
+		return -EINVAL;
+	}
+
+	return 0;
 }
 
 /*
@@ -122,6 +155,7 @@ static void init_default_options(struct scoutfs_mount_options *opts)
 static int parse_options(struct super_block *sb, char *options, struct scoutfs_mount_options *opts)
 {
 	substring_t args[MAX_OPT_ARGS];
+	u64 nr64;
 	int nr;
 	int token;
 	char *p;
@@ -134,12 +168,44 @@ static int parse_options(struct super_block *sb, char *options, struct scoutfs_m
 		token = match_token(p, tokens, args);
 		switch (token) {
 
+		case Opt_acl:
+			sb->s_flags |= MS_POSIXACL;
+			break;
+
+		case Opt_data_prealloc_blocks:
+			ret = match_u64(args, &nr64);
+			if (ret < 0 ||
+			    nr64 < MIN_DATA_PREALLOC_BLOCKS || nr64 > MAX_DATA_PREALLOC_BLOCKS) {
+				scoutfs_err(sb, "invalid data_prealloc_blocks option, must be between %llu and %llu",
+					    MIN_DATA_PREALLOC_BLOCKS, MAX_DATA_PREALLOC_BLOCKS);
+				if (ret == 0)
+					ret = -EINVAL;
+				return ret;
+			}
+			opts->data_prealloc_blocks = nr64;
+			break;
+
+		case Opt_data_prealloc_contig_only:
+			ret = match_int(args, &nr);
+			if (ret < 0 || nr < 0 || nr > 1) {
+				scoutfs_err(sb, "invalid data_prealloc_contig_only option, bool must only be 0 or 1");
+				if (ret == 0)
+					ret = -EINVAL;
+				return ret;
+			}
+			opts->data_prealloc_contig_only = nr;
+			break;
+
 		case Opt_metadev_path:
 			ret = parse_bdev_path(sb, &args[0], &opts->metadev_path);
 			if (ret < 0)
 				return ret;
 			break;
 
+		case Opt_noacl:
+			sb->s_flags &= ~MS_POSIXACL;
+			break;
+
 		case Opt_orphan_scan_delay_ms:
 			if (opts->orphan_scan_delay_ms != -1) {
 				scoutfs_err(sb, "multiple orphan_scan_delay_ms options provided, only provide one.");
@@ -158,6 +224,14 @@ static int parse_options(struct super_block *sb, char *options, struct scoutfs_m
 			opts->orphan_scan_delay_ms = nr;
 			break;
 
+		case Opt_quorum_heartbeat_timeout_ms:
+			ret = match_u64(args, &nr64);
+			ret = verify_quorum_heartbeat_timeout_ms(sb, ret, nr64);
+			if (ret < 0)
+				return ret;
+			opts->quorum_heartbeat_timeout_ms = nr64;
+			break;
+
 		case Opt_quorum_slot_nr:
 			if (opts->quorum_slot_nr != -1) {
 				scoutfs_err(sb, "multiple quorum_slot_nr options provided, only provide one.");
@@ -181,6 +255,9 @@ static int parse_options(struct super_block *sb, char *options, struct scoutfs_m
 		}
 	}
 
+	if (opts->orphan_scan_delay_ms == -1)
+		opts->orphan_scan_delay_ms = DEFAULT_ORPHAN_SCAN_DELAY_MS;
+
 	if (!opts->metadev_path) {
 		scoutfs_err(sb, "Required mount option \"metadev_path\" not found");
 		return -EINVAL;
@@ -250,10 +327,17 @@ int scoutfs_options_show(struct seq_file *seq, struct dentry *root)
 {
 	struct super_block *sb = root->d_sb;
 	struct scoutfs_mount_options opts;
+	const bool is_acl = !!(sb->s_flags & MS_POSIXACL);
 
 	scoutfs_options_read(sb, &opts);
 
+	if (is_acl)
+		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, ",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);
@@ -261,6 +345,83 @@ int scoutfs_options_show(struct seq_file *seq, struct dentry *root)
 	return 0;
 }
 
+static ssize_t data_prealloc_blocks_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, "%llu", opts.data_prealloc_blocks);
+}
+static ssize_t data_prealloc_blocks_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 */
+	u64 val;
+	int len;
+	int ret;
+
+	len = min(count, sizeof(nullterm) - 1);
+	memcpy(nullterm, buf, len);
+	nullterm[len] = '\0';
+
+	ret = kstrtoll(nullterm, 0, &val);
+	if (ret < 0 || val < MIN_DATA_PREALLOC_BLOCKS || val > MAX_DATA_PREALLOC_BLOCKS) {
+		scoutfs_err(sb, "invalid data_prealloc_blocks option, must be between %llu and %llu",
+			    MIN_DATA_PREALLOC_BLOCKS, MAX_DATA_PREALLOC_BLOCKS);
+		return -EINVAL;
+	}
+
+	write_seqlock(&optinf->seqlock);
+	optinf->opts.data_prealloc_blocks = val;
+	write_sequnlock(&optinf->seqlock);
+
+	return count;
+}
+SCOUTFS_ATTR_RW(data_prealloc_blocks);
+
+static ssize_t data_prealloc_contig_only_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.data_prealloc_contig_only);
+}
+static ssize_t data_prealloc_contig_only_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 < 0 || val > 1) {
+		scoutfs_err(sb, "invalid data_prealloc_contig_only option, bool must be 0 or 1");
+		return -EINVAL;
+	}
+
+	write_seqlock(&optinf->seqlock);
+	optinf->opts.data_prealloc_contig_only = val;
+	write_sequnlock(&optinf->seqlock);
+
+	return count;
+}
+SCOUTFS_ATTR_RW(data_prealloc_contig_only);
+
 static ssize_t metadev_path_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 {
 	struct super_block *sb = SCOUTFS_SYSFS_ATTRS_SB(kobj);
@@ -313,6 +474,43 @@ static ssize_t orphan_scan_delay_ms_store(struct kobject *kobj, struct kobj_attr
 }
 SCOUTFS_ATTR_RW(orphan_scan_delay_ms);
 
+static ssize_t quorum_heartbeat_timeout_ms_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, "%llu", opts.quorum_heartbeat_timeout_ms);
+}
+static ssize_t quorum_heartbeat_timeout_ms_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 */
+	u64 val;
+	int len;
+	int ret;
+
+	len = min(count, sizeof(nullterm) - 1);
+	memcpy(nullterm, buf, len);
+	nullterm[len] = '\0';
+
+	ret = kstrtoll(nullterm, 0, &val);
+	ret = verify_quorum_heartbeat_timeout_ms(sb, ret, val);
+	if (ret == 0) {
+		write_seqlock(&optinf->seqlock);
+		optinf->opts.quorum_heartbeat_timeout_ms = val;
+		write_sequnlock(&optinf->seqlock);
+		ret = count;
+	}
+
+	return ret;
+}
+SCOUTFS_ATTR_RW(quorum_heartbeat_timeout_ms);
+
 static ssize_t quorum_slot_nr_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
 {
 	struct super_block *sb = SCOUTFS_SYSFS_ATTRS_SB(kobj);
@@ -325,8 +523,11 @@ static ssize_t quorum_slot_nr_show(struct kobject *kobj, struct kobj_attribute *
 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(metadev_path),
 	SCOUTFS_ATTR_PTR(orphan_scan_delay_ms),
+	SCOUTFS_ATTR_PTR(quorum_heartbeat_timeout_ms),
 	SCOUTFS_ATTR_PTR(quorum_slot_nr),
 	NULL,
 };

kmod/src/options.h

@@ -6,10 +6,12 @@
 #include "format.h"
 
 struct scoutfs_mount_options {
+	u64 data_prealloc_blocks;
+	bool data_prealloc_contig_only;
 	char *metadev_path;
 	unsigned int orphan_scan_delay_ms;
 	int quorum_slot_nr;
-
+	u64 quorum_heartbeat_timeout_ms;
 };
 
 void scoutfs_options_read(struct super_block *sb, struct scoutfs_mount_options *opts);

kmod/src/quorum.c

@@ -100,6 +100,11 @@ struct last_msg {
 	ktime_t ts;
 };
 
+struct count_recent {
+	u64 count;
+	ktime_t recent;
+};
+
 enum quorum_role { FOLLOWER, CANDIDATE, LEADER };
 
 struct quorum_status {
@@ -112,8 +117,12 @@ struct quorum_status {
 	ktime_t timeout;
 };
 
+#define HB_DELAY_NR		(SCOUTFS_QUORUM_MAX_HB_TIMEO_MS / MSEC_PER_SEC)
+
 struct quorum_info {
 	struct super_block *sb;
+	struct scoutfs_quorum_config qconf;
+	struct workqueue_struct *workq;
 	struct work_struct work;
 	struct socket *sock;
 	bool shutdown;
@@ -125,6 +134,8 @@ struct quorum_info {
 	struct quorum_status show_status;
 	struct last_msg last_send[SCOUTFS_QUORUM_MAX_SLOTS];
 	struct last_msg last_recv[SCOUTFS_QUORUM_MAX_SLOTS];
+	struct count_recent *hb_delay;
+	unsigned long max_hb_delay;
 
 	struct scoutfs_sysfs_attrs ssa;
 };
@@ -134,11 +145,18 @@ struct quorum_info {
 #define DECLARE_QUORUM_INFO_KOBJ(kobj, name) \
 	DECLARE_QUORUM_INFO(SCOUTFS_SYSFS_ATTRS_SB(kobj), name)
 
-static bool quorum_slot_present(struct scoutfs_super_block *super, int i)
+static bool quorum_slot_present(struct scoutfs_quorum_config *qconf, int i)
 {
 	BUG_ON(i < 0 || i > SCOUTFS_QUORUM_MAX_SLOTS);
 
-	return super->qconf.slots[i].addr.v4.family == cpu_to_le16(SCOUTFS_AF_IPV4);
+	return qconf->slots[i].addr.v4.family == cpu_to_le16(SCOUTFS_AF_IPV4);
+}
+
+static void quorum_slot_sin(struct scoutfs_quorum_config *qconf, int i, struct sockaddr_in *sin)
+{
+	BUG_ON(i < 0 || i >= SCOUTFS_QUORUM_MAX_SLOTS);
+
+	scoutfs_addr_to_sin(sin, &qconf->slots[i].addr);
 }
 
 static ktime_t election_timeout(void)
@@ -152,15 +170,14 @@ static ktime_t heartbeat_interval(void)
 	return ktime_add_ms(ktime_get(), SCOUTFS_QUORUM_HB_IVAL_MS);
 }
 
-static ktime_t heartbeat_timeout(void)
+static ktime_t heartbeat_timeout(struct scoutfs_mount_options *opts)
 {
-	return ktime_add_ms(ktime_get(), SCOUTFS_QUORUM_HB_TIMEO_MS);
+	return ktime_add_ms(ktime_get(), opts->quorum_heartbeat_timeout_ms);
 }
 
 static int create_socket(struct super_block *sb)
 {
 	DECLARE_QUORUM_INFO(sb, qinf);
-	struct scoutfs_super_block *super = &SCOUTFS_SB(sb)->super;
 	struct socket *sock = NULL;
 	struct sockaddr_in sin;
 	int addrlen;
@@ -172,9 +189,10 @@ static int create_socket(struct super_block *sb)
 		goto out;
 	}
 
-	sock->sk->sk_allocation = GFP_NOFS;
+	/* rather fail and retry than block waiting for free */
+	sock->sk->sk_allocation = GFP_ATOMIC;
 
-	scoutfs_quorum_slot_sin(super, qinf->our_quorum_slot_nr, &sin);
+	quorum_slot_sin(&qinf->qconf, qinf->our_quorum_slot_nr, &sin);
 
 	addrlen = sizeof(sin);
 	ret = kernel_bind(sock, (struct sockaddr *)&sin, addrlen);
@@ -201,16 +219,20 @@ static __le32 quorum_message_crc(struct scoutfs_quorum_message *qmes)
 	return cpu_to_le32(crc32c(~0, qmes, len));
 }
 
-static void send_msg_members(struct super_block *sb, int type, u64 term,
-			     int only)
+/*
+ * Returns the number of failures from sendmsg.
+ */
+static int send_msg_members(struct super_block *sb, int type, u64 term, int only)
 {
+	struct scoutfs_sb_info *sbi = SCOUTFS_SB(sb);
 	DECLARE_QUORUM_INFO(sb, qinf);
-	struct scoutfs_super_block *super = &SCOUTFS_SB(sb)->super;
+	int failed = 0;
 	ktime_t now;
+	int ret;
 	int i;
 
 	struct scoutfs_quorum_message qmes = {
-		.fsid = super->hdr.fsid,
+		.fsid = cpu_to_le64(sbi->fsid),
 		.term = cpu_to_le64(term),
 		.type = type,
 		.from = qinf->our_quorum_slot_nr,
@@ -232,15 +254,21 @@ static void send_msg_members(struct super_block *sb, int type, u64 term,
 
 	qmes.crc = quorum_message_crc(&qmes);
 
-
 	for (i = 0; i < SCOUTFS_QUORUM_MAX_SLOTS; i++) {
-		if (!quorum_slot_present(super, i) ||
+		if (!quorum_slot_present(&qinf->qconf, i) ||
 		    (only >= 0 && i != only) || i == qinf->our_quorum_slot_nr)
 			continue;
 
-		scoutfs_quorum_slot_sin(super, i, &sin);
+		if (scoutfs_forcing_unmount(sb)) {
+			failed = 0;
+			break;
+		}
+
+		scoutfs_quorum_slot_sin(&qinf->qconf, i, &sin);
 		now = ktime_get();
-		kernel_sendmsg(qinf->sock, &mh, &kv, 1, kv.iov_len);
+		ret = kernel_sendmsg(qinf->sock, &mh, &kv, 1, kv.iov_len);
+		if (ret != kv.iov_len)
+			failed++;
 
 		spin_lock(&qinf->show_lock);
 		qinf->last_send[i].msg.term = term;
@@ -251,6 +279,8 @@ static void send_msg_members(struct super_block *sb, int type, u64 term,
 		if (i == only)
 			break;
 	}
+
+	return failed;
 }
 
 #define send_msg_to(sb, type, term, nr)  send_msg_members(sb, type, term, nr)
@@ -266,7 +296,7 @@ static int recv_msg(struct super_block *sb, struct quorum_host_msg *msg,
 		    ktime_t abs_to)
 {
 	DECLARE_QUORUM_INFO(sb, qinf);
-	struct scoutfs_super_block *super = &SCOUTFS_SB(sb)->super;
+	struct scoutfs_sb_info *sbi = SCOUTFS_SB(sb);
 	struct scoutfs_quorum_message qmes;
 	struct timeval tv;
 	ktime_t rel_to;
@@ -305,14 +335,17 @@ static int recv_msg(struct super_block *sb, struct quorum_host_msg *msg,
 	if (ret < 0)
 		return ret;
 
+	if (scoutfs_forcing_unmount(sb))
+		return 0;
+
 	now = ktime_get();
 
 	if (ret != sizeof(qmes) ||
 	    qmes.crc != quorum_message_crc(&qmes) ||
-	    qmes.fsid != super->hdr.fsid ||
+	    qmes.fsid != cpu_to_le64(sbi->fsid) ||
 	    qmes.type >= SCOUTFS_QUORUM_MSG_INVALID ||
 	    qmes.from >= SCOUTFS_QUORUM_MAX_SLOTS ||
-	    !quorum_slot_present(super, qmes.from)) {
+	    !quorum_slot_present(&qinf->qconf, qmes.from)) {
 		/* should we be trying to open a new socket? */
 		scoutfs_inc_counter(sb, quorum_recv_invalid);
 		return -EAGAIN;
@@ -342,7 +375,7 @@ static int read_quorum_block(struct super_block *sb, u64 blkno, struct scoutfs_q
 			     bool check_rid)
 {
 	struct scoutfs_sb_info *sbi = SCOUTFS_SB(sb);
-	struct scoutfs_super_block *super = &sbi->super;
+	const u64 fsid = sbi->fsid;
 	const u64 rid = sbi->rid;
 	char msg[150];
 	__le32 crc;
@@ -367,9 +400,9 @@ static int read_quorum_block(struct super_block *sb, u64 blkno, struct scoutfs_q
 	else if (le32_to_cpu(blk->hdr.magic) != SCOUTFS_BLOCK_MAGIC_QUORUM) 
 		snprintf(msg, sizeof(msg), "blk magic %08x != %08x",
 			 le32_to_cpu(blk->hdr.magic), SCOUTFS_BLOCK_MAGIC_QUORUM);
-	else if (blk->hdr.fsid != super->hdr.fsid)
+	else if (blk->hdr.fsid != cpu_to_le64(fsid))
 		snprintf(msg, sizeof(msg), "blk fsid %016llx != %016llx",
-			 le64_to_cpu(blk->hdr.fsid), le64_to_cpu(super->hdr.fsid));
+			 le64_to_cpu(blk->hdr.fsid), fsid);
 	else if (le64_to_cpu(blk->hdr.blkno) != blkno)
 		snprintf(msg, sizeof(msg), "blk blkno %llu != %llu",
 			 le64_to_cpu(blk->hdr.blkno), blkno);
@@ -410,8 +443,7 @@ out:
  */
 static void read_greatest_term(struct super_block *sb, u64 *term)
 {
-	struct scoutfs_sb_info *sbi = SCOUTFS_SB(sb);
-	struct scoutfs_super_block *super = &sbi->super;
+	DECLARE_QUORUM_INFO(sb, qinf);
 	struct scoutfs_quorum_block blk;
 	int ret;
 	int e;
@@ -420,7 +452,7 @@ static void read_greatest_term(struct super_block *sb, u64 *term)
 	*term = 0;
 
 	for (s = 0; s < SCOUTFS_QUORUM_MAX_SLOTS; s++) {
-		if (!quorum_slot_present(super, s))
+		if (!quorum_slot_present(&qinf->qconf, s))
 			continue;
 
 		ret = read_quorum_block(sb, SCOUTFS_QUORUM_BLKNO + s, &blk, false);
@@ -514,14 +546,15 @@ static int update_quorum_block(struct super_block *sb, int event, u64 term, bool
  * keeps us from being fenced while we allow userspace fencing to take a
  * reasonably long time.  We still want to timeout eventually.
  */
-int scoutfs_quorum_fence_leaders(struct super_block *sb, u64 term)
+int scoutfs_quorum_fence_leaders(struct super_block *sb, struct scoutfs_quorum_config *qconf,
+				 u64 term)
 {
 #define NR_OLD 2
 	struct scoutfs_quorum_block_event old[SCOUTFS_QUORUM_MAX_SLOTS][NR_OLD] = {{{0,}}};
 	struct scoutfs_sb_info *sbi = SCOUTFS_SB(sb);
-	struct scoutfs_super_block *super = &sbi->super;
 	struct scoutfs_quorum_block blk;
 	struct sockaddr_in sin;
+	const __le64 lefsid = cpu_to_le64(sbi->fsid);
 	const u64 rid = sbi->rid;
 	bool fence_started = false;
 	u64 fenced = 0;
@@ -534,7 +567,7 @@ int scoutfs_quorum_fence_leaders(struct super_block *sb, u64 term)
 	BUILD_BUG_ON(SCOUTFS_QUORUM_BLOCKS < SCOUTFS_QUORUM_MAX_SLOTS);
 
 	for (i = 0; i < SCOUTFS_QUORUM_MAX_SLOTS; i++) {
-		if (!quorum_slot_present(super, i))
+		if (!quorum_slot_present(qconf, i))
 			continue;
 
 		ret = read_quorum_block(sb, SCOUTFS_QUORUM_BLKNO + i, &blk, false);
@@ -567,11 +600,11 @@ int scoutfs_quorum_fence_leaders(struct super_block *sb, u64 term)
 				continue;
 
 			scoutfs_inc_counter(sb, quorum_fence_leader);
-			scoutfs_quorum_slot_sin(super, i, &sin);
+			quorum_slot_sin(qconf, i, &sin);
 			fence_rid = old[i][j].rid;
 
 			scoutfs_info(sb, "fencing previous leader "SCSBF" at term %llu in slot %u with address "SIN_FMT,
-				     SCSB_LEFR_ARGS(super->hdr.fsid, fence_rid),
+				     SCSB_LEFR_ARGS(lefsid, fence_rid),
 				     le64_to_cpu(old[i][j].term), i, SIN_ARG(&sin));
 			ret = scoutfs_fence_start(sb, le64_to_cpu(fence_rid), sin.sin_addr.s_addr,
 						  SCOUTFS_FENCE_QUORUM_BLOCK_LEADER);
@@ -592,6 +625,71 @@ out:
 	return ret;
 }
 
+static void clear_hb_delay(struct quorum_info *qinf)
+{
+	int i;
+
+	spin_lock(&qinf->show_lock);
+	qinf->max_hb_delay = 0;
+	for (i = 0; i < HB_DELAY_NR; i++) {
+		qinf->hb_delay[i].recent = ns_to_ktime(0);
+		qinf->hb_delay[i].count = 0;
+	}
+	spin_unlock(&qinf->show_lock);
+}
+
+struct hb_recording {
+	ktime_t prev;
+	int count;
+};
+
+/*
+ * Record long heartbeat delays.  We only record the delay between back
+ * to back send attempts in the leader or back to back recv messages in
+ * the followers.  The worker caller sets record_hb when their iteration
+ * sent or received a heartbeat.  An iteration that does anything else
+ * resets the tracking.
+ */
+static void record_hb_delay(struct super_block *sb, struct quorum_info *qinf,
+			    struct hb_recording *hbr, bool record_hb, int role)
+{
+	bool log = false;
+	ktime_t now;
+	s64 s;
+
+	if (!record_hb) {
+		hbr->count = 0;
+		return;
+	}
+
+	now = ktime_get();
+
+	if (hbr->count < 2 && ++hbr->count < 2) {
+		hbr->prev = now;
+		return;
+	}
+
+	s = ktime_ms_delta(now, hbr->prev) / MSEC_PER_SEC;
+	hbr->prev = now;
+
+	if (s <= 0 || s >= HB_DELAY_NR)
+		return;
+
+	spin_lock(&qinf->show_lock);
+	if (qinf->max_hb_delay < s) {
+		qinf->max_hb_delay = s;
+		if (s >= 3)
+			log = true;
+	}
+	qinf->hb_delay[s].recent = now;
+	qinf->hb_delay[s].count++;
+	spin_unlock(&qinf->show_lock);
+
+	if (log)
+		scoutfs_info(sb, "longest quorum heartbeat %s delay of %lld sec",
+			     role == LEADER ? "send" : "recv", s);
+}
+
 /*
  * The main quorum task maintains its private status.  It seemed cleaner
  * to occasionally copy the status for showing in sysfs/debugfs files
@@ -616,16 +714,21 @@ static void update_show_status(struct quorum_info *qinf, struct quorum_status *q
 static void scoutfs_quorum_worker(struct work_struct *work)
 {
 	struct quorum_info *qinf = container_of(work, struct quorum_info, work);
+	struct scoutfs_mount_options opts;
 	struct super_block *sb = qinf->sb;
 	struct sockaddr_in unused;
 	struct quorum_host_msg msg;
 	struct quorum_status qst = {0,};
+	struct hb_recording hbr = {{0,},};
+	bool record_hb;
 	int ret;
 	int err;
 
 	/* recording votes from slots as native single word bitmap */
 	BUILD_BUG_ON(SCOUTFS_QUORUM_MAX_SLOTS > BITS_PER_LONG);
 
+	scoutfs_options_read(sb, &opts);
+
 	/* start out as a follower */
 	qst.role = FOLLOWER;
 	qst.vote_for = -1;
@@ -635,7 +738,7 @@ static void scoutfs_quorum_worker(struct work_struct *work)
 
 	/* see if there's a server to chose heartbeat or election timeout */
 	if (scoutfs_quorum_server_sin(sb, &unused) == 0)
-		qst.timeout = heartbeat_timeout();
+		qst.timeout = heartbeat_timeout(&opts);
 	else
 		qst.timeout = election_timeout();
 
@@ -659,6 +762,9 @@ static void scoutfs_quorum_worker(struct work_struct *work)
 			ret = 0;
 		}
 
+		scoutfs_options_read(sb, &opts);
+		record_hb = false;
+
 		/* ignore messages from older terms */
 		if (msg.type != SCOUTFS_QUORUM_MSG_INVALID &&
 		    msg.term < qst.term)
@@ -674,6 +780,7 @@ static void scoutfs_quorum_worker(struct work_struct *work)
 			if (qst.role == LEADER) {
 				scoutfs_warn(sb, "saw msg type %u from %u for term %llu while leader in term %llu, shutting down server.",
 					     msg.type, msg.from, msg.term, qst.term);
+				clear_hb_delay(qinf);
 			}
 			qst.role = FOLLOWER;
 			qst.term = msg.term;
@@ -682,7 +789,7 @@ static void scoutfs_quorum_worker(struct work_struct *work)
 			scoutfs_inc_counter(sb, quorum_term_follower);
 
 			if (msg.type == SCOUTFS_QUORUM_MSG_HEARTBEAT)
-				qst.timeout = heartbeat_timeout();
+				qst.timeout = heartbeat_timeout(&opts);
 			else
 				qst.timeout = election_timeout();
 
@@ -692,6 +799,21 @@ static void scoutfs_quorum_worker(struct work_struct *work)
 				goto out;
 		}
 
+		/* receiving heartbeats extends timeout, delaying elections */
+		if (msg.type == SCOUTFS_QUORUM_MSG_HEARTBEAT) {
+			qst.timeout = heartbeat_timeout(&opts);
+			scoutfs_inc_counter(sb, quorum_recv_heartbeat);
+			record_hb = true;
+		}
+
+		/* receiving a resignation from server starts election */
+		if (msg.type == SCOUTFS_QUORUM_MSG_RESIGNATION &&
+		    qst.role == FOLLOWER &&
+		    msg.term == qst.term) {
+			qst.timeout = election_timeout();
+			scoutfs_inc_counter(sb, quorum_recv_resignation);
+		}
+
 		/* followers and candidates start new election on timeout */
 		if (qst.role != LEADER &&
 		    ktime_after(ktime_get(), qst.timeout)) {
@@ -744,6 +866,7 @@ static void scoutfs_quorum_worker(struct work_struct *work)
 			qst.timeout = heartbeat_interval();
 
 			update_show_status(qinf, &qst);
+			clear_hb_delay(qinf);
 
 			/* record that we've been elected before starting up server */
 			ret = update_quorum_block(sb, SCOUTFS_QUORUM_EVENT_ELECT, qst.term, true);
@@ -752,7 +875,7 @@ static void scoutfs_quorum_worker(struct work_struct *work)
 
 			qst.server_start_term = qst.term;
 			qst.server_event = SCOUTFS_QUORUM_EVENT_ELECT;
-			scoutfs_server_start(sb, qst.term);
+			scoutfs_server_start(sb, &qinf->qconf, qst.term);
 		}
 
 		/*
@@ -798,6 +921,7 @@ static void scoutfs_quorum_worker(struct work_struct *work)
 				send_msg_others(sb, SCOUTFS_QUORUM_MSG_RESIGNATION,
 						qst.server_start_term);
 				scoutfs_inc_counter(sb, quorum_send_resignation);
+				clear_hb_delay(qinf);
 			}
 
 			ret = update_quorum_block(sb, SCOUTFS_QUORUM_EVENT_STOP,
@@ -811,24 +935,16 @@ static void scoutfs_quorum_worker(struct work_struct *work)
 		/* leaders regularly send heartbeats to delay elections */
 		if (qst.role == LEADER &&
 		    ktime_after(ktime_get(), qst.timeout)) {
-			send_msg_others(sb, SCOUTFS_QUORUM_MSG_HEARTBEAT,
-					qst.term);
+			ret = send_msg_others(sb, SCOUTFS_QUORUM_MSG_HEARTBEAT, qst.term);
+			if (ret > 0) {
+				scoutfs_add_counter(sb, quorum_send_heartbeat_dropped, ret);
+				ret = 0;
+			}
+
 			qst.timeout = heartbeat_interval();
 			scoutfs_inc_counter(sb, quorum_send_heartbeat);
-		}
+			record_hb = true;
 
-		/* receiving heartbeats extends timeout, delaying elections */
-		if (msg.type == SCOUTFS_QUORUM_MSG_HEARTBEAT) {
-			qst.timeout = heartbeat_timeout();
-			scoutfs_inc_counter(sb, quorum_recv_heartbeat);
-		}
-
-		/* receiving a resignation from server starts election */
-		if (msg.type == SCOUTFS_QUORUM_MSG_RESIGNATION &&
-		    qst.role == FOLLOWER &&
-		    msg.term == qst.term) {
-			qst.timeout = election_timeout();
-			scoutfs_inc_counter(sb, quorum_recv_resignation);
 		}
 
 		/* followers vote once per term */
@@ -840,6 +956,8 @@ static void scoutfs_quorum_worker(struct work_struct *work)
 				    msg.from);
 			scoutfs_inc_counter(sb, quorum_send_vote);
 		}
+
+		record_hb_delay(sb, qinf, &hbr, record_hb, qst.role);
 	}
 
 	update_show_status(qinf, &qst);
@@ -877,16 +995,25 @@ out:
  */
 int scoutfs_quorum_server_sin(struct super_block *sb, struct sockaddr_in *sin)
 {
-	struct scoutfs_sb_info *sbi = SCOUTFS_SB(sb);
-	struct scoutfs_super_block *super = &sbi->super;
+	struct scoutfs_super_block *super = NULL;
 	struct scoutfs_quorum_block blk;
 	u64 elect_term;
 	u64 term = 0;
 	int ret = 0;
 	int i;
 
+	super = kmalloc(sizeof(struct scoutfs_super_block), GFP_NOFS);
+	if (!super) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = scoutfs_read_super(sb, super);
+	if (ret)
+		goto out;
+
 	for (i = 0; i < SCOUTFS_QUORUM_MAX_SLOTS; i++) {
-		if (!quorum_slot_present(super, i))
+		if (!quorum_slot_present(&super->qconf, i))
 			continue;
 
 		ret = read_quorum_block(sb, SCOUTFS_QUORUM_BLKNO + i, &blk, false);
@@ -900,7 +1027,7 @@ int scoutfs_quorum_server_sin(struct super_block *sb, struct sockaddr_in *sin)
 		if (elect_term > term &&
 		    elect_term > le64_to_cpu(blk.events[SCOUTFS_QUORUM_EVENT_STOP].term)) {
 			term = elect_term;
-			scoutfs_quorum_slot_sin(super, i, sin);
+			scoutfs_quorum_slot_sin(&super->qconf, i, sin);
 			continue;
 		}
 	}
@@ -909,6 +1036,7 @@ int scoutfs_quorum_server_sin(struct super_block *sb, struct sockaddr_in *sin)
 		ret = -ENOENT;
 
 out:
+	kfree(super);
 	return ret;
 }
 
@@ -924,12 +1052,9 @@ u8 scoutfs_quorum_votes_needed(struct super_block *sb)
 	return qinf->votes_needed;
 }
 
-void scoutfs_quorum_slot_sin(struct scoutfs_super_block *super, int i,
-			     struct sockaddr_in *sin)
+void scoutfs_quorum_slot_sin(struct scoutfs_quorum_config *qconf, int i, struct sockaddr_in *sin)
 {
-	BUG_ON(i < 0 || i >= SCOUTFS_QUORUM_MAX_SLOTS);
-
-	scoutfs_addr_to_sin(sin, &super->qconf.slots[i].addr);
+	return quorum_slot_sin(qconf, i, sin);
 }
 
 static char *role_str(int role)
@@ -969,9 +1094,11 @@ static ssize_t status_show(struct kobject *kobj, struct kobj_attribute *attr,
 {
 	DECLARE_QUORUM_INFO_KOBJ(kobj, qinf);
 	struct quorum_status qst;
+	struct count_recent cr;
 	struct last_msg last;
 	struct timespec64 ts;
 	const ktime_t now = ktime_get();
+	unsigned long ul;
 	size_t size;
 	int ret;
 	int i;
@@ -1029,6 +1156,26 @@ static ssize_t status_show(struct kobject *kobj, struct kobj_attribute *attr,
 			     (s64)ts.tv_sec, (int)ts.tv_nsec);
 	}
 
+	spin_lock(&qinf->show_lock);
+	ul = qinf->max_hb_delay;
+	spin_unlock(&qinf->show_lock);
+	if (ul)
+		snprintf_ret(buf, size, &ret, "HB Delay(s)      Count  Secs Since\n");
+
+	for (i = 1; i <= ul && i < HB_DELAY_NR; i++) {
+		spin_lock(&qinf->show_lock);
+		cr = qinf->hb_delay[i];
+		spin_unlock(&qinf->show_lock);
+
+		if (cr.count == 0)
+			continue;
+
+		ts = ktime_to_timespec64(ktime_sub(now, cr.recent));
+		snprintf_ret(buf, size, &ret,
+			     "%11u  %9llu  %lld.%09u\n",
+			     i, cr.count, (s64)ts.tv_sec, (int)ts.tv_nsec);
+	}
+
 	return ret;
 }
 SCOUTFS_ATTR_RO(status);
@@ -1060,11 +1207,10 @@ static inline bool valid_ipv4_port(__be16 port)
 	return port != 0 && be16_to_cpu(port) != U16_MAX;
 }
 
-static int verify_quorum_slots(struct super_block *sb)
+static int verify_quorum_slots(struct super_block *sb, struct quorum_info *qinf,
+			       struct scoutfs_quorum_config *qconf)
 {
-	struct scoutfs_super_block *super = &SCOUTFS_SB(sb)->super;
 	char slots[(SCOUTFS_QUORUM_MAX_SLOTS * 3) + 1];
-	DECLARE_QUORUM_INFO(sb, qinf);
 	struct sockaddr_in other;
 	struct sockaddr_in sin;
 	int found = 0;
@@ -1074,10 +1220,10 @@ static int verify_quorum_slots(struct super_block *sb)
 
 
 	for (i = 0; i < SCOUTFS_QUORUM_MAX_SLOTS; i++) {
-		if (!quorum_slot_present(super, i))
+		if (!quorum_slot_present(qconf, i))
 			continue;
 
-		scoutfs_quorum_slot_sin(super, i, &sin);
+		scoutfs_quorum_slot_sin(qconf, i, &sin);
 
 		if (!valid_ipv4_unicast(sin.sin_addr.s_addr)) {
 			scoutfs_err(sb, "quorum slot #%d has invalid ipv4 unicast address: "SIN_FMT,
@@ -1092,10 +1238,10 @@ static int verify_quorum_slots(struct super_block *sb)
 		}
 
 		for (j = i + 1; j < SCOUTFS_QUORUM_MAX_SLOTS; j++) {
-			if (!quorum_slot_present(super, j))
+			if (!quorum_slot_present(qconf, j))
 				continue;
 
-			scoutfs_quorum_slot_sin(super, j, &other);
+			scoutfs_quorum_slot_sin(qconf, j, &other);
 
 			if (sin.sin_addr.s_addr == other.sin_addr.s_addr &&
 			    sin.sin_port == other.sin_port) {
@@ -1113,11 +1259,11 @@ static int verify_quorum_slots(struct super_block *sb)
 		return -EINVAL;
 	}
 
-	if (!quorum_slot_present(super, qinf->our_quorum_slot_nr)) {
+	if (!quorum_slot_present(qconf, qinf->our_quorum_slot_nr)) {
 		char *str = slots;
 		*str = '\0';
 		for (i = 0; i < SCOUTFS_QUORUM_MAX_SLOTS; i++) {
-			if (quorum_slot_present(super, i)) {
+			if (quorum_slot_present(qconf, i)) {
 				ret = snprintf(str, &slots[ARRAY_SIZE(slots)] - str, "%c%u",
 					       str == slots ? ' ' : ',', i);
 				if (ret < 2 || ret > 3) {
@@ -1141,16 +1287,22 @@ static int verify_quorum_slots(struct super_block *sb)
 	else
 		qinf->votes_needed = (found / 2) + 1;
 
+	qinf->qconf = *qconf;
+
 	return 0;
 }
 
 /*
  * Once this schedules the quorum worker it can be elected leader and
- * start the server, possibly before this returns.
+ * start the server, possibly before this returns.  The quorum agent
+ * would be responsible for tracking the quorum config in the super
+ * block if it changes.  Until then uses a static config that it reads
+ * during setup.
  */
 int scoutfs_quorum_setup(struct super_block *sb)
 {
 	struct scoutfs_sb_info *sbi = SCOUTFS_SB(sb);
+	struct scoutfs_super_block *super = NULL;
 	struct scoutfs_mount_options opts;
 	struct quorum_info *qinf;
 	int ret;
@@ -1160,7 +1312,14 @@ int scoutfs_quorum_setup(struct super_block *sb)
 		return 0;
 
 	qinf = kzalloc(sizeof(struct quorum_info), GFP_KERNEL);
-	if (!qinf) {
+	super = kmalloc(sizeof(struct scoutfs_super_block), GFP_KERNEL);
+	if (qinf)
+		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);
+		kfree(qinf);
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -1174,7 +1333,20 @@ int scoutfs_quorum_setup(struct super_block *sb)
 	sbi->quorum_info = qinf;
 	qinf->sb = sb;
 
-	ret = verify_quorum_slots(sb);
+	/* a high priority single threaded context without mem reclaim */
+	qinf->workq = alloc_workqueue("scoutfs_quorum_work",
+				       WQ_NON_REENTRANT | WQ_UNBOUND |
+				       WQ_HIGHPRI, 1);
+	if (!qinf->workq) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = scoutfs_read_super(sb, super);
+	if (ret < 0)
+		goto out;
+
+	ret = verify_quorum_slots(sb, qinf, &super->qconf);
 	if (ret < 0)
 		goto out;
 
@@ -1188,12 +1360,13 @@ int scoutfs_quorum_setup(struct super_block *sb)
 	if (ret < 0)
 		goto out;
 
-	schedule_work(&qinf->work);
+	queue_work(qinf->workq, &qinf->work);
 
 out:
 	if (ret)
 		scoutfs_quorum_destroy(sb);
 
+	kfree(super);
 	return ret;
 }
 
@@ -1217,10 +1390,14 @@ void scoutfs_quorum_destroy(struct super_block *sb)
 		qinf->shutdown = true;
 		flush_work(&qinf->work);
 
+		if (qinf->workq)
+			destroy_workqueue(qinf->workq);
+
 		scoutfs_sysfs_destroy_attrs(sb, &qinf->ssa);
 		if (qinf->sock)
 			sock_release(qinf->sock);
 
+		vfree(qinf->hb_delay);
 		kfree(qinf);
 		sbi->quorum_info = NULL;
 	}

kmod/src/quorum.h

@@ -4,10 +4,11 @@
 int scoutfs_quorum_server_sin(struct super_block *sb, struct sockaddr_in *sin);
 
 u8 scoutfs_quorum_votes_needed(struct super_block *sb);
-void scoutfs_quorum_slot_sin(struct scoutfs_super_block *super, int i,
+void scoutfs_quorum_slot_sin(struct scoutfs_quorum_config *qconf, int i,
 			     struct sockaddr_in *sin);
 
-int scoutfs_quorum_fence_leaders(struct super_block *sb, u64 term);
+int scoutfs_quorum_fence_leaders(struct super_block *sb, struct scoutfs_quorum_config *qconf,
+				 u64 term);
 
 int scoutfs_quorum_setup(struct super_block *sb);
 void scoutfs_quorum_shutdown(struct super_block *sb);

kmod/src/scoutfs_trace.h

@@ -691,16 +691,16 @@ TRACE_EVENT(scoutfs_evict_inode,
 
 TRACE_EVENT(scoutfs_drop_inode,
 	TP_PROTO(struct super_block *sb, __u64 ino, unsigned int nlink,
-		 unsigned int unhashed, bool drop_invalidated),
+		 unsigned int unhashed, bool lock_covered),
 
-	TP_ARGS(sb, ino, nlink, unhashed, drop_invalidated),
+	TP_ARGS(sb, ino, nlink, unhashed, lock_covered),
 
 	TP_STRUCT__entry(
 		SCSB_TRACE_FIELDS
 		__field(__u64, ino)
 		__field(unsigned int, nlink)
 		__field(unsigned int, unhashed)
-		__field(unsigned int, drop_invalidated)
+		__field(unsigned int, lock_covered)
 	),
 
 	TP_fast_assign(
@@ -708,12 +708,12 @@ TRACE_EVENT(scoutfs_drop_inode,
 		__entry->ino = ino;
 		__entry->nlink = nlink;
 		__entry->unhashed = unhashed;
-		__entry->drop_invalidated = !!drop_invalidated;
+		__entry->lock_covered = !!lock_covered;
 	),
 
-	TP_printk(SCSBF" ino %llu nlink %u unhashed %d drop_invalidated %u", SCSB_TRACE_ARGS,
+	TP_printk(SCSBF" ino %llu nlink %u unhashed %d lock_covered %u", SCSB_TRACE_ARGS,
 		  __entry->ino, __entry->nlink, __entry->unhashed,
-		  __entry->drop_invalidated)
+		  __entry->lock_covered)
 );
 
 TRACE_EVENT(scoutfs_inode_walk_writeback,
@@ -817,22 +817,17 @@ TRACE_EVENT(scoutfs_advance_dirty_super,
 	TP_printk(SCSBF" super seq now %llu", SCSB_TRACE_ARGS, __entry->seq)
 );
 
-TRACE_EVENT(scoutfs_dir_add_next_linkref,
+TRACE_EVENT(scoutfs_dir_add_next_linkref_found,
 	TP_PROTO(struct super_block *sb, __u64 ino, __u64 dir_ino,
-		 __u64 dir_pos, int ret, __u64 found_dir_ino,
-		 __u64 found_dir_pos, unsigned int name_len),
+		 __u64 dir_pos, unsigned int name_len),
 
-	TP_ARGS(sb, ino, dir_ino, dir_pos, ret, found_dir_pos, found_dir_ino,
-		name_len),
+	TP_ARGS(sb, ino, dir_ino, dir_pos, name_len),
 
 	TP_STRUCT__entry(
 		SCSB_TRACE_FIELDS
 		__field(__u64, ino)
 		__field(__u64, dir_ino)
 		__field(__u64, dir_pos)
-		__field(int, ret)
-		__field(__u64, found_dir_ino)
-		__field(__u64, found_dir_pos)
 		__field(unsigned int, name_len)
 	),
 
@@ -841,16 +836,43 @@ TRACE_EVENT(scoutfs_dir_add_next_linkref,
 		__entry->ino = ino;
 		__entry->dir_ino = dir_ino;
 		__entry->dir_pos = dir_pos;
-		__entry->ret = ret;
-		__entry->found_dir_ino = dir_ino;
-		__entry->found_dir_pos = dir_pos;
 		__entry->name_len = name_len;
 	),
 
-	TP_printk(SCSBF" ino %llu dir_ino %llu dir_pos %llu ret %d found_dir_ino %llu found_dir_pos %llu name_len %u",
-		  SCSB_TRACE_ARGS, __entry->ino, __entry->dir_pos,
-		  __entry->dir_ino, __entry->ret, __entry->found_dir_pos,
-		  __entry->found_dir_ino, __entry->name_len)
+	TP_printk(SCSBF" ino %llu dir_ino %llu dir_pos %llu name_len %u",
+		  SCSB_TRACE_ARGS, __entry->ino, __entry->dir_ino,
+		  __entry->dir_pos, __entry->name_len)
+);
+
+TRACE_EVENT(scoutfs_dir_add_next_linkrefs,
+	TP_PROTO(struct super_block *sb, __u64 ino, __u64 dir_ino,
+		 __u64 dir_pos, int count, int nr, int ret),
+
+	TP_ARGS(sb, ino, dir_ino, dir_pos, count, nr, ret),
+
+	TP_STRUCT__entry(
+		SCSB_TRACE_FIELDS
+		__field(__u64, ino)
+		__field(__u64, dir_ino)
+		__field(__u64, dir_pos)
+		__field(int, count)
+		__field(int, nr)
+		__field(int, ret)
+	),
+
+	TP_fast_assign(
+		SCSB_TRACE_ASSIGN(sb);
+		__entry->ino = ino;
+		__entry->dir_ino = dir_ino;
+		__entry->dir_pos = dir_pos;
+		__entry->count = count;
+		__entry->nr = nr;
+		__entry->ret = ret;
+	),
+
+	TP_printk(SCSBF" ino %llu dir_ino %llu dir_pos %llu count %d nr %d ret %d",
+		  SCSB_TRACE_ARGS, __entry->ino, __entry->dir_ino,
+		  __entry->dir_pos, __entry->count, __entry->nr, __entry->ret)
 );
 
 TRACE_EVENT(scoutfs_write_begin,
@@ -1417,42 +1439,71 @@ TRACE_EVENT(scoutfs_rename,
 );
 
 TRACE_EVENT(scoutfs_d_revalidate,
-	TP_PROTO(struct super_block *sb,
-		 struct dentry *dentry, int flags, struct dentry *parent,
-		 bool is_covered, int ret),
+	TP_PROTO(struct super_block *sb, struct dentry *dentry, int flags, u64 dir_ino, int ret),
 
-	TP_ARGS(sb, dentry, flags, parent, is_covered, ret),
+	TP_ARGS(sb, dentry, flags, dir_ino, ret),
 
 	TP_STRUCT__entry(
 		SCSB_TRACE_FIELDS
+		__field(void *, dentry)
 		__string(name, dentry->d_name.name)
 		__field(__u64, ino)
-		__field(__u64, parent_ino)
+		__field(__u64, dir_ino)
 		__field(int, flags)
 		__field(int, is_root)
-		__field(int, is_covered)
 		__field(int, ret)
 	),
 
 	TP_fast_assign(
 		SCSB_TRACE_ASSIGN(sb);
+		__entry->dentry = dentry;
 		__assign_str(name, dentry->d_name.name)
-		__entry->ino = dentry->d_inode ?
-			       scoutfs_ino(dentry->d_inode) : 0;
-		__entry->parent_ino = parent->d_inode ?
-			       scoutfs_ino(parent->d_inode) : 0;
+		__entry->ino = dentry->d_inode ? scoutfs_ino(dentry->d_inode) : 0;
+		__entry->dir_ino = dir_ino;
 		__entry->flags = flags;
 		__entry->is_root = IS_ROOT(dentry);
-		__entry->is_covered = is_covered;
 		__entry->ret = ret;
 	),
 
-	TP_printk(SCSBF" name %s ino %llu parent_ino %llu flags 0x%x s_root %u is_covered %u ret %d",
-		  SCSB_TRACE_ARGS, __get_str(name), __entry->ino,
-		  __entry->parent_ino, __entry->flags,
-		  __entry->is_root,
-		  __entry->is_covered,
-		  __entry->ret)
+	TP_printk(SCSBF" dentry %p name %s ino %llu dir_ino %llu flags 0x%x s_root %u ret %d",
+		  SCSB_TRACE_ARGS, __entry->dentry, __get_str(name), __entry->ino, __entry->dir_ino,
+		  __entry->flags, __entry->is_root, __entry->ret)
+);
+
+TRACE_EVENT(scoutfs_validate_dentry,
+	TP_PROTO(struct super_block *sb, struct dentry *dentry, u64 dir_ino, u64 dentry_ino,
+		 u64 dent_ino, u64 refresh_gen, int ret),
+
+	TP_ARGS(sb, dentry, dir_ino, dentry_ino, dent_ino, refresh_gen, ret),
+
+	TP_STRUCT__entry(
+		SCSB_TRACE_FIELDS
+		__field(void *, dentry)
+		__field(__u64, dir_ino)
+		__string(name, dentry->d_name.name)
+		__field(__u64, dentry_ino)
+		__field(__u64, dent_ino)
+		__field(__u64, fsdata_gen)
+		__field(__u64, refresh_gen)
+		__field(int, ret)
+	),
+
+	TP_fast_assign(
+		SCSB_TRACE_ASSIGN(sb);
+		__entry->dentry = dentry;
+		__entry->dir_ino = dir_ino;
+		__assign_str(name, dentry->d_name.name)
+		__entry->dentry_ino = dentry_ino;
+		__entry->dent_ino = dent_ino;
+		__entry->fsdata_gen = (unsigned long long)dentry->d_fsdata;
+		__entry->refresh_gen = refresh_gen;
+		__entry->ret = ret;
+	),
+
+	TP_printk(SCSBF" dentry %p dir %llu name %s dentry_ino %llu dent_ino %llu fsdata_gen %llu refresh_gen %llu ret %d",
+		  SCSB_TRACE_ARGS, __entry->dentry, __entry->dir_ino, __get_str(name),
+		  __entry->dentry_ino, __entry->dent_ino, __entry->fsdata_gen,
+		  __entry->refresh_gen, __entry->ret)
 );
 
 DECLARE_EVENT_CLASS(scoutfs_super_lifecycle_class,
@@ -1845,8 +1896,9 @@ 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 avail_before, u32 freed_before, int exceeded),
-        TP_ARGS(sb, holding, applying, nr_holders, avail_before, freed_before, exceeded),
+		 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)
@@ -1854,6 +1906,7 @@ DECLARE_EVENT_CLASS(scoutfs_server_commit_users_class,
 		__field(int, nr_holders)
 		__field(__u32, avail_before)
 		__field(__u32, freed_before)
+		__field(int, committing)
 		__field(int, exceeded)
         ),
         TP_fast_assign(
@@ -1863,31 +1916,33 @@ DECLARE_EVENT_CLASS(scoutfs_server_commit_users_class,
 		__entry->nr_holders = nr_holders;
 		__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 avail_before %u freed_before %u exceeded %u",
+	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->exceeded)
+		  __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 avail_before, u32 freed_before, int exceeded),
-        TP_ARGS(sb, holding, applying, nr_holders, avail_before, freed_before, exceeded)
+		 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 avail_before, u32 freed_before, int exceeded),
-        TP_ARGS(sb, holding, applying, nr_holders, avail_before, freed_before, exceeded)
+		 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 avail_before, u32 freed_before, int exceeded),
-        TP_ARGS(sb, holding, applying, nr_holders, avail_before, freed_before, exceeded)
+		 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 avail_before, u32 freed_before, int exceeded),
-        TP_ARGS(sb, holding, applying, nr_holders, avail_before, freed_before, exceeded)
+		 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)						\

kmod/src/server.h

@@ -75,7 +75,7 @@ u64 scoutfs_server_seq(struct super_block *sb);
 u64 scoutfs_server_next_seq(struct super_block *sb);
 void scoutfs_server_set_seq_if_greater(struct super_block *sb, u64 seq);
 
-void scoutfs_server_start(struct super_block *sb, u64 term);
+void scoutfs_server_start(struct super_block *sb, struct scoutfs_quorum_config *qconf, u64 term);
 void scoutfs_server_stop(struct super_block *sb);
 void scoutfs_server_stop_wait(struct super_block *sb);
 bool scoutfs_server_is_running(struct super_block *sb);

kmod/src/srch.c

@@ -861,7 +861,6 @@ int scoutfs_srch_search_xattrs(struct super_block *sb,
 			       struct scoutfs_srch_rb_root *sroot,
 			       u64 hash, u64 ino, u64 last_ino, bool *done)
 {
-	struct scoutfs_net_roots prev_roots;
 	struct scoutfs_net_roots roots;
 	struct scoutfs_srch_entry start;
 	struct scoutfs_srch_entry end;
@@ -869,6 +868,7 @@ int scoutfs_srch_search_xattrs(struct super_block *sb,
 	struct scoutfs_log_trees lt;
 	struct scoutfs_srch_file sfl;
 	SCOUTFS_BTREE_ITEM_REF(iref);
+	DECLARE_SAVED_REFS(saved);
 	struct scoutfs_key key;
 	unsigned long limit = SRCH_LIMIT;
 	int ret;
@@ -877,7 +877,6 @@ int scoutfs_srch_search_xattrs(struct super_block *sb,
 
 	*done = false;
 	srch_init_rb_root(sroot);
-	memset(&prev_roots, 0, sizeof(prev_roots));
 
 	start.hash = cpu_to_le64(hash);
 	start.ino = cpu_to_le64(ino);
@@ -892,7 +891,6 @@ retry:
 	ret = scoutfs_client_get_roots(sb, &roots);
 	if (ret)
 		goto out;
-	memset(&roots.fs_root, 0, sizeof(roots.fs_root));
 
 	end = final;
 
@@ -968,16 +966,10 @@ retry:
 	*done = sre_cmp(&end, &final) == 0;
 	ret = 0;
 out:
-	if (ret == -ESTALE) {
-		if (memcmp(&prev_roots, &roots, sizeof(roots)) == 0) {
-			scoutfs_inc_counter(sb, srch_search_stale_eio);
-			ret = -EIO;
-		} else {
-			scoutfs_inc_counter(sb, srch_search_stale_retry);
-			prev_roots = roots;
-			goto retry;
-		}
-	}
+	ret = scoutfs_block_check_stale(sb, ret, &saved, &roots.srch_root.ref,
+					&roots.logs_root.ref);
+	if (ret == -ESTALE)
+		goto retry;
 
 	return ret;
 }
@@ -1003,6 +995,14 @@ int scoutfs_srch_rotate_log(struct super_block *sb,
 		      le64_to_cpu(sfl->ref.blkno), 0);
 	ret = scoutfs_btree_insert(sb, alloc, wri, root, &key,
 				   sfl, sizeof(*sfl));
+	/*
+	 * While it's fine to replay moving the client's logging srch
+	 * file to the core btree item, server commits should keep it
+	 * from happening.  So we'll warn if we see it happen.  This can
+	 * be removed eventually.
+	 */
+	if (WARN_ON_ONCE(ret == -EEXIST))
+		ret = 0;
 	if (ret == 0) {
 		memset(sfl, 0, sizeof(*sfl));
 		scoutfs_inc_counter(sb, srch_rotate_log);

kmod/src/super.c

@@ -47,6 +47,7 @@
 #include "omap.h"
 #include "volopt.h"
 #include "fence.h"
+#include "xattr.h"
 #include "scoutfs_trace.h"
 
 static struct dentry *scoutfs_debugfs_root;
@@ -460,9 +461,8 @@ static int scoutfs_read_supers(struct super_block *sb)
 		goto out;
 	}
 
-
+	sbi->fsid = le64_to_cpu(meta_super->hdr.fsid);
 	sbi->fmt_vers = le64_to_cpu(meta_super->fmt_vers);
-	sbi->super = *meta_super;
 out:
 	kfree(meta_super);
 	kfree(data_super);
@@ -482,8 +482,11 @@ static int scoutfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_magic = SCOUTFS_SUPER_MAGIC;
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	sb->s_op = &scoutfs_super_ops;
+	sb->s_d_op = &scoutfs_dentry_ops;
 	sb->s_export_op = &scoutfs_export_ops;
-	sb->s_flags |= MS_I_VERSION;
+	sb->s_xattr = scoutfs_xattr_handlers;
+	sb->s_flags |= MS_I_VERSION | MS_POSIXACL;
+	sb->s_time_gran = 1;
 
 	/* btree blocks use long lived bh->b_data refs */
 	mapping_set_gfp_mask(sb->s_bdev->bd_inode->i_mapping, GFP_NOFS);
@@ -496,7 +499,7 @@ static int scoutfs_fill_super(struct super_block *sb, void *data, int silent)
 
 	ret = assign_random_id(sbi);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	spin_lock_init(&sbi->next_ino_lock);
 	spin_lock_init(&sbi->data_wait_root.lock);
@@ -505,7 +508,7 @@ static int scoutfs_fill_super(struct super_block *sb, void *data, int silent)
 	/* parse options early for use during setup */
 	ret = scoutfs_options_early_setup(sb, data);
 	if (ret < 0)
-		return ret;
+		goto out;
 	scoutfs_options_read(sb, &opts);
 
 	ret = sb_set_blocksize(sb, SCOUTFS_BLOCK_SM_SIZE);
@@ -628,7 +631,6 @@ MODULE_ALIAS_FS("scoutfs");
 static void teardown_module(void)
 {
 	debugfs_remove(scoutfs_debugfs_root);
-	scoutfs_dir_exit();
 	scoutfs_inode_exit();
 	scoutfs_sysfs_exit();
 }
@@ -666,7 +668,6 @@ static int __init scoutfs_module_init(void)
 		goto out;
 	}
 	ret = scoutfs_inode_init() ?:
-	      scoutfs_dir_init() ?:
 	      register_filesystem(&scoutfs_fs_type);
 out:
 	if (ret)

kmod/src/super.h

@@ -35,11 +35,10 @@ struct scoutfs_sb_info {
 	struct super_block *sb;
 
 	/* assigned once at the start of each mount, read-only */
+	u64 fsid;
 	u64 rid;
 	u64 fmt_vers;
 
-	struct scoutfs_super_block super;
-
 	struct block_device *meta_bdev;
 
 	spinlock_t next_ino_lock;
@@ -135,14 +134,14 @@ static inline bool scoutfs_unmounting(struct super_block *sb)
 	(int)(le64_to_cpu(fsid) >> SCSB_SHIFT),				    \
 	(int)(le64_to_cpu(rid) >> SCSB_SHIFT)
 #define SCSB_ARGS(sb)							    \
-	(int)(le64_to_cpu(SCOUTFS_SB(sb)->super.hdr.fsid) >> SCSB_SHIFT),   \
+	(int)(SCOUTFS_SB(sb)->fsid >> SCSB_SHIFT),			    \
 	(int)(SCOUTFS_SB(sb)->rid >> SCSB_SHIFT)
 #define SCSB_TRACE_FIELDS	\
 	__field(__u64, fsid)	\
 	__field(__u64, rid)
 #define SCSB_TRACE_ASSIGN(sb)						\
 	__entry->fsid = SCOUTFS_HAS_SBI(sb) ?				\
-			le64_to_cpu(SCOUTFS_SB(sb)->super.hdr.fsid) : 0;\
+		        SCOUTFS_SB(sb)->fsid : 0;			\
 	__entry->rid = SCOUTFS_HAS_SBI(sb) ?				\
 		       SCOUTFS_SB(sb)->rid : 0;
 #define SCSB_TRACE_ARGS				\

kmod/src/sysfs.c

@@ -60,10 +60,9 @@ static ssize_t fsid_show(struct kobject *kobj, struct attribute *attr,
 			 char *buf)
 {
 	struct super_block *sb = KOBJ_TO_SB(kobj, sb_id_kobj);
-	struct scoutfs_super_block *super = &SCOUTFS_SB(sb)->super;
+	struct scoutfs_sb_info *sbi = SCOUTFS_SB(sb);
 
-	return snprintf(buf, PAGE_SIZE, "%016llx\n",
-			le64_to_cpu(super->hdr.fsid));
+	return snprintf(buf, PAGE_SIZE, "%016llx\n", sbi->fsid);
 }
 ATTR_FUNCS_RO(fsid);
 
@@ -268,7 +267,7 @@ int __init scoutfs_sysfs_init(void)
 	return 0;
 }
 
-void __exit scoutfs_sysfs_exit(void)
+void scoutfs_sysfs_exit(void)
 {
 	if (scoutfs_kset)
 		kset_unregister(scoutfs_kset);

kmod/src/sysfs.h

@@ -53,6 +53,6 @@ int scoutfs_setup_sysfs(struct super_block *sb);
 void scoutfs_destroy_sysfs(struct super_block *sb);
 
 int __init scoutfs_sysfs_init(void);
-void __exit scoutfs_sysfs_exit(void);
+void scoutfs_sysfs_exit(void);
 
 #endif

kmod/src/xattr.c

@@ -15,6 +15,7 @@
 #include <linux/dcache.h>
 #include <linux/xattr.h>
 #include <linux/crc32c.h>
+#include <linux/posix_acl.h>
 
 #include "format.h"
 #include "inode.h"
@@ -26,6 +27,7 @@
 #include "xattr.h"
 #include "lock.h"
 #include "hash.h"
+#include "acl.h"
 #include "scoutfs_trace.h"
 
 /*
@@ -79,16 +81,6 @@ static void init_xattr_key(struct scoutfs_key *key, u64 ino, u32 name_hash,
 #define SCOUTFS_XATTR_PREFIX		"scoutfs."
 #define SCOUTFS_XATTR_PREFIX_LEN	(sizeof(SCOUTFS_XATTR_PREFIX) - 1)
 
-static int unknown_prefix(const char *name)
-{
-	return strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) &&
-	       strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) &&
-	       strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN) &&
-	       strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)&&
-	       strncmp(name, SCOUTFS_XATTR_PREFIX, SCOUTFS_XATTR_PREFIX_LEN);
-}
-
-
 #define HIDE_TAG	"hide."
 #define SRCH_TAG	"srch."
 #define TOTL_TAG	"totl."
@@ -455,22 +447,17 @@ out:
  * Copy the value for the given xattr name into the caller's buffer, if it
  * fits.  Return the bytes copied or -ERANGE if it doesn't fit.
  */
-ssize_t scoutfs_getxattr(struct dentry *dentry, const char *name, void *buffer,
-			 size_t size)
+int scoutfs_xattr_get_locked(struct inode *inode, const char *name, void *buffer, size_t size,
+			     struct scoutfs_lock *lck)
 {
-	struct inode *inode = dentry->d_inode;
 	struct scoutfs_inode_info *si = SCOUTFS_I(inode);
 	struct super_block *sb = inode->i_sb;
 	struct scoutfs_xattr *xat = NULL;
-	struct scoutfs_lock *lck = NULL;
 	struct scoutfs_key key;
 	unsigned int xat_bytes;
 	size_t name_len;
 	int ret;
 
-	if (unknown_prefix(name))
-		return -EOPNOTSUPP;
-
 	name_len = strlen(name);
 	if (name_len > SCOUTFS_XATTR_MAX_NAME_LEN)
 		return -ENODATA;
@@ -480,10 +467,6 @@ ssize_t scoutfs_getxattr(struct dentry *dentry, const char *name, void *buffer,
 	if (!xat)
 		return -ENOMEM;
 
-	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ, 0, inode, &lck);
-	if (ret)
-		goto out;
-
 	down_read(&si->xattr_rwsem);
 
 	ret = get_next_xattr(inode, &key, xat, xat_bytes, name, name_len, 0, 0, lck);
@@ -509,12 +492,27 @@ ssize_t scoutfs_getxattr(struct dentry *dentry, const char *name, void *buffer,
 	ret = copy_xattr_value(sb, &key, xat, xat_bytes, buffer, size, lck);
 unlock:
 	up_read(&si->xattr_rwsem);
-	scoutfs_unlock(sb, lck, SCOUTFS_LOCK_READ);
-out:
+
 	kfree(xat);
 	return ret;
 }
 
+static int scoutfs_xattr_get(struct dentry *dentry, const char *name, void *buffer, size_t size)
+{
+	struct inode *inode = dentry->d_inode;
+	struct super_block *sb = inode->i_sb;
+	struct scoutfs_lock *lock = NULL;
+	int ret;
+
+	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ, 0, inode, &lock);
+	if (ret == 0) {
+		ret = scoutfs_xattr_get_locked(inode, name, buffer, size, lock);
+		scoutfs_unlock(sb, lock, SCOUTFS_LOCK_READ);
+	}
+
+	return ret;
+}
+
 void scoutfs_xattr_init_totl_key(struct scoutfs_key *key, u64 *name)
 {
 	scoutfs_key_set_zeros(key);
@@ -619,30 +617,32 @@ int scoutfs_xattr_combine_totl(void *dst, int dst_len, void *src, int src_len)
  * cause creation to fail if the xattr already exists (_CREATE) or
  * doesn't already exist (_REPLACE).  xattrs can have a zero length
  * value.
+ *
+ * The caller has acquired cluster locks, holds a transaction, and has
+ * dirtied the inode item so that they can update it after we modify it.
+ * The caller has to know the tags to acquire cluster locks before
+ * holding the transaction so they pass in the parsed tags, or all 0s for
+ * non scoutfs. prefixes.
  */
-static int scoutfs_xattr_set(struct dentry *dentry, const char *name,
-			     const void *value, size_t size, int flags)
+int scoutfs_xattr_set_locked(struct inode *inode, const char *name, size_t name_len,
+			     const void *value, size_t size, int flags,
+			     const struct scoutfs_xattr_prefix_tags *tgs,
+			     struct scoutfs_lock *lck, struct scoutfs_lock *totl_lock,
+			     struct list_head *ind_locks)
 {
-	struct inode *inode = dentry->d_inode;
 	struct scoutfs_inode_info *si = SCOUTFS_I(inode);
 	struct super_block *sb = inode->i_sb;
 	const u64 ino = scoutfs_ino(inode);
 	struct scoutfs_xattr_totl_val tval = {0,};
-	struct scoutfs_xattr_prefix_tags tgs;
 	struct scoutfs_xattr *xat = NULL;
-	struct scoutfs_lock *lck = NULL;
-	struct scoutfs_lock *totl_lock = NULL;
-	size_t name_len = strlen(name);
 	struct scoutfs_key totl_key;
 	struct scoutfs_key key;
 	bool undo_srch = false;
 	bool undo_totl = false;
-	LIST_HEAD(ind_locks);
 	u8 found_parts;
 	unsigned int xat_bytes_totl;
 	unsigned int xat_bytes;
 	unsigned int val_len;
-	u64 ind_seq;
 	u64 total;
 	u64 hash = 0;
 	u64 id = 0;
@@ -651,6 +651,9 @@ static int scoutfs_xattr_set(struct dentry *dentry, const char *name,
 
 	trace_scoutfs_xattr_set(sb, name_len, value, size, flags);
 
+	if (WARN_ON_ONCE(tgs->totl && !totl_lock))
+		return -EINVAL;
+
 	/* mirror the syscall's errors for large names and values */
 	if (name_len > SCOUTFS_XATTR_MAX_NAME_LEN)
 		return -ERANGE;
@@ -661,16 +664,10 @@ static int scoutfs_xattr_set(struct dentry *dentry, const char *name,
 	    (flags & ~(XATTR_CREATE | XATTR_REPLACE)))
 		return -EINVAL;
 
-	if (unknown_prefix(name))
-		return -EOPNOTSUPP;
-
-	if (scoutfs_xattr_parse_tags(name, name_len, &tgs) != 0)
-		return -EINVAL;
-
-	if ((tgs.hide | tgs.srch | tgs.totl) && !capable(CAP_SYS_ADMIN))
+	if ((tgs->hide | tgs->srch | tgs->totl) && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (tgs.totl && ((ret = parse_totl_key(&totl_key, name, name_len)) != 0))
+	if (tgs->totl && ((ret = parse_totl_key(&totl_key, name, name_len)) != 0))
 		return ret;
 
 	/* allocate enough to always read an existing xattr's totl */
@@ -679,51 +676,44 @@ static int scoutfs_xattr_set(struct dentry *dentry, const char *name,
 	/* but store partial first item that only includes the new xattr's value */
 	xat_bytes = first_item_bytes(name_len, size);
 	xat = kmalloc(xat_bytes_totl, GFP_NOFS);
-	if (!xat) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_WRITE,
-				 SCOUTFS_LKF_REFRESH_INODE, inode, &lck);
-	if (ret)
-		goto out;
+	if (!xat)
+		return -ENOMEM;
 
 	down_write(&si->xattr_rwsem);
 
 	/* find an existing xattr to delete, including possible totl value */
 	ret = get_next_xattr(inode, &key, xat, xat_bytes_totl, name, name_len, 0, 0, lck);
 	if (ret < 0 && ret != -ENOENT)
-		goto unlock;
+		goto out;
 
 	/* check existence constraint flags */
 	if (ret == -ENOENT && (flags & XATTR_REPLACE)) {
 		ret = -ENODATA;
-		goto unlock;
+		goto out;
 	} else if (ret >= 0 && (flags & XATTR_CREATE)) {
 		ret = -EEXIST;
-		goto unlock;
+		goto out;
 	}
 
 	/* not an error to delete something that doesn't exist */
 	if (ret == -ENOENT && !value) {
 		ret = 0;
-		goto unlock;
+		goto out;
 	}
 
 	/* s64 count delta if we create or delete */
-	if (tgs.totl)
+	if (tgs->totl)
 		tval.count = cpu_to_le64((u64)!!(value) - (u64)!!(ret != -ENOENT));
 
 	/* found fields in key will also be used */
 	found_parts = ret >= 0 ? xattr_nr_parts(xat) : 0;
 
-	if (found_parts && tgs.totl) {
+	if (found_parts && tgs->totl) {
 		/* parse old totl value before we clobber xat buf */
 		val_len = ret - offsetof(struct scoutfs_xattr, name[xat->name_len]);
 		ret = parse_totl_u64(&xat->name[xat->name_len], val_len, &total);
 		if (ret < 0)
-			goto unlock;
+			goto out;
 
 		le64_add_cpu(&tval.total, -total);
 	}
@@ -742,15 +732,90 @@ static int scoutfs_xattr_set(struct dentry *dentry, const char *name,
 		       min(size, SCOUTFS_XATTR_MAX_PART_SIZE -
 			         offsetof(struct scoutfs_xattr, name[name_len])));
 
-		if (tgs.totl) {
+		if (tgs->totl) {
 			ret = parse_totl_u64(value, size, &total);
 			if (ret < 0)
-				goto unlock;
+				goto out;
 		}
 
 		le64_add_cpu(&tval.total, total);
 	}
 
+	if (tgs->srch && !(found_parts && value)) {
+		if (found_parts)
+			id = le64_to_cpu(key.skx_id);
+		hash = scoutfs_hash64(name, name_len);
+		ret = scoutfs_forest_srch_add(sb, hash, ino, id);
+		if (ret < 0)
+			goto out;
+		undo_srch = true;
+	}
+
+	if (tgs->totl) {
+		ret = apply_totl_delta(sb, &totl_key, &tval, totl_lock);
+		if (ret < 0)
+			goto out;
+		undo_totl = true;
+	}
+
+	if (found_parts && value)
+		ret = change_xattr_items(inode, id, xat, xat_bytes, value, size,
+					 xattr_nr_parts(xat), found_parts, lck);
+	else if (found_parts)
+		ret = delete_xattr_items(inode, le64_to_cpu(key.skx_name_hash),
+					 le64_to_cpu(key.skx_id), found_parts,
+					 lck);
+	else
+		ret = create_xattr_items(inode, id, xat, xat_bytes, value, size,
+					 xattr_nr_parts(xat), lck);
+	if (ret < 0)
+		goto out;
+
+	/* XXX do these want i_mutex or anything? */
+	inode_inc_iversion(inode);
+	inode->i_ctime = CURRENT_TIME;
+	ret = 0;
+
+out:
+	if (ret < 0 && undo_srch) {
+		err = scoutfs_forest_srch_add(sb, hash, ino, id);
+		BUG_ON(err);
+	}
+	if (ret < 0 && undo_totl) {
+		/* _delta() on dirty items shouldn't fail */
+		tval.total = cpu_to_le64(-le64_to_cpu(tval.total));
+		tval.count = cpu_to_le64(-le64_to_cpu(tval.count));
+		err = apply_totl_delta(sb, &totl_key, &tval, totl_lock);
+		BUG_ON(err);
+	}
+
+	up_write(&si->xattr_rwsem);
+	kfree(xat);
+
+	return ret;
+}
+
+static int scoutfs_xattr_set(struct dentry *dentry, const char *name, const void *value,
+			     size_t size, int flags)
+{
+	struct inode *inode = dentry->d_inode;
+	struct super_block *sb = inode->i_sb;
+	struct scoutfs_xattr_prefix_tags tgs;
+	struct scoutfs_lock *totl_lock = NULL;
+	struct scoutfs_lock *lck = NULL;
+	size_t name_len = strlen(name);
+	LIST_HEAD(ind_locks);
+	u64 ind_seq;
+	int ret;
+
+	if (scoutfs_xattr_parse_tags(name, name_len, &tgs) != 0)
+		return -EINVAL;
+
+	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_WRITE,
+				 SCOUTFS_LKF_REFRESH_INODE, inode, &lck);
+	if (ret)
+		goto unlock;
+
 	if (tgs.totl) {
 		ret = scoutfs_lock_xattr_totl(sb, SCOUTFS_LOCK_WRITE_ONLY, 0, &totl_lock);
 		if (ret)
@@ -770,80 +835,98 @@ retry:
 	if (ret < 0)
 		goto release;
 
-	if (tgs.srch && !(found_parts && value)) {
-		if (found_parts)
-			id = le64_to_cpu(key.skx_id);
-		hash = scoutfs_hash64(name, name_len);
-		ret = scoutfs_forest_srch_add(sb, hash, ino, id);
-		if (ret < 0)
-			goto release;
-		undo_srch = true;
-	}
-
-	if (tgs.totl) {
-		ret = apply_totl_delta(sb, &totl_key, &tval, totl_lock);
-		if (ret < 0)
-			goto release;
-		undo_totl = true;
-	}
-
-	if (found_parts && value)
-		ret = change_xattr_items(inode, id, xat, xat_bytes, value, size,
-					 xattr_nr_parts(xat), found_parts, lck);
-	else if (found_parts)
-		ret = delete_xattr_items(inode, le64_to_cpu(key.skx_name_hash),
-					 le64_to_cpu(key.skx_id), found_parts,
-					 lck);
-	else
-		ret = create_xattr_items(inode, id, xat, xat_bytes, value, size,
-					 xattr_nr_parts(xat), lck);
-	if (ret < 0)
-		goto release;
-
-	/* XXX do these want i_mutex or anything? */
-	inode_inc_iversion(inode);
-	inode->i_ctime = CURRENT_TIME;
-	scoutfs_update_inode_item(inode, lck, &ind_locks);
-	ret = 0;
+	ret = scoutfs_xattr_set_locked(dentry->d_inode, name, name_len, value, size, flags, &tgs,
+				       lck, totl_lock, &ind_locks);
+	if (ret == 0)
+		scoutfs_update_inode_item(inode, lck, &ind_locks);
 
 release:
-	if (ret < 0 && undo_srch) {
-		err = scoutfs_forest_srch_add(sb, hash, ino, id);
-		BUG_ON(err);
-	}
-	if (ret < 0 && undo_totl) {
-		/* _delta() on dirty items shouldn't fail */
-		tval.total = cpu_to_le64(-le64_to_cpu(tval.total));
-		tval.count = cpu_to_le64(-le64_to_cpu(tval.count));
-		err = apply_totl_delta(sb, &totl_key, &tval, totl_lock);
-		BUG_ON(err);
-	}
-
 	scoutfs_release_trans(sb);
 	scoutfs_inode_index_unlock(sb, &ind_locks);
 unlock:
-	up_write(&si->xattr_rwsem);
 	scoutfs_unlock(sb, lck, SCOUTFS_LOCK_WRITE);
 	scoutfs_unlock(sb, totl_lock, SCOUTFS_LOCK_WRITE_ONLY);
-out:
-	kfree(xat);
 
 	return ret;
 }
 
-int scoutfs_setxattr(struct dentry *dentry, const char *name,
-		     const void *value, size_t size, int flags)
+/*
+ * Future kernels have this amazing hack to rewind the name to get the
+ * skipped prefix.  We're back in the stone ages without the handler
+ * arg, so we Just Know that this is possible.  This will become a
+ * compat hook to either call the kernel's xattr_full_name(handler), or
+ * our hack to use the flags as the prefix length.
+ */
+static const char *full_name_hack(void *handler, const char *name, int len)
 {
-	if (size == 0)
-		value = ""; /* set empty value */
+	return name - len;
+}
 
+static int scoutfs_xattr_get_handler(struct dentry *dentry, const char *name,
+				     void *value, size_t size, int handler_flags)
+{
+	name = full_name_hack(NULL, name, handler_flags);
+	return scoutfs_xattr_get(dentry, name, value, size);
+}
+
+static int scoutfs_xattr_set_handler(struct dentry *dentry, const char *name,
+				     const void *value, size_t size, int flags, int handler_flags)
+{
+	name = full_name_hack(NULL, name, handler_flags);
 	return scoutfs_xattr_set(dentry, name, value, size, flags);
 }
 
-int scoutfs_removexattr(struct dentry *dentry, const char *name)
-{
-	return scoutfs_xattr_set(dentry, name, NULL, 0, XATTR_REPLACE);
-}
+static const struct xattr_handler scoutfs_xattr_user_handler = {
+	.prefix = XATTR_USER_PREFIX,
+	.flags = XATTR_USER_PREFIX_LEN,
+	.get = scoutfs_xattr_get_handler,
+	.set = scoutfs_xattr_set_handler,
+};
+
+static const struct xattr_handler scoutfs_xattr_scoutfs_handler = {
+	.prefix = SCOUTFS_XATTR_PREFIX,
+	.flags = SCOUTFS_XATTR_PREFIX_LEN,
+	.get = scoutfs_xattr_get_handler,
+	.set = scoutfs_xattr_set_handler,
+};
+
+static const struct xattr_handler scoutfs_xattr_trusted_handler = {
+	.prefix = XATTR_TRUSTED_PREFIX,
+	.flags = XATTR_TRUSTED_PREFIX_LEN,
+	.get = scoutfs_xattr_get_handler,
+	.set = scoutfs_xattr_set_handler,
+};
+
+static const struct xattr_handler scoutfs_xattr_security_handler = {
+	.prefix = XATTR_SECURITY_PREFIX,
+	.flags = XATTR_SECURITY_PREFIX_LEN,
+	.get = scoutfs_xattr_get_handler,
+	.set = scoutfs_xattr_set_handler,
+};
+
+static const struct xattr_handler scoutfs_xattr_acl_access_handler = {
+	.prefix = XATTR_NAME_POSIX_ACL_ACCESS,
+	.flags  = ACL_TYPE_ACCESS,
+	.get    = scoutfs_acl_get_xattr,
+	.set    = scoutfs_acl_set_xattr,
+};
+
+static const struct xattr_handler scoutfs_xattr_acl_default_handler = {
+	.prefix = XATTR_NAME_POSIX_ACL_DEFAULT,
+	.flags  = ACL_TYPE_DEFAULT,
+	.get    = scoutfs_acl_get_xattr,
+	.set    = scoutfs_acl_set_xattr,
+};
+
+const struct xattr_handler *scoutfs_xattr_handlers[] = {
+	&scoutfs_xattr_user_handler,
+	&scoutfs_xattr_scoutfs_handler,
+	&scoutfs_xattr_trusted_handler,
+	&scoutfs_xattr_security_handler,
+	&scoutfs_xattr_acl_access_handler,
+	&scoutfs_xattr_acl_default_handler,
+	NULL
+};
 
 ssize_t scoutfs_list_xattrs(struct inode *inode, char *buffer,
 			    size_t size, __u32 *hash_pos, __u64 *id_pos,

kmod/src/xattr.h

@@ -1,25 +1,29 @@
 #ifndef _SCOUTFS_XATTR_H_
 #define _SCOUTFS_XATTR_H_
 
-ssize_t scoutfs_getxattr(struct dentry *dentry, const char *name, void *buffer,
-			 size_t size);
-int scoutfs_setxattr(struct dentry *dentry, const char *name,
-		     const void *value, size_t size, int flags);
-int scoutfs_removexattr(struct dentry *dentry, const char *name);
-ssize_t scoutfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
-ssize_t scoutfs_list_xattrs(struct inode *inode, char *buffer,
-			    size_t size, __u32 *hash_pos, __u64 *id_pos,
-			    bool e_range, bool show_hidden);
-
-int scoutfs_xattr_drop(struct super_block *sb, u64 ino,
-		       struct scoutfs_lock *lock);
-
 struct scoutfs_xattr_prefix_tags {
 	unsigned long hide:1,
 		      srch:1,
 		      totl:1;
 };
 
+extern const struct xattr_handler *scoutfs_xattr_handlers[];
+
+int scoutfs_xattr_get_locked(struct inode *inode, const char *name, void *buffer, size_t size,
+			     struct scoutfs_lock *lck);
+int scoutfs_xattr_set_locked(struct inode *inode, const char *name, size_t name_len,
+			     const void *value, size_t size, int flags,
+			     const struct scoutfs_xattr_prefix_tags *tgs,
+			     struct scoutfs_lock *lck, struct scoutfs_lock *totl_lock,
+			     struct list_head *ind_locks);
+
+ssize_t scoutfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
+ssize_t scoutfs_list_xattrs(struct inode *inode, char *buffer,
+			    size_t size, __u32 *hash_pos, __u64 *id_pos,
+			    bool e_range, bool show_hidden);
+int scoutfs_xattr_drop(struct super_block *sb, u64 ino,
+		       struct scoutfs_lock *lock);
+
 int scoutfs_xattr_parse_tags(const char *name, unsigned int name_len,
 			     struct scoutfs_xattr_prefix_tags *tgs);
 

tests/.gitignore

@@ -8,3 +8,4 @@ src/bulk_create_paths
 src/find_xattrs
 src/stage_tmpfile
 src/create_xattr_loop
+src/o_tmpfile_umask

tests/Makefile

@@ -10,7 +10,9 @@ BIN := src/createmany			\
 	src/bulk_create_paths		\
 	src/stage_tmpfile		\
 	src/find_xattrs			\
-	src/create_xattr_loop
+	src/create_xattr_loop		\
+	src/fragmented_data_extents	\
+	src/o_tmpfile_umask
 
 DEPS := $(wildcard src/*.d)
 

tests/funcs/exec.sh

@@ -39,6 +39,18 @@ t_quiet()
 		t_fail "quiet command failed"
 }
 
+#
+# Quietly run a command during a test.  The output is logged but only
+# the return code is printed, presumably because the output contains
+# a lot of invocation specific text that is difficult to filter.
+#
+t_rc()
+{
+	echo "# $*" >> "$T_TMP.rc.log"
+	"$@" >> "$T_TMP.rc.log" 2>&1
+	echo "rc: $?"
+}
+
 #
 # redirect test output back to the output of the invoking script intead
 # of the compared output.

tests/funcs/filter.sh

@@ -18,6 +18,7 @@ t_filter_dmesg()
 
 	# the kernel can just be noisy
 	re=" used greatest stack depth: "
+	re="$re|sched: RT throttling activated"
 
 	# mkfs/mount checks partition tables
 	re="$re|unknown partition table"
@@ -61,6 +62,7 @@ t_filter_dmesg()
 	re="$re|scoutfs .* error: meta_super META flag not set"
 	re="$re|scoutfs .* error: could not open metadev:.*"
 	re="$re|scoutfs .* error: Unknown or malformed option,.*"
+	re="$re|scoutfs .* error: invalid quorum_heartbeat_timeout_ms value"
 
 	# in debugging kernels we can slow things down a bit
 	re="$re|hrtimer: interrupt took .*"
@@ -81,6 +83,7 @@ t_filter_dmesg()
 	re="$re|scoutfs .* error .* freeing merged btree blocks.*.final commit del.upd freeing item"
 	re="$re|scoutfs .* error .*reading quorum block.*to update event.*"
 	re="$re|scoutfs .* error.*server failed to bind to.*"
+	re="$re|scoutfs .* critical transaction commit failure.*"
 
 	egrep -v "($re)" 
 }

tests/funcs/fs.sh

@@ -75,6 +75,15 @@ t_fs_nrs()
 	seq 0 $((T_NR_MOUNTS - 1))
 }
 
+#
+# output the fs nrs of quorum nodes, we "know" that
+# the quorum nrs are the first consequtive nrs
+#
+t_quorum_nrs()
+{
+	seq 0 $((T_QUORUM - 1))
+}
+
 #
 # outputs "1" if the fs number has "1" in its quorum/is_leader file.
 # All other cases output 0, including the fs nr being a client which
@@ -144,7 +153,27 @@ t_mount()
 	test "$nr" -lt "$T_NR_MOUNTS" || \
 		t_fail "fs nr $nr invalid"
 
-	eval t_quiet mount -t scoutfs \$T_O$nr \$T_DB$nr \$T_M$nr
+	eval t_quiet mount -t scoutfs \$T_O$nr\$opt \$T_DB$nr \$T_M$nr
+}
+
+#
+# Mount with an optional mount option string.  If the string is empty
+# then the saved mount options are used.  If the string has contents
+# then it is appended to the end of the saved options with a separating
+# comma.
+#
+# Unlike t_mount this won't inherently fail in t_quiet, errors are
+# returned so bad options can be tested.
+#
+t_mount_opt()
+{
+	local nr="$1"
+	local opt="${2:+,$2}"
+
+	test "$nr" -lt "$T_NR_MOUNTS" || \
+		t_fail "fs nr $nr invalid"
+
+	eval mount -t scoutfs \$T_O$nr\$opt \$T_DB$nr \$T_M$nr
 }
 
 t_umount()
@@ -377,13 +406,21 @@ t_wait_for_leader() {
 	done
 }
 
+t_get_sysfs_mount_option() {
+	local nr="$1"
+	local name="$2"
+	local opt="$(t_sysfs_path $nr)/mount_options/$name"
+
+	cat "$opt"
+}
+
 t_set_sysfs_mount_option() {
 	local nr="$1"
 	local name="$2"
 	local val="$3"
 	local opt="$(t_sysfs_path $nr)/mount_options/$name"
 
-	echo "$val" > "$opt"
+	echo "$val" > "$opt" 2>/dev/null
 }
 
 t_set_all_sysfs_mount_options() {
@@ -405,7 +442,7 @@ t_save_all_sysfs_mount_options() {
 
 	for i in $(t_fs_nrs); do
 		opt="$(t_sysfs_path $i)/mount_options/$name"
-		ind="$name_$i"
+		ind="${name}_${i}"
 
 		_saved_opts[$ind]="$(cat $opt)"
 	done
@@ -417,7 +454,7 @@ t_restore_all_sysfs_mount_options() {
 	local i
 
 	for i in $(t_fs_nrs); do
-		ind="$name_$i"
+		ind="${name}_${i}"
 
 		t_set_sysfs_mount_option $i $name "${_saved_opts[$ind]}"
 	done

tests/golden/basic-posix-consistency

@@ -49,6 +49,7 @@ four
 --- can't overwrite non-empty dir
 mv: cannot move ‘/mnt/test/test/basic-posix-consistency/dir/c/clobber’ to ‘/mnt/test/test/basic-posix-consistency/dir/a/dir’: Directory not empty
 --- can overwrite empty dir
+--- can rename into root
 == path resoluion
 == inode indexes match after syncing existing
 == inode indexes match after copying and syncing

tests/golden/basic-truncate

@@ -0,0 +1,6 @@
+== truncate writes zeroed partial end of file block
+0000000 0a79 0a79 0a79 0a79 0a79 0a79 0a79 0a79
+*
+0006144 0000 0000 0000 0000 0000 0000 0000 0000
+*
+0012288

tests/golden/change-devices

@@ -0,0 +1,27 @@
+== make tmp sparse data dev files
+== make scratch fs
+== small new data device fails
+rc: 1
+== check sees data device errors
+rc: 1
+rc: 0
+== preparing while mounted fails
+rc: 1
+== preparing without recovery fails
+rc: 1
+== check sees metadata errors
+rc: 1
+rc: 1
+== preparing with file data fails
+rc: 1
+== preparing after emptied
+rc: 0
+== checks pass
+rc: 0
+rc: 0
+== using prepared
+== preparing larger and resizing
+rc: 0
+equal_prepared
+large_prepared
+resized larger test rc: 0

tests/golden/data-prealloc

@@ -0,0 +1,330 @@
+== initial writes smaller than prealloc grow to prealloc size
+/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: 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: 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: 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: 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: 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
+wrote blk 40
+wrote blk 55
+wrote blk 63
+wrote blk 71
+wrote blk 72
+wrote blk 79
+wrote blk 80
+wrote blk 87
+wrote blk 88
+wrote blk 95
+before:
+24.. 1: 
+32.. 1: 
+40.. 1: 
+55.. 1: 
+63.. 1: 
+71.. 2: 
+79.. 2: 
+87.. 2: 
+95.. 1: eof
+writing into existing 0 at pos 0
+wrote blk 0
+0.. 1: 
+1.. 7: unwritten
+24.. 1: 
+32.. 1: 
+40.. 1: 
+55.. 1: 
+63.. 1: 
+71.. 2: 
+79.. 2: 
+87.. 2: 
+95.. 1: eof
+writing into existing 0 at pos 1
+wrote blk 15
+0.. 1: 
+1.. 14: unwritten
+15.. 1: 
+24.. 1: 
+32.. 1: 
+40.. 1: 
+55.. 1: 
+63.. 1: 
+71.. 2: 
+79.. 2: 
+87.. 2: 
+95.. 1: eof
+writing into existing 0 at pos 2
+wrote blk 19
+0.. 1: 
+1.. 14: unwritten
+15.. 1: 
+16.. 3: unwritten
+19.. 1: 
+20.. 4: unwritten
+24.. 1: 
+32.. 1: 
+40.. 1: 
+55.. 1: 
+63.. 1: 
+71.. 2: 
+79.. 2: 
+87.. 2: 
+95.. 1: eof
+writing into existing 1 at pos 0
+wrote blk 25
+0.. 1: 
+1.. 14: unwritten
+15.. 1: 
+16.. 3: unwritten
+19.. 1: 
+20.. 4: unwritten
+24.. 1: 
+25.. 1: 
+26.. 6: unwritten
+32.. 1: 
+40.. 1: 
+55.. 1: 
+63.. 1: 
+71.. 2: 
+79.. 2: 
+87.. 2: 
+95.. 1: eof
+writing into existing 1 at pos 1
+wrote blk 39
+0.. 1: 
+1.. 14: unwritten
+15.. 1: 
+16.. 3: unwritten
+19.. 1: 
+20.. 4: unwritten
+24.. 1: 
+25.. 1: 
+26.. 6: unwritten
+32.. 1: 
+39.. 1: 
+40.. 1: 
+55.. 1: 
+63.. 1: 
+71.. 2: 
+79.. 2: 
+87.. 2: 
+95.. 1: eof
+writing into existing 1 at pos 2
+wrote blk 44
+0.. 1: 
+1.. 14: unwritten
+15.. 1: 
+16.. 3: unwritten
+19.. 1: 
+20.. 4: unwritten
+24.. 1: 
+25.. 1: 
+26.. 6: unwritten
+32.. 1: 
+39.. 1: 
+40.. 1: 
+44.. 1: 
+45.. 3: unwritten
+55.. 1: 
+63.. 1: 
+71.. 2: 
+79.. 2: 
+87.. 2: 
+95.. 1: eof
+writing into existing 2 at pos 0
+wrote blk 48
+0.. 1: 
+1.. 14: unwritten
+15.. 1: 
+16.. 3: unwritten
+19.. 1: 
+20.. 4: unwritten
+24.. 1: 
+25.. 1: 
+26.. 6: unwritten
+32.. 1: 
+39.. 1: 
+40.. 1: 
+44.. 1: 
+45.. 3: unwritten
+48.. 1: 
+49.. 6: unwritten
+55.. 1: 
+63.. 1: 
+71.. 2: 
+79.. 2: 
+87.. 2: 
+95.. 1: eof
+writing into existing 2 at pos 1
+wrote blk 62
+0.. 1: 
+1.. 14: unwritten
+15.. 1: 
+16.. 3: unwritten
+19.. 1: 
+20.. 4: unwritten
+24.. 1: 
+25.. 1: 
+26.. 6: unwritten
+32.. 1: 
+39.. 1: 
+40.. 1: 
+44.. 1: 
+45.. 3: unwritten
+48.. 1: 
+49.. 6: unwritten
+55.. 1: 
+56.. 6: unwritten
+62.. 1: 
+63.. 1: 
+71.. 2: 
+79.. 2: 
+87.. 2: 
+95.. 1: eof
+writing into existing 2 at pos 2
+wrote blk 67
+0.. 1: 
+1.. 14: unwritten
+15.. 1: 
+16.. 3: unwritten
+19.. 1: 
+20.. 4: unwritten
+24.. 1: 
+25.. 1: 
+26.. 6: unwritten
+32.. 1: 
+39.. 1: 
+40.. 1: 
+44.. 1: 
+45.. 3: unwritten
+48.. 1: 
+49.. 6: unwritten
+55.. 1: 
+56.. 6: unwritten
+62.. 1: 
+63.. 1: 
+64.. 3: unwritten
+67.. 1: 
+68.. 3: unwritten
+71.. 2: 
+79.. 2: 
+87.. 2: 
+95.. 1: eof
+writing into existing 3 at pos 0
+wrote blk 73
+0.. 1: 
+1.. 14: unwritten
+15.. 1: 
+16.. 3: unwritten
+19.. 1: 
+20.. 4: unwritten
+24.. 1: 
+25.. 1: 
+26.. 6: unwritten
+32.. 1: 
+39.. 1: 
+40.. 1: 
+44.. 1: 
+45.. 3: unwritten
+48.. 1: 
+49.. 6: unwritten
+55.. 1: 
+56.. 6: unwritten
+62.. 1: 
+63.. 1: 
+64.. 3: unwritten
+67.. 1: 
+68.. 3: unwritten
+71.. 2: 
+73.. 1: 
+74.. 5: unwritten
+79.. 2: 
+87.. 2: 
+95.. 1: eof
+writing into existing 3 at pos 1
+wrote blk 86
+0.. 1: 
+1.. 14: unwritten
+15.. 1: 
+16.. 3: unwritten
+19.. 1: 
+20.. 4: unwritten
+24.. 1: 
+25.. 1: 
+26.. 6: unwritten
+32.. 1: 
+39.. 1: 
+40.. 1: 
+44.. 1: 
+45.. 3: unwritten
+48.. 1: 
+49.. 6: unwritten
+55.. 1: 
+56.. 6: unwritten
+62.. 1: 
+63.. 1: 
+64.. 3: unwritten
+67.. 1: 
+68.. 3: unwritten
+71.. 2: 
+73.. 1: 
+74.. 5: unwritten
+79.. 2: 
+86.. 1: 
+87.. 2: 
+95.. 1: eof
+writing into existing 3 at pos 2
+wrote blk 92
+0.. 1: 
+1.. 14: unwritten
+15.. 1: 
+16.. 3: unwritten
+19.. 1: 
+20.. 4: unwritten
+24.. 1: 
+25.. 1: 
+26.. 6: unwritten
+32.. 1: 
+39.. 1: 
+40.. 1: 
+44.. 1: 
+45.. 3: unwritten
+48.. 1: 
+49.. 6: unwritten
+55.. 1: 
+56.. 6: unwritten
+62.. 1: 
+63.. 1: 
+64.. 3: unwritten
+67.. 1: 
+68.. 3: unwritten
+71.. 2: 
+73.. 1: 
+74.. 5: unwritten
+79.. 2: 
+86.. 1: 
+87.. 2: 
+92.. 1: 
+93.. 2: unwritten
+95.. 1: eof

tests/golden/get-referring-entries

@@ -0,0 +1,18 @@
+== root inode returns nothing
+== crazy large unused inode does nothing
+== basic entry
+file
+== rename
+renamed
+== hard link
+file
+link
+== removal
+== different dirs
+== file types
+type b name block
+type c name char
+type d name dir
+type f name file
+type l name symlink
+== all name lengths work

tests/golden/large-fragmented-free

@@ -0,0 +1,3 @@
+== creating fragmented extents
+== unlink file with moved extents to free extents per block
+== cleanup

tests/golden/lock-recover-invalidate

@@ -0,0 +1,3 @@
+== starting background invalidating read/write load
+== 60s of lock recovery during invalidating load
+== stopping background load

tests/golden/o_tmpfile

@@ -1,3 +1,11 @@
+== non-acl O_TMPFILE creation honors umask
+umask 022
+fstat after open(0777): 0100755
+stat after linkat: 0100755
+umask 077
+fstat after open(0777): 0100700
+stat after linkat: 0100700
+== stage from tmpfile
 total file size 33669120
 00000000  41 41 41 41 41 41 41 41  41 41 41 41 41 41 41 41  |AAAAAAAAAAAAAAAA|
 *

tests/golden/quorum-heartbeat-timeout

@@ -0,0 +1,5 @@
+== bad timeout values fail
+== bad mount option fails
+== mount option
+== sysfs
+== reset all options

tests/golden/simple-inode-index

@@ -7,3 +7,4 @@ found second
 == changing metadata must increase meta seq
 == changing contents must increase data seq
 == make sure dirtying doesn't livelock walk
+== concurrent update attempts maintain single entries

tests/golden/xfstests

@@ -40,6 +40,7 @@ generic/092
 generic/098
 generic/101
 generic/104
+generic/105
 generic/106
 generic/107
 generic/117
@@ -51,6 +52,7 @@ generic/184
 generic/221
 generic/228
 generic/236
+generic/237
 generic/245
 generic/249
 generic/257
@@ -63,6 +65,7 @@ generic/308
 generic/309
 generic/313
 generic/315
+generic/319
 generic/322
 generic/335
 generic/336
@@ -72,6 +75,7 @@ generic/342
 generic/343
 generic/348
 generic/360
+generic/375
 generic/376
 generic/377
 Not
@@ -282,4 +286,4 @@ shared/004
 shared/032
 shared/051
 shared/289
-Passed all 75 tests
+Passed all 79 tests

tests/run-tests.sh

@@ -58,6 +58,7 @@ $(basename $0) options:
     -m        | Run mkfs on the device before mounting and running
               | tests.  Implies unmounting existing mounts first.
     -n <nr>   | The number of devices and mounts to test.
+    -o <opts> | Add option string to all mounts during all tests.
     -P        | Enable trace_printk.
     -p        | Exit script after preparing mounts only, don't run tests.
     -q <nr>   | The first <nr> mounts will be quorum members.  Must be
@@ -68,6 +69,7 @@ $(basename $0) options:
     -s        | Skip git repo checkouts.
     -t        | Enabled trace events that match the given glob argument.
               | Multiple options enable multiple globbed events.
+    -T <nr>   | Multiply the original trace buffer size by nr during the run.
     -X        | xfstests git repo. Used by tests/xfstests.sh.
     -x        | xfstests git branch to checkout and track.
     -y        | xfstests ./check additional args
@@ -136,6 +138,12 @@ while true; do
 		T_NR_MOUNTS="$2"
 		shift
 		;;
+	-o)
+		test -n "$2" || die "-o must have option string argument"
+		# always appending to existing options
+		T_MNT_OPTIONS+=",$2"
+		shift
+		;;
 	-P)
 		T_TRACE_PRINTK="1"
 		;;
@@ -160,6 +168,11 @@ while true; do
 		T_TRACE_GLOB+=("$2")
 		shift
 		;;
+	-T)
+		test -n "$2" || die "-T must have trace buffer size multiplier argument"
+		T_TRACE_MULT="$2"
+		shift
+		;;
 	-X)
 		test -n "$2" || die "-X requires xfstests git repo dir argument"
 		T_XFSTESTS_REPO="$2"
@@ -345,6 +358,13 @@ if [ -n "$T_INSMOD" ]; then
 	cmd insmod "$T_KMOD/src/scoutfs.ko"
 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
@@ -374,6 +394,7 @@ fi
 # always describe tracing in the logs
 cmd cat /sys/kernel/debug/tracing/set_event
 cmd grep .  /sys/kernel/debug/tracing/options/trace_printk \
+	    /sys/kernel/debug/tracing/buffer_size_kb \
 	    /proc/sys/kernel/ftrace_dump_on_oops
 
 #
@@ -430,6 +451,7 @@ for i in $(seq 0 $((T_NR_MOUNTS - 1))); do
 	if [ "$i" -lt "$T_QUORUM" ]; then
 		opts="$opts,quorum_slot_nr=$i"
 	fi
+	opts="${opts}${T_MNT_OPTIONS}"
 
 	msg "mounting $meta_dev|$data_dev on $dir"
 	cmd mount -t scoutfs $opts "$data_dev" "$dir" &
@@ -604,6 +626,9 @@ if [ -n "$T_TRACE_GLOB" -o -n "$T_TRACE_PRINTK" ]; then
 	echo 0 > /sys/kernel/debug/tracing/events/scoutfs/enable
 	echo 0 > /sys/kernel/debug/tracing/options/trace_printk
 	cat /sys/kernel/debug/tracing/trace > "$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

tests/sequence

@@ -5,10 +5,14 @@ inode-items-updated.sh
 simple-inode-index.sh
 simple-staging.sh
 simple-release-extents.sh
+get-referring-entries.sh
 fallocate.sh
+basic-truncate.sh
+data-prealloc.sh
 setattr_more.sh
 offline-extent-waiting.sh
 move-blocks.sh
+large-fragmented-free.sh
 enospc.sh
 srch-basic-functionality.sh
 simple-xattr-unit.sh
@@ -17,13 +21,14 @@ lock-refleak.sh
 lock-shrink-consistency.sh
 lock-pr-cw-conflict.sh
 lock-revoke-getcwd.sh
+lock-recover-invalidate.sh
 export-lookup-evict-race.sh
 createmany-parallel.sh
 createmany-large-names.sh
 createmany-rename-large-dir.sh
 stage-release-race-alloc.sh
 stage-multi-part.sh
-stage-tmpfile.sh
+o_tmpfile.sh
 basic-posix-consistency.sh
 dirent-consistency.sh
 mkdir-rename-rmdir.sh
@@ -32,7 +37,9 @@ cross-mount-data-free.sh
 persistent-item-vers.sh
 setup-error-teardown.sh
 resize-devices.sh
+change-devices.sh
 fence-and-reclaim.sh
+quorum-heartbeat-timeout.sh
 orphan-inodes.sh
 mount-unmount-race.sh
 client-unmount-recovery.sh

tests/src/fragmented_data_extents.c

@@ -0,0 +1,113 @@
+/*
+ * Copyright (C) 2021 Versity Software, Inc.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+/*
+ * This creates fragmented data extents.
+ *
+ * A file is created that has alternating free and allocated extents.
+ * This also results in the global allocator having the matching
+ * fragmented free extent pattern.  While that file is being created,
+ * occasionally an allocated extent is moved to another file.   This
+ * results in a file that has fragmented extents at a given stride that
+ * can be deleted to create free data extents with a given stride.
+ *
+ * We don't have hole punching so to do this quickly we use a goofy
+ * combination of fallocate, truncate, and our move_blocks ioctl.
+ */
+
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE
+#endif
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <linux/types.h>
+#include <assert.h>
+
+#include "ioctl.h"
+
+#define BLOCK_SIZE 4096
+
+int main(int argc, char **argv)
+{
+	struct scoutfs_ioctl_move_blocks mb = {0,};
+	unsigned long long freed_extents;
+	unsigned long long move_stride;
+	unsigned long long i;
+	int alloc_fd;
+	int trunc_fd;
+	off_t off;
+	int ret;
+
+	if (argc != 5) {
+		printf("%s <freed_extents> <move_stride> <alloc_file> <trunc_file>\n", argv[0]);
+		return 1;
+	}
+
+	freed_extents = strtoull(argv[1], NULL, 0);
+	move_stride = strtoull(argv[2], NULL, 0);
+
+	alloc_fd = open(argv[3], O_RDWR | O_CREAT | O_TRUNC, S_IRUSR | S_IWUSR);
+	if (alloc_fd == -1) {
+		fprintf(stderr, "error opening %s: %d (%s)\n", argv[3], errno, strerror(errno));
+		exit(1);
+	}
+
+	trunc_fd = open(argv[4], O_RDWR | O_CREAT | O_TRUNC, S_IRUSR | S_IWUSR);
+	if (trunc_fd == -1) {
+		fprintf(stderr, "error opening %s: %d (%s)\n", argv[4], errno, strerror(errno));
+		exit(1);
+	}
+
+	for (i = 0, off = 0; i < freed_extents; i++, off += BLOCK_SIZE * 2) {
+
+		ret = fallocate(alloc_fd, 0, off, BLOCK_SIZE * 2);
+		if (ret < 0) {
+			fprintf(stderr, "fallocate at off %llu error: %d (%s)\n",
+				(unsigned long long)off, errno, strerror(errno));
+			exit(1);
+		}
+
+		ret = ftruncate(alloc_fd, off + BLOCK_SIZE);
+		if (ret < 0) {
+			fprintf(stderr, "truncate to off %llu error: %d (%s)\n",
+				(unsigned long long)off + BLOCK_SIZE, errno, strerror(errno));
+			exit(1);
+		}
+
+		if ((i % move_stride) == 0) {
+			mb.from_fd = alloc_fd;
+			mb.from_off = off;
+			mb.len = BLOCK_SIZE;
+			mb.to_off = i * BLOCK_SIZE;
+
+			ret = ioctl(trunc_fd, SCOUTFS_IOC_MOVE_BLOCKS, &mb);
+			if (ret < 0) {
+				fprintf(stderr, "move from off %llu error: %d (%s)\n",
+					(unsigned long long)off,
+					errno, strerror(errno));
+			}
+		}
+	}
+
+	if (alloc_fd > -1)
+		close(alloc_fd);
+	if (trunc_fd > -1)
+		close(trunc_fd);
+
+	return 0;
+}

tests/src/o_tmpfile_umask.c

@@ -0,0 +1,97 @@
+/*
+ * Show the modes of files as we create them with O_TMPFILE and link
+ * them into the namespace.
+ *
+ * Copyright (C) 2022 Versity Software, Inc.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE
+#endif
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <sys/stat.h>
+#include <assert.h>
+#include <limits.h>
+
+static void linkat_tmpfile_modes(char *dir, char *lpath, mode_t mode)
+{
+	char proc_self[PATH_MAX];
+	struct stat st;
+	int ret;
+	int fd;
+
+	umask(mode);
+	printf("umask 0%o\n", mode);
+
+	fd = open(dir, O_RDWR | O_TMPFILE, 0777);
+	if (fd < 0) {
+		perror("open(O_TMPFILE)");
+		exit(1);
+	}
+
+	ret = fstat(fd, &st);
+	if (ret < 0) {
+		perror("fstat");
+		exit(1);
+	}
+
+	printf("fstat after open(0777): 0%o\n", st.st_mode);
+
+	snprintf(proc_self, sizeof(proc_self), "/proc/self/fd/%d", fd);
+
+	ret = linkat(AT_FDCWD, proc_self, AT_FDCWD, lpath, AT_SYMLINK_FOLLOW);
+	if (ret < 0) {
+		perror("linkat");
+		exit(1);
+	}
+
+	close(fd);
+
+	ret = stat(lpath, &st);
+	if (ret < 0) {
+		perror("fstat");
+		exit(1);
+	}
+
+	printf("stat after linkat: 0%o\n", st.st_mode);
+
+	ret = unlink(lpath);
+	if (ret < 0) {
+		perror("unlink");
+		exit(1);
+	}
+}
+
+int main(int argc, char **argv)
+{
+	char *lpath;
+	char *dir;
+
+	if (argc < 3) {
+		printf("%s <open_dir> <linkat_path>\n", argv[0]);
+		return 1;
+	}
+
+	dir = argv[1];
+	lpath = argv[2];
+
+	linkat_tmpfile_modes(dir, lpath, 022);
+	linkat_tmpfile_modes(dir, lpath, 077);
+
+	return 0;
+}

tests/tests/basic-bad-mounts.sh

@@ -12,7 +12,7 @@ mount_fail()
 }
 
 echo "== prepare devices, mount point, and logs"
-SCR="/mnt/scoutfs.extra"
+SCR="$T_TMPDIR/mnt.scratch"
 mkdir -p "$SCR"
 > $T_TMP.mount.out
 scoutfs mkfs -f -Q 0,127.0.0.1,53000 "$T_EX_META_DEV" "$T_EX_DATA_DEV" > $T_TMP.mkfs.out 2>&1 \

tests/tests/basic-posix-consistency.sh

@@ -149,6 +149,10 @@ find "$T_D0/dir" -ls 2>&1 | t_filter_fs > "$T_TMP.0"
 find "$T_D1/dir" -ls 2>&1 | t_filter_fs > "$T_TMP.1"
 diff -u "$T_TMP.0" "$T_TMP.1"
 rm -rf "$T_D0/dir"
+echo "--- can rename into root"
+touch "$T_D0/rename-into-root"
+mv "$T_D0/rename-into-root" "$T_M0/"
+rm -f "$T_M0/rename-into-root"
 
 echo "== path resoluion"
 touch "$T_D0/file"

tests/tests/basic-truncate.sh

@@ -0,0 +1,21 @@
+#
+# Test basic correctness of truncate.
+#
+
+t_require_commands yes dd od truncate
+
+FILE="$T_D0/file"
+
+#
+# We forgot to write a dirty block that zeroed the tail of a partial
+# final block as we truncated past it.
+#
+echo "== truncate writes zeroed partial end of file block"
+yes | dd of="$FILE" bs=8K count=1 status=none
+sync
+truncate -s 6K "$FILE"
+truncate -s 12K "$FILE"
+echo 3 > /proc/sys/vm/drop_caches
+od -Ad -x "$FILE"
+
+t_pass

tests/tests/change-devices.sh

@@ -0,0 +1,76 @@
+#
+# test changing devices
+#
+
+echo "== make tmp sparse data dev files"
+sz=$(blockdev --getsize64 "$T_EX_DATA_DEV")
+large_sz=$((sz * 2))
+touch "$T_TMP."{small,equal,large}
+truncate -s 1MB "$T_TMP.small"
+truncate -s $sz "$T_TMP.equal"
+truncate -s $large_sz "$T_TMP.large"
+
+echo "== make scratch fs"
+t_quiet scoutfs mkfs -f -Q 0,127.0.0.1,53000 "$T_EX_META_DEV" "$T_EX_DATA_DEV"
+SCR="$T_TMPDIR/mnt.scratch"
+mkdir -p "$SCR"
+
+echo "== small new data device fails"
+t_rc scoutfs prepare-empty-data-device "$T_EX_META_DEV" "$T_TMP.small"
+
+echo "== check sees data device errors"
+t_rc scoutfs prepare-empty-data-device --check "$T_EX_META_DEV" "$T_TMP.small"
+t_rc scoutfs prepare-empty-data-device --check "$T_EX_META_DEV"
+
+echo "== preparing while mounted fails"
+mount -t scoutfs -o metadev_path=$T_EX_META_DEV,quorum_slot_nr=0 "$T_EX_DATA_DEV" "$SCR"
+t_rc scoutfs prepare-empty-data-device "$T_EX_META_DEV" "$T_TMP.equal"
+umount "$SCR"
+
+echo "== preparing without recovery fails"
+mount -t scoutfs -o metadev_path=$T_EX_META_DEV,quorum_slot_nr=0 "$T_EX_DATA_DEV" "$SCR"
+umount -f "$SCR"
+t_rc scoutfs prepare-empty-data-device "$T_EX_META_DEV" "$T_TMP.equal"
+
+echo "== check sees metadata errors"
+t_rc scoutfs prepare-empty-data-device --check "$T_EX_META_DEV"
+t_rc scoutfs prepare-empty-data-device --check "$T_EX_META_DEV" "$T_TMP.equal"
+
+echo "== preparing with file data fails"
+mount -t scoutfs -o metadev_path=$T_EX_META_DEV,quorum_slot_nr=0 "$T_EX_DATA_DEV" "$SCR"
+echo hi > "$SCR"/file
+umount "$SCR"
+scoutfs print "$T_EX_META_DEV" > "$T_TMP.print"
+t_rc scoutfs prepare-empty-data-device "$T_EX_META_DEV" "$T_TMP.equal"
+
+echo "== preparing after emptied"
+mount -t scoutfs -o metadev_path=$T_EX_META_DEV,quorum_slot_nr=0 "$T_EX_DATA_DEV" "$SCR"
+rm -f "$SCR"/file
+umount "$SCR"
+t_rc scoutfs prepare-empty-data-device "$T_EX_META_DEV" "$T_TMP.equal"
+
+echo "== checks pass"
+t_rc scoutfs prepare-empty-data-device --check "$T_EX_META_DEV"
+t_rc scoutfs prepare-empty-data-device --check "$T_EX_META_DEV" "$T_TMP.equal"
+
+echo "== using prepared"
+scr_loop=$(losetup --find --show "$T_TMP.equal")
+mount -t scoutfs -o metadev_path=$T_EX_META_DEV,quorum_slot_nr=0 "$scr_loop" "$SCR"
+touch "$SCR"/equal_prepared
+equal_tot=$(scoutfs statfs -s total_data_blocks -p "$SCR")
+umount "$SCR"
+losetup -d "$scr_loop"
+
+echo "== preparing larger and resizing"
+t_rc scoutfs prepare-empty-data-device "$T_EX_META_DEV" "$T_TMP.large"
+scr_loop=$(losetup --find --show "$T_TMP.large")
+mount -t scoutfs -o metadev_path=$T_EX_META_DEV,quorum_slot_nr=0 "$scr_loop" "$SCR"
+touch "$SCR"/large_prepared
+ls "$SCR"
+scoutfs resize-devices -p "$SCR" -d $large_sz
+large_tot=$(scoutfs statfs -s total_data_blocks -p "$SCR")
+test "$large_tot" -gt "$equal_tot" ; echo "resized larger test rc: $?"
+umount "$SCR"
+losetup -d "$scr_loop"
+
+t_pass

tests/tests/data-prealloc.sh

@@ -0,0 +1,231 @@
+#
+# test that the data prealloc options behave as expected.  We write to
+# two files a block at a time so that a single file doesn't naturally
+# merge adjacent consecutive allocations.  (we don't have multiple
+# allocation cursors)
+#
+t_require_commands scoutfs stat filefrag dd touch truncate
+
+write_block()
+{
+	local file="$1"
+	local blk="$2"
+
+	dd if=/dev/zero of="$file" bs=4096 seek=$blk count=1 conv=notrunc status=none
+	echo "wrote blk $blk"
+}
+
+write_forwards()
+{
+	local prefix="$1"
+	local nr="$2"
+	local blk
+
+	touch "$prefix"-{1,2}
+	truncate -s 0 "$prefix"-{1,2}
+
+	for blk in $(seq 0 1 $((nr - 1))); do
+		dd if=/dev/zero of="$prefix"-1 bs=4096 seek=$blk count=1 conv=notrunc status=none
+		dd if=/dev/zero of="$prefix"-2 bs=4096 seek=$blk count=1 conv=notrunc status=none
+	done
+}
+
+write_backwards()
+{
+	local prefix="$1"
+	local nr="$2"
+	local blk
+
+	touch "$prefix"-{1,2}
+	truncate -s 0 "$prefix"-{1,2}
+
+	for blk in $(seq $((nr - 1)) -1 0); do
+		dd if=/dev/zero of="$prefix"-1 bs=4096 seek=$blk count=1 conv=notrunc status=none
+		dd if=/dev/zero of="$prefix"-2 bs=4096 seek=$blk count=1 conv=notrunc status=none
+	done
+}
+
+release_files() {
+	local prefix="$1"
+	local size=$(($2 * 4096))
+	local vers
+	local f
+
+	for f in "$prefix"*; do
+		size=$(stat -c "%s" "$f")
+		vers=$(scoutfs stat -s data_version "$f")
+		scoutfs release "$f" -V "$vers" -o 0 -l $size
+	done
+}
+
+stage_files() {
+	local prefix="$1"
+	local nr="$2"
+	local vers
+	local f
+
+	for blk in $(seq 0 1 $((nr - 1))); do
+		for f in "$prefix"*; do
+			vers=$(scoutfs stat -s data_version "$f")
+			scoutfs stage /dev/zero "$f" -V "$vers" -o $((blk * 4096)) -l 4096
+		done
+	done
+}
+
+print_extents_found()
+{
+	local prefix="$1"
+
+	filefrag "$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, $6, flags
+		}
+	'
+}
+
+t_save_all_sysfs_mount_options data_prealloc_blocks
+t_save_all_sysfs_mount_options data_prealloc_contig_only
+restore_options()
+{
+	t_restore_all_sysfs_mount_options data_prealloc_blocks
+	t_restore_all_sysfs_mount_options data_prealloc_contig_only
+}
+trap restore_options EXIT
+
+prefix="$T_D0/file"
+
+echo "== initial writes smaller than prealloc grow to prealloc size"
+t_set_sysfs_mount_option 0 data_prealloc_blocks 32
+t_set_sysfs_mount_option 0 data_prealloc_contig_only 1
+write_forwards $prefix 64
+print_extents_found $prefix
+
+echo "== larger files get full prealloc extents"
+t_set_sysfs_mount_option 0 data_prealloc_blocks 32
+t_set_sysfs_mount_option 0 data_prealloc_contig_only 1
+write_forwards $prefix 128
+print_extents_found $prefix
+
+echo "== non-streaming writes with contig have per-block extents"
+t_set_sysfs_mount_option 0 data_prealloc_blocks 32
+t_set_sysfs_mount_option 0 data_prealloc_contig_only 1
+write_backwards $prefix 32
+print_extents_found $prefix
+
+echo "== any writes to region prealloc get full extents"
+t_set_sysfs_mount_option 0 data_prealloc_blocks 16
+t_set_sysfs_mount_option 0 data_prealloc_contig_only 0
+write_forwards $prefix 64
+print_extents_found $prefix
+write_backwards $prefix 64
+print_extents_found $prefix
+
+echo "== streaming offline writes get full extents either way"
+t_set_sysfs_mount_option 0 data_prealloc_blocks 16
+t_set_sysfs_mount_option 0 data_prealloc_contig_only 1
+write_forwards $prefix 64
+release_files $prefix 64
+stage_files $prefix 64
+print_extents_found $prefix
+t_set_sysfs_mount_option 0 data_prealloc_contig_only 0
+release_files $prefix 64
+stage_files $prefix 64
+print_extents_found $prefix
+
+echo "== goofy preallocation amounts work"
+t_set_sysfs_mount_option 0 data_prealloc_blocks 7
+t_set_sysfs_mount_option 0 data_prealloc_contig_only 1
+write_forwards $prefix 14
+print_extents_found $prefix
+t_set_sysfs_mount_option 0 data_prealloc_blocks 13
+t_set_sysfs_mount_option 0 data_prealloc_contig_only 0
+write_forwards $prefix 53
+print_extents_found $prefix
+t_set_sysfs_mount_option 0 data_prealloc_blocks 1
+t_set_sysfs_mount_option 0 data_prealloc_contig_only 0
+write_forwards $prefix 3
+print_extents_found $prefix
+
+#
+# prepare aligned regions of 8 blocks that we'll write into.
+# We'll right into the first, last, and middle block of each
+# region which was prepared with no existing extents, one at
+# the start, and one at the end.
+#
+# Let's keep this last because it creates a ton of output to read
+# through.  The correct output is tied to preallocation strategy so it
+# has to be verified each time we change preallocation.
+#
+echo "== block writes into region allocs hole" 
+t_set_sysfs_mount_option 0 data_prealloc_blocks 8
+t_set_sysfs_mount_option 0 data_prealloc_contig_only 1
+touch "$prefix"
+truncate -s 0 "$prefix"
+
+# write initial blocks in regions
+base=0
+for sides in 0 1 2 3; do
+	for i in 0 1 2; do
+                case "$sides" in
+			# none
+			0) ;;
+			# left
+			1) write_block $prefix $((base + 0)) ;;
+			# right
+			2) write_block $prefix $((base + 7)) ;;
+			# both
+			3) write_block $prefix $((base + 0)) 
+			   write_block $prefix $((base + 7)) ;;
+		esac
+		((base+=8))
+	done
+done
+
+echo before:
+print_logical_extents "$prefix"
+
+# now write into the first, middle, and last empty block of each
+t_set_sysfs_mount_option 0 data_prealloc_contig_only 0
+base=0
+for sides in 0 1 2 3; do
+	for i in 0 1 2; do
+		echo "writing into existing $sides at pos $i"
+		case "$sides" in
+			# none
+			0) left=$base; right=$((base + 7));;
+			# left
+			1) left=$((base + 1)); right=$((base + 7));;
+			# right
+			2) left=$((base)); right=$((base + 6));;
+			# both
+			3) left=$((base + 1)); right=$((base + 6));;
+		esac
+		case "$i" in
+			# start
+			0) write_block $prefix $left ;;
+			# end
+			1) write_block $prefix $right ;;
+			# mid (both has 6 blocks internally)
+			2) write_block $prefix $((left + 3)) ;;
+		esac
+		print_logical_extents "$prefix"
+		((base+=8))
+	done
+done
+
+t_pass

tests/tests/enospc.sh

@@ -59,7 +59,7 @@ echo "== make small meta fs"
 # meta device just big enough for reserves and the metadata we'll fill
 scoutfs mkfs -A -f -Q 0,127.0.0.1,53000 -m 10G "$T_EX_META_DEV" "$T_EX_DATA_DEV" > $T_TMP.mkfs.out 2>&1 || \
 	t_fail "mkfs failed"
-SCR="/mnt/scoutfs.enospc"
+SCR="$T_TMPDIR/mnt.scratch"
 mkdir -p "$SCR"
 mount -t scoutfs -o metadev_path=$T_EX_META_DEV,quorum_slot_nr=0 \
 	"$T_EX_DATA_DEV" "$SCR"

tests/tests/get-referring-entries.sh

@@ -0,0 +1,99 @@
+
+#
+# Test _GET_REFERRING_ENTRIES ioctl via the get-referring-entries cli
+# command
+#
+
+# consistently print only entry names
+filter_names() {
+	exec cut -d ' ' -f 8- | sort
+}
+
+# print entries with type characters to match find.  not happy with hard
+# coding, but abi won't change much.
+filter_types() {
+	exec cut -d ' ' -f 5- | \
+	sed \
+		-e 's/type 1 /type p /' \
+		-e 's/type 2 /type c /' \
+		-e 's/type 4 /type d /' \
+		-e 's/type 6 /type b /' \
+		-e 's/type 8 /type f /' \
+		-e 's/type 10 /type l /' \
+		-e 's/type 12 /type s /' \
+		| \
+	sort
+}
+
+n_chars() {
+	local n="$1"
+	printf 'A%.0s' $(eval echo {1..\$n})
+}
+
+GRE="scoutfs get-referring-entries -p $T_M0"
+
+echo "== root inode returns nothing"
+$GRE 1
+
+echo "== crazy large unused inode does nothing"
+$GRE 4611686018427387904 # 1 << 62
+
+echo "== basic entry"
+touch $T_D0/file
+ino=$(stat -c '%i' $T_D0/file)
+$GRE $ino | filter_names
+
+echo "== rename"
+mv $T_D0/file $T_D0/renamed
+$GRE $ino | filter_names
+
+echo "== hard link"
+mv $T_D0/renamed $T_D0/file
+ln $T_D0/file $T_D0/link
+$GRE $ino | filter_names
+
+echo "== removal"
+rm $T_D0/file $T_D0/link
+$GRE $ino
+
+echo "== different dirs"
+touch $T_D0/file
+ino=$(stat -c '%i' $T_D0/file)
+for i in $(seq 1 10); do
+	mkdir $T_D0/dir-$i
+	ln $T_D0/file $T_D0/dir-$i/file-$i
+done
+diff -u <(find $T_D0 -type f -printf '%f\n' | sort) <($GRE $ino | filter_names)
+rm $T_D0/file
+
+echo "== file types"
+mkdir $T_D0/dir
+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 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
+done
+rm -rf $T_D0/dir
+
+echo "== all name lengths work"
+mkdir $T_D0/dir
+touch $T_D0/dir/file
+ino=$(stat -c '%i' $T_D0/dir/file)
+name=""
+> $T_TMP.unsorted
+for i in $(seq 1 255); do
+	name+="a"
+	echo "$name" >> $T_TMP.unsorted
+	ln $T_D0/dir/file $T_D0/dir/$name
+done
+sort $T_TMP.unsorted > $T_TMP.sorted
+rm $T_D0/dir/file
+$GRE $ino | filter_names > $T_TMP.gre
+diff -u $T_TMP.sorted $T_TMP.gre
+rm -rf $T_D0/dir
+
+t_pass

tests/tests/large-fragmented-free.sh

@@ -0,0 +1,22 @@
+#
+# Make sure the server can handle a transaction with a data_freed whose
+# blocks all hit different btree blocks in the main free list.  It
+# probably has to be merged in multiple commits.
+#
+
+t_require_commands fragmented_data_extents
+
+EXTENTS_PER_BTREE_BLOCK=600
+EXTENTS_PER_LIST_BLOCK=8192
+FREED_EXTENTS=$((EXTENTS_PER_BTREE_BLOCK * EXTENTS_PER_LIST_BLOCK))
+
+echo "== creating fragmented extents"
+fragmented_data_extents $FREED_EXTENTS $EXTENTS_PER_BTREE_BLOCK "$T_D0/alloc" "$T_D0/move"
+
+echo "== unlink file with moved extents to free extents per block"
+rm -f "$T_D0/move"
+
+echo "== cleanup"
+rm -f "$T_D0/alloc"
+
+t_pass

tests/tests/lock-recover-invalidate.sh

@@ -0,0 +1,43 @@
+#
+# trigger server failover and lock recovery during heavy invalidating
+# load on multiple mounts
+#
+
+majority_nr=$(t_majority_count)
+quorum_nr=$T_QUORUM
+
+test "$quorum_nr" == "$majority_nr" && \
+        t_skip "need remaining majority when leader unmounted"
+
+test "$T_NR_MOUNTS" -lt "$((quorum_nr + 2))" && \
+        t_skip "need at least 2 non-quorum load mounts"
+
+echo "== starting background invalidating read/write load"
+touch "$T_D0/file"
+load_pids=""
+for i in $(t_fs_nrs); do
+	if [ "$i" -ge "$quorum_nr" ]; then
+		eval path="\$T_D${i}/file"
+
+		(while true; do touch $path > /dev/null 2>&1; done) &
+		load_pids="$load_pids $!"
+		(while true; do stat $path > /dev/null 2>&1; done) &
+		load_pids="$load_pids $!"
+	fi
+done
+
+# had it reproduce in ~40s on wimpy debug kernel guests
+LENGTH=60
+echo "== ${LENGTH}s of lock recovery during invalidating load"
+END=$((SECONDS + LENGTH))
+while [ "$SECONDS" -lt "$END" ]; do
+        sv=$(t_server_nr)
+        t_umount $sv
+        t_mount $sv
+	# new server had to process greeting for mount to finish
+done
+
+echo "== stopping background load"
+kill $load_pids
+
+t_pass

tests/tests/o_tmpfile.sh

@@ -0,0 +1,16 @@
+#
+# basic tests of O_TMPFILE
+#
+
+t_require_commands stage_tmpfile hexdump
+
+echo "== non-acl O_TMPFILE creation honors umask"
+o_tmpfile_umask "$T_D0" "$T_D0/umask-file" 
+
+echo "== stage from tmpfile"
+DEST_FILE="$T_D0/dest_file"
+stage_tmpfile $T_D0 $DEST_FILE
+hexdump -C "$DEST_FILE"
+rm -f "$DEST_FILE"
+
+t_pass

tests/tests/quorum-heartbeat-timeout.sh

@@ -0,0 +1,117 @@
+#
+# test that the quorum_heartbeat_time_ms option affects how long it
+# takes to recover from a failed mount.
+#
+
+t_require_mounts 2
+
+time_ms()
+{
+	# time_t in seconds, then trunate nanoseconds to 3 most dig digits
+	date +%s%3N
+}
+
+set_bad_timeout() {
+	local to="$1"
+	t_set_sysfs_mount_option 0 quorum_heartbeat_timeout_ms $to && \
+		t_fail "set bad q hb to $to"
+}
+
+set_timeout()
+{
+	local nr="$1"
+	local how="$2"
+	local to="$3"
+	local is
+
+	if [ $how == "sysfs" ]; then
+		t_set_sysfs_mount_option $nr quorum_heartbeat_timeout_ms $to
+	fi
+	if [ $how == "mount" ]; then
+		t_umount $nr
+		t_mount_opt $nr "quorum_heartbeat_timeout_ms=$to"
+	fi
+
+	is=$(t_get_sysfs_mount_option $nr quorum_heartbeat_timeout_ms)
+
+	if [ "$is" != "$to" ]; then
+		t_fail "tried to set qhbto on $nr via $how to $to but got $is"
+	fi
+}
+
+test_timeout()
+{
+	local how="$1"
+	local to="$2"
+	local start
+	local nr
+	local sv
+	local delay
+	local low
+	local high
+
+	# set timeout on non-server quorum mounts
+	sv=$(t_server_nr)
+	for nr in $(t_quorum_nrs); do
+		if [ $nr -ne $sv ]; then
+			set_timeout $nr $how $to
+		fi
+	done
+
+	# give followers time to recv heartbeats and reset timeouts
+	sleep 1
+
+	# tear down the current server/leader
+	t_force_umount $sv
+
+	# see how long it takes for the next leader to start
+	start=$(time_ms)
+	t_wait_for_leader
+	delay=$(($(time_ms) - start))
+
+	# kind of fun to have these logged
+	echo "to $to delay $delay" >> $T_TMP.delay
+
+	# restore the mount that we tore down
+	t_mount $sv
+
+	# make sure the new leader delay was reasonable, allowing for some slack
+	low=$((to - 1000))
+	high=$((to + 5000))
+
+	# make sure the new leader delay was reasonable
+	test "$delay" -lt "$low" && t_fail "delay $delay < low $low (to $to)"
+	test "$delay" -gt "$high" && t_fail "delay $delay > high $high (to $to)"
+}
+
+echo "== bad timeout values fail"
+set_bad_timeout 0
+set_bad_timeout -1
+set_bad_timeout 1000000
+
+echo "== bad mount option fails"
+if [ "$(t_server_nr)" == 0 ]; then
+	nr=1
+else
+	nr=0
+fi
+t_umount $nr
+t_mount_opt $nr "quorum_heartbeat_timeout_ms=1000000" 2>/dev/null && \
+	t_fail "bad mount option succeeded"
+t_mount $nr
+
+echo "== mount option"
+def=$(t_get_sysfs_mount_option 0 quorum_heartbeat_timeout_ms)
+test_timeout mount $def
+test_timeout mount 3000
+test_timeout mount $((def + 19000))
+
+echo "== sysfs"
+test_timeout sysfs $def
+test_timeout sysfs 3000
+test_timeout sysfs $((def + 19000))
+
+echo "== reset all options"
+t_remount_all
+
+t_pass

tests/tests/resize-devices.sh

@@ -73,7 +73,7 @@ echo "== make initial small fs"
 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" > $T_TMP.mkfs.out 2>&1 || \
 		t_fail "mkfs failed"
-SCR="/mnt/scoutfs.enospc"
+SCR="$T_TMPDIR/mnt.scratch"
 mkdir -p "$SCR"
 mount -t scoutfs -o metadev_path=$T_EX_META_DEV,quorum_slot_nr=0 \
 	"$T_EX_DATA_DEV" "$SCR"

tests/tests/simple-inode-index.sh

@@ -103,4 +103,34 @@ while [ "$nr" -lt 100 ]; do
 	((nr++))
 done
 
+#
+# make sure rapid concurrent metadata updates don't create multiple
+# meta_seq entries
+#
+# we had a bug where deletion items created under concurrent_write locks
+# could get versions older than the items they're deleting which were
+# protected by read/write locks.
+#
+echo "== concurrent update attempts maintain single entries"
+FILES=4
+nr=1
+while [ "$nr" -lt 10 ]; do
+	# touch a bunch of files in parallel from all mounts
+	for i in $(t_fs_nrs); do
+		eval path="\$T_D${i}"
+		seq -f "$path/file-%.0f" 1 $FILES | xargs touch &
+	done
+	wait || t_fail "concurrent file updates failed"
+
+	# make sure no inodes have duplicate entries
+	sync
+	scoutfs walk-inodes -p "$T_D0" meta_seq -- 0 -1 | \
+		grep -v "minor" | \
+		awk '{print $4}' | \
+		sort -n | uniq -c | \
+		awk '($1 != 1)' | \
+		sort -n
+	((nr++))
+done
+
 t_pass

tests/tests/simple-xattr-unit.sh

@@ -36,7 +36,8 @@ test_xattr_lengths() {
 	else
 		echo "$name=\"$val\"" > "$T_TMP.good"
 	fi
-	cmp "$T_TMP.good" "$T_TMP.got" || exit 1
+	cmp "$T_TMP.good" "$T_TMP.got" || \
+		t_fail "cmp failed name len $name_len val len $val_len"
 
 	setfattr -x $name "$FILE"
 }

tests/tests/stage-tmpfile.sh

@@ -1,15 +0,0 @@
-#
-# Run tmpfile_stage and check the output with hexdump.
-#
-
-t_require_commands stage_tmpfile hexdump
-
-DEST_FILE="$T_D0/dest_file"
-
-stage_tmpfile $T_D0 $DEST_FILE
-
-hexdump -C "$DEST_FILE"
-
-rm -fr "$DEST_FILE"
-
-t_pass

tests/tests/xfstests.sh

@@ -65,7 +65,6 @@ generic/030	# mmap missing
 generic/075	# file content mismatch failures (fds, etc)
 generic/080	# mmap missing
 generic/103	# enospc causes trans commit failures
-generic/105	# needs trigage: something about acls
 generic/108	# mount fails on failing device?
 generic/112	# file content mismatch failures (fds, etc)
 generic/120	# (can't exec 'cause no mmap)
@@ -73,17 +72,14 @@ generic/126	# (can't exec 'cause no mmap)
 generic/141	# mmap missing
 generic/213	# enospc causes trans commit failures
 generic/215	# mmap missing
-generic/237	# wrong error return from failing setfacl?
 generic/246	# mmap missing
 generic/247	# mmap missing
 generic/248	# mmap missing
-generic/319	# utils output change?  update branch?
 generic/321	# requires selinux enabled for '+' in ls?
 generic/325	# mmap missing
 generic/338	# BUG_ON update inode error handling
 generic/346	# mmap missing
 generic/347	# _dmthin_mount doesn't work?
-generic/375	# utils output change?  update branch?
 EOF
 
 t_restore_output

utils/man/scoutfs.5

@@ -15,12 +15,61 @@ general mount options described in the
 .BR mount (8)
 manual page.
 .TP
+.B acl
+The acl mount option enables support for POSIX Access Control Lists
+as detailed in
+.BR acl (5) .
+Support for POSIX ACLs is the default.
+.TP
+.B data_prealloc_blocks=<blocks>
+Set the size of preallocation regions of data files, in 4KiB blocks.
+Writes to these regions that contain no extents will attempt to
+preallocate the size of the full region.  This can waste a lot of space
+with small files, files with sparse regions, and files whose final
+length isn't a multiple of the preallocation size.  The following
+data_prealloc_contig_only option, which is the default, restricts this
+behaviour to waste less space.
+.sp
+All the preallocation options can be changed in an active mount by
+writing to their respective files in the options directory in the
+mount's sysfs directory.
+.sp
+It is worth noting that it is always more efficient in every way to use 
+.BR fallocate (2)
+to precisely allocate large extents for the resulting size of the file.
+Always attempt to enable it in software that supports it.
+.TP
+.B data_prealloc_contig_only=<0|1>
+This option, currently the default, limits file data preallocation in
+two ways.  First, it will only preallocate when extending a fully
+allocated file.  Second, it will limit the size of preallocation to the
+existing length of the file.  These limits reduce the amount of
+preallocation wasted per file at the cost of multiple initial extents in
+all files.  It only supports simple streaming writes, any other write
+pattern will not be recognized and could result in many fragmented
+extent allocations.
+.sp
+This option can be disabled to encourage large allocated extents
+regardless of write patterns.  This can be helpful if files are written
+with initial sparse regions (perhaps by multiple threads writing to
+different regions) and wasted space isn't an issue (perhaps because the
+file population contains few small files).
+.TP
 .B metadev_path=<device>
 The metadev_path option specifies the path to the block device that
 contains the filesystem's metadata.
 .sp
 This option is required.
 .TP
+.B noacl
+The noacl mount option disables the default support for POSIX Access
+Control Lists.  Any existing system.posix_acl_default and
+system.posix_acl_access extended attributes remain in inodes.   They
+will appear in listings from
+.BR listxattr (5)
+but specific retrieval or reomval operations will fail.  They will be
+used for enforcement again if ACL support is later enabled.
+.TP
 .B orphan_scan_delay_ms=<number>
 This option sets the average expected delay, in milliseconds, between
 each mount's scan of the global orphaned inode list.  Jitter is added to
@@ -36,6 +85,25 @@ the options directory in the mount's sysfs directory.  Writing a new
 value will cause the next pending orphan scan to be rescheduled
 with the newly written delay time.
 .TP
+.B quorum_heartbeat_timeout_ms=<number>
+This option sets the amount of time, in milliseconds, that a quorum
+member will wait without receiving heartbeat messages from the current
+leader before trying to take over as leader.  This setting is per-mount
+and only changes the behavior of that mount.
+.sp
+This determines how long it may take before a failed leader is replaced
+by a waiting quorum member.  Setting it too low may lead to spurious
+fencing as active leaders are prematurely replaced due to task or
+network delays that prevent the quorum members from promptly sending and
+receiving messages.  The ideal setting is the longest acceptable
+downtime during server failover.  The default is 10000 (10s) and it can
+not be less than 2000 greater than 60000.
+.sp
+This option can be changed in an active mount by writing to its file in
+the options directory in the mount's sysfs directory.  Writing a new
+value will take effect the next time the quorum agent receives a
+heartbeat message and sets the next timeout.
+.TP
 .B quorum_slot_nr=<number>
 The quorum_slot_nr option assigns a quorum member slot to the mount.
 The mount will use the slot assignment to claim exclusive ownership of

utils/man/scoutfs.8

@@ -76,6 +76,97 @@ run when the file system will not be mounted.
 .RE
 .PD
 
+.TP
+.BI "counters [-t|--table] SYSFS-DIR"
+.sp
+Display the counters and their values for a mounted ScoutFS filesystem.
+.RS 1.0i
+.PD 0
+.sp
+.TP
+.B SYSFS-DIR
+The mount's sysfs directory in which to find the
+.B counters/
+directory when then contains files for each counter.
+The sysfs directory is
+of the form
+.I /sys/fs/scoutfs/f.<fsid>.r.<rid>/
+\&.
+.TP
+.B "-t, --table"
+Format the counters into a columnar table that fills the width of the display
+instead of printing one counter per line.
+.RE
+.PD
+
+.TP
+.BI "data-waiting {-I|--inode} INODE-NUM {-B|--block} BLOCK-NUM [-p|--path PATH]"
+.sp
+Display all the files and blocks for which there is a task blocked waiting on
+offline data.
+.sp
+The results are sorted by the file's inode number and the
+logical block offset that is being waited on.
+.sp
+Each line of output describes a block in a file that has a task waiting
+and is formatted as:
+.I "ino <nr> iblock <nr> ops [str]"
+\&. The ops string indicates blocked operations seperated by commas and can
+include
+.B read
+for a read operation,
+.B write
+for a write operation, and
+.B change_size
+for a truncate or extending write.
+.RS 1.0i
+.PD 0
+.sp
+.TP
+.B "-I, --inode INODE-NUM"
+Start iterating over waiting tasks from the given inode number.
+Value of 0 will show all waiting tasks.
+.TP
+.B "-B, --block BLOCK-NUM"
+Start iterating over waiting tasks from the given logical block number
+in the starting inode.  Value of 0 will show blocks in the first inode
+and then continue to show all blocks with tasks waiting in all the
+remaining inodes.
+.TP
+.B "-p, --path PATH"
+A path within a ScoutFS filesystem.
+.RE
+.PD
+
+.TP
+.BI "data-wait-err {-I|--inode} INODE-NUM {-V|--version} VER-NUM {-F|--offset} OFF-NUM {-C|--count} COUNT {-O|--op} OP {-E|--err} ERR [-p|--path PATH]"
+.sp
+Return error from matching waiters.
+.RS 1.0i
+.PD 0
+.sp
+.TP
+.B "-C, --count COUNT"
+Count.
+.TP
+.B "-E, --err ERR"
+Error.
+.TP
+.B "-F, --offset OFF-NUM"
+Offset. May be expressed in bytes, or with KMGTP (Kibi, Mibi, etc.) size
+suffixes.
+.TP
+.B "-I, --inode INODE-NUM"
+Inode number.
+.TP
+.B "-O, --op OP"
+Operation. One of: "read", "write", "change_size".
+.TP
+.B "-p, --path PATH"
+A path within a ScoutFS filesystem.
+.RE
+.PD
+
 .TP
 .BI "df [-h|--human-readable] [-p|--path PATH]"
 .sp
@@ -93,6 +184,95 @@ A path within a ScoutFS filesystem.
 .RE
 .PD
 
+.TP
+.BI "get-allocated-inos [-i|--ino INO] [-s|--single] [-p|--path PATH]"
+.sp
+This debugging command prints allocated inode numbers.  It only prints
+inodes
+found in the group that contains the starting inode.  The printed inode
+numbers aren't necessarily reachable.  They could be anywhere in the
+process from being unlinked to finally deleted when their items
+were found.
+.RS 1.0i
+.PD 0
+.TP
+.sp
+.B "-i, --ino INO"
+The first 64bit inode number which could be printed.
+.TP
+.B "-s, --single"
+Only print the single starting inode when it is allocated, all other allocated
+inode numbers will be ignored.
+.TP
+.B "-p, --path PATH"
+A path within a ScoutFS filesystem.
+.RE
+.PD
+
+.TP
+.BI "get-referring-entries [-p|--path PATH] INO"
+.sp
+Find directory entries that reference an inode number.
+.sp
+Display all the directory entries that refer to a given inode.  Each
+entry includes the inode number of the directory that contains it, the
+d_off and d_type values for the entry as described by
+.BR readdir (3)
+, and the name of the entry.
+.RS 1.0i
+.PD 0
+.TP
+.sp
+.TP
+.B "-p, --path PATH"
+A path within a ScoutFS filesystem.
+.TP
+.B "INO"
+The inode number of the target inode.
+.RE
+.PD
+
+.TP
+.BI "ino-path INODE-NUM [-p|--path PATH]"
+.sp
+Display all paths that reference an inode number.
+.sp
+Ongoing filesystem changes, such as renaming a common parent of multiple paths,
+can cause displayed paths to be inconsistent.
+.RS 1.0i
+.PD 0
+.sp
+.TP
+.B "INODE-NUM"
+The inode number of the target inode.
+.TP
+.B "-p|--path PATH"
+A path within a ScoutFS filesystem.
+.RE
+.PD
+
+.TP
+.BI "list-hidden-xattrs FILE"
+.sp
+Display extended attributes starting with the
+.BR scoutfs.
+prefix and containing the
+.BR hide.
+tag
+which makes them invisible to
+.BR listxattr (2) .
+The names of each attribute are output, one per line.  Their order
+is not specified.
+.RS 1.0i
+.PD 0
+.TP
+.sp
+.B "FILE"
+The path to a file within a ScoutFS filesystem.  File permissions must allow
+reading.
+.RE
+.PD
+
 .TP
 .BI "mkfs META-DEVICE DATA-DEVICE {-Q|--quorum-slot} NR,ADDR,PORT [-m|--max-meta-size SIZE] [-d|--max-data-size SIZE] [-z|--data-alloc-zone-blocks BLOCKS] [-f|--force] [-A|--allow-small-size] [-V|--format-version VERS]"
 .sp
@@ -171,6 +351,79 @@ The range of supported versions is visible in the output of
 .RE
 .PD
 
+.TP
+.BI "prepare-empty-data-device {-c|--check} META-DEVICE DATA-DEVICE"
+.sp
+Prepare an unused device for use as the data device for an existing file
+system.  This will write an initialized super block to the specified
+data device, destroying any existing contents.  The specified metadata
+device will not be modified.  The file system must be fully unmounted
+and any client mount recovery must be complete.
+.sp
+The existing metadata device is read to ensure that it's safe to stop
+using the old data device.  The data block allocators must indicate that
+all data blocks are free.  If there are still data blocks referenced by
+files then the command will fail.  The contents of these files must be
+freed for the command to proceed.
+.sp
+A new super block is written to the new data device.  The device can
+then be used as the data device to mount the file system.  As this
+switch is made all client mounts must refer to the new device.  The old
+device is not modified and still contains a valid data super block that
+could be mounted, creating data device writes that wouldn't be read by
+mounts using the new device.
+.sp
+The number of data blocks available to the file system will not change
+as the new data device is used.  The new device must be large enough to
+store all the data blocks that were available on the old device.  If the
+new device is larger then its added capacity can be used by growing the
+new data device with the resize-devices command once it is mounted.
+.RS 1.0i
+.PD 0
+.TP
+.sp
+.B "-c, --check"
+Only check for errors that would prevent a new empty data device from
+being used.  No changes will be made to the data device.  If the data
+device is provided then its size will be checked to make sure that it is
+large enough.  This can be used to test the metadata for data references
+before destroying an old empty data device.
+.RE
+.PD
+
+.TP
+.BI "print {-S|--skip-likely-huge} META-DEVICE"
+.sp
+Prints out all of the metadata in the file system.  This makes no effort
+to ensure that the structures are consistent as they're traversed and
+can present structures that seem corrupt as they change as they're
+output.
+.RS 1.0i
+.PD 0
+.TP
+.sp
+.B "-S, --skip-likely-huge"
+Skip printing structures that are likely to be very large.  The
+structures that are skipped tend to be global and whose size tends to be
+related to the size of the volume.   Examples of skipped structures include
+the global fs items, srch files, and metadata and data
+allocators.  Similar structures that are not skipped are related to the
+number of mounts and are maintained at a relatively reasonable size.
+These include per-mount log trees, srch files, allocators, and the
+metadata allocators used by server commits.
+.sp
+Skipping the larger structures limits the print output to a relatively
+constant size rather than being a large multiple of the used metadata
+space of the volume making the output much more useful for inspection.
+.TP
+.B "META-DEVICE"
+The path to the metadata device for the filesystem whose metadata will be
+printed.  An attempt will be made to flush the host's buffer cache for
+this device with the BLKFLSBUF ioctl, or with posix_fadvise() if
+the path refers to a regular file.
+.RE
+.PD
+
 .TP
 .BI "resize-devices [-p|--path PATH] [-m|--meta-size SIZE] [-d|--data-size SIZE]"
 .sp
@@ -229,6 +482,92 @@ kibibytes, mebibytes, etc.
 .RE
 .PD
 
+.TP
+.BI "search-xattrs XATTR-NAME [-p|--path PATH]"
+.sp
+Display the inode numbers of inodes in the filesystem which may have
+an extended attribute with the given name.
+.sp
+The results may contain false positives.  The returned inode numbers
+should be checked to verify that the extended attribute is in fact
+present on the inode.
+.RS 1.0i
+.PD 0
+.TP
+.sp
+.B XATTR-NAME
+The full name of the extended attribute to search for as
+described in the
+.BR xattr (7)
+manual page.
+.TP
+.B "-p|--path PATH"
+A path within a ScoutFS filesystem.
+.RE
+.PD
+
+.TP
+.BI "setattr FILE [-d, --data-version=VERSION [-s, --size=SIZE [-o, --offline]]] [-t, --ctime=TIMESPEC]"
+.sp
+Set ScoutFS-specific attributes on a newly created zero-length file.
+.RS 1.0i
+.PD 0
+.sp
+.TP
+.B "-V, --data-version=VERSION"
+Set data version.
+.TP
+.B "-o, --offline"
+Set file contents as offline, not sparse. Requires
+.I --size
+option also be present.
+.TP
+.B "-s, --size=SIZE"
+Set file size. May be expressed in bytes, or with
+KMGTP (Kibi, Mibi, etc.) size suffixes. Requires
+.I --data-version
+option also be present.
+.TP
+.B "-t, --ctime=TIMESPEC"
+Set creation time using
+.I "<seconds-since-epoch>.<nanoseconds>"
+format.
+.RE
+.PD
+
+.TP
+.BI "stage ARCHIVE-FILE FILE {-V|--version} VERSION [-o, --offset OFF-NUM] [-l, --length LENGTH]"
+.sp
+.B Stage
+(i.e. return to online) the previously-offline contents of a file by copying a
+region from another file, the archive, and without updating regular inode
+metadata.  Any operations that are blocked by the existence of an offline
+region will proceed once the region has been staged.
+.RS 1.0i
+.PD 0
+.TP
+.sp
+.B "ARCHIVE-FILE"
+The source file for the file contents being staged.
+.TP
+.B "FILE"
+The regular file whose contents will be staged.
+.TP
+.B "-V, --version VERSION"
+The data_version of the contents to be staged.  It must match the
+current data_version of the file.
+.TP
+.B "-o, --offset OFF-NUM"
+The starting byte offset of the region to write.  May be expressed in bytes, or with
+KMGTP (Kibi, Mibi, etc.) size suffixes. Default is 0.
+.TP
+.B "-l, --length LENGTH"
+Length of range (bytes or KMGTP units) of file to stage. Default is the file's
+total size.
+.RE
+.PD
+
+.TP
 .BI "stat FILE [-s|--single-field FIELD-NAME]"
 .sp
 Display ScoutFS-specific metadata fields for the given file.
@@ -314,221 +653,6 @@ The total number of 4K data blocks in the filesystem.
 .RE
 .PD
 
-.TP
-.BI "counters [-t|--table] SYSFS-DIR"
-.sp
-Display the counters and their values for a mounted ScoutFS filesystem.
-.RS 1.0i
-.PD 0
-.sp
-.TP
-.B SYSFS-DIR
-The mount's sysfs directory in which to find the
-.B counters/
-directory when then contains files for each counter.
-The sysfs directory is
-of the form
-.I /sys/fs/scoutfs/f.<fsid>.r.<rid>/
-\&.
-.TP
-.B "-t, --table"
-Format the counters into a columnar table that fills the width of the display
-instead of printing one counter per line.
-.RE
-.PD
-
-.TP
-.BI "search-xattrs XATTR-NAME [-p|--path PATH]"
-.sp
-Display the inode numbers of inodes in the filesystem which may have
-an extended attribute with the given name.
-.sp
-The results may contain false positives.  The returned inode numbers
-should be checked to verify that the extended attribute is in fact
-present on the inode.
-.RS 1.0i
-.PD 0
-.TP
-.sp
-.B XATTR-NAME
-The full name of the extended attribute to search for as
-described in the
-.BR xattr (7)
-manual page.
-.TP
-.B "-p|--path PATH"
-A path within a ScoutFS filesystem.
-.RE
-.PD
-
-.TP
-.BI "list-hidden-xattrs FILE"
-.sp
-Display extended attributes starting with the
-.BR scoutfs.
-prefix and containing the
-.BR hide.
-tag
-which makes them invisible to
-.BR listxattr (2) .
-The names of each attribute are output, one per line.  Their order
-is not specified.
-.RS 1.0i
-.PD 0
-.TP
-.sp
-.B "FILE"
-The path to a file within a ScoutFS filesystem.  File permissions must allow
-reading.
-.RE
-.PD
-
-.TP
-.BI "walk-inodes {meta_seq|data_seq} FIRST-INODE LAST-INODE [-p|--path PATH]"
-.sp
-Walk an inode index in the file system and output the inode numbers
-that are found between the first and last positions in the index.
-.RS 1.0i
-.PD 0
-.sp
-.TP
-.BR meta_seq , data_seq
-Which index to walk.
-.TP
-.B "FIRST-INODE"
-An integer index value giving starting position of the index walk.
-.I 0
-is the first possible position.
-.TP
-.B "LAST-INODE"
-An integer index value giving the last position to include in the index walk.
-.I \-1
-can be given to indicate the last possible position.
-.TP
-.B "-p|--path PATH"
-A path within a ScoutFS filesystem.
-.RE
-.PD
-
-.TP
-.BI "ino-path INODE-NUM [-p|--path PATH]"
-.sp
-Display all paths that reference an inode number.
-.sp
-Ongoing filesystem changes, such as renaming a common parent of multiple paths,
-can cause displayed paths to be inconsistent.
-.RS 1.0i
-.PD 0
-.sp
-.TP
-.B "INODE-NUM"
-The inode number of the target inode.
-.TP
-.B "-p|--path PATH"
-A path within a ScoutFS filesystem.
-.RE
-.PD
-
-.TP
-.BI "data-waiting {-I|--inode} INODE-NUM {-B|--block} BLOCK-NUM [-p|--path PATH]"
-.sp
-Display all the files and blocks for which there is a task blocked waiting on
-offline data.
-.sp
-The results are sorted by the file's inode number and the
-logical block offset that is being waited on.
-.sp
-Each line of output describes a block in a file that has a task waiting
-and is formatted as:
-.I "ino <nr> iblock <nr> ops [str]"
-\&. The ops string indicates blocked operations seperated by commas and can
-include
-.B read
-for a read operation,
-.B write
-for a write operation, and
-.B change_size
-for a truncate or extending write.
-.RS 1.0i
-.PD 0
-.sp
-.TP
-.B "-I, --inode INODE-NUM"
-Start iterating over waiting tasks from the given inode number.
-Value of 0 will show all waiting tasks.
-.TP
-.B "-B, --block BLOCK-NUM"
-Start iterating over waiting tasks from the given logical block number
-in the starting inode.  Value of 0 will show blocks in the first inode
-and then continue to show all blocks with tasks waiting in all the
-remaining inodes.
-.TP
-.B "-p, --path PATH"
-A path within a ScoutFS filesystem.
-.RE
-.PD
-
-.TP
-.BI "data-wait-err {-I|--inode} INODE-NUM {-V|--version} VER-NUM {-F|--offset} OFF-NUM {-C|--count} COUNT {-O|--op} OP {-E|--err} ERR [-p|--path PATH]"
-.sp
-Return error from matching waiters.
-.RS 1.0i
-.PD 0
-.sp
-.TP
-.B "-C, --count COUNT"
-Count.
-.TP
-.B "-E, --err ERR"
-Error.
-.TP
-.B "-F, --offset OFF-NUM"
-Offset. May be expressed in bytes, or with KMGTP (Kibi, Mibi, etc.) size
-suffixes.
-.TP
-.B "-I, --inode INODE-NUM"
-Inode number.
-.TP
-.B "-O, --op OP"
-Operation. One of: "read", "write", "change_size".
-.TP
-.B "-p, --path PATH"
-A path within a ScoutFS filesystem.
-.RE
-.PD
-
-.TP
-.BI "stage ARCHIVE-FILE FILE {-V|--version} VERSION [-o, --offset OFF-NUM] [-l, --length LENGTH]"
-.sp
-.B Stage
-(i.e. return to online) the previously-offline contents of a file by copying a
-region from another file, the archive, and without updating regular inode
-metadata.  Any operations that are blocked by the existence of an offline
-region will proceed once the region has been staged.
-.RS 1.0i
-.PD 0
-.TP
-.sp
-.B "ARCHIVE-FILE"
-The source file for the file contents being staged.
-.TP
-.B "FILE"
-The regular file whose contents will be staged.
-.TP
-.B "-V, --version VERSION"
-The data_version of the contents to be staged.  It must match the
-current data_version of the file.
-.TP
-.B "-o, --offset OFF-NUM"
-The starting byte offset of the region to write.  May be expressed in bytes, or with
-KMGTP (Kibi, Mibi, etc.) size suffixes. Default is 0.
-.TP
-.B "-l, --length LENGTH"
-Length of range (bytes or KMGTP units) of file to stage. Default is the file's
-total size.
-.RE
-.PD
-
 .TP
 .BI "release FILE {-V|--version} VERSION [-o, --offset OFF-NUM] [-l, --length LENGTH]"
 .sp
@@ -568,76 +692,28 @@ total size.
 .PD
 
 .TP
-.BI "setattr FILE [-d, --data-version=VERSION [-s, --size=SIZE [-o, --offline]]] [-t, --ctime=TIMESPEC]"
+.BI "walk-inodes {meta_seq|data_seq} FIRST-INODE LAST-INODE [-p|--path PATH]"
 .sp
-Set ScoutFS-specific attributes on a newly created zero-length file.
+Walk an inode index in the file system and output the inode numbers
+that are found between the first and last positions in the index.
 .RS 1.0i
 .PD 0
 .sp
 .TP
-.B "-V, --data-version=VERSION"
-Set data version.
+.BR meta_seq , data_seq
+Which index to walk.
 .TP
-.B "-o, --offline"
-Set file contents as offline, not sparse. Requires
-.I --size
-option also be present.
+.B "FIRST-INODE"
+An integer index value giving starting position of the index walk.
+.I 0
+is the first possible position.
 .TP
-.B "-s, --size=SIZE"
-Set file size. May be expressed in bytes, or with
-KMGTP (Kibi, Mibi, etc.) size suffixes. Requires
-.I --data-version
-option also be present.
+.B "LAST-INODE"
+An integer index value giving the last position to include in the index walk.
+.I \-1
+can be given to indicate the last possible position.
 .TP
-.B "-t, --ctime=TIMESPEC"
-Set creation time using
-.I "<seconds-since-epoch>.<nanoseconds>"
-format.
-.RE
-.PD
-
-.TP
-.BI "print META-DEVICE"
-.sp
-Prints out all of the metadata in the file system.  This makes no effort
-to ensure that the structures are consistent as they're traversed and
-can present structures that seem corrupt as they change as they're
-output.
-.RS 1.0i
-.PD 0
-.TP
-.sp
-.B "META-DEVICE"
-The path to the metadata device for the filesystem whose metadata will be
-printed.  Since this command reads via the host's buffer cache, it may not
-reflect the current blocks in the filesystem possibly written to the shared
-block devices from another host, unless
-.B blockdev \--flushbufs
-command is used first.
-.RE
-.PD
-
-.TP
-.BI "get-allocated-inos [-i|--ino INO] [-s|--single] [-p|--path PATH]"
-.sp
-This debugging command prints allocated inode numbers.  It only prints
-inodes
-found in the group that contains the starting inode.  The printed inode
-numbers aren't necessarily reachable.  They could be anywhere in the
-process from being unlinked to finally deleted when their items
-were found.
-.RS 1.0i
-.PD 0
-.TP
-.sp
-.B "-i, --ino INO"
-The first 64bit inode number which could be printed.
-.TP
-.B "-s, --single"
-Only print the single starting inode when it is allocated, all other allocated
-inode numbers will be ignored.
-.TP
-.B "-p, --path PATH"
+.B "-p|--path PATH"
 A path within a ScoutFS filesystem.
 .RE
 .PD

utils/src/dev.c

@@ -3,6 +3,7 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>
+#include <fcntl.h>
 #include <sys/ioctl.h>
 #include <linux/fs.h>
 #include <errno.h>
@@ -11,13 +12,10 @@
 #include "sparse.h"
 #include "dev.h"
 
-int device_size(char *path, int fd,
-		u64 min_size, u64 max_size, bool allow_small_size,
-		char *use_type, u64 *size_ret)
+int get_device_size(char *path, int fd, u64 *size_ret)
 {
 	struct stat st;
 	u64 size;
-	char *target_type;
 	int ret;
 
 	if (fstat(fd, &st)) {
@@ -29,7 +27,6 @@ int device_size(char *path, int fd,
 
 	if (S_ISREG(st.st_mode)) {
 		size = st.st_size;
-		target_type = "file";
 	} else if (S_ISBLK(st.st_mode)) {
 		if (ioctl(fd, BLKGETSIZE64, &size)) {
 			ret = -errno;
@@ -37,13 +34,26 @@ int device_size(char *path, int fd,
 				path, strerror(errno), errno);
 			return ret;
 		}
-		target_type = "device";
 	} else {
 		fprintf(stderr, "path isn't regular or device file '%s'\n",
 			path);
 		return -EINVAL;
 	}
 
+	*size_ret = size;
+	return 0;
+}
+
+int limit_device_size(char *path, int fd, u64 min_size, u64 max_size, bool allow_small_size,
+		      char *use_type, u64 *size_ret)
+{
+	u64 size;
+	int ret;
+
+	ret = get_device_size(path, fd, &size);
+	if (ret < 0)
+		return ret;
+
 	if (max_size) {
 		if (size > max_size) {
 			printf("Limiting use of "BASE_SIZE_FMT
@@ -63,9 +73,9 @@ int device_size(char *path, int fd,
 
 	if (size < min_size) {
 		fprintf(stderr,
-			BASE_SIZE_FMT" %s too small for min "
+			BASE_SIZE_FMT" too small for min "
 			BASE_SIZE_FMT" %s device%s\n",
-			BASE_SIZE_ARGS(size), target_type,
+			BASE_SIZE_ARGS(size),
 			BASE_SIZE_ARGS(min_size), use_type,
 			allow_small_size ? ", allowing with -A" : "");
 
@@ -103,3 +113,44 @@ char *size_str(u64 nr, unsigned size)
 
 	return suffixes[i];
 }
+
+/*
+ * Try to flush the local read cache for a device.  This is only a best
+ * effort as these interfaces don't block waiting to fully purge the
+ * cache.  This is OK because it's used by cached readers that are known
+ * to be racy anyway.
+ */
+int flush_device(int fd)
+{
+	struct stat st;
+	int ret;
+
+	ret = fstat(fd, &st);
+	if (ret < 0) {
+		ret = -errno;
+		fprintf(stderr, "fstat failed: %s (%d)\n", strerror(errno), errno);
+		goto out;
+	}
+
+	if (S_ISREG(st.st_mode)) {
+		ret = posix_fadvise(fd, 0, st.st_size, POSIX_FADV_DONTNEED);
+		if (ret < 0) {
+			ret = -errno;
+			fprintf(stderr, "POSIX_FADV_DONTNEED failed: %s (%d)\n",
+				strerror(errno), errno);
+			goto out;
+		}
+
+	} else if (S_ISBLK(st.st_mode)) {
+		ret = ioctl(fd, BLKFLSBUF, 0);
+		if (ret < 0) {
+			ret = -errno;
+			fprintf(stderr, "BLKFLSBUF, failed: %s (%d)\n", strerror(errno), errno);
+			goto out;
+		}
+	}
+
+	ret = 0;
+out:
+	return ret;
+}

utils/src/dev.h

@@ -9,10 +9,11 @@
 #define SIZE_FMT "%llu (%.2f %s)"
 #define SIZE_ARGS(nr, sz) (nr), size_flt(nr, sz), size_str(nr, sz)
 
-int device_size(char *path, int fd,
-		u64 min_size, u64 max_size, bool allow_small_size,
-		char *use_type, u64 *size_ret);
+int get_device_size(char *path, int fd, u64 *size_ret);
+int limit_device_size(char *path, int fd, u64 min_size, u64 max_size, bool allow_small_size,
+		      char *use_type, u64 *size_ret);
 float size_flt(u64 nr, unsigned size);
 char *size_str(u64 nr, unsigned size);
+int flush_device(int fd);
 
 #endif

utils/src/get_referring_entries.c

@@ -0,0 +1,150 @@
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/ioctl.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <string.h>
+#include <limits.h>
+#include <argp.h>
+
+#include "sparse.h"
+#include "parse.h"
+#include "util.h"
+#include "format.h"
+#include "ioctl.h"
+#include "parse.h"
+#include "cmd.h"
+
+struct gre_args {
+	char *path;
+	u64 ino;
+};
+
+static int do_get_referring_entries(struct gre_args *args)
+{
+	struct scoutfs_ioctl_get_referring_entries gre;
+	struct scoutfs_ioctl_dirent *dent;
+	unsigned int bytes;
+	void *buf;
+	int ret;
+	int fd;
+
+	fd = get_path(args->path, O_RDONLY);
+	if (fd < 0)
+		return fd;
+
+	bytes = PATH_MAX * 1024;
+	buf = malloc(bytes);
+	if (!buf) {
+		fprintf(stderr, "couldn't allocate %u byte buffer\n", bytes);
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	gre.ino = args->ino;
+	gre.dir_ino = 0;
+	gre.dir_pos = 0;
+	gre.entries_ptr = (intptr_t)buf;
+	gre.entries_bytes = bytes;
+
+	for (;;) {
+		ret = ioctl(fd, SCOUTFS_IOC_GET_REFERRING_ENTRIES, &gre);
+		if (ret <= 0) {
+			if (ret < 0) {
+				ret = -errno;
+				fprintf(stderr, "ioctl failed: %s (%d)\n", strerror(errno), errno);
+			}
+			goto out;
+		}
+
+		dent = buf;
+		while (ret-- > 0) {
+			printf("dir %llu pos %llu type %u name %s\n",
+			       dent->dir_ino, dent->dir_pos, dent->d_type, dent->name);
+
+			gre.dir_ino = dent->dir_ino;
+			gre.dir_pos = dent->dir_pos;
+
+			if (dent->flags & SCOUTFS_IOCTL_DIRENT_FLAG_LAST) {
+				ret = 0;
+				goto out;
+			}
+
+			dent = (void *)dent + dent->entry_bytes;
+		}
+
+		if (++gre.dir_pos == 0) {
+			if (++gre.dir_ino == 0) {
+				ret = 0;
+				goto out;
+			}
+		}
+	}
+
+out:
+	close(fd);
+	free(buf);
+
+	return ret;
+};
+
+static int parse_opt(int key, char *arg, struct argp_state *state)
+{
+	struct gre_args *args = state->input;
+	int ret;
+
+	switch (key) {
+	case 'p':
+		args->path = strdup_or_error(state, arg);
+		break;
+	case ARGP_KEY_ARG:
+		if (args->ino)
+			argp_error(state, "more than one argument given");
+		ret = parse_u64(arg, &args->ino);
+		if (ret)
+			argp_error(state, "inode parse error");
+		break;
+	case ARGP_KEY_FINI:
+		if (!args->ino) {
+			argp_error(state, "must provide inode number");
+		}
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static struct argp_option options[] = {
+	{ "path", 'p', "PATH", 0, "Path to ScoutFS filesystem"},
+	{ NULL }
+};
+
+static struct argp argp = {
+	options,
+	parse_opt,
+	"INODE-NUM",
+	"Print directory entries that refer to inode number"
+};
+
+static int get_referring_entries_cmd(int argc, char **argv)
+{
+	struct gre_args args = {NULL};
+	int ret;
+
+	ret = argp_parse(&argp, argc, argv, 0, NULL, &args);
+	if (ret)
+		return ret;
+
+	return do_get_referring_entries(&args);
+}
+
+
+static void __attribute__((constructor)) get_referring_entries_ctor(void)
+{
+	cmd_register_argp("get-referring-entries", &argp, GROUP_SEARCH, get_referring_entries_cmd);
+}

utils/src/mkfs.c

@@ -118,6 +118,33 @@ struct mkfs_args {
 	struct scoutfs_quorum_slot slots[SCOUTFS_QUORUM_MAX_SLOTS];
 };
 
+static int open_mkfs_dev(struct mkfs_args *args, char *path, mode_t mode, char *which)
+{
+	int ret;
+	int fd = -1;
+
+	fd = open(path, mode);
+	if (fd < 0) {
+		ret = -errno;
+		fprintf(stderr, "failed to open %s dev '%s': %s (%d)\n",
+			which, path, strerror(errno), errno);
+		goto out;
+	}
+
+	ret = flush_device(fd);
+	if (ret < 0)
+		goto out;
+
+	if (!args->force)
+		ret = check_bdev(fd, path, which);
+
+out:
+	if (ret < 0 && fd >= 0)
+		close(fd);
+
+	return ret ?: fd;
+}
+
 /*
  * Make a new file system by writing:
  *  - super blocks
@@ -156,32 +183,17 @@ static int do_mkfs(struct mkfs_args *args)
 	gettimeofday(&tv, NULL);
 	pseudo_random_bytes(&fsid, sizeof(fsid));
 
-	meta_fd = open(args->meta_device, O_RDWR | O_EXCL);
+	meta_fd = open_mkfs_dev(args, args->meta_device, O_RDWR | O_EXCL, "meta");
 	if (meta_fd < 0) {
-		ret = -errno;
-		fprintf(stderr, "failed to open '%s': %s (%d)\n",
-			args->meta_device, strerror(errno), errno);
+		ret = meta_fd;
 		goto out;
 	}
-	if (!args->force) {
-		ret = check_bdev(meta_fd, args->meta_device, "meta");
-		if (ret)
-			return ret;
-	}
 
-	data_fd = open(args->data_device, O_RDWR | O_EXCL);
+	data_fd = open_mkfs_dev(args, args->data_device, O_RDWR | O_EXCL, "data");
 	if (data_fd < 0) {
-		ret = -errno;
-		fprintf(stderr, "failed to open '%s': %s (%d)\n",
-			args->data_device, strerror(errno), errno);
+		ret = data_fd;
 		goto out;
 	}
-	if (!args->force) {
-		ret = check_bdev(data_fd, args->data_device, "data");
-		if (ret)
-			return ret;
-	}
-
 
 	super = calloc(1, SCOUTFS_BLOCK_SM_SIZE);
 	bt = calloc(1, SCOUTFS_BLOCK_LG_SIZE);
@@ -194,14 +206,14 @@ static int do_mkfs(struct mkfs_args *args)
 	}
 
 	/* minumum meta device size to make reserved blocks reasonably large */
-	ret = device_size(args->meta_device, meta_fd, 64ULL * (1024 * 1024 * 1024),
-			  args->max_meta_size, args->allow_small_size, "meta", &meta_size);
+	ret = limit_device_size(args->meta_device, meta_fd, 64ULL * (1024 * 1024 * 1024),
+				args->max_meta_size, args->allow_small_size, "meta", &meta_size);
 	if (ret)
 		goto out;
 
 	/* .. then arbitrarily the same minimum data device size */
-	ret = device_size(args->data_device, data_fd, 64ULL * (1024 * 1024 * 1024),
-			  args->max_data_size, args->allow_small_size, "data", &data_size);
+	ret = limit_device_size(args->data_device, data_fd, 64ULL * (1024 * 1024 * 1024),
+				args->max_data_size, args->allow_small_size, "data", &data_size);
 	if (ret)
 		goto out;
 

utils/src/prepare_empty_data_device.c

@@ -0,0 +1,247 @@
+#define _GNU_SOURCE /* O_DIRECT */
+#include <unistd.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <sys/time.h>
+#include <uuid/uuid.h>
+#include <fcntl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <assert.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <ctype.h>
+#include <inttypes.h>
+#include <argp.h>
+
+#include "sparse.h"
+#include "cmd.h"
+#include "util.h"
+#include "format.h"
+#include "parse.h"
+#include "crc.h"
+#include "rand.h"
+#include "dev.h"
+#include "key.h"
+#include "bitops.h"
+#include "btree.h"
+#include "leaf_item_hash.h"
+#include "blkid.h"
+#include "quorum.h"
+
+struct prepare_empty_data_dev_args {
+	char *meta_device;
+	char *data_device;
+	bool check;
+};
+
+static int do_prepare_empty_data_dev(struct prepare_empty_data_dev_args *args)
+{
+	struct scoutfs_super_block *meta_super = NULL;
+	struct scoutfs_super_block *data_super = NULL;
+	char uuid_str[37];
+	int meta_fd = -1;
+	int data_fd = -1;
+	u64 data_blocks;
+	u64 data_size;
+	u64 in_use;
+	int ret;
+
+	ret = posix_memalign((void **)&data_super, SCOUTFS_BLOCK_SM_SIZE, SCOUTFS_BLOCK_SM_SIZE);
+	if (ret < 0) {
+		ret = -errno;
+		fprintf(stderr, "failed to allocate data super block: %s (%d)\n",
+			strerror(errno), errno);
+		goto out;
+	}
+
+	meta_fd = open(args->meta_device, O_DIRECT | O_SYNC | O_RDONLY | O_EXCL);
+	if (meta_fd < 0) {
+		ret = -errno;
+		fprintf(stderr, "failed to open meta device '%s': %s (%d)\n",
+			args->meta_device, strerror(errno), errno);
+		goto out;
+	}
+
+	ret = read_block_verify(meta_fd, SCOUTFS_BLOCK_MAGIC_SUPER, 0, SCOUTFS_SUPER_BLKNO,
+				SCOUTFS_BLOCK_SM_SHIFT, (void **)&meta_super);
+	if (ret) {
+		ret = -errno;
+		fprintf(stderr, "failed to read meta super block: %s (%d)\n",
+			strerror(errno), errno);
+		goto out;
+	}
+
+	ret = meta_super_in_use(meta_fd, meta_super);
+	if (ret < 0) {
+		if (ret == -EBUSY)
+			fprintf(stderr, "The filesystem must be fully recovered and cleanly unmounted to determine if the data device is empty.\n");
+		goto out;
+	}
+
+	in_use = (le64_to_cpu(meta_super->total_data_blocks) - SCOUTFS_DATA_DEV_START_BLKNO) -
+		 le64_to_cpu(meta_super->data_alloc.total_len);
+	if (in_use) {
+		fprintf(stderr, "Data block allocator metadata shows "SIZE_FMT" data blocks used by files.  They must be removed, truncated, or released before a new empty data device can be used.\n",
+		       SIZE_ARGS(in_use, SCOUTFS_BLOCK_SM_SIZE));
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (args->data_device) {
+		data_fd = open(args->data_device, O_DIRECT | O_EXCL |
+						  (args->check ? O_RDONLY : O_RDWR | O_SYNC));
+		if (data_fd < 0) {
+			ret = -errno;
+			fprintf(stderr, "failed to open data device '%s': %s (%d)\n",
+				args->data_device, strerror(errno), errno);
+			goto out;
+		}
+
+		ret = get_device_size(args->data_device, data_fd, &data_size);
+		if (ret < 0)
+			goto out;
+
+		data_blocks = data_size >> SCOUTFS_BLOCK_SM_SHIFT;
+
+		if (data_blocks < le64_to_cpu(meta_super->total_data_blocks)) {
+			fprintf(stderr, "new data device %s of size "BASE_SIZE_FMT" has %llu 4KiB blocks, it needs at least "SIZE_FMT" blocks.\n",
+			       args->data_device,
+			       BASE_SIZE_ARGS(data_size),
+			       data_blocks,
+			       SIZE_ARGS(le64_to_cpu(meta_super->total_data_blocks),
+					  SCOUTFS_BLOCK_SM_SIZE));
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+	if (args->check) {
+		ret = 0;
+		goto out;
+	}
+
+	/* the data device superblock only needs fs identifying fields */
+	memset(data_super, 0, sizeof(struct scoutfs_super_block));
+	data_super->id = meta_super->id;
+	data_super->fmt_vers = meta_super->fmt_vers;
+	data_super->flags = meta_super->flags &~ cpu_to_le64(SCOUTFS_FLAG_IS_META_BDEV);
+	memcpy(data_super->uuid, meta_super->uuid,sizeof(data_super->uuid));
+	data_super->seq = meta_super->seq;
+	data_super->total_meta_blocks = meta_super->total_meta_blocks;
+	data_super->total_data_blocks = meta_super->total_data_blocks;
+
+	ret = write_block(data_fd, SCOUTFS_BLOCK_MAGIC_SUPER, meta_super->hdr.fsid, 1,
+			  SCOUTFS_SUPER_BLKNO, SCOUTFS_BLOCK_SM_SHIFT, &data_super->hdr);
+	if (ret < 0) {
+		ret = -errno;
+		fprintf(stderr, "Error writing super block to new data device '%s': %s (%d)\n",
+			args->data_device, strerror(errno), errno);
+		goto out;
+	}
+
+	uuid_unparse(meta_super->uuid, uuid_str);
+
+	printf("Successfully initialized empty data device for scoutfs filesystem:\n"
+	       "  meta device path:       %s\n"
+	       "  data device path:       %s\n"
+	       "  fsid:                   %llx\n"
+	       "  uuid:                   %s\n"
+	       "  format version:         %llu\n"
+	       "  64KB metadata blocks:   "SIZE_FMT"\n"
+	       "  4KB data blocks:        "SIZE_FMT"\n",
+		args->meta_device,
+	        args->data_device,
+		le64_to_cpu(meta_super->hdr.fsid),
+		uuid_str,
+		le64_to_cpu(meta_super->fmt_vers),
+		SIZE_ARGS(le64_to_cpu(meta_super->total_meta_blocks),
+			  SCOUTFS_BLOCK_LG_SIZE),
+		SIZE_ARGS(le64_to_cpu(meta_super->total_data_blocks),
+			  SCOUTFS_BLOCK_SM_SIZE));
+
+	ret = 0;
+out:
+	if (args->check) {
+		if (ret == 0)
+			printf("All checks passed.\n");
+		else
+			printf("Errors were found that must be addressed before a new empty data device could be prepared and used.\n");
+	}
+
+	if (meta_super)
+		free(meta_super);
+	if (data_super)
+		free(data_super);
+	if (meta_fd != -1)
+		close(meta_fd);
+	if (data_fd != -1)
+		close(data_fd);
+	return ret;
+}
+
+static int parse_opt(int key, char *arg, struct argp_state *state)
+{
+	struct prepare_empty_data_dev_args *args = state->input;
+
+	switch (key) {
+	case 'c':
+		args->check = true;
+		break;
+	case ARGP_KEY_ARG:
+		if (!args->meta_device)
+			args->meta_device = strdup_or_error(state, arg);
+		else if (!args->data_device)
+			args->data_device = strdup_or_error(state, arg);
+		else
+			argp_error(state, "more than two device arguments given");
+		break;
+	case ARGP_KEY_FINI:
+		if (!args->meta_device)
+			argp_error(state, "no metadata device argument given");
+		if (!args->data_device && !args->check)
+			argp_error(state, "no data device argument given");
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static struct argp_option options[] = {
+	{ "check", 'c', NULL, 0, "Only check for errors and do not write", },
+	{ NULL }
+};
+
+static struct argp argp = {
+	options,
+	parse_opt,
+	"META-DEVICE DATA-DEVICE",
+	"Prepare empty data device for use with an existing ScoutFS filesystem"
+};
+
+static int prepare_empty_data_dev_cmd(int argc, char *argv[])
+{
+	struct prepare_empty_data_dev_args prepare_empty_data_dev_args = { 
+		.check = false,
+	};
+	int ret;
+
+	ret = argp_parse(&argp, argc, argv, 0, NULL, &prepare_empty_data_dev_args);
+	if (ret)
+		return ret;
+
+	return do_prepare_empty_data_dev(&prepare_empty_data_dev_args);
+}
+
+static void __attribute__((constructor)) prepare_empty_data_dev_ctor(void)
+{
+	cmd_register_argp("prepare-empty-data-device", &argp, GROUP_CORE,
+			  prepare_empty_data_dev_cmd);
+}

utils/src/print.c

@@ -8,6 +8,7 @@
 #include <errno.h>
 #include <string.h>
 #include <stdarg.h>
+#include <stdbool.h>
 #include <ctype.h>
 #include <uuid/uuid.h>
 #include <sys/socket.h>
@@ -26,6 +27,7 @@
 #include "avl.h"
 #include "srch.h"
 #include "leaf_item_hash.h"
+#include "dev.h"
 
 static void print_block_header(struct scoutfs_block_header *hdr, int size)
 {
@@ -989,9 +991,10 @@ static void print_super_block(struct scoutfs_super_block *super, u64 blkno)
 
 struct print_args {
 	char *meta_device;
+	bool skip_likely_huge;
 };
 
-static int print_volume(int fd)
+static int print_volume(int fd, struct print_args *args)
 {
 	struct scoutfs_super_block *super = NULL;
 	struct print_recursion_args pa;
@@ -1041,23 +1044,26 @@ static int print_volume(int fd)
 			ret = err;
 	}
 
-	for (i = 0; i < array_size(super->meta_alloc); i++) {
-		snprintf(str, sizeof(str), "meta_alloc[%u]", i);
-		err = print_btree(fd, super, str, &super->meta_alloc[i].root,
+	if (!args->skip_likely_huge) {
+		for (i = 0; i < array_size(super->meta_alloc); i++) {
+			snprintf(str, sizeof(str), "meta_alloc[%u]", i);
+			err = print_btree(fd, super, str, &super->meta_alloc[i].root,
+					  print_alloc_item, NULL);
+			if (err && !ret)
+				ret = err;
+		}
+
+		err = print_btree(fd, super, "data_alloc", &super->data_alloc.root,
 				  print_alloc_item, NULL);
 		if (err && !ret)
 			ret = err;
 	}
 
-	err = print_btree(fd, super, "data_alloc", &super->data_alloc.root,
-			  print_alloc_item, NULL);
-	if (err && !ret)
-		ret = err;
-
 	err = print_btree(fd, super, "srch_root", &super->srch_root,
 			  print_srch_root_item, NULL);
 	if (err && !ret)
 		ret = err;
+
 	err = print_btree(fd, super, "logs_root", &super->logs_root,
 			  print_log_trees_item, NULL);
 	if (err && !ret)
@@ -1065,19 +1071,23 @@ static int print_volume(int fd)
 
 	pa.super = super;
 	pa.fd = fd;
-	err = print_btree_leaf_items(fd, super, &super->srch_root.ref,
-				     print_srch_root_files, &pa);
-	if (err && !ret)
-		ret = err;
+	if (!args->skip_likely_huge) {
+		err = print_btree_leaf_items(fd, super, &super->srch_root.ref,
+					     print_srch_root_files, &pa);
+		if (err && !ret)
+			ret = err;
+	}
 	err = print_btree_leaf_items(fd, super, &super->logs_root.ref,
 				     print_log_trees_roots, &pa);
 	if (err && !ret)
 		ret = err;
 
-	err = print_btree(fd, super, "fs_root", &super->fs_root,
-			  print_fs_item, NULL);
-	if (err && !ret)
-		ret = err;
+	if (!args->skip_likely_huge) {
+		err = print_btree(fd, super, "fs_root", &super->fs_root,
+				  print_fs_item, NULL);
+		if (err && !ret)
+			ret = err;
+	}
 
 out:
 	free(super);
@@ -1098,7 +1108,12 @@ static int do_print(struct print_args *args)
 		return ret;
 	}
 
-	ret = print_volume(fd);
+	ret = flush_device(fd);
+	if (ret < 0)
+		goto out;
+
+	ret = print_volume(fd, args);
+out:
 	close(fd);
 	return ret;
 };
@@ -1108,6 +1123,9 @@ static int parse_opt(int key, char *arg, struct argp_state *state)
 	struct print_args *args = state->input;
 
 	switch (key) {
+	case 'S':
+		args->skip_likely_huge = true;
+		break;
 	case ARGP_KEY_ARG:
 		if (!args->meta_device)
 			args->meta_device = strdup_or_error(state, arg);
@@ -1125,8 +1143,13 @@ static int parse_opt(int key, char *arg, struct argp_state *state)
 	return 0;
 }
 
+static struct argp_option options[] = {
+	{ "skip-likely-huge", 'S', NULL, 0, "Skip large structures to minimize output size"},
+	{ NULL }
+};
+
 static struct argp argp = {
-	NULL,
+	options,
 	parse_opt,
 	"META-DEV",
 	"Print metadata structures"