OpenZFS restructuring - move platform specific headers

Move platform specific Linux headers under include/os/linux/.
Update the build system accordingly to detect the platform.
This lays some of the initial groundwork to supporting building
for other platforms.

As part of this change it was necessary to create both a user
and kernel space sys/simd.h header which can be included in
either context.  No functional change, the source has been
refactored and the relevant #include's updated.

Reviewed-by: Jorgen Lundman <lundman@lundman.net>
Reviewed-by: Igor Kozhukhov <igor@dilos.org>
Signed-off-by: Matthew Macy <mmacy@FreeBSD.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #9198

include/os/linux/kernel/Makefile.am

@@ -0,0 +1 @@
+SUBDIRS = linux

include/os/linux/kernel/linux/Makefile.am

@@ -0,0 +1,29 @@
+COMMON_H =
+
+KERNEL_H = \
+	$(top_srcdir)/include/os/linux/kernel/linux/dcache_compat.h \
+	$(top_srcdir)/include/os/linux/kernel/linux/xattr_compat.h \
+	$(top_srcdir)/include/os/linux/kernel/linux/vfs_compat.h \
+	$(top_srcdir)/include/os/linux/kernel/linux/blkdev_compat.h \
+	$(top_srcdir)/include/os/linux/kernel/linux/utsname_compat.h \
+	$(top_srcdir)/include/os/linux/kernel/linux/kmap_compat.h \
+	$(top_srcdir)/include/os/linux/kernel/linux/simd.h \
+	$(top_srcdir)/include/os/linux/kernel/linux/simd_x86.h \
+	$(top_srcdir)/include/os/linux/kernel/linux/simd_aarch64.h \
+	$(top_srcdir)/include/os/linux/kernel/linux/mod_compat.h \
+	$(top_srcdir)/include/os/linux/kernel/linux/page_compat.h \
+	$(top_srcdir)/include/os/linux/kernel/linux/compiler_compat.h
+
+USER_H =
+
+EXTRA_DIST = $(COMMON_H) $(KERNEL_H) $(USER_H)
+
+if CONFIG_USER
+libzfsdir = $(includedir)/libzfs/linux
+libzfs_HEADERS = $(COMMON_H) $(USER_H)
+endif
+
+if CONFIG_KERNEL
+kerneldir = @prefix@/src/zfs-$(VERSION)/include/linux
+kernel_HEADERS = $(COMMON_H) $(KERNEL_H)
+endif

include/os/linux/kernel/linux/blkdev_compat.h

@@ -0,0 +1,680 @@
+/*
+ * 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) 2011 Lawrence Livermore National Security, LLC.
+ * Produced at Lawrence Livermore National Laboratory (cf, DISCLAIMER).
+ * Written by Brian Behlendorf <behlendorf1@llnl.gov>.
+ * LLNL-CODE-403049.
+ */
+
+#ifndef _ZFS_BLKDEV_H
+#define	_ZFS_BLKDEV_H
+
+#include <linux/blkdev.h>
+#include <linux/elevator.h>
+#include <linux/backing-dev.h>
+#include <linux/hdreg.h>
+#include <linux/msdos_fs.h>	/* for SECTOR_* */
+
+#ifndef HAVE_FMODE_T
+typedef unsigned __bitwise__ fmode_t;
+#endif /* HAVE_FMODE_T */
+
+#ifndef HAVE_BLK_QUEUE_FLAG_SET
+static inline void
+blk_queue_flag_set(unsigned int flag, struct request_queue *q)
+{
+	queue_flag_set(flag, q);
+}
+#endif
+
+#ifndef HAVE_BLK_QUEUE_FLAG_CLEAR
+static inline void
+blk_queue_flag_clear(unsigned int flag, struct request_queue *q)
+{
+	queue_flag_clear(flag, q);
+}
+#endif
+
+/*
+ * 4.7 - 4.x API,
+ * The blk_queue_write_cache() interface has replaced blk_queue_flush()
+ * interface.  However, the new interface is GPL-only thus we implement
+ * our own trivial wrapper when the GPL-only version is detected.
+ *
+ * 2.6.36 - 4.6 API,
+ * The blk_queue_flush() interface has replaced blk_queue_ordered()
+ * interface.  However, while the old interface was available to all the
+ * new one is GPL-only.   Thus if the GPL-only version is detected we
+ * implement our own trivial helper.
+ *
+ * 2.6.x - 2.6.35
+ * Legacy blk_queue_ordered() interface.
+ */
+static inline void
+blk_queue_set_write_cache(struct request_queue *q, bool wc, bool fua)
+{
+#if defined(HAVE_BLK_QUEUE_WRITE_CACHE_GPL_ONLY)
+	if (wc)
+		blk_queue_flag_set(QUEUE_FLAG_WC, q);
+	else
+		blk_queue_flag_clear(QUEUE_FLAG_WC, q);
+	if (fua)
+		blk_queue_flag_set(QUEUE_FLAG_FUA, q);
+	else
+		blk_queue_flag_clear(QUEUE_FLAG_FUA, q);
+#elif defined(HAVE_BLK_QUEUE_WRITE_CACHE)
+	blk_queue_write_cache(q, wc, fua);
+#elif defined(HAVE_BLK_QUEUE_FLUSH_GPL_ONLY)
+	if (wc)
+		q->flush_flags |= REQ_FLUSH;
+	if (fua)
+		q->flush_flags |= REQ_FUA;
+#elif defined(HAVE_BLK_QUEUE_FLUSH)
+	blk_queue_flush(q, (wc ? REQ_FLUSH : 0) | (fua ? REQ_FUA : 0));
+#else
+	blk_queue_ordered(q, QUEUE_ORDERED_DRAIN, NULL);
+#endif
+}
+
+/*
+ * Most of the blk_* macros were removed in 2.6.36.  Ostensibly this was
+ * done to improve readability and allow easier grepping.  However, from
+ * a portability stand point the macros are helpful.  Therefore the needed
+ * macros are redefined here if they are missing from the kernel.
+ */
+#ifndef blk_fs_request
+#define	blk_fs_request(rq)	((rq)->cmd_type == REQ_TYPE_FS)
+#endif
+
+/*
+ * 2.6.34 API change,
+ * The blk_queue_max_hw_sectors() function replaces blk_queue_max_sectors().
+ */
+#ifndef HAVE_BLK_QUEUE_MAX_HW_SECTORS
+#define	blk_queue_max_hw_sectors __blk_queue_max_hw_sectors
+static inline void
+__blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors)
+{
+	blk_queue_max_sectors(q, max_hw_sectors);
+}
+#endif
+
+/*
+ * 2.6.34 API change,
+ * The blk_queue_max_segments() function consolidates
+ * blk_queue_max_hw_segments() and blk_queue_max_phys_segments().
+ */
+#ifndef HAVE_BLK_QUEUE_MAX_SEGMENTS
+#define	blk_queue_max_segments __blk_queue_max_segments
+static inline void
+__blk_queue_max_segments(struct request_queue *q, unsigned short max_segments)
+{
+	blk_queue_max_phys_segments(q, max_segments);
+	blk_queue_max_hw_segments(q, max_segments);
+}
+#endif
+
+static inline void
+blk_queue_set_read_ahead(struct request_queue *q, unsigned long ra_pages)
+{
+#ifdef HAVE_BLK_QUEUE_BDI_DYNAMIC
+	q->backing_dev_info->ra_pages = ra_pages;
+#else
+	q->backing_dev_info.ra_pages = ra_pages;
+#endif
+}
+
+#ifndef HAVE_GET_DISK_AND_MODULE
+static inline struct kobject *
+get_disk_and_module(struct gendisk *disk)
+{
+	return (get_disk(disk));
+}
+#endif
+
+#ifndef HAVE_GET_DISK_RO
+static inline int
+get_disk_ro(struct gendisk *disk)
+{
+	int policy = 0;
+
+	if (disk->part[0])
+		policy = disk->part[0]->policy;
+
+	return (policy);
+}
+#endif /* HAVE_GET_DISK_RO */
+
+#ifdef HAVE_BIO_BVEC_ITER
+#define	BIO_BI_SECTOR(bio)	(bio)->bi_iter.bi_sector
+#define	BIO_BI_SIZE(bio)	(bio)->bi_iter.bi_size
+#define	BIO_BI_IDX(bio)		(bio)->bi_iter.bi_idx
+#define	BIO_BI_SKIP(bio)	(bio)->bi_iter.bi_bvec_done
+#define	bio_for_each_segment4(bv, bvp, b, i)	\
+	bio_for_each_segment((bv), (b), (i))
+typedef struct bvec_iter bvec_iterator_t;
+#else
+#define	BIO_BI_SECTOR(bio)	(bio)->bi_sector
+#define	BIO_BI_SIZE(bio)	(bio)->bi_size
+#define	BIO_BI_IDX(bio)		(bio)->bi_idx
+#define	BIO_BI_SKIP(bio)	(0)
+#define	bio_for_each_segment4(bv, bvp, b, i)	\
+	bio_for_each_segment((bvp), (b), (i))
+typedef int bvec_iterator_t;
+#endif
+
+/*
+ * Portable helper for correctly setting the FAILFAST flags.  The
+ * correct usage has changed 3 times from 2.6.12 to 2.6.38.
+ */
+static inline void
+bio_set_flags_failfast(struct block_device *bdev, int *flags)
+{
+#ifdef CONFIG_BUG
+	/*
+	 * Disable FAILFAST for loopback devices because of the
+	 * following incorrect BUG_ON() in loop_make_request().
+	 * This support is also disabled for md devices because the
+	 * test suite layers md devices on top of loopback devices.
+	 * This may be removed when the loopback driver is fixed.
+	 *
+	 *   BUG_ON(!lo || (rw != READ && rw != WRITE));
+	 */
+	if ((MAJOR(bdev->bd_dev) == LOOP_MAJOR) ||
+	    (MAJOR(bdev->bd_dev) == MD_MAJOR))
+		return;
+
+#ifdef BLOCK_EXT_MAJOR
+	if (MAJOR(bdev->bd_dev) == BLOCK_EXT_MAJOR)
+		return;
+#endif /* BLOCK_EXT_MAJOR */
+#endif /* CONFIG_BUG */
+
+#if defined(HAVE_BIO_RW_FAILFAST_DTD)
+	/* BIO_RW_FAILFAST_* preferred interface from 2.6.28 - 2.6.35 */
+	*flags |= (
+	    (1 << BIO_RW_FAILFAST_DEV) |
+	    (1 << BIO_RW_FAILFAST_TRANSPORT) |
+	    (1 << BIO_RW_FAILFAST_DRIVER));
+#elif defined(HAVE_REQ_FAILFAST_MASK)
+	/*
+	 * REQ_FAILFAST_* preferred interface from 2.6.36 - 2.6.xx,
+	 * the BIO_* and REQ_* flags were unified under REQ_* flags.
+	 */
+	*flags |= REQ_FAILFAST_MASK;
+#else
+#error "Undefined block IO FAILFAST interface."
+#endif
+}
+
+/*
+ * Maximum disk label length, it may be undefined for some kernels.
+ */
+#ifndef DISK_NAME_LEN
+#define	DISK_NAME_LEN	32
+#endif /* DISK_NAME_LEN */
+
+#ifdef HAVE_BIO_BI_STATUS
+static inline int
+bi_status_to_errno(blk_status_t status)
+{
+	switch (status)	{
+	case BLK_STS_OK:
+		return (0);
+	case BLK_STS_NOTSUPP:
+		return (EOPNOTSUPP);
+	case BLK_STS_TIMEOUT:
+		return (ETIMEDOUT);
+	case BLK_STS_NOSPC:
+		return (ENOSPC);
+	case BLK_STS_TRANSPORT:
+		return (ENOLINK);
+	case BLK_STS_TARGET:
+		return (EREMOTEIO);
+	case BLK_STS_NEXUS:
+		return (EBADE);
+	case BLK_STS_MEDIUM:
+		return (ENODATA);
+	case BLK_STS_PROTECTION:
+		return (EILSEQ);
+	case BLK_STS_RESOURCE:
+		return (ENOMEM);
+	case BLK_STS_AGAIN:
+		return (EAGAIN);
+	case BLK_STS_IOERR:
+		return (EIO);
+	default:
+		return (EIO);
+	}
+}
+
+static inline blk_status_t
+errno_to_bi_status(int error)
+{
+	switch (error) {
+	case 0:
+		return (BLK_STS_OK);
+	case EOPNOTSUPP:
+		return (BLK_STS_NOTSUPP);
+	case ETIMEDOUT:
+		return (BLK_STS_TIMEOUT);
+	case ENOSPC:
+		return (BLK_STS_NOSPC);
+	case ENOLINK:
+		return (BLK_STS_TRANSPORT);
+	case EREMOTEIO:
+		return (BLK_STS_TARGET);
+	case EBADE:
+		return (BLK_STS_NEXUS);
+	case ENODATA:
+		return (BLK_STS_MEDIUM);
+	case EILSEQ:
+		return (BLK_STS_PROTECTION);
+	case ENOMEM:
+		return (BLK_STS_RESOURCE);
+	case EAGAIN:
+		return (BLK_STS_AGAIN);
+	case EIO:
+		return (BLK_STS_IOERR);
+	default:
+		return (BLK_STS_IOERR);
+	}
+}
+#endif /* HAVE_BIO_BI_STATUS */
+
+/*
+ * 4.3 API change
+ * The bio_endio() prototype changed slightly.  These are helper
+ * macro's to ensure the prototype and invocation are handled.
+ */
+#ifdef HAVE_1ARG_BIO_END_IO_T
+#ifdef HAVE_BIO_BI_STATUS
+#define	BIO_END_IO_ERROR(bio)		bi_status_to_errno(bio->bi_status)
+#define	BIO_END_IO_PROTO(fn, x, z)	static void fn(struct bio *x)
+#define	BIO_END_IO(bio, error)		bio_set_bi_status(bio, error)
+static inline void
+bio_set_bi_status(struct bio *bio, int error)
+{
+	ASSERT3S(error, <=, 0);
+	bio->bi_status = errno_to_bi_status(-error);
+	bio_endio(bio);
+}
+#else
+#define	BIO_END_IO_ERROR(bio)		(-(bio->bi_error))
+#define	BIO_END_IO_PROTO(fn, x, z)	static void fn(struct bio *x)
+#define	BIO_END_IO(bio, error)		bio_set_bi_error(bio, error)
+static inline void
+bio_set_bi_error(struct bio *bio, int error)
+{
+	ASSERT3S(error, <=, 0);
+	bio->bi_error = error;
+	bio_endio(bio);
+}
+#endif /* HAVE_BIO_BI_STATUS */
+
+#else
+#define	BIO_END_IO_PROTO(fn, x, z)	static void fn(struct bio *x, int z)
+#define	BIO_END_IO(bio, error)		bio_endio(bio, error);
+#endif /* HAVE_1ARG_BIO_END_IO_T */
+
+/*
+ * 2.6.38 - 2.6.x API,
+ *   blkdev_get_by_path()
+ *   blkdev_put()
+ *
+ * 2.6.28 - 2.6.37 API,
+ *   open_bdev_exclusive()
+ *   close_bdev_exclusive()
+ *
+ * 2.6.12 - 2.6.27 API,
+ *   open_bdev_excl()
+ *   close_bdev_excl()
+ *
+ * Used to exclusively open a block device from within the kernel.
+ */
+#if defined(HAVE_BLKDEV_GET_BY_PATH)
+#define	vdev_bdev_open(path, md, hld)	blkdev_get_by_path(path, \
+					    (md) | FMODE_EXCL, hld)
+#define	vdev_bdev_close(bdev, md)	blkdev_put(bdev, (md) | FMODE_EXCL)
+#elif defined(HAVE_OPEN_BDEV_EXCLUSIVE)
+#define	vdev_bdev_open(path, md, hld)	open_bdev_exclusive(path, md, hld)
+#define	vdev_bdev_close(bdev, md)	close_bdev_exclusive(bdev, md)
+#else
+#define	vdev_bdev_open(path, md, hld)	open_bdev_excl(path, md, hld)
+#define	vdev_bdev_close(bdev, md)	close_bdev_excl(bdev)
+#endif /* HAVE_BLKDEV_GET_BY_PATH | HAVE_OPEN_BDEV_EXCLUSIVE */
+
+/*
+ * 4.1 - x.y.z API,
+ * 3.10.0 CentOS 7.x API,
+ *   blkdev_reread_part()
+ *
+ * For older kernels trigger a re-reading of the partition table by calling
+ * check_disk_change() which calls flush_disk() to invalidate the device.
+ */
+#ifdef HAVE_BLKDEV_REREAD_PART
+#define	vdev_bdev_reread_part(bdev)	blkdev_reread_part(bdev)
+#else
+#define	vdev_bdev_reread_part(bdev)	check_disk_change(bdev)
+#endif /* HAVE_BLKDEV_REREAD_PART */
+
+/*
+ * 2.6.22 API change
+ * The function invalidate_bdev() lost it's second argument because
+ * it was unused.
+ */
+#ifdef HAVE_1ARG_INVALIDATE_BDEV
+#define	vdev_bdev_invalidate(bdev)	invalidate_bdev(bdev)
+#else
+#define	vdev_bdev_invalidate(bdev)	invalidate_bdev(bdev, 1)
+#endif /* HAVE_1ARG_INVALIDATE_BDEV */
+
+/*
+ * 2.6.27 API change
+ * 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.
+ */
+#ifdef HAVE_1ARG_LOOKUP_BDEV
+#define	vdev_lookup_bdev(path)	lookup_bdev(path)
+#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
+ * To ensure good performance preferentially use the physical block size
+ * for proper alignment.  The physical size is supposed to be the internal
+ * sector size used by the device.  This is often 4096 byte for AF devices,
+ * while a smaller 512 byte logical size is supported for compatibility.
+ *
+ * Unfortunately, many drives still misreport their physical sector size.
+ * For devices which are known to lie you may need to manually set this
+ * at pool creation time with 'zpool create -o ashift=12 ...'.
+ *
+ * When the physical block size interface isn't available, we fall back to
+ * the logical block size interface and then the older hard sector size.
+ */
+#ifdef HAVE_BDEV_PHYSICAL_BLOCK_SIZE
+#define	vdev_bdev_block_size(bdev)	bdev_physical_block_size(bdev)
+#else
+#ifdef HAVE_BDEV_LOGICAL_BLOCK_SIZE
+#define	vdev_bdev_block_size(bdev)	bdev_logical_block_size(bdev)
+#else
+#define	vdev_bdev_block_size(bdev)	bdev_hardsect_size(bdev)
+#endif /* HAVE_BDEV_LOGICAL_BLOCK_SIZE */
+#endif /* HAVE_BDEV_PHYSICAL_BLOCK_SIZE */
+
+#ifndef HAVE_BIO_SET_OP_ATTRS
+/*
+ * Kernels without bio_set_op_attrs use bi_rw for the bio flags.
+ */
+static inline void
+bio_set_op_attrs(struct bio *bio, unsigned rw, unsigned flags)
+{
+	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."
+#endif
+}
+
+/*
+ * 4.8 - 4.x API,
+ *   REQ_OP_FLUSH
+ *
+ * 4.8-rc0 - 4.8-rc1,
+ *   REQ_PREFLUSH
+ *
+ * 2.6.36 - 4.7 API,
+ *   REQ_FLUSH
+ *
+ * 2.6.x - 2.6.35 API,
+ *   HAVE_BIO_RW_BARRIER
+ *
+ * Used to determine if a cache flush has been requested.  This check has
+ * been left intentionally broad in order to cover both a legacy flush
+ * 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)
+{
+#if defined(HAVE_REQ_OP_FLUSH) && defined(HAVE_BIO_BI_OPF)
+	return ((bio_op(bio) == REQ_OP_FLUSH) || (bio->bi_opf & REQ_PREFLUSH));
+#elif defined(REQ_PREFLUSH) && defined(HAVE_BIO_BI_OPF)
+	return (bio->bi_opf & REQ_PREFLUSH);
+#elif defined(REQ_PREFLUSH) && !defined(HAVE_BIO_BI_OPF)
+	return (bio->bi_rw & REQ_PREFLUSH);
+#elif defined(REQ_FLUSH)
+	return (bio->bi_rw & REQ_FLUSH);
+#elif defined(HAVE_BIO_RW_BARRIER)
+	return (bio->bi_rw & (1 << BIO_RW_BARRIER));
+#else
+#error	"Allowing the build will cause flush requests to be ignored."
+#endif
+}
+
+/*
+ * 4.8 - 4.x API,
+ *   REQ_FUA flag moved to bio->bi_opf
+ *
+ * 2.6.x - 4.7 API,
+ *   REQ_FUA
+ */
+static inline boolean_t
+bio_is_fua(struct bio *bio)
+{
+#if defined(HAVE_BIO_BI_OPF)
+	return (bio->bi_opf & REQ_FUA);
+#elif defined(REQ_FUA)
+	return (bio->bi_rw & REQ_FUA);
+#else
+#error	"Allowing the build will cause fua requests to be ignored."
+#endif
+}
+
+/*
+ * 4.8 - 4.x API,
+ *   REQ_OP_DISCARD
+ *
+ * 2.6.36 - 4.7 API,
+ *   REQ_DISCARD
+ *
+ * 2.6.28 - 2.6.35 API,
+ *   BIO_RW_DISCARD
+ *
+ * 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(HAVE_BIO_RW_DISCARD)
+	return (bio->bi_rw & (1 << BIO_RW_DISCARD));
+#elif defined(REQ_DISCARD)
+	return (bio->bi_rw & REQ_DISCARD);
+#else
+/* potentially triggering the DMU_MAX_ACCESS assertion.  */
+#error	"Allowing the build will cause discard requests to become writes."
+#endif
+}
+
+/*
+ * 4.8 - 4.x API,
+ *   REQ_OP_SECURE_ERASE
+ *
+ * 2.6.36 - 4.7 API,
+ *   REQ_SECURE
+ *
+ * 2.6.x - 2.6.35 API,
+ *   Unsupported by kernel
+ */
+static inline boolean_t
+bio_is_secure_erase(struct bio *bio)
+{
+#if defined(HAVE_REQ_OP_SECURE_ERASE)
+	return (bio_op(bio) == REQ_OP_SECURE_ERASE);
+#elif defined(REQ_SECURE)
+	return (bio->bi_rw & REQ_SECURE);
+#else
+	return (0);
+#endif
+}
+
+/*
+ * 2.6.33 API change
+ * Discard granularity and alignment restrictions may now be set.  For
+ * older kernels which do not support this it is safe to skip it.
+ */
+#ifdef HAVE_DISCARD_GRANULARITY
+static inline void
+blk_queue_discard_granularity(struct request_queue *q, unsigned int dg)
+{
+	q->limits.discard_granularity = dg;
+}
+#else
+#define	blk_queue_discard_granularity(x, dg)	((void)0)
+#endif /* HAVE_DISCARD_GRANULARITY */
+
+/*
+ * 2.6.32 - 4.x API,
+ *   blk_queue_discard()
+ */
+#if !defined(HAVE_BLK_QUEUE_DISCARD)
+#define	blk_queue_discard(q)			(0);
+#endif
+
+/*
+ * 4.8 - 4.x API,
+ *   blk_queue_secure_erase()
+ *
+ * 2.6.36 - 4.7 API,
+ *   blk_queue_secdiscard()
+ *
+ * 2.6.x - 2.6.35 API,
+ *   Unsupported by kernel
+ */
+static inline int
+blk_queue_discard_secure(struct request_queue *q)
+{
+#if defined(HAVE_BLK_QUEUE_SECURE_ERASE)
+	return (blk_queue_secure_erase(q));
+#elif defined(HAVE_BLK_QUEUE_SECDISCARD)
+	return (blk_queue_secdiscard(q));
+#else
+	return (0);
+#endif
+}
+
+/*
+ * Default Linux IO Scheduler,
+ * Setting the scheduler to noop will allow the Linux IO scheduler to
+ * still perform front and back merging, while leaving the request
+ * ordering and prioritization to the ZFS IO scheduler.
+ */
+#define	VDEV_SCHEDULER			"noop"
+
+/*
+ * A common holder for vdev_bdev_open() is used to relax the exclusive open
+ * semantics slightly.  Internal vdev disk callers may pass VDEV_HOLDER to
+ * allow them to open the device multiple times.  Other kernel callers and
+ * user space processes which don't pass this value will get EBUSY.  This is
+ * currently required for the correct operation of hot spares.
+ */
+#define	VDEV_HOLDER			((void *)0x2401de7)
+
+static inline void
+blk_generic_start_io_acct(struct request_queue *q, int rw,
+    unsigned long sectors, struct hd_struct *part)
+{
+#if defined(HAVE_GENERIC_IO_ACCT_3ARG)
+	generic_start_io_acct(rw, sectors, part);
+#elif defined(HAVE_GENERIC_IO_ACCT_4ARG)
+	generic_start_io_acct(q, rw, sectors, part);
+#endif
+}
+
+static inline void
+blk_generic_end_io_acct(struct request_queue *q, int rw,
+    struct hd_struct *part, unsigned long start_time)
+{
+#if defined(HAVE_GENERIC_IO_ACCT_3ARG)
+	generic_end_io_acct(rw, part, start_time);
+#elif defined(HAVE_GENERIC_IO_ACCT_4ARG)
+	generic_end_io_acct(q, rw, part, start_time);
+#endif
+}
+
+#endif /* _ZFS_BLKDEV_H */

include/os/linux/kernel/linux/compiler_compat.h

@@ -0,0 +1,35 @@
+/*
+ * 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 Lawrence Livermore National Security, LLC.
+ */
+
+#ifndef _ZFS_COMPILER_COMPAT_H
+#define	_ZFS_COMPILER_COMPAT_H
+
+#include <linux/compiler.h>
+
+#if !defined(READ_ONCE)
+#define	READ_ONCE(x)		ACCESS_ONCE(x)
+#endif
+
+#endif	/* _ZFS_COMPILER_COMPAT_H */

include/os/linux/kernel/linux/dcache_compat.h

@@ -0,0 +1,83 @@
+/*
+ * 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) 2011 Lawrence Livermore National Security, LLC.
+ */
+
+#ifndef _ZFS_DCACHE_H
+#define	_ZFS_DCACHE_H
+
+#include <linux/dcache.h>
+
+#define	dname(dentry)	((char *)((dentry)->d_name.name))
+#define	dlen(dentry)	((int)((dentry)->d_name.len))
+
+#ifndef HAVE_D_MAKE_ROOT
+#define	d_make_root(inode)	d_alloc_root(inode)
+#endif /* HAVE_D_MAKE_ROOT */
+
+/*
+ * 2.6.30 API change,
+ * The const keyword was added to the 'struct dentry_operations' in
+ * the dentry structure.  To handle this we define an appropriate
+ * dentry_operations_t typedef which can be used.
+ */
+#ifdef HAVE_CONST_DENTRY_OPERATIONS
+typedef const struct dentry_operations	dentry_operations_t;
+#else
+typedef struct dentry_operations	dentry_operations_t;
+#endif
+
+/*
+ * 2.6.38 API change,
+ * Added d_set_d_op() helper function which sets some flags in
+ * dentry->d_flags based on which operations are defined.
+ */
+#ifndef HAVE_D_SET_D_OP
+static inline void
+d_set_d_op(struct dentry *dentry, dentry_operations_t *op)
+{
+	dentry->d_op = op;
+}
+#endif /* HAVE_D_SET_D_OP */
+
+/*
+ * 2.6.38 API addition,
+ * Added d_clear_d_op() helper function which clears some flags and the
+ * registered dentry->d_op table.  This is required because d_set_d_op()
+ * issues a warning when the dentry operations table is already set.
+ * For the .zfs control directory to work properly we must be able to
+ * override the default operations table and register custom .d_automount
+ * and .d_revalidate callbacks.
+ */
+static inline void
+d_clear_d_op(struct dentry *dentry)
+{
+#ifdef HAVE_D_SET_D_OP
+	dentry->d_op = NULL;
+	dentry->d_flags &= ~(
+	    DCACHE_OP_HASH | DCACHE_OP_COMPARE |
+	    DCACHE_OP_REVALIDATE | DCACHE_OP_DELETE);
+#endif /* HAVE_D_SET_D_OP */
+}
+
+#endif /* _ZFS_DCACHE_H */

include/os/linux/kernel/linux/kmap_compat.h

@@ -0,0 +1,48 @@
+/*
+ * 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) 2015 by Chunwei Chen. All rights reserved.
+ */
+
+#ifndef _ZFS_KMAP_H
+#define	_ZFS_KMAP_H
+
+#include <linux/highmem.h>
+#include <linux/uaccess.h>
+
+#ifdef HAVE_1ARG_KMAP_ATOMIC
+/* 2.6.37 API change */
+#define	zfs_kmap_atomic(page, km_type)		kmap_atomic(page)
+#define	zfs_kunmap_atomic(addr, km_type)	kunmap_atomic(addr)
+#else
+#define	zfs_kmap_atomic(page, km_type)		kmap_atomic(page, km_type)
+#define	zfs_kunmap_atomic(addr, km_type)	kunmap_atomic(addr, km_type)
+#endif
+
+/* 5.0 API change - no more 'type' argument for access_ok() */
+#ifdef HAVE_ACCESS_OK_TYPE
+#define	zfs_access_ok(type, addr, size)	access_ok(type, addr, size)
+#else
+#define	zfs_access_ok(type, addr, size)	access_ok(addr, size)
+#endif
+
+#endif	/* _ZFS_KMAP_H */

include/os/linux/kernel/linux/mod_compat.h

@@ -0,0 +1,39 @@
+/*
+ * 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) 2016 Gvozden Neskovic <neskovic@gmail.com>.
+ */
+
+#ifndef _MOD_COMPAT_H
+#define	_MOD_COMPAT_H
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+
+/* Grsecurity kernel API change */
+#ifdef MODULE_PARAM_CALL_CONST
+typedef const struct kernel_param zfs_kernel_param_t;
+#else
+typedef struct kernel_param zfs_kernel_param_t;
+#endif
+
+#endif	/* _MOD_COMPAT_H */

include/os/linux/kernel/linux/page_compat.h

@@ -0,0 +1,78 @@
+#ifndef	_ZFS_PAGE_COMPAT_H
+#define	_ZFS_PAGE_COMPAT_H
+
+/*
+ * We have various enum members moving between two separate enum types,
+ * and accessed by different functions at various times. Centralise the
+ * insanity.
+ *
+ * < v4.8: all enums in zone_stat_item, via global_page_state()
+ * v4.8: some enums moved to node_stat_item, global_node_page_state() introduced
+ * v4.13: some enums moved from zone_stat_item to node_state_item
+ * v4.14: global_page_state() rename to global_zone_page_state()
+ *
+ * The defines used here are created by config/kernel-global_page_state.m4
+ */
+
+/*
+ * Create our own accessor functions to follow the Linux API changes
+ */
+#if	defined(ZFS_GLOBAL_ZONE_PAGE_STATE)
+
+/* global_zone_page_state() introduced */
+#if	defined(ZFS_ENUM_NODE_STAT_ITEM_NR_FILE_PAGES)
+#define	nr_file_pages() global_node_page_state(NR_FILE_PAGES)
+#else
+#define	nr_file_pages() global_zone_page_state(NR_FILE_PAGES)
+#endif
+#if	defined(ZFS_ENUM_NODE_STAT_ITEM_NR_INACTIVE_ANON)
+#define	nr_inactive_anon_pages() global_node_page_state(NR_INACTIVE_ANON)
+#else
+#define	nr_inactive_anon_pages() global_zone_page_state(NR_INACTIVE_ANON)
+#endif
+#if	defined(ZFS_ENUM_NODE_STAT_ITEM_NR_INACTIVE_FILE)
+#define	nr_inactive_file_pages() global_node_page_state(NR_INACTIVE_FILE)
+#else
+#define	nr_inactive_file_pages() global_zone_page_state(NR_INACTIVE_FILE)
+#endif
+#if	defined(ZFS_ENUM_NODE_STAT_ITEM_NR_SLAB_RECLAIMABLE)
+#define	nr_slab_reclaimable_pages() global_node_page_state(NR_SLAB_RECLAIMABLE)
+#else
+#define	nr_slab_reclaimable_pages() global_zone_page_state(NR_SLAB_RECLAIMABLE)
+#endif
+
+#elif	defined(ZFS_GLOBAL_NODE_PAGE_STATE)
+
+/* global_node_page_state() introduced */
+#if	defined(ZFS_ENUM_NODE_STAT_ITEM_NR_FILE_PAGES)
+#define	nr_file_pages() global_node_page_state(NR_FILE_PAGES)
+#else
+#define	nr_file_pages() global_page_state(NR_FILE_PAGES)
+#endif
+#if	defined(ZFS_ENUM_NODE_STAT_ITEM_NR_INACTIVE_ANON)
+#define	nr_inactive_anon_pages() global_node_page_state(NR_INACTIVE_ANON)
+#else
+#define	nr_inactive_anon_pages() global_page_state(NR_INACTIVE_ANON)
+#endif
+#if	defined(ZFS_ENUM_NODE_STAT_ITEM_NR_INACTIVE_FILE)
+#define	nr_inactive_file_pages() global_node_page_state(NR_INACTIVE_FILE)
+#else
+#define	nr_inactive_file_pages() global_page_state(NR_INACTIVE_FILE)
+#endif
+#if	defined(ZFS_ENUM_NODE_STAT_ITEM_NR_SLAB_RECLAIMABLE)
+#define	nr_slab_reclaimable_pages() global_node_page_state(NR_SLAB_RECLAIMABLE)
+#else
+#define	nr_slab_reclaimable_pages() global_page_state(NR_SLAB_RECLAIMABLE)
+#endif
+
+#else
+
+/* global_page_state() only */
+#define	nr_file_pages()			global_page_state(NR_FILE_PAGES)
+#define	nr_inactive_anon_pages()	global_page_state(NR_INACTIVE_ANON)
+#define	nr_inactive_file_pages()	global_page_state(NR_INACTIVE_FILE)
+#define	nr_slab_reclaimable_pages()	global_page_state(NR_SLAB_RECLAIMABLE)
+
+#endif /* ZFS_GLOBAL_ZONE_PAGE_STATE */
+
+#endif /* _ZFS_PAGE_COMPAT_H */

include/os/linux/kernel/linux/simd.h

@@ -0,0 +1,41 @@
+/*
+ * 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) 2019 Lawrence Livermore National Security, LLC.
+ */
+
+#ifndef _LINUX_SIMD_H
+#define	_LINUX_SIMD_H
+
+#if defined(__x86)
+#include <linux/simd_x86.h>
+
+#elif defined(__aarch64__)
+#include <linux/simd_aarch64.h>
+#else
+
+#define	kfpu_allowed()		0
+#define	kfpu_initialize(tsk)	do {} while (0)
+#define	kfpu_begin()		do {} while (0)
+#define	kfpu_end()		do {} while (0)
+
+#endif
+#endif /* _LINUX_SIMD_H */

include/os/linux/kernel/linux/simd_aarch64.h

@@ -0,0 +1,52 @@
+/*
+ * 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) 2016 Romain Dolbeau <romain@dolbeau.org>.
+ */
+
+/*
+ * USER API:
+ *
+ * Kernel fpu methods:
+ *	kfpu_allowed()
+ *	kfpu_initialize()
+ *	kfpu_begin()
+ *	kfpu_end()
+ */
+
+#ifndef _LINUX_SIMD_AARCH64_H
+#define	_LINUX_SIMD_AARCH64_H
+
+#include <sys/isa_defs.h>
+
+#if defined(__aarch64__)
+
+#include <sys/types.h>
+#include <asm/neon.h>
+
+#define	kfpu_allowed()		1
+#define	kfpu_initialize(tsk)	do {} while (0)
+#define	kfpu_begin()		kernel_neon_begin()
+#define	kfpu_end()		kernel_neon_end()
+
+#endif /* __aarch64__ */
+
+#endif /* _LINUX_SIMD_AARCH64_H */

include/os/linux/kernel/linux/simd_x86.h

@@ -0,0 +1,523 @@
+/*
+ * 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) 2016 Gvozden Neskovic <neskovic@compeng.uni-frankfurt.de>.
+ */
+
+/*
+ * USER API:
+ *
+ * Kernel fpu methods:
+ *	kfpu_allowed()
+ *	kfpu_initialize()
+ *	kfpu_begin()
+ *	kfpu_end()
+ *
+ * SIMD support:
+ *
+ * Following functions should be called to determine whether CPU feature
+ * is supported. All functions are usable in kernel and user space.
+ * If a SIMD algorithm is using more than one instruction set
+ * all relevant feature test functions should be called.
+ *
+ * Supported features:
+ *	zfs_sse_available()
+ *	zfs_sse2_available()
+ *	zfs_sse3_available()
+ *	zfs_ssse3_available()
+ *	zfs_sse4_1_available()
+ *	zfs_sse4_2_available()
+ *
+ *	zfs_avx_available()
+ *	zfs_avx2_available()
+ *
+ *	zfs_bmi1_available()
+ *	zfs_bmi2_available()
+ *
+ *	zfs_avx512f_available()
+ *	zfs_avx512cd_available()
+ *	zfs_avx512er_available()
+ *	zfs_avx512pf_available()
+ *	zfs_avx512bw_available()
+ *	zfs_avx512dq_available()
+ *	zfs_avx512vl_available()
+ *	zfs_avx512ifma_available()
+ *	zfs_avx512vbmi_available()
+ *
+ * NOTE(AVX-512VL):	If using AVX-512 instructions with 128Bit registers
+ *			also add zfs_avx512vl_available() to feature check.
+ */
+
+#ifndef _LINUX_SIMD_X86_H
+#define	_LINUX_SIMD_X86_H
+
+/* only for __x86 */
+#if defined(__x86)
+
+#include <sys/types.h>
+#include <asm/cpufeature.h>
+
+/*
+ * Disable the WARN_ON_FPU() macro to prevent additional dependencies
+ * when providing the kfpu_* functions.  Relevant warnings are included
+ * as appropriate and are unconditionally enabled.
+ */
+#if defined(CONFIG_X86_DEBUG_FPU) && !defined(KERNEL_EXPORTS_X86_FPU)
+#undef CONFIG_X86_DEBUG_FPU
+#endif
+
+#if defined(HAVE_KERNEL_FPU_API_HEADER)
+#include <asm/fpu/api.h>
+#include <asm/fpu/internal.h>
+#else
+#include <asm/i387.h>
+#include <asm/xcr.h>
+#endif
+
+/*
+ * The following cases are for kernels which export either the
+ * kernel_fpu_* or __kernel_fpu_* functions.
+ */
+#if defined(KERNEL_EXPORTS_X86_FPU)
+
+#define	kfpu_allowed()		1
+#define	kfpu_initialize(tsk)	do {} while (0)
+
+#if defined(HAVE_UNDERSCORE_KERNEL_FPU)
+#define	kfpu_begin()		\
+{				\
+	preempt_disable();	\
+	__kernel_fpu_begin();	\
+}
+#define	kfpu_end()		\
+{				\
+	__kernel_fpu_end();	\
+	preempt_enable();	\
+}
+
+#elif defined(HAVE_KERNEL_FPU)
+#define	kfpu_begin()		kernel_fpu_begin()
+#define	kfpu_end()		kernel_fpu_end()
+
+#else
+/*
+ * This case is unreachable.  When KERNEL_EXPORTS_X86_FPU is defined then
+ * either HAVE_UNDERSCORE_KERNEL_FPU or HAVE_KERNEL_FPU must be defined.
+ */
+#error "Unreachable kernel configuration"
+#endif
+
+#else /* defined(KERNEL_EXPORTS_X86_FPU) */
+/*
+ * When the kernel_fpu_* symbols are unavailable then provide our own
+ * versions which allow the FPU to be safely used in kernel threads.
+ * In practice, this is not a significant restriction for ZFS since the
+ * vast majority of SIMD operations are performed by the IO pipeline.
+ */
+
+/*
+ * Returns non-zero if FPU operations are allowed in the current context.
+ */
+#if defined(HAVE_KERNEL_TIF_NEED_FPU_LOAD)
+#define	kfpu_allowed()		((current->flags & PF_KTHREAD) && \
+				test_thread_flag(TIF_NEED_FPU_LOAD))
+#elif defined(HAVE_KERNEL_FPU_INITIALIZED)
+#define	kfpu_allowed()		((current->flags & PF_KTHREAD) && \
+				current->thread.fpu.initialized)
+#else
+#define	kfpu_allowed()		0
+#endif
+
+static inline void
+kfpu_initialize(void)
+{
+	WARN_ON_ONCE(!(current->flags & PF_KTHREAD));
+
+#if defined(HAVE_KERNEL_TIF_NEED_FPU_LOAD)
+	__fpu_invalidate_fpregs_state(&current->thread.fpu);
+	set_thread_flag(TIF_NEED_FPU_LOAD);
+#elif defined(HAVE_KERNEL_FPU_INITIALIZED)
+	__fpu_invalidate_fpregs_state(&current->thread.fpu);
+	current->thread.fpu.initialized = 1;
+#endif
+}
+
+static inline void
+kfpu_begin(void)
+{
+	WARN_ON_ONCE(!kfpu_allowed());
+
+	/*
+	 * Preemption and interrupts must be disabled for the critical
+	 * region where the FPU state is being modified.
+	 */
+	preempt_disable();
+	local_irq_disable();
+
+#if defined(HAVE_KERNEL_TIF_NEED_FPU_LOAD)
+	/*
+	 * The current FPU registers need to be preserved by kfpu_begin()
+	 * and restored by kfpu_end().  This is required because we can
+	 * not call __cpu_invalidate_fpregs_state() to invalidate the
+	 * per-cpu FPU state and force them to be restored during a
+	 * context switch.
+	 */
+	copy_fpregs_to_fpstate(&current->thread.fpu);
+#elif defined(HAVE_KERNEL_FPU_INITIALIZED)
+	/*
+	 * There is no need to preserve and restore the FPU registers.
+	 * They will always be restored from the task's stored FPU state
+	 * when switching contexts.
+	 */
+	WARN_ON_ONCE(current->thread.fpu.initialized == 0);
+#endif
+}
+
+static inline void
+kfpu_end(void)
+{
+#if defined(HAVE_KERNEL_TIF_NEED_FPU_LOAD)
+	union fpregs_state *state = &current->thread.fpu.state;
+	int error;
+
+	if (use_xsave()) {
+		error = copy_kernel_to_xregs_err(&state->xsave, -1);
+	} else if (use_fxsr()) {
+		error = copy_kernel_to_fxregs_err(&state->fxsave);
+	} else {
+		error = copy_kernel_to_fregs_err(&state->fsave);
+	}
+	WARN_ON_ONCE(error);
+#endif
+
+	local_irq_enable();
+	preempt_enable();
+}
+#endif /* defined(HAVE_KERNEL_FPU) */
+
+/*
+ * Linux kernel provides an interface for CPU feature testing.
+ */
+/*
+ * Detect register set support
+ */
+static inline boolean_t
+__simd_state_enabled(const uint64_t state)
+{
+	boolean_t has_osxsave;
+	uint64_t xcr0;
+
+#if defined(X86_FEATURE_OSXSAVE)
+	has_osxsave = !!boot_cpu_has(X86_FEATURE_OSXSAVE);
+#else
+	has_osxsave = B_FALSE;
+#endif
+	if (!has_osxsave)
+		return (B_FALSE);
+
+	xcr0 = xgetbv(0);
+	return ((xcr0 & state) == state);
+}
+
+#define	_XSTATE_SSE_AVX		(0x2 | 0x4)
+#define	_XSTATE_AVX512		(0xE0 | _XSTATE_SSE_AVX)
+
+#define	__ymm_enabled() __simd_state_enabled(_XSTATE_SSE_AVX)
+#define	__zmm_enabled() __simd_state_enabled(_XSTATE_AVX512)
+
+/*
+ * Check if SSE instruction set is available
+ */
+static inline boolean_t
+zfs_sse_available(void)
+{
+	return (!!boot_cpu_has(X86_FEATURE_XMM));
+}
+
+/*
+ * Check if SSE2 instruction set is available
+ */
+static inline boolean_t
+zfs_sse2_available(void)
+{
+	return (!!boot_cpu_has(X86_FEATURE_XMM2));
+}
+
+/*
+ * Check if SSE3 instruction set is available
+ */
+static inline boolean_t
+zfs_sse3_available(void)
+{
+	return (!!boot_cpu_has(X86_FEATURE_XMM3));
+}
+
+/*
+ * Check if SSSE3 instruction set is available
+ */
+static inline boolean_t
+zfs_ssse3_available(void)
+{
+	return (!!boot_cpu_has(X86_FEATURE_SSSE3));
+}
+
+/*
+ * Check if SSE4.1 instruction set is available
+ */
+static inline boolean_t
+zfs_sse4_1_available(void)
+{
+	return (!!boot_cpu_has(X86_FEATURE_XMM4_1));
+}
+
+/*
+ * Check if SSE4.2 instruction set is available
+ */
+static inline boolean_t
+zfs_sse4_2_available(void)
+{
+	return (!!boot_cpu_has(X86_FEATURE_XMM4_2));
+}
+
+/*
+ * Check if AVX instruction set is available
+ */
+static inline boolean_t
+zfs_avx_available(void)
+{
+	return (boot_cpu_has(X86_FEATURE_AVX) && __ymm_enabled());
+}
+
+/*
+ * Check if AVX2 instruction set is available
+ */
+static inline boolean_t
+zfs_avx2_available(void)
+{
+	return (boot_cpu_has(X86_FEATURE_AVX2) && __ymm_enabled());
+}
+
+/*
+ * Check if BMI1 instruction set is available
+ */
+static inline boolean_t
+zfs_bmi1_available(void)
+{
+#if defined(X86_FEATURE_BMI1)
+	return (!!boot_cpu_has(X86_FEATURE_BMI1));
+#else
+	return (B_FALSE);
+#endif
+}
+
+/*
+ * Check if BMI2 instruction set is available
+ */
+static inline boolean_t
+zfs_bmi2_available(void)
+{
+#if defined(X86_FEATURE_BMI2)
+	return (!!boot_cpu_has(X86_FEATURE_BMI2));
+#else
+	return (B_FALSE);
+#endif
+}
+
+/*
+ * Check if AES instruction set is available
+ */
+static inline boolean_t
+zfs_aes_available(void)
+{
+#if defined(X86_FEATURE_AES)
+	return (!!boot_cpu_has(X86_FEATURE_AES));
+#else
+	return (B_FALSE);
+#endif
+}
+
+/*
+ * Check if PCLMULQDQ instruction set is available
+ */
+static inline boolean_t
+zfs_pclmulqdq_available(void)
+{
+#if defined(X86_FEATURE_PCLMULQDQ)
+	return (!!boot_cpu_has(X86_FEATURE_PCLMULQDQ));
+#else
+	return (B_FALSE);
+#endif
+}
+
+/*
+ * AVX-512 family of instruction sets:
+ *
+ * AVX512F	Foundation
+ * AVX512CD	Conflict Detection Instructions
+ * AVX512ER	Exponential and Reciprocal Instructions
+ * AVX512PF	Prefetch Instructions
+ *
+ * AVX512BW	Byte and Word Instructions
+ * AVX512DQ	Double-word and Quadword Instructions
+ * AVX512VL	Vector Length Extensions
+ *
+ * AVX512IFMA	Integer Fused Multiply Add (Not supported by kernel 4.4)
+ * AVX512VBMI	Vector Byte Manipulation Instructions
+ */
+
+/*
+ * Check if AVX512F instruction set is available
+ */
+static inline boolean_t
+zfs_avx512f_available(void)
+{
+	boolean_t has_avx512 = B_FALSE;
+
+#if defined(X86_FEATURE_AVX512F)
+	has_avx512 = !!boot_cpu_has(X86_FEATURE_AVX512F);
+#endif
+	return (has_avx512 && __zmm_enabled());
+}
+
+/*
+ * Check if AVX512CD instruction set is available
+ */
+static inline boolean_t
+zfs_avx512cd_available(void)
+{
+	boolean_t has_avx512 = B_FALSE;
+
+#if defined(X86_FEATURE_AVX512CD)
+	has_avx512 = boot_cpu_has(X86_FEATURE_AVX512F) &&
+	    boot_cpu_has(X86_FEATURE_AVX512CD);
+#endif
+	return (has_avx512 && __zmm_enabled());
+}
+
+/*
+ * Check if AVX512ER instruction set is available
+ */
+static inline boolean_t
+zfs_avx512er_available(void)
+{
+	boolean_t has_avx512 = B_FALSE;
+
+#if defined(X86_FEATURE_AVX512ER)
+	has_avx512 = boot_cpu_has(X86_FEATURE_AVX512F) &&
+	    boot_cpu_has(X86_FEATURE_AVX512ER);
+#endif
+	return (has_avx512 && __zmm_enabled());
+}
+
+/*
+ * Check if AVX512PF instruction set is available
+ */
+static inline boolean_t
+zfs_avx512pf_available(void)
+{
+	boolean_t has_avx512 = B_FALSE;
+
+#if defined(X86_FEATURE_AVX512PF)
+	has_avx512 = boot_cpu_has(X86_FEATURE_AVX512F) &&
+	    boot_cpu_has(X86_FEATURE_AVX512PF);
+#endif
+	return (has_avx512 && __zmm_enabled());
+}
+
+/*
+ * Check if AVX512BW instruction set is available
+ */
+static inline boolean_t
+zfs_avx512bw_available(void)
+{
+	boolean_t has_avx512 = B_FALSE;
+
+#if defined(X86_FEATURE_AVX512BW)
+	has_avx512 = boot_cpu_has(X86_FEATURE_AVX512F) &&
+	    boot_cpu_has(X86_FEATURE_AVX512BW);
+#endif
+
+	return (has_avx512 && __zmm_enabled());
+}
+
+/*
+ * Check if AVX512DQ instruction set is available
+ */
+static inline boolean_t
+zfs_avx512dq_available(void)
+{
+	boolean_t has_avx512 = B_FALSE;
+
+#if defined(X86_FEATURE_AVX512DQ)
+	has_avx512 = boot_cpu_has(X86_FEATURE_AVX512F) &&
+	    boot_cpu_has(X86_FEATURE_AVX512DQ);
+#endif
+	return (has_avx512 && __zmm_enabled());
+}
+
+/*
+ * Check if AVX512VL instruction set is available
+ */
+static inline boolean_t
+zfs_avx512vl_available(void)
+{
+	boolean_t has_avx512 = B_FALSE;
+
+#if defined(X86_FEATURE_AVX512VL)
+	has_avx512 = boot_cpu_has(X86_FEATURE_AVX512F) &&
+	    boot_cpu_has(X86_FEATURE_AVX512VL);
+#endif
+	return (has_avx512 && __zmm_enabled());
+}
+
+/*
+ * Check if AVX512IFMA instruction set is available
+ */
+static inline boolean_t
+zfs_avx512ifma_available(void)
+{
+	boolean_t has_avx512 = B_FALSE;
+
+#if defined(X86_FEATURE_AVX512IFMA)
+	has_avx512 = boot_cpu_has(X86_FEATURE_AVX512F) &&
+	    boot_cpu_has(X86_FEATURE_AVX512IFMA);
+#endif
+	return (has_avx512 && __zmm_enabled());
+}
+
+/*
+ * Check if AVX512VBMI instruction set is available
+ */
+static inline boolean_t
+zfs_avx512vbmi_available(void)
+{
+	boolean_t has_avx512 = B_FALSE;
+
+#if defined(X86_FEATURE_AVX512VBMI)
+	has_avx512 = boot_cpu_has(X86_FEATURE_AVX512F) &&
+	    boot_cpu_has(X86_FEATURE_AVX512VBMI);
+#endif
+	return (has_avx512 && __zmm_enabled());
+}
+
+#endif /* defined(__x86) */
+
+#endif /* _LINUX_SIMD_X86_H */

include/os/linux/kernel/linux/utsname_compat.h

@@ -0,0 +1,29 @@
+/*
+ * 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
+ */
+
+#ifndef	_ZFS_UTSNAME_H
+#define	_ZFS_UTSNAME_H
+
+#include <linux/utsname.h>
+
+typedef struct new_utsname	utsname_t;
+
+#endif	/* _ZFS_UTSNAME_H */

include/os/linux/kernel/linux/vfs_compat.h

@@ -0,0 +1,646 @@
+/*
+ * 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) 2011 Lawrence Livermore National Security, LLC.
+ * Copyright (C) 2015 Jörg Thalheim.
+ */
+
+#ifndef _ZFS_VFS_H
+#define	_ZFS_VFS_H
+
+#include <sys/taskq.h>
+#include <sys/cred.h>
+#include <linux/backing-dev.h>
+#include <linux/compat.h>
+
+/*
+ * 2.6.28 API change,
+ * Added insert_inode_locked() helper function, prior to this most callers
+ * used insert_inode_hash().  The older method doesn't check for collisions
+ * in the inode_hashtable but it still acceptable for use.
+ */
+#ifndef HAVE_INSERT_INODE_LOCKED
+static inline int
+insert_inode_locked(struct inode *ip)
+{
+	insert_inode_hash(ip);
+	return (0);
+}
+#endif /* HAVE_INSERT_INODE_LOCKED */
+
+/*
+ * 2.6.35 API change,
+ * Add truncate_setsize() if it is not exported by the Linux kernel.
+ *
+ * Truncate the inode and pages associated with the inode. The pages are
+ * unmapped and removed from cache.
+ */
+#ifndef HAVE_TRUNCATE_SETSIZE
+static inline void
+truncate_setsize(struct inode *ip, loff_t new)
+{
+	struct address_space *mapping = ip->i_mapping;
+
+	i_size_write(ip, new);
+
+	unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1);
+	truncate_inode_pages(mapping, new);
+	unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1);
+}
+#endif /* HAVE_TRUNCATE_SETSIZE */
+
+/*
+ * 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 - 4.11, bdi_setup_and_register() takes 2 arguments.
+ * 4.12 - x.y, super_setup_bdi_name() new interface.
+ */
+#if defined(HAVE_SUPER_SETUP_BDI_NAME)
+extern atomic_long_t zfs_bdi_seq;
+
+static inline int
+zpl_bdi_setup(struct super_block *sb, char *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(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, 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(struct super_block *sb, char *name)
+{
+	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) {
+		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
+
+/*
+ * 4.14 adds SB_* flag definitions, define them to MS_* equivalents
+ * if not set.
+ */
+#ifndef	SB_RDONLY
+#define	SB_RDONLY	MS_RDONLY
+#endif
+
+#ifndef	SB_SILENT
+#define	SB_SILENT	MS_SILENT
+#endif
+
+#ifndef	SB_ACTIVE
+#define	SB_ACTIVE	MS_ACTIVE
+#endif
+
+#ifndef	SB_POSIXACL
+#define	SB_POSIXACL	MS_POSIXACL
+#endif
+
+#ifndef	SB_MANDLOCK
+#define	SB_MANDLOCK	MS_MANDLOCK
+#endif
+
+#ifndef	SB_NOATIME
+#define	SB_NOATIME	MS_NOATIME
+#endif
+
+/*
+ * 2.6.38 API change,
+ * LOOKUP_RCU flag introduced to distinguish rcu-walk from ref-walk cases.
+ */
+#ifndef LOOKUP_RCU
+#define	LOOKUP_RCU	0x0
+#endif /* LOOKUP_RCU */
+
+/*
+ * 3.2-rc1 API change,
+ * Add set_nlink() if it is not exported by the Linux kernel.
+ *
+ * i_nlink is read-only in Linux 3.2, but it can be set directly in
+ * earlier kernels.
+ */
+#ifndef HAVE_SET_NLINK
+static inline void
+set_nlink(struct inode *inode, unsigned int nlink)
+{
+	inode->i_nlink = nlink;
+}
+#endif /* HAVE_SET_NLINK */
+
+/*
+ * 3.3 API change,
+ * The VFS .create, .mkdir and .mknod callbacks were updated to take a
+ * umode_t type rather than an int.  To cleanly handle both definitions
+ * the zpl_umode_t type is introduced and set accordingly.
+ */
+#ifdef HAVE_MKDIR_UMODE_T
+typedef	umode_t		zpl_umode_t;
+#else
+typedef	int		zpl_umode_t;
+#endif
+
+/*
+ * 3.5 API change,
+ * The clear_inode() function replaces end_writeback() and introduces an
+ * ordering change regarding when the inode_sync_wait() occurs.  See the
+ * configure check in config/kernel-clear-inode.m4 for full details.
+ */
+#if defined(HAVE_EVICT_INODE) && !defined(HAVE_CLEAR_INODE)
+#define	clear_inode(ip)		end_writeback(ip)
+#endif /* HAVE_EVICT_INODE && !HAVE_CLEAR_INODE */
+
+/*
+ * 3.6 API change,
+ * The sget() helper function now takes the mount flags as an argument.
+ */
+#ifdef HAVE_5ARG_SGET
+#define	zpl_sget(type, cmp, set, fl, mtd)	sget(type, cmp, set, fl, mtd)
+#else
+#define	zpl_sget(type, cmp, set, fl, mtd)	sget(type, cmp, set, mtd)
+#endif /* HAVE_5ARG_SGET */
+
+#if defined(SEEK_HOLE) && defined(SEEK_DATA) && !defined(HAVE_LSEEK_EXECUTE)
+static inline loff_t
+lseek_execute(
+	struct file *filp,
+	struct inode *inode,
+	loff_t offset,
+	loff_t maxsize)
+{
+	if (offset < 0 && !(filp->f_mode & FMODE_UNSIGNED_OFFSET))
+		return (-EINVAL);
+
+	if (offset > maxsize)
+		return (-EINVAL);
+
+	if (offset != filp->f_pos) {
+		spin_lock(&filp->f_lock);
+		filp->f_pos = offset;
+		filp->f_version = 0;
+		spin_unlock(&filp->f_lock);
+	}
+
+	return (offset);
+}
+#endif /* SEEK_HOLE && SEEK_DATA && !HAVE_LSEEK_EXECUTE */
+
+#if defined(CONFIG_FS_POSIX_ACL)
+/*
+ * These functions safely approximates the behavior of posix_acl_release()
+ * which cannot be used because it calls the GPL-only symbol kfree_rcu().
+ * The in-kernel version, which can access the RCU, frees the ACLs after
+ * the grace period expires.  Because we're unsure how long that grace
+ * period may be this implementation conservatively delays for 60 seconds.
+ * This is several orders of magnitude larger than expected grace period.
+ * At 60 seconds the kernel will also begin issuing RCU stall warnings.
+ */
+
+#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)
+#else
+void zpl_posix_acl_release_impl(struct posix_acl *);
+
+static inline void
+zpl_posix_acl_release(struct posix_acl *acl)
+{
+	if ((acl == NULL) || (acl == ACL_NOT_CACHED))
+		return;
+#ifdef HAVE_ACL_REFCOUNT
+	if (refcount_dec_and_test(&acl->a_refcount))
+		zpl_posix_acl_release_impl(acl);
+#else
+	if (atomic_dec_and_test(&acl->a_refcount))
+		zpl_posix_acl_release_impl(acl);
+#endif
+}
+#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;
+
+	spin_lock(&ip->i_lock);
+
+	if ((newer != ACL_NOT_CACHED) && (newer != NULL))
+		posix_acl_dup(newer);
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		older = ip->i_acl;
+		rcu_assign_pointer(ip->i_acl, newer);
+		break;
+	case ACL_TYPE_DEFAULT:
+		older = ip->i_default_acl;
+		rcu_assign_pointer(ip->i_default_acl, newer);
+		break;
+	}
+
+	spin_unlock(&ip->i_lock);
+
+	zpl_posix_acl_release(older);
+}
+
+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_SET_CACHED_ACL_USABLE */
+
+#ifndef HAVE___POSIX_ACL_CHMOD
+#ifdef HAVE_POSIX_ACL_CHMOD
+#define	__posix_acl_chmod(acl, gfp, mode)	posix_acl_chmod(acl, gfp, mode)
+#define	__posix_acl_create(acl, gfp, mode)	posix_acl_create(acl, gfp, mode)
+#else
+static inline int
+__posix_acl_chmod(struct posix_acl **acl, int flags, umode_t umode)
+{
+	struct posix_acl *oldacl = *acl;
+	mode_t mode = umode;
+	int error;
+
+	*acl = posix_acl_clone(*acl, flags);
+	zpl_posix_acl_release(oldacl);
+
+	if (!(*acl))
+		return (-ENOMEM);
+
+	error = posix_acl_chmod_masq(*acl, mode);
+	if (error) {
+		zpl_posix_acl_release(*acl);
+		*acl = NULL;
+	}
+
+	return (error);
+}
+
+static inline int
+__posix_acl_create(struct posix_acl **acl, int flags, umode_t *umodep)
+{
+	struct posix_acl *oldacl = *acl;
+	mode_t mode = *umodep;
+	int error;
+
+	*acl = posix_acl_clone(*acl, flags);
+	zpl_posix_acl_release(oldacl);
+
+	if (!(*acl))
+		return (-ENOMEM);
+
+	error = posix_acl_create_masq(*acl, &mode);
+	*umodep = mode;
+
+	if (error < 0) {
+		zpl_posix_acl_release(*acl);
+		*acl = NULL;
+	}
+
+	return (error);
+}
+#endif /* HAVE_POSIX_ACL_CHMOD */
+#endif /* HAVE___POSIX_ACL_CHMOD */
+
+#ifdef HAVE_POSIX_ACL_EQUIV_MODE_UMODE_T
+typedef umode_t zpl_equivmode_t;
+#else
+typedef mode_t zpl_equivmode_t;
+#endif /* HAVE_POSIX_ACL_EQUIV_MODE_UMODE_T */
+
+/*
+ * 4.8 API change,
+ * posix_acl_valid() now must be passed a namespace, the namespace from
+ * from super block associated with the given inode is used for this purpose.
+ */
+#ifdef HAVE_POSIX_ACL_VALID_WITH_NS
+#define	zpl_posix_acl_valid(ip, acl)  posix_acl_valid(ip->i_sb->s_user_ns, acl)
+#else
+#define	zpl_posix_acl_valid(ip, acl)  posix_acl_valid(acl)
+#endif
+
+#endif /* CONFIG_FS_POSIX_ACL */
+
+/*
+ * 2.6.38 API change,
+ * The is_owner_or_cap() function was renamed to inode_owner_or_capable().
+ */
+#ifdef HAVE_INODE_OWNER_OR_CAPABLE
+#define	zpl_inode_owner_or_capable(ip)		inode_owner_or_capable(ip)
+#else
+#define	zpl_inode_owner_or_capable(ip)		is_owner_or_cap(ip)
+#endif /* HAVE_INODE_OWNER_OR_CAPABLE */
+
+/*
+ * 3.19 API change
+ * struct access f->f_dentry->d_inode was replaced by accessor function
+ * file_inode(f)
+ */
+#ifndef HAVE_FILE_INODE
+static inline struct inode *file_inode(const struct file *f)
+{
+	return (f->f_dentry->d_inode);
+}
+#endif /* HAVE_FILE_INODE */
+
+/*
+ * 4.1 API change
+ * struct access file->f_path.dentry was replaced by accessor function
+ * file_dentry(f)
+ */
+#ifndef HAVE_FILE_DENTRY
+static inline struct dentry *file_dentry(const struct file *f)
+{
+	return (f->f_path.dentry);
+}
+#endif /* HAVE_FILE_DENTRY */
+
+#ifdef HAVE_KUID_HELPERS
+static inline uid_t zfs_uid_read_impl(struct inode *ip)
+{
+#ifdef HAVE_SUPER_USER_NS
+	return (from_kuid(ip->i_sb->s_user_ns, ip->i_uid));
+#else
+	return (from_kuid(kcred->user_ns, ip->i_uid));
+#endif
+}
+
+static inline uid_t zfs_uid_read(struct inode *ip)
+{
+	return (zfs_uid_read_impl(ip));
+}
+
+static inline gid_t zfs_gid_read_impl(struct inode *ip)
+{
+#ifdef HAVE_SUPER_USER_NS
+	return (from_kgid(ip->i_sb->s_user_ns, ip->i_gid));
+#else
+	return (from_kgid(kcred->user_ns, ip->i_gid));
+#endif
+}
+
+static inline gid_t zfs_gid_read(struct inode *ip)
+{
+	return (zfs_gid_read_impl(ip));
+}
+
+static inline void zfs_uid_write(struct inode *ip, uid_t uid)
+{
+#ifdef HAVE_SUPER_USER_NS
+	ip->i_uid = make_kuid(ip->i_sb->s_user_ns, uid);
+#else
+	ip->i_uid = make_kuid(kcred->user_ns, uid);
+#endif
+}
+
+static inline void zfs_gid_write(struct inode *ip, gid_t gid)
+{
+#ifdef HAVE_SUPER_USER_NS
+	ip->i_gid = make_kgid(ip->i_sb->s_user_ns, gid);
+#else
+	ip->i_gid = make_kgid(kcred->user_ns, gid);
+#endif
+}
+
+#else
+static inline uid_t zfs_uid_read(struct inode *ip)
+{
+	return (ip->i_uid);
+}
+
+static inline gid_t zfs_gid_read(struct inode *ip)
+{
+	return (ip->i_gid);
+}
+
+static inline void zfs_uid_write(struct inode *ip, uid_t uid)
+{
+	ip->i_uid = uid;
+}
+
+static inline void zfs_gid_write(struct inode *ip, gid_t gid)
+{
+	ip->i_gid = gid;
+}
+#endif
+
+/*
+ * 2.6.38 API change
+ */
+#ifdef HAVE_FOLLOW_DOWN_ONE
+#define	zpl_follow_down_one(path)		follow_down_one(path)
+#define	zpl_follow_up(path)			follow_up(path)
+#else
+#define	zpl_follow_down_one(path)		follow_down(path)
+#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
+
+/*
+ * 4.16 API change
+ * Added iversion interface for managing inode version field.
+ */
+#ifdef HAVE_INODE_SET_IVERSION
+#include <linux/iversion.h>
+#else
+static inline void
+inode_set_iversion(struct inode *ip, u64 val)
+{
+	ip->i_version = val;
+}
+#endif
+
+/*
+ * Returns true when called in the context of a 32-bit system call.
+ */
+static inline int
+zpl_is_32bit_api(void)
+{
+#ifdef CONFIG_COMPAT
+#ifdef HAVE_IN_COMPAT_SYSCALL
+	return (in_compat_syscall());
+#else
+	return (is_compat_task());
+#endif
+#else
+	return (BITS_PER_LONG == 32);
+#endif
+}
+
+#endif /* _ZFS_VFS_H */

include/os/linux/kernel/linux/xattr_compat.h

@@ -0,0 +1,251 @@
+/*
+ * 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) 2011 Lawrence Livermore National Security, LLC.
+ */
+
+#ifndef _ZFS_XATTR_H
+#define	_ZFS_XATTR_H
+
+#include <linux/posix_acl_xattr.h>
+
+/*
+ * 2.6.35 API change,
+ * The const keyword was added to the 'struct xattr_handler' in the
+ * generic Linux super_block structure.  To handle this we define an
+ * appropriate xattr_handler_t typedef which can be used.  This was
+ * the preferred solution because it keeps the code clean and readable.
+ */
+#ifdef HAVE_CONST_XATTR_HANDLER
+typedef const struct xattr_handler	xattr_handler_t;
+#else
+typedef struct xattr_handler		xattr_handler_t;
+#endif
+
+/*
+ * 3.7 API change,
+ * Preferred XATTR_NAME_* definitions introduced, these are mapped to
+ * the previous definitions for older kernels.
+ */
+#ifndef XATTR_NAME_POSIX_ACL_DEFAULT
+#define	XATTR_NAME_POSIX_ACL_DEFAULT	POSIX_ACL_XATTR_DEFAULT
+#endif
+
+#ifndef XATTR_NAME_POSIX_ACL_ACCESS
+#define	XATTR_NAME_POSIX_ACL_ACCESS	POSIX_ACL_XATTR_ACCESS
+#endif
+
+/*
+ * 4.5 API change,
+ */
+#if defined(HAVE_XATTR_LIST_SIMPLE)
+#define	ZPL_XATTR_LIST_WRAPPER(fn)					\
+static bool								\
+fn(struct dentry *dentry)						\
+{									\
+	return (!!__ ## fn(dentry->d_inode, NULL, 0, NULL, 0));		\
+}
+/*
+ * 4.4 API change,
+ */
+#elif defined(HAVE_XATTR_LIST_DENTRY)
+#define	ZPL_XATTR_LIST_WRAPPER(fn)					\
+static size_t								\
+fn(struct dentry *dentry, char *list, size_t list_size,			\
+    const char *name, size_t name_len, int type)			\
+{									\
+	return (__ ## fn(dentry->d_inode,				\
+	    list, list_size, name, name_len));				\
+}
+/*
+ * 2.6.33 API change,
+ */
+#elif defined(HAVE_XATTR_LIST_HANDLER)
+#define	ZPL_XATTR_LIST_WRAPPER(fn)					\
+static size_t								\
+fn(const struct xattr_handler *handler, struct dentry *dentry,		\
+    char *list, size_t list_size, const char *name, size_t name_len)	\
+{									\
+	return (__ ## fn(dentry->d_inode,				\
+	    list, list_size, name, name_len));				\
+}
+/*
+ * 2.6.32 API
+ */
+#elif defined(HAVE_XATTR_LIST_INODE)
+#define	ZPL_XATTR_LIST_WRAPPER(fn)					\
+static size_t								\
+fn(struct inode *ip, char *list, size_t list_size,			\
+    const char *name, size_t name_len)					\
+{									\
+	return (__ ## fn(ip, list, list_size, name, name_len));		\
+}
+#endif
+
+/*
+ * 4.7 API change,
+ * The xattr_handler->get() callback was changed to take a both dentry and
+ * inode, because the dentry might not be attached to an inode yet.
+ */
+#if defined(HAVE_XATTR_GET_DENTRY_INODE)
+#define	ZPL_XATTR_GET_WRAPPER(fn)					\
+static int								\
+fn(const struct xattr_handler *handler, struct dentry *dentry,		\
+    struct inode *inode, const char *name, void *buffer, size_t size)	\
+{									\
+	return (__ ## fn(inode, name, buffer, size));			\
+}
+/*
+ * 4.4 API change,
+ * The xattr_handler->get() callback was changed to take a xattr_handler,
+ * and handler_flags argument was removed and should be accessed by
+ * handler->flags.
+ */
+#elif defined(HAVE_XATTR_GET_HANDLER)
+#define	ZPL_XATTR_GET_WRAPPER(fn)					\
+static int								\
+fn(const struct xattr_handler *handler, struct dentry *dentry,		\
+    const char *name, void *buffer, size_t size)			\
+{									\
+	return (__ ## fn(dentry->d_inode, name, buffer, size));		\
+}
+/*
+ * 2.6.33 API change,
+ * The xattr_handler->get() callback was changed to take a dentry
+ * instead of an inode, and a handler_flags argument was added.
+ */
+#elif defined(HAVE_XATTR_GET_DENTRY)
+#define	ZPL_XATTR_GET_WRAPPER(fn)					\
+static int								\
+fn(struct dentry *dentry, const char *name, void *buffer, size_t size,	\
+    int unused_handler_flags)						\
+{									\
+	return (__ ## fn(dentry->d_inode, name, buffer, size));		\
+}
+/*
+ * 2.6.32 API
+ */
+#elif defined(HAVE_XATTR_GET_INODE)
+#define	ZPL_XATTR_GET_WRAPPER(fn)					\
+static int								\
+fn(struct inode *ip, const char *name, void *buffer, size_t size)	\
+{									\
+	return (__ ## fn(ip, name, buffer, size));			\
+}
+#endif
+
+/*
+ * 4.7 API change,
+ * The xattr_handler->set() callback was changed to take a both dentry and
+ * inode, because the dentry might not be attached to an inode yet.
+ */
+#if defined(HAVE_XATTR_SET_DENTRY_INODE)
+#define	ZPL_XATTR_SET_WRAPPER(fn)					\
+static int								\
+fn(const struct xattr_handler *handler, struct dentry *dentry,		\
+    struct inode *inode, const char *name, const void *buffer,		\
+    size_t size, int flags)						\
+{									\
+	return (__ ## fn(inode, name, buffer, size, flags));		\
+}
+/*
+ * 4.4 API change,
+ * The xattr_handler->set() callback was changed to take a xattr_handler,
+ * and handler_flags argument was removed and should be accessed by
+ * handler->flags.
+ */
+#elif defined(HAVE_XATTR_SET_HANDLER)
+#define	ZPL_XATTR_SET_WRAPPER(fn)					\
+static int								\
+fn(const struct xattr_handler *handler, struct dentry *dentry,		\
+    const char *name, const void *buffer, size_t size, int flags)	\
+{									\
+	return (__ ## fn(dentry->d_inode, name, buffer, size, flags));	\
+}
+/*
+ * 2.6.33 API change,
+ * The xattr_handler->set() callback was changed to take a dentry
+ * instead of an inode, and a handler_flags argument was added.
+ */
+#elif defined(HAVE_XATTR_SET_DENTRY)
+#define	ZPL_XATTR_SET_WRAPPER(fn)					\
+static int								\
+fn(struct dentry *dentry, const char *name, const void *buffer,		\
+    size_t size, int flags, int unused_handler_flags)			\
+{									\
+	return (__ ## fn(dentry->d_inode, name, buffer, size, flags));	\
+}
+/*
+ * 2.6.32 API
+ */
+#elif defined(HAVE_XATTR_SET_INODE)
+#define	ZPL_XATTR_SET_WRAPPER(fn)					\
+static int								\
+fn(struct inode *ip, const char *name, const void *buffer,		\
+    size_t size, int flags)						\
+{									\
+	return (__ ## fn(ip, name, buffer, size, flags));		\
+}
+#endif
+
+#ifdef HAVE_6ARGS_SECURITY_INODE_INIT_SECURITY
+#define	zpl_security_inode_init_security(ip, dip, qstr, nm, val, len)	\
+	security_inode_init_security(ip, dip, qstr, nm, val, len)
+#else
+#define	zpl_security_inode_init_security(ip, dip, qstr, nm, val, len)	\
+	security_inode_init_security(ip, dip, nm, val, len)
+#endif /* HAVE_6ARGS_SECURITY_INODE_INIT_SECURITY */
+
+/*
+ * Linux 3.7 API change. posix_acl_{from,to}_xattr gained the user_ns
+ * parameter.  All callers are expected to pass the &init_user_ns which
+ * is available through the init credential (kcred).
+ */
+#ifdef HAVE_POSIX_ACL_FROM_XATTR_USERNS
+static inline struct posix_acl *
+zpl_acl_from_xattr(const void *value, int size)
+{
+	return (posix_acl_from_xattr(kcred->user_ns, value, size));
+}
+
+static inline int
+zpl_acl_to_xattr(struct posix_acl *acl, void *value, int size)
+{
+	return (posix_acl_to_xattr(kcred->user_ns, acl, value, size));
+}
+
+#else
+
+static inline struct posix_acl *
+zpl_acl_from_xattr(const void *value, int size)
+{
+	return (posix_acl_from_xattr(value, size));
+}
+
+static inline int
+zpl_acl_to_xattr(struct posix_acl *acl, void *value, int size)
+{
+	return (posix_acl_to_xattr(acl, value, size));
+}
+#endif /* HAVE_POSIX_ACL_FROM_XATTR_USERNS */
+
+#endif /* _ZFS_XATTR_H */