xor: make 'xor_blocks' a library routine for use with async_tx

The async_tx api tries to use a dma engine for an operation, but will fall
back to an optimized software routine otherwise.  Xor support is
implemented using the raid5 xor routines.  For organizational purposes this
routine is moved to a common area.

The following fixes are also made:
* rename xor_block => xor_blocks, suggested by Adrian Bunk
* ensure that xor.o initializes before md.o in the built-in case
* checkpatch.pl fixes
* mark calibrate_xor_blocks __init, Adrian Bunk

Cc: Adrian Bunk <bunk@stusta.de>
Cc: NeilBrown <neilb@suse.de>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

drivers/md/Kconfig

@@ -109,6 +109,7 @@ config MD_RAID10
 config MD_RAID456
 	tristate "RAID-4/RAID-5/RAID-6 mode"
 	depends on BLK_DEV_MD
+	select XOR_BLOCKS
 	---help---
 	  A RAID-5 set of N drives with a capacity of C MB per drive provides
 	  the capacity of C * (N - 1) MB, and protects against a failure

drivers/md/Makefile

@@ -17,7 +17,7 @@ raid456-objs	:= raid5.o raid6algos.o raid6recov.o raid6tables.o \
 hostprogs-y	:= mktables
 
 # Note: link order is important.  All raid personalities
-# and xor.o must come before md.o, as they each initialise 
+# and must come before md.o, as they each initialise 
 # themselves, and md.o may use the personalities when it 
 # auto-initialised.
 
@@ -25,7 +25,7 @@ obj-$(CONFIG_MD_LINEAR)		+= linear.o
 obj-$(CONFIG_MD_RAID0)		+= raid0.o
 obj-$(CONFIG_MD_RAID1)		+= raid1.o
 obj-$(CONFIG_MD_RAID10)		+= raid10.o
-obj-$(CONFIG_MD_RAID456)	+= raid456.o xor.o
+obj-$(CONFIG_MD_RAID456)	+= raid456.o
 obj-$(CONFIG_MD_MULTIPATH)	+= multipath.o
 obj-$(CONFIG_MD_FAULTY)		+= faulty.o
 obj-$(CONFIG_BLK_DEV_MD)	+= md-mod.o

drivers/md/md.c

@@ -5814,7 +5814,7 @@ static __exit void md_exit(void)
 	}
 }
 
-module_init(md_init)
+subsys_initcall(md_init);
 module_exit(md_exit)
 
 static int get_ro(char *buffer, struct kernel_param *kp)

drivers/md/raid5.c

@@ -918,7 +918,7 @@ static void copy_data(int frombio, struct bio *bio,
 
 #define check_xor() 	do { 						\
 			   if (count == MAX_XOR_BLOCKS) {		\
-				xor_block(count, STRIPE_SIZE, ptr);	\
+				xor_blocks(count, STRIPE_SIZE, ptr);	\
 				count = 1;				\
 			   }						\
 			} while(0)
@@ -949,7 +949,7 @@ static void compute_block(struct stripe_head *sh, int dd_idx)
 		check_xor();
 	}
 	if (count != 1)
-		xor_block(count, STRIPE_SIZE, ptr);
+		xor_blocks(count, STRIPE_SIZE, ptr);
 	set_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
 }
 
@@ -1004,7 +1004,7 @@ static void compute_parity5(struct stripe_head *sh, int method)
 		break;
 	}
 	if (count>1) {
-		xor_block(count, STRIPE_SIZE, ptr);
+		xor_blocks(count, STRIPE_SIZE, ptr);
 		count = 1;
 	}
 	
@@ -1038,7 +1038,7 @@ static void compute_parity5(struct stripe_head *sh, int method)
 			}
 	}
 	if (count != 1)
-		xor_block(count, STRIPE_SIZE, ptr);
+		xor_blocks(count, STRIPE_SIZE, ptr);
 	
 	if (method != CHECK_PARITY) {
 		set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
@@ -1160,7 +1160,7 @@ static void compute_block_1(struct stripe_head *sh, int dd_idx, int nozero)
 			check_xor();
 		}
 		if (count != 1)
-			xor_block(count, STRIPE_SIZE, ptr);
+			xor_blocks(count, STRIPE_SIZE, ptr);
 		if (!nozero) set_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
 		else clear_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
 	}

drivers/md/xor.c

@@ -1,154 +0,0 @@
-/*
- * xor.c : Multiple Devices driver for Linux
- *
- * Copyright (C) 1996, 1997, 1998, 1999, 2000,
- * Ingo Molnar, Matti Aarnio, Jakub Jelinek, Richard Henderson.
- *
- * Dispatch optimized RAID-5 checksumming functions.
- *
- * 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; either version 2, or (at your option)
- * any later version.
- *
- * You should have received a copy of the GNU General Public License
- * (for example /usr/src/linux/COPYING); if not, write to the Free
- * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#define BH_TRACE 0
-#include <linux/module.h>
-#include <linux/raid/md.h>
-#include <linux/raid/xor.h>
-#include <asm/xor.h>
-
-/* The xor routines to use.  */
-static struct xor_block_template *active_template;
-
-void
-xor_block(unsigned int count, unsigned int bytes, void **ptr)
-{
-	unsigned long *p0, *p1, *p2, *p3, *p4;
-
-	p0 = (unsigned long *) ptr[0];
-	p1 = (unsigned long *) ptr[1];
-	if (count == 2) {
-		active_template->do_2(bytes, p0, p1);
-		return;
-	}
-
-	p2 = (unsigned long *) ptr[2];
-	if (count == 3) {
-		active_template->do_3(bytes, p0, p1, p2);
-		return;
-	}
-
-	p3 = (unsigned long *) ptr[3];
-	if (count == 4) {
-		active_template->do_4(bytes, p0, p1, p2, p3);
-		return;
-	}
-
-	p4 = (unsigned long *) ptr[4];
-	active_template->do_5(bytes, p0, p1, p2, p3, p4);
-}
-
-/* Set of all registered templates.  */
-static struct xor_block_template *template_list;
-
-#define BENCH_SIZE (PAGE_SIZE)
-
-static void
-do_xor_speed(struct xor_block_template *tmpl, void *b1, void *b2)
-{
-	int speed;
-	unsigned long now;
-	int i, count, max;
-
-	tmpl->next = template_list;
-	template_list = tmpl;
-
-	/*
-	 * Count the number of XORs done during a whole jiffy, and use
-	 * this to calculate the speed of checksumming.  We use a 2-page
-	 * allocation to have guaranteed color L1-cache layout.
-	 */
-	max = 0;
-	for (i = 0; i < 5; i++) {
-		now = jiffies;
-		count = 0;
-		while (jiffies == now) {
-			mb();
-			tmpl->do_2(BENCH_SIZE, b1, b2);
-			mb();
-			count++;
-			mb();
-		}
-		if (count > max)
-			max = count;
-	}
-
-	speed = max * (HZ * BENCH_SIZE / 1024);
-	tmpl->speed = speed;
-
-	printk("   %-10s: %5d.%03d MB/sec\n", tmpl->name,
-	       speed / 1000, speed % 1000);
-}
-
-static int
-calibrate_xor_block(void)
-{
-	void *b1, *b2;
-	struct xor_block_template *f, *fastest;
-
-	b1 = (void *) __get_free_pages(GFP_KERNEL, 2);
-	if (! b1) {
-		printk("raid5: Yikes!  No memory available.\n");
-		return -ENOMEM;
-	}
-	b2 = b1 + 2*PAGE_SIZE + BENCH_SIZE;
-
-	/*
-	 * If this arch/cpu has a short-circuited selection, don't loop through all
-	 * the possible functions, just test the best one
-	 */
-
-	fastest = NULL;
-
-#ifdef XOR_SELECT_TEMPLATE
-		fastest = XOR_SELECT_TEMPLATE(fastest);
-#endif
-
-#define xor_speed(templ)	do_xor_speed((templ), b1, b2)
-
-	if (fastest) {
-		printk(KERN_INFO "raid5: automatically using best checksumming function: %s\n",
-			fastest->name);
-		xor_speed(fastest);
-	} else {
-		printk(KERN_INFO "raid5: measuring checksumming speed\n");
-		XOR_TRY_TEMPLATES;
-		fastest = template_list;
-		for (f = fastest; f; f = f->next)
-			if (f->speed > fastest->speed)
-				fastest = f;
-	}
-
-	printk("raid5: using function: %s (%d.%03d MB/sec)\n",
-	       fastest->name, fastest->speed / 1000, fastest->speed % 1000);
-
-#undef xor_speed
-
-	free_pages((unsigned long)b1, 2);
-
-	active_template = fastest;
-	return 0;
-}
-
-static __exit void xor_exit(void) { }
-
-EXPORT_SYMBOL(xor_block);
-MODULE_LICENSE("GPL");
-
-module_init(calibrate_xor_block);
-module_exit(xor_exit);