Direct IO support

config/kernel-vfs-direct_IO.m4

@@ -0,0 +1,130 @@
+dnl #
+dnl # Linux 4.6.x API change
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_VFS_DIRECT_IO_ITER], [
+	AC_MSG_CHECKING([whether aops->direct_IO() uses iov_iter])
+	ZFS_LINUX_TRY_COMPILE([
+		#include <linux/fs.h>
+
+		ssize_t test_direct_IO(struct kiocb *kiocb,
+		    struct iov_iter *iter) { return 0; }
+
+		static const struct address_space_operations
+		    aops __attribute__ ((unused)) = {
+			.direct_IO = test_direct_IO,
+		};
+	],[
+	],[
+		AC_MSG_RESULT([yes])
+		AC_DEFINE(HAVE_VFS_DIRECT_IO_ITER, 1,
+		    [aops->direct_IO() uses iov_iter without rw])
+		zfs_ac_direct_io="yes"
+	],[
+		AC_MSG_RESULT([no])
+	])
+])
+
+dnl #
+dnl # Linux 4.1.x API change
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_VFS_DIRECT_IO_ITER_OFFSET], [
+	AC_MSG_CHECKING(
+	    [whether aops->direct_IO() uses iov_iter with offset])
+	ZFS_LINUX_TRY_COMPILE([
+		#include <linux/fs.h>
+
+		ssize_t test_direct_IO(struct kiocb *kiocb,
+		    struct iov_iter *iter, loff_t offset) { return 0; }
+
+		static const struct address_space_operations
+		    aops __attribute__ ((unused)) = {
+			.direct_IO = test_direct_IO,
+		};
+	],[
+	],[
+		AC_MSG_RESULT([yes])
+		AC_DEFINE(HAVE_VFS_DIRECT_IO_ITER_OFFSET, 1,
+		    [aops->direct_IO() uses iov_iter with offset])
+		zfs_ac_direct_io="yes"
+	],[
+		AC_MSG_RESULT([no])
+	])
+])
+
+dnl #
+dnl # Linux 3.16.x API change
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_VFS_DIRECT_IO_ITER_RW_OFFSET], [
+	AC_MSG_CHECKING(
+	    [whether aops->direct_IO() uses iov_iter with rw and offset])
+	ZFS_LINUX_TRY_COMPILE([
+		#include <linux/fs.h>
+
+		ssize_t test_direct_IO(int rw, struct kiocb *kiocb,
+		    struct iov_iter *iter, loff_t offset) { return 0; }
+
+		static const struct address_space_operations
+		    aops __attribute__ ((unused)) = {
+		    .direct_IO = test_direct_IO,
+		};
+	],[
+	],[
+		AC_MSG_RESULT([yes])
+		AC_DEFINE(HAVE_VFS_DIRECT_IO_ITER_RW_OFFSET, 1,
+		    [aops->direct_IO() uses iov_iter with rw and offset])
+		zfs_ac_direct_io="yes"
+	],[
+		AC_MSG_RESULT([no])
+	])
+])
+
+dnl #
+dnl # Ancient Linux API (predates git)
+dnl #
+AC_DEFUN([ZFS_AC_KERNEL_VFS_DIRECT_IO_IOVEC], [
+	AC_MSG_CHECKING([whether aops->direct_IO() uses iovec])
+	ZFS_LINUX_TRY_COMPILE([
+		#include <linux/fs.h>
+
+		ssize_t test_direct_IO(int rw, struct kiocb *kiocb,
+		    const struct iovec *iov, loff_t offset,
+		    unsigned long nr_segs) { return 0; }
+
+		static const struct address_space_operations
+		    aops __attribute__ ((unused)) = {
+		    .direct_IO = test_direct_IO,
+		};
+	],[
+	],[
+		AC_MSG_RESULT([yes])
+		AC_DEFINE(HAVE_VFS_DIRECT_IO_IOVEC, 1,
+		    [aops->direct_IO() uses iovec])
+		zfs_ac_direct_io="yes"
+	],[
+		AC_MSG_RESULT([no])
+	])
+])
+
+AC_DEFUN([ZFS_AC_KERNEL_VFS_DIRECT_IO], [
+	zfs_ac_direct_io="no"
+
+	if test "$zfs_ac_direct_io" = "no"; then
+		ZFS_AC_KERNEL_VFS_DIRECT_IO_ITER
+	fi
+
+	if test "$zfs_ac_direct_io" = "no"; then
+		ZFS_AC_KERNEL_VFS_DIRECT_IO_ITER_OFFSET
+	fi
+
+	if test "$zfs_ac_direct_io" = "no"; then
+		ZFS_AC_KERNEL_VFS_DIRECT_IO_ITER_RW_OFFSET
+	fi
+
+	if test "$zfs_ac_direct_io" = "no"; then
+		ZFS_AC_KERNEL_VFS_DIRECT_IO_IOVEC
+	fi
+
+	if test "$zfs_ac_direct_io" = "no"; then
+		AC_MSG_ERROR([no; unknown direct IO interface])
+	fi
+])

config/kernel.m4

@@ -144,6 +144,7 @@ AC_DEFUN([ZFS_AC_CONFIG_KERNEL], [
 	ZFS_AC_KERNEL_LSEEK_EXECUTE
 	ZFS_AC_KERNEL_VFS_ITERATE
 	ZFS_AC_KERNEL_VFS_RW_ITERATE
+	ZFS_AC_KERNEL_VFS_DIRECT_IO
 	ZFS_AC_KERNEL_GENERIC_WRITE_CHECKS
 	ZFS_AC_KERNEL_KMAP_ATOMIC_ARGS
 	ZFS_AC_KERNEL_FOLLOW_DOWN_ONE

configure.ac

@@ -280,6 +280,7 @@ AC_CONFIG_FILES([
 	tests/zfs-tests/tests/functional/hkdf/Makefile
 	tests/zfs-tests/tests/functional/inheritance/Makefile
 	tests/zfs-tests/tests/functional/inuse/Makefile
+	tests/zfs-tests/tests/functional/io/Makefile
 	tests/zfs-tests/tests/functional/kstat/Makefile
 	tests/zfs-tests/tests/functional/large_files/Makefile
 	tests/zfs-tests/tests/functional/largest_pool/Makefile

module/zfs/zpl_file.c

@@ -438,6 +438,57 @@ zpl_aio_write(struct kiocb *kiocb, const struct iovec *iovp,
 }
 #endif /* HAVE_VFS_RW_ITERATE */
 
+#if defined(HAVE_VFS_RW_ITERATE)
+static ssize_t
+zpl_direct_IO_impl(int rw, struct kiocb *kiocb, struct iov_iter *iter)
+{
+	if (rw == WRITE)
+		return (zpl_iter_write(kiocb, iter));
+	else
+		return (zpl_iter_read(kiocb, iter));
+}
+#if defined(HAVE_VFS_DIRECT_IO_ITER)
+static ssize_t
+zpl_direct_IO(struct kiocb *kiocb, struct iov_iter *iter)
+{
+	return (zpl_direct_IO_impl(iov_iter_rw(iter), kiocb, iter));
+}
+#elif defined(HAVE_VFS_DIRECT_IO_ITER_OFFSET)
+static ssize_t
+zpl_direct_IO(struct kiocb *kiocb, struct iov_iter *iter, loff_t pos)
+{
+	ASSERT3S(pos, ==, kiocb->ki_pos);
+	return (zpl_direct_IO_impl(iov_iter_rw(iter), kiocb, iter));
+}
+#elif defined(HAVE_VFS_DIRECT_IO_ITER_RW_OFFSET)
+static ssize_t
+zpl_direct_IO(int rw, struct kiocb *kiocb, struct iov_iter *iter, loff_t pos)
+{
+	ASSERT3S(pos, ==, kiocb->ki_pos);
+	return (zpl_direct_IO_impl(rw, kiocb, iter));
+}
+#else
+#error "Unknown direct IO interface"
+#endif
+
+#else
+
+#if defined(HAVE_VFS_DIRECT_IO_IOVEC)
+static ssize_t
+zpl_direct_IO(int rw, struct kiocb *kiocb, const struct iovec *iovp,
+    loff_t pos, unsigned long nr_segs)
+{
+	if (rw == WRITE)
+		return (zpl_aio_write(kiocb, iovp, nr_segs, pos));
+	else
+		return (zpl_aio_read(kiocb, iovp, nr_segs, pos));
+}
+#else
+#error "Unknown direct IO interface"
+#endif
+
+#endif /* HAVE_VFS_RW_ITERATE */
+
 static loff_t
 zpl_llseek(struct file *filp, loff_t offset, int whence)
 {
@@ -929,6 +980,7 @@ const struct address_space_operations zpl_address_space_operations = {
 	.readpage	= zpl_readpage,
 	.writepage	= zpl_writepage,
 	.writepages	= zpl_writepages,
+	.direct_IO	= zpl_direct_IO,
 };
 
 const struct file_operations zpl_file_operations = {

scripts/commitcheck.sh

@@ -16,10 +16,11 @@ function test_url()
 }
 
 # test commit body for length
+# lines containing urls are exempt for the length limit.
 function test_commit_bodylength()
 {
     length="72"
-    body=$(git log -n 1 --pretty=%b "$REF" | grep -E -m 1 ".{$((length + 1))}")
+    body=$(git log -n 1 --pretty=%b "$REF" | grep -Ev "http(s)*://" | grep -E -m 1 ".{$((length + 1))}")
     if [ -n "$body" ]; then
         echo "error: commit message body contains line over ${length} characters"
         return 1

tests/runfiles/linux.run

@@ -558,6 +558,10 @@ tests = ['inherit_001_pos']
 pre =
 tags = ['functional', 'inheritance']
 
+[tests/functional/io]
+tests = ['sync', 'psync', 'libaio', 'posixaio', 'mmap']
+tags = ['functional', 'io']
+
 [tests/functional/inuse]
 tests = ['inuse_001_pos', 'inuse_003_pos', 'inuse_004_pos',
     'inuse_005_pos', 'inuse_006_pos', 'inuse_007_pos', 'inuse_008_pos',

tests/test-runner/bin/zts-report.py

@@ -120,6 +120,12 @@
 #
 enospc_reason = 'Exact free space reporting is not guaranteed'
 
+#
+# Some tests require a minimum version of the fio benchmark utility.
+# Older distributions such as CentOS 6.x only provide fio-2.0.13.
+#
+fio_reason = 'Fio v2.3 or newer required'
+
 #
 # Some tests are not applicable to Linux or need to be updated to operate
 # in the manor required by Linux.  Any tests which are skipped for this
@@ -246,6 +252,7 @@
     'inuse/inuse_005_pos': ['SKIP', disk_reason],
     'inuse/inuse_008_pos': ['SKIP', disk_reason],
     'inuse/inuse_009_pos': ['SKIP', disk_reason],
+    'io/mmap': ['SKIP', fio_reason],
     'largest_pool/largest_pool_001_pos': ['FAIL', known_reason],
     'pyzfs/pyzfs_unittest': ['SKIP', python_deps_reason],
     'no_space/enospc_002_pos': ['FAIL', enospc_reason],

tests/zfs-tests/include/libtest.shlib

@@ -41,6 +41,20 @@ if [ -n "$STF_PATH" ]; then
 	PATH="$STF_PATH"
 fi
 
+#
+# Generic dot version comparison function
+#
+# Returns success when version $1 is greater than or equal to $2.
+#
+function compare_version_gte
+{
+	if [[ "$(printf "$1\n$2" | sort -V | tail -n1)" == "$1" ]]; then
+		return 0
+	else
+		return 1
+	fi
+}
+
 # Linux kernel version comparison function
 #
 # $1 Linux version ("4.10", "2.6.32") or blank for installed Linux version

tests/zfs-tests/tests/functional/Makefile.am

@@ -27,6 +27,7 @@ SUBDIRS = \
 	hkdf \
 	inheritance \
 	inuse \
+	io \
 	kstat \
 	large_files \
 	largest_pool \

tests/zfs-tests/tests/functional/io/Makefile.am

@@ -0,0 +1,12 @@
+pkgdatadir = $(datadir)/@PACKAGE@/zfs-tests/tests/functional/io
+dist_pkgdata_SCRIPTS = \
+	setup.ksh \
+	cleanup.ksh \
+	sync.ksh \
+	psync.ksh \
+	libaio.ksh \
+	posixaio.ksh \
+	mmap.ksh
+
+dist_pkgdata_DATA = \
+	io.cfg

tests/zfs-tests/tests/functional/io/cleanup.ksh

@@ -0,0 +1,31 @@
+#!/bin/ksh -p
+#
+# CDDL HEADER START
+#
+# The contents of this file are subject to the terms of the
+# Common Development and Distribution License (the "License").
+# You may not use this file except in compliance with the License.
+#
+# You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
+# or http://www.opensolaris.org/os/licensing.
+# See the License for the specific language governing permissions
+# and limitations under the License.
+#
+# When distributing Covered Code, include this CDDL HEADER in each
+# file and include the License file at usr/src/OPENSOLARIS.LICENSE.
+# If applicable, add the following below this CDDL HEADER, with the
+# fields enclosed by brackets "[]" replaced with your own identifying
+# information: Portions Copyright [yyyy] [name of copyright owner]
+#
+# CDDL HEADER END
+#
+
+#
+# Copyright (c) 2018 by Lawrence Livermore National Security, LLC.
+#
+
+. $STF_SUITE/include/libtest.shlib
+
+verify_runnable "global"
+
+default_cleanup

tests/zfs-tests/tests/functional/io/io.cfg

@@ -0,0 +1,25 @@
+#
+# CDDL HEADER START
+#
+# This file and its contents are supplied under the terms of the
+# Common Development and Distribution License ("CDDL"), version 1.0.
+# You may only use this file in accordance with the terms of version
+# 1.0 of the CDDL.
+#
+# A full copy of the text of the CDDL should have accompanied this
+# source.  A copy of the CDDL is also available via the Internet at
+# http://www.illumos.org/license/CDDL.
+#
+# CDDL HEADER END
+#
+
+#
+# Copyright (c) 2018 by Lawrence Livermore National Security, LLC.
+#
+
+FIO_COMMON_ARGS="--numjobs=1 --bs=32k --size=32M --fallocate=none --group_reporting --verify=sha1 --minimal"
+
+FIO_READ_ARGS="--name=rw --rw=read $FIO_COMMON_ARGS"
+FIO_WRITE_ARGS="--name=rw --rw=write $FIO_COMMON_ARGS"
+FIO_RANDREAD_ARGS="--name=rw --rw=randread $FIO_COMMON_ARGS"
+FIO_RANDWRITE_ARGS="--name=rw --rw=randwrite $FIO_COMMON_ARGS"