Linux 5.0 compat: SIMD compatibility

Restore the SIMD optimization for 4.19.38 LTS, 4.14.120 LTS,
and 5.0 and newer kernels.

This commit squashes the following commits from master in to
a single commit which can be applied to 0.8.2.

10fa254 - Linux 4.14, 4.19, 5.0+ compat: SIMD save/restore
b88ca2a - Enable SIMD for encryption
095b541 - Fix CONFIG_X86_DEBUG_FPU build failure
e5db313 - Linux 5.0 compat: SIMD compatibility

Reviewed-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
TEST_ZIMPORT_SKIP="yes"

cmd/ztest/ztest.c

@@ -107,6 +107,7 @@
 #include <sys/vdev_impl.h>
 #include <sys/vdev_file.h>
 #include <sys/vdev_initialize.h>
+#include <sys/vdev_raidz.h>
 #include <sys/vdev_trim.h>
 #include <sys/spa_impl.h>
 #include <sys/metaslab_impl.h>
@@ -7110,6 +7111,8 @@ ztest_run(ztest_shared_t *zs)
 	metaslab_preload_limit = ztest_random(20) + 1;
 	ztest_spa = spa;
 
+	VERIFY0(vdev_raidz_impl_set("cycle"));
+
 	dmu_objset_stats_t dds;
 	VERIFY0(ztest_dmu_objset_own(ztest_opts.zo_pool,
 	    DMU_OST_ANY, B_TRUE, B_TRUE, FTAG, &os));

config/kernel-fpu.m4

@@ -2,8 +2,9 @@ dnl #
 dnl # Handle differences in kernel FPU code.
 dnl #
 dnl # Kernel
-dnl # 5.0:	All kernel fpu functions are GPL only, so we can't use them.
-dnl #		(nothing defined)
+dnl # 5.0:	Wrappers have been introduced to save/restore the FPU state.
+dnl #		This change was made to the 4.19.38 and 4.14.120 LTS kernels.
+dnl #		HAVE_KERNEL_FPU_INTERNAL
 dnl #
 dnl # 4.2:	Use __kernel_fpu_{begin,end}()
 dnl #		HAVE_UNDERSCORE_KERNEL_FPU & KERNEL_EXPORTS_X86_FPU
@@ -12,7 +13,11 @@ dnl # Pre-4.2:	Use kernel_fpu_{begin,end}()
 dnl #		HAVE_KERNEL_FPU & KERNEL_EXPORTS_X86_FPU
 dnl #
 AC_DEFUN([ZFS_AC_KERNEL_FPU], [
-	AC_MSG_CHECKING([which kernel_fpu header to use])
+	dnl #
+	dnl # N.B. The header check is performed before all other checks since
+	dnl # it depends on HAVE_KERNEL_FPU_API_HEADER being set in confdefs.h.
+	dnl #
+	AC_MSG_CHECKING([whether fpu headers are available])
 	ZFS_LINUX_TRY_COMPILE([
 		#include <linux/module.h>
 		#include <asm/fpu/api.h>
@@ -25,9 +30,13 @@ AC_DEFUN([ZFS_AC_KERNEL_FPU], [
 		AC_MSG_RESULT(i387.h & xcr.h)
 	])
 
-	AC_MSG_CHECKING([which kernel_fpu function to use])
+	dnl #
+	dnl # Legacy kernel
+	dnl #
+	AC_MSG_CHECKING([whether kernel fpu is available])
 	ZFS_LINUX_TRY_COMPILE_SYMBOL([
 		#include <linux/module.h>
+		#include <linux/types.h>
 		#ifdef HAVE_KERNEL_FPU_API_HEADER
 		#include <asm/fpu/api.h>
 		#else
@@ -45,8 +54,12 @@ AC_DEFUN([ZFS_AC_KERNEL_FPU], [
 		AC_DEFINE(KERNEL_EXPORTS_X86_FPU, 1,
 		    [kernel exports FPU functions])
 	],[
+		dnl #
+		dnl # Linux 4.2 kernel
+		dnl #
 		ZFS_LINUX_TRY_COMPILE_SYMBOL([
 			#include <linux/module.h>
+			#include <linux/types.h>
 			#ifdef HAVE_KERNEL_FPU_API_HEADER
 			#include <asm/fpu/api.h>
 			#else
@@ -57,12 +70,60 @@ AC_DEFUN([ZFS_AC_KERNEL_FPU], [
 		],[
 			__kernel_fpu_begin();
 			__kernel_fpu_end();
-		], [__kernel_fpu_begin], [arch/x86/kernel/fpu/core.c arch/x86/kernel/i387.c], [
+		], [__kernel_fpu_begin],
+		[arch/x86/kernel/fpu/core.c arch/x86/kernel/i387.c], [
 			AC_MSG_RESULT(__kernel_fpu_*)
-			AC_DEFINE(HAVE_UNDERSCORE_KERNEL_FPU, 1, [kernel has __kernel_fpu_* functions])
-			AC_DEFINE(KERNEL_EXPORTS_X86_FPU, 1, [kernel exports FPU functions])
+			AC_DEFINE(HAVE_UNDERSCORE_KERNEL_FPU, 1,
+			    [kernel has __kernel_fpu_* functions])
+			AC_DEFINE(KERNEL_EXPORTS_X86_FPU, 1,
+			    [kernel exports FPU functions])
 		],[
-			AC_MSG_RESULT(not exported)
+			ZFS_LINUX_TRY_COMPILE([
+				#include <linux/module.h>
+
+				#if defined(__x86_64) || defined(__x86_64__) || \
+				    defined(__i386) || defined(__i386__)
+				#if !defined(__x86)
+				#define __x86
+				#endif
+				#endif
+
+				#if !defined(__x86)
+				#error Unsupported architecture
+				#endif
+
+				#include <linux/types.h>
+				#ifdef 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
+
+				#if !defined(XSTATE_XSAVE)
+				#error XSTATE_XSAVE not defined
+				#endif
+
+				#if !defined(XSTATE_XRESTORE)
+				#error XSTATE_XRESTORE not defined
+				#endif
+			],[
+				struct fpu *fpu = &current->thread.fpu;
+				union fpregs_state *st = &fpu->state;
+				struct fregs_state *fr __attribute__ ((unused)) =
+				    &st->fsave;
+				struct fxregs_state *fxr __attribute__ ((unused)) =
+				    &st->fxsave;
+				struct xregs_state *xr __attribute__ ((unused)) =
+				    &st->xsave;
+			], [
+				AC_MSG_RESULT(internal)
+				AC_DEFINE(HAVE_KERNEL_FPU_INTERNAL, 1,
+				    [kernel fpu internal])
+			],[
+				AC_MSG_RESULT(unavailable)
+			])
 		])
 	])
 ])

include/linux/Makefile.am

@@ -7,6 +7,7 @@ KERNEL_H = \
 	$(top_srcdir)/include/linux/blkdev_compat.h \
 	$(top_srcdir)/include/linux/utsname_compat.h \
 	$(top_srcdir)/include/linux/kmap_compat.h \
+	$(top_srcdir)/include/linux/simd.h \
 	$(top_srcdir)/include/linux/simd_x86.h \
 	$(top_srcdir)/include/linux/simd_aarch64.h \
 	$(top_srcdir)/include/linux/mod_compat.h \

include/linux/simd.h

@@ -0,0 +1,42 @@
+/*
+ * 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 _SIMD_H
+#define	_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_begin()		do {} while (0)
+#define	kfpu_end()		do {} while (0)
+#define	kfpu_init()		0
+#define	kfpu_fini()		((void) 0)
+
+#endif
+#endif /* _SIMD_H */

include/linux/simd_aarch64.h

@@ -27,9 +27,10 @@
  *
  * Kernel fpu methods:
  *	kfpu_allowed()
- *	kfpu_initialize()
  *	kfpu_begin()
  *	kfpu_end()
+ *	kfpu_init()
+ *	kfpu_fini()
  */
 
 #ifndef _SIMD_AARCH64_H
@@ -43,20 +44,20 @@
 
 #if defined(_KERNEL)
 #include <asm/neon.h>
-#define	kfpu_begin()		\
-{					\
-	kernel_neon_begin();		\
-}
-#define	kfpu_end()			\
-{					\
-	kernel_neon_end();		\
-}
+#define	kfpu_allowed()		1
+#define	kfpu_begin()		kernel_neon_begin()
+#define	kfpu_end()		kernel_neon_end()
+#define	kfpu_init()		0
+#define	kfpu_fini()		((void) 0)
 #else
 /*
  * fpu dummy methods for userspace
  */
-#define	kfpu_begin() 	do {} while (0)
-#define	kfpu_end() 		do {} while (0)
+#define	kfpu_allowed()		1
+#define	kfpu_begin()		do {} while (0)
+#define	kfpu_end()		do {} while (0)
+#define	kfpu_init()		0
+#define	kfpu_fini()		((void) 0)
 #endif /* defined(_KERNEL) */
 
 #endif /* __aarch64__ */