Merge branch 'for-linus' of git://git.open-osd.org/linux-open-osd

* 'for-linus' of git://git.open-osd.org/linux-open-osd: (21 commits)
  ore: Enable RAID5 mounts
  exofs: Support for RAID5 read-4-write interface.
  ore: RAID5 Write
  ore: RAID5 read
  fs/Makefile: Always inspect exofs/
  ore: Make ore_calc_stripe_info EXPORT_SYMBOL
  ore/exofs: Change ore_check_io API
  ore/exofs: Define new ore_verify_layout
  ore: Support for partial component table
  ore: Support for short read/writes
  exofs: Support for short read/writes
  ore: Remove check for ios->kern_buff in _prepare_for_striping to later
  ore: cleanup: Embed an ore_striping_info inside ore_io_state
  ore: Only IO one group at a time (API change)
  ore/exofs: Change the type of the devices array (API change)
  ore: Make ore_striping_info and ore_calc_stripe_info public
  exofs: Remove unused data_map member from exofs_sb_info
  exofs: Rename struct ore_components comps => oc
  exofs/super.c: local functions should be static
  exofs/ore.c: local functions should be static
  ...

drivers/scsi/osd/Kconfig

@@ -11,10 +11,6 @@
 # it under the terms of the GNU General Public version 2 License as
 # published by the Free Software Foundation
 #
-# FIXME: SCSI_OSD_INITIATOR should select CONFIG (HMAC) SHA1 somehow.
-#        How is it done properly?
-#
-
 config SCSI_OSD_INITIATOR
 	tristate "OSD-Initiator library"
 	depends on SCSI

fs/Makefile

@@ -120,6 +120,6 @@ obj-$(CONFIG_DEBUG_FS)		+= debugfs/
 obj-$(CONFIG_OCFS2_FS)		+= ocfs2/
 obj-$(CONFIG_BTRFS_FS)		+= btrfs/
 obj-$(CONFIG_GFS2_FS)           += gfs2/
-obj-$(CONFIG_EXOFS_FS)          += exofs/
+obj-$(y)          		+= exofs/ # Multiple mods, used by nfs/objlayout
 obj-$(CONFIG_CEPH_FS)		+= ceph/
 obj-$(CONFIG_PSTORE)		+= pstore/

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/Kconfig

+# Note ORE needs to "select ASYNC_XOR". So Not to force multiple selects
+# for every ORE user we do it like this. Any user should add itself here
+# at the "depends on EXOFS_FS || ..." with an ||. The dependencies are
+# selected here, and we default to "ON". So in effect it is like been
+# selected by any of the users.
 config ORE
 	tristate
+	depends on EXOFS_FS
+	select ASYNC_XOR
+	default SCSI_OSD_ULD
 
 config EXOFS_FS
 	tristate "exofs: OSD based file system support"
 	depends on SCSI_OSD_ULD
-	select ORE
 	help
 	  EXOFS is a file system that uses an OSD storage device,
 	  as its backing storage.

fs/exofs/exofs.h

@@ -53,6 +53,10 @@
 /* u64 has problems with printk this will cast it to unsigned long long */
 #define _LLU(x) (unsigned long long)(x)
 
+struct exofs_dev {
+	struct ore_dev ored;
+	unsigned did;
+};
 /*
  * our extension to the in-memory superblock
  */
@@ -66,13 +70,9 @@ struct exofs_sb_info {
 	u32		s_next_generation;	/* next gen # to use          */
 	atomic_t	s_curr_pending;		/* number of pending commands */
 
-	struct pnfs_osd_data_map data_map;	/* Default raid to use
-						 * FIXME: Needed ?
-						 */
 	struct ore_layout	layout;		/* Default files layout       */
 	struct ore_comp one_comp;		/* id & cred of partition id=0*/
-	struct ore_components comps;		/* comps for the partition    */
-	struct osd_dev	*_min_one_dev[1];	/* Place holder for one dev   */
+	struct ore_components oc;		/* comps for the partition    */
 };
 
 /*
@@ -86,7 +86,7 @@ struct exofs_i_info {
 	uint32_t       i_dir_start_lookup; /* which page to start lookup      */
 	uint64_t       i_commit_size;      /* the object's written length     */
 	struct ore_comp one_comp;	   /* same component for all devices  */
-	struct ore_components comps;	   /* inode view of the device table  */
+	struct ore_components oc;	   /* inode view of the device table  */
 };
 
 static inline osd_id exofs_oi_objno(struct exofs_i_info *oi)
@@ -207,7 +207,7 @@ extern const struct inode_operations exofs_fast_symlink_inode_operations;
  * bigger and that the device table repeats twice.
  * See: exofs_read_lookup_dev_table()
  */
-static inline void exofs_init_comps(struct ore_components *comps,
+static inline void exofs_init_comps(struct ore_components *oc,
 				    struct ore_comp *one_comp,
 				    struct exofs_sb_info *sbi, osd_id oid)
 {
@@ -217,13 +217,15 @@ static inline void exofs_init_comps(struct ore_components *comps,
 	one_comp->obj.id = oid;
 	exofs_make_credential(one_comp->cred, &one_comp->obj);
 
-	comps->numdevs = sbi->comps.numdevs;
-	comps->single_comp = EC_SINGLE_COMP;
-	comps->comps = one_comp;
+	oc->first_dev = 0;
+	oc->numdevs = sbi->layout.group_width * sbi->layout.mirrors_p1 *
+							sbi->layout.group_count;
+	oc->single_comp = EC_SINGLE_COMP;
+	oc->comps = one_comp;
 
 	/* Round robin device view of the table */
-	first_dev = (dev_mod * sbi->layout.mirrors_p1) % sbi->comps.numdevs;
-	comps->ods = sbi->comps.ods + first_dev;
+	first_dev = (dev_mod * sbi->layout.mirrors_p1) % sbi->oc.numdevs;
+	oc->ods = &sbi->oc.ods[first_dev];
 }
 
 #endif

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);
+void _ore_add_stripe_page(struct __stripe_pages_2d *sp2d,
+		       struct ore_striping_info *si, struct page *page);
+static inline void _add_stripe_page(struct __stripe_pages_2d *sp2d,
+				struct ore_striping_info *si, struct page *page)
+{
+	if (!sp2d) /* Inline the fast path */
+		return; /* Hay no raid stuff */
+	_ore_add_stripe_page(sp2d, si, page);
+}
+
+/* ios.c stuff needed by ios_raid.c */
+int  _ore_get_io_state(struct ore_layout *layout,
+			struct ore_components *oc, unsigned numdevs,
+			unsigned sgs_per_dev, unsigned num_par_pages,
+			struct ore_io_state **pios);
+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);
+int _ore_read_mirror(struct ore_io_state *ios, unsigned cur_comp);
+int ore_io_execute(struct ore_io_state *ios);

include/scsi/osd_ore.h

@@ -34,15 +34,30 @@ struct ore_comp {
 
 struct ore_layout {
 	/* Our way of looking at the data_map */
+	enum pnfs_osd_raid_algorithm4
+		 raid_algorithm;
 	unsigned stripe_unit;
 	unsigned mirrors_p1;
 
 	unsigned group_width;
+	unsigned parity;
 	u64	 group_depth;
 	unsigned group_count;
+
+	/* Cached often needed calculations filled in by
+	 * ore_verify_layout
+	 */
+	unsigned long max_io_length;	/* Max length that should be passed to
+					 * ore_get_rw_state
+					 */
+};
+
+struct ore_dev {
+	struct osd_dev *od;
 };
 
 struct ore_components {
+	unsigned	first_dev;		/* First logical device no    */
 	unsigned	numdevs;		/* Num of devices in array    */
 	/* If @single_comp == EC_SINGLE_COMP, @comps points to a single
 	 * component. else there are @numdevs components
@@ -51,20 +66,60 @@ struct ore_components {
 		EC_SINGLE_COMP = 0, EC_MULTPLE_COMPS = 0xffffffff
 	}		single_comp;
 	struct ore_comp	*comps;
-	struct osd_dev	**ods;			/* osd_dev array              */
+
+	/* Array of pointers to ore_dev-* . User will usually have these pointed
+	 * too a bigger struct which contain an "ore_dev ored" member and use
+	 * container_of(oc->ods[i], struct foo_dev, ored) to access the bigger
+	 * structure.
+	 */
+	struct ore_dev	**ods;
+};
+
+/* ore_comp_dev Recievies a logical device index */
+static inline struct osd_dev *ore_comp_dev(
+	const struct ore_components *oc, unsigned i)
+{
+	BUG_ON((i < oc->first_dev) || (oc->first_dev + oc->numdevs <= i));
+	return oc->ods[i - oc->first_dev]->od;
+}
+
+static inline void ore_comp_set_dev(
+	struct ore_components *oc, unsigned i, struct osd_dev *od)
+{
+	oc->ods[i - oc->first_dev]->od = od;
+}
+
+struct ore_striping_info {
+	u64 offset;
+	u64 obj_offset;
+	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_pg;
+	unsigned cur_comp;
 };
 
 struct ore_io_state;
 typedef void (*ore_io_done_fn)(struct ore_io_state *ios, void *private);
+struct _ore_r4w_op {
+	/* @Priv given here is passed ios->private */
+	struct page * (*get_page)(void *priv, u64 page_index, bool *uptodate);
+	void (*put_page)(void *priv, struct page *page);
+};
 
 struct ore_io_state {
 	struct kref		kref;
+	struct ore_striping_info si;
 
 	void			*private;
 	ore_io_done_fn	done;
 
 	struct ore_layout	*layout;
-	struct ore_components	*comps;
+	struct ore_components	*oc;
 
 	/* Global read/write IO*/
 	loff_t			offset;
@@ -84,6 +139,16 @@ 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;
+	struct __stripe_pages_2d *sp2d;
+	struct ore_io_state	 *ios_read_4_write;
+	const struct _ore_r4w_op *r4w;
+
 	/* Variable array of size numdevs */
 	unsigned numdevs;
 	struct ore_per_dev_state {
@@ -91,7 +156,10 @@ 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[];
 };
 
@@ -102,6 +170,9 @@ 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,
+			  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);
@@ -109,7 +180,10 @@ int ore_get_io_state(struct ore_layout *layout, struct ore_components *comps,
 		     struct ore_io_state **ios);
 void ore_put_io_state(struct ore_io_state *ios);
 
-int ore_check_io(struct ore_io_state *ios, u64 *resid);
+typedef void (*ore_on_dev_error)(struct ore_io_state *ios, struct ore_dev *od,
+	unsigned dev_index, enum osd_err_priority oep,
+	u64 dev_offset, u64  dev_len);
+int ore_check_io(struct ore_io_state *ios, ore_on_dev_error rep);
 
 int ore_create(struct ore_io_state *ios);
 int ore_remove(struct ore_io_state *ios);