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
  ...

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);