Show last holder PID, inode in client_locks

Add last_user_pid[mode] and last_user_ino[mode] arrays to scoutfs_lock,
filled in at the granted-mode path alongside the existing counts.
The inode is passed by callers for all per-inode cases, and set to 0
for others. PID is from the current task.

The client_locks line is expanded with "ino: rd I wr I wo I pid: rd P
wr P wo P".  Existing users:/waiters: field positions are unchanged.

A simple test case demonstrates the functionality for the two simple
inode/non-inode case, and for a contended lock case (multiple rd/wr
lock holders).

Signed-off-by: Auke Kok <auke.kok@versity.com>

ReleaseNotes.md

@@ -1,20 +1,6 @@
 Versity ScoutFS Release Notes
 =============================
 
----
-v1.32
-\
-*June 2, 2026*
-
-Fix writing POSIX ACLs over NFS mounts that export the scoutfs
-filesystem.
-
-Add support for kernels in the RHEL 9.8 minor release.
-
-Reduce unneeded block allocation when data\_prealloc\_contig\_only was
-set to 0. This will help achieve more efficient data space usage when
-writing small files.
-
 ---
 v1.31
 \

kmod/src/Makefile.kernelcompat

@@ -6,6 +6,231 @@
 
 ccflags-y += -include $(src)/kernelcompat.h
 
+#
+# v3.18-rc2-19-gb5ae6b15bd73
+# 
+# Folds d_materialise_unique into d_splice_alias. Note reversal
+# of arguments (Also note Documentation/filesystems/porting.rst)
+#
+ifneq (,$(shell grep 'd_materialise_unique' include/linux/dcache.h))
+ccflags-y += -DKC_D_MATERIALISE_UNIQUE=1
+endif
+
+#
+# RHEL extended the fop struct so to use it we have to set
+# a flag to indicate that the struct is large enough and
+# contains the pointer.
+#
+ifneq (,$(shell grep 'FMODE_KABI_ITERATE' include/linux/fs.h))
+ccflags-y += -DKC_FMODE_KABI_ITERATE
+endif
+
+#
+# v4.7-rc2-23-g0d4d717f2583
+#
+# Added user_ns argument to posix_acl_valid
+#
+ifneq (,$(shell grep 'posix_acl_valid.*user_namespace' include/linux/posix_acl.h))
+ccflags-y += -DKC_POSIX_ACL_VALID_USER_NS
+endif
+
+#
+# v5.3-12296-g6d2052d188d9
+#
+# The RBCOMPUTE function is now passed an extra flag, and should return a bool
+# to indicate whether the propagated callback should stop or not.
+#
+ifneq (,$(shell grep 'static inline bool RBNAME.*_compute_max' include/linux/rbtree_augmented.h))
+ccflags-y += -DKC_RB_TREE_AUGMENTED_COMPUTE_MAX
+endif
+
+#
+# v3.13-25-g37bc15392a23
+#
+# Renames posix_acl_create to __posix_acl_create and provide some
+# new interfaces for creating ACLs
+#
+ifneq (,$(shell grep '__posix_acl_create' include/linux/posix_acl.h))
+ccflags-y += -DKC___POSIX_ACL_CREATE
+endif
+
+#
+# v4.8-rc1-29-g31051c85b5e2
+#
+# inode_change_ok() removed - replace with setattr_prepare()
+# v5.11-rc4-7-g2f221d6f7b88 removes extern attribute
+#
+ifneq (,$(shell grep 'int setattr_prepare' include/linux/fs.h))
+ccflags-y += -DKC_SETATTR_PREPARE
+endif
+
+#
+# v4.15-rc3-4-gae5e165d855d
+#
+# linux/iversion.h needs to manually be included for code that
+# manipulates this field.
+#
+ifneq (,$(shell grep -s 'define _LINUX_IVERSION_H' include/linux/iversion.h))
+ccflags-y += -DKC_NEED_LINUX_IVERSION_H=1
+endif
+
+# v4.11-12447-g104b4e5139fe
+#
+# Renamed __percpu_counter_add to percpu_counter_add_batch to clarify
+# that the __ wasn't less safe, just took an extra parameter.
+#
+ifneq (,$(shell grep 'percpu_counter_add_batch' include/linux/percpu_counter.h))
+ccflags-y += -DKC_PERCPU_COUNTER_ADD_BATCH
+endif
+
+#
+# v4.11-4550-g7dea19f9ee63
+#
+# Introduced memalloc_nofs_{save,restore} preferred instead of _noio_.
+#
+ifneq (,$(shell grep 'memalloc_nofs_save' include/linux/sched/mm.h))
+ccflags-y += -DKC_MEMALLOC_NOFS_SAVE
+endif
+
+#
+# v4.7-12414-g1eff9d322a44
+#
+# Renamed bi_rw to bi_opf to force old code to catch up.  We use it as a
+# single switch between old and new bio structures.
+#
+ifneq (,$(shell grep 'bi_opf' include/linux/blk_types.h))
+ccflags-y += -DKC_BIO_BI_OPF
+endif
+
+#
+# v4.12-rc2-201-g4e4cbee93d56
+#
+# Moves to bi_status BLK_STS_ API instead of having a mix of error
+# end_io args or bi_error.
+#
+ifneq (,$(shell grep 'bi_status' include/linux/blk_types.h))
+ccflags-y += -DKC_BIO_BI_STATUS
+endif
+
+#
+# v3.11-8765-ga0b02131c5fc
+#
+# Remove the old ->shrink() API, ->{scan,count}_objects is preferred.
+#
+ifneq (,$(shell grep '(*shrink)' include/linux/shrinker.h))
+ccflags-y += -DKC_SHRINKER_SHRINK
+endif
+
+#
+# v3.19-4777-g6bec00352861
+#
+# backing_dev_info is removed from address_space. Instead we need to use
+# inode_to_bdi() inline from <backing-dev.h>.
+#
+ifneq (,$(shell grep 'struct backing_dev_info.*backing_dev_info' include/linux/fs.h))
+ccflags-y += -DKC_LINUX_BACKING_DEV_INFO=1
+endif
+
+#
+# v4.3-9290-ge409de992e3e
+#
+# xattr handlers are now passed a struct that contains `flags`
+#
+ifneq (,$(shell grep 'int...get..const struct xattr_handler.*struct dentry.*dentry,' include/linux/xattr.h))
+ccflags-y += -DKC_XATTR_STRUCT_XATTR_HANDLER=1
+endif
+
+#
+# v4.16-rc1-1-g9b2c45d479d0
+#
+# kernel_getsockname() and kernel_getpeername dropped addrlen arg
+#
+ifneq (,$(shell grep 'kernel_getsockname.*,$$' include/linux/net.h))
+ccflags-y += -DKC_KERNEL_GETSOCKNAME_ADDRLEN=1
+endif
+
+#
+# v4.1-rc1-410-geeb1bd5c40ed
+#
+# Adds a struct net parameter to sock_create_kern
+#
+ifneq (,$(shell grep 'sock_create_kern.*struct net' include/linux/net.h))
+ccflags-y += -DKC_SOCK_CREATE_KERN_NET=1
+endif
+
+#
+# v4.17-rc6-7-g95582b008388
+#
+# Kernel has current_time(inode) to uniformly retreive timespec in the right unit
+#
+ifneq (,$(shell grep 'struct timespec64 current_time' include/linux/fs.h))
+ccflags-y += -DKC_CURRENT_TIME_INODE=1
+endif
+
+#
+# v4.9-12228-g530e9b76ae8f
+#
+# register_cpu_notifier and family were all removed and to be
+# replaced with cpuhp_* API calls.
+#
+ifneq (,$(shell grep 'define register_hotcpu_notifier' include/linux/cpu.h))
+ccflags-y += -DKC_CPU_NOTIFIER
+endif
+
+#
+# v3.14-rc8-130-gccad2365668f
+#
+# generic_file_buffered_write is removed, backport it
+#
+ifneq (,$(shell grep 'extern ssize_t generic_file_buffered_write' include/linux/fs.h))
+ccflags-y += -DKC_GENERIC_FILE_BUFFERED_WRITE=1
+endif
+
+#
+# v5.7-438-g8151b4c8bee4
+#
+# struct address_space_operations switches away from .readpages to .readahead
+#
+# RHEL has backported this feature all the way to RHEL8, as part of RHEL_KABI,
+# which means we need to detect this very precisely
+#
+ifneq (,$(shell grep 'readahead.*struct readahead_control' include/linux/fs.h))
+ccflags-y += -DKC_FILE_AOPS_READAHEAD
+endif
+
+#
+# v4.0-rc7-1743-g8436318205b9
+#
+# .aio_read and .aio_write no longer exist. All reads and writes now use the
+# .read_iter and .write_iter methods, or must implement .read and .write (which
+# we don't).
+#
+ifneq (,$(shell grep 'ssize_t.*aio_read' include/linux/fs.h))
+ccflags-y += -DKC_LINUX_HAVE_FOP_AIO_READ=1
+endif
+
+#
+# rhel7 has a custom inode_operations_wrapper struct that is discarded
+# entirely in favor of upstream structure since rhel8.
+#
+ifneq (,$(shell grep 'void.*follow_link.*struct dentry' include/linux/fs.h))
+ccflags-y += -DKC_LINUX_HAVE_RHEL_IOPS_WRAPPER=1
+endif
+
+ifneq (,$(shell grep 'size_t.*ki_left;' include/linux/aio.h))
+ccflags-y += -DKC_LINUX_AIO_KI_LEFT=1
+endif
+
+#
+# v4.4-rc4-4-g98e9cb5711c6
+#
+# Introduces a new xattr_handler .name member that can be used to match the
+# entire field, instead of just a prefix. For these kernels, we must use
+# the new .name field instead.
+ifneq (,$(shell grep 'static inline const char .xattr_prefix' include/linux/xattr.h))
+ccflags-y += -DKC_XATTR_HANDLER_NAME=1
+endif
+
 #
 # v5.19-rc4-96-g342a72a33407
 #
@@ -109,6 +334,14 @@ ifneq (,$(shell grep 'int tcp_sock_set_keepintvl' include/linux/tcp.h))
 ccflags-y += -DKC_HAVE_TCP_SET_SOCKFN
 endif
 
+#
+# v4.16-rc3-13-ga84d1169164b
+#
+# Fixes y2038 issues with struct timeval.
+ifneq (,$(shell grep -s '^struct __kernel_old_timeval .' include/uapi/linux/time_types.h))
+ccflags-y += -DKC_KERNEL_OLD_TIMEVAL_STRUCT
+endif
+
 #
 # v5.19-rc4-52-ge33c267ab70d
 #
@@ -178,6 +411,47 @@ ifneq (,$(shell grep 'struct file.*bdev_file_open_by_path.const char.*path' incl
 ccflags-y += -DKC_BDEV_FILE_OPEN_BY_PATH
 endif
 
+# v4.0-rc7-1796-gfe0f07d08ee3
+#
+# direct-io changes modify inode_dio_done to now be called inode_dio_end
+ifneq (,$(shell grep 'void inode_dio_end.struct inode' include/linux/fs.h))
+ccflags-y += -DKC_INODE_DIO_END
+endif
+
+#
+# v5.0-6476-g3d3539018d2c
+#
+# page fault handlers return a bitmask vm_fault_t instead
+# Note: el8's header has a slightly modified prefix here
+ifneq (,$(shell grep 'typedef.*__bitwise unsigned.*int vm_fault_t' include/linux/mm_types.h))
+ccflags-y += -DKC_MM_VM_FAULT_T
+endif
+
+# v3.19-499-gd83a08db5ba6
+#
+# .remap pages becomes obsolete
+ifneq (,$(shell grep 'int ..remap_pages..struct vm_area_struct' include/linux/mm.h))
+ccflags-y += -DKC_MM_REMAP_PAGES
+endif
+
+#
+# v3.19-4742-g503c358cf192
+#
+# list_lru_shrink_count() and list_lru_shrink_walk() introduced
+#
+ifneq (,$(shell grep 'list_lru_shrink_count.*struct list_lru' include/linux/list_lru.h))
+ccflags-y += -DKC_LIST_LRU_SHRINK_COUNT_WALK
+endif
+
+#
+# v3.19-4757-g3f97b163207c
+#
+# lru_list_walk_cb lru arg added
+#
+ifneq (,$(shell grep 'struct list_head \*item, spinlock_t \*lock, void \*cb_arg' include/linux/list_lru.h))
+ccflags-y += -DKC_LIST_LRU_WALK_CB_ITEM_LOCK
+endif
+
 #
 # v6.7-rc4-153-g0a97c01cd20b
 #
@@ -196,6 +470,15 @@ ifneq (,$(shell grep 'struct list_lru_one \*list, spinlock_t \*lock, void \*cb_a
 ccflags-y += -DKC_LIST_LRU_WALK_CB_LIST_LOCK
 endif
 
+#
+# v5.1-rc4-273-ge9b98e162aa5
+#
+# introduce stack trace helpers
+#
+ifneq (,$(shell grep '^unsigned int stack_trace_save' include/linux/stacktrace.h))
+ccflags-y += -DKC_STACK_TRACE_SAVE
+endif
+
 #
 # v6.1-rc1-2-g138060ba92b3
 #
@@ -213,12 +496,3 @@ endif
 ifneq (,$(shell grep 'struct posix_acl.*get_inode_acl' include/linux/fs.h))
 ccflags-y += -DKC_GET_INODE_ACL
 endif
-
-#
-# v6.15-13744-g41cb08555c41
-#
-# from_timer renamed to timer_container_of.
-#
-ifneq (,$(shell grep 'define timer_container_of' include/linux/timer.h))
-ccflags-y += -DKC_TIMER_CONTAINER_OF
-endif

kmod/src/acl.c

@@ -16,7 +16,6 @@
 #include <linux/xattr.h>
 #include <linux/posix_acl.h>
 #include <linux/posix_acl_xattr.h>
-#include <linux/iversion.h>
 
 #include "format.h"
 #include "super.h"
@@ -70,6 +69,15 @@ struct posix_acl *scoutfs_get_acl_locked(struct inode *inode, int type, struct s
 	char *name;
 	int ret;
 
+#ifndef KC___POSIX_ACL_CREATE
+	if (!IS_POSIXACL(inode))
+		return NULL;
+
+	acl = get_cached_acl(inode, type);
+	if (acl != ACL_NOT_CACHED)
+		return acl;
+#endif
+
 	ret = acl_xattr_name_len(type, &name, NULL);
 	if (ret < 0)
 		return ERR_PTR(ret);
@@ -115,6 +123,11 @@ struct posix_acl *scoutfs_get_acl(struct inode *inode, int type)
 		return ERR_PTR(-ECHILD);
 #endif
 
+#ifndef KC___POSIX_ACL_CREATE
+	if (!IS_POSIXACL(inode))
+		return NULL;
+#endif
+
 	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ, 0, inode, &lock);
 	if (ret < 0) {
 		acl = ERR_PTR(ret);
@@ -203,8 +216,7 @@ int scoutfs_set_acl(KC_VFS_NS_DEF
 {
 	struct inode *inode = dentry->d_inode;
 #else
-int scoutfs_set_acl(KC_VFS_NS_DEF
-		    struct inode *inode, struct posix_acl *acl, int type)
+int scoutfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
 #endif
 	struct super_block *sb = inode->i_sb;
@@ -227,11 +239,17 @@ int scoutfs_set_acl(KC_VFS_NS_DEF
 	scoutfs_unlock(sb, lock, SCOUTFS_LOCK_WRITE);
 	return ret;
 }
+#ifdef KC_XATTR_STRUCT_XATTR_HANDLER
 int scoutfs_acl_get_xattr(const struct xattr_handler *handler, struct dentry *dentry,
 			  struct inode *inode, const char *name, void *value,
 			  size_t size)
 {
 	int type = handler->flags;
+#else
+int scoutfs_acl_get_xattr(struct dentry *dentry, const char *name, void *value, size_t size,
+			  int type)
+{
+#endif
 	struct posix_acl *acl;
 	int ret = 0;
 
@@ -254,6 +272,7 @@ int scoutfs_acl_get_xattr(const struct xattr_handler *handler, struct dentry *de
 	return ret;
 }
 
+#ifdef KC_XATTR_STRUCT_XATTR_HANDLER
 int scoutfs_acl_set_xattr(const struct xattr_handler *handler,
 			  KC_VFS_NS_DEF
 			  struct dentry *dentry,
@@ -261,6 +280,11 @@ int scoutfs_acl_set_xattr(const struct xattr_handler *handler,
 			  size_t size, int flags)
 {
 	int type = handler->flags;
+#else
+int scoutfs_acl_set_xattr(struct dentry *dentry, const char *name, const void *value, size_t size,
+			  int flags, int type)
+{
+#endif
 	struct posix_acl *acl = NULL;
 	int ret;
 
@@ -276,7 +300,7 @@ int scoutfs_acl_set_xattr(const struct xattr_handler *handler,
 			return PTR_ERR(acl);
 
 		if (acl) {
-			ret = posix_acl_valid(&init_user_ns, acl);
+			ret = kc_posix_acl_valid(&init_user_ns, acl);
 			if (ret)
 				goto out;
 		}
@@ -285,7 +309,7 @@ int scoutfs_acl_set_xattr(const struct xattr_handler *handler,
 #ifdef KC_SET_ACL_DENTRY
 	ret = scoutfs_set_acl(KC_VFS_INIT_NS dentry, acl, type);
 #else
-	ret = scoutfs_set_acl(KC_VFS_INIT_NS dentry->d_inode, acl, type);
+	ret = scoutfs_set_acl(dentry->d_inode, acl, type);
 #endif
 out:
 	posix_acl_release(acl);

kmod/src/acl.h

@@ -5,8 +5,7 @@
 int scoutfs_set_acl(KC_VFS_NS_DEF
 		    struct dentry *dentry, struct posix_acl *acl, int type);
 #else
-int scoutfs_set_acl(KC_VFS_NS_DEF
-		    struct inode *inode, struct posix_acl *acl, int type);
+int scoutfs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
 #endif
 #ifdef KC_GET_INODE_ACL
 struct posix_acl *scoutfs_get_acl(struct inode *inode, int type, bool rcu);
@@ -16,6 +15,7 @@ struct posix_acl *scoutfs_get_acl(struct inode *inode, int type);
 struct posix_acl *scoutfs_get_acl_locked(struct inode *inode, int type, struct scoutfs_lock *lock);
 int scoutfs_set_acl_locked(struct inode *inode, struct posix_acl *acl, int type,
 			   struct scoutfs_lock *lock, struct list_head *ind_locks);
+#ifdef KC_XATTR_STRUCT_XATTR_HANDLER
 int scoutfs_acl_get_xattr(const struct xattr_handler *, struct dentry *dentry,
 			  struct inode *inode, const char *name, void *value,
 			  size_t size);
@@ -24,6 +24,12 @@ int scoutfs_acl_set_xattr(const struct xattr_handler *,
 			  struct dentry *dentry,
 			  struct inode *inode, const char *name, const void *value,
 			  size_t size, int flags);
+#else
+int scoutfs_acl_get_xattr(struct dentry *dentry, const char *name, void *value, size_t size,
+			  int type);
+int scoutfs_acl_set_xattr(struct dentry *dentry, const char *name, const void *value, size_t size,
+			  int flags, int type);
+#endif
 int scoutfs_acl_chmod_locked(struct inode *inode, struct iattr *attr,
 			     struct scoutfs_lock *lock, struct list_head *ind_locks);
 int scoutfs_init_acl_locked(struct inode *inode, struct inode *dir,

kmod/src/block.c

@@ -444,13 +444,13 @@ static void block_end_io(struct super_block *sb, blk_opf_t opf,
 		wake_up(&binf->waitq);
 }
 
-static void block_bio_end_io(struct bio *bio)
+static void KC_DECLARE_BIO_END_IO(block_bio_end_io, struct bio *bio)
 {
 	struct block_private *bp = bio->bi_private;
 	struct super_block *sb = bp->sb;
 
 	TRACE_BLOCK(end_io, bp);
-	block_end_io(sb, bio->bi_opf, bp, blk_status_to_errno(bio->bi_status));
+	block_end_io(sb, kc_bio_get_opf(bio), bp, kc_bio_get_errno(bio));
 	bio_put(bio);
 }
 
@@ -499,7 +499,7 @@ static int block_submit_bio(struct super_block *sb, struct block_private *bp,
 				break;
 			}
 
-			bio->bi_iter.bi_sector = sector + (off >> 9);
+			kc_bio_set_sector(bio, sector + (off >> 9));
 			bio->bi_end_io = block_bio_end_io;
 			bio->bi_private = bp;
 
@@ -516,13 +516,13 @@ static int block_submit_bio(struct super_block *sb, struct block_private *bp,
 			BUG();
 
 		if (!bio_add_page(bio, page, PAGE_SIZE, 0)) {
-			submit_bio(bio);
+			kc_submit_bio(bio);
 			bio = NULL;
 		}
 	}
 
 	if (bio)
-		submit_bio(bio);
+		kc_submit_bio(bio);
 
 	blk_finish_plug(&plug);
 
@@ -1179,11 +1179,11 @@ struct sm_block_completion {
 	int err;
 };
 
-static void sm_block_bio_end_io(struct bio *bio)
+static void KC_DECLARE_BIO_END_IO(sm_block_bio_end_io, struct bio *bio)
 {
 	struct sm_block_completion *sbc = bio->bi_private;
 
-	sbc->err = blk_status_to_errno(bio->bi_status);
+	sbc->err = kc_bio_get_errno(bio);
 	complete(&sbc->comp);
 	bio_put(bio);
 }
@@ -1236,7 +1236,7 @@ static int sm_block_io(struct super_block *sb, struct block_device *bdev, blk_op
 		goto out;
 	}
 
-	bio->bi_iter.bi_sector = blkno << (SCOUTFS_BLOCK_SM_SHIFT - 9);
+	kc_bio_set_sector(bio, blkno << (SCOUTFS_BLOCK_SM_SHIFT - 9));
 	bio->bi_end_io = sm_block_bio_end_io;
 	bio->bi_private = &sbc;
 	bio_add_page(bio, page, SCOUTFS_BLOCK_SM_SIZE, 0);
@@ -1244,7 +1244,7 @@ static int sm_block_io(struct super_block *sb, struct block_device *bdev, blk_op
 	init_completion(&sbc.comp);
 	sbc.err = 0;
 
-	submit_bio(bio);
+	kc_submit_bio(bio);
 
 	wait_for_completion(&sbc.comp);
 	ret = sbc.err;

kmod/src/data.c

@@ -23,7 +23,6 @@
 #include <linux/fiemap.h>
 #include <linux/writeback.h>
 #include <linux/overflow.h>
-#include <linux/iversion.h>
 
 #include "format.h"
 #include "super.h"
@@ -423,8 +422,6 @@ 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;
@@ -447,6 +444,7 @@ static int alloc_block(struct super_block *sb, struct inode *inode,
 		 * the preallocation size to the number of online
 		 * blocks.
 		 */
+		scoutfs_inode_get_onoff(inode, &online, &offline);
 		if (iblock > 1 && iblock == online) {
 			ret = scoutfs_ext_next(sb, &data_ext_ops, &args,
 					       iblock, 1, &found);
@@ -488,13 +486,6 @@ static int alloc_block(struct super_block *sb, struct inode *inode,
 		/* trim count by next extent after iblock */
 		if (found.len && found.start > start && found.start < start + count)
 			count = (found.start - start);
-
-		/*
-		 * Ramp the aligned region size up proportionally with
-		 * the file's online block count rather than jumping to
-		 * the full prealloc size.
-		 */
-		count = max_t(u64, 1, min(count, online));
 	}
 
 	/* overall prealloc limit */
@@ -758,6 +749,54 @@ static int scoutfs_readpage(struct file *file, struct page *page)
 	return ret;
 }
 
+#ifndef KC_FILE_AOPS_READAHEAD
+/*
+ * This is used for opportunistic read-ahead which can throw the pages
+ * away if it needs to.  If the caller didn't deal with offline extents
+ * then we drop those pages rather than trying to wait.  Whoever is
+ * staging offline extents should be doing it in enormous chunks so that
+ * read-ahead can ramp up within each staged region.  The check for
+ * offline extents is cheap when the inode has no offline extents.
+ */
+static int scoutfs_readpages(struct file *file, struct address_space *mapping,
+			     struct list_head *pages, unsigned nr_pages)
+{
+	struct inode *inode = file->f_inode;
+	struct super_block *sb = inode->i_sb;
+	struct scoutfs_lock *inode_lock = NULL;
+	struct page *page;
+	struct page *tmp;
+	int ret;
+
+	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ,
+				 SCOUTFS_LKF_REFRESH_INODE, inode, &inode_lock);
+	if (ret)
+		goto out;
+
+	list_for_each_entry_safe(page, tmp, pages, lru) {
+		ret = scoutfs_data_wait_check(inode, page_offset(page),
+					      PAGE_SIZE, SEF_OFFLINE,
+					      SCOUTFS_IOC_DWO_READ, NULL,
+					      inode_lock);
+		if (ret < 0)
+			goto out;
+		if (ret > 0) {
+			list_del(&page->lru);
+			put_page(page);
+			if (--nr_pages == 0) {
+				ret = 0;
+				goto out;
+			}
+		}
+	}
+
+	ret = mpage_readpages(mapping, pages, nr_pages, scoutfs_get_block_read);
+out:
+	scoutfs_unlock(sb, inode_lock, SCOUTFS_LOCK_READ);
+	BUG_ON(!list_empty(pages));
+	return ret;
+}
+#else
 static void scoutfs_readahead(struct readahead_control *rac)
 {
 	struct inode *inode = rac->file->f_inode;
@@ -779,6 +818,7 @@ static void scoutfs_readahead(struct readahead_control *rac)
 
 	scoutfs_unlock(sb, inode_lock, SCOUTFS_LOCK_READ);
 }
+#endif
 
 static int scoutfs_writepage(struct page *page, struct writeback_control *wbc)
 {
@@ -1219,7 +1259,7 @@ int scoutfs_data_move_blocks(struct inode *from, u64 from_off,
 	struct data_ext_args from_args;
 	struct data_ext_args to_args;
 	struct scoutfs_extent ext;
-	struct timespec64 cur_time;
+	struct kc_timespec cur_time;
 	LIST_HEAD(locks);
 	bool done = false;
 	loff_t from_size;
@@ -2015,9 +2055,15 @@ int scoutfs_data_waiting(struct super_block *sb, u64 ino, u64 iblock,
 	return ret;
 }
 
+#ifdef KC_MM_VM_FAULT_T
 static vm_fault_t scoutfs_data_page_mkwrite(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
+#else
+static int scoutfs_data_page_mkwrite(struct vm_area_struct *vma,
+				     struct vm_fault *vmf)
+{
+#endif
 	struct page *page = vmf->page;
 	struct file *file = vma->vm_file;
 	struct inode *inode = file_inode(file);
@@ -2159,9 +2205,14 @@ out:
 	return ret;
 }
 
+#ifdef KC_MM_VM_FAULT_T
 static vm_fault_t scoutfs_data_filemap_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
+#else
+static int scoutfs_data_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+#endif
 	struct file *file = vma->vm_file;
 	struct inode *inode = file_inode(file);
 	struct scoutfs_inode_info *si = SCOUTFS_I(inode);
@@ -2196,11 +2247,15 @@ retry:
 		}
 	}
 
+#ifdef KC_MM_VM_FAULT_T
 	ret = filemap_fault(vmf);
+#else
+	ret = filemap_fault(vma, vmf);
+#endif
 
 out:
 	if (scoutfs_per_task_del(&si->pt_data_lock, &pt_ent))
-		inode_dio_end(inode);
+		kc_inode_dio_end(inode);
 	scoutfs_unlock(sb, inode_lock, SCOUTFS_LOCK_READ);
 	if (scoutfs_data_wait_found(&dw)) {
 		err = scoutfs_data_wait(inode, &dw);
@@ -2218,6 +2273,9 @@ out:
 static const struct vm_operations_struct scoutfs_data_file_vm_ops = {
 	.fault		= scoutfs_data_filemap_fault,
 	.page_mkwrite	= scoutfs_data_page_mkwrite,
+#ifdef KC_MM_REMAP_PAGES
+	.remap_pages	= generic_file_remap_pages,
+#endif
 };
 
 static int scoutfs_file_mmap(struct file *file, struct vm_area_struct *vma)
@@ -2235,7 +2293,11 @@ const struct address_space_operations scoutfs_file_aops = {
 #else
 	.readpage		= scoutfs_readpage,
 #endif
+#ifndef KC_FILE_AOPS_READAHEAD
+	.readpages		= scoutfs_readpages,
+#else
 	.readahead		= scoutfs_readahead,
+#endif
 	.writepage		= scoutfs_writepage,
 	.writepages		= scoutfs_writepages,
 	.write_begin		= scoutfs_write_begin,
@@ -2243,10 +2305,17 @@ const struct address_space_operations scoutfs_file_aops = {
 };
 
 const struct file_operations scoutfs_file_fops = {
+#ifdef KC_LINUX_HAVE_FOP_AIO_READ
+	.read		= do_sync_read,
+	.write		= do_sync_write,
+	.aio_read	= scoutfs_file_aio_read,
+	.aio_write	= scoutfs_file_aio_write,
+#else
 	.read_iter	= scoutfs_file_read_iter,
 	.write_iter	= scoutfs_file_write_iter,
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= iter_file_splice_write,
+#endif
 	.mmap		= scoutfs_file_mmap,
 	.unlocked_ioctl	= scoutfs_ioctl,
 	.fsync		= scoutfs_file_fsync,

kmod/src/dir.c

@@ -18,7 +18,6 @@
 #include <linux/xattr.h>
 #include <linux/namei.h>
 #include <linux/mm.h>
-#include <linux/iversion.h>
 
 #include "format.h"
 #include "file.h"
@@ -423,7 +422,18 @@ out:
 	else
 		inode = scoutfs_iget(sb, ino, 0, 0);
 
-	return d_splice_alias(inode, dentry);
+	/*
+	 * We can't splice dir aliases into the dcache.  dir entries
+	 * might have changed on other nodes so our dcache could still
+	 * contain them, rather than having been moved in rename.  For
+	 * dirs, we use d_materialize_unique to remove any existing
+	 * aliases which must be stale.  Our inode numbers aren't reused
+	 * so inodes pointed to by entries can't change types.
+	 */
+	if (!IS_ERR_OR_NULL(inode) && S_ISDIR(inode->i_mode))
+		return d_materialise_unique(dentry, inode);
+	else
+		return d_splice_alias(inode, dentry);
 }
 
 /*
@@ -952,7 +962,7 @@ static int scoutfs_unlink(struct inode *dir, struct dentry *dentry)
 {
 	struct super_block *sb = dir->i_sb;
 	struct inode *inode = dentry->d_inode;
-	struct timespec64 ts = current_time(inode);
+	struct kc_timespec ts = current_time(inode);
 	struct scoutfs_lock *inode_lock = NULL;
 	struct scoutfs_lock *orph_lock = NULL;
 	struct scoutfs_lock *dir_lock = NULL;
@@ -1187,6 +1197,24 @@ out:
 	return path;
 }
 
+#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
+static void *scoutfs_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	char *path;
+
+	path = scoutfs_get_link_target(dentry);
+	if (!IS_ERR_OR_NULL(path))
+		nd_set_link(nd, path);
+	return path;
+}
+
+static void scoutfs_put_link(struct dentry *dentry, struct nameidata *nd,
+			     void *cookie)
+{
+	if (!IS_ERR_OR_NULL(cookie))
+		kfree(cookie);
+}
+#else
 static const char *scoutfs_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done)
 {
 	char *path;
@@ -1197,6 +1225,7 @@ static const char *scoutfs_get_link(struct dentry *dentry, struct inode *inode,
 
 	return path;
 }
+#endif
 
 /*
  * Symlink target paths can be annoyingly large.  We store relatively
@@ -1606,7 +1635,7 @@ static int scoutfs_rename_common(KC_VFS_NS_DEF
 	struct scoutfs_lock *orph_lock = NULL;
 	struct scoutfs_dirent new_dent;
 	struct scoutfs_dirent old_dent;
-	struct timespec64 now;
+	struct kc_timespec now;
 	bool ins_new = false;
 	bool del_new = false;
 	bool ins_old = false;
@@ -1618,9 +1647,6 @@ static int scoutfs_rename_common(KC_VFS_NS_DEF
 	int ret;
 	int err;
 
-	if (flags & ~RENAME_NOREPLACE)
-		return -EINVAL;
-
 	trace_scoutfs_rename(sb, old_dir, old_dentry, new_dir, new_dentry);
 
 	old_hash = dirent_name_hash(old_dentry->d_name.name,
@@ -1866,7 +1892,36 @@ out_unlock:
 	return ret;
 }
 
+#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
+static int scoutfs_rename(struct inode *old_dir,
+			  struct dentry *old_dentry, struct inode *new_dir,
+			  struct dentry *new_dentry)
+{
+	return scoutfs_rename_common(KC_VFS_INIT_NS
+				     old_dir, old_dentry, new_dir, new_dentry, 0);
+}
+#endif
 
+static int scoutfs_rename2(KC_VFS_NS_DEF
+			  struct inode *old_dir,
+			  struct dentry *old_dentry, struct inode *new_dir,
+			  struct dentry *new_dentry, unsigned int flags)
+{
+	if (flags & ~RENAME_NOREPLACE)
+		return -EINVAL;
+
+	return scoutfs_rename_common(KC_VFS_NS
+				     old_dir, old_dentry, new_dir, new_dentry, flags);
+}
+
+#ifdef KC_FMODE_KABI_ITERATE
+/* we only need this to set the iterate flag for kabi :/ */
+static int scoutfs_dir_open(struct inode *inode, struct file *file)
+{
+        file->f_mode |= FMODE_KABI_ITERATE;
+        return 0;
+}
+#endif
 
 static int scoutfs_tmpfile(KC_VFS_NS_DEF
 			   struct inode *dir,
@@ -1936,15 +1991,29 @@ out:
 }
 
 const struct inode_operations scoutfs_symlink_iops = {
+#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
+	.readlink       = generic_readlink,
+	.follow_link    = scoutfs_follow_link,
+	.put_link       = scoutfs_put_link,
+#else
 	.get_link	= scoutfs_get_link,
+#endif
 	.getattr	= scoutfs_getattr,
 	.setattr	= scoutfs_setattr,
+#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+#endif
 	.listxattr	= scoutfs_listxattr,
+#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
+	.removexattr	= generic_removexattr,
+#endif
 #ifdef KC_GET_INODE_ACL
 	.get_inode_acl	= scoutfs_get_acl,
 #else
 	.get_acl	= scoutfs_get_acl,
 #endif
+#ifndef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
 	.tmpfile	= scoutfs_tmpfile,
 	.rename		= scoutfs_rename_common,
 	.symlink	= scoutfs_symlink,
@@ -1953,17 +2022,26 @@ const struct inode_operations scoutfs_symlink_iops = {
 	.mkdir		= scoutfs_mkdir,
 	.create		= scoutfs_create,
 	.lookup		= scoutfs_lookup,
+#endif
 };
 
 const struct file_operations scoutfs_dir_fops = {
 	.iterate	= scoutfs_readdir,
+#ifdef KC_FMODE_KABI_ITERATE
+	.open		= scoutfs_dir_open,
+#endif
 	.unlocked_ioctl	= scoutfs_ioctl,
 	.fsync		= scoutfs_file_fsync,
 	.llseek		= generic_file_llseek,
 };
 
 
+#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
+const struct inode_operations_wrapper scoutfs_dir_iops = {
+	.ops = {
+#else
 const struct inode_operations scoutfs_dir_iops = {
+#endif
 	.lookup		= scoutfs_lookup,
 	.mknod		= scoutfs_mknod,
 	.create		= scoutfs_create,
@@ -1973,15 +2051,30 @@ const struct inode_operations scoutfs_dir_iops = {
 	.rmdir		= scoutfs_unlink,
 	.getattr	= scoutfs_getattr,
 	.setattr	= scoutfs_setattr,
+#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
+	.rename		= scoutfs_rename,
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.removexattr	= generic_removexattr,
+#endif
 	.listxattr	= scoutfs_listxattr,
 #ifdef KC_GET_INODE_ACL
 	.get_inode_acl	= scoutfs_get_acl,
 #else
 	.get_acl	= scoutfs_get_acl,
 #endif
+#ifdef KC_SET_ACL_DENTRY
 	.set_acl	= scoutfs_set_acl,
+#endif
 	.symlink	= scoutfs_symlink,
 	.permission	= scoutfs_permission,
+#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
+	},
+#endif
 	.tmpfile	= scoutfs_tmpfile,
-	.rename		= scoutfs_rename_common,
+#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
+	.rename2	= scoutfs_rename2,
+#else
+	.rename		= scoutfs_rename2,
+#endif
 };

kmod/src/dir.h

@@ -5,7 +5,11 @@
 #include "lock.h"
 
 extern const struct file_operations scoutfs_dir_fops;
+#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
+extern const struct inode_operations_wrapper scoutfs_dir_iops;
+#else
 extern const struct inode_operations scoutfs_dir_iops;
+#endif
 extern const struct inode_operations scoutfs_symlink_iops;
 
 extern const struct dentry_operations scoutfs_dentry_ops;

kmod/src/fence.c

@@ -222,7 +222,7 @@ static struct attribute *fence_attrs[] = {
 
 static void fence_timeout(struct timer_list *timer)
 {
-	struct pending_fence *fence = timer_container_of(fence, timer, timer);
+	struct pending_fence *fence = from_timer(fence, timer, timer);
 	struct super_block *sb = fence->sb;
 	DECLARE_FENCE_INFO(sb, fi);
 
@@ -424,7 +424,8 @@ int scoutfs_fence_setup(struct super_block *sb)
 		goto out;
 	}
 
-	fi->wq = alloc_workqueue("scoutfs_fence", WQ_UNBOUND, 0);
+	fi->wq = alloc_workqueue("scoutfs_fence",
+				 WQ_UNBOUND | WQ_NON_REENTRANT, 0);
 	if (!fi->wq) {
 		ret = -ENOMEM;
 		goto out;

kmod/src/file.c

@@ -30,6 +30,133 @@
 #include "omap.h"
 #include "quota.h"
 
+#ifdef KC_LINUX_HAVE_FOP_AIO_READ
+/*
+ * Start a high level file read.  We check for offline extents in the
+ * read region here so that we only check the extents once.  We use the
+ * dio count to prevent releasing while we're reading after we've
+ * checked the extents.
+ */
+ssize_t scoutfs_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
+			      unsigned long nr_segs, loff_t pos)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	struct scoutfs_inode_info *si = SCOUTFS_I(inode);
+	struct super_block *sb = inode->i_sb;
+	struct scoutfs_lock *scoutfs_inode_lock = NULL;
+	SCOUTFS_DECLARE_PER_TASK_ENTRY(pt_ent);
+	DECLARE_DATA_WAIT(dw);
+	int ret;
+
+retry:
+	/* protect checked extents from release */
+	inode_lock(inode);
+	atomic_inc(&inode->i_dio_count);
+	inode_unlock(inode);
+
+	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_READ,
+				 SCOUTFS_LKF_REFRESH_INODE, inode, &scoutfs_inode_lock);
+	if (ret)
+		goto out;
+
+	if (scoutfs_per_task_add_excl(&si->pt_data_lock, &pt_ent, scoutfs_inode_lock)) {
+		ret = scoutfs_data_wait_check_iov(inode, iov, nr_segs, pos,
+						  SEF_OFFLINE,
+						  SCOUTFS_IOC_DWO_READ,
+						  &dw, scoutfs_inode_lock);
+		if (ret != 0)
+			goto out;
+	} else {
+		WARN_ON_ONCE(true);
+	}
+
+	ret = generic_file_aio_read(iocb, iov, nr_segs, pos);
+
+out:
+	inode_dio_done(inode);
+	scoutfs_per_task_del(&si->pt_data_lock, &pt_ent);
+	scoutfs_unlock(sb, scoutfs_inode_lock, SCOUTFS_LOCK_READ);
+
+	if (scoutfs_data_wait_found(&dw)) {
+		ret = scoutfs_data_wait(inode, &dw);
+		if (ret == 0)
+			goto retry;
+	}
+
+	return ret;
+}
+
+ssize_t scoutfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
+			       unsigned long nr_segs, loff_t pos)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	struct scoutfs_inode_info *si = SCOUTFS_I(inode);
+	struct super_block *sb = inode->i_sb;
+	struct scoutfs_lock *scoutfs_inode_lock = NULL;
+	SCOUTFS_DECLARE_PER_TASK_ENTRY(pt_ent);
+	DECLARE_DATA_WAIT(dw);
+	int ret;
+
+	if (iocb->ki_left == 0) /* Does this even happen? */
+		return 0;
+
+retry:
+	inode_lock(inode);
+	ret = scoutfs_lock_inode(sb, SCOUTFS_LOCK_WRITE,
+				 SCOUTFS_LKF_REFRESH_INODE, inode, &scoutfs_inode_lock);
+	if (ret)
+		goto out;
+
+	ret = scoutfs_inode_check_retention(inode);
+	if (ret < 0)
+		goto out;
+
+	ret = scoutfs_complete_truncate(inode, scoutfs_inode_lock);
+	if (ret)
+		goto out;
+
+	if (scoutfs_per_task_add_excl(&si->pt_data_lock, &pt_ent, scoutfs_inode_lock)) {
+		/* data_version is per inode, whole file must be online */
+		ret = scoutfs_data_wait_check(inode, 0, i_size_read(inode),
+					      SEF_OFFLINE,
+					      SCOUTFS_IOC_DWO_WRITE,
+					      &dw, scoutfs_inode_lock);
+		if (ret != 0)
+			goto out;
+	}
+
+	ret = scoutfs_quota_check_data(sb, inode);
+	if (ret)
+		goto out;
+
+	/* XXX: remove SUID bit */
+
+	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+
+out:
+	scoutfs_per_task_del(&si->pt_data_lock, &pt_ent);
+	scoutfs_unlock(sb, scoutfs_inode_lock, SCOUTFS_LOCK_WRITE);
+	inode_unlock(inode);
+
+	if (scoutfs_data_wait_found(&dw)) {
+		ret = scoutfs_data_wait(inode, &dw);
+		if (ret == 0)
+			goto retry;
+	}
+
+	if (ret > 0 || ret == -EIOCBQUEUED) {
+		ssize_t err;
+
+		err = generic_write_sync(file, pos, ret);
+		if (err < 0 && ret > 0)
+			ret = err;
+	}
+
+	return ret;
+}
+#else
 ssize_t scoutfs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct file *file = iocb->ki_filp;
@@ -138,6 +265,7 @@ out:
 
 	return ret;
 }
+#endif
 
 int scoutfs_permission(KC_VFS_NS_DEF
 		       struct inode *inode, int mask)

kmod/src/file.h

@@ -1,8 +1,15 @@
 #ifndef _SCOUTFS_FILE_H_
 #define _SCOUTFS_FILE_H_
 
+#ifdef KC_LINUX_HAVE_FOP_AIO_READ
+ssize_t scoutfs_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
+			      unsigned long nr_segs, loff_t pos);
+ssize_t scoutfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
+			       unsigned long nr_segs, loff_t pos);
+#else
 ssize_t scoutfs_file_read_iter(struct kiocb *, struct iov_iter *);
 ssize_t scoutfs_file_write_iter(struct kiocb *, struct iov_iter *);
+#endif
 int scoutfs_permission(KC_VFS_NS_DEF
 		       struct inode *inode, int mask);
 loff_t scoutfs_file_llseek(struct file *file, loff_t offset, int whence);

kmod/src/forest.c

@@ -783,7 +783,7 @@ int scoutfs_forest_setup(struct super_block *sb)
 			  scoutfs_forest_log_merge_worker);
 	sbi->forest_info = finf;
 
-	finf->workq = alloc_workqueue("scoutfs_log_merge",
+	finf->workq = alloc_workqueue("scoutfs_log_merge", WQ_NON_REENTRANT |
 				      WQ_UNBOUND | WQ_HIGHPRI, 0);
 	if (!finf->workq) {
 		ret = -ENOMEM;

kmod/src/inode.c

@@ -21,7 +21,6 @@
 #include <linux/list_sort.h>
 #include <linux/workqueue.h>
 #include <linux/buffer_head.h>
-#include <linux/iversion.h>
 
 #include "format.h"
 #include "super.h"
@@ -144,26 +143,40 @@ void scoutfs_destroy_inode(struct inode *inode)
 static const struct inode_operations scoutfs_file_iops = {
 	.getattr	= scoutfs_getattr,
 	.setattr	= scoutfs_setattr,
+#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.removexattr	= generic_removexattr,
+#endif
 	.listxattr	= scoutfs_listxattr,
 #ifdef KC_GET_INODE_ACL
 	.get_inode_acl	= scoutfs_get_acl,
 #else
 	.get_acl	= scoutfs_get_acl,
 #endif
+#ifdef KC_SET_ACL_DENTRY
 	.set_acl	= scoutfs_set_acl,
+#endif
 	.fiemap		= scoutfs_data_fiemap,
 };
 
 static const struct inode_operations scoutfs_special_iops = {
 	.getattr	= scoutfs_getattr,
 	.setattr	= scoutfs_setattr,
+#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
+	.setxattr	= generic_setxattr,
+	.getxattr	= generic_getxattr,
+	.removexattr	= generic_removexattr,
+#endif
 	.listxattr	= scoutfs_listxattr,
 #ifdef KC_GET_INODE_ACL
 	.get_inode_acl	= scoutfs_get_acl,
 #else
 	.get_acl	= scoutfs_get_acl,
 #endif
+#ifdef KC_SET_ACL_DENTRY
 	.set_acl	= scoutfs_set_acl,
+#endif
 };
 
 /*
@@ -179,7 +192,12 @@ static void set_inode_ops(struct inode *inode)
 		inode->i_fop = &scoutfs_file_fops;
 		break;
 	case S_IFDIR:
+#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
+		inode->i_op = &scoutfs_dir_iops.ops;
+		inode->i_flags |= S_IOPS_WRAPPER;
+#else
 		inode->i_op = &scoutfs_dir_iops;
+#endif
 		inode->i_fop = &scoutfs_dir_fops;
 		break;
 	case S_IFLNK:
@@ -363,11 +381,18 @@ int scoutfs_inode_refresh(struct inode *inode, struct scoutfs_lock *lock)
 	return ret;
 }
 
+#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
+int scoutfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
+		    struct kstat *stat)
+{
+	struct inode *inode = dentry->d_inode;
+#else
 int scoutfs_getattr(KC_VFS_NS_DEF
 		    const struct path *path, struct kstat *stat,
 		    u32 request_mask, unsigned int query_flags)
 {
 	struct inode *inode = d_inode(path->dentry);
+#endif
 	struct super_block *sb = inode->i_sb;
 	struct scoutfs_lock *lock = NULL;
 	int ret;

kmod/src/inode.h

@@ -23,7 +23,7 @@ struct scoutfs_inode_info {
 	u64 offline_blocks;
 	u64 proj;
 	u32 flags;
-	struct timespec64 crtime;
+	struct kc_timespec crtime;
 
 	/*
 	 * Protects per-inode extent items, most particularly readers
@@ -131,9 +131,14 @@ int scoutfs_complete_truncate(struct inode *inode, struct scoutfs_lock *lock);
 int scoutfs_inode_check_retention(struct inode *inode);
 
 int scoutfs_inode_refresh(struct inode *inode, struct scoutfs_lock *lock);
+#ifdef KC_LINUX_HAVE_RHEL_IOPS_WRAPPER
+int scoutfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
+		    struct kstat *stat);
+#else
 int scoutfs_getattr(KC_VFS_NS_DEF
 		    const struct path *path, struct kstat *stat,
 		    u32 request_mask, unsigned int query_flags);
+#endif
 int scoutfs_setattr(KC_VFS_NS_DEF
 		    struct dentry *dentry, struct iattr *attr);
 

kmod/src/ioctl.c

@@ -489,7 +489,6 @@ static long scoutfs_ioc_stage(struct file *file, unsigned long arg)
 	struct scoutfs_lock *lock = NULL;
 	struct kiocb kiocb;
 	struct iovec iov;
-	struct iov_iter iter;
 	size_t written;
 	loff_t end_size;
 	loff_t isize;
@@ -515,6 +514,10 @@ static long scoutfs_ioc_stage(struct file *file, unsigned long arg)
 	/* the iocb is really only used for the file pointer :P */
 	init_sync_kiocb(&kiocb, file);
 	kiocb.ki_pos = args.offset;
+#ifdef KC_LINUX_AIO_KI_LEFT
+	kiocb.ki_left = args.length;
+	kiocb.ki_nbytes = args.length;
+#endif
 	iov.iov_base = (void __user *)(unsigned long)args.buf_ptr;
 	iov.iov_len = args.length;
 
@@ -556,9 +559,8 @@ static long scoutfs_ioc_stage(struct file *file, unsigned long arg)
 	pos = args.offset;
 	written = 0;
 	do {
-		iov_iter_init(&iter, WRITE, &iov, 1, args.length);
-		ret = kc_generic_perform_write(&kiocb, &iter, pos);
-
+		ret = generic_file_buffered_write(&kiocb, &iov, 1, pos, &pos,
+						  args.length, written);
 		BUG_ON(ret == -EIOCBQUEUED);
 		if (ret > 0)
 			written += ret;

kmod/src/item.c

@@ -79,6 +79,9 @@ struct item_cache_info {
 	struct super_block *sb;
 	struct item_percpu_pages __percpu *pcpu_pages;
 	KC_DEFINE_SHRINKER(shrinker);
+#ifdef KC_CPU_NOTIFIER
+	struct notifier_block notifier;
+#endif
 
 	/* often walked, but per-cpu refs are fast path */
 	rwlock_t rwlock;
@@ -2581,6 +2584,22 @@ static unsigned long item_cache_scan_objects(struct shrinker *shrink,
 	return freed;
 }
 
+#ifdef KC_CPU_NOTIFIER
+static int item_cpu_callback(struct notifier_block *nfb,
+			     unsigned long action, void *hcpu)
+{
+	struct item_cache_info *cinf = container_of(nfb,
+						    struct item_cache_info,
+						    notifier);
+	struct super_block *sb = cinf->sb;
+	unsigned long cpu = (unsigned long)hcpu;
+
+        if (action == CPU_DEAD)
+		drop_pcpu_pages(sb, cinf, cpu);
+
+	return NOTIFY_OK;
+}
+#endif
 
 int scoutfs_item_setup(struct super_block *sb)
 {
@@ -2611,6 +2630,10 @@ int scoutfs_item_setup(struct super_block *sb)
 	KC_INIT_SHRINKER_FUNCS(&cinf->shrinker, item_cache_count_objects,
 			       item_cache_scan_objects);
 	KC_REGISTER_SHRINKER(&cinf->shrinker, "scoutfs-item:" SCSBF, SCSB_ARGS(sb));
+#ifdef KC_CPU_NOTIFIER
+        cinf->notifier.notifier_call = item_cpu_callback;
+        register_hotcpu_notifier(&cinf->notifier);
+#endif
 
 	sbi->item_cache_info = cinf;
 	return 0;
@@ -2628,6 +2651,9 @@ void scoutfs_item_destroy(struct super_block *sb)
 	int cpu;
 
 	if (cinf) {
+#ifdef KC_CPU_NOTIFIER
+		unregister_hotcpu_notifier(&cinf->notifier);
+#endif
 		KC_UNREGISTER_SHRINKER(&cinf->shrinker);
 
 		for_each_possible_cpu(cpu)

kmod/src/kernelcompat.c

@@ -3,8 +3,119 @@
 
 #include "kernelcompat.h"
 
+#ifdef KC_SHRINKER_SHRINK
+#include <linux/shrinker.h>
+/*
+ * If a target doesn't have that .{count,scan}_objects() interface then
+ * we have a .shrink() helper that performs the shrink work in terms of
+ * count/scan.
+ */
+int kc_shrink_wrapper_fn(struct shrinker *shrink, struct shrink_control *sc)
+{
+	struct kc_shrinker_wrapper *wrapper = container_of(shrink, struct kc_shrinker_wrapper, shrink);
+	unsigned long nr;
+	unsigned long rc;
+
+	if (sc->nr_to_scan != 0) {
+		rc = wrapper->scan_objects(shrink, sc);
+		/* translate magic values to the equivalent for older kernels */
+		if (rc == SHRINK_STOP)
+			return -1;
+		else if (rc == SHRINK_EMPTY)
+			return 0;
+	}
+
+	nr = wrapper->count_objects(shrink, sc);
+
+	return min_t(unsigned long, nr, INT_MAX);
+}
+#endif
+
+#ifndef KC_CURRENT_TIME_INODE
+struct timespec64 kc_current_time(struct inode *inode)
+{
+	struct timespec64 now;
+	unsigned gran;
+
+	getnstimeofday64(&now);
+
+	if (unlikely(!inode->i_sb)) {
+		WARN(1, "current_time() called with uninitialized super_block in the inode");
+		return now;
+	}
+
+	gran = inode->i_sb->s_time_gran;
+
+	/* Avoid division in the common cases 1 ns and 1 s. */
+	if (gran == 1) {
+		/* nothing */
+	} else if (gran == NSEC_PER_SEC) {
+		now.tv_nsec = 0;
+	} else if (gran > 1 && gran < NSEC_PER_SEC) {
+		now.tv_nsec -= now.tv_nsec % gran;
+	} else {
+		WARN(1, "illegal file time granularity: %u", gran);
+	}
+
+	return now;
+}
+#endif
+
+#ifndef KC_GENERIC_FILE_BUFFERED_WRITE
+ssize_t
+kc_generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
+			       unsigned long nr_segs, loff_t pos, loff_t *ppos,
+			       size_t count, ssize_t written)
+{
+	ssize_t status;
+	struct iov_iter i;
+
+	iov_iter_init(&i, WRITE, iov, nr_segs, count);
+	status = kc_generic_perform_write(iocb, &i, pos);
+
+	if (likely(status >= 0)) {
+		written += status;
+		*ppos = pos + status;
+	}
+
+	return written ? written : status;
+}
+#endif
+
 #include <linux/list_lru.h>
 
+#ifdef KC_LIST_LRU_WALK_CB_ITEM_LOCK
+static enum lru_status kc_isolate(struct list_head *item, spinlock_t *lock, void *cb_arg)
+{
+	struct kc_isolate_args *args = cb_arg;
+
+	/* isolate doesn't use list, nr_items updated in caller */
+	return args->isolate(item, NULL, args->cb_arg);
+}
+
+unsigned long kc_list_lru_walk(struct list_lru *lru, kc_list_lru_walk_cb_t isolate, void *cb_arg,
+				      unsigned long nr_to_walk)
+{
+	struct kc_isolate_args args = {
+		.isolate = isolate,
+		.cb_arg = cb_arg,
+	};
+
+	return list_lru_walk(lru, kc_isolate, &args, nr_to_walk);
+}
+
+unsigned long kc_list_lru_shrink_walk(struct list_lru *lru, struct shrink_control *sc,
+				      kc_list_lru_walk_cb_t isolate, void *cb_arg)
+{
+	struct kc_isolate_args args = {
+		.isolate = isolate,
+		.cb_arg = cb_arg,
+	};
+
+	return list_lru_shrink_walk(lru, sc, kc_isolate, &args);
+}
+#endif
+
 #ifdef KC_LIST_LRU_WALK_CB_LIST_LOCK
 static enum lru_status kc_isolate(struct list_head *item, struct list_lru_one *list,
 				  spinlock_t *lock, void *cb_arg)

kmod/src/kernelcompat.h

@@ -4,6 +4,146 @@
 #include <linux/kernel.h>
 #include <linux/fs.h>
 
+/*
+ * v4.15-rc3-4-gae5e165d855d
+ *
+ * new API for handling inode->i_version. This forces us to
+ * include this API where we need. We include it here for
+ * convenience instead of where it's needed.
+ */
+#ifdef KC_NEED_LINUX_IVERSION_H
+#include <linux/iversion.h>
+#else
+/*
+ * Kernels before above version will need to fall back to
+ * manipulating inode->i_version as previous with degraded
+ * methods.
+ */
+#define inode_set_iversion_queried(inode, val)	\
+do {						\
+	(inode)->i_version = val;		\
+} while (0)
+#define inode_peek_iversion(inode)		\
+({						\
+	(inode)->i_version;			\
+})
+#endif
+
+#ifdef KC_POSIX_ACL_VALID_USER_NS
+#define kc_posix_acl_valid(user_ns, acl) posix_acl_valid(user_ns, acl)
+#else
+#define kc_posix_acl_valid(user_ns, acl) posix_acl_valid(acl)
+#endif
+
+/*
+ * v3.6-rc1-24-gdbf2576e37da
+ *
+ * All workqueues are now non-reentrant, and the bit flag is removed
+ * shortly after its uses were removed.
+ */
+#ifndef WQ_NON_REENTRANT
+#define WQ_NON_REENTRANT 0
+#endif
+
+/*
+ * v3.18-rc2-19-gb5ae6b15bd73
+ *
+ * Folds d_materialise_unique into d_splice_alias. Note reversal
+ * of arguments (Also note Documentation/filesystems/porting.rst)
+ */
+#ifndef KC_D_MATERIALISE_UNIQUE
+#define d_materialise_unique(dentry, inode) d_splice_alias(inode, dentry)
+#endif
+
+/*
+ * v4.8-rc1-29-g31051c85b5e2
+ *
+ * fall back to inode_change_ok() if setattr_prepare() isn't available
+ */
+#ifndef KC_SETATTR_PREPARE
+#define setattr_prepare(dentry, attr) inode_change_ok(d_inode(dentry), attr)
+#endif
+
+#ifndef KC___POSIX_ACL_CREATE
+#define __posix_acl_create posix_acl_create
+#define __posix_acl_chmod posix_acl_chmod
+#endif
+
+#ifndef KC_PERCPU_COUNTER_ADD_BATCH
+#define percpu_counter_add_batch __percpu_counter_add
+#endif
+
+#ifndef KC_MEMALLOC_NOFS_SAVE
+#define memalloc_nofs_save memalloc_noio_save
+#define memalloc_nofs_restore memalloc_noio_restore
+#endif
+
+#ifdef KC_BIO_BI_OPF
+#define kc_bio_get_opf(bio)		\
+({					\
+	(bio)->bi_opf;			\
+})
+#define kc_bio_set_opf(bio, opf)	\
+do {					\
+	(bio)->bi_opf = opf;		\
+} while (0)
+#define kc_bio_set_sector(bio, sect)	\
+do {					\
+	(bio)->bi_iter.bi_sector = sect;\
+} while (0)
+#define kc_submit_bio(bio) submit_bio(bio)
+#else
+#define kc_bio_get_opf(bio)		\
+({					\
+	(bio)->bi_rw;			\
+})
+#define kc_bio_set_opf(bio, opf)	\
+do {					\
+	(bio)->bi_rw = opf;		\
+} while (0)
+#define kc_bio_set_sector(bio, sect)	\
+do {					\
+	(bio)->bi_sector = sect;	\
+} while (0)
+#define kc_submit_bio(bio)		\
+do {					\
+	submit_bio((bio)->bi_rw, bio);	\
+} while (0)
+#define bio_set_dev(bio, bdev)		\
+do {					\
+	(bio)->bi_bdev = (bdev);	\
+} while (0)
+#endif
+
+#ifdef KC_BIO_BI_STATUS
+#define KC_DECLARE_BIO_END_IO(name, bio)	name(bio)
+#define kc_bio_get_errno(bio)			({ blk_status_to_errno((bio)->bi_status); })
+#else
+#define KC_DECLARE_BIO_END_IO(name, bio)	name(bio, int _error_arg)
+#define kc_bio_get_errno(bio)			({ (int)((void)(bio), _error_arg); })
+#endif
+
+/*
+ * v4.13-rc1-6-ge462ec50cb5f
+ *
+ * MS_* (mount) flags from <linux/mount.h> should not be used in the kernel
+ * anymore from 4.x onwards. Instead, we need to use the SB_* (superblock) flags
+ */
+#ifndef SB_POSIXACL
+#define SB_POSIXACL MS_POSIXACL
+#define SB_I_VERSION MS_I_VERSION
+#endif
+
+#ifndef KC_CURRENT_TIME_INODE
+struct timespec64 kc_current_time(struct inode *inode);
+#define current_time kc_current_time
+#define kc_timespec timespec
+#else
+#define kc_timespec timespec64
+#endif
+
+#ifndef KC_SHRINKER_SHRINK
+
 #define KC_DEFINE_SHRINKER(name) struct shrinker name
 #define KC_INIT_SHRINKER_FUNCS(name, countfn, scanfn) do {	\
 	__typeof__(name) _shrink = (name);			\
@@ -20,7 +160,77 @@
 #endif /* KC_SHRINKER_NAME */
 #define KC_UNREGISTER_SHRINKER(ptr) (unregister_shrinker(ptr))
 #define KC_SHRINKER_FN(ptr) (ptr)
+#else
 
+#include <linux/shrinker.h>
+#ifndef SHRINK_STOP
+#define SHRINK_STOP (~0UL)
+#define SHRINK_EMPTY (~0UL - 1)
+#endif
+
+int kc_shrink_wrapper_fn(struct shrinker *shrink, struct shrink_control *sc);
+struct kc_shrinker_wrapper {
+	unsigned long (*count_objects)(struct shrinker *, struct shrink_control *sc);
+	unsigned long (*scan_objects)(struct shrinker *, struct shrink_control *sc);
+	struct shrinker shrink;
+};
+
+#define KC_DEFINE_SHRINKER(name) struct kc_shrinker_wrapper name;
+#define KC_INIT_SHRINKER_FUNCS(name, countfn, scanfn) do {	\
+	struct kc_shrinker_wrapper *_wrap = (name);		\
+	_wrap->count_objects = (countfn);			\
+	_wrap->scan_objects = (scanfn);				\
+	_wrap->shrink.shrink = kc_shrink_wrapper_fn;		\
+	_wrap->shrink.seeks = DEFAULT_SEEKS;			\
+} while (0)
+#define KC_SHRINKER_CONTAINER_OF(ptr, type) container_of(container_of(ptr, struct kc_shrinker_wrapper, shrink), type, shrinker)
+#define KC_REGISTER_SHRINKER(ptr, fmt, ...) (register_shrinker(ptr.shrink))
+#define KC_UNREGISTER_SHRINKER(ptr) (unregister_shrinker(ptr.shrink))
+#define KC_SHRINKER_FN(ptr) (ptr.shrink)
+
+#endif /* KC_SHRINKER_SHRINK */
+
+#ifdef KC_KERNEL_GETSOCKNAME_ADDRLEN
+#include <linux/net.h>
+#include <linux/inet.h>
+static inline int kc_kernel_getsockname(struct socket *sock, struct sockaddr *addr)
+{
+	int addrlen = sizeof(struct sockaddr_in);
+	int ret = kernel_getsockname(sock, addr, &addrlen);
+	if (ret == 0 && addrlen != sizeof(struct sockaddr_in))
+		return -EAFNOSUPPORT;
+	else if (ret < 0)
+		return ret;
+
+	return sizeof(struct sockaddr_in);
+}
+static inline int kc_kernel_getpeername(struct socket *sock, struct sockaddr *addr)
+{
+	int addrlen = sizeof(struct sockaddr_in);
+	int ret = kernel_getpeername(sock, addr, &addrlen);
+	if (ret == 0 && addrlen != sizeof(struct sockaddr_in))
+		return -EAFNOSUPPORT;
+	else if (ret < 0)
+		return ret;
+
+	return sizeof(struct sockaddr_in);
+}
+#else
+#define kc_kernel_getsockname(sock, addr) kernel_getsockname(sock, addr)
+#define kc_kernel_getpeername(sock, addr) kernel_getpeername(sock, addr)
+#endif
+
+#ifdef KC_SOCK_CREATE_KERN_NET
+#define kc_sock_create_kern(family, type, proto, res) sock_create_kern(&init_net, family, type, proto, res)
+#else
+#define kc_sock_create_kern sock_create_kern
+#endif
+
+#ifndef KC_GENERIC_FILE_BUFFERED_WRITE
+ssize_t kc_generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
+               unsigned long nr_segs, loff_t pos, loff_t *ppos,
+               size_t count, ssize_t written);
+#define generic_file_buffered_write kc_generic_file_buffered_write
 #ifdef KC_GENERIC_PERFORM_WRITE_KIOCB_IOV_ITER
 static inline int kc_generic_perform_write(struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
 {
@@ -34,6 +244,7 @@ static inline int kc_generic_perform_write(struct kiocb *iocb, struct iov_iter *
 	return generic_perform_write(file, iter, pos);
 }
 #endif
+#endif // KC_GENERIC_FILE_BUFFERED_WRITE
 
 #ifndef KC_HAVE_BLK_OPF_T
 /* typedef __u32 __bitwise blk_opf_t; */
@@ -77,7 +288,7 @@ static inline struct bio *kc_bio_alloc(struct block_device *bdev, unsigned short
 {
 	struct bio *b = bio_alloc(gfp_mask, nr_vecs);
 	if (b) {
-		b->bi_opf = opf;
+		kc_bio_set_opf(b, opf);
 		bio_set_dev(b, bdev);
 	}
 	return b;
@@ -88,6 +299,11 @@ static inline struct bio *kc_bio_alloc(struct block_device *bdev, unsigned short
 #define fiemap_prep(inode, fieinfo, start, len, flags) fiemap_check_flags(fieinfo, flags)
 #endif
 
+#ifndef KC_KERNEL_OLD_TIMEVAL_STRUCT
+#define __kernel_old_timeval timeval
+#define ns_to_kernel_old_timeval(ktime) ns_to_timeval(ktime.tv64)
+#endif
+
 #ifdef KC_SOCK_SET_SNDTIMEO
 #include <net/sock.h>
 static inline int kc_sock_set_sndtimeo(struct socket *sock, s64 secs)
@@ -184,14 +400,45 @@ static inline int kc_tcp_sock_set_nodelay(struct socket *sock)
 }
 #endif
 
+#ifdef KC_INODE_DIO_END
+#define kc_inode_dio_end inode_dio_end
+#else
+#define kc_inode_dio_end inode_dio_done
+#endif
+
+#ifndef KC_MM_VM_FAULT_T
+typedef unsigned int vm_fault_t;
+static inline vm_fault_t vmf_error(int err)
+{
+	if (err == -ENOMEM)
+		return VM_FAULT_OOM;
+	return VM_FAULT_SIGBUS;
+}
+#endif
+
 #include <linux/list_lru.h>
 
+#ifndef KC_LIST_LRU_SHRINK_COUNT_WALK
+/* we don't bother with sc->{nid,memcg} (which doesn't exist in oldest kernels) */
+static inline unsigned long list_lru_shrink_count(struct list_lru *lru,
+                                                  struct shrink_control *sc)
+{
+        return list_lru_count(lru);
+}
+static inline unsigned long
+list_lru_shrink_walk(struct list_lru *lru, struct shrink_control *sc,
+		     list_lru_walk_cb isolate, void *cb_arg)
+{
+	return list_lru_walk(lru, isolate, cb_arg, sc->nr_to_scan);
+}
+#endif
+
 #ifndef KC_LIST_LRU_ADD_OBJ
 #define list_lru_add_obj list_lru_add
 #define list_lru_del_obj list_lru_del
 #endif
 
-#if defined(KC_LIST_LRU_WALK_CB_LIST_LOCK)
+#if defined(KC_LIST_LRU_WALK_CB_LIST_LOCK) || defined(KC_LIST_LRU_WALK_CB_ITEM_LOCK)
 struct list_lru_one;
 typedef enum lru_status (*kc_list_lru_walk_cb_t)(struct list_head *item, struct list_lru_one *list,
 						 void *cb_arg);
@@ -207,9 +454,39 @@ unsigned long kc_list_lru_shrink_walk(struct list_lru *lru, struct shrink_contro
 #define kc_list_lru_shrink_walk list_lru_shrink_walk
 #endif
 
-#ifndef KC_TIMER_CONTAINER_OF
-#define timer_container_of(var, callback_timer, timer_fieldname) \
-	from_timer(var, callback_timer, timer_fieldname)
+#if defined(KC_LIST_LRU_WALK_CB_ITEM_LOCK)
+/* isolate moved by hand, nr_items updated in walk as _REMOVE returned */
+static inline void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item,
+					 struct list_head *head)
+{
+        list_move(item, head);
+}
+#endif
+
+#ifndef KC_STACK_TRACE_SAVE
+#include <linux/stacktrace.h>
+static inline unsigned int stack_trace_save(unsigned long *store, unsigned int size,
+					    unsigned int skipnr)
+{
+        struct stack_trace trace = {
+                .entries        = store,
+                .max_entries    = size,
+                .skip           = skipnr,
+        };
+
+        save_stack_trace(&trace);
+        return trace.nr_entries;
+}
+
+static inline void stack_trace_print(unsigned long *entries, unsigned int nr_entries, int spaces)
+{
+        struct stack_trace trace = {
+                .entries        = entries,
+                .nr_entries     = nr_entries,
+        };
+
+	print_stack_trace(&trace, spaces);
+}
 #endif
 
 #endif

kmod/src/lock.c

@@ -980,7 +980,7 @@ static bool lock_flags_invalid(int flags)
  */
 static int lock_key_range(struct super_block *sb, enum scoutfs_lock_mode mode, int flags,
 			  struct scoutfs_key *start, struct scoutfs_key *end,
-			  struct scoutfs_lock **ret_lock)
+			  u64 ino, struct scoutfs_lock **ret_lock)
 {
 	DECLARE_LOCK_INFO(sb, linfo);
 	struct scoutfs_lock *lock;
@@ -1028,6 +1028,8 @@ static int lock_key_range(struct super_block *sb, enum scoutfs_lock_mode mode, i
 		/* the fast path where we can use the granted mode */
 		if (lock_modes_match(lock->mode, mode)) {
 			lock_inc_count(lock->users, mode);
+			lock->last_user_pid[mode] = task_pid_nr(current);
+			lock->last_user_ino[mode] = ino;
 			*ret_lock = lock;
 			ret = 0;
 			break;
@@ -1108,7 +1110,7 @@ int scoutfs_lock_ino(struct super_block *sb, enum scoutfs_lock_mode mode, int fl
 	end.sk_zone = SCOUTFS_FS_ZONE;
 	end.ski_ino = cpu_to_le64(ino | SCOUTFS_LOCK_INODE_GROUP_MASK);
 
-	return lock_key_range(sb, mode, flags, &start, &end, ret_lock);
+	return lock_key_range(sb, mode, flags, &start, &end, ino, ret_lock);
 }
 
 /*
@@ -1238,7 +1240,7 @@ int scoutfs_lock_rename(struct super_block *sb, enum scoutfs_lock_mode mode, int
 		.sk_type = SCOUTFS_RENAME_TYPE,
 	};
 
-	return lock_key_range(sb, mode, flags, &key, &key, lock);
+	return lock_key_range(sb, mode, flags, &key, &key, 0, lock);
 }
 
 /*
@@ -1286,7 +1288,7 @@ int scoutfs_lock_inode_index(struct super_block *sb, enum scoutfs_lock_mode mode
 
 	scoutfs_lock_get_index_item_range(type, major, ino, &start, &end);
 
-	return lock_key_range(sb, mode, 0, &start, &end, ret_lock);
+	return lock_key_range(sb, mode, 0, &start, &end, ino, ret_lock);
 }
 
 /*
@@ -1313,7 +1315,7 @@ int scoutfs_lock_orphan(struct super_block *sb, enum scoutfs_lock_mode mode, int
 	end.sko_ino = cpu_to_le64(U64_MAX);
 	end.sk_type = SCOUTFS_ORPHAN_TYPE;
 
-	return lock_key_range(sb, mode, flags, &start, &end, lock);
+	return lock_key_range(sb, mode, flags, &start, &end, ino, lock);
 }
 
 int scoutfs_lock_xattr_totl(struct super_block *sb, enum scoutfs_lock_mode mode, int flags,
@@ -1324,7 +1326,7 @@ int scoutfs_lock_xattr_totl(struct super_block *sb, enum scoutfs_lock_mode mode,
 
 	scoutfs_totl_set_range(&start, &end);
 
-	return lock_key_range(sb, mode, flags, &start, &end, lock);
+	return lock_key_range(sb, mode, flags, &start, &end, 0, lock);
 }
 
 int scoutfs_lock_xattr_indx(struct super_block *sb, enum scoutfs_lock_mode mode, int flags,
@@ -1335,7 +1337,7 @@ int scoutfs_lock_xattr_indx(struct super_block *sb, enum scoutfs_lock_mode mode,
 
 	scoutfs_xattr_indx_get_range(&start, &end);
 
-	return lock_key_range(sb, mode, flags, &start, &end, lock);
+	return lock_key_range(sb, mode, flags, &start, &end, 0, lock);
 }
 
 int scoutfs_lock_quota(struct super_block *sb, enum scoutfs_lock_mode mode, int flags,
@@ -1346,7 +1348,7 @@ int scoutfs_lock_quota(struct super_block *sb, enum scoutfs_lock_mode mode, int
 
 	scoutfs_quota_get_lock_range(&start, &end);
 
-	return lock_key_range(sb, mode, flags, &start, &end, lock);
+	return lock_key_range(sb, mode, flags, &start, &end, 0, lock);
 }
 
 void scoutfs_unlock(struct super_block *sb, struct scoutfs_lock *lock, enum scoutfs_lock_mode mode)
@@ -1463,7 +1465,7 @@ static void lock_tseq_show(struct seq_file *m, struct scoutfs_tseq_entry *ent)
 	struct scoutfs_lock *lock =
 		container_of(ent, struct scoutfs_lock, tseq_entry);
 
-	seq_printf(m, "start "SK_FMT" end "SK_FMT" refresh_gen %llu mode %d waiters: rd %u wr %u wo %u users: rd %u wr %u wo %u\n",
+	seq_printf(m, "start "SK_FMT" end "SK_FMT" refresh_gen %llu mode %d waiters: rd %u wr %u wo %u users: rd %u wr %u wo %u ino: rd %llu wr %llu wo %llu pid: rd %d wr %d wo %d\n",
 			   SK_ARG(&lock->start), SK_ARG(&lock->end),
 			   lock->refresh_gen, lock->mode,
 			   lock->waiters[SCOUTFS_LOCK_READ],
@@ -1471,7 +1473,13 @@ static void lock_tseq_show(struct seq_file *m, struct scoutfs_tseq_entry *ent)
 			   lock->waiters[SCOUTFS_LOCK_WRITE_ONLY],
 			   lock->users[SCOUTFS_LOCK_READ],
 			   lock->users[SCOUTFS_LOCK_WRITE],
-			   lock->users[SCOUTFS_LOCK_WRITE_ONLY]);
+			   lock->users[SCOUTFS_LOCK_WRITE_ONLY],
+			   lock->last_user_ino[SCOUTFS_LOCK_READ],
+			   lock->last_user_ino[SCOUTFS_LOCK_WRITE],
+			   lock->last_user_ino[SCOUTFS_LOCK_WRITE_ONLY],
+			   lock->last_user_pid[SCOUTFS_LOCK_READ],
+			   lock->last_user_pid[SCOUTFS_LOCK_WRITE],
+			   lock->last_user_pid[SCOUTFS_LOCK_WRITE_ONLY]);
 }
 
 /*
@@ -1693,7 +1701,8 @@ int scoutfs_lock_setup(struct super_block *sb)
 	}
 
 	linfo->workq = alloc_workqueue("scoutfs_lock_client_work",
-				       WQ_UNBOUND | WQ_HIGHPRI, 0);
+				       WQ_NON_REENTRANT | WQ_UNBOUND |
+				       WQ_HIGHPRI, 0);
 	if (!linfo->workq) {
 		ret = -ENOMEM;
 		goto out;

kmod/src/lock.h

@@ -42,6 +42,8 @@ struct scoutfs_lock {
 	enum scoutfs_lock_mode invalidating_mode;
 	unsigned int waiters[SCOUTFS_LOCK_NR_MODES];
 	unsigned int users[SCOUTFS_LOCK_NR_MODES];
+	pid_t last_user_pid[SCOUTFS_LOCK_NR_MODES];
+	u64 last_user_ino[SCOUTFS_LOCK_NR_MODES];
 
 	struct scoutfs_tseq_entry tseq_entry;
 

kmod/src/net.c

@@ -1113,11 +1113,11 @@ static int sock_opts_and_names(struct super_block *sb,
 	if (ret)
 		goto out;
 
-	ret = kernel_getsockname(sock, (struct sockaddr *)&conn->sockname);
+	ret = kc_kernel_getsockname(sock, (struct sockaddr *)&conn->sockname);
 	if (ret < 0)
 		goto out;
 
-	ret = kernel_getpeername(sock, (struct sockaddr *)&conn->peername);
+	ret = kc_kernel_getpeername(sock, (struct sockaddr *)&conn->peername);
 	if (ret < 0)
 		goto out;
 
@@ -1218,7 +1218,7 @@ static void scoutfs_net_connect_worker(struct work_struct *work)
 
 	trace_scoutfs_net_connect_work_enter(sb, 0, 0);
 
-	ret = sock_create_kern(&init_net, AF_INET, SOCK_STREAM, IPPROTO_TCP, &sock);
+	ret = kc_sock_create_kern(AF_INET, SOCK_STREAM, IPPROTO_TCP, &sock);
 	if (ret)
 		goto out;
 
@@ -1517,7 +1517,8 @@ scoutfs_net_alloc_conn(struct super_block *sb,
 		conn->ordered_proc_wlists = kmalloc_array(nr, sizeof(struct scoutfs_work_list),
 							  GFP_NOFS);
 		conn->workq = alloc_workqueue("scoutfs_net_%s",
-					      WQ_UNBOUND, 0, name_suffix);
+					      WQ_UNBOUND | WQ_NON_REENTRANT, 0,
+					      name_suffix);
 	}
 	if (!conn || (info_size && !conn->info) || !conn->workq || !conn->ordered_proc_wlists) {
 		if (conn) {
@@ -1629,7 +1630,7 @@ int scoutfs_net_bind(struct super_block *sb,
 	if (WARN_ON_ONCE(conn->sock))
 		return -EINVAL;
 
-	ret = sock_create_kern(&init_net, AF_INET, SOCK_STREAM, IPPROTO_TCP, &sock);
+	ret = kc_sock_create_kern(AF_INET, SOCK_STREAM, IPPROTO_TCP, &sock);
 	if (ret)
 		goto out;
 
@@ -1650,7 +1651,7 @@ int scoutfs_net_bind(struct super_block *sb,
 	if (ret < 0)
 		goto out;
 
-	ret = kernel_getsockname(sock, (struct sockaddr *)&conn->sockname);
+	ret = kc_kernel_getsockname(sock, (struct sockaddr *)&conn->sockname);
 	if (ret < 0)
 		goto out;
 
@@ -2098,9 +2099,11 @@ int scoutfs_net_setup(struct super_block *sb)
 	scoutfs_tseq_tree_init(&ninf->msg_tseq_tree, net_tseq_show_msg);
 
 	ninf->shutdown_workq = alloc_workqueue("scoutfs_net_shutdown",
-					       WQ_UNBOUND, 0);
+					       WQ_UNBOUND | WQ_NON_REENTRANT,
+					       0);
 	ninf->destroy_workq = alloc_workqueue("scoutfs_net_destroy",
-					       WQ_UNBOUND, 0);
+					       WQ_UNBOUND | WQ_NON_REENTRANT,
+					       0);
 	if (!ninf->shutdown_workq || !ninf->destroy_workq) {
 		ret = -ENOMEM;
 		goto out;

kmod/src/quorum.c

@@ -183,7 +183,7 @@ static int create_socket(struct super_block *sb)
 	int addrlen;
 	int ret;
 
-	ret = sock_create_kern(&init_net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
+	ret = kc_sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
 	if (ret) {
 		scoutfs_err(sb, "quorum couldn't create udp socket: %d", ret);
 		goto out;
@@ -1332,7 +1332,8 @@ int scoutfs_quorum_setup(struct super_block *sb)
 
 	/* a high priority single threaded context without mem reclaim */
 	qinf->workq = alloc_workqueue("scoutfs_quorum_work",
-				       WQ_UNBOUND | WQ_HIGHPRI, 1);
+				       WQ_NON_REENTRANT | WQ_UNBOUND |
+				       WQ_HIGHPRI, 1);
 	if (!qinf->workq) {
 		ret = -ENOMEM;
 		goto out;

kmod/src/recov.c

@@ -134,7 +134,7 @@ static int recov_finished(struct recov_info *recinf)
 
 static void timer_callback(struct timer_list *timer)
 {
-	struct recov_info *recinf = timer_container_of(recinf, timer, timer);
+	struct recov_info *recinf = from_timer(recinf, timer, timer);
 
 	recinf->timeout_fn(recinf->sb);
 }

kmod/src/server.c

@@ -4751,7 +4751,7 @@ int scoutfs_server_setup(struct super_block *sb)
 	INIT_DELAYED_WORK(&server->reclaim_dwork, reclaim_worker);
 
 	server->wq = alloc_workqueue("scoutfs_server",
-				     WQ_UNBOUND, 0);
+				     WQ_UNBOUND | WQ_NON_REENTRANT, 0);
 	if (!server->wq) {
 		kfree(server);
 		return -ENOMEM;

kmod/src/srch.c

@@ -2392,7 +2392,8 @@ int scoutfs_srch_setup(struct super_block *sb)
 		goto out;
 
 	srinf->workq = alloc_workqueue("scoutfs_srch_compact",
-				       WQ_UNBOUND | WQ_HIGHPRI, 0);
+				       WQ_NON_REENTRANT | WQ_UNBOUND |
+				       WQ_HIGHPRI, 0);
 	if (!srinf->workq) {
 		ret = -ENOMEM;
 		goto out;

kmod/src/tseq.c

@@ -46,6 +46,7 @@ static struct scoutfs_tseq_entry *tseq_rb_next(struct scoutfs_tseq_entry *ent)
 	return rb_entry(node, struct scoutfs_tseq_entry, node);
 }
 
+#ifdef KC_RB_TREE_AUGMENTED_COMPUTE_MAX
 static bool tseq_compute_total(struct scoutfs_tseq_entry *ent, bool exit)
 {
 	loff_t total = 1 + tseq_node_total(ent->node.rb_left) +
@@ -60,6 +61,17 @@ static bool tseq_compute_total(struct scoutfs_tseq_entry *ent, bool exit)
 
 RB_DECLARE_CALLBACKS(static, tseq_rb_callbacks, struct scoutfs_tseq_entry,
 		     node, total, tseq_compute_total);
+#else
+
+static loff_t tseq_compute_total(struct scoutfs_tseq_entry *ent)
+{
+	return 1 + tseq_node_total(ent->node.rb_left) +
+	       tseq_node_total(ent->node.rb_right);
+}
+
+RB_DECLARE_CALLBACKS(static, tseq_rb_callbacks, struct scoutfs_tseq_entry,
+		     node, loff_t, total, tseq_compute_total);
+#endif
 
 void scoutfs_tseq_tree_init(struct scoutfs_tseq_tree *tree,
 			    scoutfs_tseq_show_t show)

kmod/src/xattr.c

@@ -16,7 +16,6 @@
 #include <linux/xattr.h>
 #include <linux/crc32c.h>
 #include <linux/posix_acl.h>
-#include <linux/iversion.h>
 
 #include "format.h"
 #include "inode.h"
@@ -995,17 +994,38 @@ unlock:
 	return ret;
 }
 
+#ifndef KC_XATTR_STRUCT_XATTR_HANDLER
+/*
+ * Future kernels have this amazing hack to rewind the name to get the
+ * skipped prefix.  We're back in the stone ages without the handler
+ * arg, so we Just Know that this is possible.  This will become a
+ * compat hook to either call the kernel's xattr_full_name(handler), or
+ * our hack to use the flags as the prefix length.
+ */
+static const char *full_name_hack(const char *name, int len)
+{
+	return name - len;
+}
+#endif
 
 static int scoutfs_xattr_get_handler
+#ifdef KC_XATTR_STRUCT_XATTR_HANDLER
 		(const struct xattr_handler *handler, struct dentry *dentry,
 		 struct inode *inode, const char *name, void *value,
 		 size_t size)
 {
 	name = xattr_full_name(handler, name);
+#else
+		(struct dentry *dentry, const char *name,
+		 void *value, size_t size, int handler_flags)
+{
+	name = full_name_hack(name, handler_flags);
+#endif
 	return scoutfs_xattr_get(dentry, name, value, size);
 }
 
 static int scoutfs_xattr_set_handler
+#ifdef KC_XATTR_STRUCT_XATTR_HANDLER
 		(const struct xattr_handler *handler,
 		 KC_VFS_NS_DEF
 		 struct dentry *dentry,
@@ -1013,6 +1033,12 @@ static int scoutfs_xattr_set_handler
 		 size_t size, int flags)
 {
 	name = xattr_full_name(handler, name);
+#else
+		(struct dentry *dentry, const char *name,
+		 const void *value, size_t size, int flags, int handler_flags)
+{
+	name = full_name_hack(name, handler_flags);
+#endif
 	return scoutfs_xattr_set(dentry, name, value, size, flags);
 }
 
@@ -1045,14 +1071,22 @@ static const struct xattr_handler scoutfs_xattr_security_handler = {
 };
 
 static const struct xattr_handler scoutfs_xattr_acl_access_handler = {
+#ifdef KC_XATTR_HANDLER_NAME
 	.name   = XATTR_NAME_POSIX_ACL_ACCESS,
+#else
+	.prefix = XATTR_NAME_POSIX_ACL_ACCESS,
+#endif
 	.flags  = ACL_TYPE_ACCESS,
 	.get    = scoutfs_acl_get_xattr,
 	.set    = scoutfs_acl_set_xattr,
 };
 
 static const struct xattr_handler scoutfs_xattr_acl_default_handler = {
+#ifdef KC_XATTR_HANDLER_NAME
 	.name   = XATTR_NAME_POSIX_ACL_DEFAULT,
+#else
+	.prefix = XATTR_NAME_POSIX_ACL_DEFAULT,
+#endif
 	.flags  = ACL_TYPE_DEFAULT,
 	.get    = scoutfs_acl_get_xattr,
 	.set    = scoutfs_acl_set_xattr,

tests/funcs/filter.sh

@@ -171,13 +171,6 @@ t_filter_dmesg()
 	# orphan log trees reclaim is handled, not an error
 	re="$re|scoutfs .* reclaiming orphan log trees"
 
-	# nfs can emit a whole range of messages we can ignore
-	re="$re|Installing knfsd .*"
-	re="$re|nfsd: .*"
-	re="$re|NFSD: .*"
-	re="$re|RPC: .*"
-	re="$re|FS-Cache: .*"
-
 	# fencing tests force unmounts and trigger timeouts
 	re="$re|scoutfs .* forcing unmount"
 	re="$re|scoutfs .* reconnect timed out"

tests/golden/basic-nfs

@@ -1,32 +0,0 @@
-== write via NFS, read both sides
-== POSIX ACL set via NFS, read both sides
-user::rw-
-user:22222:rw-
-group::r--
-mask::rw-
-other::r--
-
-user::rw-
-user:22222:rw-
-group::r--
-mask::rw-
-other::r--
-
-== POSIX ACL set on scoutfs, read via NFS
-user::rw-
-user:22222:rw-
-group::r--
-group:44444:r--
-mask::rw-
-other::r--
-
-== default ACL inheritance via NFS
-user::rw-
-user:22222:rwx	#effective:rw-
-group::r-x	#effective:r--
-mask::rw-
-other::r--
-
-== NFS read demand-stages a released file
-1
-== cleanup

tests/golden/data-prealloc

@@ -8,10 +8,10 @@
 /mnt/test/test/data-prealloc/file-1: extents: 32
 /mnt/test/test/data-prealloc/file-2: extents: 32
 == any writes to region prealloc get full extents
-/mnt/test/test/data-prealloc/file-1: extents: 8
-/mnt/test/test/data-prealloc/file-2: extents: 8
-/mnt/test/test/data-prealloc/file-1: extents: 8
-/mnt/test/test/data-prealloc/file-2: extents: 8
+/mnt/test/test/data-prealloc/file-1: extents: 4
+/mnt/test/test/data-prealloc/file-2: extents: 4
+/mnt/test/test/data-prealloc/file-1: extents: 4
+/mnt/test/test/data-prealloc/file-2: extents: 4
 == streaming offline writes get full extents either way
 /mnt/test/test/data-prealloc/file-1: extents: 4
 /mnt/test/test/data-prealloc/file-2: extents: 4
@@ -20,8 +20,8 @@
 == goofy preallocation amounts work
 /mnt/test/test/data-prealloc/file-1: extents: 6
 /mnt/test/test/data-prealloc/file-2: extents: 6
-/mnt/test/test/data-prealloc/file-1: extents: 10
-/mnt/test/test/data-prealloc/file-2: extents: 10
+/mnt/test/test/data-prealloc/file-1: extents: 6
+/mnt/test/test/data-prealloc/file-2: extents: 6
 /mnt/test/test/data-prealloc/file-1: extents: 3
 /mnt/test/test/data-prealloc/file-2: extents: 3
 == block writes into region allocs hole

tests/golden/format-version-forward-back

@@ -0,0 +1,4 @@
+== ensuring utils and module for old versions
+== unmounting test fs and removing test module
+== testing combinations of old and new format versions
+== restoring test module and mount

tests/golden/lock-pid-ino

@@ -0,0 +1,6 @@
+== set up file
+== exercise read, write, and write-only modes
+== verify FS-zone lock recorded read and write ino+pid
+== verify orphan-zone lock recorded write-only ino+pid
+== contend on a single inode with concurrent read and write loops
+== verify both rd and wr slots populated by concurrent contention

tests/sequence

@@ -3,7 +3,6 @@ basic-block-counts.sh
 basic-bad-mounts.sh
 basic-posix-acl.sh
 basic-acl-consistency.sh
-basic-nfs.sh
 inode-items-updated.sh
 simple-inode-index.sh
 simple-staging.sh
@@ -19,6 +18,7 @@ offline-extent-waiting.sh
 move-blocks.sh
 projects.sh
 large-fragmented-free.sh
+format-version-forward-back.sh
 enospc.sh
 mmap.sh
 srch-safe-merge-pos.sh
@@ -32,6 +32,7 @@ totl-merge-read.sh
 quota-invalidate-race.sh
 totl-delta-inject.sh
 lock-refleak.sh
+lock-pid-ino.sh
 lock-shrink-consistency.sh
 lock-shrink-read-race.sh
 lock-pr-cw-conflict.sh

tests/tests/basic-nfs.sh

@@ -1,86 +0,0 @@
-#
-# Test basic scoutfs-nfs interactions:
-# - read/write
-# - stage/release and data wait
-# - nfs setacl/getacl mapping
-#
-
-t_require_commands scoutfs setfacl getfacl exportfs mount.nfs umount \
-		   stat dd cmp systemctl
-
-systemctl start nfs-server >> "$T_TMPDIR/nfs.log" 2>&1 || \
-	t_skip "nfs-server not available"
-
-# Keep file creation modes deterministic for the ACL golden output.
-umask 022
-
-EXPORT_OPTS="rw,async,no_root_squash,no_subtree_check,fsid=42"
-NFS_MNT="$T_TMP.nfs"
-NFS_DIR="$NFS_MNT/test/basic-nfs"
-
-filter() { sed "s@$T_TMPDIR@T_TMPDIR@g" | t_filter_fs; }
-gf() { getfacl -n --omit-header "$@" 2>/dev/null; }
-
-teardown_nfs()
-{
-	(
-		umount "$NFS_MNT"
-		exportfs -u "127.0.0.1:$T_M0"
-		exportfs -f
-		systemctl stop nfs-server
-		rmdir "$NFS_MNT"
-	) >> "$T_TMPDIR/nfs.log" 2>&1
-}
-trap teardown_nfs EXIT
-
-exportfs -u "127.0.0.1:$T_M0" >> "$T_TMPDIR/nfs.log" 2>&1 || true
-t_quiet mkdir -p "$NFS_MNT"
-exportfs -o "$EXPORT_OPTS" "127.0.0.1:$T_M0" >> "$T_TMPDIR/nfs.log" 2>&1
-mount.nfs -o vers=3,noac,actimeo=0 "127.0.0.1:$T_M0" "$NFS_MNT" >> "$T_TMPDIR/nfs.log" 2>&1
-
-test -d "$NFS_DIR" || t_fail "test dir $NFS_DIR not visible over NFS"
-
-echo "== write via NFS, read both sides"
-dd if=/dev/urandom bs=4096 count=1 of="$T_TMP.data" status=none
-cp "$T_TMP.data" "$NFS_DIR/file"
-cmp "$T_TMP.data" "$T_D0/file"
-cmp "$T_TMP.data" "$NFS_DIR/file"
-
-echo "== POSIX ACL set via NFS, read both sides"
-setfacl -m u:22222:rw "$NFS_DIR/file" 2>&1 | filter
-gf "$NFS_DIR/file"
-gf "$T_D0/file"
-
-echo "== POSIX ACL set on scoutfs, read via NFS"
-setfacl -m g:44444:r "$T_D0/file" 2>&1 | filter
-gf "$NFS_DIR/file"
-
-echo "== default ACL inheritance via NFS"
-mkdir "$NFS_DIR/d"
-setfacl -d -m u:22222:rwx "$NFS_DIR/d" 2>&1 | filter
-touch "$NFS_DIR/d/child"
-gf "$NFS_DIR/d/child"
-
-echo "== NFS read demand-stages a released file"
-dd if=/dev/urandom bs=4096 count=1 of="$T_TMP.big" status=none
-cp "$T_TMP.big" "$T_D0/big"
-sync
-vers=$(scoutfs stat -s data_version "$T_D0/big")
-t_quiet scoutfs release "$T_D0/big" -V "$vers" -o 0 -l 4K
-
-# NFS read against the offline file blocks in scoutfs_read waiting
-# for the data to come back online.
-cat "$NFS_DIR/big" > "$T_TMP.read" &
-read_pid=$!
-sleep 1
-scoutfs data-waiting -B 0 -I 0 -p "$T_D0" | wc -l
-
-t_quiet scoutfs stage "$T_TMP.big" "$T_D0/big" -V "$vers" -o 0 -l 4096
-wait "$read_pid"
-cmp "$T_TMP.big" "$T_TMP.read"
-
-echo "== cleanup"
-rm -f "$T_D0/file" "$T_D0/big"
-rm -rf "$T_D0/d"
-
-t_pass

tests/tests/format-version-forward-back.sh

@@ -0,0 +1,184 @@
+#
+# Test our basic ability to work with different format versions.
+#
+# The current code being tested has a range of supported format
+# versions.   For each of the older supported format versions we have a
+# git hash of the commit before the next greater version was introduced.
+# We build versions of the scoutfs utility and kernel module for the
+# last commit in tree that had a lesser supported version as its max
+# supported version.   We use those binaries to test forward and back
+# compat as new and old code works with a persistent volume with a given
+# format version.
+#
+
+# not supported on el8 or higher
+if [ $(source /etc/os-release ; echo ${VERSION_ID:0:1}) -gt 7 ]; then
+	t_skip_permitted "Unsupported OS version"
+fi
+
+mount_has_format_version()
+{
+	local mnt="$1"
+	local vers="$2"
+	local sysfs_fmt_vers="$(t_sysfs_path_from_mnt $SCR)/format_version"
+
+	test "$(cat $sysfs_fmt_vers)" == "$vers"
+}
+
+SCR="/mnt/scoutfs.scratch"
+
+MIN=$(modinfo $T_MODULE | awk '($1 == "scoutfs_format_version_min:"){print $2}')
+MAX=$(modinfo $T_MODULE | awk '($1 == "scoutfs_format_version_max:"){print $2}')
+
+echo "min: $MIN max: $MAX" > "$T_TMP.log"
+
+test "$MIN" -gt 0 -a "$MAX" -gt 0 -a "$MIN" -le "$MAX" || \
+	t_fail "parsed bad versions, min: $MIN max: $MAX"
+
+test "$MIN" == "$MAX" && \
+	t_skip "only one supported format version: $MIN"
+
+# prepare dir and wipe any weird old partial state
+builds="$T_RESULTS/format_version_builds"
+mkdir -p "$builds"
+
+echo "== ensuring utils and module for old versions"
+declare -A commits
+commits[1]=c3c4b080
+for vers in $(seq $MIN $((MAX - 1))); do
+	dir="$builds/$vers"
+	platform=$(uname -rp)
+	buildmark="$dir/buildmark"
+	commit="${commits[$vers]}"
+
+	test -n "$commit" || \
+		t_fail "no commit for vers $vers"
+
+	# have our files for this version
+	test "$(cat $buildmark 2>&1)" == "$platform" && \
+		continue
+
+	# build as one big sequence of commands that can return failure
+	(
+		set -o pipefail
+
+		rm -rf $dir							&&
+		mkdir -p $dir/building						&&
+		cd "$T_TESTS/.."						&&
+		git archive --format=tar "$commit" | tar -C "$dir/building" -xf - &&
+		cd -								&&
+		find $dir							&&
+		make -C "$dir/building"						&&
+		mv $dir/building/utils/src/scoutfs $dir				&&
+		mv $dir/building/kmod/src/scoutfs.ko $dir			&&
+		rm -rf $dir/building						&&
+		echo "$platform" > $buildmark					&&
+		find $dir							&&
+		cat $buildmark
+	) >> "$T_TMP.log" 2>&1 || t_fail "version $vers build failed"
+done
+
+echo "== unmounting test fs and removing test module"
+t_quiet t_umount_all
+t_quiet rmmod scoutfs
+
+echo "== testing combinations of old and new format versions"
+mkdir -p "$SCR"
+for vers in $(seq $MIN $((MAX - 1))); do
+	old_scoutfs="$builds/$vers/scoutfs"
+	old_module="$builds/$vers/scoutfs.ko"
+
+	echo "mkfs $vers" >> "$T_TMP.log"
+	t_quiet $old_scoutfs mkfs -f -Q 0,127.0.0.1,$T_SCRATCH_PORT "$T_EX_META_DEV" "$T_EX_DATA_DEV" \
+		|| t_fail "mkfs $vers failed"
+
+	echo "mount $vers with $vers" >> "$T_TMP.log"
+	t_quiet insmod $old_module
+	t_quiet mount -t scoutfs -o metadev_path=$T_EX_META_DEV,quorum_slot_nr=0 \
+		"$T_EX_DATA_DEV" "$SCR"
+	t_quiet mount_has_format_version "$SCR" "$vers"
+
+	echo "creating files in $vers" >> "$T_TMP.log"
+	t_quiet touch "$SCR/file-"{1,2,3}
+	stat "$SCR"/file-* > "$T_TMP.stat" || \
+		t_fail "stat in $vers failed"
+
+	echo "remounting $vers fs with $MAX" >> "$T_TMP.log"
+	t_quiet umount "$SCR"
+	rmmod scoutfs
+	insmod "$T_MODULE"
+	t_quiet mount -t scoutfs -o metadev_path=$T_EX_META_DEV,quorum_slot_nr=0 \
+		"$T_EX_DATA_DEV" "$SCR"
+	t_quiet mount_has_format_version "$SCR" "$vers"
+
+	echo "verifying stat in $vers with $MAX" >> "$T_TMP.log"
+	diff -u "$T_TMP.stat" <(stat "$SCR"/file-*)
+
+	echo "keep/update/del existing, create new in $vers" >> "$T_TMP.log"
+	t_quiet touch "$SCR/file-2"
+	t_quiet rm -f "$SCR/file-3"
+	t_quiet touch "$SCR/file-4"
+	stat "$SCR"/file-* > "$T_TMP.stat" || \
+		t_fail "stat in $vers failed"
+
+	echo "remounting $vers fs with $vers" >> "$T_TMP.log"
+	t_quiet umount "$SCR"
+	rmmod scoutfs
+	insmod "$old_module"
+	t_quiet mount -t scoutfs -o metadev_path=$T_EX_META_DEV,quorum_slot_nr=0 \
+		"$T_EX_DATA_DEV" "$SCR"
+	t_quiet mount_has_format_version "$SCR" "$vers"
+
+	echo "verifying stat in $vers with $vers" >> "$T_TMP.log"
+	diff -u "$T_TMP.stat" <(stat "$SCR"/file-*)
+
+	echo "changing format vers to $MAX" >> "$T_TMP.log"
+	t_quiet umount "$SCR"
+	rmmod scoutfs
+	t_quiet scoutfs change-format-version -F -V $MAX $T_EX_META_DEV "$T_EX_DATA_DEV"
+
+	echo "mount fs $MAX with old $vers should fail" >> "$T_TMP.log"
+	insmod "$old_module"
+	mount -t scoutfs -o metadev_path=$T_EX_META_DEV,quorum_slot_nr=0 \
+		"$T_EX_DATA_DEV" "$SCR" >> "$T_TMP.log" 2>&1
+	if [ "$?" == "0" ]; then
+		umount "$SCR"
+		t_fail "old code ver $vers able to mount new ver $MAX"
+	fi
+
+	echo "remounting $MAX fs with $MAX" >> "$T_TMP.log"
+	rmmod scoutfs
+	insmod "$T_MODULE"
+	t_quiet mount -t scoutfs -o metadev_path=$T_EX_META_DEV,quorum_slot_nr=0 \
+		"$T_EX_DATA_DEV" "$SCR"
+	t_quiet mount_has_format_version "$SCR" "$MAX"
+
+	echo "verifying stat in $MAX with $MAX" >> "$T_TMP.log"
+	diff -u "$T_TMP.stat" <(stat "$SCR"/file-*)
+
+	echo "keep/update/del existing, create new in $MAX" >> "$T_TMP.log"
+	t_quiet touch "$SCR/file-2"
+	t_quiet rm -f "$SCR/file-4"
+	t_quiet touch "$SCR/file-5"
+	stat "$SCR"/file-* > "$T_TMP.stat" || \
+		t_fail "stat in $MAX failed"
+
+	echo "remounting $MAX fs with $MAX again" >> "$T_TMP.log"
+	t_quiet umount "$SCR"
+	t_quiet mount -t scoutfs -o metadev_path=$T_EX_META_DEV,quorum_slot_nr=0 \
+		"$T_EX_DATA_DEV" "$SCR"
+	t_quiet mount_has_format_version "$SCR" "$MAX"
+
+	echo "verifying stat in $MAX with $MAX again" >> "$T_TMP.log"
+	diff -u "$T_TMP.stat" <(stat "$SCR"/file-*)
+
+	echo "done with old vers $vers" >> "$T_TMP.log"
+	t_quiet umount "$SCR"
+	rmmod scoutfs
+done
+
+echo "== restoring test module and mount"
+insmod "$T_MODULE"
+t_mount_all
+
+t_pass

tests/tests/lock-pid-ino.sh

@@ -0,0 +1,68 @@
+#
+# verify debugfs client_locks reports per-mode last-user PID and inode.
+#
+
+t_require_commands stat touch awk rm
+
+FILE="$T_D0/file"
+
+echo "== set up file"
+touch "$FILE"
+INO=$(stat -c %i "$FILE")
+GROUP_START=$(( INO & ~1023 ))
+
+echo "== exercise read, write, and write-only modes"
+t_quiet stat "$FILE"
+echo data > "$FILE"
+rm -f "$FILE"
+
+echo "== verify FS-zone lock recorded read and write ino+pid"
+ERR=$(awk -v group="$GROUP_START" -v ino="$INO" '
+	$2 == "16." group ".0.0.0.0" {
+		if ($25 != ino || $32 <= 0)
+			print "read mode: ino=" $25 " pid=" $32 " want ino=" ino " pid>0"
+		if ($27 != ino || $34 <= 0)
+			print "write mode: ino=" $27 " pid=" $34 " want ino=" ino " pid>0"
+		found = 1
+	}
+	END { if (!found) print "no FS-zone client_locks line for group " group }
+' < "$(t_debugfs_path)/client_locks")
+[ -n "$ERR" ] && t_fail "$ERR"
+
+echo "== verify orphan-zone lock recorded write-only ino+pid"
+ERR=$(awk -v ino="$INO" '
+	$2 == "8.0.4.0.0.0" {
+		if ($29 != ino || $36 <= 0)
+			print "write-only mode: ino=" $29 " pid=" $36 " want ino=" ino " pid>0"
+		found = 1
+	}
+	END { if (!found) print "no orphan-zone client_locks line" }
+' < "$(t_debugfs_path)/client_locks")
+[ -n "$ERR" ] && t_fail "$ERR"
+
+echo "== contend on a single inode with concurrent read and write loops"
+FILE2="$T_D0/file2"
+touch "$FILE2"
+INO2=$(stat -c %i "$FILE2")
+GROUP2=$(( INO2 & ~1023 ))
+
+for i in $(seq 1 5); do t_quiet stat "$FILE2"; done &
+RPID=$!
+for i in $(seq 1 5); do echo $i > "$FILE2"; done &
+WPID=$!
+wait $RPID $WPID
+
+echo "== verify both rd and wr slots populated by concurrent contention"
+ERR=$(awk -v group="$GROUP2" -v ino="$INO2" '
+	$2 == "16." group ".0.0.0.0" {
+		if ($25 != ino || $32 <= 0)
+			print "concurrent read: ino=" $25 " pid=" $32 " want ino=" ino " pid>0"
+		if ($27 != ino || $34 <= 0)
+			print "concurrent write: ino=" $27 " pid=" $34 " want ino=" ino " pid>0"
+		found = 1
+	}
+	END { if (!found) print "no FS-zone client_locks line for group " group }
+' < "$(t_debugfs_path)/client_locks")
+[ -n "$ERR" ] && t_fail "$ERR"
+
+t_pass