Merge tag 'md/4.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md

Pull MD updates from Shaohua Li:
 "This update includes:

   - new AVX512 instruction based raid6 gen/recovery algorithm

   - a couple of md-cluster related bug fixes

   - fix a potential deadlock

   - set nonrotational bit for raid array with SSD

   - set correct max_hw_sectors for raid5/6, which hopefuly can improve
     performance a little bit

   - other minor fixes"

* tag 'md/4.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md:
  md: set rotational bit
  raid6/test/test.c: bug fix: Specify aligned(alignment) attributes to the char arrays
  raid5: handle register_shrinker failure
  raid5: fix to detect failure of register_shrinker
  md: fix a potential deadlock
  md/bitmap: fix wrong cleanup
  raid5: allow arbitrary max_hw_sectors
  lib/raid6: Add AVX512 optimized xor_syndrome functions
  lib/raid6/test/Makefile: Add avx512 gen_syndrome and recovery functions
  lib/raid6: Add AVX512 optimized recovery functions
  lib/raid6: Add AVX512 optimized gen_syndrome functions
  md-cluster: make resync lock also could be interruptted
  md-cluster: introduce dlm_lock_sync_interruptible to fix tasks hang
  md-cluster: convert the completion to wait queue
  md-cluster: protect md_find_rdev_nr_rcu with rcu lock
  md-cluster: clean related infos of cluster
  md: changes for MD_STILL_CLOSED flag
  md-cluster: remove some unnecessary dlm_unlock_sync
  md-cluster: use FORCEUNLOCK in lockres_free
  md-cluster: call md_kick_rdev_from_array once ack failed

arch/x86/Makefile

@@ -163,11 +163,12 @@ asinstr += $(call as-instr,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=1)
 asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1)
 avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1)
 avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1)
+avx512_instr :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,-DCONFIG_AS_AVX512=1)
 sha1_ni_instr :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA1_NI=1)
 sha256_ni_instr :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA256_NI=1)
 
-KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(sha1_ni_instr) $(sha256_ni_instr)
-KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(sha1_ni_instr) $(sha256_ni_instr)
+KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr)
+KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(avx512_instr) $(sha1_ni_instr) $(sha256_ni_instr)
 
 LDFLAGS := -m elf_$(UTS_MACHINE)
 

drivers/md/bitmap.c

@@ -1903,10 +1903,8 @@ int bitmap_copy_from_slot(struct mddev *mddev, int slot,
 	struct bitmap_counts *counts;
 	struct bitmap *bitmap = bitmap_create(mddev, slot);
 
-	if (IS_ERR(bitmap)) {
-		bitmap_free(bitmap);
+	if (IS_ERR(bitmap))
 		return PTR_ERR(bitmap);
-	}
 
 	rv = bitmap_init_from_disk(bitmap, 0);
 	if (rv)

drivers/md/md-cluster.c

@@ -10,6 +10,7 @@
 
 
 #include <linux/module.h>
+#include <linux/kthread.h>
 #include <linux/dlm.h>
 #include <linux/sched.h>
 #include <linux/raid/md_p.h>
@@ -25,7 +26,8 @@ struct dlm_lock_resource {
 	struct dlm_lksb lksb;
 	char *name; /* lock name. */
 	uint32_t flags; /* flags to pass to dlm_lock() */
-	struct completion completion; /* completion for synchronized locking */
+	wait_queue_head_t sync_locking; /* wait queue for synchronized locking */
+	bool sync_locking_done;
 	void (*bast)(void *arg, int mode); /* blocking AST function pointer*/
 	struct mddev *mddev; /* pointing back to mddev. */
 	int mode;
@@ -118,7 +120,8 @@ static void sync_ast(void *arg)
 	struct dlm_lock_resource *res;
 
 	res = arg;
-	complete(&res->completion);
+	res->sync_locking_done = true;
+	wake_up(&res->sync_locking);
 }
 
 static int dlm_lock_sync(struct dlm_lock_resource *res, int mode)
@@ -130,7 +133,8 @@ static int dlm_lock_sync(struct dlm_lock_resource *res, int mode)
 			0, sync_ast, res, res->bast);
 	if (ret)
 		return ret;
-	wait_for_completion(&res->completion);
+	wait_event(res->sync_locking, res->sync_locking_done);
+	res->sync_locking_done = false;
 	if (res->lksb.sb_status == 0)
 		res->mode = mode;
 	return res->lksb.sb_status;
@@ -141,6 +145,44 @@ static int dlm_unlock_sync(struct dlm_lock_resource *res)
 	return dlm_lock_sync(res, DLM_LOCK_NL);
 }
 
+/*
+ * An variation of dlm_lock_sync, which make lock request could
+ * be interrupted
+ */
+static int dlm_lock_sync_interruptible(struct dlm_lock_resource *res, int mode,
+				       struct mddev *mddev)
+{
+	int ret = 0;
+
+	ret = dlm_lock(res->ls, mode, &res->lksb,
+			res->flags, res->name, strlen(res->name),
+			0, sync_ast, res, res->bast);
+	if (ret)
+		return ret;
+
+	wait_event(res->sync_locking, res->sync_locking_done
+				      || kthread_should_stop()
+				      || test_bit(MD_CLOSING, &mddev->flags));
+	if (!res->sync_locking_done) {
+		/*
+		 * the convert queue contains the lock request when request is
+		 * interrupted, and sync_ast could still be run, so need to
+		 * cancel the request and reset completion
+		 */
+		ret = dlm_unlock(res->ls, res->lksb.sb_lkid, DLM_LKF_CANCEL,
+			&res->lksb, res);
+		res->sync_locking_done = false;
+		if (unlikely(ret != 0))
+			pr_info("failed to cancel previous lock request "
+				 "%s return %d\n", res->name, ret);
+		return -EPERM;
+	} else
+		res->sync_locking_done = false;
+	if (res->lksb.sb_status == 0)
+		res->mode = mode;
+	return res->lksb.sb_status;
+}
+
 static struct dlm_lock_resource *lockres_init(struct mddev *mddev,
 		char *name, void (*bastfn)(void *arg, int mode), int with_lvb)
 {
@@ -151,7 +193,8 @@ static struct dlm_lock_resource *lockres_init(struct mddev *mddev,
 	res = kzalloc(sizeof(struct dlm_lock_resource), GFP_KERNEL);
 	if (!res)
 		return NULL;
-	init_completion(&res->completion);
+	init_waitqueue_head(&res->sync_locking);
+	res->sync_locking_done = false;
 	res->ls = cinfo->lockspace;
 	res->mddev = mddev;
 	res->mode = DLM_LOCK_IV;
@@ -194,25 +237,21 @@ static struct dlm_lock_resource *lockres_init(struct mddev *mddev,
 
 static void lockres_free(struct dlm_lock_resource *res)
 {
-	int ret;
+	int ret = 0;
 
 	if (!res)
 		return;
 
-	/* cancel a lock request or a conversion request that is blocked */
-	res->flags |= DLM_LKF_CANCEL;
-retry:
-	ret = dlm_unlock(res->ls, res->lksb.sb_lkid, 0, &res->lksb, res);
-	if (unlikely(ret != 0)) {
-		pr_info("%s: failed to unlock %s return %d\n", __func__, res->name, ret);
-
-		/* if a lock conversion is cancelled, then the lock is put
-		 * back to grant queue, need to ensure it is unlocked */
-		if (ret == -DLM_ECANCEL)
-			goto retry;
-	}
-	res->flags &= ~DLM_LKF_CANCEL;
-	wait_for_completion(&res->completion);
+	/*
+	 * use FORCEUNLOCK flag, so we can unlock even the lock is on the
+	 * waiting or convert queue
+	 */
+	ret = dlm_unlock(res->ls, res->lksb.sb_lkid, DLM_LKF_FORCEUNLOCK,
+		&res->lksb, res);
+	if (unlikely(ret != 0))
+		pr_err("failed to unlock %s return %d\n", res->name, ret);
+	else
+		wait_event(res->sync_locking, res->sync_locking_done);
 
 	kfree(res->name);
 	kfree(res->lksb.sb_lvbptr);
@@ -279,7 +318,7 @@ static void recover_bitmaps(struct md_thread *thread)
 			goto clear_bit;
 		}
 
-		ret = dlm_lock_sync(bm_lockres, DLM_LOCK_PW);
+		ret = dlm_lock_sync_interruptible(bm_lockres, DLM_LOCK_PW, mddev);
 		if (ret) {
 			pr_err("md-cluster: Could not DLM lock %s: %d\n",
 					str, ret);
@@ -288,7 +327,7 @@ static void recover_bitmaps(struct md_thread *thread)
 		ret = bitmap_copy_from_slot(mddev, slot, &lo, &hi, true);
 		if (ret) {
 			pr_err("md-cluster: Could not copy data from bitmap %d\n", slot);
-			goto dlm_unlock;
+			goto clear_bit;
 		}
 		if (hi > 0) {
 			if (lo < mddev->recovery_cp)
@@ -300,8 +339,6 @@ static void recover_bitmaps(struct md_thread *thread)
 			    md_wakeup_thread(mddev->thread);
 			}
 		}
-dlm_unlock:
-		dlm_unlock_sync(bm_lockres);
 clear_bit:
 		lockres_free(bm_lockres);
 		clear_bit(slot, &cinfo->recovery_map);
@@ -495,9 +532,10 @@ static void process_metadata_update(struct mddev *mddev, struct cluster_msg *msg
 
 static void process_remove_disk(struct mddev *mddev, struct cluster_msg *msg)
 {
-	struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev,
-						   le32_to_cpu(msg->raid_slot));
+	struct md_rdev *rdev;
 
+	rcu_read_lock();
+	rdev = md_find_rdev_nr_rcu(mddev, le32_to_cpu(msg->raid_slot));
 	if (rdev) {
 		set_bit(ClusterRemove, &rdev->flags);
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
@@ -506,18 +544,21 @@ static void process_remove_disk(struct mddev *mddev, struct cluster_msg *msg)
 	else
 		pr_warn("%s: %d Could not find disk(%d) to REMOVE\n",
 			__func__, __LINE__, le32_to_cpu(msg->raid_slot));
+	rcu_read_unlock();
 }
 
 static void process_readd_disk(struct mddev *mddev, struct cluster_msg *msg)
 {
-	struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev,
-						   le32_to_cpu(msg->raid_slot));
+	struct md_rdev *rdev;
 
+	rcu_read_lock();
+	rdev = md_find_rdev_nr_rcu(mddev, le32_to_cpu(msg->raid_slot));
 	if (rdev && test_bit(Faulty, &rdev->flags))
 		clear_bit(Faulty, &rdev->flags);
 	else
 		pr_warn("%s: %d Could not find disk(%d) which is faulty",
 			__func__, __LINE__, le32_to_cpu(msg->raid_slot));
+	rcu_read_unlock();
 }
 
 static int process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
@@ -770,7 +811,6 @@ static int gather_all_resync_info(struct mddev *mddev, int total_slots)
 			md_check_recovery(mddev);
 		}
 
-		dlm_unlock_sync(bm_lockres);
 		lockres_free(bm_lockres);
 	}
 out:
@@ -1006,7 +1046,7 @@ static void metadata_update_cancel(struct mddev *mddev)
 static int resync_start(struct mddev *mddev)
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
-	return dlm_lock_sync(cinfo->resync_lockres, DLM_LOCK_EX);
+	return dlm_lock_sync_interruptible(cinfo->resync_lockres, DLM_LOCK_EX, mddev);
 }
 
 static int resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi)
@@ -1186,7 +1226,6 @@ static void unlock_all_bitmaps(struct mddev *mddev)
 	if (cinfo->other_bitmap_lockres) {
 		for (i = 0; i < mddev->bitmap_info.nodes - 1; i++) {
 			if (cinfo->other_bitmap_lockres[i]) {
-				dlm_unlock_sync(cinfo->other_bitmap_lockres[i]);
 				lockres_free(cinfo->other_bitmap_lockres[i]);
 			}
 		}

drivers/md/md.c

@@ -5297,6 +5297,21 @@ int md_run(struct mddev *mddev)
 		return err;
 	}
 	if (mddev->queue) {
+		bool nonrot = true;
+
+		rdev_for_each(rdev, mddev) {
+			if (rdev->raid_disk >= 0 &&
+			    !blk_queue_nonrot(bdev_get_queue(rdev->bdev))) {
+				nonrot = false;
+				break;
+			}
+		}
+		if (mddev->degraded)
+			nonrot = false;
+		if (nonrot)
+			queue_flag_set_unlocked(QUEUE_FLAG_NONROT, mddev->queue);
+		else
+			queue_flag_clear_unlocked(QUEUE_FLAG_NONROT, mddev->queue);
 		mddev->queue->backing_dev_info.congested_data = mddev;
 		mddev->queue->backing_dev_info.congested_fn = md_congested;
 	}
@@ -5454,12 +5469,14 @@ static void md_clean(struct mddev *mddev)
 	mddev->degraded = 0;
 	mddev->safemode = 0;
 	mddev->private = NULL;
+	mddev->cluster_info = NULL;
 	mddev->bitmap_info.offset = 0;
 	mddev->bitmap_info.default_offset = 0;
 	mddev->bitmap_info.default_space = 0;
 	mddev->bitmap_info.chunksize = 0;
 	mddev->bitmap_info.daemon_sleep = 0;
 	mddev->bitmap_info.max_write_behind = 0;
+	mddev->bitmap_info.nodes = 0;
 }
 
 static void __md_stop_writes(struct mddev *mddev)
@@ -5573,8 +5590,7 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 	mutex_lock(&mddev->open_mutex);
 	if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) ||
 	    mddev->sync_thread ||
-	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
-	    (bdev && !test_bit(MD_STILL_CLOSED, &mddev->flags))) {
+	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
 		printk("md: %s still in use.\n",mdname(mddev));
 		if (did_freeze) {
 			clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
@@ -5636,8 +5652,7 @@ static int do_md_stop(struct mddev *mddev, int mode,
 	if ((mddev->pers && atomic_read(&mddev->openers) > !!bdev) ||
 	    mddev->sysfs_active ||
 	    mddev->sync_thread ||
-	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
-	    (bdev && !test_bit(MD_STILL_CLOSED, &mddev->flags))) {
+	    test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) {
 		printk("md: %s still in use.\n",mdname(mddev));
 		mutex_unlock(&mddev->open_mutex);
 		if (did_freeze) {
@@ -6101,9 +6116,14 @@ static int add_new_disk(struct mddev *mddev, mdu_disk_info_t *info)
 			export_rdev(rdev);
 
 		if (mddev_is_clustered(mddev)) {
-			if (info->state & (1 << MD_DISK_CANDIDATE))
-				md_cluster_ops->new_disk_ack(mddev, (err == 0));
-			else {
+			if (info->state & (1 << MD_DISK_CANDIDATE)) {
+				if (!err) {
+					err = md_cluster_ops->new_disk_ack(mddev,
+						err == 0);
+					if (err)
+						md_kick_rdev_from_array(rdev);
+				}
+			} else {
 				if (err)
 					md_cluster_ops->add_new_disk_cancel(mddev);
 				else
@@ -6821,7 +6841,7 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 			err = -EBUSY;
 			goto out;
 		}
-		set_bit(MD_STILL_CLOSED, &mddev->flags);
+		set_bit(MD_CLOSING, &mddev->flags);
 		mutex_unlock(&mddev->open_mutex);
 		sync_blockdev(bdev);
 	}
@@ -7070,9 +7090,13 @@ static int md_open(struct block_device *bdev, fmode_t mode)
 	if ((err = mutex_lock_interruptible(&mddev->open_mutex)))
 		goto out;
 
+	if (test_bit(MD_CLOSING, &mddev->flags)) {
+		mutex_unlock(&mddev->open_mutex);
+		return -ENODEV;
+	}
+
 	err = 0;
 	atomic_inc(&mddev->openers);
-	clear_bit(MD_STILL_CLOSED, &mddev->flags);
 	mutex_unlock(&mddev->open_mutex);
 
 	check_disk_change(bdev);
@@ -8873,7 +8897,9 @@ static void autostart_arrays(int part)
 		list_del(&node_detected_dev->list);
 		dev = node_detected_dev->dev;
 		kfree(node_detected_dev);
+		mutex_unlock(&detected_devices_mutex);
 		rdev = md_import_device(dev,0, 90);
+		mutex_lock(&detected_devices_mutex);
 		if (IS_ERR(rdev))
 			continue;
 

drivers/md/md.h

@@ -201,9 +201,8 @@ struct mddev {
 #define MD_CHANGE_PENDING 2	/* switch from 'clean' to 'active' in progress */
 #define MD_UPDATE_SB_FLAGS (1 | 2 | 4)	/* If these are set, md_update_sb needed */
 #define MD_ARRAY_FIRST_USE 3    /* First use of array, needs initialization */
-#define MD_STILL_CLOSED	4	/* If set, then array has not been opened since
-				 * md_ioctl checked on it.
-				 */
+#define MD_CLOSING	4	/* If set, we are closing the array, do not open
+				 * it then */
 #define MD_JOURNAL_CLEAN 5	/* A raid with journal is already clean */
 #define MD_HAS_JOURNAL	6	/* The raid array has journal feature set */
 #define MD_RELOAD_SB	7	/* Reload the superblock because another node

drivers/md/raid5.c

@@ -6370,7 +6370,7 @@ static void free_conf(struct r5conf *conf)
 {
 	if (conf->log)
 		r5l_exit_log(conf->log);
-	if (conf->shrinker.seeks)
+	if (conf->shrinker.nr_deferred)
 		unregister_shrinker(&conf->shrinker);
 
 	free_thread_groups(conf);
@@ -6632,7 +6632,12 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	conf->shrinker.count_objects = raid5_cache_count;
 	conf->shrinker.batch = 128;
 	conf->shrinker.flags = 0;
-	register_shrinker(&conf->shrinker);
+	if (register_shrinker(&conf->shrinker)) {
+		printk(KERN_ERR
+		       "md/raid:%s: couldn't register shrinker.\n",
+		       mdname(mddev));
+		goto abort;
+	}
 
 	sprintf(pers_name, "raid%d", mddev->new_level);
 	conf->thread = md_register_thread(raid5d, mddev, pers_name);
@@ -7028,6 +7033,8 @@ static int raid5_run(struct mddev *mddev)
 		else
 			queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD,
 						mddev->queue);
+
+		blk_queue_max_hw_sectors(mddev->queue, UINT_MAX);
 	}
 
 	if (journal_dev) {

include/linux/raid/pq.h

@@ -102,6 +102,9 @@ extern const struct raid6_calls raid6_altivec8;
 extern const struct raid6_calls raid6_avx2x1;
 extern const struct raid6_calls raid6_avx2x2;
 extern const struct raid6_calls raid6_avx2x4;
+extern const struct raid6_calls raid6_avx512x1;
+extern const struct raid6_calls raid6_avx512x2;
+extern const struct raid6_calls raid6_avx512x4;
 extern const struct raid6_calls raid6_tilegx8;
 extern const struct raid6_calls raid6_s390vx8;
 
@@ -116,6 +119,7 @@ struct raid6_recov_calls {
 extern const struct raid6_recov_calls raid6_recov_intx1;
 extern const struct raid6_recov_calls raid6_recov_ssse3;
 extern const struct raid6_recov_calls raid6_recov_avx2;
+extern const struct raid6_recov_calls raid6_recov_avx512;
 extern const struct raid6_recov_calls raid6_recov_s390xc;
 
 extern const struct raid6_calls raid6_neonx1;

lib/raid6/Makefile

@@ -3,7 +3,7 @@ obj-$(CONFIG_RAID6_PQ)	+= raid6_pq.o
 raid6_pq-y	+= algos.o recov.o tables.o int1.o int2.o int4.o \
 		   int8.o int16.o int32.o
 
-raid6_pq-$(CONFIG_X86) += recov_ssse3.o recov_avx2.o mmx.o sse1.o sse2.o avx2.o
+raid6_pq-$(CONFIG_X86) += recov_ssse3.o recov_avx2.o mmx.o sse1.o sse2.o avx2.o avx512.o recov_avx512.o
 raid6_pq-$(CONFIG_ALTIVEC) += altivec1.o altivec2.o altivec4.o altivec8.o
 raid6_pq-$(CONFIG_KERNEL_MODE_NEON) += neon.o neon1.o neon2.o neon4.o neon8.o
 raid6_pq-$(CONFIG_TILEGX) += tilegx8.o

lib/raid6/algos.c

@@ -49,6 +49,10 @@ const struct raid6_calls * const raid6_algos[] = {
 	&raid6_avx2x1,
 	&raid6_avx2x2,
 #endif
+#ifdef CONFIG_AS_AVX512
+	&raid6_avx512x1,
+	&raid6_avx512x2,
+#endif
 #endif
 #if defined(__x86_64__) && !defined(__arch_um__)
 	&raid6_sse2x1,
@@ -59,6 +63,11 @@ const struct raid6_calls * const raid6_algos[] = {
 	&raid6_avx2x2,
 	&raid6_avx2x4,
 #endif
+#ifdef CONFIG_AS_AVX512
+	&raid6_avx512x1,
+	&raid6_avx512x2,
+	&raid6_avx512x4,
+#endif
 #endif
 #ifdef CONFIG_ALTIVEC
 	&raid6_altivec1,
@@ -92,6 +101,9 @@ void (*raid6_datap_recov)(int, size_t, int, void **);
 EXPORT_SYMBOL_GPL(raid6_datap_recov);
 
 const struct raid6_recov_calls *const raid6_recov_algos[] = {
+#ifdef CONFIG_AS_AVX512
+	&raid6_recov_avx512,
+#endif
 #ifdef CONFIG_AS_AVX2
 	&raid6_recov_avx2,
 #endif

lib/raid6/avx512.c

+/* -*- linux-c -*- --------------------------------------------------------
+ *
+ *   Copyright (C) 2016 Intel Corporation
+ *
+ *   Author: Gayatri Kammela <gayatri.kammela@intel.com>
+ *   Author: Megha Dey <megha.dey@linux.intel.com>
+ *
+ *   Based on avx2.c: Copyright 2012 Yuanhan Liu All Rights Reserved
+ *   Based on sse2.c: Copyright 2002 H. Peter Anvin - All Rights Reserved
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation, Inc., 53 Temple Place Ste 330,
+ *   Boston MA 02111-1307, USA; either version 2 of the License, or
+ *   (at your option) any later version; incorporated herein by reference.
+ *
+ * -----------------------------------------------------------------------
+ */
+
+/*
+ * AVX512 implementation of RAID-6 syndrome functions
+ *
+ */
+
+#ifdef CONFIG_AS_AVX512
+
+#include <linux/raid/pq.h>
+#include "x86.h"
+
+static const struct raid6_avx512_constants {
+	u64 x1d[8];
+} raid6_avx512_constants __aligned(512) = {
+	{ 0x1d1d1d1d1d1d1d1dULL, 0x1d1d1d1d1d1d1d1dULL,
+	  0x1d1d1d1d1d1d1d1dULL, 0x1d1d1d1d1d1d1d1dULL,
+	  0x1d1d1d1d1d1d1d1dULL, 0x1d1d1d1d1d1d1d1dULL,
+	  0x1d1d1d1d1d1d1d1dULL, 0x1d1d1d1d1d1d1d1dULL,},
+};
+
+static int raid6_have_avx512(void)
+{
+	return boot_cpu_has(X86_FEATURE_AVX2) &&
+		boot_cpu_has(X86_FEATURE_AVX) &&
+		boot_cpu_has(X86_FEATURE_AVX512F) &&
+		boot_cpu_has(X86_FEATURE_AVX512BW) &&
+		boot_cpu_has(X86_FEATURE_AVX512VL) &&
+		boot_cpu_has(X86_FEATURE_AVX512DQ);
+}
+
+static void raid6_avx5121_gen_syndrome(int disks, size_t bytes, void **ptrs)
+{
+	u8 **dptr = (u8 **)ptrs;
+	u8 *p, *q;
+	int d, z, z0;
+
+	z0 = disks - 3;         /* Highest data disk */
+	p = dptr[z0+1];         /* XOR parity */
+	q = dptr[z0+2];         /* RS syndrome */
+
+	kernel_fpu_begin();
+
+	asm volatile("vmovdqa64 %0,%%zmm0\n\t"
+		     "vpxorq %%zmm1,%%zmm1,%%zmm1" /* Zero temp */
+		     :
+		     : "m" (raid6_avx512_constants.x1d[0]));
+
+	for (d = 0; d < bytes; d += 64) {
+		asm volatile("prefetchnta %0\n\t"
+			     "vmovdqa64 %0,%%zmm2\n\t"     /* P[0] */
+			     "prefetchnta %1\n\t"
+			     "vmovdqa64 %%zmm2,%%zmm4\n\t" /* Q[0] */
+			     "vmovdqa64 %1,%%zmm6"
+			     :
+			     : "m" (dptr[z0][d]), "m" (dptr[z0-1][d]));
+		for (z = z0-2; z >= 0; z--) {
+			asm volatile("prefetchnta %0\n\t"
+				     "vpcmpgtb %%zmm4,%%zmm1,%%k1\n\t"
+				     "vpmovm2b %%k1,%%zmm5\n\t"
+				     "vpaddb %%zmm4,%%zmm4,%%zmm4\n\t"
+				     "vpandq %%zmm0,%%zmm5,%%zmm5\n\t"
+				     "vpxorq %%zmm5,%%zmm4,%%zmm4\n\t"
+				     "vpxorq %%zmm6,%%zmm2,%%zmm2\n\t"
+				     "vpxorq %%zmm6,%%zmm4,%%zmm4\n\t"
+				     "vmovdqa64 %0,%%zmm6"
+				     :
+				     : "m" (dptr[z][d]));
+		}
+		asm volatile("vpcmpgtb %%zmm4,%%zmm1,%%k1\n\t"
+			     "vpmovm2b %%k1,%%zmm5\n\t"
+			     "vpaddb %%zmm4,%%zmm4,%%zmm4\n\t"
+			     "vpandq %%zmm0,%%zmm5,%%zmm5\n\t"
+			     "vpxorq %%zmm5,%%zmm4,%%zmm4\n\t"
+			     "vpxorq %%zmm6,%%zmm2,%%zmm2\n\t"
+			     "vpxorq %%zmm6,%%zmm4,%%zmm4\n\t"
+			     "vmovntdq %%zmm2,%0\n\t"
+			     "vpxorq %%zmm2,%%zmm2,%%zmm2\n\t"
+			     "vmovntdq %%zmm4,%1\n\t"
+			     "vpxorq %%zmm4,%%zmm4,%%zmm4"
+			     :
+			     : "m" (p[d]), "m" (q[d]));
+	}
+
+	asm volatile("sfence" : : : "memory");
+	kernel_fpu_end();
+}
+
+static void raid6_avx5121_xor_syndrome(int disks, int start, int stop,
+				       size_t bytes, void **ptrs)
+{
+	u8 **dptr = (u8 **)ptrs;
+	u8 *p, *q;
+	int d, z, z0;
+
+	z0 = stop;		/* P/Q right side optimization */
+	p = dptr[disks-2];	/* XOR parity */
+	q = dptr[disks-1];	/* RS syndrome */
+
+	kernel_fpu_begin();
+
+	asm volatile("vmovdqa64 %0,%%zmm0"
+		     : : "m" (raid6_avx512_constants.x1d[0]));
+
+	for (d = 0 ; d < bytes ; d += 64) {
+		asm volatile("vmovdqa64 %0,%%zmm4\n\t"
+			     "vmovdqa64 %1,%%zmm2\n\t"
+			     "vpxorq %%zmm4,%%zmm2,%%zmm2"
+			     :
+			     : "m" (dptr[z0][d]),  "m" (p[d]));
+		/* P/Q data pages */
+		for (z = z0-1 ; z >= start ; z--) {
+			asm volatile("vpxorq %%zmm5,%%zmm5,%%zmm5\n\t"
+				     "vpcmpgtb %%zmm4,%%zmm5,%%k1\n\t"
+				     "vpmovm2b %%k1,%%zmm5\n\t"
+				     "vpaddb %%zmm4,%%zmm4,%%zmm4\n\t"
+				     "vpandq %%zmm0,%%zmm5,%%zmm5\n\t"
+				     "vpxorq %%zmm5,%%zmm4,%%zmm4\n\t"
+				     "vmovdqa64 %0,%%zmm5\n\t"
+				     "vpxorq %%zmm5,%%zmm2,%%zmm2\n\t"
+				     "vpxorq %%zmm5,%%zmm4,%%zmm4"
+				     :
+				     : "m" (dptr[z][d]));
+		}
+		/* P/Q left side optimization */
+		for (z = start-1 ; z >= 0 ; z--) {
+			asm volatile("vpxorq %%zmm5,%%zmm5,%%zmm5\n\t"
+				     "vpcmpgtb %%zmm4,%%zmm5,%%k1\n\t"
+				     "vpmovm2b %%k1,%%zmm5\n\t"
+				     "vpaddb %%zmm4,%%zmm4,%%zmm4\n\t"
+				     "vpandq %%zmm0,%%zmm5,%%zmm5\n\t"
+				     "vpxorq %%zmm5,%%zmm4,%%zmm4"
+				     :
+				     : );
+		}
+		asm volatile("vpxorq %0,%%zmm4,%%zmm4\n\t"
+		/* Don't use movntdq for r/w memory area < cache line */
+			     "vmovdqa64 %%zmm4,%0\n\t"
+			     "vmovdqa64 %%zmm2,%1"
+			     :
+			     : "m" (q[d]), "m" (p[d]));
+	}
+
+	asm volatile("sfence" : : : "memory");
+	kernel_fpu_end();
+}
+
+const struct raid6_calls raid6_avx512x1 = {
+	raid6_avx5121_gen_syndrome,
+	raid6_avx5121_xor_syndrome,
+	raid6_have_avx512,
+	"avx512x1",
+	1                       /* Has cache hints */
+};
+
+/*
+ * Unrolled-by-2 AVX512 implementation
+ */
+static void raid6_avx5122_gen_syndrome(int disks, size_t bytes, void **ptrs)
+{
+	u8 **dptr = (u8 **)ptrs;
+	u8 *p, *q;
+	int d, z, z0;
+
+	z0 = disks - 3;         /* Highest data disk */
+	p = dptr[z0+1];         /* XOR parity */
+	q = dptr[z0+2];         /* RS syndrome */
+
+	kernel_fpu_begin();
+
+	asm volatile("vmovdqa64 %0,%%zmm0\n\t"
+		     "vpxorq %%zmm1,%%zmm1,%%zmm1" /* Zero temp */
+		     :
+		     : "m" (raid6_avx512_constants.x1d[0]));
+
+	/* We uniformly assume a single prefetch covers at least 64 bytes */
+	for (d = 0; d < bytes; d += 128) {
+		asm volatile("prefetchnta %0\n\t"
+			     "prefetchnta %1\n\t"
+			     "vmovdqa64 %0,%%zmm2\n\t"      /* P[0] */
+			     "vmovdqa64 %1,%%zmm3\n\t"      /* P[1] */
+			     "vmovdqa64 %%zmm2,%%zmm4\n\t"  /* Q[0] */
+			     "vmovdqa64 %%zmm3,%%zmm6"      /* Q[1] */
+			     :
+			     : "m" (dptr[z0][d]), "m" (dptr[z0][d+64]));
+		for (z = z0-1; z >= 0; z--) {
+			asm volatile("prefetchnta %0\n\t"
+				     "prefetchnta %1\n\t"
+				     "vpcmpgtb %%zmm4,%%zmm1,%%k1\n\t"
+				     "vpcmpgtb %%zmm6,%%zmm1,%%k2\n\t"
+				     "vpmovm2b %%k1,%%zmm5\n\t"
+				     "vpmovm2b %%k2,%%zmm7\n\t"
+				     "vpaddb %%zmm4,%%zmm4,%%zmm4\n\t"
+				     "vpaddb %%zmm6,%%zmm6,%%zmm6\n\t"
+				     "vpandq %%zmm0,%%zmm5,%%zmm5\n\t"
+				     "vpandq %%zmm0,%%zmm7,%%zmm7\n\t"
+				     "vpxorq %%zmm5,%%zmm4,%%zmm4\n\t"
+				     "vpxorq %%zmm7,%%zmm6,%%zmm6\n\t"
+				     "vmovdqa64 %0,%%zmm5\n\t"
+				     "vmovdqa64 %1,%%zmm7\n\t"
+				     "vpxorq %%zmm5,%%zmm2,%%zmm2\n\t"
+				     "vpxorq %%zmm7,%%zmm3,%%zmm3\n\t"
+				     "vpxorq %%zmm5,%%zmm4,%%zmm4\n\t"
+				     "vpxorq %%zmm7,%%zmm6,%%zmm6"
+				     :
+				     : "m" (dptr[z][d]), "m" (dptr[z][d+64]));
+		}
+		asm volatile("vmovntdq %%zmm2,%0\n\t"
+			     "vmovntdq %%zmm3,%1\n\t"
+			     "vmovntdq %%zmm4,%2\n\t"
+			     "vmovntdq %%zmm6,%3"
+			     :
+			     : "m" (p[d]), "m" (p[d+64]), "m" (q[d]),
+			       "m" (q[d+64]));
+	}
+
+	asm volatile("sfence" : : : "memory");
+	kernel_fpu_end();
+}
+
+static void raid6_avx5122_xor_syndrome(int disks, int start, int stop,
+				       size_t bytes, void **ptrs)
+{
+	u8 **dptr = (u8 **)ptrs;
+	u8 *p, *q;
+	int d, z, z0;
+
+	z0 = stop;		/* P/Q right side optimization */
+	p = dptr[disks-2];	/* XOR parity */
+	q = dptr[disks-1];	/* RS syndrome */
+
+	kernel_fpu_begin();
+
+	asm volatile("vmovdqa64 %0,%%zmm0"
+		     : : "m" (raid6_avx512_constants.x1d[0]));
+
+	for (d = 0 ; d < bytes ; d += 128) {
+		asm volatile("vmovdqa64 %0,%%zmm4\n\t"
+			     "vmovdqa64 %1,%%zmm6\n\t"
+			     "vmovdqa64 %2,%%zmm2\n\t"
+			     "vmovdqa64 %3,%%zmm3\n\t"
+			     "vpxorq %%zmm4,%%zmm2,%%zmm2\n\t"
+			     "vpxorq %%zmm6,%%zmm3,%%zmm3"
+			     :
+			     : "m" (dptr[z0][d]), "m" (dptr[z0][d+64]),
+			       "m" (p[d]), "m" (p[d+64]));
+		/* P/Q data pages */
+		for (z = z0-1 ; z >= start ; z--) {
+			asm volatile("vpxorq %%zmm5,%%zmm5,%%zmm5\n\t"
+				     "vpxorq %%zmm7,%%zmm7,%%zmm7\n\t"
+				     "vpcmpgtb %%zmm4,%%zmm5,%%k1\n\t"
+				     "vpcmpgtb %%zmm6,%%zmm7,%%k2\n\t"
+				     "vpmovm2b %%k1,%%zmm5\n\t"
+				     "vpmovm2b %%k2,%%zmm7\n\t"
+				     "vpaddb %%zmm4,%%zmm4,%%zmm4\n\t"
+				     "vpaddb %%zmm6,%%zmm6,%%zmm6\n\t"
+				     "vpandq %%zmm0,%%zmm5,%%zmm5\n\t"
+				     "vpandq %%zmm0,%%zmm7,%%zmm7\n\t"
+				     "vpxorq %%zmm5,%%zmm4,%%zmm4\n\t"
+				     "vpxorq %%zmm7,%%zmm6,%%zmm6\n\t"
+				     "vmovdqa64 %0,%%zmm5\n\t"
+				     "vmovdqa64 %1,%%zmm7\n\t"
+				     "vpxorq %%zmm5,%%zmm2,%%zmm2\n\t"
+				     "vpxorq %%zmm7,%%zmm3,%%zmm3\n\t"
+				     "vpxorq %%zmm5,%%zmm4,%%zmm4\n\t"
+				     "vpxorq %%zmm7,%%zmm6,%%zmm6"
+				     :
+				     : "m" (dptr[z][d]),  "m" (dptr[z][d+64]));
+		}
+		/* P/Q left side optimization */
+		for (z = start-1 ; z >= 0 ; z--) {
+			asm volatile("vpxorq %%zmm5,%%zmm5,%%zmm5\n\t"
+				     "vpxorq %%zmm7,%%zmm7,%%zmm7\n\t"
+				     "vpcmpgtb %%zmm4,%%zmm5,%%k1\n\t"
+				     "vpcmpgtb %%zmm6,%%zmm7,%%k2\n\t"
+				     "vpmovm2b %%k1,%%zmm5\n\t"
+				     "vpmovm2b %%k2,%%zmm7\n\t"
+				     "vpaddb %%zmm4,%%zmm4,%%zmm4\n\t"
+				     "vpaddb %%zmm6,%%zmm6,%%zmm6\n\t"
+				     "vpandq %%zmm0,%%zmm5,%%zmm5\n\t"
+				     "vpandq %%zmm0,%%zmm7,%%zmm7\n\t"
+				     "vpxorq %%zmm5,%%zmm4,%%zmm4\n\t"
+				     "vpxorq %%zmm7,%%zmm6,%%zmm6"
+				     :
+				     : );
+		}
+		asm volatile("vpxorq %0,%%zmm4,%%zmm4\n\t"
+			     "vpxorq %1,%%zmm6,%%zmm6\n\t"
+			     /* Don't use movntdq for r/w
+			      * memory area < cache line
+			      */
+			     "vmovdqa64 %%zmm4,%0\n\t"
+			     "vmovdqa64 %%zmm6,%1\n\t"
+			     "vmovdqa64 %%zmm2,%2\n\t"
+			     "vmovdqa64 %%zmm3,%3"
+			     :
+			     : "m" (q[d]), "m" (q[d+64]), "m" (p[d]),
+			       "m" (p[d+64]));
+	}
+
+	asm volatile("sfence" : : : "memory");
+	kernel_fpu_end();
+}
+
+const struct raid6_calls raid6_avx512x2 = {
+	raid6_avx5122_gen_syndrome,
+	raid6_avx5122_xor_syndrome,
+	raid6_have_avx512,
+	"avx512x2",
+	1                       /* Has cache hints */
+};
+
+#ifdef CONFIG_X86_64
+
+/*
+ * Unrolled-by-4 AVX2 implementation
+ */
+static void raid6_avx5124_gen_syndrome(int disks, size_t bytes, void **ptrs)
+{
+	u8 **dptr = (u8 **)ptrs;
+	u8 *p, *q;
+	int d, z, z0;
+
+	z0 = disks - 3;         /* Highest data disk */
+	p = dptr[z0+1];         /* XOR parity */
+	q = dptr[z0+2];         /* RS syndrome */
+
+	kernel_fpu_begin();
+
+	asm volatile("vmovdqa64 %0,%%zmm0\n\t"
+		     "vpxorq %%zmm1,%%zmm1,%%zmm1\n\t"       /* Zero temp */
+		     "vpxorq %%zmm2,%%zmm2,%%zmm2\n\t"       /* P[0] */
+		     "vpxorq %%zmm3,%%zmm3,%%zmm3\n\t"       /* P[1] */
+		     "vpxorq %%zmm4,%%zmm4,%%zmm4\n\t"       /* Q[0] */
+		     "vpxorq %%zmm6,%%zmm6,%%zmm6\n\t"       /* Q[1] */
+		     "vpxorq %%zmm10,%%zmm10,%%zmm10\n\t"    /* P[2] */
+		     "vpxorq %%zmm11,%%zmm11,%%zmm11\n\t"    /* P[3] */
+		     "vpxorq %%zmm12,%%zmm12,%%zmm12\n\t"    /* Q[2] */
+		     "vpxorq %%zmm14,%%zmm14,%%zmm14"        /* Q[3] */
+		     :
+		     : "m" (raid6_avx512_constants.x1d[0]));
+
+	for (d = 0; d < bytes; d += 256) {
+		for (z = z0; z >= 0; z--) {
+		asm volatile("prefetchnta %0\n\t"
+			     "prefetchnta %1\n\t"
+			     "prefetchnta %2\n\t"
+			     "prefetchnta %3\n\t"
+			     "vpcmpgtb %%zmm4,%%zmm1,%%k1\n\t"
+			     "vpcmpgtb %%zmm6,%%zmm1,%%k2\n\t"
+			     "vpcmpgtb %%zmm12,%%zmm1,%%k3\n\t"
+			     "vpcmpgtb %%zmm14,%%zmm1,%%k4\n\t"
+			     "vpmovm2b %%k1,%%zmm5\n\t"
+			     "vpmovm2b %%k2,%%zmm7\n\t"
+			     "vpmovm2b %%k3,%%zmm13\n\t"
+			     "vpmovm2b %%k4,%%zmm15\n\t"
+			     "vpaddb %%zmm4,%%zmm4,%%zmm4\n\t"
+			     "vpaddb %%zmm6,%%zmm6,%%zmm6\n\t"
+			     "vpaddb %%zmm12,%%zmm12,%%zmm12\n\t"
+			     "vpaddb %%zmm14,%%zmm14,%%zmm14\n\t"
+			     "vpandq %%zmm0,%%zmm5,%%zmm5\n\t"
+			     "vpandq %%zmm0,%%zmm7,%%zmm7\n\t"
+			     "vpandq %%zmm0,%%zmm13,%%zmm13\n\t"
+			     "vpandq %%zmm0,%%zmm15,%%zmm15\n\t"
+			     "vpxorq %%zmm5,%%zmm4,%%zmm4\n\t"
+			     "vpxorq %%zmm7,%%zmm6,%%zmm6\n\t"
+			     "vpxorq %%zmm13,%%zmm12,%%zmm12\n\t"
+			     "vpxorq %%zmm15,%%zmm14,%%zmm14\n\t"
+			     "vmovdqa64 %0,%%zmm5\n\t"
+			     "vmovdqa64 %1,%%zmm7\n\t"
+			     "vmovdqa64 %2,%%zmm13\n\t"
+			     "vmovdqa64 %3,%%zmm15\n\t"
+			     "vpxorq %%zmm5,%%zmm2,%%zmm2\n\t"
+			     "vpxorq %%zmm7,%%zmm3,%%zmm3\n\t"
+			     "vpxorq %%zmm13,%%zmm10,%%zmm10\n\t"
+			     "vpxorq %%zmm15,%%zmm11,%%zmm11\n"
+			     "vpxorq %%zmm5,%%zmm4,%%zmm4\n\t"
+			     "vpxorq %%zmm7,%%zmm6,%%zmm6\n\t"
+			     "vpxorq %%zmm13,%%zmm12,%%zmm12\n\t"
+			     "vpxorq %%zmm15,%%zmm14,%%zmm14"
+			     :
+			     : "m" (dptr[z][d]), "m" (dptr[z][d+64]),
+			       "m" (dptr[z][d+128]), "m" (dptr[z][d+192]));
+		}
+		asm volatile("vmovntdq %%zmm2,%0\n\t"
+			     "vpxorq %%zmm2,%%zmm2,%%zmm2\n\t"
+			     "vmovntdq %%zmm3,%1\n\t"
+			     "vpxorq %%zmm3,%%zmm3,%%zmm3\n\t"
+			     "vmovntdq %%zmm10,%2\n\t"
+			     "vpxorq %%zmm10,%%zmm10,%%zmm10\n\t"
+			     "vmovntdq %%zmm11,%3\n\t"
+			     "vpxorq %%zmm11,%%zmm11,%%zmm11\n\t"
+			     "vmovntdq %%zmm4,%4\n\t"
+			     "vpxorq %%zmm4,%%zmm4,%%zmm4\n\t"
+			     "vmovntdq %%zmm6,%5\n\t"
+			     "vpxorq %%zmm6,%%zmm6,%%zmm6\n\t"
+			     "vmovntdq %%zmm12,%6\n\t"
+			     "vpxorq %%zmm12,%%zmm12,%%zmm12\n\t"
+			     "vmovntdq %%zmm14,%7\n\t"
+			     "vpxorq %%zmm14,%%zmm14,%%zmm14"
+			     :
+			     : "m" (p[d]), "m" (p[d+64]), "m" (p[d+128]),
+			       "m" (p[d+192]), "m" (q[d]), "m" (q[d+64]),
+			       "m" (q[d+128]), "m" (q[d+192]));
+	}
+
+	asm volatile("sfence" : : : "memory");
+	kernel_fpu_end();
+}
+
+static void raid6_avx5124_xor_syndrome(int disks, int start, int stop,
+				       size_t bytes, void **ptrs)
+{
+	u8 **dptr = (u8 **)ptrs;
+	u8 *p, *q;
+	int d, z, z0;
+
+	z0 = stop;		/* P/Q right side optimization */
+	p = dptr[disks-2];	/* XOR parity */
+	q = dptr[disks-1];	/* RS syndrome */
+
+	kernel_fpu_begin();
+
+	asm volatile("vmovdqa64 %0,%%zmm0"
+		     :: "m" (raid6_avx512_constants.x1d[0]));
+
+	for (d = 0 ; d < bytes ; d += 256) {
+		asm volatile("vmovdqa64 %0,%%zmm4\n\t"
+			     "vmovdqa64 %1,%%zmm6\n\t"
+			     "vmovdqa64 %2,%%zmm12\n\t"
+			     "vmovdqa64 %3,%%zmm14\n\t"
+			     "vmovdqa64 %4,%%zmm2\n\t"
+			     "vmovdqa64 %5,%%zmm3\n\t"
+			     "vmovdqa64 %6,%%zmm10\n\t"
+			     "vmovdqa64 %7,%%zmm11\n\t"
+			     "vpxorq %%zmm4,%%zmm2,%%zmm2\n\t"
+			     "vpxorq %%zmm6,%%zmm3,%%zmm3\n\t"
+			     "vpxorq %%zmm12,%%zmm10,%%zmm10\n\t"
+			     "vpxorq %%zmm14,%%zmm11,%%zmm11"
+			     :
+			     : "m" (dptr[z0][d]), "m" (dptr[z0][d+64]),
+			       "m" (dptr[z0][d+128]), "m" (dptr[z0][d+192]),
+			       "m" (p[d]), "m" (p[d+64]), "m" (p[d+128]),
+			       "m" (p[d+192]));
+		/* P/Q data pages */
+		for (z = z0-1 ; z >= start ; z--) {
+			asm volatile("vpxorq %%zmm5,%%zmm5,%%zmm5\n\t"
+				     "vpxorq %%zmm7,%%zmm7,%%zmm7\n\t"
+				     "vpxorq %%zmm13,%%zmm13,%%zmm13\n\t"
+				     "vpxorq %%zmm15,%%zmm15,%%zmm15\n\t"
+				     "prefetchnta %0\n\t"
+				     "prefetchnta %2\n\t"
+				     "vpcmpgtb %%zmm4,%%zmm5,%%k1\n\t"
+				     "vpcmpgtb %%zmm6,%%zmm7,%%k2\n\t"
+				     "vpcmpgtb %%zmm12,%%zmm13,%%k3\n\t"
+				     "vpcmpgtb %%zmm14,%%zmm15,%%k4\n\t"
+				     "vpmovm2b %%k1,%%zmm5\n\t"
+				     "vpmovm2b %%k2,%%zmm7\n\t"
+				     "vpmovm2b %%k3,%%zmm13\n\t"
+				     "vpmovm2b %%k4,%%zmm15\n\t"
+				     "vpaddb %%zmm4,%%zmm4,%%zmm4\n\t"
+				     "vpaddb %%zmm6,%%zmm6,%%zmm6\n\t"
+				     "vpaddb %%zmm12,%%zmm12,%%zmm12\n\t"
+				     "vpaddb %%Zmm14,%%zmm14,%%zmm14\n\t"
+				     "vpandq %%zmm0,%%zmm5,%%zmm5\n\t"
+				     "vpandq %%zmm0,%%zmm7,%%zmm7\n\t"
+				     "vpandq %%zmm0,%%zmm13,%%zmm13\n\t"
+				     "vpandq %%zmm0,%%zmm15,%%zmm15\n\t"
+				     "vpxorq %%zmm5,%%zmm4,%%zmm4\n\t"
+				     "vpxorq %%zmm7,%%zmm6,%%zmm6\n\t"
+				     "vpxorq %%zmm13,%%zmm12,%%zmm12\n\t"
+				     "vpxorq %%zmm15,%%zmm14,%%zmm14\n\t"
+				     "vmovdqa64 %0,%%zmm5\n\t"
+				     "vmovdqa64 %1,%%zmm7\n\t"
+				     "vmovdqa64 %2,%%zmm13\n\t"
+				     "vmovdqa64 %3,%%zmm15\n\t"
+				     "vpxorq %%zmm5,%%zmm2,%%zmm2\n\t"
+				     "vpxorq %%zmm7,%%zmm3,%%zmm3\n\t"
+				     "vpxorq %%zmm13,%%zmm10,%%zmm10\n\t"
+				     "vpxorq %%zmm15,%%zmm11,%%zmm11\n\t"
+				     "vpxorq %%zmm5,%%zmm4,%%zmm4\n\t"
+				     "vpxorq %%zmm7,%%zmm6,%%zmm6\n\t"
+				     "vpxorq %%zmm13,%%zmm12,%%zmm12\n\t"
+				     "vpxorq %%zmm15,%%zmm14,%%zmm14"
+				     :
+				     : "m" (dptr[z][d]), "m" (dptr[z][d+64]),
+				       "m" (dptr[z][d+128]),
+				       "m" (dptr[z][d+192]));
+		}
+		asm volatile("prefetchnta %0\n\t"
+			     "prefetchnta %1\n\t"
+			     :
+			     : "m" (q[d]), "m" (q[d+128]));
+		/* P/Q left side optimization */
+		for (z = start-1 ; z >= 0 ; z--) {
+			asm volatile("vpxorq %%zmm5,%%zmm5,%%zmm5\n\t"
+				     "vpxorq %%zmm7,%%zmm7,%%zmm7\n\t"
+				     "vpxorq %%zmm13,%%zmm13,%%zmm13\n\t"
+				     "vpxorq %%zmm15,%%zmm15,%%zmm15\n\t"
+				     "vpcmpgtb %%zmm4,%%zmm5,%%k1\n\t"
+				     "vpcmpgtb %%zmm6,%%zmm7,%%k2\n\t"
+				     "vpcmpgtb %%zmm12,%%zmm13,%%k3\n\t"
+				     "vpcmpgtb %%zmm14,%%zmm15,%%k4\n\t"
+				     "vpmovm2b %%k1,%%zmm5\n\t"
+				     "vpmovm2b %%k2,%%zmm7\n\t"
+				     "vpmovm2b %%k3,%%zmm13\n\t"
+				     "vpmovm2b %%k4,%%zmm15\n\t"
+				     "vpaddb %%zmm4,%%zmm4,%%zmm4\n\t"
+				     "vpaddb %%zmm6,%%zmm6,%%zmm6\n\t"
+				     "vpaddb %%zmm12,%%zmm12,%%zmm12\n\t"
+				     "vpaddb %%zmm14,%%zmm14,%%zmm14\n\t"
+				     "vpandq %%zmm0,%%zmm5,%%zmm5\n\t"
+				     "vpandq %%zmm0,%%zmm7,%%zmm7\n\t"
+				     "vpandq %%zmm0,%%zmm13,%%zmm13\n\t"
+				     "vpandq %%zmm0,%%zmm15,%%zmm15\n\t"
+				     "vpxorq %%zmm5,%%zmm4,%%zmm4\n\t"
+				     "vpxorq %%zmm7,%%zmm6,%%zmm6\n\t"
+				     "vpxorq %%zmm13,%%zmm12,%%zmm12\n\t"
+				     "vpxorq %%zmm15,%%zmm14,%%zmm14"
+				     :
+				     : );
+		}
+		asm volatile("vmovntdq %%zmm2,%0\n\t"
+			     "vmovntdq %%zmm3,%1\n\t"
+			     "vmovntdq %%zmm10,%2\n\t"
+			     "vmovntdq %%zmm11,%3\n\t"
+			     "vpxorq %4,%%zmm4,%%zmm4\n\t"
+			     "vpxorq %5,%%zmm6,%%zmm6\n\t"
+			     "vpxorq %6,%%zmm12,%%zmm12\n\t"
+			     "vpxorq %7,%%zmm14,%%zmm14\n\t"
+			     "vmovntdq %%zmm4,%4\n\t"
+			     "vmovntdq %%zmm6,%5\n\t"
+			     "vmovntdq %%zmm12,%6\n\t"
+			     "vmovntdq %%zmm14,%7"
+			     :
+			     : "m" (p[d]),  "m" (p[d+64]), "m" (p[d+128]),
+			       "m" (p[d+192]), "m" (q[d]),  "m" (q[d+64]),
+			       "m" (q[d+128]), "m" (q[d+192]));
+	}
+	asm volatile("sfence" : : : "memory");
+	kernel_fpu_end();
+}
+const struct raid6_calls raid6_avx512x4 = {
+	raid6_avx5124_gen_syndrome,
+	raid6_avx5124_xor_syndrome,
+	raid6_have_avx512,
+	"avx512x4",
+	1                       /* Has cache hints */
+};
+#endif
+
+#endif /* CONFIG_AS_AVX512 */

lib/raid6/recov_avx512.c

+/*
+ * Copyright (C) 2016 Intel Corporation
+ *
+ * Author: Gayatri Kammela <gayatri.kammela@intel.com>
+ * Author: Megha Dey <megha.dey@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ *
+ */
+
+#ifdef CONFIG_AS_AVX512
+
+#include <linux/raid/pq.h>
+#include "x86.h"
+
+static int raid6_has_avx512(void)
+{
+	return boot_cpu_has(X86_FEATURE_AVX2) &&
+		boot_cpu_has(X86_FEATURE_AVX) &&
+		boot_cpu_has(X86_FEATURE_AVX512F) &&
+		boot_cpu_has(X86_FEATURE_AVX512BW) &&
+		boot_cpu_has(X86_FEATURE_AVX512VL) &&
+		boot_cpu_has(X86_FEATURE_AVX512DQ);
+}
+
+static void raid6_2data_recov_avx512(int disks, size_t bytes, int faila,
+				     int failb, void **ptrs)
+{
+	u8 *p, *q, *dp, *dq;
+	const u8 *pbmul;	/* P multiplier table for B data */
+	const u8 *qmul;		/* Q multiplier table (for both) */
+	const u8 x0f = 0x0f;
+
+	p = (u8 *)ptrs[disks-2];
+	q = (u8 *)ptrs[disks-1];
+
+	/*
+	 * Compute syndrome with zero for the missing data pages
+	 * Use the dead data pages as temporary storage for
+	 * delta p and delta q
+	 */
+
+	dp = (u8 *)ptrs[faila];
+	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[disks-2] = dp;
+	dq = (u8 *)ptrs[failb];
+	ptrs[failb] = (void *)raid6_empty_zero_page;
+	ptrs[disks-1] = dq;
+
+	raid6_call.gen_syndrome(disks, bytes, ptrs);
+
+	/* Restore pointer table */
+	ptrs[faila]   = dp;
+	ptrs[failb]   = dq;
+	ptrs[disks-2] = p;
+	ptrs[disks-1] = q;
+
+	/* Now, pick the proper data tables */
+	pbmul = raid6_vgfmul[raid6_gfexi[failb-faila]];
+	qmul  = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila] ^
+		raid6_gfexp[failb]]];
+
+	kernel_fpu_begin();
+
+	/* zmm0 = x0f[16] */
+	asm volatile("vpbroadcastb %0, %%zmm7" : : "m" (x0f));
+
+	while (bytes) {
+#ifdef CONFIG_X86_64
+		asm volatile("vmovdqa64 %0, %%zmm1\n\t"
+			     "vmovdqa64 %1, %%zmm9\n\t"
+			     "vmovdqa64 %2, %%zmm0\n\t"
+			     "vmovdqa64 %3, %%zmm8\n\t"
+			     "vpxorq %4, %%zmm1, %%zmm1\n\t"
+			     "vpxorq %5, %%zmm9, %%zmm9\n\t"
+			     "vpxorq %6, %%zmm0, %%zmm0\n\t"
+			     "vpxorq %7, %%zmm8, %%zmm8"
+			     :
+			     : "m" (q[0]), "m" (q[64]), "m" (p[0]),
+			       "m" (p[64]), "m" (dq[0]), "m" (dq[64]),
+			       "m" (dp[0]), "m" (dp[64]));
+
+		/*
+		 * 1 = dq[0]  ^ q[0]
+		 * 9 = dq[64] ^ q[64]
+		 * 0 = dp[0]  ^ p[0]
+		 * 8 = dp[64] ^ p[64]
+		 */
+
+		asm volatile("vbroadcasti64x2 %0, %%zmm4\n\t"
+			     "vbroadcasti64x2 %1, %%zmm5"
+			     :
+			     : "m" (qmul[0]), "m" (qmul[16]));
+
+		asm volatile("vpsraw $4, %%zmm1, %%zmm3\n\t"
+			     "vpsraw $4, %%zmm9, %%zmm12\n\t"
+			     "vpandq %%zmm7, %%zmm1, %%zmm1\n\t"
+			     "vpandq %%zmm7, %%zmm9, %%zmm9\n\t"
+			     "vpandq %%zmm7, %%zmm3, %%zmm3\n\t"
+			     "vpandq %%zmm7, %%zmm12, %%zmm12\n\t"
+			     "vpshufb %%zmm9, %%zmm4, %%zmm14\n\t"
+			     "vpshufb %%zmm1, %%zmm4, %%zmm4\n\t"
+			     "vpshufb %%zmm12, %%zmm5, %%zmm15\n\t"
+			     "vpshufb %%zmm3, %%zmm5, %%zmm5\n\t"
+			     "vpxorq %%zmm14, %%zmm15, %%zmm15\n\t"
+			     "vpxorq %%zmm4, %%zmm5, %%zmm5"
+			     :
+			     : );
+
+		/*
+		 * 5 = qx[0]
+		 * 15 = qx[64]
+		 */
+
+		asm volatile("vbroadcasti64x2 %0, %%zmm4\n\t"
+			     "vbroadcasti64x2 %1, %%zmm1\n\t"
+			     "vpsraw $4, %%zmm0, %%zmm2\n\t"
+			     "vpsraw $4, %%zmm8, %%zmm6\n\t"
+			     "vpandq %%zmm7, %%zmm0, %%zmm3\n\t"
+			     "vpandq %%zmm7, %%zmm8, %%zmm14\n\t"
+			     "vpandq %%zmm7, %%zmm2, %%zmm2\n\t"
+			     "vpandq %%zmm7, %%zmm6, %%zmm6\n\t"
+			     "vpshufb %%zmm14, %%zmm4, %%zmm12\n\t"
+			     "vpshufb %%zmm3, %%zmm4, %%zmm4\n\t"
+			     "vpshufb %%zmm6, %%zmm1, %%zmm13\n\t"
+			     "vpshufb %%zmm2, %%zmm1, %%zmm1\n\t"
+			     "vpxorq %%zmm4, %%zmm1, %%zmm1\n\t"
+			     "vpxorq %%zmm12, %%zmm13, %%zmm13"
+			     :
+			     : "m" (pbmul[0]), "m" (pbmul[16]));
+
+		/*
+		 * 1  = pbmul[px[0]]
+		 * 13 = pbmul[px[64]]
+		 */
+		asm volatile("vpxorq %%zmm5, %%zmm1, %%zmm1\n\t"
+			     "vpxorq %%zmm15, %%zmm13, %%zmm13"
+			     :
+			     : );
+
+		/*
+		 * 1 = db = DQ
+		 * 13 = db[64] = DQ[64]
+		 */
+		asm volatile("vmovdqa64 %%zmm1, %0\n\t"
+			     "vmovdqa64 %%zmm13,%1\n\t"
+			     "vpxorq %%zmm1, %%zmm0, %%zmm0\n\t"
+			     "vpxorq %%zmm13, %%zmm8, %%zmm8"
+			     :
+			     : "m" (dq[0]), "m" (dq[64]));
+
+		asm volatile("vmovdqa64 %%zmm0, %0\n\t"
+			     "vmovdqa64 %%zmm8, %1"
+			     :
+			     : "m" (dp[0]), "m" (dp[64]));
+
+		bytes -= 128;
+		p += 128;
+		q += 128;
+		dp += 128;
+		dq += 128;
+#else
+		asm volatile("vmovdqa64 %0, %%zmm1\n\t"
+			     "vmovdqa64 %1, %%zmm0\n\t"
+			     "vpxorq %2, %%zmm1, %%zmm1\n\t"
+			     "vpxorq %3, %%zmm0, %%zmm0"
+			     :
+			     : "m" (*q), "m" (*p), "m"(*dq), "m" (*dp));
+
+		/* 1 = dq ^ q;  0 = dp ^ p */
+
+		asm volatile("vbroadcasti64x2 %0, %%zmm4\n\t"
+			     "vbroadcasti64x2 %1, %%zmm5"
+			     :
+			     : "m" (qmul[0]), "m" (qmul[16]));
+
+		/*
+		 * 1 = dq ^ q
+		 * 3 = dq ^ p >> 4
+		 */
+		asm volatile("vpsraw $4, %%zmm1, %%zmm3\n\t"
+			     "vpandq %%zmm7, %%zmm1, %%zmm1\n\t"
+			     "vpandq %%zmm7, %%zmm3, %%zmm3\n\t"
+			     "vpshufb %%zmm1, %%zmm4, %%zmm4\n\t"
+			     "vpshufb %%zmm3, %%zmm5, %%zmm5\n\t"
+			     "vpxorq %%zmm4, %%zmm5, %%zmm5"
+			     :
+			     : );
+
+		/* 5 = qx */
+
+		asm volatile("vbroadcasti64x2 %0, %%zmm4\n\t"
+			     "vbroadcasti64x2 %1, %%zmm1"
+			     :
+			     : "m" (pbmul[0]), "m" (pbmul[16]));
+
+		asm volatile("vpsraw $4, %%zmm0, %%zmm2\n\t"
+			     "vpandq %%zmm7, %%zmm0, %%zmm3\n\t"
+			     "vpandq %%zmm7, %%zmm2, %%zmm2\n\t"
+			     "vpshufb %%zmm3, %%zmm4, %%zmm4\n\t"
+			     "vpshufb %%zmm2, %%zmm1, %%zmm1\n\t"
+			     "vpxorq %%zmm4, %%zmm1, %%zmm1"
+			     :
+			     : );
+
+		/* 1 = pbmul[px] */
+		asm volatile("vpxorq %%zmm5, %%zmm1, %%zmm1\n\t"
+			     /* 1 = db = DQ */
+			     "vmovdqa64 %%zmm1, %0\n\t"
+			     :
+			     : "m" (dq[0]));
+
+		asm volatile("vpxorq %%zmm1, %%zmm0, %%zmm0\n\t"
+			     "vmovdqa64 %%zmm0, %0"
+			     :
+			     : "m" (dp[0]));
+
+		bytes -= 64;
+		p += 64;
+		q += 64;
+		dp += 64;
+		dq += 64;
+#endif
+	}
+
+	kernel_fpu_end();
+}
+
+static void raid6_datap_recov_avx512(int disks, size_t bytes, int faila,
+				     void **ptrs)
+{
+	u8 *p, *q, *dq;
+	const u8 *qmul;		/* Q multiplier table */
+	const u8 x0f = 0x0f;
+
+	p = (u8 *)ptrs[disks-2];
+	q = (u8 *)ptrs[disks-1];
+
+	/*
+	 * Compute syndrome with zero for the missing data page
+	 * Use the dead data page as temporary storage for delta q
+	 */
+
+	dq = (u8 *)ptrs[faila];
+	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[disks-1] = dq;
+
+	raid6_call.gen_syndrome(disks, bytes, ptrs);
+
+	/* Restore pointer table */
+	ptrs[faila]   = dq;
+	ptrs[disks-1] = q;
+
+	/* Now, pick the proper data tables */
+	qmul  = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila]]];
+
+	kernel_fpu_begin();
+
+	asm volatile("vpbroadcastb %0, %%zmm7" : : "m" (x0f));
+
+	while (bytes) {
+#ifdef CONFIG_X86_64
+		asm volatile("vmovdqa64 %0, %%zmm3\n\t"
+			     "vmovdqa64 %1, %%zmm8\n\t"
+			     "vpxorq %2, %%zmm3, %%zmm3\n\t"
+			     "vpxorq %3, %%zmm8, %%zmm8"
+			     :
+			     : "m" (dq[0]), "m" (dq[64]), "m" (q[0]),
+			       "m" (q[64]));
+
+		/*
+		 * 3 = q[0] ^ dq[0]
+		 * 8 = q[64] ^ dq[64]
+		 */
+		asm volatile("vbroadcasti64x2 %0, %%zmm0\n\t"
+			     "vmovapd %%zmm0, %%zmm13\n\t"
+			     "vbroadcasti64x2 %1, %%zmm1\n\t"
+			     "vmovapd %%zmm1, %%zmm14"
+			     :
+			     : "m" (qmul[0]), "m" (qmul[16]));
+
+		asm volatile("vpsraw $4, %%zmm3, %%zmm6\n\t"
+			     "vpsraw $4, %%zmm8, %%zmm12\n\t"
+			     "vpandq %%zmm7, %%zmm3, %%zmm3\n\t"
+			     "vpandq %%zmm7, %%zmm8, %%zmm8\n\t"
+			     "vpandq %%zmm7, %%zmm6, %%zmm6\n\t"
+			     "vpandq %%zmm7, %%zmm12, %%zmm12\n\t"
+			     "vpshufb %%zmm3, %%zmm0, %%zmm0\n\t"
+			     "vpshufb %%zmm8, %%zmm13, %%zmm13\n\t"
+			     "vpshufb %%zmm6, %%zmm1, %%zmm1\n\t"
+			     "vpshufb %%zmm12, %%zmm14, %%zmm14\n\t"
+			     "vpxorq %%zmm0, %%zmm1, %%zmm1\n\t"
+			     "vpxorq %%zmm13, %%zmm14, %%zmm14"
+			     :
+			     : );
+
+		/*
+		 * 1  = qmul[q[0]  ^ dq[0]]
+		 * 14 = qmul[q[64] ^ dq[64]]
+		 */
+		asm volatile("vmovdqa64 %0, %%zmm2\n\t"
+			     "vmovdqa64 %1, %%zmm12\n\t"
+			     "vpxorq %%zmm1, %%zmm2, %%zmm2\n\t"
+			     "vpxorq %%zmm14, %%zmm12, %%zmm12"
+			     :
+			     : "m" (p[0]), "m" (p[64]));
+
+		/*
+		 * 2  = p[0]  ^ qmul[q[0]  ^ dq[0]]
+		 * 12 = p[64] ^ qmul[q[64] ^ dq[64]]
+		 */
+
+		asm volatile("vmovdqa64 %%zmm1, %0\n\t"
+			     "vmovdqa64 %%zmm14, %1\n\t"
+			     "vmovdqa64 %%zmm2, %2\n\t"
+			     "vmovdqa64 %%zmm12,%3"
+			     :
+			     : "m" (dq[0]), "m" (dq[64]), "m" (p[0]),
+			       "m" (p[64]));
+
+		bytes -= 128;
+		p += 128;
+		q += 128;
+		dq += 128;
+#else
+		asm volatile("vmovdqa64 %0, %%zmm3\n\t"
+			     "vpxorq %1, %%zmm3, %%zmm3"
+			     :
+			     : "m" (dq[0]), "m" (q[0]));
+
+		/* 3 = q ^ dq */
+
+		asm volatile("vbroadcasti64x2 %0, %%zmm0\n\t"
+			     "vbroadcasti64x2 %1, %%zmm1"
+			     :
+			     : "m" (qmul[0]), "m" (qmul[16]));
+
+		asm volatile("vpsraw $4, %%zmm3, %%zmm6\n\t"
+			     "vpandq %%zmm7, %%zmm3, %%zmm3\n\t"
+			     "vpandq %%zmm7, %%zmm6, %%zmm6\n\t"
+			     "vpshufb %%zmm3, %%zmm0, %%zmm0\n\t"
+			     "vpshufb %%zmm6, %%zmm1, %%zmm1\n\t"
+			     "vpxorq %%zmm0, %%zmm1, %%zmm1"
+			     :
+			     : );
+
+		/* 1 = qmul[q ^ dq] */
+
+		asm volatile("vmovdqa64 %0, %%zmm2\n\t"
+			     "vpxorq %%zmm1, %%zmm2, %%zmm2"
+			     :
+			     : "m" (p[0]));
+
+		/* 2 = p ^ qmul[q ^ dq] */
+
+		asm volatile("vmovdqa64 %%zmm1, %0\n\t"
+			     "vmovdqa64 %%zmm2, %1"
+			     :
+			     : "m" (dq[0]), "m" (p[0]));
+
+		bytes -= 64;
+		p += 64;
+		q += 64;
+		dq += 64;
+#endif
+	}
+
+	kernel_fpu_end();
+}
+
+const struct raid6_recov_calls raid6_recov_avx512 = {
+	.data2 = raid6_2data_recov_avx512,
+	.datap = raid6_datap_recov_avx512,
+	.valid = raid6_has_avx512,
+#ifdef CONFIG_X86_64
+	.name = "avx512x2",
+#else
+	.name = "avx512x1",
+#endif
+	.priority = 3,
+};
+
+#else
+#warning "your version of binutils lacks AVX512 support"
+#endif

lib/raid6/test/Makefile

@@ -32,10 +32,13 @@ ifeq ($(ARCH),arm64)
 endif
 
 ifeq ($(IS_X86),yes)
-        OBJS   += mmx.o sse1.o sse2.o avx2.o recov_ssse3.o recov_avx2.o
+        OBJS   += mmx.o sse1.o sse2.o avx2.o recov_ssse3.o recov_avx2.o avx512.o recov_avx512.o
         CFLAGS += $(shell echo "vpbroadcastb %xmm0, %ymm1" |	\
                     gcc -c -x assembler - >&/dev/null &&	\
                     rm ./-.o && echo -DCONFIG_AS_AVX2=1)
+	CFLAGS += $(shell echo "vpmovm2b %k1, %zmm5" |          \
+		    gcc -c -x assembler - >&/dev/null &&        \
+		    rm ./-.o && echo -DCONFIG_AS_AVX512=1)
 else ifeq ($(HAS_NEON),yes)
         OBJS   += neon.o neon1.o neon2.o neon4.o neon8.o
         CFLAGS += -DCONFIG_KERNEL_MODE_NEON=1

lib/raid6/test/test.c

@@ -21,12 +21,13 @@
 
 #define NDISKS		16	/* Including P and Q */
 
-const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(256)));
+const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(PAGE_SIZE)));
 struct raid6_calls raid6_call;
 
 char *dataptrs[NDISKS];
-char data[NDISKS][PAGE_SIZE];
-char recovi[PAGE_SIZE], recovj[PAGE_SIZE];
+char data[NDISKS][PAGE_SIZE] __attribute__((aligned(PAGE_SIZE)));
+char recovi[PAGE_SIZE] __attribute__((aligned(PAGE_SIZE)));
+char recovj[PAGE_SIZE] __attribute__((aligned(PAGE_SIZE)));
 
 static void makedata(int start, int stop)
 {

lib/raid6/x86.h

@@ -46,6 +46,16 @@ static inline void kernel_fpu_end(void)
 #define X86_FEATURE_SSSE3	(4*32+ 9) /* Supplemental SSE-3 */
 #define X86_FEATURE_AVX	(4*32+28) /* Advanced Vector Extensions */
 #define X86_FEATURE_AVX2        (9*32+ 5) /* AVX2 instructions */
+#define X86_FEATURE_AVX512F     (9*32+16) /* AVX-512 Foundation */
+#define X86_FEATURE_AVX512DQ    (9*32+17) /* AVX-512 DQ (Double/Quad granular)
+					   * Instructions
+					   */
+#define X86_FEATURE_AVX512BW    (9*32+30) /* AVX-512 BW (Byte/Word granular)
+					   * Instructions
+					   */
+#define X86_FEATURE_AVX512VL    (9*32+31) /* AVX-512 VL (128/256 Vector Length)
+					   * Extensions
+					   */
 #define X86_FEATURE_MMXEXT	(1*32+22) /* AMD MMX extensions */
 
 /* Should work well enough on modern CPUs for testing */