Prepare to release 0.6.5.11

META file and RPM release log updated.

Signed-off-by: Tony Hutter <hutter2@llnl.gov>

META

@@ -1,7 +1,7 @@
 Meta:         1
 Name:         zfs
 Branch:       1.0
-Version:      0.6.5.8
+Version:      0.6.5.11
 Release:      1
 Release-Tags: relext
 License:      CDDL

cmd/mount_zfs/mount_zfs.c

@@ -77,7 +77,10 @@ static const option_map_t option_map[] = {
 	{ MNTOPT_RELATIME,	MS_RELATIME,	ZS_COMMENT	},
 #endif
 #ifdef MS_STRICTATIME
-	{ MNTOPT_DFRATIME,	MS_STRICTATIME,	ZS_COMMENT	},
+	{ MNTOPT_STRICTATIME,	MS_STRICTATIME,	ZS_COMMENT	},
+#endif
+#ifdef MS_LAZYTIME
+	{ MNTOPT_LAZYTIME,	MS_LAZYTIME,	ZS_COMMENT	},
 #endif
 	{ MNTOPT_CONTEXT,	MS_COMMENT,	ZS_COMMENT	},
 	{ MNTOPT_FSCONTEXT,	MS_COMMENT,	ZS_COMMENT	},
@@ -605,10 +608,23 @@ main(int argc, char **argv)
 				    "failed for unknown reason.\n"), dataset);
 			}
 			return (MOUNT_SYSERR);
+#ifdef MS_MANDLOCK
+		case EPERM:
+			if (mntflags & MS_MANDLOCK) {
+				(void) fprintf(stderr, gettext("filesystem "
+				    "'%s' has the 'nbmand=on' property set, "
+				    "this mount\noption may be disabled in "
+				    "your kernel.  Use 'zfs set nbmand=off'\n"
+				    "to disable this option and try to "
+				    "mount the filesystem again.\n"), dataset);
+				return (MOUNT_SYSERR);
+			}
+			/* fallthru */
+#endif
 		default:
 			(void) fprintf(stderr, gettext("filesystem "
-			    "'%s' can not be mounted due to error "
+			    "'%s' can not be mounted: %s\n"), dataset,
-			    "%d\n"), dataset, errno);
+			    strerror(errno));
 			return (MOUNT_USAGE);
 		}
 	}

cmd/vdev_id/vdev_id

@@ -184,9 +184,9 @@ sas_handler() {
 			return
 		fi
 
-		# Get the raw scsi device name from multipath -l.  Strip off
+		# Get the raw scsi device name from multipath -ll. Strip off
 		# leading pipe symbols to make field numbering consistent.
-		DEV=`multipath -l $DM_NAME |
+		DEV=`multipath -ll $DM_NAME |
 			awk '/running/{gsub("^[|]"," "); print $3 ; exit}'`
 		if [ -z "$DEV" ] ; then
 			return

cmd/zdb/zdb.c

@@ -478,7 +478,7 @@ static void
 dump_bpobj_subobjs(objset_t *os, uint64_t object, void *data, size_t size)
 {
 	dmu_object_info_t doi;
-	uint64_t i;
+	int64_t i;
 
 	VERIFY0(dmu_object_info(os, object, &doi));
 	uint64_t *subobjs = kmem_alloc(doi.doi_max_offset, KM_SLEEP);
@@ -497,7 +497,7 @@ dump_bpobj_subobjs(objset_t *os, uint64_t object, void *data, size_t size)
 	}
 
 	for (i = 0; i <= last_nonzero; i++) {
-		(void) printf("\t%llu\n", (longlong_t)subobjs[i]);
+		(void) printf("\t%llu\n", (u_longlong_t)subobjs[i]);
 	}
 	kmem_free(subobjs, doi.doi_max_offset);
 }

cmd/zfs/zfs_iter.c

@@ -444,13 +444,13 @@ zfs_for_each(int argc, char **argv, int flags, zfs_type_t types,
 
 		/*
 		 * If we're recursive, then we always allow filesystems as
-		 * arguments.  If we also are interested in snapshots, then we
+		 * arguments.  If we also are interested in snapshots or
-		 * can take volumes as well.
+		 * bookmarks, then we can take volumes as well.
 		 */
 		argtype = types;
 		if (flags & ZFS_ITER_RECURSE) {
 			argtype |= ZFS_TYPE_FILESYSTEM;
-			if (types & ZFS_TYPE_SNAPSHOT)
+			if (types & (ZFS_TYPE_SNAPSHOT | ZFS_TYPE_BOOKMARK))
 				argtype |= ZFS_TYPE_VOLUME;
 		}
 

cmd/ztest/Makefile.am

@@ -1,6 +1,8 @@
 include $(top_srcdir)/config/Rules.am
 
-AM_CFLAGS += $(DEBUG_STACKFLAGS) $(FRAME_LARGER_THAN)
+# -Wnoformat-truncation to get rid of compiler warning for unchecked
+#  truncating snprintfs on gcc 7.1.1.
+AM_CFLAGS += $(DEBUG_STACKFLAGS) $(FRAME_LARGER_THAN) $(NO_FORMAT_TRUNCATION)
 
 DEFAULT_INCLUDES += \
 	-I$(top_srcdir)/include \

config/Rules.am

@@ -7,7 +7,8 @@ AM_CFLAGS += ${NO_BOOL_COMPARE}
 AM_CFLAGS += -fno-strict-aliasing
 AM_CPPFLAGS  = -D_GNU_SOURCE -D__EXTENSIONS__ -D_REENTRANT
 AM_CPPFLAGS += -D_POSIX_PTHREAD_SEMANTICS -D_FILE_OFFSET_BITS=64
-AM_CPPFLAGS += -D_LARGEFILE64_SOURCE -DTEXT_DOMAIN=\"zfs-linux-user\"
+AM_CPPFLAGS += -D_LARGEFILE64_SOURCE -DHAVE_LARGE_STACKS=1
+AM_CPPFLAGS += -DTEXT_DOMAIN=\"zfs-linux-user\"
 AM_CPPFLAGS += -DLIBEXECDIR=\"$(libexecdir)\"
 AM_CPPFLAGS += -DRUNSTATEDIR=\"$(runstatedir)\"
 AM_CPPFLAGS += -DSBINDIR=\"$(sbindir)\"

config/kernel-acl.m4

@@ -39,6 +39,35 @@ AC_DEFUN([ZFS_AC_KERNEL_POSIX_ACL_RELEASE], [
 	])
 ])
 
+dnl #
+dnl # 3.14 API change,
+dnl # set_cached_acl() and forget_cached_acl() changed from inline to
+dnl # EXPORT_SYMBOL. In the former case, they may not be usable because of
+dnl # posix_acl_release. In the latter case, we can always use them.
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_SET_CACHED_ACL_USABLE], [
+	AC_MSG_CHECKING([whether set_cached_acl() is usable])
+	ZFS_LINUX_TRY_COMPILE([
+		#include <linux/module.h>
+		#include <linux/cred.h>
+		#include <linux/fs.h>
+		#include <linux/posix_acl.h>
+
+		MODULE_LICENSE("$ZFS_META_LICENSE");
+	],[
+		struct inode *ip = NULL;
+		struct posix_acl *acl = posix_acl_alloc(1, 0);
+		set_cached_acl(ip, ACL_TYPE_ACCESS, acl);
+		forget_cached_acl(ip, ACL_TYPE_ACCESS);
+	],[
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_SET_CACHED_ACL_USABLE, 1,
+		    [posix_acl_release() is usable])
+	],[
+		AC_MSG_RESULT(no)
+	])
+])
+
 dnl #
 dnl # 3.1 API change,
 dnl # posix_acl_chmod_masq() is not exported anymore and posix_acl_chmod()
@@ -249,13 +278,38 @@ AC_DEFUN([ZFS_AC_KERNEL_INODE_OPERATIONS_GET_ACL], [
 	])
 ])
 
+dnl #
+dnl # 3.14 API change,
+dnl # Check if inode_operations contains the function set_acl
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_INODE_OPERATIONS_SET_ACL], [
+	AC_MSG_CHECKING([whether iops->set_acl() exists])
+	ZFS_LINUX_TRY_COMPILE([
+		#include <linux/fs.h>
+
+		int set_acl_fn(struct inode *inode, struct posix_acl *acl, int type)
+		    { return 0; }
+
+		static const struct inode_operations
+		    iops __attribute__ ((unused)) = {
+			.set_acl = set_acl_fn,
+		};
+	],[
+	],[
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_SET_ACL, 1, [iops->set_acl() exists])
+	],[
+		AC_MSG_RESULT(no)
+	])
+])
+
 dnl #
 dnl # 4.7 API change,
 dnl # The kernel get_acl will now check cache before calling i_op->get_acl and
 dnl # do set_cached_acl after that, so i_op->get_acl don't need to do that
 dnl # anymore.
 dnl #
-AC_DEFUN([ZFS_AC_KERNE_GET_ACL_HANDLE_CACHE], [
+AC_DEFUN([ZFS_AC_KERNEL_GET_ACL_HANDLE_CACHE], [
 	AC_MSG_CHECKING([whether uncached_acl_sentinel() exists])
 	ZFS_LINUX_TRY_COMPILE([
 		#include <linux/fs.h>

config/kernel-aio-fsync.m4

@@ -0,0 +1,21 @@
+dnl #
+dnl # Linux 4.9-rc5+ ABI, removal of the .aio_fsync field
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_AIO_FSYNC], [
+	AC_MSG_CHECKING([whether fops->aio_fsync() exists])
+	ZFS_LINUX_TRY_COMPILE([
+		#include <linux/fs.h>
+
+		static const struct file_operations
+		    fops __attribute__ ((unused)) = {
+			.aio_fsync = NULL,
+		};
+	],[
+	],[
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_FILE_AIO_FSYNC, 1, [fops->aio_fsync() exists])
+	],[
+		AC_MSG_RESULT(no)
+	])
+])
+

config/kernel-bdi-setup-and-register.m4

@@ -1,38 +0,0 @@
-dnl #
-dnl # 2.6.32 - 2.6.33, bdi_setup_and_register() is not exported.
-dnl # 2.6.34 - 3.19, bdi_setup_and_register() takes 3 arguments.
-dnl # 4.0 - x.y, bdi_setup_and_register() takes 2 arguments.
-dnl #
-AC_DEFUN([ZFS_AC_KERNEL_BDI_SETUP_AND_REGISTER], [
-	AC_MSG_CHECKING([whether bdi_setup_and_register() wants 2 args])
-	ZFS_LINUX_TRY_COMPILE_SYMBOL([
-		#include <linux/backing-dev.h>
-		struct backing_dev_info bdi;
-	], [
-		char *name = "bdi";
-		int error __attribute__((unused)) =
-		    bdi_setup_and_register(&bdi, name);
-	], [bdi_setup_and_register], [mm/backing-dev.c], [
-		AC_MSG_RESULT(yes)
-		AC_DEFINE(HAVE_2ARGS_BDI_SETUP_AND_REGISTER, 1,
-		    [bdi_setup_and_register() wants 2 args])
-	], [
-		AC_MSG_RESULT(no)
-		AC_MSG_CHECKING([whether bdi_setup_and_register() wants 3 args])
-		ZFS_LINUX_TRY_COMPILE_SYMBOL([
-			#include <linux/backing-dev.h>
-			struct backing_dev_info bdi;
-		], [
-			char *name = "bdi";
-			unsigned int cap = BDI_CAP_MAP_COPY;
-			int error __attribute__((unused)) =
-			    bdi_setup_and_register(&bdi, name, cap);
-		], [bdi_setup_and_register], [mm/backing-dev.c], [
-			AC_MSG_RESULT(yes)
-			AC_DEFINE(HAVE_3ARGS_BDI_SETUP_AND_REGISTER, 1,
-			    [bdi_setup_and_register() wants 3 args])
-		], [
-			AC_MSG_RESULT(no)
-		])
-	])
-])

config/kernel-bdi.m4

@@ -0,0 +1,56 @@
+dnl #
+dnl # 2.6.32 - 2.6.33, bdi_setup_and_register() is not exported.
+dnl # 2.6.34 - 3.19, bdi_setup_and_register() takes 3 arguments.
+dnl # 4.0 - 4.11, bdi_setup_and_register() takes 2 arguments.
+dnl # 4.12 - x.y, super_setup_bdi_name() new interface.
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_BDI], [
+	AC_MSG_CHECKING([whether super_setup_bdi_name() exists])
+	ZFS_LINUX_TRY_COMPILE_SYMBOL([
+		#include <linux/fs.h>
+		struct super_block sb;
+	], [
+		char *name = "bdi";
+		int error __attribute__((unused)) =
+		    super_setup_bdi_name(&sb, name);
+	], [super_setup_bdi_name], [fs/super.c], [
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_SUPER_SETUP_BDI_NAME, 1,
+                    [super_setup_bdi_name() exits])
+	], [
+		AC_MSG_RESULT(no)
+		AC_MSG_CHECKING(
+		    [whether bdi_setup_and_register() wants 2 args])
+		ZFS_LINUX_TRY_COMPILE_SYMBOL([
+			#include <linux/backing-dev.h>
+			struct backing_dev_info bdi;
+		], [
+			char *name = "bdi";
+			int error __attribute__((unused)) =
+			    bdi_setup_and_register(&bdi, name);
+		], [bdi_setup_and_register], [mm/backing-dev.c], [
+			AC_MSG_RESULT(yes)
+			AC_DEFINE(HAVE_2ARGS_BDI_SETUP_AND_REGISTER, 1,
+			    [bdi_setup_and_register() wants 2 args])
+		], [
+			AC_MSG_RESULT(no)
+			AC_MSG_CHECKING(
+			    [whether bdi_setup_and_register() wants 3 args])
+			ZFS_LINUX_TRY_COMPILE_SYMBOL([
+				#include <linux/backing-dev.h>
+				struct backing_dev_info bdi;
+			], [
+				char *name = "bdi";
+				unsigned int cap = BDI_CAP_MAP_COPY;
+				int error __attribute__((unused)) =
+				    bdi_setup_and_register(&bdi, name, cap);
+			], [bdi_setup_and_register], [mm/backing-dev.c], [
+				AC_MSG_RESULT(yes)
+				AC_DEFINE(HAVE_3ARGS_BDI_SETUP_AND_REGISTER, 1,
+				    [bdi_setup_and_register() wants 3 args])
+			], [
+				AC_MSG_RESULT(no)
+			])
+		])
+	])
+])

config/kernel-bio-op.m4

@@ -10,7 +10,7 @@ AC_DEFUN([ZFS_AC_KERNEL_REQ_OP_DISCARD], [
 	ZFS_LINUX_TRY_COMPILE([
 		#include <linux/blk_types.h>
 	],[
-		enum req_op op __attribute__ ((unused)) = REQ_OP_DISCARD;
+		int op __attribute__ ((unused)) = REQ_OP_DISCARD;
 	],[
 		AC_MSG_RESULT(yes)
 		AC_DEFINE(HAVE_REQ_OP_DISCARD, 1,
@@ -25,10 +25,10 @@ AC_DEFUN([ZFS_AC_KERNEL_REQ_OP_SECURE_ERASE], [
 	ZFS_LINUX_TRY_COMPILE([
 		#include <linux/blk_types.h>
 	],[
-		enum req_op op __attribute__ ((unused)) = REQ_OP_SECURE_ERASE;
+		int op __attribute__ ((unused)) = REQ_OP_SECURE_ERASE;
 	],[
 		AC_MSG_RESULT(yes)
-		AC_DEFINE(HAVE_REQ_OP_SECURE_DISCARD, 1,
+		AC_DEFINE(HAVE_REQ_OP_SECURE_ERASE, 1,
 		    [REQ_OP_SECURE_ERASE is defined])
 	],[
 		AC_MSG_RESULT(no)
@@ -41,7 +41,7 @@ AC_DEFUN([ZFS_AC_KERNEL_REQ_OP_FLUSH], [
 	ZFS_LINUX_TRY_COMPILE([
 		#include <linux/blk_types.h>
 	],[
-		enum req_op op __attribute__ ((unused)) = REQ_OP_FLUSH;
+		int op __attribute__ ((unused)) = REQ_OP_FLUSH;
 	],[
 		AC_MSG_RESULT(yes)
 		AC_DEFINE(HAVE_REQ_OP_FLUSH, 1,
@@ -65,3 +65,20 @@ AC_DEFUN([ZFS_AC_KERNEL_BIO_BI_OPF], [
 		AC_MSG_RESULT(no)
 	])
 ])
+
+AC_DEFUN([ZFS_AC_KERNEL_HAVE_BIO_SET_OP_ATTRS], [
+	AC_MSG_CHECKING([whether bio_set_op_attrs is available])
+	ZFS_LINUX_TRY_COMPILE([
+		#include <linux/bio.h>
+	],[
+		struct bio *bio __attribute__ ((unused)) = NULL;
+
+		bio_set_op_attrs(bio, 0, 0);
+	],[
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_BIO_SET_OP_ATTRS, 1,
+		    [bio_set_op_attrs is available])
+	],[
+		AC_MSG_RESULT(no)
+	])
+])

config/kernel-blk-queue-unplug.m4

@@ -0,0 +1,44 @@
+dnl #
+dnl # 2.6.32-2.6.35 API - The BIO_RW_UNPLUG enum can be used as a hint
+dnl # to unplug the queue.
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_BLK_QUEUE_HAVE_BIO_RW_UNPLUG], [
+	AC_MSG_CHECKING([whether the BIO_RW_UNPLUG enum is available])
+	tmp_flags="$EXTRA_KCFLAGS"
+	EXTRA_KCFLAGS="${NO_UNUSED_BUT_SET_VARIABLE}"
+	ZFS_LINUX_TRY_COMPILE([
+		#include <linux/blkdev.h>
+	],[
+		extern enum bio_rw_flags rw;
+
+		rw = BIO_RW_UNPLUG;
+	],[
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_BLK_QUEUE_HAVE_BIO_RW_UNPLUG, 1,
+		          [BIO_RW_UNPLUG is available])
+	],[
+		AC_MSG_RESULT(no)
+	])
+	EXTRA_KCFLAGS="$tmp_flags"
+])
+
+AC_DEFUN([ZFS_AC_KERNEL_BLK_QUEUE_HAVE_BLK_PLUG], [
+	AC_MSG_CHECKING([whether struct blk_plug is available])
+	tmp_flags="$EXTRA_KCFLAGS"
+	EXTRA_KCFLAGS="${NO_UNUSED_BUT_SET_VARIABLE}"
+	ZFS_LINUX_TRY_COMPILE([
+		#include <linux/blkdev.h>
+	],[
+		struct blk_plug plug;
+
+		blk_start_plug(&plug);
+		blk_finish_plug(&plug);
+	],[
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_BLK_QUEUE_HAVE_BLK_PLUG, 1,
+		          [struct blk_plug is available])
+	],[
+		AC_MSG_RESULT(no)
+	])
+	EXTRA_KCFLAGS="$tmp_flags"
+])

config/kernel-current-time.m4

@@ -0,0 +1,19 @@
+dnl #
+dnl # 4.9, current_time() added
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_CURRENT_TIME],
+	[AC_MSG_CHECKING([whether current_time() exists])
+	ZFS_LINUX_TRY_COMPILE_SYMBOL([
+		#include <linux/fs.h>
+	], [
+		struct inode ip;
+		struct timespec now __attribute__ ((unused));
+
+		now = current_time(&ip);
+	], [current_time], [fs/inode.c], [
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_CURRENT_TIME, 1, [current_time() exists])
+	], [
+		AC_MSG_RESULT(no)
+	])
+])

config/kernel-generic_readlink.m4

@@ -0,0 +1,22 @@
+dnl #
+dnl # 4.10 API
+dnl #
+dnl # NULL inode_operations.readlink implies generic_readlink(), which
+dnl # has been made static.
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_GENERIC_READLINK_GLOBAL], [
+	AC_MSG_CHECKING([whether generic_readlink is global])
+	ZFS_LINUX_TRY_COMPILE([
+		#include <linux/fs.h>
+	],[
+		int i __attribute__ ((unused));
+
+		i = generic_readlink(NULL, NULL, 0);
+	],[
+		AC_MSG_RESULT([yes])
+		AC_DEFINE(HAVE_GENERIC_READLINK, 1,
+		          [generic_readlink is global])
+	],[
+		AC_MSG_RESULT([no])
+	])
+])

config/kernel-inode-getattr.m4

@@ -0,0 +1,67 @@
+dnl #
+dnl # Linux 4.11 API
+dnl # See torvalds/linux@a528d35
+dnl #
+AC_DEFUN([ZFS_AC_PATH_KERNEL_IOPS_GETATTR], [
+	AC_MSG_CHECKING([whether iops->getattr() takes a path])
+	ZFS_LINUX_TRY_COMPILE([
+		#include <linux/fs.h>
+
+		int test_getattr(
+		    const struct path *p, struct kstat *k,
+		    u32 request_mask, unsigned int query_flags)
+		    { return 0; }
+
+		static const struct inode_operations
+		    iops __attribute__ ((unused)) = {
+			.getattr = test_getattr,
+		};
+	],[
+	],[
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_PATH_IOPS_GETATTR, 1,
+		    [iops->getattr() takes a path])
+	],[
+		AC_MSG_RESULT(no)
+	])
+])
+
+
+
+dnl #
+dnl # Linux 3.9 - 4.10 API
+dnl #
+AC_DEFUN([ZFS_AC_VFSMOUNT_KERNEL_IOPS_GETATTR], [
+	AC_MSG_CHECKING([whether iops->getattr() takes a vfsmount])
+	ZFS_LINUX_TRY_COMPILE([
+		#include <linux/fs.h>
+
+		int test_getattr(
+		    struct vfsmount *mnt, struct dentry *d,
+		    struct kstat *k)
+		    { return 0; }
+
+		static const struct inode_operations
+		    iops __attribute__ ((unused)) = {
+			.getattr = test_getattr,
+		};
+	],[
+	],[
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_VFSMOUNT_IOPS_GETATTR, 1,
+		    [iops->getattr() takes a vfsmount])
+	],[
+		AC_MSG_RESULT(no)
+	])
+])
+
+
+dnl #
+dnl # The interface of the getattr callback from the inode_operations
+dnl # structure changed.  Also, the interface of the simple_getattr()
+dnl # function provided by the kernel changed.
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_INODE_OPERATIONS_GETATTR], [
+	ZFS_AC_PATH_KERNEL_IOPS_GETATTR
+	ZFS_AC_VFSMOUNT_KERNEL_IOPS_GETATTR
+])

config/kernel-lookup-bdev.m4

@@ -1,17 +1,29 @@
 dnl #
-dnl # 2.6.27 API change
+dnl # 2.6.27, lookup_bdev() was exported.
-dnl # lookup_bdev() was exported.
+dnl # 4.4.0-6.21 - x.y on Ubuntu, lookup_bdev() takes 2 arguments.
 dnl #
 AC_DEFUN([ZFS_AC_KERNEL_LOOKUP_BDEV],
-	[AC_MSG_CHECKING([whether lookup_bdev() is available])
+	[AC_MSG_CHECKING([whether lookup_bdev() wants 1 arg])
 	ZFS_LINUX_TRY_COMPILE_SYMBOL([
 		#include <linux/fs.h>
 	], [
 		lookup_bdev(NULL);
 	], [lookup_bdev], [fs/block_dev.c], [
 		AC_MSG_RESULT(yes)
-		AC_DEFINE(HAVE_LOOKUP_BDEV, 1, [lookup_bdev() is available])
+		AC_DEFINE(HAVE_1ARG_LOOKUP_BDEV, 1, [lookup_bdev() wants 1 arg])
+	], [
+		AC_MSG_RESULT(no)
+		AC_MSG_CHECKING([whether lookup_bdev() wants 2 args])
+		ZFS_LINUX_TRY_COMPILE_SYMBOL([
+			#include <linux/fs.h>
+		], [
+			lookup_bdev(NULL, FMODE_READ);
+		], [lookup_bdev], [fs/block_dev.c], [
+			AC_MSG_RESULT(yes)
+			AC_DEFINE(HAVE_2ARGS_LOOKUP_BDEV, 1,
+			    [lookup_bdev() wants 2 args])
 		], [
 			AC_MSG_RESULT(no)
 		])
 	])
+])

config/kernel-rename.m4

@@ -0,0 +1,25 @@
+dnl #
+dnl # 4.9 API change,
+dnl # iops->rename2() merged into iops->rename(), and iops->rename() now wants
+dnl # flags.
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_RENAME_WANTS_FLAGS], [
+	AC_MSG_CHECKING([whether iops->rename() wants flags])
+	ZFS_LINUX_TRY_COMPILE([
+		#include <linux/fs.h>
+		int rename_fn(struct inode *sip, struct dentry *sdp,
+			struct inode *tip, struct dentry *tdp,
+			unsigned int flags) { return 0; }
+
+		static const struct inode_operations
+		    iops __attribute__ ((unused)) = {
+			.rename = rename_fn,
+		};
+	],[
+	],[
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_RENAME_WANTS_FLAGS, 1, [iops->rename() wants flags])
+	],[
+		AC_MSG_RESULT(no)
+	])
+])

config/kernel-setattr-prepare.m4

@@ -0,0 +1,23 @@
+dnl #
+dnl # 4.9 API change
+dnl # The inode_change_ok() function has been renamed setattr_prepare()
+dnl # and updated to take a dentry rather than an inode.
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_SETATTR_PREPARE],
+	[AC_MSG_CHECKING([whether setattr_prepare() is available])
+	ZFS_LINUX_TRY_COMPILE_SYMBOL([
+		#include <linux/fs.h>
+	], [
+		struct dentry *dentry = NULL;
+		struct iattr *attr = NULL;
+		int error;
+
+		error = setattr_prepare(dentry, attr);
+	], [setattr_prepare], [fs/attr.c], [
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_SETATTR_PREPARE, 1,
+		    [setattr_prepare() is available])
+	], [
+		AC_MSG_RESULT(no)
+	])
+])

config/kernel-vfs-rw-iterate.m4

@@ -1,5 +1,5 @@
 dnl #
-dnl # Linux 4.1.x API
+dnl # Linux 3.16 API
 dnl #
 AC_DEFUN([ZFS_AC_KERNEL_VFS_RW_ITERATE],
 	[AC_MSG_CHECKING([whether fops->read/write_iter() are available])
@@ -21,6 +21,47 @@ AC_DEFUN([ZFS_AC_KERNEL_VFS_RW_ITERATE],
 		AC_MSG_RESULT(yes)
 		AC_DEFINE(HAVE_VFS_RW_ITERATE, 1,
 			[fops->read/write_iter() are available])
+
+		ZFS_AC_KERNEL_NEW_SYNC_READ
+	],[
+		AC_MSG_RESULT(no)
+	])
+])
+
+dnl #
+dnl # Linux 4.1 API
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_NEW_SYNC_READ],
+	[AC_MSG_CHECKING([whether new_sync_read() is available])
+	ZFS_LINUX_TRY_COMPILE([
+		#include <linux/fs.h>
+	],[
+		new_sync_read(NULL, NULL, 0, NULL);
+	],[
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_NEW_SYNC_READ, 1,
+			[new_sync_read() is available])
+	],[
+		AC_MSG_RESULT(no)
+	])
+])
+
+dnl #
+dnl # Linux 4.1.x API
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_GENERIC_WRITE_CHECKS],
+	[AC_MSG_CHECKING([whether generic_write_checks() takes kiocb])
+	ZFS_LINUX_TRY_COMPILE([
+		#include <linux/fs.h>
+
+	],[
+		struct kiocb *iocb = NULL;
+		struct iov_iter *iov = NULL;
+		generic_write_checks(iocb, iov);
+	],[
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_GENERIC_WRITE_CHECKS_KIOCB, 1,
+			[generic_write_checks() takes kiocb])
 	],[
 		AC_MSG_RESULT(no)
 	])

config/kernel-xattr-handler.m4

@@ -57,6 +57,31 @@ AC_DEFUN([ZFS_AC_KERNEL_XATTR_HANDLER_NAME], [
 	])
 ])
 
+dnl #
+dnl # 4.9 API change,
+dnl # iops->{set,get,remove}xattr and generic_{set,get,remove}xattr are
+dnl # removed. xattr operations will directly go through sb->s_xattr.
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_HAVE_GENERIC_SETXATTR], [
+	AC_MSG_CHECKING([whether generic_setxattr() exists])
+	ZFS_LINUX_TRY_COMPILE([
+		#include <linux/fs.h>
+		#include <linux/xattr.h>
+
+		static const struct inode_operations
+		    iops __attribute__ ((unused)) = {
+			.setxattr = generic_setxattr
+		};
+	],[
+	],[
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_GENERIC_SETXATTR, 1,
+		    [generic_setxattr() exists])
+	],[
+		AC_MSG_RESULT(no)
+	])
+])
+
 dnl #
 dnl # Supported xattr handler get() interfaces checked newest to oldest.
 dnl #

config/kernel.m4

@@ -33,8 +33,12 @@ AC_DEFUN([ZFS_AC_CONFIG_KERNEL], [
 	ZFS_AC_KERNEL_BLK_QUEUE_FLUSH
 	ZFS_AC_KERNEL_BLK_QUEUE_MAX_HW_SECTORS
 	ZFS_AC_KERNEL_BLK_QUEUE_MAX_SEGMENTS
+	ZFS_AC_KERNEL_BLK_QUEUE_HAVE_BIO_RW_UNPLUG
+	ZFS_AC_KERNEL_BLK_QUEUE_HAVE_BLK_PLUG
 	ZFS_AC_KERNEL_GET_DISK_RO
 	ZFS_AC_KERNEL_GET_GENDISK
+	ZFS_AC_KERNEL_HAVE_BIO_SET_OP_ATTRS
+	ZFS_AC_KERNEL_GENERIC_READLINK_GLOBAL
 	ZFS_AC_KERNEL_DISCARD_GRANULARITY
 	ZFS_AC_KERNEL_CONST_XATTR_HANDLER
 	ZFS_AC_KERNEL_XATTR_HANDLER_NAME
@@ -44,6 +48,7 @@ AC_DEFUN([ZFS_AC_CONFIG_KERNEL], [
 	ZFS_AC_KERNEL_INODE_OWNER_OR_CAPABLE
 	ZFS_AC_KERNEL_POSIX_ACL_FROM_XATTR_USERNS
 	ZFS_AC_KERNEL_POSIX_ACL_RELEASE
+	ZFS_AC_KERNEL_SET_CACHED_ACL_USABLE
 	ZFS_AC_KERNEL_POSIX_ACL_CHMOD
 	ZFS_AC_KERNEL_POSIX_ACL_EQUIV_MODE_WANTS_UMODE_T
 	ZFS_AC_KERNEL_POSIX_ACL_VALID_WITH_NS
@@ -52,7 +57,9 @@ AC_DEFUN([ZFS_AC_CONFIG_KERNEL], [
 	ZFS_AC_KERNEL_INODE_OPERATIONS_CHECK_ACL
 	ZFS_AC_KERNEL_INODE_OPERATIONS_CHECK_ACL_WITH_FLAGS
 	ZFS_AC_KERNEL_INODE_OPERATIONS_GET_ACL
-	ZFS_AC_KERNE_GET_ACL_HANDLE_CACHE
+	ZFS_AC_KERNEL_INODE_OPERATIONS_SET_ACL
+	ZFS_AC_KERNEL_INODE_OPERATIONS_GETATTR
+	ZFS_AC_KERNEL_GET_ACL_HANDLE_CACHE
 	ZFS_AC_KERNEL_SHOW_OPTIONS
 	ZFS_AC_KERNEL_FILE_INODE
 	ZFS_AC_KERNEL_FSYNC
@@ -61,6 +68,7 @@ AC_DEFUN([ZFS_AC_CONFIG_KERNEL], [
 	ZFS_AC_KERNEL_NR_CACHED_OBJECTS
 	ZFS_AC_KERNEL_FREE_CACHED_OBJECTS
 	ZFS_AC_KERNEL_FALLOCATE
+	ZFS_AC_KERNEL_AIO_FSYNC
 	ZFS_AC_KERNEL_MKDIR_UMODE_T
 	ZFS_AC_KERNEL_LOOKUP_NAMEIDATA
 	ZFS_AC_KERNEL_CREATE_NAMEIDATA
@@ -71,6 +79,7 @@ AC_DEFUN([ZFS_AC_CONFIG_KERNEL], [
 	ZFS_AC_KERNEL_ENCODE_FH_WITH_INODE
 	ZFS_AC_KERNEL_COMMIT_METADATA
 	ZFS_AC_KERNEL_CLEAR_INODE
+	ZFS_AC_KERNEL_SETATTR_PREPARE
 	ZFS_AC_KERNEL_INSERT_INODE_LOCKED
 	ZFS_AC_KERNEL_D_MAKE_ROOT
 	ZFS_AC_KERNEL_D_OBTAIN_ALIAS
@@ -87,17 +96,21 @@ AC_DEFUN([ZFS_AC_CONFIG_KERNEL], [
 	ZFS_AC_KERNEL_SHRINK_CONTROL_HAS_NID
 	ZFS_AC_KERNEL_S_INSTANCES_LIST_HEAD
 	ZFS_AC_KERNEL_S_D_OP
-	ZFS_AC_KERNEL_BDI_SETUP_AND_REGISTER
+	ZFS_AC_KERNEL_BDI
 	ZFS_AC_KERNEL_SET_NLINK
 	ZFS_AC_KERNEL_ELEVATOR_CHANGE
 	ZFS_AC_KERNEL_5ARG_SGET
 	ZFS_AC_KERNEL_LSEEK_EXECUTE
 	ZFS_AC_KERNEL_VFS_ITERATE
 	ZFS_AC_KERNEL_VFS_RW_ITERATE
+	ZFS_AC_KERNEL_GENERIC_WRITE_CHECKS
 	ZFS_AC_KERNEL_KMAP_ATOMIC_ARGS
 	ZFS_AC_KERNEL_FOLLOW_DOWN_ONE
 	ZFS_AC_KERNEL_MAKE_REQUEST_FN
 	ZFS_AC_KERNEL_GENERIC_IO_ACCT
+	ZFS_AC_KERNEL_RENAME_WANTS_FLAGS
+	ZFS_AC_KERNEL_HAVE_GENERIC_SETXATTR
+	ZFS_AC_KERNEL_CURRENT_TIME
 
 	AS_IF([test "$LINUX_OBJ" != "$LINUX"], [
 		KERNELMAKE_PARAMS="$KERNELMAKE_PARAMS O=$LINUX_OBJ"
@@ -468,9 +481,35 @@ AC_DEFUN([ZFS_AC_KERNEL_CONFIG], [
 		])
 	])
 
+	ZFS_AC_KERNEL_CONFIG_THREAD_SIZE
 	ZFS_AC_KERNEL_CONFIG_DEBUG_LOCK_ALLOC
 ])
 
+dnl #
+dnl # Check configured THREAD_SIZE
+dnl #
+dnl # The stack size will vary by architecture, but as of Linux 3.15 on x86_64
+dnl # the default thread stack size was increased to 16K from 8K.  Therefore,
+dnl # on newer kernels and some architectures stack usage optimizations can be
+dnl # conditionally applied to improve performance without negatively impacting
+dnl # stability.
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_CONFIG_THREAD_SIZE], [
+	AC_MSG_CHECKING([whether kernel was built with 16K or larger stacks])
+	ZFS_LINUX_TRY_COMPILE([
+		#include <linux/module.h>
+	],[
+		#if (THREAD_SIZE < 16384)
+		#error "THREAD_SIZE is less than 16K"
+		#endif
+	],[
+		AC_MSG_RESULT([yes])
+		AC_DEFINE(HAVE_LARGE_STACKS, 1, [kernel has large stacks])
+	],[
+		AC_MSG_RESULT([no])
+	])
+])
+
 dnl #
 dnl # Check CONFIG_DEBUG_LOCK_ALLOC
 dnl #
@@ -580,7 +619,7 @@ dnl #
 dnl # ZFS_LINUX_CONFIG
 dnl #
 AC_DEFUN([ZFS_LINUX_CONFIG],
-	[AC_MSG_CHECKING([whether Linux was built with CONFIG_$1])
+	[AC_MSG_CHECKING([whether kernel was built with CONFIG_$1])
 	ZFS_LINUX_TRY_COMPILE([
 		#include <linux/module.h>
 	],[

config/user-makedev.m4

@@ -0,0 +1,39 @@
+dnl #
+dnl # glibc 2.25
+dnl #
+AC_DEFUN([ZFS_AC_CONFIG_USER_MAKEDEV_IN_SYSMACROS], [
+	AC_MSG_CHECKING([makedev() is declared in sys/sysmacros.h])
+	AC_TRY_COMPILE(
+	[
+		#include <sys/sysmacros.h>
+	],[
+		int k;
+		k = makedev(0,0);
+	],[
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_MAKEDEV_IN_SYSMACROS, 1,
+		    [makedev() is declared in sys/sysmacros.h])
+	],[
+		AC_MSG_RESULT(no)
+	])
+])
+
+dnl #
+dnl # glibc X < Y < 2.25
+dnl #
+AC_DEFUN([ZFS_AC_CONFIG_USER_MAKEDEV_IN_MKDEV], [
+	AC_MSG_CHECKING([makedev() is declared in sys/mkdev.h])
+	AC_TRY_COMPILE(
+	[
+		#include <sys/mkdev.h>
+	],[
+		int k;
+		k = makedev(0,0);
+	],[
+		AC_MSG_RESULT(yes)
+		AC_DEFINE(HAVE_MAKEDEV_IN_MKDEV, 1,
+		    [makedev() is declared in sys/mkdev.h])
+	],[
+		AC_MSG_RESULT(no)
+	])
+])

config/user-no-format-truncation.m4

@@ -0,0 +1,22 @@
+dnl #
+dnl # Check if gcc supports -Wno-format-truncation option.
+dnl #
+AC_DEFUN([ZFS_AC_CONFIG_USER_NO_FORMAT_TRUNCATION], [
+	AC_MSG_CHECKING([for -Wno-format-truncation support])
+
+	saved_flags="$CFLAGS"
+	CFLAGS="$CFLAGS -Wno-format-truncation"
+
+	AC_COMPILE_IFELSE([AC_LANG_PROGRAM([], [])],
+	[
+		NO_FORMAT_TRUNCATION=-Wno-format-truncation
+		AC_MSG_RESULT([yes])
+	],
+	[
+		NO_FORMAT_TRUNCATION=
+		AC_MSG_RESULT([no])
+	])
+
+	CFLAGS="$saved_flags"
+	AC_SUBST([NO_FORMAT_TRUNCATION])
+])

config/user.m4

@@ -13,6 +13,9 @@ AC_DEFUN([ZFS_AC_CONFIG_USER], [
 	ZFS_AC_CONFIG_USER_LIBBLKID
 	ZFS_AC_CONFIG_USER_FRAME_LARGER_THAN
 	ZFS_AC_CONFIG_USER_RUNSTATEDIR
+	ZFS_AC_CONFIG_USER_MAKEDEV_IN_SYSMACROS
+	ZFS_AC_CONFIG_USER_MAKEDEV_IN_MKDEV
+	ZFS_AC_CONFIG_USER_NO_FORMAT_TRUNCATION
 dnl #
 dnl #	Checks for library functions
 	AC_CHECK_FUNCS([mlockall])

etc/systemd/system/zfs-mount.service.in

@@ -11,6 +11,7 @@ Before=local-fs.target
 Type=oneshot
 RemainAfterExit=yes
 ExecStart=@sbindir@/zfs mount -a
+WorkingDirectory=-/sbin/
 
 [Install]
 WantedBy=zfs-share.service

include/libzfs_impl.h

@@ -46,11 +46,6 @@
 extern "C" {
 #endif
 
-#ifdef	VERIFY
-#undef	VERIFY
-#endif
-#define	VERIFY	verify
-
 typedef struct libzfs_fru {
 	char *zf_device;
 	char *zf_fru;

include/linux/blkdev_compat.h

@@ -261,12 +261,21 @@ bio_set_flags_failfast(struct block_device *bdev, int *flags)
 
 /*
  * 2.6.27 API change
- * The function was exported for use, prior to this it existed by the
+ * The function was exported for use, prior to this it existed but the
  * symbol was not exported.
+ *
+ * 4.4.0-6.21 API change for Ubuntu
+ * lookup_bdev() gained a second argument, FMODE_*, to check inode permissions.
  */
-#ifndef HAVE_LOOKUP_BDEV
+#ifdef HAVE_1ARG_LOOKUP_BDEV
-#define	lookup_bdev(path)		ERR_PTR(-ENOTSUP)
+#define	vdev_lookup_bdev(path)	lookup_bdev(path)
-#endif
+#else
+#ifdef HAVE_2ARGS_LOOKUP_BDEV
+#define	vdev_lookup_bdev(path)	lookup_bdev(path, 0)
+#else
+#define	vdev_lookup_bdev(path)	ERR_PTR(-ENOTSUP)
+#endif /* HAVE_2ARGS_LOOKUP_BDEV */
+#endif /* HAVE_1ARG_LOOKUP_BDEV */
 
 /*
  * 2.6.30 API change
@@ -292,20 +301,59 @@ bio_set_flags_failfast(struct block_device *bdev, int *flags)
 #endif /* HAVE_BDEV_LOGICAL_BLOCK_SIZE */
 #endif /* HAVE_BDEV_PHYSICAL_BLOCK_SIZE */
 
+#ifndef HAVE_BIO_SET_OP_ATTRS
 /*
- * 2.6.37 API change
+ * Kernels without bio_set_op_attrs use bi_rw for the bio flags.
- * The WRITE_FLUSH, WRITE_FUA, and WRITE_FLUSH_FUA flags have been
- * introduced as a replacement for WRITE_BARRIER.  This was done to
- * allow richer semantics to be expressed to the block layer.  It is
- * the block layers responsibility to choose the correct way to
- * implement these semantics.
  */
-#ifdef WRITE_FLUSH_FUA
+static inline void
-#define	VDEV_WRITE_FLUSH_FUA		WRITE_FLUSH_FUA
+bio_set_op_attrs(struct bio *bio, unsigned rw, unsigned flags)
-#else
+{
-#define	VDEV_WRITE_FLUSH_FUA		WRITE_BARRIER
+	bio->bi_rw |= rw | flags;
+}
 #endif
 
+/*
+ * bio_set_flush - Set the appropriate flags in a bio to guarantee
+ * data are on non-volatile media on completion.
+ *
+ * 2.6.X - 2.6.36 API,
+ *   WRITE_BARRIER - Tells the block layer to commit all previously submitted
+ *   writes to stable storage before this one is started and that the current
+ *   write is on stable storage upon completion.  Also prevents reordering
+ *   on both sides of the current operation.
+ *
+ * 2.6.37 - 4.8 API,
+ *   Introduce  WRITE_FLUSH, WRITE_FUA, and WRITE_FLUSH_FUA flags as a
+ *   replacement for WRITE_BARRIER to allow expressing richer semantics
+ *   to the block layer.  It's up to the block layer to implement the
+ *   semantics correctly. Use the WRITE_FLUSH_FUA flag combination.
+ *
+ * 4.8 - 4.9 API,
+ *   REQ_FLUSH was renamed to REQ_PREFLUSH.  For consistency with previous
+ *   ZoL releases, prefer the WRITE_FLUSH_FUA flag set if it's available.
+ *
+ * 4.10 API,
+ *   The read/write flags and their modifiers, including WRITE_FLUSH,
+ *   WRITE_FUA and WRITE_FLUSH_FUA were removed from fs.h in
+ *   torvalds/linux@70fd7614 and replaced by direct flag modification
+ *   of the REQ_ flags in bio->bi_opf.  Use REQ_PREFLUSH.
+ */
+static inline void
+bio_set_flush(struct bio *bio)
+{
+#if defined(REQ_PREFLUSH)	/* >= 4.10 */
+	bio_set_op_attrs(bio, 0, REQ_PREFLUSH);
+#elif defined(WRITE_FLUSH_FUA)	/* >= 2.6.37 and <= 4.9 */
+	bio_set_op_attrs(bio, 0, WRITE_FLUSH_FUA);
+#elif defined(WRITE_BARRIER)	/* < 2.6.37 */
+	bio_set_op_attrs(bio, 0, WRITE_BARRIER);
+#else
+#error	"Allowing the build will cause bio_set_flush requests to be ignored."
+	"Please file an issue report at: "
+	"https://github.com/zfsonlinux/zfs/issues/new"
+#endif
+}
+
 /*
  * 4.8 - 4.x API,
  *   REQ_OP_FLUSH
@@ -324,6 +372,7 @@ bio_set_flags_failfast(struct block_device *bdev, int *flags)
  * and the new preflush behavior introduced in Linux 4.8.  This is correct
  * in all cases but may have a performance impact for some kernels.  It
  * has the advantage of minimizing kernel specific changes in the zvol code.
+ *
  */
 static inline boolean_t
 bio_is_flush(struct bio *bio)
@@ -376,16 +425,20 @@ bio_is_fua(struct bio *bio)
  *
  * In all cases the normal I/O path is used for discards.  The only
  * difference is how the kernel tags individual I/Os as discards.
+ *
+ * Note that 2.6.32 era kernels provide both BIO_RW_DISCARD and REQ_DISCARD,
+ * where BIO_RW_DISCARD is the correct interface.  Therefore, it is important
+ * that the HAVE_BIO_RW_DISCARD check occur before the REQ_DISCARD check.
  */
 static inline boolean_t
 bio_is_discard(struct bio *bio)
 {
 #if defined(HAVE_REQ_OP_DISCARD)
 	return (bio_op(bio) == REQ_OP_DISCARD);
-#elif defined(REQ_DISCARD)
-	return (bio->bi_rw & REQ_DISCARD);
 #elif defined(HAVE_BIO_RW_DISCARD)
 	return (bio->bi_rw & (1 << BIO_RW_DISCARD));
+#elif defined(REQ_DISCARD)
+	return (bio->bi_rw & REQ_DISCARD);
 #else
 #error	"Allowing the build will cause discard requests to become writes "
 	"potentially triggering the DMU_MAX_ACCESS assertion. Please file "

include/linux/vfs_compat.h

@@ -69,46 +69,116 @@ truncate_setsize(struct inode *ip, loff_t new)
 /*
  * 2.6.32 - 2.6.33, bdi_setup_and_register() is not available.
  * 2.6.34 - 3.19, bdi_setup_and_register() takes 3 arguments.
- * 4.0 - x.y, bdi_setup_and_register() takes 2 arguments.
+ * 4.0 - 4.11, bdi_setup_and_register() takes 2 arguments.
+ * 4.12 - x.y, super_setup_bdi_name() new interface.
  */
-#if defined(HAVE_2ARGS_BDI_SETUP_AND_REGISTER)
+#if defined(HAVE_SUPER_SETUP_BDI_NAME)
+extern atomic_long_t zfs_bdi_seq;
+
 static inline int
-zpl_bdi_setup_and_register(struct backing_dev_info *bdi, char *name)
+zpl_bdi_setup(struct super_block *sb, char *name)
 {
-	return (bdi_setup_and_register(bdi, name));
+	return super_setup_bdi_name(sb, "%.28s-%ld", name,
+	    atomic_long_inc_return(&zfs_bdi_seq));
+}
+static inline void
+zpl_bdi_destroy(struct super_block *sb)
+{
+}
+#elif defined(HAVE_2ARGS_BDI_SETUP_AND_REGISTER)
+static inline int
+zpl_bdi_setup(struct super_block *sb, char *name)
+{
+	struct backing_dev_info *bdi;
+	int error;
+
+	bdi = kmem_zalloc(sizeof (struct backing_dev_info), KM_SLEEP);
+	error = bdi_setup_and_register(bdi, name);
+	if (error) {
+		kmem_free(bdi, sizeof (struct backing_dev_info));
+		return (error);
+	}
+
+	sb->s_bdi = bdi;
+
+	return (0);
+}
+static inline void
+zpl_bdi_destroy(struct super_block *sb)
+{
+	struct backing_dev_info *bdi = sb->s_bdi;
+
+	bdi_destroy(bdi);
+	kmem_free(bdi, sizeof (struct backing_dev_info));
+	sb->s_bdi = NULL;
 }
 #elif defined(HAVE_3ARGS_BDI_SETUP_AND_REGISTER)
 static inline int
-zpl_bdi_setup_and_register(struct backing_dev_info *bdi, char *name)
+zpl_bdi_setup(struct super_block *sb, char *name)
 {
-	return (bdi_setup_and_register(bdi, name, BDI_CAP_MAP_COPY));
+	struct backing_dev_info *bdi;
+	int error;
+
+	bdi = kmem_zalloc(sizeof (struct backing_dev_info), KM_SLEEP);
+	error = bdi_setup_and_register(bdi, name, BDI_CAP_MAP_COPY);
+	if (error) {
+		kmem_free(sb->s_bdi, sizeof (struct backing_dev_info));
+		return (error);
+	}
+
+	sb->s_bdi = bdi;
+
+	return (0);
+}
+static inline void
+zpl_bdi_destroy(struct super_block *sb)
+{
+	struct backing_dev_info *bdi = sb->s_bdi;
+
+	bdi_destroy(bdi);
+	kmem_free(bdi, sizeof (struct backing_dev_info));
+	sb->s_bdi = NULL;
 }
 #else
 extern atomic_long_t zfs_bdi_seq;
 
 static inline int
-zpl_bdi_setup_and_register(struct backing_dev_info *bdi, char *name)
+zpl_bdi_setup(struct super_block *sb, char *name)
 {
-	char tmp[32];
+	struct backing_dev_info *bdi;
 	int error;
 
+	bdi = kmem_zalloc(sizeof (struct backing_dev_info), KM_SLEEP);
 	bdi->name = name;
 	bdi->capabilities = BDI_CAP_MAP_COPY;
 
 	error = bdi_init(bdi);
-	if (error)
-		return (error);
-
-	sprintf(tmp, "%.28s%s", name, "-%d");
-	error = bdi_register(bdi, NULL, tmp,
-	    atomic_long_inc_return(&zfs_bdi_seq));
 	if (error) {
-		bdi_destroy(bdi);
+		kmem_free(bdi, sizeof (struct backing_dev_info));
 		return (error);
 	}
 
+	error = bdi_register(bdi, NULL, "%.28s-%ld", name,
+	    atomic_long_inc_return(&zfs_bdi_seq));
+	if (error) {
+		bdi_destroy(bdi);
+		kmem_free(bdi, sizeof (struct backing_dev_info));
 		return (error);
 	}
+
+	sb->s_bdi = bdi;
+
+	return (0);
+}
+static inline void
+zpl_bdi_destroy(struct super_block *sb)
+{
+	struct backing_dev_info *bdi = sb->s_bdi;
+
+	bdi_destroy(bdi);
+	kmem_free(bdi, sizeof (struct backing_dev_info));
+	sb->s_bdi = NULL;
+}
 #endif
 
 /*
@@ -204,17 +274,9 @@ lseek_execute(
 #include <linux/posix_acl.h>
 
 #if defined(HAVE_POSIX_ACL_RELEASE) && !defined(HAVE_POSIX_ACL_RELEASE_GPL_ONLY)
-
 #define	zpl_posix_acl_release(arg)		posix_acl_release(arg)
-#define	zpl_set_cached_acl(ip, ty, n)		set_cached_acl(ip, ty, n)
-#define	zpl_forget_cached_acl(ip, ty)		forget_cached_acl(ip, ty)
-
 #else
-
+void zpl_posix_acl_release_impl(struct posix_acl *);
-static inline void
-zpl_posix_acl_free(void *arg) {
-	kfree(arg);
-}
 
 static inline void
 zpl_posix_acl_release(struct posix_acl *acl)
@@ -222,12 +284,15 @@ zpl_posix_acl_release(struct posix_acl *acl)
 	if ((acl == NULL) || (acl == ACL_NOT_CACHED))
 		return;
 
-	if (atomic_dec_and_test(&acl->a_refcount)) {
+	if (atomic_dec_and_test(&acl->a_refcount))
-		taskq_dispatch_delay(system_taskq, zpl_posix_acl_free, acl,
+		zpl_posix_acl_release_impl(acl);
-		    TQ_SLEEP, ddi_get_lbolt() + 60*HZ);
-	}
 }
+#endif /* HAVE_POSIX_ACL_RELEASE */
 
+#ifdef HAVE_SET_CACHED_ACL_USABLE
+#define	zpl_set_cached_acl(ip, ty, n)		set_cached_acl(ip, ty, n)
+#define	zpl_forget_cached_acl(ip, ty)		forget_cached_acl(ip, ty)
+#else
 static inline void
 zpl_set_cached_acl(struct inode *ip, int type, struct posix_acl *newer) {
 	struct posix_acl *older = NULL;
@@ -257,7 +322,7 @@ static inline void
 zpl_forget_cached_acl(struct inode *ip, int type) {
 	zpl_set_cached_acl(ip, type, (struct posix_acl *)ACL_NOT_CACHED);
 }
-#endif /* HAVE_POSIX_ACL_RELEASE */
+#endif /* HAVE_SET_CACHED_ACL_USABLE */
 
 #ifndef HAVE___POSIX_ACL_CHMOD
 #ifdef HAVE_POSIX_ACL_CHMOD
@@ -362,4 +427,69 @@ static inline struct inode *file_inode(const struct file *f)
 #define	zpl_follow_up(path)			follow_up(path)
 #endif
 
+/*
+ * 4.9 API change
+ */
+#ifndef HAVE_SETATTR_PREPARE
+static inline int
+setattr_prepare(struct dentry *dentry, struct iattr *ia)
+{
+	return (inode_change_ok(dentry->d_inode, ia));
+}
+#endif
+
+/*
+ * 4.11 API change
+ * These macros are defined by kernel 4.11.  We define them so that the same
+ * code builds under kernels < 4.11 and >= 4.11.  The macros are set to 0 so
+ * that it will create obvious failures if they are accidentally used when built
+ * against a kernel >= 4.11.
+ */
+
+#ifndef STATX_BASIC_STATS
+#define	STATX_BASIC_STATS	0
+#endif
+
+#ifndef AT_STATX_SYNC_AS_STAT
+#define	AT_STATX_SYNC_AS_STAT	0
+#endif
+
+/*
+ * 4.11 API change
+ * 4.11 takes struct path *, < 4.11 takes vfsmount *
+ */
+
+#ifdef HAVE_VFSMOUNT_IOPS_GETATTR
+#define	ZPL_GETATTR_WRAPPER(func)					\
+static int								\
+func(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)	\
+{									\
+	struct path path = { .mnt = mnt, .dentry = dentry };		\
+	return func##_impl(&path, stat, STATX_BASIC_STATS,		\
+	    AT_STATX_SYNC_AS_STAT);					\
+}
+#elif defined(HAVE_PATH_IOPS_GETATTR)
+#define	ZPL_GETATTR_WRAPPER(func)					\
+static int								\
+func(const struct path *path, struct kstat *stat, u32 request_mask,	\
+    unsigned int query_flags)						\
+{									\
+	return (func##_impl(path, stat, request_mask, query_flags));	\
+}
+#else
+#error
+#endif
+
+/*
+ * 4.9 API change
+ * Preferred interface to get the current FS time.
+ */
+#if !defined(HAVE_CURRENT_TIME)
+static inline struct timespec
+current_time(struct inode *ip)
+{
+	return (timespec_trunc(current_kernel_time(), ip->i_sb->s_time_gran));
+}
+#endif
+
 #endif /* _ZFS_VFS_H */

include/sys/mntent.h

@@ -68,8 +68,9 @@
 #define	MNTOPT_NOFAIL	"nofail"	/* no failure */
 #define	MNTOPT_RELATIME	"relatime"	/* allow relative time updates */
 #define	MNTOPT_NORELATIME "norelatime"	/* do not allow relative time updates */
-#define	MNTOPT_DFRATIME	"strictatime"	/* Deferred access time updates */
+#define	MNTOPT_STRICTATIME "strictatime" /* strict access time updates */
-#define	MNTOPT_NODFRATIME "nostrictatime" /* No Deferred access time updates */
+#define	MNTOPT_NOSTRICTATIME "nostrictatime" /* No strict access time updates */
+#define	MNTOPT_LAZYTIME "lazytime"	/* Defer access time writing */
 #define	MNTOPT_SETUID	"suid"		/* Both setuid and devices allowed */
 #define	MNTOPT_NOSETUID	"nosuid"	/* Neither setuid nor devices allowed */
 #define	MNTOPT_OWNER	"owner"		/* allow owner mount */

include/sys/refcount.h

@@ -40,6 +40,17 @@ extern "C" {
  */
 #define	FTAG ((char *)__func__)
 
+/*
+ * Starting with 4.11, torvalds/linux@f405df5, the linux kernel defines a
+ * refcount_t type of its own.  The macro below effectively changes references
+ * in the ZFS code from refcount_t to zfs_refcount_t at compile time, so that
+ * existing code need not be altered, reducing conflicts when landing openZFS
+ * patches.
+ */
+
+#define	refcount_t	zfs_refcount_t
+#define	refcount_add	zfs_refcount_add
+
 #ifdef	ZFS_DEBUG
 typedef struct reference {
 	list_node_t ref_link;
@@ -55,7 +66,7 @@ typedef struct refcount {
 	list_t rc_removed;
 	int64_t rc_count;
 	int64_t rc_removed_count;
-} refcount_t;
+} zfs_refcount_t;
 
 /* Note: refcount_t must be initialized with refcount_create[_untracked]() */
 
@@ -65,7 +76,7 @@ void refcount_destroy(refcount_t *rc);
 void refcount_destroy_many(refcount_t *rc, uint64_t number);
 int refcount_is_zero(refcount_t *rc);
 int64_t refcount_count(refcount_t *rc);
-int64_t refcount_add(refcount_t *rc, void *holder_tag);
+int64_t zfs_refcount_add(refcount_t *rc, void *holder_tag);
 int64_t refcount_remove(refcount_t *rc, void *holder_tag);
 int64_t refcount_add_many(refcount_t *rc, uint64_t number, void *holder_tag);
 int64_t refcount_remove_many(refcount_t *rc, uint64_t number, void *holder_tag);
@@ -86,7 +97,7 @@ typedef struct refcount {
 #define	refcount_destroy_many(rc, number) ((rc)->rc_count = 0)
 #define	refcount_is_zero(rc) ((rc)->rc_count == 0)
 #define	refcount_count(rc) ((rc)->rc_count)
-#define	refcount_add(rc, holder) atomic_add_64_nv(&(rc)->rc_count, 1)
+#define	zfs_refcount_add(rc, holder) atomic_add_64_nv(&(rc)->rc_count, 1)
 #define	refcount_remove(rc, holder) atomic_add_64_nv(&(rc)->rc_count, -1)
 #define	refcount_add_many(rc, number, holder) \
 	atomic_add_64_nv(&(rc)->rc_count, number)

include/sys/trace_acl.h

@@ -56,7 +56,6 @@ DECLARE_EVENT_CLASS(zfs_ace_class,
 	    __field(uint64_t,		z_mapcnt)
 	    __field(uint64_t,		z_gen)
 	    __field(uint64_t,		z_size)
-	    __array(uint64_t,		z_atime, 2)
 	    __field(uint64_t,		z_links)
 	    __field(uint64_t,		z_pflags)
 	    __field(uint64_t,		z_uid)
@@ -94,8 +93,6 @@ DECLARE_EVENT_CLASS(zfs_ace_class,
 	    __entry->z_mapcnt		= zn->z_mapcnt;
 	    __entry->z_gen		= zn->z_gen;
 	    __entry->z_size		= zn->z_size;
-	    __entry->z_atime[0]		= zn->z_atime[0];
-	    __entry->z_atime[1]		= zn->z_atime[1];
 	    __entry->z_links		= zn->z_links;
 	    __entry->z_pflags		= zn->z_pflags;
 	    __entry->z_uid		= zn->z_uid;
@@ -124,7 +121,7 @@ DECLARE_EVENT_CLASS(zfs_ace_class,
 	),
 	TP_printk("zn { id %llu unlinked %u atime_dirty %u "
 	    "zn_prefetch %u moved %u blksz %u seq %u "
-	    "mapcnt %llu gen %llu size %llu atime 0x%llx:0x%llx "
+	    "mapcnt %llu gen %llu size %llu "
 	    "links %llu pflags %llu uid %llu gid %llu "
 	    "sync_cnt %u mode 0x%x is_sa %d "
 	    "is_mapped %d is_ctldir %d is_stale %d inode { "
@@ -134,7 +131,7 @@ DECLARE_EVENT_CLASS(zfs_ace_class,
 	    __entry->z_id, __entry->z_unlinked, __entry->z_atime_dirty,
 	    __entry->z_zn_prefetch, __entry->z_moved, __entry->z_blksz,
 	    __entry->z_seq, __entry->z_mapcnt, __entry->z_gen,
-	    __entry->z_size, __entry->z_atime[0], __entry->z_atime[1],
+	    __entry->z_size,
 	    __entry->z_links, __entry->z_pflags, __entry->z_uid,
 	    __entry->z_gid, __entry->z_sync_cnt, __entry->z_mode,
 	    __entry->z_is_sa, __entry->z_is_mapped,

include/sys/vdev_disk.h

@@ -37,9 +37,5 @@ typedef struct vdev_disk {
 	struct block_device	*vd_bdev;
 } vdev_disk_t;
 
-extern int vdev_disk_physio(struct block_device *, caddr_t,
-			    size_t, uint64_t, int, int);
-extern int vdev_disk_read_rootlabel(char *, char *, nvlist_t **);
-
 #endif /* _KERNEL */
 #endif /* _SYS_VDEV_DISK_H */

include/sys/xvattr.h

@@ -225,7 +225,7 @@ typedef struct xvattr {
  * of requested attributes (xva_reqattrmap[]).
  */
 #define	XVA_SET_REQ(xvap, attr)					\
-	ASSERT((xvap)->xva_vattr.va_mask | AT_XVATTR);		\
+	ASSERT((xvap)->xva_vattr.va_mask & AT_XVATTR);		\
 	ASSERT((xvap)->xva_magic == XVA_MAGIC);			\
 	(xvap)->xva_reqattrmap[XVA_INDEX(attr)] |= XVA_ATTRBIT(attr)
 /*
@@ -233,7 +233,7 @@ typedef struct xvattr {
  * of requested attributes (xva_reqattrmap[]).
  */
 #define	XVA_CLR_REQ(xvap, attr)					\
-	ASSERT((xvap)->xva_vattr.va_mask | AT_XVATTR);		\
+	ASSERT((xvap)->xva_vattr.va_mask & AT_XVATTR);		\
 	ASSERT((xvap)->xva_magic == XVA_MAGIC);			\
 	(xvap)->xva_reqattrmap[XVA_INDEX(attr)] &= ~XVA_ATTRBIT(attr)
 
@@ -242,7 +242,7 @@ typedef struct xvattr {
  * of returned attributes (xva_rtnattrmap[]).
  */
 #define	XVA_SET_RTN(xvap, attr)					\
-	ASSERT((xvap)->xva_vattr.va_mask | AT_XVATTR);		\
+	ASSERT((xvap)->xva_vattr.va_mask & AT_XVATTR);		\
 	ASSERT((xvap)->xva_magic == XVA_MAGIC);			\
 	(XVA_RTNATTRMAP(xvap))[XVA_INDEX(attr)] |= XVA_ATTRBIT(attr)
 
@@ -251,7 +251,7 @@ typedef struct xvattr {
  * to see of the corresponding attribute bit is set.  If so, returns non-zero.
  */
 #define	XVA_ISSET_REQ(xvap, attr)					\
-	((((xvap)->xva_vattr.va_mask | AT_XVATTR) &&			\
+	((((xvap)->xva_vattr.va_mask & AT_XVATTR) &&			\
 		((xvap)->xva_magic == XVA_MAGIC) &&			\
 		((xvap)->xva_mapsize > XVA_INDEX(attr))) ?		\
 	((xvap)->xva_reqattrmap[XVA_INDEX(attr)] & XVA_ATTRBIT(attr)) :	0)
@@ -261,7 +261,7 @@ typedef struct xvattr {
  * to see of the corresponding attribute bit is set.  If so, returns non-zero.
  */
 #define	XVA_ISSET_RTN(xvap, attr)					\
-	((((xvap)->xva_vattr.va_mask | AT_XVATTR) &&			\
+	((((xvap)->xva_vattr.va_mask & AT_XVATTR) &&			\
 		((xvap)->xva_magic == XVA_MAGIC) &&			\
 		((xvap)->xva_mapsize > XVA_INDEX(attr))) ?		\
 	((XVA_RTNATTRMAP(xvap))[XVA_INDEX(attr)] & XVA_ATTRBIT(attr)) : 0)

include/sys/zfs_vfsops.h

@@ -64,7 +64,6 @@ typedef struct zfs_mntopts {
 
 typedef struct zfs_sb {
 	struct super_block *z_sb;	/* generic super_block */
-	struct backing_dev_info z_bdi;	/* generic backing dev info */
 	struct zfs_sb	*z_parent;	/* parent fs */
 	objset_t	*z_os;		/* objset reference */
 	zfs_mntopts_t	*z_mntopts;	/* passed mount options */

include/sys/zfs_znode.h

@@ -198,7 +198,6 @@ typedef struct znode {
 	uint64_t	z_mapcnt;	/* number of pages mapped to file */
 	uint64_t	z_gen;		/* generation (cached) */
 	uint64_t	z_size;		/* file size (cached) */
-	uint64_t	z_atime[2];	/* atime (cached) */
 	uint64_t	z_links;	/* file links (cached) */
 	uint64_t	z_pflags;	/* pflags (cached) */
 	uint64_t	z_uid;		/* uid fuid (cached) */
@@ -304,16 +303,12 @@ extern unsigned int zfs_object_mutex_size;
 #define	STATE_CHANGED		(ATTR_CTIME)
 #define	CONTENT_MODIFIED	(ATTR_MTIME | ATTR_CTIME)
 
-#define	ZFS_ACCESSTIME_STAMP(zsb, zp) \
-	if ((zsb)->z_atime && !(zfs_is_readonly(zsb))) \
-		zfs_tstamp_update_setup(zp, ACCESSED, NULL, NULL, B_FALSE);
-
 extern int	zfs_init_fs(zfs_sb_t *, znode_t **);
 extern void	zfs_set_dataprop(objset_t *);
 extern void	zfs_create_fs(objset_t *os, cred_t *cr, nvlist_t *,
     dmu_tx_t *tx);
 extern void	zfs_tstamp_update_setup(znode_t *, uint_t, uint64_t [2],
-    uint64_t [2], boolean_t);
+    uint64_t [2]);
 extern void	zfs_grow_blocksize(znode_t *, uint64_t, dmu_tx_t *);
 extern int	zfs_freesp(znode_t *, uint64_t, uint64_t, int, boolean_t);
 extern void	zfs_znode_init(void);

include/sys/zpl.h

@@ -76,7 +76,7 @@ extern ssize_t zpl_xattr_list(struct dentry *dentry, char *buf, size_t size);
 extern int zpl_xattr_security_init(struct inode *ip, struct inode *dip,
     const struct qstr *qstr);
 #if defined(CONFIG_FS_POSIX_ACL)
-extern int zpl_set_acl(struct inode *ip, int type, struct posix_acl *acl);
+extern int zpl_set_acl(struct inode *ip, struct posix_acl *acl, int type);
 extern struct posix_acl *zpl_get_acl(struct inode *ip, int type);
 #if !defined(HAVE_GET_ACL)
 #if defined(HAVE_CHECK_ACL_WITH_FLAGS)

lib/libspl/asm-i386/atomic.S

@@ -507,7 +507,7 @@
 	movl	16(%esp), %ebx
 	movl	20(%esp), %ecx
 	subl	%eax, %ebx
-	adcl	%edx, %ecx
+	sbbl	%edx, %ecx
 	lock
 	cmpxchg8b (%edi)
 	jne	1b

lib/libspl/getmntany.c

@@ -34,6 +34,7 @@
 #include <sys/mnttab.h>
 
 #include <sys/types.h>
+#include <sys/sysmacros.h>
 #include <sys/stat.h>
 #include <unistd.h>
 

lib/libspl/include/assert.h

@@ -31,69 +31,66 @@
 
 #include <stdio.h>
 #include <stdlib.h>
-
+#include <stdarg.h>
-#ifndef __assert_c99
-static inline void
-__assert_c99(const char *expr, const char *file, int line, const char *func)
-{
-	fprintf(stderr, "%s:%i: %s: Assertion `%s` failed.\n",
-		file, line, func, expr);
-	abort();
-}
-#endif  /* __assert_c99 */
-
-#ifndef verify
-#if defined(__STDC__)
-#if __STDC_VERSION__ - 0 >= 199901L
-#define	verify(EX) (void)((EX) || \
-	(__assert_c99(#EX, __FILE__, __LINE__, __func__), 0))
-#else
-#define	verify(EX) (void)((EX) || (__assert(#EX, __FILE__, __LINE__), 0))
-#endif  /* __STDC_VERSION__ - 0 >= 199901L */
-#else
-#define	verify(EX) (void)((EX) || (_assert("EX", __FILE__, __LINE__), 0))
-#endif	/* __STDC__ */
-#endif  /* verify */
-
-#undef VERIFY
-#undef ASSERT
-
-#define	VERIFY	verify
-#define	ASSERT	assert
-
-extern void __assert(const char *, const char *, int);
 
 static inline int
-assfail(const char *buf, const char *file, int line)
+libspl_assert(const char *buf, const char *file, const char *func, int line)
 {
-	__assert(buf, file, line);
+	fprintf(stderr, "%s\n", buf);
-	return (0);
+	fprintf(stderr, "ASSERT at %s:%d:%s()", file, line, func);
+	abort();
 }
 
-/* BEGIN CSTYLED */
+/* printf version of libspl_assert */
-#define	VERIFY3_IMPL(LEFT, OP, RIGHT, TYPE) do { \
+static inline void
+libspl_assertf(const char *file, const char *func, int line, char *format, ...)
+{
+	va_list args;
+
+	va_start(args, format);
+	vfprintf(stderr, format, args);
+	fprintf(stderr, "\n");
+	fprintf(stderr, "ASSERT at %s:%d:%s()", file, line, func);
+	va_end(args);
+	abort();
+}
+
+#ifdef verify
+#undef verify
+#endif
+
+#define	VERIFY(cond)							\
+	(void) ((!(cond)) &&						\
+	    libspl_assert(#cond, __FILE__, __FUNCTION__, __LINE__))
+#define	verify(cond)							\
+	(void) ((!(cond)) &&						\
+	    libspl_assert(#cond, __FILE__, __FUNCTION__, __LINE__))
+
+#define	VERIFY3_IMPL(LEFT, OP, RIGHT, TYPE)				\
+do {									\
 	const TYPE __left = (TYPE)(LEFT);				\
 	const TYPE __right = (TYPE)(RIGHT);				\
-	if (!(__left OP __right)) { \
+	if (!(__left OP __right))					\
-		char *__buf = alloca(256); \
+		libspl_assertf(__FILE__, __FUNCTION__, __LINE__,	\
-		(void) snprintf(__buf, 256, "%s %s %s (0x%llx %s 0x%llx)", \
+		    "%s %s %s (0x%llx %s 0x%llx)", #LEFT, #OP, #RIGHT);	\
-			#LEFT, #OP, #RIGHT, \
-			(u_longlong_t)__left, #OP, (u_longlong_t)__right); \
-		assfail(__buf, __FILE__, __LINE__); \
-	} \
 } while (0)
-/* END CSTYLED */
 
 #define	VERIFY3S(x, y, z)	VERIFY3_IMPL(x, y, z, int64_t)
 #define	VERIFY3U(x, y, z)	VERIFY3_IMPL(x, y, z, uint64_t)
 #define	VERIFY3P(x, y, z)	VERIFY3_IMPL(x, y, z, uintptr_t)
 #define	VERIFY0(x)		VERIFY3_IMPL(x, ==, 0, uint64_t)
 
+#ifdef assert
+#undef assert
+#endif
+
 #ifdef NDEBUG
 #define	ASSERT3S(x, y, z)	((void)0)
 #define	ASSERT3U(x, y, z)	((void)0)
 #define	ASSERT3P(x, y, z)	((void)0)
 #define	ASSERT0(x)		((void)0)
+#define	ASSERT(x)		((void)0)
+#define	assert(x)		((void)0)
 #define	ASSERTV(x)
 #define	IMPLY(A, B)		((void)0)
 #define	EQUIV(A, B)		((void)0)
@@ -102,13 +99,17 @@ assfail(const char *buf, const char *file, int line)
 #define	ASSERT3U(x, y, z)	VERIFY3U(x, y, z)
 #define	ASSERT3P(x, y, z)	VERIFY3P(x, y, z)
 #define	ASSERT0(x)		VERIFY0(x)
+#define	ASSERT(x)		VERIFY(x)
+#define	assert(x)		VERIFY(x)
 #define	ASSERTV(x)		x
 #define	IMPLY(A, B) \
 	((void)(((!(A)) || (B)) || \
-	    assfail("(" #A ") implies (" #B ")", __FILE__, __LINE__)))
+	    libspl_assert("(" #A ") implies (" #B ")", \
+	    __FILE__, __FUNCTION__, __LINE__)))
 #define	EQUIV(A, B) \
 	((void)((!!(A) == !!(B)) || \
-	    assfail("(" #A ") is equivalent to (" #B ")", __FILE__, __LINE__)))
+	    libspl_assert("(" #A ") is equivalent to (" #B ")", \
+	    __FILE__, __FUNCTION__, __LINE__)))
 
 #endif  /* NDEBUG */
 

lib/libspl/include/sys/sysmacros.h

@@ -42,7 +42,6 @@
 
 #define	makedevice(maj, min)	makedev(maj, min)
 #define	_sysconf(a)		sysconf(a)
-#define	__NORETURN		__attribute__((noreturn))
 
 /*
  * Compatibility macros/typedefs needed for Solaris -> Linux port

lib/libspl/include/sys/types.h

@@ -27,6 +27,12 @@
 #ifndef _LIBSPL_SYS_TYPES_H
 #define	_LIBSPL_SYS_TYPES_H
 
+#if defined(HAVE_MAKEDEV_IN_SYSMACROS)
+#include <sys/sysmacros.h>
+#elif defined(HAVE_MAKEDEV_IN_MKDEV)
+#include <sys/mkdev.h>
+#endif
+
 #include <sys/isa_defs.h>
 #include <sys/feature_tests.h>
 #include_next <sys/types.h>

lib/libzfs/libzfs_dataset.c

@@ -3315,8 +3315,9 @@ zfs_check_snap_cb(zfs_handle_t *zhp, void *arg)
 	char name[ZFS_MAXNAMELEN];
 	int rv = 0;
 
-	(void) snprintf(name, sizeof (name),
+	if (snprintf(name, sizeof (name), "%s@%s", zhp->zfs_name,
-	    "%s@%s", zhp->zfs_name, dd->snapname);
+	    dd->snapname) >= sizeof (name))
+		return (EINVAL);
 
 	if (lzc_exists(name))
 		verify(nvlist_add_boolean(dd->nvl, name) == 0);
@@ -3534,8 +3535,9 @@ zfs_snapshot_cb(zfs_handle_t *zhp, void *arg)
 	int rv = 0;
 
 	if (zfs_prop_get_int(zhp, ZFS_PROP_INCONSISTENT) == 0) {
-		(void) snprintf(name, sizeof (name),
+		if (snprintf(name, sizeof (name), "%s@%s", zfs_get_name(zhp),
-		    "%s@%s", zfs_get_name(zhp), sd->sd_snapname);
+		    sd->sd_snapname) >= sizeof (name))
+			return (EINVAL);
 
 		fnvlist_add_boolean(sd->sd_nvl, name);
 
@@ -4257,8 +4259,9 @@ zfs_hold_one(zfs_handle_t *zhp, void *arg)
 	char name[ZFS_MAXNAMELEN];
 	int rv = 0;
 
-	(void) snprintf(name, sizeof (name),
+	if (snprintf(name, sizeof (name), "%s@%s", zhp->zfs_name,
-	    "%s@%s", zhp->zfs_name, ha->snapname);
+	    ha->snapname) >= sizeof (name))
+		return (EINVAL);
 
 	if (lzc_exists(name))
 		fnvlist_add_string(ha->nvl, name, ha->tag);
@@ -4377,8 +4380,11 @@ zfs_release_one(zfs_handle_t *zhp, void *arg)
 	int rv = 0;
 	nvlist_t *existing_holds;
 
-	(void) snprintf(name, sizeof (name),
+	if (snprintf(name, sizeof (name), "%s@%s", zhp->zfs_name,
-	    "%s@%s", zhp->zfs_name, ha->snapname);
+	    ha->snapname) >= sizeof (name)) {
+		ha->error = EINVAL;
+		rv = EINVAL;
+	}
 
 	if (lzc_get_holds(name, &existing_holds) != 0) {
 		ha->error = ENOENT;

lib/libzfs/libzfs_import.c

@@ -1337,16 +1337,33 @@ zpool_find_import_impl(libzfs_handle_t *hdl, importargs_t *iarg)
 
 			if (config != NULL) {
 				boolean_t matched = B_TRUE;
+				boolean_t aux = B_FALSE;
 				char *pname;
 
-				if ((iarg->poolname != NULL) &&
+				/*
+				 * Check if it's a spare or l2cache device. If
+				 * it is, we need to skip the name and guid
+				 * check since they don't exist on aux device
+				 * label.
+				 */
+				if (iarg->poolname != NULL ||
+				    iarg->guid != 0) {
+					uint64_t state;
+					aux = nvlist_lookup_uint64(config,
+					    ZPOOL_CONFIG_POOL_STATE,
+					    &state) == 0 &&
+					    (state == POOL_STATE_SPARE ||
+					    state == POOL_STATE_L2CACHE);
+				}
+
+				if ((iarg->poolname != NULL) && !aux &&
 				    (nvlist_lookup_string(config,
 				    ZPOOL_CONFIG_POOL_NAME, &pname) == 0)) {
 
 					if (strcmp(iarg->poolname, pname))
 						matched = B_FALSE;
 
-				} else if (iarg->guid != 0) {
+				} else if (iarg->guid != 0 && !aux) {
 					uint64_t this_guid;
 
 					matched = nvlist_lookup_uint64(config,

lib/libzfs/libzfs_iter.c

@@ -204,8 +204,11 @@ zfs_iter_bookmarks(zfs_handle_t *zhp, zfs_iter_f func, void *data)
 		bmark_name = nvpair_name(pair);
 		bmark_props = fnvpair_value_nvlist(pair);
 
-		(void) snprintf(name, sizeof (name), "%s#%s", zhp->zfs_name,
+		if (snprintf(name, sizeof (name), "%s#%s", zhp->zfs_name,
-		    bmark_name);
+		    bmark_name) >= sizeof (name)) {
+			err = EINVAL;
+			goto out;
+		}
 
 		nzhp = make_bookmark_handle(zhp, name, bmark_props);
 		if (nzhp == NULL)

lib/libzfs/libzfs_mount.c

@@ -364,6 +364,14 @@ zfs_add_options(zfs_handle_t *zhp, char *options, int len)
 
 	error = zfs_add_option(zhp, options, len,
 	    ZFS_PROP_ATIME, MNTOPT_ATIME, MNTOPT_NOATIME);
+	/*
+	 * don't add relatime/strictatime when atime=off, otherwise strictatime
+	 * will force atime=on
+	 */
+	if (strstr(options, MNTOPT_NOATIME) == NULL) {
+		error = zfs_add_option(zhp, options, len,
+		    ZFS_PROP_RELATIME, MNTOPT_RELATIME, MNTOPT_STRICTATIME);
+	}
 	error = error ? error : zfs_add_option(zhp, options, len,
 	    ZFS_PROP_DEVICES, MNTOPT_DEVICES, MNTOPT_NODEVICES);
 	error = error ? error : zfs_add_option(zhp, options, len,

lib/libzfs/libzfs_sendrecv.c

@@ -1487,9 +1487,13 @@ zfs_send(zfs_handle_t *zhp, const char *fromsnap, const char *tosnap,
 			    drr_versioninfo, DMU_COMPOUNDSTREAM);
 			DMU_SET_FEATUREFLAGS(drr.drr_u.drr_begin.
 			    drr_versioninfo, featureflags);
-			(void) snprintf(drr.drr_u.drr_begin.drr_toname,
+			if (snprintf(drr.drr_u.drr_begin.drr_toname,
 			    sizeof (drr.drr_u.drr_begin.drr_toname),
-			    "%s@%s", zhp->zfs_name, tosnap);
+			    "%s@%s", zhp->zfs_name, tosnap) >=
+			    sizeof (drr.drr_u.drr_begin.drr_toname)) {
+				err = EINVAL;
+				goto stderr_out;
+			}
 			drr.drr_payloadlen = buflen;
 			err = cksum_and_write(&drr, sizeof (drr), &zc, outfd);
 
@@ -2689,7 +2693,8 @@ zfs_receive_one(libzfs_handle_t *hdl, int infd, const char *tosnap,
 	    ENOENT);
 
 	if (stream_avl != NULL) {
-		char *snapname;
+		char *snapname = NULL;
+		nvlist_t *lookup = NULL;
 		nvlist_t *fs = fsavl_find(stream_avl, drrb->drr_toguid,
 		    &snapname);
 		nvlist_t *props;
@@ -2710,6 +2715,11 @@ zfs_receive_one(libzfs_handle_t *hdl, int infd, const char *tosnap,
 			nvlist_free(props);
 		if (ret != 0)
 			return (-1);
+
+		if (0 == nvlist_lookup_nvlist(fs, "snapprops", &lookup)) {
+			VERIFY(0 == nvlist_lookup_nvlist(lookup,
+			    snapname, &snapprops_nvlist));
+		}
 	}
 
 	cp = NULL;

man/man5/zfs-module-parameters.5

@@ -883,7 +883,12 @@ Default value: \fB10\fR.
 Minimum asynchronous write I/Os active to each device.
 See the section "ZFS I/O SCHEDULER".
 .sp
-Default value: \fB1\fR.
+Lower values are associated with better latency on rotational media but poorer
+resilver performance. The default value of 2 was chosen as a compromise. A
+value of 3 has been shown to improve resilver performance further at a cost of
+further increasing latency.
+.sp
+Default value: \fB2\fR.
 .RE
 
 .sp

module/avl/avl.c

@@ -630,7 +630,7 @@ avl_insert_here(
 void
 avl_add(avl_tree_t *tree, void *new_node)
 {
-	avl_index_t where;
+	avl_index_t where = 0;
 
 	/*
 	 * This is unfortunate.  We want to call panic() here, even for

module/zfs/arc.c

@@ -5475,11 +5475,12 @@ arc_init(void)
 	 * If it has been set by a module parameter, take that.
 	 * Otherwise, use a percentage of physical memory defined by
 	 * zfs_dirty_data_max_percent (default 10%) with a cap at
-	 * zfs_dirty_data_max_max (default 25% of physical memory).
+	 * zfs_dirty_data_max_max (default 4G or 25% of physical memory).
 	 */
 	if (zfs_dirty_data_max_max == 0)
-		zfs_dirty_data_max_max = (uint64_t)physmem * PAGESIZE *
+		zfs_dirty_data_max_max = MIN(4ULL * 1024 * 1024 * 1024,
-		    zfs_dirty_data_max_max_percent / 100;
+		    (uint64_t)physmem * PAGESIZE *
+		    zfs_dirty_data_max_max_percent / 100);
 
 	if (zfs_dirty_data_max == 0) {
 		zfs_dirty_data_max = (uint64_t)physmem * PAGESIZE *

module/zfs/dmu.c

@@ -49,6 +49,7 @@
 #ifdef _KERNEL
 #include <sys/vmsystm.h>
 #include <sys/zfs_znode.h>
+#include <linux/kmap_compat.h>
 #endif
 
 /*
@@ -1056,6 +1057,7 @@ dmu_bio_copy(void *arg_buf, int size, struct bio *bio, size_t bio_offset)
 	char *bv_buf;
 	int tocpy, bv_len, bv_offset;
 	int offset = 0;
+	void *paddr;
 
 	bio_for_each_segment4(bv, bvp, bio, iter) {
 
@@ -1080,14 +1082,15 @@ dmu_bio_copy(void *arg_buf, int size, struct bio *bio, size_t bio_offset)
 		tocpy = MIN(bv_len, size - offset);
 		ASSERT3S(tocpy, >=, 0);
 
-		bv_buf = page_address(bvp->bv_page) + bv_offset;
+		paddr = zfs_kmap_atomic(bvp->bv_page, KM_USER0);
-		ASSERT3P(bv_buf, !=, NULL);
+		bv_buf = paddr + bv_offset;
+		ASSERT3P(paddr, !=, NULL);
 
 		if (bio_data_dir(bio) == WRITE)
 			memcpy(arg_buf + offset, bv_buf, tocpy);
 		else
 			memcpy(bv_buf, arg_buf + offset, tocpy);
-
+		zfs_kunmap_atomic(paddr, KM_USER0);
 		offset += tocpy;
 	}
 out:

module/zfs/dmu_send.c

@@ -69,7 +69,7 @@ typedef struct dump_bytes_io {
 } dump_bytes_io_t;
 
 static void
-dump_bytes_strategy(void *arg)
+dump_bytes_cb(void *arg)
 {
 	dump_bytes_io_t *dbi = (dump_bytes_io_t *)arg;
 	dmu_sendarg_t *dsp = dbi->dbi_dsp;
@@ -96,6 +96,9 @@ dump_bytes(dmu_sendarg_t *dsp, void *buf, int len)
 	dbi.dbi_buf = buf;
 	dbi.dbi_len = len;
 
+#if defined(HAVE_LARGE_STACKS)
+	dump_bytes_cb(&dbi);
+#else
 	/*
 	 * The vn_rdwr() call is performed in a taskq to ensure that there is
 	 * always enough stack space to write safely to the target filesystem.
@@ -103,7 +106,8 @@ dump_bytes(dmu_sendarg_t *dsp, void *buf, int len)
 	 * them and they are used in vdev_file.c for a similar purpose.
 	 */
 	spa_taskq_dispatch_sync(dmu_objset_spa(dsp->dsa_os), ZIO_TYPE_FREE,
-	    ZIO_TASKQ_ISSUE, dump_bytes_strategy, &dbi, TQ_SLEEP);
+	    ZIO_TASKQ_ISSUE, dump_bytes_cb, &dbi, TQ_SLEEP);
+#endif /* HAVE_LARGE_STACKS */
 
 	return (dsp->dsa_err);
 }

module/zfs/dsl_dataset.c

@@ -671,7 +671,11 @@ dsl_dataset_namelen(dsl_dataset_t *ds)
 	int len;
 	VERIFY0(dsl_dataset_get_snapname(ds));
 	mutex_enter(&ds->ds_lock);
-	len = dsl_dir_namelen(ds->ds_dir) + 1 + strlen(ds->ds_snapname);
+	len = strlen(ds->ds_snapname);
+	/* add '@' if ds is a snap */
+	if (len > 0)
+		len++;
+	len += dsl_dir_namelen(ds->ds_dir);
 	mutex_exit(&ds->ds_lock);
 	return (len);
 }

module/zfs/refcount.c

@@ -137,7 +137,7 @@ refcount_add_many(refcount_t *rc, uint64_t number, void *holder)
 }
 
 int64_t
-refcount_add(refcount_t *rc, void *holder)
+zfs_refcount_add(refcount_t *rc, void *holder)
 {
 	return (refcount_add_many(rc, 1, holder));
 }

module/zfs/spa.c

@@ -845,7 +845,7 @@ spa_taskqs_init(spa_t *spa, zio_type_t t, zio_taskq_type_t q)
 	uint_t count = ztip->zti_count;
 	spa_taskqs_t *tqs = &spa->spa_zio_taskq[t][q];
 	char name[32];
-	uint_t i, flags = TASKQ_DYNAMIC;
+	uint_t i, flags = 0;
 	boolean_t batch = B_FALSE;
 
 	if (mode == ZTI_MODE_NULL) {
@@ -863,6 +863,7 @@ spa_taskqs_init(spa_t *spa, zio_type_t t, zio_taskq_type_t q)
 	case ZTI_MODE_FIXED:
 		ASSERT3U(value, >=, 1);
 		value = MAX(value, 1);
+		flags |= TASKQ_DYNAMIC;
 		break;
 
 	case ZTI_MODE_BATCH:
@@ -3862,211 +3863,6 @@ spa_create(const char *pool, nvlist_t *nvroot, nvlist_t *props,
 	return (0);
 }
 
-#ifdef _KERNEL
-/*
- * Get the root pool information from the root disk, then import the root pool
- * during the system boot up time.
- */
-extern int vdev_disk_read_rootlabel(char *, char *, nvlist_t **);
-
-static nvlist_t *
-spa_generate_rootconf(char *devpath, char *devid, uint64_t *guid)
-{
-	nvlist_t *config;
-	nvlist_t *nvtop, *nvroot;
-	uint64_t pgid;
-
-	if (vdev_disk_read_rootlabel(devpath, devid, &config) != 0)
-		return (NULL);
-
-	/*
-	 * Add this top-level vdev to the child array.
-	 */
-	VERIFY(nvlist_lookup_nvlist(config, ZPOOL_CONFIG_VDEV_TREE,
-	    &nvtop) == 0);
-	VERIFY(nvlist_lookup_uint64(config, ZPOOL_CONFIG_POOL_GUID,
-	    &pgid) == 0);
-	VERIFY(nvlist_lookup_uint64(config, ZPOOL_CONFIG_GUID, guid) == 0);
-
-	/*
-	 * Put this pool's top-level vdevs into a root vdev.
-	 */
-	VERIFY(nvlist_alloc(&nvroot, NV_UNIQUE_NAME, KM_SLEEP) == 0);
-	VERIFY(nvlist_add_string(nvroot, ZPOOL_CONFIG_TYPE,
-	    VDEV_TYPE_ROOT) == 0);
-	VERIFY(nvlist_add_uint64(nvroot, ZPOOL_CONFIG_ID, 0ULL) == 0);
-	VERIFY(nvlist_add_uint64(nvroot, ZPOOL_CONFIG_GUID, pgid) == 0);
-	VERIFY(nvlist_add_nvlist_array(nvroot, ZPOOL_CONFIG_CHILDREN,
-	    &nvtop, 1) == 0);
-
-	/*
-	 * Replace the existing vdev_tree with the new root vdev in
-	 * this pool's configuration (remove the old, add the new).
-	 */
-	VERIFY(nvlist_add_nvlist(config, ZPOOL_CONFIG_VDEV_TREE, nvroot) == 0);
-	nvlist_free(nvroot);
-	return (config);
-}
-
-/*
- * Walk the vdev tree and see if we can find a device with "better"
- * configuration. A configuration is "better" if the label on that
- * device has a more recent txg.
- */
-static void
-spa_alt_rootvdev(vdev_t *vd, vdev_t **avd, uint64_t *txg)
-{
-	int c;
-
-	for (c = 0; c < vd->vdev_children; c++)
-		spa_alt_rootvdev(vd->vdev_child[c], avd, txg);
-
-	if (vd->vdev_ops->vdev_op_leaf) {
-		nvlist_t *label;
-		uint64_t label_txg;
-
-		if (vdev_disk_read_rootlabel(vd->vdev_physpath, vd->vdev_devid,
-		    &label) != 0)
-			return;
-
-		VERIFY(nvlist_lookup_uint64(label, ZPOOL_CONFIG_POOL_TXG,
-		    &label_txg) == 0);
-
-		/*
-		 * Do we have a better boot device?
-		 */
-		if (label_txg > *txg) {
-			*txg = label_txg;
-			*avd = vd;
-		}
-		nvlist_free(label);
-	}
-}
-
-/*
- * Import a root pool.
- *
- * For x86. devpath_list will consist of devid and/or physpath name of
- * the vdev (e.g. "id1,sd@SSEAGATE..." or "/pci@1f,0/ide@d/disk@0,0:a").
- * The GRUB "findroot" command will return the vdev we should boot.
- *
- * For Sparc, devpath_list consists the physpath name of the booting device
- * no matter the rootpool is a single device pool or a mirrored pool.
- * e.g.
- *	"/pci@1f,0/ide@d/disk@0,0:a"
- */
-int
-spa_import_rootpool(char *devpath, char *devid)
-{
-	spa_t *spa;
-	vdev_t *rvd, *bvd, *avd = NULL;
-	nvlist_t *config, *nvtop;
-	uint64_t guid, txg;
-	char *pname;
-	int error;
-
-	/*
-	 * Read the label from the boot device and generate a configuration.
-	 */
-	config = spa_generate_rootconf(devpath, devid, &guid);
-#if defined(_OBP) && defined(_KERNEL)
-	if (config == NULL) {
-		if (strstr(devpath, "/iscsi/ssd") != NULL) {
-			/* iscsi boot */
-			get_iscsi_bootpath_phy(devpath);
-			config = spa_generate_rootconf(devpath, devid, &guid);
-		}
-	}
-#endif
-	if (config == NULL) {
-		cmn_err(CE_NOTE, "Cannot read the pool label from '%s'",
-		    devpath);
-		return (SET_ERROR(EIO));
-	}
-
-	VERIFY(nvlist_lookup_string(config, ZPOOL_CONFIG_POOL_NAME,
-	    &pname) == 0);
-	VERIFY(nvlist_lookup_uint64(config, ZPOOL_CONFIG_POOL_TXG, &txg) == 0);
-
-	mutex_enter(&spa_namespace_lock);
-	if ((spa = spa_lookup(pname)) != NULL) {
-		/*
-		 * Remove the existing root pool from the namespace so that we
-		 * can replace it with the correct config we just read in.
-		 */
-		spa_remove(spa);
-	}
-
-	spa = spa_add(pname, config, NULL);
-	spa->spa_is_root = B_TRUE;
-	spa->spa_import_flags = ZFS_IMPORT_VERBATIM;
-
-	/*
-	 * Build up a vdev tree based on the boot device's label config.
-	 */
-	VERIFY(nvlist_lookup_nvlist(config, ZPOOL_CONFIG_VDEV_TREE,
-	    &nvtop) == 0);
-	spa_config_enter(spa, SCL_ALL, FTAG, RW_WRITER);
-	error = spa_config_parse(spa, &rvd, nvtop, NULL, 0,
-	    VDEV_ALLOC_ROOTPOOL);
-	spa_config_exit(spa, SCL_ALL, FTAG);
-	if (error) {
-		mutex_exit(&spa_namespace_lock);
-		nvlist_free(config);
-		cmn_err(CE_NOTE, "Can not parse the config for pool '%s'",
-		    pname);
-		return (error);
-	}
-
-	/*
-	 * Get the boot vdev.
-	 */
-	if ((bvd = vdev_lookup_by_guid(rvd, guid)) == NULL) {
-		cmn_err(CE_NOTE, "Can not find the boot vdev for guid %llu",
-		    (u_longlong_t)guid);
-		error = SET_ERROR(ENOENT);
-		goto out;
-	}
-
-	/*
-	 * Determine if there is a better boot device.
-	 */
-	avd = bvd;
-	spa_alt_rootvdev(rvd, &avd, &txg);
-	if (avd != bvd) {
-		cmn_err(CE_NOTE, "The boot device is 'degraded'. Please "
-		    "try booting from '%s'", avd->vdev_path);
-		error = SET_ERROR(EINVAL);
-		goto out;
-	}
-
-	/*
-	 * If the boot device is part of a spare vdev then ensure that
-	 * we're booting off the active spare.
-	 */
-	if (bvd->vdev_parent->vdev_ops == &vdev_spare_ops &&
-	    !bvd->vdev_isspare) {
-		cmn_err(CE_NOTE, "The boot device is currently spared. Please "
-		    "try booting from '%s'",
-		    bvd->vdev_parent->
-		    vdev_child[bvd->vdev_parent->vdev_children - 1]->vdev_path);
-		error = SET_ERROR(EINVAL);
-		goto out;
-	}
-
-	error = 0;
-out:
-	spa_config_enter(spa, SCL_ALL, FTAG, RW_WRITER);
-	vdev_free(rvd);
-	spa_config_exit(spa, SCL_ALL, FTAG);
-	mutex_exit(&spa_namespace_lock);
-
-	nvlist_free(config);
-	return (error);
-}
-
-#endif
-
 /*
  * Import a non-root pool into the system.
  */
@@ -4166,12 +3962,6 @@ spa_import(char *pool, nvlist_t *config, nvlist_t *props, uint64_t flags)
 
 	VERIFY(nvlist_lookup_nvlist(config, ZPOOL_CONFIG_VDEV_TREE,
 	    &nvroot) == 0);
-	if (error == 0)
-		error = spa_validate_aux(spa, nvroot, -1ULL,
-		    VDEV_ALLOC_SPARE);
-	if (error == 0)
-		error = spa_validate_aux(spa, nvroot, -1ULL,
-		    VDEV_ALLOC_L2CACHE);
 	spa_config_exit(spa, SCL_ALL, FTAG);
 
 	if (props != NULL)
@@ -6780,7 +6570,6 @@ EXPORT_SYMBOL(spa_open);
 EXPORT_SYMBOL(spa_open_rewind);
 EXPORT_SYMBOL(spa_get_stats);
 EXPORT_SYMBOL(spa_create);
-EXPORT_SYMBOL(spa_import_rootpool);
 EXPORT_SYMBOL(spa_import);
 EXPORT_SYMBOL(spa_tryimport);
 EXPORT_SYMBOL(spa_destroy);

module/zfs/vdev.c

@@ -1799,6 +1799,9 @@ vdev_dtl_should_excise(vdev_t *vd)
 	ASSERT0(scn->scn_phys.scn_errors);
 	ASSERT0(vd->vdev_children);
 
+	if (vd->vdev_state < VDEV_STATE_DEGRADED)
+		return (B_FALSE);
+
 	if (vd->vdev_resilver_txg == 0 ||
 	    range_tree_space(vd->vdev_dtl[DTL_MISSING]) == 0)
 		return (B_TRUE);

module/zfs/vdev_disk.c

@@ -41,10 +41,8 @@ static void *zfs_vdev_holder = VDEV_HOLDER;
  * Virtual device vector for disks.
  */
 typedef struct dio_request {
-	struct completion	dr_comp;	/* Completion for sync IO */
 	zio_t			*dr_zio;	/* Parent ZIO */
 	atomic_t		dr_ref;		/* References */
-	int			dr_wait;	/* Wait for IO */
 	int			dr_error;	/* Bio error */
 	int			dr_bio_count;	/* Count of bio's */
 	struct bio		*dr_bio[0];	/* Attached bio's */
@@ -363,7 +361,6 @@ vdev_disk_dio_alloc(int bio_count)
 	dr = kmem_zalloc(sizeof (dio_request_t) +
 	    sizeof (struct bio *) * bio_count, KM_SLEEP);
 	if (dr) {
-		init_completion(&dr->dr_comp);
 		atomic_set(&dr->dr_ref, 0);
 		dr->dr_bio_count = bio_count;
 		dr->dr_error = 0;
@@ -426,7 +423,6 @@ BIO_END_IO_PROTO(vdev_disk_physio_completion, bio, error)
 {
 	dio_request_t *dr = bio->bi_private;
 	int rc;
-	int wait;
 
 	if (dr->dr_error == 0) {
 #ifdef HAVE_1ARG_BIO_END_IO_T
@@ -439,13 +435,8 @@ BIO_END_IO_PROTO(vdev_disk_physio_completion, bio, error)
 #endif
 	}
 
-	wait = dr->dr_wait;
 	/* Drop reference aquired by __vdev_disk_physio */
 	rc = vdev_disk_dio_put(dr);
-
-	/* Wake up synchronous waiter this is the last outstanding bio */
-	if (wait && rc == 1)
-		complete(&dr->dr_comp);
 }
 
 static inline unsigned long
@@ -494,11 +485,6 @@ bio_map(struct bio *bio, void *bio_ptr, unsigned int bio_size)
 	return (bio_size);
 }
 
-#ifndef bio_set_op_attrs
-#define	bio_set_op_attrs(bio, rw, flags) \
-	do { (bio)->bi_rw |= (rw)|(flags); } while (0)
-#endif
-
 static inline void
 vdev_submit_bio_impl(struct bio *bio)
 {
@@ -527,13 +513,16 @@ vdev_submit_bio(struct bio *bio)
 
 static int
 __vdev_disk_physio(struct block_device *bdev, zio_t *zio, caddr_t kbuf_ptr,
-    size_t kbuf_size, uint64_t kbuf_offset, int rw, int flags, int wait)
+    size_t kbuf_size, uint64_t kbuf_offset, int rw, int flags)
 {
 	dio_request_t *dr;
 	caddr_t bio_ptr;
 	uint64_t bio_offset;
 	int bio_size, bio_count = 16;
 	int i = 0, error = 0;
+#if defined(HAVE_BLK_QUEUE_HAVE_BLK_PLUG)
+	struct blk_plug plug;
+#endif
 
 	ASSERT3U(kbuf_offset + kbuf_size, <=, bdev->bd_inode->i_size);
 
@@ -546,7 +535,6 @@ retry:
 		bio_set_flags_failfast(bdev, &flags);
 
 	dr->dr_zio = zio;
-	dr->dr_wait = wait;
 
 	/*
 	 * When the IO size exceeds the maximum bio size for the request
@@ -605,39 +593,26 @@ retry:
 	if (zio)
 		zio->io_delay = jiffies_64;
 
+#if defined(HAVE_BLK_QUEUE_HAVE_BLK_PLUG)
+	if (dr->dr_bio_count > 1)
+		blk_start_plug(&plug);
+#endif
+
 	/* Submit all bio's associated with this dio */
 	for (i = 0; i < dr->dr_bio_count; i++)
 		if (dr->dr_bio[i])
 			vdev_submit_bio(dr->dr_bio[i]);
 
-	/*
+#if defined(HAVE_BLK_QUEUE_HAVE_BLK_PLUG)
-	 * On synchronous blocking requests we wait for all bio the completion
+	if (dr->dr_bio_count > 1)
-	 * callbacks to run.  We will be woken when the last callback runs
+		blk_finish_plug(&plug);
-	 * for this dio.  We are responsible for putting the last dio_request
+#endif
-	 * reference will in turn put back the last bio references.  The
-	 * only synchronous consumer is vdev_disk_read_rootlabel() all other
-	 * IO originating from vdev_disk_io_start() is asynchronous.
-	 */
-	if (wait) {
-		wait_for_completion(&dr->dr_comp);
-		error = dr->dr_error;
-		ASSERT3S(atomic_read(&dr->dr_ref), ==, 1);
-	}
 
 	(void) vdev_disk_dio_put(dr);
 
 	return (error);
 }
 
-int
-vdev_disk_physio(struct block_device *bdev, caddr_t kbuf,
-    size_t size, uint64_t offset, int rw, int flags)
-{
-	bio_set_flags_failfast(bdev, &flags);
-	return (__vdev_disk_physio(bdev, NULL, kbuf, size, offset, rw, flags,
-	    1));
-}
-
 BIO_END_IO_PROTO(vdev_disk_io_flush_completion, bio, rc)
 {
 	zio_t *zio = bio->bi_private;
@@ -676,7 +651,7 @@ vdev_disk_io_flush(struct block_device *bdev, zio_t *zio)
 	bio->bi_private = zio;
 	bio->bi_bdev = bdev;
 	zio->io_delay = jiffies_64;
-	bio_set_op_attrs(bio, 0, VDEV_WRITE_FLUSH_FUA);
+	bio_set_flush(bio);
 	vdev_submit_bio(bio);
 	invalidate_bdev(bdev);
 
@@ -688,7 +663,6 @@ vdev_disk_io_start(zio_t *zio)
 {
 	vdev_t *v = zio->io_vd;
 	vdev_disk_t *vd = v->vdev_tsd;
-	zio_priority_t pri = zio->io_priority;
 	int rw, flags, error;
 
 	switch (zio->io_type) {
@@ -729,18 +703,24 @@ vdev_disk_io_start(zio_t *zio)
 		return;
 	case ZIO_TYPE_WRITE:
 		rw = WRITE;
-		if ((pri == ZIO_PRIORITY_SYNC_WRITE) && (v->vdev_nonrot))
+#if defined(HAVE_BLK_QUEUE_HAVE_BIO_RW_UNPLUG)
-			flags = WRITE_SYNC;
+		flags = (1 << BIO_RW_UNPLUG);
-		else
+#elif defined(REQ_UNPLUG)
+		flags = REQ_UNPLUG;
+#else
 		flags = 0;
+#endif
 		break;
 
 	case ZIO_TYPE_READ:
 		rw = READ;
-		if ((pri == ZIO_PRIORITY_SYNC_READ) && (v->vdev_nonrot))
+#if defined(HAVE_BLK_QUEUE_HAVE_BIO_RW_UNPLUG)
-			flags = READ_SYNC;
+		flags = (1 << BIO_RW_UNPLUG);
-		else
+#elif defined(REQ_UNPLUG)
+		flags = REQ_UNPLUG;
+#else
 		flags = 0;
+#endif
 		break;
 
 	default:
@@ -750,7 +730,7 @@ vdev_disk_io_start(zio_t *zio)
 	}
 
 	error = __vdev_disk_physio(vd->vd_bdev, zio, zio->io_data,
-	    zio->io_size, zio->io_offset, rw, flags, 0);
+	    zio->io_size, zio->io_offset, rw, flags);
 	if (error) {
 		zio->io_error = error;
 		zio_interrupt(zio);
@@ -820,69 +800,5 @@ vdev_ops_t vdev_disk_ops = {
 	B_TRUE			/* leaf vdev */
 };
 
-/*
- * Given the root disk device devid or pathname, read the label from
- * the device, and construct a configuration nvlist.
- */
-int
-vdev_disk_read_rootlabel(char *devpath, char *devid, nvlist_t **config)
-{
-	struct block_device *bdev;
-	vdev_label_t *label;
-	uint64_t s, size;
-	int i;
-
-	bdev = vdev_bdev_open(devpath, vdev_bdev_mode(FREAD), zfs_vdev_holder);
-	if (IS_ERR(bdev))
-		return (-PTR_ERR(bdev));
-
-	s = bdev_capacity(bdev);
-	if (s == 0) {
-		vdev_bdev_close(bdev, vdev_bdev_mode(FREAD));
-		return (EIO);
-	}
-
-	size = P2ALIGN_TYPED(s, sizeof (vdev_label_t), uint64_t);
-	label = vmem_alloc(sizeof (vdev_label_t), KM_SLEEP);
-
-	for (i = 0; i < VDEV_LABELS; i++) {
-		uint64_t offset, state, txg = 0;
-
-		/* read vdev label */
-		offset = vdev_label_offset(size, i, 0);
-		if (vdev_disk_physio(bdev, (caddr_t)label,
-		    VDEV_SKIP_SIZE + VDEV_PHYS_SIZE, offset, READ,
-		    REQ_SYNC) != 0)
-			continue;
-
-		if (nvlist_unpack(label->vl_vdev_phys.vp_nvlist,
-		    sizeof (label->vl_vdev_phys.vp_nvlist), config, 0) != 0) {
-			*config = NULL;
-			continue;
-		}
-
-		if (nvlist_lookup_uint64(*config, ZPOOL_CONFIG_POOL_STATE,
-		    &state) != 0 || state >= POOL_STATE_DESTROYED) {
-			nvlist_free(*config);
-			*config = NULL;
-			continue;
-		}
-
-		if (nvlist_lookup_uint64(*config, ZPOOL_CONFIG_POOL_TXG,
-		    &txg) != 0 || txg == 0) {
-			nvlist_free(*config);
-			*config = NULL;
-			continue;
-		}
-
-		break;
-	}
-
-	vmem_free(label, sizeof (vdev_label_t));
-	vdev_bdev_close(bdev, vdev_bdev_mode(FREAD));
-
-	return (0);
-}
-
 module_param(zfs_vdev_scheduler, charp, 0644);
 MODULE_PARM_DESC(zfs_vdev_scheduler, "I/O scheduler");

module/zfs/vdev_queue.c

@@ -24,7 +24,7 @@
  */
 
 /*
- * Copyright (c) 2012, 2014 by Delphix. All rights reserved.
+ * Copyright (c) 2012, 2017 by Delphix. All rights reserved.
  */
 
 #include <sys/zfs_context.h>
@@ -146,7 +146,7 @@ uint32_t zfs_vdev_sync_write_min_active = 10;
 uint32_t zfs_vdev_sync_write_max_active = 10;
 uint32_t zfs_vdev_async_read_min_active = 1;
 uint32_t zfs_vdev_async_read_max_active = 3;
-uint32_t zfs_vdev_async_write_min_active = 1;
+uint32_t zfs_vdev_async_write_min_active = 2;
 uint32_t zfs_vdev_async_write_max_active = 10;
 uint32_t zfs_vdev_scrub_min_active = 1;
 uint32_t zfs_vdev_scrub_max_active = 2;
@@ -545,7 +545,7 @@ vdev_queue_aggregate(vdev_queue_t *vq, zio_t *zio)
 
 	/*
 	 * Walk backwards through sufficiently contiguous I/Os
-	 * recording the last non-option I/O.
+	 * recording the last non-optional I/O.
 	 */
 	while ((dio = AVL_PREV(t, first)) != NULL &&
 	    (dio->io_flags & ZIO_FLAG_AGG_INHERIT) == flags &&
@@ -567,10 +567,14 @@ vdev_queue_aggregate(vdev_queue_t *vq, zio_t *zio)
 
 	/*
 	 * Walk forward through sufficiently contiguous I/Os.
+	 * The aggregation limit does not apply to optional i/os, so that
+	 * we can issue contiguous writes even if they are larger than the
+	 * aggregation limit.
 	 */
 	while ((dio = AVL_NEXT(t, last)) != NULL &&
 	    (dio->io_flags & ZIO_FLAG_AGG_INHERIT) == flags &&
-	    IO_SPAN(first, dio) <= zfs_vdev_aggregation_limit &&
+	    (IO_SPAN(first, dio) <= zfs_vdev_aggregation_limit ||
+	    (dio->io_flags & ZIO_FLAG_OPTIONAL)) &&
 	    IO_GAP(last, dio) <= maxgap) {
 		last = dio;
 		if (!(last->io_flags & ZIO_FLAG_OPTIONAL))
@@ -605,6 +609,7 @@ vdev_queue_aggregate(vdev_queue_t *vq, zio_t *zio)
 		dio = AVL_NEXT(t, last);
 		dio->io_flags &= ~ZIO_FLAG_OPTIONAL;
 	} else {
+		/* do not include the optional i/o */
 		while (last != mandatory && last != first) {
 			ASSERT(last->io_flags & ZIO_FLAG_OPTIONAL);
 			last = AVL_PREV(t, last);
@@ -616,7 +621,6 @@ vdev_queue_aggregate(vdev_queue_t *vq, zio_t *zio)
 		return (NULL);
 
 	size = IO_SPAN(first, last);
-	ASSERT3U(size, <=, zfs_vdev_aggregation_limit);
 
 	buf = zio_buf_alloc_flags(size, KM_NOSLEEP);
 	if (buf == NULL)

module/zfs/zfs_acl.c

@@ -1457,7 +1457,7 @@ zfs_aclset_common(znode_t *zp, zfs_acl_t *aclp, cred_t *cr, dmu_tx_t *tx)
 	if (ace_trivial_common(aclp, 0, zfs_ace_walk) == 0)
 		zp->z_pflags |= ZFS_ACL_TRIVIAL;
 
-	zfs_tstamp_update_setup(zp, STATE_CHANGED, NULL, ctime, B_TRUE);
+	zfs_tstamp_update_setup(zp, STATE_CHANGED, NULL, ctime);
 	return (sa_bulk_update(zp->z_sa_hdl, bulk, count, tx));
 }
 

module/zfs/zfs_ctldir.c

@@ -455,7 +455,7 @@ static struct inode *
 zfsctl_inode_alloc(zfs_sb_t *zsb, uint64_t id,
     const struct file_operations *fops, const struct inode_operations *ops)
 {
-	struct timespec now = current_fs_time(zsb->z_sb);
+	struct timespec now;
 	struct inode *ip;
 	znode_t *zp;
 
@@ -463,6 +463,7 @@ zfsctl_inode_alloc(zfs_sb_t *zsb, uint64_t id,
 	if (ip == NULL)
 		return (NULL);
 
+	now = current_time(ip);
 	zp = ITOZ(ip);
 	ASSERT3P(zp->z_dirlocks, ==, NULL);
 	ASSERT3P(zp->z_acl_cached, ==, NULL);
@@ -478,8 +479,6 @@ zfsctl_inode_alloc(zfs_sb_t *zsb, uint64_t id,
 	zp->z_mapcnt = 0;
 	zp->z_gen = 0;
 	zp->z_size = 0;
-	zp->z_atime[0] = 0;
-	zp->z_atime[1] = 0;
 	zp->z_links = 0;
 	zp->z_pflags = 0;
 	zp->z_uid = 0;
@@ -500,6 +499,9 @@ zfsctl_inode_alloc(zfs_sb_t *zsb, uint64_t id,
 	ip->i_ctime = now;
 	ip->i_fop = fops;
 	ip->i_op = ops;
+#if defined(IOP_XATTR)
+	ip->i_opflags &= ~IOP_XATTR;
+#endif
 
 	if (insert_inode_locked(ip)) {
 		unlock_new_inode(ip);
@@ -1009,16 +1011,11 @@ out:
  * best effort.  In the case where it does fail, perhaps because
  * it's in use, the unmount will fail harmlessly.
  */
-#define	SET_UNMOUNT_CMD \
-	"exec 0</dev/null " \
-	"     1>/dev/null " \
-	"     2>/dev/null; " \
-	"umount -t zfs -n %s'%s'"
-
 int
 zfsctl_snapshot_unmount(char *snapname, int flags)
 {
-	char *argv[] = { "/bin/sh", "-c", NULL, NULL };
+	char *argv[] = { "/usr/bin/env", "umount", "-t", "zfs", "-n", NULL,
+	    NULL };
 	char *envp[] = { NULL };
 	zfs_snapentry_t *se;
 	int error;
@@ -1030,12 +1027,12 @@ zfsctl_snapshot_unmount(char *snapname, int flags)
 	}
 	rw_exit(&zfs_snapshot_lock);
 
-	argv[2] = kmem_asprintf(SET_UNMOUNT_CMD,
+	if (flags & MNT_FORCE)
-	    flags & MNT_FORCE ? "-f " : "", se->se_path);
+		argv[4] = "-fn";
-	zfsctl_snapshot_rele(se);
+	argv[5] = se->se_path;
 	dprintf("unmount; path=%s\n", se->se_path);
 	error = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
-	strfree(argv[2]);
+	zfsctl_snapshot_rele(se);
 
 
 	/*
@@ -1050,11 +1047,6 @@ zfsctl_snapshot_unmount(char *snapname, int flags)
 }
 
 #define	MOUNT_BUSY 0x80		/* Mount failed due to EBUSY (from mntent.h) */
-#define	SET_MOUNT_CMD \
-	"exec 0</dev/null " \
-	"     1>/dev/null " \
-	"     2>/dev/null; " \
-	"mount -t zfs -n '%s' '%s'"
 
 int
 zfsctl_snapshot_mount(struct path *path, int flags)
@@ -1065,7 +1057,8 @@ zfsctl_snapshot_mount(struct path *path, int flags)
 	zfs_sb_t *snap_zsb;
 	zfs_snapentry_t *se;
 	char *full_name, *full_path;
-	char *argv[] = { "/bin/sh", "-c", NULL, NULL };
+	char *argv[] = { "/usr/bin/env", "mount", "-t", "zfs", "-n", NULL, NULL,
+	    NULL };
 	char *envp[] = { NULL };
 	int error;
 	struct path spath;
@@ -1110,9 +1103,9 @@ zfsctl_snapshot_mount(struct path *path, int flags)
 	 * value from call_usermodehelper() will be (exitcode << 8 + signal).
 	 */
 	dprintf("mount; name=%s path=%s\n", full_name, full_path);
-	argv[2] = kmem_asprintf(SET_MOUNT_CMD, full_name, full_path);
+	argv[5] = full_name;
+	argv[6] = full_path;
 	error = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
-	strfree(argv[2]);
 	if (error) {
 		if (!(error & MOUNT_BUSY << 8)) {
 			cmn_err(CE_WARN, "Unable to automount %s/%s: %d",

module/zfs/zfs_dir.c

@@ -760,7 +760,7 @@ zfs_link_create(zfs_dirlock_t *dl, znode_t *zp, dmu_tx_t *tx, int flag)
 		SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CTIME(zsb), NULL,
 		    ctime, sizeof (ctime));
 		zfs_tstamp_update_setup(zp, STATE_CHANGED, mtime,
-		    ctime, B_TRUE);
+		    ctime);
 	}
 	error = sa_bulk_update(zp->z_sa_hdl, bulk, count, tx);
 	ASSERT(error == 0);
@@ -781,7 +781,7 @@ zfs_link_create(zfs_dirlock_t *dl, znode_t *zp, dmu_tx_t *tx, int flag)
 	    ctime, sizeof (ctime));
 	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_FLAGS(zsb), NULL,
 	    &dzp->z_pflags, sizeof (dzp->z_pflags));
-	zfs_tstamp_update_setup(dzp, CONTENT_MODIFIED, mtime, ctime, B_TRUE);
+	zfs_tstamp_update_setup(dzp, CONTENT_MODIFIED, mtime, ctime);
 	error = sa_bulk_update(dzp->z_sa_hdl, bulk, count, tx);
 	ASSERT(error == 0);
 	mutex_exit(&dzp->z_lock);
@@ -876,8 +876,8 @@ zfs_link_destroy(zfs_dirlock_t *dl, znode_t *zp, dmu_tx_t *tx, int flag,
 			    NULL, &ctime, sizeof (ctime));
 			SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_FLAGS(zsb),
 			    NULL, &zp->z_pflags, sizeof (zp->z_pflags));
-			zfs_tstamp_update_setup(zp, STATE_CHANGED, mtime, ctime,
+			zfs_tstamp_update_setup(zp, STATE_CHANGED, mtime,
-			    B_TRUE);
+			    ctime);
 		}
 		SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_LINKS(zsb),
 		    NULL, &zp->z_links, sizeof (zp->z_links));
@@ -904,7 +904,7 @@ zfs_link_destroy(zfs_dirlock_t *dl, znode_t *zp, dmu_tx_t *tx, int flag,
 	    NULL, mtime, sizeof (mtime));
 	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_FLAGS(zsb),
 	    NULL, &dzp->z_pflags, sizeof (dzp->z_pflags));
-	zfs_tstamp_update_setup(dzp, CONTENT_MODIFIED, mtime, ctime, B_TRUE);
+	zfs_tstamp_update_setup(dzp, CONTENT_MODIFIED, mtime, ctime);
 	error = sa_bulk_update(dzp->z_sa_hdl, bulk, count, tx);
 	ASSERT(error == 0);
 	mutex_exit(&dzp->z_lock);

module/zfs/zfs_sa.c

@@ -277,7 +277,7 @@ zfs_sa_upgrade(sa_handle_t *hdl, dmu_tx_t *tx)
 	sa_bulk_attr_t *bulk, *sa_attrs;
 	zfs_acl_locator_cb_t locate = { 0 };
 	uint64_t uid, gid, mode, rdev, xattr, parent;
-	uint64_t crtime[2], mtime[2], ctime[2];
+	uint64_t crtime[2], mtime[2], ctime[2], atime[2];
 	zfs_acl_phys_t znode_acl;
 	char scanstamp[AV_SCANSTAMP_SZ];
 	boolean_t drop_lock = B_FALSE;
@@ -309,6 +309,7 @@ zfs_sa_upgrade(sa_handle_t *hdl, dmu_tx_t *tx)
 
 	/* First do a bulk query of the attributes that aren't cached */
 	bulk = kmem_alloc(sizeof (sa_bulk_attr_t) * 20, KM_SLEEP);
+	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_ATIME(zsb), NULL, &atime, 16);
 	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_MTIME(zsb), NULL, &mtime, 16);
 	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CTIME(zsb), NULL, &ctime, 16);
 	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CRTIME(zsb), NULL, &crtime, 16);
@@ -344,7 +345,7 @@ zfs_sa_upgrade(sa_handle_t *hdl, dmu_tx_t *tx)
 	SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_FLAGS(zsb), NULL,
 	    &zp->z_pflags, 8);
 	SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_ATIME(zsb), NULL,
-	    zp->z_atime, 16);
+	    &atime, 16);
 	SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_MTIME(zsb), NULL,
 	    &mtime, 16);
 	SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_CTIME(zsb), NULL,

module/zfs/zfs_vfsops.c

@@ -699,20 +699,18 @@ zfs_sb_create(const char *osname, zfs_mntopts_t *zmo, zfs_sb_t **zsbp)
 
 	zsb = kmem_zalloc(sizeof (zfs_sb_t), KM_SLEEP);
 
+	/*
+	 * Optional temporary mount options, free'd in zfs_sb_free().
+	 */
+	zsb->z_mntopts = (zmo ? zmo : zfs_mntopts_alloc());
+
 	/*
 	 * We claim to always be readonly so we can open snapshots;
 	 * other ZPL code will prevent us from writing to snapshots.
 	 */
 	error = dmu_objset_own(osname, DMU_OST_ZFS, B_TRUE, zsb, &os);
-	if (error) {
+	if (error)
-		kmem_free(zsb, sizeof (zfs_sb_t));
+		goto out_zmo;
-		return (error);
-	}
-
-	/*
-	 * Optional temporary mount options, free'd in zfs_sb_free().
-	 */
-	zsb->z_mntopts = (zmo ? zmo : zfs_mntopts_alloc());
 
 	/*
 	 * Initialize the zfs-specific filesystem structure.
@@ -840,8 +838,9 @@ zfs_sb_create(const char *osname, zfs_mntopts_t *zmo, zfs_sb_t **zsbp)
 
 out:
 	dmu_objset_disown(os, zsb);
+out_zmo:
 	*zsbp = NULL;
-
+	zfs_mntopts_free(zsb->z_mntopts);
 	kmem_free(zsb, sizeof (zfs_sb_t));
 	return (error);
 }
@@ -1404,13 +1403,13 @@ zfs_domount(struct super_block *sb, zfs_mntopts_t *zmo, int silent)
 	sb->s_time_gran = 1;
 	sb->s_blocksize = recordsize;
 	sb->s_blocksize_bits = ilog2(recordsize);
-	zsb->z_bdi.ra_pages = 0;
-	sb->s_bdi = &zsb->z_bdi;
 
-	error = -zpl_bdi_setup_and_register(&zsb->z_bdi, "zfs");
+	error = -zpl_bdi_setup(sb, "zfs");
 	if (error)
 		goto out;
 
+	sb->s_bdi->ra_pages = 0;
+
 	/* Set callback operations for the file system. */
 	sb->s_op = &zpl_super_operations;
 	sb->s_xattr = zpl_xattr_handlers;
@@ -1506,7 +1505,7 @@ zfs_umount(struct super_block *sb)
 	arc_remove_prune_callback(zsb->z_arc_prune);
 	VERIFY(zfs_sb_teardown(zsb, B_TRUE) == 0);
 	os = zsb->z_os;
-	bdi_destroy(sb->s_bdi);
+	zpl_bdi_destroy(sb);
 
 	/*
 	 * z_os will be NULL if there was an error in
@@ -1879,7 +1878,10 @@ zfs_init(void)
 void
 zfs_fini(void)
 {
-	taskq_wait_outstanding(system_taskq, 0);
+	/*
+	 * we don't use outstanding because zpl_posix_acl_free might add more.
+	 */
+	taskq_wait(system_taskq);
 	unregister_filesystem(&zpl_fs_type);
 	zfs_znode_fini();
 	zfsctl_fini();

module/zfs/zfs_vnops.c

@@ -550,7 +550,6 @@ zfs_read(struct inode *ip, uio_t *uio, int ioflag, cred_t *cr)
 out:
 	zfs_range_unlock(rl);
 
-	ZFS_ACCESSTIME_STAMP(zsb, zp);
 	ZFS_EXIT(zsb);
 	return (error);
 }
@@ -865,8 +864,7 @@ zfs_write(struct inode *ip, uio_t *uio, int ioflag, cred_t *cr)
 		}
 		mutex_exit(&zp->z_acl_lock);
 
-		zfs_tstamp_update_setup(zp, CONTENT_MODIFIED, mtime, ctime,
+		zfs_tstamp_update_setup(zp, CONTENT_MODIFIED, mtime, ctime);
-		    B_TRUE);
 
 		/*
 		 * Update the file size (zp_size) if it has changed;
@@ -1604,13 +1602,13 @@ top:
 	error = dmu_tx_assign(tx, waited ? TXG_WAITED : TXG_NOWAIT);
 	if (error) {
 		zfs_dirent_unlock(dl);
-		iput(ip);
-		if (xzp)
-			iput(ZTOI(xzp));
 		if (error == ERESTART) {
 			waited = B_TRUE;
 			dmu_tx_wait(tx);
 			dmu_tx_abort(tx);
+			iput(ip);
+			if (xzp)
+				iput(ZTOI(xzp));
 			goto top;
 		}
 #ifdef HAVE_PN_UTILS
@@ -1618,6 +1616,9 @@ top:
 			pn_free(realnmp);
 #endif /* HAVE_PN_UTILS */
 		dmu_tx_abort(tx);
+		iput(ip);
+		if (xzp)
+			iput(ZTOI(xzp));
 		ZFS_EXIT(zsb);
 		return (error);
 	}
@@ -1946,14 +1947,15 @@ top:
 		rw_exit(&zp->z_parent_lock);
 		rw_exit(&zp->z_name_lock);
 		zfs_dirent_unlock(dl);
-		iput(ip);
 		if (error == ERESTART) {
 			waited = B_TRUE;
 			dmu_tx_wait(tx);
 			dmu_tx_abort(tx);
+			iput(ip);
 			goto top;
 		}
 		dmu_tx_abort(tx);
+		iput(ip);
 		ZFS_EXIT(zsb);
 		return (error);
 	}
@@ -2140,9 +2142,6 @@ update:
 	zap_cursor_fini(&zc);
 	if (error == ENOENT)
 		error = 0;
-
-	ZFS_ACCESSTIME_STAMP(zsb, zp);
-
 out:
 	ZFS_EXIT(zsb);
 
@@ -2195,11 +2194,11 @@ zfs_getattr(struct inode *ip, vattr_t *vap, int flags, cred_t *cr)
 	zfs_sb_t *zsb = ITOZSB(ip);
 	int	error = 0;
 	uint64_t links;
-	uint64_t mtime[2], ctime[2];
+	uint64_t atime[2], mtime[2], ctime[2];
 	xvattr_t *xvap = (xvattr_t *)vap;	/* vap may be an xvattr_t * */
 	xoptattr_t *xoap = NULL;
 	boolean_t skipaclchk = (flags & ATTR_NOACLCHECK) ? B_TRUE : B_FALSE;
-	sa_bulk_attr_t bulk[2];
+	sa_bulk_attr_t bulk[3];
 	int count = 0;
 
 	ZFS_ENTER(zsb);
@@ -2207,6 +2206,7 @@ zfs_getattr(struct inode *ip, vattr_t *vap, int flags, cred_t *cr)
 
 	zfs_fuid_map_ids(zp, cr, &vap->va_uid, &vap->va_gid);
 
+	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_ATIME(zsb), NULL, &atime, 16);
 	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_MTIME(zsb), NULL, &mtime, 16);
 	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CTIME(zsb), NULL, &ctime, 16);
 
@@ -2355,7 +2355,7 @@ zfs_getattr(struct inode *ip, vattr_t *vap, int flags, cred_t *cr)
 		}
 	}
 
-	ZFS_TIME_DECODE(&vap->va_atime, zp->z_atime);
+	ZFS_TIME_DECODE(&vap->va_atime, atime);
 	ZFS_TIME_DECODE(&vap->va_mtime, mtime);
 	ZFS_TIME_DECODE(&vap->va_ctime, ctime);
 
@@ -2402,7 +2402,6 @@ zfs_getattr_fast(struct inode *ip, struct kstat *sp)
 	mutex_enter(&zp->z_lock);
 
 	generic_fillattr(ip, sp);
-	ZFS_TIME_DECODE(&sp->atime, zp->z_atime);
 
 	sa_object_size(zp->z_sa_hdl, &blksize, &nblocks);
 	sp->blksize = blksize;
@@ -2466,7 +2465,7 @@ zfs_setattr(struct inode *ip, vattr_t *vap, int flags, cred_t *cr)
 	uint64_t	new_mode;
 	uint64_t	new_uid, new_gid;
 	uint64_t	xattr_obj;
-	uint64_t	mtime[2], ctime[2];
+	uint64_t	mtime[2], ctime[2], atime[2];
 	znode_t		*attrzp;
 	int		need_policy = FALSE;
 	int		err, err2;
@@ -2939,10 +2938,11 @@ top:
 	}
 
 
-	if (mask & ATTR_ATIME) {
+	if ((mask & ATTR_ATIME) || zp->z_atime_dirty) {
-		ZFS_TIME_ENCODE(&vap->va_atime, zp->z_atime);
+		zp->z_atime_dirty = 0;
+		ZFS_TIME_ENCODE(&ip->i_atime, atime);
 		SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_ATIME(zsb), NULL,
-		    &zp->z_atime, sizeof (zp->z_atime));
+		    &atime, sizeof (atime));
 	}
 
 	if (mask & ATTR_MTIME) {
@@ -2957,19 +2957,17 @@ top:
 		    NULL, mtime, sizeof (mtime));
 		SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CTIME(zsb), NULL,
 		    &ctime, sizeof (ctime));
-		zfs_tstamp_update_setup(zp, CONTENT_MODIFIED, mtime, ctime,
+		zfs_tstamp_update_setup(zp, CONTENT_MODIFIED, mtime, ctime);
-		    B_TRUE);
 	} else if (mask != 0) {
 		SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CTIME(zsb), NULL,
 		    &ctime, sizeof (ctime));
-		zfs_tstamp_update_setup(zp, STATE_CHANGED, mtime, ctime,
+		zfs_tstamp_update_setup(zp, STATE_CHANGED, mtime, ctime);
-		    B_TRUE);
 		if (attrzp) {
 			SA_ADD_BULK_ATTR(xattr_bulk, xattr_count,
 			    SA_ZPL_CTIME(zsb), NULL,
 			    &ctime, sizeof (ctime));
 			zfs_tstamp_update_setup(attrzp, STATE_CHANGED,
-			    mtime, ctime, B_TRUE);
+			    mtime, ctime);
 		}
 	}
 	/*
@@ -3031,8 +3029,6 @@ out:
 		ASSERT(err2 == 0);
 	}
 
-	if (attrzp)
-		iput(ZTOI(attrzp));
 	if (aclp)
 		zfs_acl_free(aclp);
 
@@ -3043,11 +3039,15 @@ out:
 
 	if (err) {
 		dmu_tx_abort(tx);
+		if (attrzp)
+			iput(ZTOI(attrzp));
 		if (err == ERESTART)
 			goto top;
 	} else {
 		err2 = sa_bulk_update(zp->z_sa_hdl, bulk, count, tx);
 		dmu_tx_commit(tx);
+		if (attrzp)
+			iput(ZTOI(attrzp));
 		zfs_inode_update(zp);
 	}
 
@@ -3080,7 +3080,7 @@ zfs_rename_unlock(zfs_zlock_t **zlpp)
 
 	while ((zl = *zlpp) != NULL) {
 		if (zl->zl_znode != NULL)
-			iput(ZTOI(zl->zl_znode));
+			zfs_iput_async(ZTOI(zl->zl_znode));
 		rw_exit(zl->zl_rwlock);
 		*zlpp = zl->zl_next;
 		kmem_free(zl, sizeof (*zl));
@@ -3417,16 +3417,19 @@ top:
 		if (sdzp == tdzp)
 			rw_exit(&sdzp->z_name_lock);
 
-		iput(ZTOI(szp));
-		if (tzp)
-			iput(ZTOI(tzp));
 		if (error == ERESTART) {
 			waited = B_TRUE;
 			dmu_tx_wait(tx);
 			dmu_tx_abort(tx);
+			iput(ZTOI(szp));
+			if (tzp)
+				iput(ZTOI(tzp));
 			goto top;
 		}
 		dmu_tx_abort(tx);
+		iput(ZTOI(szp));
+		if (tzp)
+			iput(ZTOI(tzp));
 		ZFS_EXIT(zsb);
 		return (error);
 	}
@@ -3690,7 +3693,6 @@ zfs_readlink(struct inode *ip, uio_t *uio, cred_t *cr)
 		error = zfs_sa_readlink(zp, uio);
 	mutex_exit(&zp->z_lock);
 
-	ZFS_ACCESSTIME_STAMP(zsb, zp);
 	ZFS_EXIT(zsb);
 	return (error);
 }
@@ -4056,7 +4058,7 @@ zfs_dirty_inode(struct inode *ip, int flags)
 	dmu_tx_t	*tx;
 	uint64_t	mode, atime[2], mtime[2], ctime[2];
 	sa_bulk_attr_t	bulk[4];
-	int		error;
+	int		error = 0;
 	int		cnt = 0;
 
 	if (zfs_is_readonly(zsb) || dmu_objset_is_snapshot(zsb->z_os))
@@ -4065,6 +4067,20 @@ zfs_dirty_inode(struct inode *ip, int flags)
 	ZFS_ENTER(zsb);
 	ZFS_VERIFY_ZP(zp);
 
+#ifdef I_DIRTY_TIME
+	/*
+	 * This is the lazytime semantic indroduced in Linux 4.0
+	 * This flag will only be called from update_time when lazytime is set.
+	 * (Note, I_DIRTY_SYNC will also set if not lazytime)
+	 * Fortunately mtime and ctime are managed within ZFS itself, so we
+	 * only need to dirty atime.
+	 */
+	if (flags == I_DIRTY_TIME) {
+		zp->z_atime_dirty = 1;
+		goto out;
+	}
+#endif
+
 	tx = dmu_tx_create(zsb->z_os);
 
 	dmu_tx_hold_sa(tx, zp->z_sa_hdl, B_FALSE);
@@ -4077,6 +4093,8 @@ zfs_dirty_inode(struct inode *ip, int flags)
 	}
 
 	mutex_enter(&zp->z_lock);
+	zp->z_atime_dirty = 0;
+
 	SA_ADD_BULK_ATTR(bulk, cnt, SA_ZPL_MODE(zsb), NULL, &mode, 8);
 	SA_ADD_BULK_ATTR(bulk, cnt, SA_ZPL_ATIME(zsb), NULL, &atime, 16);
 	SA_ADD_BULK_ATTR(bulk, cnt, SA_ZPL_MTIME(zsb), NULL, &mtime, 16);
@@ -4089,7 +4107,6 @@ zfs_dirty_inode(struct inode *ip, int flags)
 	mode = ip->i_mode;
 
 	zp->z_mode = mode;
-	zp->z_atime_dirty = 0;
 
 	error = sa_bulk_update(zp->z_sa_hdl, bulk, cnt, tx);
 	mutex_exit(&zp->z_lock);
@@ -4107,6 +4124,7 @@ zfs_inactive(struct inode *ip)
 {
 	znode_t	*zp = ITOZ(ip);
 	zfs_sb_t *zsb = ITOZSB(ip);
+	uint64_t atime[2];
 	int error;
 	int need_unlock = 0;
 
@@ -4130,9 +4148,10 @@ zfs_inactive(struct inode *ip)
 		if (error) {
 			dmu_tx_abort(tx);
 		} else {
+			ZFS_TIME_ENCODE(&ip->i_atime, atime);
 			mutex_enter(&zp->z_lock);
 			(void) sa_update(zp->z_sa_hdl, SA_ZPL_ATIME(zsb),
-			    (void *)&zp->z_atime, sizeof (zp->z_atime), tx);
+			    (void *)&atime, sizeof (atime), tx);
 			zp->z_atime_dirty = 0;
 			mutex_exit(&zp->z_lock);
 			dmu_tx_commit(tx);
@@ -4241,9 +4260,6 @@ zfs_getpage(struct inode *ip, struct page *pl[], int nr_pages)
 
 	err = zfs_fillpage(ip, pl, nr_pages);
 
-	if (!err)
-		ZFS_ACCESSTIME_STAMP(zsb, zp);
-
 	ZFS_EXIT(zsb);
 	return (err);
 }

module/zfs/zfs_znode.c

@@ -482,6 +482,90 @@ zfs_inode_set_ops(zfs_sb_t *zsb, struct inode *ip)
 	}
 }
 
+void
+zfs_set_inode_flags(znode_t *zp, struct inode *ip)
+{
+	/*
+	 * Linux and Solaris have different sets of file attributes, so we
+	 * restrict this conversion to the intersection of the two.
+	 */
+
+	if (zp->z_pflags & ZFS_IMMUTABLE)
+		ip->i_flags |= S_IMMUTABLE;
+	else
+		ip->i_flags &= ~S_IMMUTABLE;
+
+	if (zp->z_pflags & ZFS_APPENDONLY)
+		ip->i_flags |= S_APPEND;
+	else
+		ip->i_flags &= ~S_APPEND;
+}
+
+/*
+ * Update the embedded inode given the znode.  We should work toward
+ * eliminating this function as soon as possible by removing values
+ * which are duplicated between the znode and inode.  If the generic
+ * inode has the correct field it should be used, and the ZFS code
+ * updated to access the inode.  This can be done incrementally.
+ */
+static void
+zfs_inode_update_impl(znode_t *zp, boolean_t new)
+{
+	zfs_sb_t	*zsb;
+	struct inode	*ip;
+	uint32_t	blksize;
+	u_longlong_t	i_blocks;
+	uint64_t	atime[2], mtime[2], ctime[2];
+
+	ASSERT(zp != NULL);
+	zsb = ZTOZSB(zp);
+	ip = ZTOI(zp);
+
+	/* Skip .zfs control nodes which do not exist on disk. */
+	if (zfsctl_is_node(ip))
+		return;
+
+	sa_lookup(zp->z_sa_hdl, SA_ZPL_ATIME(zsb), &atime, 16);
+	sa_lookup(zp->z_sa_hdl, SA_ZPL_MTIME(zsb), &mtime, 16);
+	sa_lookup(zp->z_sa_hdl, SA_ZPL_CTIME(zsb), &ctime, 16);
+
+	dmu_object_size_from_db(sa_get_db(zp->z_sa_hdl), &blksize, &i_blocks);
+
+	spin_lock(&ip->i_lock);
+	ip->i_generation = zp->z_gen;
+	ip->i_uid = SUID_TO_KUID(zp->z_uid);
+	ip->i_gid = SGID_TO_KGID(zp->z_gid);
+	set_nlink(ip, zp->z_links);
+	ip->i_mode = zp->z_mode;
+	zfs_set_inode_flags(zp, ip);
+	ip->i_blkbits = SPA_MINBLOCKSHIFT;
+	ip->i_blocks = i_blocks;
+
+	/*
+	 * Only read atime from SA if we are newly created inode (or rezget),
+	 * otherwise i_atime might be dirty.
+	 */
+	if (new)
+		ZFS_TIME_DECODE(&ip->i_atime, atime);
+	ZFS_TIME_DECODE(&ip->i_mtime, mtime);
+	ZFS_TIME_DECODE(&ip->i_ctime, ctime);
+
+	i_size_write(ip, zp->z_size);
+	spin_unlock(&ip->i_lock);
+}
+
+static void
+zfs_inode_update_new(znode_t *zp)
+{
+	zfs_inode_update_impl(zp, B_TRUE);
+}
+
+void
+zfs_inode_update(znode_t *zp)
+{
+	zfs_inode_update_impl(zp, B_FALSE);
+}
+
 /*
  * Construct a znode+inode and initialize.
  *
@@ -497,7 +581,7 @@ zfs_znode_alloc(zfs_sb_t *zsb, dmu_buf_t *db, int blksz,
 	struct inode *ip;
 	uint64_t mode;
 	uint64_t parent;
-	sa_bulk_attr_t bulk[9];
+	sa_bulk_attr_t bulk[8];
 	int count = 0;
 
 	ASSERT(zsb != NULL);
@@ -536,8 +620,6 @@ zfs_znode_alloc(zfs_sb_t *zsb, dmu_buf_t *db, int blksz,
 	    &zp->z_pflags, 8);
 	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_PARENT(zsb), NULL,
 	    &parent, 8);
-	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_ATIME(zsb), NULL,
-	    &zp->z_atime, 16);
 	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_UID(zsb), NULL, &zp->z_uid, 8);
 	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_GID(zsb), NULL, &zp->z_gid, 8);
 
@@ -551,7 +633,7 @@ zfs_znode_alloc(zfs_sb_t *zsb, dmu_buf_t *db, int blksz,
 	zp->z_mode = mode;
 
 	ip->i_ino = obj;
-	zfs_inode_update(zp);
+	zfs_inode_update_new(zp);
 	zfs_inode_set_ops(zsb, ip);
 
 	/*
@@ -578,71 +660,6 @@ error:
 	return (NULL);
 }
 
-void
-zfs_set_inode_flags(znode_t *zp, struct inode *ip)
-{
-	/*
-	 * Linux and Solaris have different sets of file attributes, so we
-	 * restrict this conversion to the intersection of the two.
-	 */
-
-	if (zp->z_pflags & ZFS_IMMUTABLE)
-		ip->i_flags |= S_IMMUTABLE;
-	else
-		ip->i_flags &= ~S_IMMUTABLE;
-
-	if (zp->z_pflags & ZFS_APPENDONLY)
-		ip->i_flags |= S_APPEND;
-	else
-		ip->i_flags &= ~S_APPEND;
-}
-
-/*
- * Update the embedded inode given the znode.  We should work toward
- * eliminating this function as soon as possible by removing values
- * which are duplicated between the znode and inode.  If the generic
- * inode has the correct field it should be used, and the ZFS code
- * updated to access the inode.  This can be done incrementally.
- */
-void
-zfs_inode_update(znode_t *zp)
-{
-	zfs_sb_t	*zsb;
-	struct inode	*ip;
-	uint32_t	blksize;
-	uint64_t	atime[2], mtime[2], ctime[2];
-
-	ASSERT(zp != NULL);
-	zsb = ZTOZSB(zp);
-	ip = ZTOI(zp);
-
-	/* Skip .zfs control nodes which do not exist on disk. */
-	if (zfsctl_is_node(ip))
-		return;
-
-	sa_lookup(zp->z_sa_hdl, SA_ZPL_ATIME(zsb), &atime, 16);
-	sa_lookup(zp->z_sa_hdl, SA_ZPL_MTIME(zsb), &mtime, 16);
-	sa_lookup(zp->z_sa_hdl, SA_ZPL_CTIME(zsb), &ctime, 16);
-
-	spin_lock(&ip->i_lock);
-	ip->i_generation = zp->z_gen;
-	ip->i_uid = SUID_TO_KUID(zp->z_uid);
-	ip->i_gid = SGID_TO_KGID(zp->z_gid);
-	set_nlink(ip, zp->z_links);
-	ip->i_mode = zp->z_mode;
-	zfs_set_inode_flags(zp, ip);
-	ip->i_blkbits = SPA_MINBLOCKSHIFT;
-	dmu_object_size_from_db(sa_get_db(zp->z_sa_hdl), &blksize,
-	    (u_longlong_t *)&ip->i_blocks);
-
-	ZFS_TIME_DECODE(&ip->i_atime, atime);
-	ZFS_TIME_DECODE(&ip->i_mtime, mtime);
-	ZFS_TIME_DECODE(&ip->i_ctime, ctime);
-
-	i_size_write(ip, zp->z_size);
-	spin_unlock(&ip->i_lock);
-}
-
 /*
  * Safely mark an inode dirty.  Inodes which are part of a read-only
  * file system or snapshot may not be dirtied.
@@ -1123,7 +1140,7 @@ zfs_rezget(znode_t *zp)
 	dmu_buf_t *db;
 	uint64_t obj_num = zp->z_id;
 	uint64_t mode;
-	sa_bulk_attr_t bulk[8];
+	sa_bulk_attr_t bulk[7];
 	int err;
 	int count = 0;
 	uint64_t gen;
@@ -1183,8 +1200,6 @@ zfs_rezget(znode_t *zp)
 	    &zp->z_links, sizeof (zp->z_links));
 	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_FLAGS(zsb), NULL,
 	    &zp->z_pflags, sizeof (zp->z_pflags));
-	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_ATIME(zsb), NULL,
-	    &zp->z_atime, sizeof (zp->z_atime));
 	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_UID(zsb), NULL,
 	    &zp->z_uid, sizeof (zp->z_uid));
 	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_GID(zsb), NULL,
@@ -1208,7 +1223,8 @@ zfs_rezget(znode_t *zp)
 
 	zp->z_unlinked = (zp->z_links == 0);
 	zp->z_blksz = doi.doi_data_block_size;
-	zfs_inode_update(zp);
+	zp->z_atime_dirty = 0;
+	zfs_inode_update_new(zp);
 
 	zfs_znode_hold_exit(zsb, zh);
 
@@ -1279,78 +1295,28 @@ zfs_compare_timespec(struct timespec *t1, struct timespec *t2)
 	return (t1->tv_nsec - t2->tv_nsec);
 }
 
-/*
- *  Determine whether the znode's atime must be updated.  The logic mostly
- *  duplicates the Linux kernel's relatime_need_update() functionality.
- *  This function is only called if the underlying filesystem actually has
- *  atime updates enabled.
- */
-static inline boolean_t
-zfs_atime_need_update(znode_t *zp, timestruc_t *now)
-{
-	if (!ZTOZSB(zp)->z_relatime)
-		return (B_TRUE);
-
-	/*
-	 * In relatime mode, only update the atime if the previous atime
-	 * is earlier than either the ctime or mtime or if at least a day
-	 * has passed since the last update of atime.
-	 */
-	if (zfs_compare_timespec(&ZTOI(zp)->i_mtime, &ZTOI(zp)->i_atime) >= 0)
-		return (B_TRUE);
-
-	if (zfs_compare_timespec(&ZTOI(zp)->i_ctime, &ZTOI(zp)->i_atime) >= 0)
-		return (B_TRUE);
-
-	if ((long)now->tv_sec - ZTOI(zp)->i_atime.tv_sec >= 24*60*60)
-		return (B_TRUE);
-
-	return (B_FALSE);
-}
-
 /*
  * Prepare to update znode time stamps.
  *
  *	IN:	zp	- znode requiring timestamp update
- *		flag	- ATTR_MTIME, ATTR_CTIME, ATTR_ATIME flags
+ *		flag	- ATTR_MTIME, ATTR_CTIME flags
- *		have_tx	- true of caller is creating a new txg
  *
- *	OUT:	zp	- new atime (via underlying inode's i_atime)
+ *	OUT:	zp	- z_seq
  *		mtime	- new mtime
  *		ctime	- new ctime
  *
- * NOTE: The arguments are somewhat redundant.  The following condition
+ *	Note: We don't update atime here, because we rely on Linux VFS to do
- * is always true:
+ *	atime updating.
- *
- *		have_tx == !(flag & ATTR_ATIME)
  */
 void
 zfs_tstamp_update_setup(znode_t *zp, uint_t flag, uint64_t mtime[2],
-    uint64_t ctime[2], boolean_t have_tx)
+    uint64_t ctime[2])
 {
 	timestruc_t	now;
 
-	ASSERT(have_tx == !(flag & ATTR_ATIME));
 	gethrestime(&now);
 
-	/*
-	 * NOTE: The following test intentionally does not update z_atime_dirty
-	 * in the case where an ATIME update has been requested but for which
-	 * the update is omitted due to relatime logic.  The rationale being
-	 * that if the flag was set somewhere else, we should leave it alone
-	 * here.
-	 */
-	if (flag & ATTR_ATIME) {
-		if (zfs_atime_need_update(zp, &now)) {
-			ZFS_TIME_ENCODE(&now, zp->z_atime);
-			ZTOI(zp)->i_atime.tv_sec = zp->z_atime[0];
-			ZTOI(zp)->i_atime.tv_nsec = zp->z_atime[1];
-			zp->z_atime_dirty = 1;
-		}
-	} else {
-		zp->z_atime_dirty = 0;
 	zp->z_seq++;
-	}
 
 	if (flag & ATTR_MTIME) {
 		ZFS_TIME_ENCODE(&now, mtime);
@@ -1722,7 +1688,7 @@ log:
 	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CTIME(zsb), NULL, ctime, 16);
 	SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_FLAGS(zsb),
 	    NULL, &zp->z_pflags, 8);
-	zfs_tstamp_update_setup(zp, CONTENT_MODIFIED, mtime, ctime, B_TRUE);
+	zfs_tstamp_update_setup(zp, CONTENT_MODIFIED, mtime, ctime);
 	error = sa_bulk_update(zp->z_sa_hdl, bulk, count, tx);
 	ASSERT(error == 0);
 

module/zfs/zio.c

@@ -139,10 +139,10 @@ zio_init(void)
 		if (arc_watch && !IS_P2ALIGNED(size, PAGESIZE))
 			continue;
 #endif
-		if (size <= 4 * SPA_MINBLOCKSIZE) {
+		if (size < PAGESIZE) {
 			align = SPA_MINBLOCKSIZE;
 		} else if (IS_P2ALIGNED(size, p2 >> 2)) {
-			align = MIN(p2 >> 2, PAGESIZE);
+			align = PAGESIZE;
 		}
 
 		if (align != 0) {
@@ -1415,6 +1415,31 @@ zio_execute(zio_t *zio)
 	spl_fstrans_unmark(cookie);
 }
 
+/*
+ * Used to determine if in the current context the stack is sized large
+ * enough to allow zio_execute() to be called recursively.  A minimum
+ * stack size of 16K is required to avoid needing to re-dispatch the zio.
+ */
+boolean_t
+zio_execute_stack_check(zio_t *zio)
+{
+#if !defined(HAVE_LARGE_STACKS)
+	dsl_pool_t *dp = spa_get_dsl(zio->io_spa);
+
+	/* Executing in txg_sync_thread() context. */
+	if (dp && curthread == dp->dp_tx.tx_sync_thread)
+		return (B_TRUE);
+
+	/* Pool initialization outside of zio_taskq context. */
+	if (dp && spa_is_initializing(dp->dp_spa) &&
+	    !zio_taskq_member(zio, ZIO_TASKQ_ISSUE) &&
+	    !zio_taskq_member(zio, ZIO_TASKQ_ISSUE_HIGH))
+		return (B_TRUE);
+#endif /* HAVE_LARGE_STACKS */
+
+	return (B_FALSE);
+}
+
 __attribute__((always_inline))
 static inline void
 __zio_execute(zio_t *zio)
@@ -1424,8 +1449,6 @@ __zio_execute(zio_t *zio)
 	while (zio->io_stage < ZIO_STAGE_DONE) {
 		enum zio_stage pipeline = zio->io_pipeline;
 		enum zio_stage stage = zio->io_stage;
-		dsl_pool_t *dp;
-		boolean_t cut;
 		int rv;
 
 		ASSERT(!MUTEX_HELD(&zio->io_lock));
@@ -1438,10 +1461,6 @@ __zio_execute(zio_t *zio)
 
 		ASSERT(stage <= ZIO_STAGE_DONE);
 
-		dp = spa_get_dsl(zio->io_spa);
-		cut = (stage == ZIO_STAGE_VDEV_IO_START) ?
-		    zio_requeue_io_start_cut_in_line : B_FALSE;
-
 		/*
 		 * If we are in interrupt context and this pipeline stage
 		 * will grab a config lock that is held across I/O,
@@ -1453,21 +1472,19 @@ __zio_execute(zio_t *zio)
 		 */
 		if ((stage & ZIO_BLOCKING_STAGES) && zio->io_vd == NULL &&
 		    zio_taskq_member(zio, ZIO_TASKQ_INTERRUPT)) {
+			boolean_t cut = (stage == ZIO_STAGE_VDEV_IO_START) ?
+			    zio_requeue_io_start_cut_in_line : B_FALSE;
 			zio_taskq_dispatch(zio, ZIO_TASKQ_ISSUE, cut);
 			return;
 		}
 
 		/*
-		 * If we executing in the context of the tx_sync_thread,
+		 * If the current context doesn't have large enough stacks
-		 * or we are performing pool initialization outside of a
+		 * the zio must be issued asynchronously to prevent overflow.
-		 * zio_taskq[ZIO_TASKQ_ISSUE|ZIO_TASKQ_ISSUE_HIGH] context.
-		 * Then issue the zio asynchronously to minimize stack usage
-		 * for these deep call paths.
 		 */
-		if ((dp && curthread == dp->dp_tx.tx_sync_thread) ||
+		if (zio_execute_stack_check(zio)) {
-		    (dp && spa_is_initializing(dp->dp_spa) &&
+			boolean_t cut = (stage == ZIO_STAGE_VDEV_IO_START) ?
-		    !zio_taskq_member(zio, ZIO_TASKQ_ISSUE) &&
+			    zio_requeue_io_start_cut_in_line : B_FALSE;
-		    !zio_taskq_member(zio, ZIO_TASKQ_ISSUE_HIGH))) {
 			zio_taskq_dispatch(zio, ZIO_TASKQ_ISSUE, cut);
 			return;
 		}
@@ -3455,7 +3472,7 @@ zbookmark_is_before(const dnode_phys_t *dnp, const zbookmark_phys_t *zb1,
 
 	if (zb1->zb_object == DMU_META_DNODE_OBJECT) {
 		uint64_t nextobj = zb1nextL0 *
-		    (dnp->dn_datablkszsec << SPA_MINBLOCKSHIFT) >> DNODE_SHIFT;
+		    (dnp->dn_datablkszsec << (SPA_MINBLOCKSHIFT - DNODE_SHIFT));
 		return (nextobj <= zb2thisobj);
 	}
 

module/zfs/zpl_ctldir.c

@@ -100,16 +100,17 @@ zpl_root_readdir(struct file *filp, void *dirent, filldir_t filldir)
  */
 /* ARGSUSED */
 static int
-zpl_root_getattr(struct vfsmount *mnt, struct dentry *dentry,
+zpl_root_getattr_impl(const struct path *path, struct kstat *stat,
-    struct kstat *stat)
+    u32 request_mask, unsigned int query_flags)
 {
-	int error;
+	struct inode *ip = path->dentry->d_inode;
 
-	error = simple_getattr(mnt, dentry, stat);
+	generic_fillattr(ip, stat);
-	stat->atime = CURRENT_TIME;
+	stat->atime = current_time(ip);
 
-	return (error);
+	return (0);
 }
+ZPL_GETATTR_WRAPPER(zpl_root_getattr);
 
 static struct dentry *
 #ifdef HAVE_LOOKUP_NAMEIDATA
@@ -301,13 +302,17 @@ zpl_snapdir_readdir(struct file *filp, void *dirent, filldir_t filldir)
 }
 #endif /* HAVE_VFS_ITERATE */
 
-int
+static int
-zpl_snapdir_rename(struct inode *sdip, struct dentry *sdentry,
+zpl_snapdir_rename2(struct inode *sdip, struct dentry *sdentry,
-    struct inode *tdip, struct dentry *tdentry)
+    struct inode *tdip, struct dentry *tdentry, unsigned int flags)
 {
 	cred_t *cr = CRED();
 	int error;
 
+	/* We probably don't want to support renameat2(2) in ctldir */
+	if (flags)
+		return (-EINVAL);
+
 	crhold(cr);
 	error = -zfsctl_snapdir_rename(sdip, dname(sdentry),
 	    tdip, dname(tdentry), cr, 0);
@@ -317,6 +322,15 @@ zpl_snapdir_rename(struct inode *sdip, struct dentry *sdentry,
 	return (error);
 }
 
+#ifndef HAVE_RENAME_WANTS_FLAGS
+static int
+zpl_snapdir_rename(struct inode *sdip, struct dentry *sdentry,
+    struct inode *tdip, struct dentry *tdentry)
+{
+	return (zpl_snapdir_rename2(sdip, sdentry, tdip, tdentry, 0));
+}
+#endif
+
 static int
 zpl_snapdir_rmdir(struct inode *dip, struct dentry *dentry)
 {
@@ -362,21 +376,22 @@ zpl_snapdir_mkdir(struct inode *dip, struct dentry *dentry, zpl_umode_t mode)
  */
 /* ARGSUSED */
 static int
-zpl_snapdir_getattr(struct vfsmount *mnt, struct dentry *dentry,
+zpl_snapdir_getattr_impl(const struct path *path, struct kstat *stat,
-    struct kstat *stat)
+    u32 request_mask, unsigned int query_flags)
 {
-	zfs_sb_t *zsb = ITOZSB(dentry->d_inode);
+	struct inode *ip = path->dentry->d_inode;
-	int error;
+	zfs_sb_t *zsb = ITOZSB(path->dentry->d_inode);
 
 	ZFS_ENTER(zsb);
-	error = simple_getattr(mnt, dentry, stat);
+	generic_fillattr(path->dentry->d_inode, stat);
 	stat->nlink = stat->size = 2;
 	stat->ctime = stat->mtime = dmu_objset_snap_cmtime(zsb->z_os);
-	stat->atime = CURRENT_TIME;
+	stat->atime = current_time(ip);
 	ZFS_EXIT(zsb);
 
-	return (error);
+	return (0);
 }
+ZPL_GETATTR_WRAPPER(zpl_snapdir_getattr);
 
 /*
  * The '.zfs/snapshot' directory file operations.  These mainly control
@@ -405,7 +420,11 @@ const struct file_operations zpl_fops_snapdir = {
 const struct inode_operations zpl_ops_snapdir = {
 	.lookup		= zpl_snapdir_lookup,
 	.getattr	= zpl_snapdir_getattr,
+#ifdef HAVE_RENAME_WANTS_FLAGS
+	.rename		= zpl_snapdir_rename2,
+#else
 	.rename		= zpl_snapdir_rename,
+#endif
 	.rmdir		= zpl_snapdir_rmdir,
 	.mkdir		= zpl_snapdir_mkdir,
 };
@@ -492,10 +511,10 @@ zpl_shares_readdir(struct file *filp, void *dirent, filldir_t filldir)
 
 /* ARGSUSED */
 static int
-zpl_shares_getattr(struct vfsmount *mnt, struct dentry *dentry,
+zpl_shares_getattr_impl(const struct path *path, struct kstat *stat,
-    struct kstat *stat)
+    u32 request_mask, unsigned int query_flags)
 {
-	struct inode *ip = dentry->d_inode;
+	struct inode *ip = path->dentry->d_inode;
 	zfs_sb_t *zsb = ITOZSB(ip);
 	znode_t *dzp;
 	int error;
@@ -503,11 +522,11 @@ zpl_shares_getattr(struct vfsmount *mnt, struct dentry *dentry,
 	ZFS_ENTER(zsb);
 
 	if (zsb->z_shares_dir == 0) {
-		error = simple_getattr(mnt, dentry, stat);
+		generic_fillattr(path->dentry->d_inode, stat);
 		stat->nlink = stat->size = 2;
-		stat->atime = CURRENT_TIME;
+		stat->atime = current_time(ip);
 		ZFS_EXIT(zsb);
-		return (error);
+		return (0);
 	}
 
 	error = -zfs_zget(zsb, zsb->z_shares_dir, &dzp);
@@ -521,6 +540,7 @@ zpl_shares_getattr(struct vfsmount *mnt, struct dentry *dentry,
 
 	return (error);
 }
+ZPL_GETATTR_WRAPPER(zpl_shares_getattr);
 
 /*
  * The '.zfs/shares' directory file operations.

module/zfs/zpl_file.c

@@ -131,12 +131,15 @@ zpl_fsync(struct file *filp, struct dentry *dentry, int datasync)
 	return (error);
 }
 
+#ifdef HAVE_FILE_AIO_FSYNC
 static int
 zpl_aio_fsync(struct kiocb *kiocb, int datasync)
 {
 	struct file *filp = kiocb->ki_filp;
 	return (zpl_fsync(filp, filp->f_path.dentry, datasync));
 }
+#endif
+
 #elif defined(HAVE_FSYNC_WITHOUT_DENTRY)
 /*
  * Linux 2.6.35 - 3.0 API,
@@ -162,11 +165,14 @@ zpl_fsync(struct file *filp, int datasync)
 	return (error);
 }
 
+#ifdef HAVE_FILE_AIO_FSYNC
 static int
 zpl_aio_fsync(struct kiocb *kiocb, int datasync)
 {
 	return (zpl_fsync(kiocb->ki_filp, datasync));
 }
+#endif
+
 #elif defined(HAVE_FSYNC_RANGE)
 /*
  * Linux 3.1 - 3.x API,
@@ -197,11 +203,14 @@ zpl_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
 	return (error);
 }
 
+#ifdef HAVE_FILE_AIO_FSYNC
 static int
 zpl_aio_fsync(struct kiocb *kiocb, int datasync)
 {
 	return (zpl_fsync(kiocb->ki_filp, kiocb->ki_pos, -1, datasync));
 }
+#endif
+
 #else
 #error "Unsupported fops->fsync() implementation"
 #endif
@@ -250,20 +259,6 @@ zpl_read_common(struct inode *ip, const char *buf, size_t len, loff_t *ppos,
 	    flags, cr, 0));
 }
 
-static ssize_t
-zpl_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
-{
-	cred_t *cr = CRED();
-	ssize_t read;
-
-	crhold(cr);
-	read = zpl_read_common(filp->f_mapping->host, buf, len, ppos,
-	    UIO_USERSPACE, filp->f_flags, cr);
-	crfree(cr);
-
-	return (read);
-}
-
 static ssize_t
 zpl_iter_read_common(struct kiocb *kiocb, const struct iovec *iovp,
     unsigned long nr_segs, size_t count, uio_seg_t seg, size_t skip)
@@ -277,6 +272,7 @@ zpl_iter_read_common(struct kiocb *kiocb, const struct iovec *iovp,
 	    nr_segs, &kiocb->ki_pos, seg, filp->f_flags, cr, skip);
 	crfree(cr);
 
+	file_accessed(filp);
 	return (read);
 }
 
@@ -301,7 +297,14 @@ static ssize_t
 zpl_aio_read(struct kiocb *kiocb, const struct iovec *iovp,
     unsigned long nr_segs, loff_t pos)
 {
-	return (zpl_iter_read_common(kiocb, iovp, nr_segs, kiocb->ki_nbytes,
+	ssize_t ret;
+	size_t count;
+
+	ret = generic_segment_checks(iovp, &nr_segs, &count, VERIFY_WRITE);
+	if (ret)
+		return (ret);
+
+	return (zpl_iter_read_common(kiocb, iovp, nr_segs, count,
 	    UIO_USERSPACE, 0));
 }
 #endif /* HAVE_VFS_RW_ITERATE */
@@ -339,6 +342,7 @@ zpl_write_common_iovec(struct inode *ip, const struct iovec *iovp, size_t count,
 
 	return (wrote);
 }
+
 inline ssize_t
 zpl_write_common(struct inode *ip, const char *buf, size_t len, loff_t *ppos,
     uio_seg_t segment, int flags, cred_t *cr)
@@ -352,20 +356,6 @@ zpl_write_common(struct inode *ip, const char *buf, size_t len, loff_t *ppos,
 	    flags, cr, 0));
 }
 
-static ssize_t
-zpl_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
-{
-	cred_t *cr = CRED();
-	ssize_t wrote;
-
-	crhold(cr);
-	wrote = zpl_write_common(filp->f_mapping->host, buf, len, ppos,
-	    UIO_USERSPACE, filp->f_flags, cr);
-	crfree(cr);
-
-	return (wrote);
-}
-
 static ssize_t
 zpl_iter_write_common(struct kiocb *kiocb, const struct iovec *iovp,
     unsigned long nr_segs, size_t count, uio_seg_t seg, size_t skip)
@@ -386,16 +376,42 @@ zpl_iter_write_common(struct kiocb *kiocb, const struct iovec *iovp,
 static ssize_t
 zpl_iter_write(struct kiocb *kiocb, struct iov_iter *from)
 {
+	size_t count;
 	ssize_t ret;
 	uio_seg_t seg = UIO_USERSPACE;
+
+#ifndef HAVE_GENERIC_WRITE_CHECKS_KIOCB
+	struct file *file = kiocb->ki_filp;
+	struct address_space *mapping = file->f_mapping;
+	struct inode *ip = mapping->host;
+	int isblk = S_ISBLK(ip->i_mode);
+
+	count = iov_iter_count(from);
+	ret = generic_write_checks(file, &kiocb->ki_pos, &count, isblk);
+	if (ret)
+		return (ret);
+#else
+	/*
+	 * XXX - ideally this check should be in the same lock region with
+	 * write operations, so that there's no TOCTTOU race when doing
+	 * append and someone else grow the file.
+	 */
+	ret = generic_write_checks(kiocb, from);
+	if (ret <= 0)
+		return (ret);
+	count = ret;
+#endif
+
 	if (from->type & ITER_KVEC)
 		seg = UIO_SYSSPACE;
 	if (from->type & ITER_BVEC)
 		seg = UIO_BVEC;
+
 	ret = zpl_iter_write_common(kiocb, from->iov, from->nr_segs,
-	    iov_iter_count(from), seg, from->iov_offset);
+	    count, seg, from->iov_offset);
 	if (ret > 0)
 		iov_iter_advance(from, ret);
+
 	return (ret);
 }
 #else
@@ -403,7 +419,22 @@ static ssize_t
 zpl_aio_write(struct kiocb *kiocb, const struct iovec *iovp,
     unsigned long nr_segs, loff_t pos)
 {
-	return (zpl_iter_write_common(kiocb, iovp, nr_segs, kiocb->ki_nbytes,
+	struct file *file = kiocb->ki_filp;
+	struct address_space *mapping = file->f_mapping;
+	struct inode *ip = mapping->host;
+	int isblk = S_ISBLK(ip->i_mode);
+	size_t count;
+	ssize_t ret;
+
+	ret = generic_segment_checks(iovp, &nr_segs, &count, VERIFY_READ);
+	if (ret)
+		return (ret);
+
+	ret = generic_write_checks(file, &pos, &count, isblk);
+	if (ret)
+		return (ret);
+
+	return (zpl_iter_write_common(kiocb, iovp, nr_segs, count,
 	    UIO_USERSPACE, 0));
 }
 #endif /* HAVE_VFS_RW_ITERATE */
@@ -649,8 +680,6 @@ zpl_fallocate_common(struct inode *ip, int mode, loff_t offset, loff_t len)
 	if (mode != (FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
 		return (error);
 
-	crhold(cr);
-
 	if (offset < 0 || len <= 0)
 		return (-EINVAL);
 
@@ -669,6 +698,7 @@ zpl_fallocate_common(struct inode *ip, int mode, loff_t offset, loff_t len)
 	bf.l_len = len;
 	bf.l_pid = 0;
 
+	crhold(cr);
 	cookie = spl_fstrans_mark();
 	error = -zfs_space(ip, F_FREESP, &bf, FWRITE, offset, cr);
 	spl_fstrans_unmark(cookie);
@@ -728,8 +758,7 @@ zpl_ioctl_getflags(struct file *filp, void __user *arg)
  * is outside of our jurisdiction.
  */
 
-#define	fchange(f0, f1, b0, b1) ((((f0) & (b0)) == (b0)) != \
+#define	fchange(f0, f1, b0, b1) (!((f0) & (b0)) != !((f1) & (b1)))
-	(((b1) & (f1)) == (f1)))
 
 static int
 zpl_ioctl_setflags(struct file *filp, void __user *arg)
@@ -827,18 +856,24 @@ const struct file_operations zpl_file_operations = {
 	.open		= zpl_open,
 	.release	= zpl_release,
 	.llseek		= zpl_llseek,
-	.read		= zpl_read,
-	.write		= zpl_write,
 #ifdef HAVE_VFS_RW_ITERATE
+#ifdef HAVE_NEW_SYNC_READ
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+#endif
 	.read_iter	= zpl_iter_read,
 	.write_iter	= zpl_iter_write,
 #else
+	.read		= do_sync_read,
+	.write		= do_sync_write,
 	.aio_read	= zpl_aio_read,
 	.aio_write	= zpl_aio_write,
 #endif
 	.mmap		= zpl_mmap,
 	.fsync		= zpl_fsync,
+#ifdef HAVE_FILE_AIO_FSYNC
 	.aio_fsync	= zpl_aio_fsync,
+#endif
 #ifdef HAVE_FILE_FALLOCATE
 	.fallocate	= zpl_fallocate,
 #endif /* HAVE_FILE_FALLOCATE */

module/zfs/zpl_inode.c

@@ -50,7 +50,7 @@ zpl_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 	int zfs_flags = 0;
 	zfs_sb_t *zsb = dentry->d_sb->s_fs_info;
 
-	if (dlen(dentry) > ZFS_MAXNAMELEN)
+	if (dlen(dentry) >= ZAP_MAXNAMELEN)
 		return (ERR_PTR(-ENAMETOOLONG));
 
 	crhold(cr);
@@ -102,9 +102,13 @@ zpl_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
 		struct dentry *new_dentry;
 		struct qstr ci_name;
 
+		if (strcmp(dname(dentry), pn.pn_buf) == 0) {
+			new_dentry = d_splice_alias(ip,  dentry);
+		} else {
 			ci_name.name = pn.pn_buf;
 			ci_name.len = strlen(pn.pn_buf);
 			new_dentry = d_add_ci(dentry, ip, &ci_name);
+		}
 		kmem_free(pn.pn_buf, ZFS_MAXNAMELEN);
 		return (new_dentry);
 	} else {
@@ -298,18 +302,25 @@ zpl_rmdir(struct inode * dir, struct dentry *dentry)
 }
 
 static int
-zpl_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+zpl_getattr_impl(const struct path *path, struct kstat *stat, u32 request_mask,
+    unsigned int query_flags)
 {
 	int error;
 	fstrans_cookie_t cookie;
 
 	cookie = spl_fstrans_mark();
-	error = -zfs_getattr_fast(dentry->d_inode, stat);
+
+	/*
+	 * XXX request_mask and query_flags currently ignored.
+	 */
+
+	error = -zfs_getattr_fast(path->dentry->d_inode, stat);
 	spl_fstrans_unmark(cookie);
 	ASSERT3S(error, <=, 0);
 
 	return (error);
 }
+ZPL_GETATTR_WRAPPER(zpl_getattr);
 
 static int
 zpl_setattr(struct dentry *dentry, struct iattr *ia)
@@ -320,7 +331,7 @@ zpl_setattr(struct dentry *dentry, struct iattr *ia)
 	int error;
 	fstrans_cookie_t cookie;
 
-	error = inode_change_ok(ip, ia);
+	error = setattr_prepare(dentry, ia);
 	if (error)
 		return (error);
 
@@ -335,6 +346,9 @@ zpl_setattr(struct dentry *dentry, struct iattr *ia)
 	vap->va_mtime = ia->ia_mtime;
 	vap->va_ctime = ia->ia_ctime;
 
+	if (vap->va_mask & ATTR_ATIME)
+		ip->i_atime = ia->ia_atime;
+
 	cookie = spl_fstrans_mark();
 	error = -zfs_setattr(ip, vap, 0, cr);
 	if (!error && (ia->ia_valid & ATTR_MODE))
@@ -349,13 +363,17 @@ zpl_setattr(struct dentry *dentry, struct iattr *ia)
 }
 
 static int
-zpl_rename(struct inode *sdip, struct dentry *sdentry,
+zpl_rename2(struct inode *sdip, struct dentry *sdentry,
-    struct inode *tdip, struct dentry *tdentry)
+    struct inode *tdip, struct dentry *tdentry, unsigned int flags)
 {
 	cred_t *cr = CRED();
 	int error;
 	fstrans_cookie_t cookie;
 
+	/* We don't have renameat2(2) support */
+	if (flags)
+		return (-EINVAL);
+
 	crhold(cr);
 	cookie = spl_fstrans_mark();
 	error = -zfs_rename(sdip, dname(sdentry), tdip, dname(tdentry), cr, 0);
@@ -366,6 +384,15 @@ zpl_rename(struct inode *sdip, struct dentry *sdentry,
 	return (error);
 }
 
+#ifndef HAVE_RENAME_WANTS_FLAGS
+static int
+zpl_rename(struct inode *sdip, struct dentry *sdentry,
+    struct inode *tdip, struct dentry *tdentry)
+{
+	return (zpl_rename2(sdip, sdentry, tdip, tdentry, 0));
+}
+#endif
+
 static int
 zpl_symlink(struct inode *dir, struct dentry *dentry, const char *name)
 {
@@ -530,7 +557,7 @@ zpl_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
 		return (-EMLINK);
 
 	crhold(cr);
-	ip->i_ctime = CURRENT_TIME_SEC;
+	ip->i_ctime = current_time(ip);
 	igrab(ip); /* Use ihold() if available */
 
 	cookie = spl_fstrans_mark();
@@ -642,19 +669,13 @@ zpl_revalidate(struct dentry *dentry, unsigned int flags)
 }
 
 const struct inode_operations zpl_inode_operations = {
-	.create		= zpl_create,
-	.link		= zpl_link,
-	.unlink		= zpl_unlink,
-	.symlink	= zpl_symlink,
-	.mkdir		= zpl_mkdir,
-	.rmdir		= zpl_rmdir,
-	.mknod		= zpl_mknod,
-	.rename		= zpl_rename,
 	.setattr	= zpl_setattr,
 	.getattr	= zpl_getattr,
+#ifdef HAVE_GENERIC_SETXATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
 	.removexattr	= generic_removexattr,
+#endif
 	.listxattr	= zpl_xattr_list,
 #ifdef HAVE_INODE_TRUNCATE_RANGE
 	.truncate_range = zpl_truncate_range,
@@ -663,6 +684,9 @@ const struct inode_operations zpl_inode_operations = {
 	.fallocate	= zpl_fallocate,
 #endif /* HAVE_INODE_FALLOCATE */
 #if defined(CONFIG_FS_POSIX_ACL)
+#if defined(HAVE_SET_ACL)
+	.set_acl	= zpl_set_acl,
+#endif
 #if defined(HAVE_GET_ACL)
 	.get_acl	= zpl_get_acl,
 #elif defined(HAVE_CHECK_ACL)
@@ -682,14 +706,23 @@ const struct inode_operations zpl_dir_inode_operations = {
 	.mkdir		= zpl_mkdir,
 	.rmdir		= zpl_rmdir,
 	.mknod		= zpl_mknod,
+#ifdef HAVE_RENAME_WANTS_FLAGS
+	.rename		= zpl_rename2,
+#else
 	.rename		= zpl_rename,
+#endif
 	.setattr	= zpl_setattr,
 	.getattr	= zpl_getattr,
+#ifdef HAVE_GENERIC_SETXATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
 	.removexattr	= generic_removexattr,
+#endif
 	.listxattr	= zpl_xattr_list,
 #if defined(CONFIG_FS_POSIX_ACL)
+#if defined(HAVE_SET_ACL)
+	.set_acl	= zpl_set_acl,
+#endif
 #if defined(HAVE_GET_ACL)
 	.get_acl	= zpl_get_acl,
 #elif defined(HAVE_CHECK_ACL)
@@ -701,7 +734,9 @@ const struct inode_operations zpl_dir_inode_operations = {
 };
 
 const struct inode_operations zpl_symlink_inode_operations = {
+#ifdef HAVE_GENERIC_READLINK
 	.readlink	= generic_readlink,
+#endif
 #if defined(HAVE_GET_LINK_DELAYED) || defined(HAVE_GET_LINK_COOKIE)
 	.get_link	= zpl_get_link,
 #elif defined(HAVE_FOLLOW_LINK_COOKIE) || defined(HAVE_FOLLOW_LINK_NAMEIDATA)
@@ -712,20 +747,27 @@ const struct inode_operations zpl_symlink_inode_operations = {
 #endif
 	.setattr	= zpl_setattr,
 	.getattr	= zpl_getattr,
+#ifdef HAVE_GENERIC_SETXATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
 	.removexattr	= generic_removexattr,
+#endif
 	.listxattr	= zpl_xattr_list,
 };
 
 const struct inode_operations zpl_special_inode_operations = {
 	.setattr	= zpl_setattr,
 	.getattr	= zpl_getattr,
+#ifdef HAVE_GENERIC_SETXATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
 	.removexattr	= generic_removexattr,
+#endif
 	.listxattr	= zpl_xattr_list,
 #if defined(CONFIG_FS_POSIX_ACL)
+#if defined(HAVE_SET_ACL)
+	.set_acl	= zpl_set_acl,
+#endif
 #if defined(HAVE_GET_ACL)
 	.get_acl	= zpl_get_acl,
 #elif defined(HAVE_CHECK_ACL)

module/zfs/zpl_xattr.c

@@ -936,9 +936,8 @@ xattr_handler_t zpl_xattr_security_handler = {
  */
 #ifdef CONFIG_FS_POSIX_ACL
 int
-zpl_set_acl(struct inode *ip, int type, struct posix_acl *acl)
+zpl_set_acl(struct inode *ip, struct posix_acl *acl, int type)
 {
-	struct super_block *sb = ITOZSB(ip)->z_sb;
 	char *name, *value = NULL;
 	int error = 0;
 	size_t size = 0;
@@ -964,7 +963,7 @@ zpl_set_acl(struct inode *ip, int type, struct posix_acl *acl)
 				 */
 				if (ip->i_mode != mode) {
 					ip->i_mode = mode;
-					ip->i_ctime = current_fs_time(sb);
+					ip->i_ctime = current_time(ip);
 					zfs_mark_inode_dirty(ip);
 				}
 
@@ -1130,7 +1129,7 @@ zpl_init_acl(struct inode *ip, struct inode *dir)
 
 		if (!acl) {
 			ip->i_mode &= ~current_umask();
-			ip->i_ctime = current_fs_time(ITOZSB(ip)->z_sb);
+			ip->i_ctime = current_time(ip);
 			zfs_mark_inode_dirty(ip);
 			return (0);
 		}
@@ -1140,7 +1139,7 @@ zpl_init_acl(struct inode *ip, struct inode *dir)
 		umode_t mode;
 
 		if (S_ISDIR(ip->i_mode)) {
-			error = zpl_set_acl(ip, ACL_TYPE_DEFAULT, acl);
+			error = zpl_set_acl(ip, acl, ACL_TYPE_DEFAULT);
 			if (error)
 				goto out;
 		}
@@ -1151,7 +1150,7 @@ zpl_init_acl(struct inode *ip, struct inode *dir)
 			ip->i_mode = mode;
 			zfs_mark_inode_dirty(ip);
 			if (error > 0)
-				error = zpl_set_acl(ip, ACL_TYPE_ACCESS, acl);
+				error = zpl_set_acl(ip, acl, ACL_TYPE_ACCESS);
 		}
 	}
 out:
@@ -1178,7 +1177,7 @@ zpl_chmod_acl(struct inode *ip)
 
 	error = __posix_acl_chmod(&acl, GFP_KERNEL, ip->i_mode);
 	if (!error)
-		error = zpl_set_acl(ip, ACL_TYPE_ACCESS, acl);
+		error = zpl_set_acl(ip, acl, ACL_TYPE_ACCESS);
 
 	zpl_posix_acl_release(acl);
 
@@ -1308,7 +1307,7 @@ __zpl_xattr_acl_set_access(struct inode *ip, const char *name,
 		acl = NULL;
 	}
 
-	error = zpl_set_acl(ip, type, acl);
+	error = zpl_set_acl(ip, acl, type);
 	zpl_posix_acl_release(acl);
 
 	return (error);
@@ -1348,7 +1347,7 @@ __zpl_xattr_acl_set_default(struct inode *ip, const char *name,
 		acl = NULL;
 	}
 
-	error = zpl_set_acl(ip, type, acl);
+	error = zpl_set_acl(ip, acl, type);
 	zpl_posix_acl_release(acl);
 
 	return (error);
@@ -1441,3 +1440,103 @@ zpl_xattr_handler(const char *name)
 
 	return (NULL);
 }
+
+#if !defined(HAVE_POSIX_ACL_RELEASE) || defined(HAVE_POSIX_ACL_RELEASE_GPL_ONLY)
+struct acl_rel_struct {
+	struct acl_rel_struct *next;
+	struct posix_acl *acl;
+	clock_t time;
+};
+
+#define	ACL_REL_GRACE	(60*HZ)
+#define	ACL_REL_WINDOW	(1*HZ)
+#define	ACL_REL_SCHED	(ACL_REL_GRACE+ACL_REL_WINDOW)
+
+/*
+ * Lockless multi-producer single-consumer fifo list.
+ * Nodes are added to tail and removed from head. Tail pointer is our
+ * synchronization point. It always points to the next pointer of the last
+ * node, or head if list is empty.
+ */
+static struct acl_rel_struct *acl_rel_head = NULL;
+static struct acl_rel_struct **acl_rel_tail = &acl_rel_head;
+
+static void
+zpl_posix_acl_free(void *arg)
+{
+	struct acl_rel_struct *freelist = NULL;
+	struct acl_rel_struct *a;
+	clock_t new_time;
+	boolean_t refire = B_FALSE;
+
+	ASSERT3P(acl_rel_head, !=, NULL);
+	while (acl_rel_head) {
+		a = acl_rel_head;
+		if (ddi_get_lbolt() - a->time >= ACL_REL_GRACE) {
+			/*
+			 * If a is the last node we need to reset tail, but we
+			 * need to use cmpxchg to make sure it is still the
+			 * last node.
+			 */
+			if (acl_rel_tail == &a->next) {
+				acl_rel_head = NULL;
+				if (cmpxchg(&acl_rel_tail, &a->next,
+				    &acl_rel_head) == &a->next) {
+					ASSERT3P(a->next, ==, NULL);
+					a->next = freelist;
+					freelist = a;
+					break;
+				}
+			}
+			/*
+			 * a is not last node, make sure next pointer is set
+			 * by the adder and advance the head.
+			 */
+			while (ACCESS_ONCE(a->next) == NULL)
+				cpu_relax();
+			acl_rel_head = a->next;
+			a->next = freelist;
+			freelist = a;
+		} else {
+			/*
+			 * a is still in grace period. We are responsible to
+			 * reschedule the free task, since adder will only do
+			 * so if list is empty.
+			 */
+			new_time = a->time + ACL_REL_SCHED;
+			refire = B_TRUE;
+			break;
+		}
+	}
+
+	if (refire)
+		taskq_dispatch_delay(system_taskq, zpl_posix_acl_free, NULL,
+		    TQ_SLEEP, new_time);
+
+	while (freelist) {
+		a = freelist;
+		freelist = a->next;
+		kfree(a->acl);
+		kmem_free(a, sizeof (struct acl_rel_struct));
+	}
+}
+
+void
+zpl_posix_acl_release_impl(struct posix_acl *acl)
+{
+	struct acl_rel_struct *a, **prev;
+
+	a = kmem_alloc(sizeof (struct acl_rel_struct), KM_SLEEP);
+	a->next = NULL;
+	a->acl = acl;
+	a->time = ddi_get_lbolt();
+	/* atomically points tail to us and get the previous tail */
+	prev = xchg(&acl_rel_tail, &a->next);
+	ASSERT3P(*prev, ==, NULL);
+	*prev = a;
+	/* if it was empty before, schedule the free task */
+	if (prev == &acl_rel_head)
+		taskq_dispatch_delay(system_taskq, zpl_posix_acl_free, NULL,
+		    TQ_SLEEP, ddi_get_lbolt() + ACL_REL_SCHED);
+}
+#endif

module/zfs/zvol.c

@@ -174,7 +174,7 @@ zvol_is_zvol(const char *device)
 	struct block_device *bdev;
 	unsigned int major;
 
-	bdev = lookup_bdev(device);
+	bdev = vdev_lookup_bdev(device);
 	if (IS_ERR(bdev))
 		return (B_FALSE);
 
@@ -1615,14 +1615,12 @@ zvol_rename_minors_impl(const char *oldname, const char *newname)
 {
 	zvol_state_t *zv, *zv_next;
 	int oldnamelen, newnamelen;
-	char *name;
 
 	if (zvol_inhibit_dev)
 		return;
 
 	oldnamelen = strlen(oldname);
 	newnamelen = strlen(newname);
-	name = kmem_alloc(MAXNAMELEN, KM_SLEEP);
 
 	mutex_enter(&zvol_state_lock);
 
@@ -1638,16 +1636,15 @@ zvol_rename_minors_impl(const char *oldname, const char *newname)
 		} else if (strncmp(zv->zv_name, oldname, oldnamelen) == 0 &&
 		    (zv->zv_name[oldnamelen] == '/' ||
 		    zv->zv_name[oldnamelen] == '@')) {
-			snprintf(name, MAXNAMELEN, "%s%c%s", newname,
+			char *name = kmem_asprintf("%s%c%s", newname,
 			    zv->zv_name[oldnamelen],
 			    zv->zv_name + oldnamelen + 1);
 			zvol_rename_minor(zv, name);
+			kmem_free(name, strlen(name + 1));
 		}
 	}
 
 	mutex_exit(&zvol_state_lock);
-
-	kmem_free(name, MAXNAMELEN);
 }
 
 typedef struct zvol_snapdev_cb_arg {

rpm/generic/zfs-kmod.spec.in

@@ -186,6 +186,69 @@ chmod u+x ${RPM_BUILD_ROOT}%{kmodinstdir_prefix}/*/extra/*/*/*
 rm -rf $RPM_BUILD_ROOT
 
 %changelog
+* Mon Jul 10 2017 Tony Hutter <hutter2@llnl.gov> - 0.6.5.11-1
+- Linux 4.12 compat: super_setup_bdi_name() - add missing code zfsonlinux/zfs#6089 zfsonlinux/zfs#6324
+- Musl libc fixes zfsonlinux/zfs#6310
+- Increase zfs_vdev_async_write_min_active to 2 zfsonlinux/zfs#5926
+- Fix int overflow in zbookmark_is_before()- Fix RHEL 7.4 bio_set_op_attrs build error zfsonlinux/zfs#6234 zfsonlinux/zfs#6271
+- Fix RHEL 7.4 bio_set_op_attrs build error zfsonlinux/zfs#6253 zfsonlinux/zfs#6271
+- GCC 7.1 fixes zfsonlinux/zfs#6253
+- Remove complicated libspl assert wrappers zfsonlinux/zfs#4449
+- Compatibilty with glibc-2.23 zfsonlinux/zfs#6132
+- glibc 2.5 compat: use correct header for makedev() et al. zfsonlinux/zfs#5945
+* Mon Jun 12 2017 Tony Hutter <hutter2@llnl.gov> - 0.6.5.10-1
+- OpenZFS 8005 - poor performance of 1MB writes on certain RAID-Z configurations zfsonlinux/zfs#5931
+- Add MS_MANDLOCK mount failure message zfsonlinux/zfs#4729 zfsonlinux/zfs#6199
+- Fix import wrong spare/l2 device when path change zfsonlinux/zfs#6158
+- Fix import finding spare/l2cache when path changes zfsonlinux/zfs#6158
+- Linux 4.9 compat: fix zfs_ctldir xattr handling zfsonlinux/zfs#6189
+- Linux 4.12 compat: fix super_setup_bdi_name() call zfsonlinux/zfs#6147
+- Linux 4.12 compat: CURRENT_TIME removed zfsonlinux/zfs#6114
+- Linux 4.12 compat: super_setup_bdi_name() zfsonlinux/zfs#6089
+- Limit zfs_dirty_data_max_max to 4G zfsonlinux/zfs#6072 zfsonlinux/zfs#6081
+- OpenZFS 8166 - zpool scrub thinks it repaired offline device zfsonlinux/zfs#5806 zfsonlinux/zfs#6103
+- vdev_id: fix failure due to multipath -l bug zfsonlinux/zfs#6039
+- Guarantee PAGESIZE alignment for large zio buffers zfsonlinux/zfs#6084
+- Fix harmless "BARRIER is deprecated" kernel warning on Centos 6.8 zfsonlinux/zfs#5739 zfsonlinux/zfs#5828
+- Add kmap_atomic in dmu_bio_copy- zdb: segfault in dump_bpobj_subobjs() zfsonlinux/zfs#3905
+- Fix atomic_sub_64() i386 assembly implementation zfsonlinux/zfs#5671 zfsonlinux/zfs#5717
+- Fix loop device becomes read-only zfsonlinux/zfs#5776 zfsonlinux/zfs#5855
+- Allow ZVOL bookmarks to be listed recursively zfsonlinux/zfs#4503 zfsonlinux/zfs#5072
+- Fix zfs-mount.service failure on boot zfsonlinux/zfs#5719
+- Fix iput() calls within a tx zfsonlinux/zfs#5758
+- Fix off by one in zpl_lookup zfsonlinux/zfs#5768
+- Linux 4.11 compat: iops.getattr and friends zfsonlinux/zfs#5875
+- Linux 4.11 compat: avoid refcount_t name conflict zfsonlinux/zfs#5823 zfsonlinux/zfs#5842
+* Fri Feb 3 2017 Brian Behlendorf <behlendorf1@llnl.gov> - 0.6.5.9-1
+- Use large stacks when available zfsonlinux/zfs#4059
+- Use set_cached_acl() and forget_cached_acl() when possible zfsonlinux/zfs#5378
+- Fix batch free zpl_posix_acl_release zfsonlinux/zfs#5340 zfsonlinux/zfs#5353
+- Fix zfsctl_snapshot_{,un}mount() issues zfsonlinux/zfs#5250
+- Fix systemd services configutation through preset file zfsonlinux/zfs#5356
+- Fix RLIMIT_FSIZE enforcement zfsonlinux/zfs#5587 zfsonlinux/zfs#5673 zfsonlinux/zfs#5720 zfsonlinux/zfs#5726
+- Fix leak on zfs_sb_create() failure zfsonlinux/zfs#5490 zfsonlinux/zfs#5496
+- Fix zpl_fallocate_common() creak leak zfsonlinux/zfs#5244 zfsonlinux/zfs#5330
+- Fix fchange in zpl_ioctl_setflags() zfsonlinux/zfs#5486
+- Fix wrong operator in xvattr.h zfsonlinux/zfs#5486
+- Fix counting '@' in dataset namelen zfsonlinux/zfs#5432 zfsonlinux/zfs#5456
+- Fix dmu_object_size_from_db() call under spinlock zfsonlinux/zfs#3858
+- Fix lookup_bdev() on Ubuntu zfsonlinux/zfs#5336
+- Fix receiving custom snapshot properties zfsonlinux/zfs#5189
+- Fix bio merging w/noop scheduler zfsonlinux/zfs#5181
+- Fix sync behavior for disk vdevs zfsonlinux/zfs#4858
+- Fix uninitialized variable in avl_add() zfsonlinux/zfs#3609
+- Fix tq_lock contention by making write taskq non-dynamic zfsonlinux/zfs#5236
+- Fix atime handling (relatime, lazytime) zfsonlinux/zfs#4482
+- Linux 4.10 compat: BIO flag changes zfsonlinux/zfs#5499
+- Linux 4.9 compat: inode_change_ok() renamed setattr_prepare() zfsonlinux/zfs#5307
+- Linux 4.9 compat: remove iops->{set,get,remove}xattr zfsonlinux/zfs#5307
+- Linux 4.9 compat: iops->rename() wants flags zfsonlinux/zfs#5307
+- Linux 4.9 compat: file_operations->aio_fsync removal zfsonlinux/zfs#5393
+- Linux 4.9 compat: Remove dir inode operations from zpl_inode_operations zfsonlinux/zfs#5307
+- Linux 4.7 compat: Fix deadlock during lookup on case-insensitive zfsonlinux/zfs#5124 zfsonlinux/zfs#5141 zfsonlinux/zfs#5147 zfsonlinux/zfs#5148
+- Linux 3.14 compat: assign inode->set_acl zfsonlinux/zfs#5371 zfsonlinux/zfs#5375
+- Linux 2.6.32 compat: Reorder HAVE_BIO_RW_* checks zfsonlinux/zfs#4951 zfsonlinux/zfs#4959
+- Remove dead root pool import code zfsonlinux/zfs#4951
 * Fri Sep 9 2016 Ned Bass <bass6@llnl.gov> - 0.6.5.8-1
 - Linux 4.6, 4.7 and 4.8 compatibility zfsonlinux/spl#549 zfsonlinux/spl#563 zfsonlinux/spl#565 zfsonlinux/spl#566 zfsonlinux/zfs#4664 zfsonlinux/zfs#4665 zfsonlinux/zfs#4717 zfsonlinux/zfs#4726 zfsonlinux/zfs#4892  zfsonlinux/zfs#4899 zfsonlinux/zfs#4922  zfsonlinux/zfs#4944  zfsonlinux/zfs#4946 zfsonlinux/zfs#4951
 - Fix new tunable to ignore hole_birth, enabled by default zfsonlinux/zfs#4833

rpm/generic/zfs.spec.in

@@ -40,6 +40,7 @@
 # Generic enable switch for systemd
 %if %{with systemd}
 %define _systemd 1
+%define systemd_svcs zfs-import-cache.service zfs-import-scan.service zfs-mount.service zfs-share.service zfs-zed.service zfs.target
 %endif
 
 # RHEL >= 7 comes with systemd
@@ -240,7 +241,7 @@ find %{?buildroot}%{_libdir} -name '*.la' -exec rm -f {} \;
 
 %post
 %if 0%{?_systemd}
-%systemd_post zfs.target
+%systemd_post %{systemd_svcs}
 %else
 if [ -x /sbin/chkconfig ]; then
     /sbin/chkconfig --add zfs-import
@@ -253,7 +254,7 @@ exit 0
 
 %preun
 %if 0%{?_systemd}
-%systemd_preun zfs.target
+%systemd_preun %{systemd_svcs}
 %else
 if [ $1 -eq 0 ] && [ -x /sbin/chkconfig ]; then
     /sbin/chkconfig --del zfs-import
@@ -266,7 +267,7 @@ exit 0
 
 %postun
 %if 0%{?_systemd}
-%systemd_postun zfs.target
+%systemd_postun %{systemd_svcs}
 %endif
 
 %files
@@ -327,6 +328,69 @@ exit 0
 %endif
 
 %changelog
+* Mon Jul 10 2017 Tony Hutter <hutter2@llnl.gov> - 0.6.5.11-1
+- Linux 4.12 compat: super_setup_bdi_name() - add missing code zfsonlinux/zfs#6089 zfsonlinux/zfs#6324
+- Musl libc fixes zfsonlinux/zfs#6310
+- Increase zfs_vdev_async_write_min_active to 2 zfsonlinux/zfs#5926
+- Fix int overflow in zbookmark_is_before()- Fix RHEL 7.4 bio_set_op_attrs build error zfsonlinux/zfs#6234 zfsonlinux/zfs#6271
+- Fix RHEL 7.4 bio_set_op_attrs build error zfsonlinux/zfs#6253 zfsonlinux/zfs#6271
+- GCC 7.1 fixes zfsonlinux/zfs#6253
+- Remove complicated libspl assert wrappers zfsonlinux/zfs#4449
+- Compatibilty with glibc-2.23 zfsonlinux/zfs#6132
+- glibc 2.5 compat: use correct header for makedev() et al. zfsonlinux/zfs#5945
+* Mon Jun 12 2017 Tony Hutter <hutter2@llnl.gov> - 0.6.5.10-1
+- OpenZFS 8005 - poor performance of 1MB writes on certain RAID-Z configurations zfsonlinux/zfs#5931
+- Add MS_MANDLOCK mount failure message zfsonlinux/zfs#4729 zfsonlinux/zfs#6199
+- Fix import wrong spare/l2 device when path change zfsonlinux/zfs#6158
+- Fix import finding spare/l2cache when path changes zfsonlinux/zfs#6158
+- Linux 4.9 compat: fix zfs_ctldir xattr handling zfsonlinux/zfs#6189
+- Linux 4.12 compat: fix super_setup_bdi_name() call zfsonlinux/zfs#6147
+- Linux 4.12 compat: CURRENT_TIME removed zfsonlinux/zfs#6114
+- Linux 4.12 compat: super_setup_bdi_name() zfsonlinux/zfs#6089
+- Limit zfs_dirty_data_max_max to 4G zfsonlinux/zfs#6072 zfsonlinux/zfs#6081
+- OpenZFS 8166 - zpool scrub thinks it repaired offline device zfsonlinux/zfs#5806 zfsonlinux/zfs#6103
+- vdev_id: fix failure due to multipath -l bug zfsonlinux/zfs#6039
+- Guarantee PAGESIZE alignment for large zio buffers zfsonlinux/zfs#6084
+- Fix harmless "BARRIER is deprecated" kernel warning on Centos 6.8 zfsonlinux/zfs#5739 zfsonlinux/zfs#5828
+- Add kmap_atomic in dmu_bio_copy- zdb: segfault in dump_bpobj_subobjs() zfsonlinux/zfs#3905
+- Fix atomic_sub_64() i386 assembly implementation zfsonlinux/zfs#5671 zfsonlinux/zfs#5717
+- Fix loop device becomes read-only zfsonlinux/zfs#5776 zfsonlinux/zfs#5855
+- Allow ZVOL bookmarks to be listed recursively zfsonlinux/zfs#4503 zfsonlinux/zfs#5072
+- Fix zfs-mount.service failure on boot zfsonlinux/zfs#5719
+- Fix iput() calls within a tx zfsonlinux/zfs#5758
+- Fix off by one in zpl_lookup zfsonlinux/zfs#5768
+- Linux 4.11 compat: iops.getattr and friends zfsonlinux/zfs#5875
+- Linux 4.11 compat: avoid refcount_t name conflict zfsonlinux/zfs#5823 zfsonlinux/zfs#5842
+* Fri Feb 3 2017 Brian Behlendorf <behlendorf1@llnl.gov> - 0.6.5.9-1
+- Use large stacks when available zfsonlinux/zfs#4059
+- Use set_cached_acl() and forget_cached_acl() when possible zfsonlinux/zfs#5378
+- Fix batch free zpl_posix_acl_release zfsonlinux/zfs#5340 zfsonlinux/zfs#5353
+- Fix zfsctl_snapshot_{,un}mount() issues zfsonlinux/zfs#5250
+- Fix systemd services configutation through preset file zfsonlinux/zfs#5356
+- Fix RLIMIT_FSIZE enforcement zfsonlinux/zfs#5587 zfsonlinux/zfs#5673 zfsonlinux/zfs#5720 zfsonlinux/zfs#5726
+- Fix leak on zfs_sb_create() failure zfsonlinux/zfs#5490 zfsonlinux/zfs#5496
+- Fix zpl_fallocate_common() creak leak zfsonlinux/zfs#5244 zfsonlinux/zfs#5330
+- Fix fchange in zpl_ioctl_setflags() zfsonlinux/zfs#5486
+- Fix wrong operator in xvattr.h zfsonlinux/zfs#5486
+- Fix counting '@' in dataset namelen zfsonlinux/zfs#5432 zfsonlinux/zfs#5456
+- Fix dmu_object_size_from_db() call under spinlock zfsonlinux/zfs#3858
+- Fix lookup_bdev() on Ubuntu zfsonlinux/zfs#5336
+- Fix receiving custom snapshot properties zfsonlinux/zfs#5189
+- Fix bio merging w/noop scheduler zfsonlinux/zfs#5181
+- Fix sync behavior for disk vdevs zfsonlinux/zfs#4858
+- Fix uninitialized variable in avl_add() zfsonlinux/zfs#3609
+- Fix tq_lock contention by making write taskq non-dynamic zfsonlinux/zfs#5236
+- Fix atime handling (relatime, lazytime) zfsonlinux/zfs#4482
+- Linux 4.10 compat: BIO flag changes zfsonlinux/zfs#5499
+- Linux 4.9 compat: inode_change_ok() renamed setattr_prepare() zfsonlinux/zfs#5307
+- Linux 4.9 compat: remove iops->{set,get,remove}xattr zfsonlinux/zfs#5307
+- Linux 4.9 compat: iops->rename() wants flags zfsonlinux/zfs#5307
+- Linux 4.9 compat: file_operations->aio_fsync removal zfsonlinux/zfs#5393
+- Linux 4.9 compat: Remove dir inode operations from zpl_inode_operations zfsonlinux/zfs#5307
+- Linux 4.7 compat: Fix deadlock during lookup on case-insensitive zfsonlinux/zfs#5124 zfsonlinux/zfs#5141 zfsonlinux/zfs#5147 zfsonlinux/zfs#5148
+- Linux 3.14 compat: assign inode->set_acl zfsonlinux/zfs#5371 zfsonlinux/zfs#5375
+- Linux 2.6.32 compat: Reorder HAVE_BIO_RW_* checks zfsonlinux/zfs#4951 zfsonlinux/zfs#4959
+- Remove dead root pool import code zfsonlinux/zfs#4951
 * Fri Sep 9 2016 Ned Bass <bass6@llnl.gov> - 0.6.5.8-1
 - Linux 4.6, 4.7 and 4.8 compatibility zfsonlinux/spl#549 zfsonlinux/spl#563 zfsonlinux/spl#565 zfsonlinux/spl#566 zfsonlinux/zfs#4664 zfsonlinux/zfs#4665 zfsonlinux/zfs#4717 zfsonlinux/zfs#4726 zfsonlinux/zfs#4892  zfsonlinux/zfs#4899 zfsonlinux/zfs#4922  zfsonlinux/zfs#4944  zfsonlinux/zfs#4946 zfsonlinux/zfs#4951
 - Fix new tunable to ignore hole_birth, enabled by default zfsonlinux/zfs#4833