ore: RAID5 read

This patch introduces the first stage of RAID5 support
mainly the skip-over-raid-units when reading. For
writes it inserts BLANK units, into where XOR blocks
should be calculated and written to.

It introduces the new "general raid maths", and the main
additional parameters and components needed for raid5.

Since at this stage it could corrupt future version that
actually do support raid5. The enablement of raid5
mounting and setting of parity-count > 0 is disabled. So
the raid5 code will never be used. Mounting of raid5 is
only enabled later once the basic XOR write is also in.
But if the patch "enable RAID5" is applied this code has
been tested to be able to properly read raid5 volumes
and is according to standard.

Also it has been tested that the new maths still properly
supports RAID0 and grouping code just as before.
(BTW: I have found more bugs in the pnfs-obj RAID math
 fixed here)

The ore.c file is getting too big, so new ore_raid.[hc]
files are added that will include the special raid stuff
that are not used in striping and mirrors. In future write
support these will get bigger.
When adding the ore_raid.c to Kbuild file I was forced to
rename ore.ko to libore.ko. Is it possible to keep source
file, say ore.c and module file ore.ko the same even if there
are multiple files inside ore.ko?
Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>

fs/exofs/Kbuild

@@ -13,7 +13,8 @@
 #
 
 # ore module library
-obj-$(CONFIG_ORE) += ore.o
+libore-y := ore.o ore_raid.o
+obj-$(CONFIG_ORE) += libore.o
 
 exofs-y := inode.o file.o symlink.o namei.o dir.o super.o
 obj-$(CONFIG_EXOFS_FS) += exofs.o

fs/exofs/ore_raid.c

+/*
+ * Copyright (C) 2011
+ * Boaz Harrosh <bharrosh@panasas.com>
+ *
+ * This file is part of the objects raid engine (ore).
+ *
+ * It is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with "ore". If not, write to the Free Software Foundation, Inc:
+ *	"Free Software Foundation <info@fsf.org>"
+ */
+
+#include <linux/gfp.h>
+
+#include "ore_raid.h"
+
+struct page *_raid_page_alloc(void)
+{
+	return alloc_page(GFP_KERNEL);
+}
+
+void _raid_page_free(struct page *p)
+{
+	__free_page(p);
+}
+
+void _ore_add_sg_seg(struct ore_per_dev_state *per_dev, unsigned cur_len,
+		     bool not_last)
+{
+	struct osd_sg_entry *sge;
+
+	ORE_DBGMSG("dev=%d cur_len=0x%x not_last=%d cur_sg=%d "
+		     "offset=0x%llx length=0x%x last_sgs_total=0x%x\n",
+		     per_dev->dev, cur_len, not_last, per_dev->cur_sg,
+		     _LLU(per_dev->offset), per_dev->length,
+		     per_dev->last_sgs_total);
+
+	if (!per_dev->cur_sg) {
+		sge = per_dev->sglist;
+
+		/* First time we prepare two entries */
+		if (per_dev->length) {
+			++per_dev->cur_sg;
+			sge->offset = per_dev->offset;
+			sge->len = per_dev->length;
+		} else {
+			/* Here the parity is the first unit of this object.
+			 * This happens every time we reach a parity device on
+			 * the same stripe as the per_dev->offset. We need to
+			 * just skip this unit.
+			 */
+			per_dev->offset += cur_len;
+			return;
+		}
+	} else {
+		/* finalize the last one */
+		sge = &per_dev->sglist[per_dev->cur_sg - 1];
+		sge->len = per_dev->length - per_dev->last_sgs_total;
+	}
+
+	if (not_last) {
+		/* Partly prepare the next one */
+		struct osd_sg_entry *next_sge = sge + 1;
+
+		++per_dev->cur_sg;
+		next_sge->offset = sge->offset + sge->len + cur_len;
+		/* Save cur len so we know how mutch was added next time */
+		per_dev->last_sgs_total = per_dev->length;
+		next_sge->len = 0;
+	} else if (!sge->len) {
+		/* Optimize for when the last unit is a parity */
+		--per_dev->cur_sg;
+	}
+}
+
+/* In writes @cur_len means length left. .i.e cur_len==0 is the last parity U */
+int _ore_add_parity_unit(struct ore_io_state *ios,
+			    struct ore_striping_info *si,
+			    struct ore_per_dev_state *per_dev,
+			    unsigned cur_len)
+{
+	if (ios->reading) {
+		BUG_ON(per_dev->cur_sg >= ios->sgs_per_dev);
+		_ore_add_sg_seg(per_dev, cur_len, true);
+	} else {
+		struct page **pages = ios->parity_pages + ios->cur_par_page;
+		unsigned num_pages = ios->layout->stripe_unit / PAGE_SIZE;
+		unsigned array_start = 0;
+		unsigned i;
+		int ret;
+
+		for (i = 0; i < num_pages; i++) {
+			pages[i] = _raid_page_alloc();
+			if (unlikely(!pages[i]))
+				return -ENOMEM;
+
+			++(ios->cur_par_page);
+			/* TODO: only read support for now */
+			clear_highpage(pages[i]);
+		}
+
+		ORE_DBGMSG("writing dev=%d num_pages=%d cur_par_page=%d",
+			     per_dev->dev, num_pages, ios->cur_par_page);
+
+		ret = _ore_add_stripe_unit(ios,  &array_start, 0, pages,
+					   per_dev, num_pages * PAGE_SIZE);
+		if (unlikely(ret))
+			return ret;
+	}
+	return 0;
+}
+
+int _ore_post_alloc_raid_stuff(struct ore_io_state *ios)
+{
+	/*TODO: Only raid writes has stuff to add here */
+	return 0;
+}
+
+void _ore_free_raid_stuff(struct ore_io_state *ios)
+{
+	if (ios->parity_pages) { /* writing and raid */
+		unsigned i;
+
+		for (i = 0; i < ios->cur_par_page; i++) {
+			struct page *page = ios->parity_pages[i];
+
+			if (page)
+				_raid_page_free(page);
+		}
+		if (ios->extra_part_alloc)
+			kfree(ios->parity_pages);
+	} else {
+		/* Will only be set if raid reading && sglist is big */
+		if (ios->extra_part_alloc)
+			kfree(ios->per_dev[0].sglist);
+	}
+}

fs/exofs/ore_raid.h

+/*
+ * Copyright (C) from 2011
+ * Boaz Harrosh <bharrosh@panasas.com>
+ *
+ * This file is part of the objects raid engine (ore).
+ *
+ * It is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with "ore". If not, write to the Free Software Foundation, Inc:
+ *	"Free Software Foundation <info@fsf.org>"
+ */
+
+#include <scsi/osd_ore.h>
+
+#define ORE_ERR(fmt, a...) printk(KERN_ERR "ore: " fmt, ##a)
+
+#ifdef CONFIG_EXOFS_DEBUG
+#define ORE_DBGMSG(fmt, a...) \
+	printk(KERN_NOTICE "ore @%s:%d: " fmt, __func__, __LINE__, ##a)
+#else
+#define ORE_DBGMSG(fmt, a...) \
+	do { if (0) printk(fmt, ##a); } while (0)
+#endif
+
+/* u64 has problems with printk this will cast it to unsigned long long */
+#define _LLU(x) (unsigned long long)(x)
+
+#define ORE_DBGMSG2(M...) do {} while (0)
+/* #define ORE_DBGMSG2 ORE_DBGMSG */
+
+/* Calculate the component order in a stripe. eg the logical data unit
+ * address within the stripe of @dev given the @par_dev of this stripe.
+ */
+static inline unsigned _dev_order(unsigned devs_in_group, unsigned mirrors_p1,
+				  unsigned par_dev, unsigned dev)
+{
+	unsigned first_dev = dev - dev % devs_in_group;
+
+	dev -= first_dev;
+	par_dev -= first_dev;
+
+	if (devs_in_group == par_dev) /* The raid 0 case */
+		return dev / mirrors_p1;
+	/* raid4/5/6 case */
+	return ((devs_in_group + dev - par_dev - mirrors_p1) % devs_in_group) /
+	       mirrors_p1;
+}
+
+/* ios_raid.c stuff needed by ios.c */
+int _ore_post_alloc_raid_stuff(struct ore_io_state *ios);
+void _ore_free_raid_stuff(struct ore_io_state *ios);
+
+void _ore_add_sg_seg(struct ore_per_dev_state *per_dev, unsigned cur_len,
+		 bool not_last);
+int _ore_add_parity_unit(struct ore_io_state *ios, struct ore_striping_info *si,
+		     struct ore_per_dev_state *per_dev, unsigned cur_len);
+
+/* ios.c stuff needed by ios_raid.c */
+int _ore_add_stripe_unit(struct ore_io_state *ios,  unsigned *cur_pg,
+		unsigned pgbase, struct page **pages,
+		struct ore_per_dev_state *per_dev, int cur_len);

include/scsi/osd_ore.h

@@ -40,6 +40,7 @@ struct ore_layout {
 	unsigned mirrors_p1;
 
 	unsigned group_width;
+	unsigned parity;
 	u64	 group_depth;
 	unsigned group_count;
 
@@ -89,11 +90,16 @@ static inline void ore_comp_set_dev(
 }
 
 struct ore_striping_info {
+	u64 offset;
 	u64 obj_offset;
-	u64 group_length;
+	u64 length;
+	u64 first_stripe_start; /* only used in raid writes */
 	u64 M; /* for truncate */
+	unsigned bytes_in_stripe;
 	unsigned dev;
+	unsigned par_dev;
 	unsigned unit_off;
+	unsigned cur_comp;
 };
 
 struct ore_io_state;
@@ -127,6 +133,13 @@ struct ore_io_state {
 
 	bool			reading;
 
+	/* House keeping of Parity pages */
+	bool			extra_part_alloc;
+	struct page		**parity_pages;
+	unsigned		max_par_pages;
+	unsigned		cur_par_page;
+	unsigned		sgs_per_dev;
+
 	/* Variable array of size numdevs */
 	unsigned numdevs;
 	struct ore_per_dev_state {
@@ -134,7 +147,10 @@ struct ore_io_state {
 		struct bio *bio;
 		loff_t offset;
 		unsigned length;
+		unsigned last_sgs_total;
 		unsigned dev;
+		struct osd_sg_entry *sglist;
+		unsigned cur_sg;
 	} per_dev[];
 };
 
@@ -147,8 +163,7 @@ static inline unsigned ore_io_state_size(unsigned numdevs)
 /* ore.c */
 int ore_verify_layout(unsigned total_comps, struct ore_layout *layout);
 void ore_calc_stripe_info(struct ore_layout *layout, u64 file_offset,
-			  struct ore_striping_info *si);
-
+			  u64 length, struct ore_striping_info *si);
 int ore_get_rw_state(struct ore_layout *layout, struct ore_components *comps,
 		     bool is_reading, u64 offset, u64 length,
 		     struct ore_io_state **ios);