#ifndef _RAID5_H
#define _RAID5_H
-#include <linux/raid/md.h>
#include <linux/raid/xor.h>
+#include <linux/dmaengine.h>
/*
*
*/
enum check_states {
check_state_idle = 0,
- check_state_run, /* parity check */
+ check_state_run, /* xor parity check */
+ check_state_run_q, /* q-parity check */
+ check_state_run_pq, /* pq dual parity check */
check_state_check_result,
check_state_compute_run, /* parity repair */
check_state_compute_result,
struct stripe_head {
struct hlist_node hash;
- struct list_head lru; /* inactive_list or handle_list */
- struct raid5_private_data *raid_conf;
- sector_t sector; /* sector of this row */
- int pd_idx; /* parity disk index */
- unsigned long state; /* state flags */
- atomic_t count; /* nr of active thread/requests */
+ struct list_head lru; /* inactive_list or handle_list */
+ struct raid5_private_data *raid_conf;
+ short generation; /* increments with every
+ * reshape */
+ sector_t sector; /* sector of this row */
+ short pd_idx; /* parity disk index */
+ short qd_idx; /* 'Q' disk index for raid6 */
+ short ddf_layout;/* use DDF ordering to calculate Q */
+ unsigned long state; /* state flags */
+ atomic_t count; /* nr of active thread/requests */
spinlock_t lock;
int bm_seq; /* sequence number for bitmap flushes */
- int disks; /* disks in stripe */
+ int disks; /* disks in stripe */
enum check_states check_state;
enum reconstruct_states reconstruct_state;
- /* stripe_operations
+ /**
+ * struct stripe_operations
* @target - STRIPE_OP_COMPUTE_BLK target
+ * @target2 - 2nd compute target in the raid6 case
+ * @zero_sum_result - P and Q verification flags
+ * @request - async service request flags for raid_run_ops
*/
struct stripe_operations {
- int target;
- u32 zero_sum_result;
+ int target, target2;
+ enum sum_check_flags zero_sum_result;
+ #ifdef CONFIG_MULTICORE_RAID456
+ unsigned long request;
+ wait_queue_head_t wait_for_ops;
+ #endif
} ops;
struct r5dev {
struct bio req;
/* r6_state - extra state data only relevant to r6 */
struct r6_state {
- int p_failed, q_failed, qd_idx, failed_num[2];
+ int p_failed, q_failed, failed_num[2];
};
/* Flags */
#define READ_MODIFY_WRITE 2
/* not a write method, but a compute_parity mode */
#define CHECK_PARITY 3
+/* Additional compute_parity mode -- updates the parity w/o LOCKING */
+#define UPDATE_PARITY 4
/*
* Stripe state
#define STRIPE_FULL_WRITE 13 /* all blocks are set to be overwritten */
#define STRIPE_BIOFILL_RUN 14
#define STRIPE_COMPUTE_RUN 15
+#define STRIPE_OPS_REQ_PENDING 16
+
/*
* Operation request flags
*/
#define STRIPE_OP_COMPUTE_BLK 1
#define STRIPE_OP_PREXOR 2
#define STRIPE_OP_BIODRAIN 3
-#define STRIPE_OP_POSTXOR 4
+#define STRIPE_OP_RECONSTRUCT 4
#define STRIPE_OP_CHECK 5
/*
struct hlist_head *stripe_hashtbl;
mddev_t *mddev;
struct disk_info *spare;
- int chunk_size, level, algorithm;
+ int chunk_sectors;
+ int level, algorithm;
int max_degraded;
int raid_disks;
int max_nr_stripes;
- /* used during an expand */
- sector_t expand_progress; /* MaxSector when no expand happening */
- sector_t expand_lo; /* from here up to expand_progress it out-of-bounds
- * as we haven't flushed the metadata yet
- */
+ /* reshape_progress is the leading edge of a 'reshape'
+ * It has value MaxSector when no reshape is happening
+ * If delta_disks < 0, it is the last sector we started work on,
+ * else is it the next sector to work on.
+ */
+ sector_t reshape_progress;
+ /* reshape_safe is the trailing edge of a reshape. We know that
+ * before (or after) this address, all reshape has completed.
+ */
+ sector_t reshape_safe;
int previous_raid_disks;
+ int prev_chunk_sectors;
+ int prev_algo;
+ short generation; /* increments with every reshape */
+ unsigned long reshape_checkpoint; /* Time we last updated
+ * metadata */
struct list_head handle_list; /* stripes needing handling */
struct list_head hold_list; /* preread ready stripes */
* (fresh device added).
* Cleared when a sync completes.
*/
-
- struct page *spare_page; /* Used when checking P/Q in raid6 */
+ /* per cpu variables */
+ struct raid5_percpu {
+ struct page *spare_page; /* Used when checking P/Q in raid6 */
+ void *scribble; /* space for constructing buffer
+ * lists and performing address
+ * conversions
+ */
+ } __percpu *percpu;
+ size_t scribble_len; /* size of scribble region must be
+ * associated with conf to handle
+ * cpu hotplug while reshaping
+ */
+#ifdef CONFIG_HOTPLUG_CPU
+ struct notifier_block cpu_notify;
+#endif
/*
* Free stripes pool
int pool_size; /* number of disks in stripeheads in pool */
spinlock_t device_lock;
struct disk_info *disks;
+
+ /* When taking over an array from a different personality, we store
+ * the new thread here until we fully activate the array.
+ */
+ struct mdk_thread_s *thread;
};
typedef struct raid5_private_data raid5_conf_t;
-#define mddev_to_conf(mddev) ((raid5_conf_t *) mddev->private)
-
/*
* Our supported algorithms
*/
-#define ALGORITHM_LEFT_ASYMMETRIC 0
-#define ALGORITHM_RIGHT_ASYMMETRIC 1
-#define ALGORITHM_LEFT_SYMMETRIC 2
-#define ALGORITHM_RIGHT_SYMMETRIC 3
+#define ALGORITHM_LEFT_ASYMMETRIC 0 /* Rotating Parity N with Data Restart */
+#define ALGORITHM_RIGHT_ASYMMETRIC 1 /* Rotating Parity 0 with Data Restart */
+#define ALGORITHM_LEFT_SYMMETRIC 2 /* Rotating Parity N with Data Continuation */
+#define ALGORITHM_RIGHT_SYMMETRIC 3 /* Rotating Parity 0 with Data Continuation */
+
+/* Define non-rotating (raid4) algorithms. These allow
+ * conversion of raid4 to raid5.
+ */
+#define ALGORITHM_PARITY_0 4 /* P or P,Q are initial devices */
+#define ALGORITHM_PARITY_N 5 /* P or P,Q are final devices. */
+
+/* DDF RAID6 layouts differ from md/raid6 layouts in two ways.
+ * Firstly, the exact positioning of the parity block is slightly
+ * different between the 'LEFT_*' modes of md and the "_N_*" modes
+ * of DDF.
+ * Secondly, or order of datablocks over which the Q syndrome is computed
+ * is different.
+ * Consequently we have different layouts for DDF/raid6 than md/raid6.
+ * These layouts are from the DDFv1.2 spec.
+ * Interestingly DDFv1.2-Errata-A does not specify N_CONTINUE but
+ * leaves RLQ=3 as 'Vendor Specific'
+ */
+
+#define ALGORITHM_ROTATING_ZERO_RESTART 8 /* DDF PRL=6 RLQ=1 */
+#define ALGORITHM_ROTATING_N_RESTART 9 /* DDF PRL=6 RLQ=2 */
+#define ALGORITHM_ROTATING_N_CONTINUE 10 /*DDF PRL=6 RLQ=3 */
+
+
+/* For every RAID5 algorithm we define a RAID6 algorithm
+ * with exactly the same layout for data and parity, and
+ * with the Q block always on the last device (N-1).
+ * This allows trivial conversion from RAID5 to RAID6
+ */
+#define ALGORITHM_LEFT_ASYMMETRIC_6 16
+#define ALGORITHM_RIGHT_ASYMMETRIC_6 17
+#define ALGORITHM_LEFT_SYMMETRIC_6 18
+#define ALGORITHM_RIGHT_SYMMETRIC_6 19
+#define ALGORITHM_PARITY_0_6 20
+#define ALGORITHM_PARITY_N_6 ALGORITHM_PARITY_N
+
+static inline int algorithm_valid_raid5(int layout)
+{
+ return (layout >= 0) &&
+ (layout <= 5);
+}
+static inline int algorithm_valid_raid6(int layout)
+{
+ return (layout >= 0 && layout <= 5)
+ ||
+ (layout >= 8 && layout <= 10)
+ ||
+ (layout >= 16 && layout <= 20);
+}
+static inline int algorithm_is_DDF(int layout)
+{
+ return layout >= 8 && layout <= 10;
+}
#endif