#ifndef _RAID5_H#define _RAID5_H #include <linux/raid/xor.h>#include <linux/dmaengine.h> /* * * Each stripe contains one buffer per device.  Each buffer can be in * one of a number of states stored in "flags".  Changes between * these states happen *almost* exclusively under the protection of the * STRIPE_ACTIVE flag.  Some very specific changes can happen in bi_end_io, and * these are not protected by STRIPE_ACTIVE. * * The flag bits that are used to represent these states are: *   R5_UPTODATE and R5_LOCKED * * State Empty == !UPTODATE, !LOCK *        We have no data, and there is no active request * State Want == !UPTODATE, LOCK *        A read request is being submitted for this block * State Dirty == UPTODATE, LOCK *        Some new data is in this buffer, and it is being written out * State Clean == UPTODATE, !LOCK *        We have valid data which is the same as on disc * * The possible state transitions are: * *  Empty -> Want   - on read or write to get old data for  parity calc *  Empty -> Dirty  - on compute_parity to satisfy write/sync request. *  Empty -> Clean  - on compute_block when computing a block for failed drive *  Want  -> Empty  - on failed read *  Want  -> Clean  - on successful completion of read request *  Dirty -> Clean  - on successful completion of write request *  Dirty -> Clean  - on failed write *  Clean -> Dirty  - on compute_parity to satisfy write/sync (RECONSTRUCT or RMW) * * The Want->Empty, Want->Clean, Dirty->Clean, transitions * all happen in b_end_io at interrupt time. * Each sets the Uptodate bit before releasing the Lock bit. * This leaves one multi-stage transition: *    Want->Dirty->Clean * This is safe because thinking that a Clean buffer is actually dirty * will at worst delay some action, and the stripe will be scheduled * for attention after the transition is complete. * * There is one possibility that is not covered by these states.  That * is if one drive has failed and there is a spare being rebuilt.  We * can't distinguish between a clean block that has been generated * from parity calculations, and a clean block that has been * successfully written to the spare ( or to parity when resyncing). * To distingush these states we have a stripe bit STRIPE_INSYNC that * is set whenever a write is scheduled to the spare, or to the parity * disc if there is no spare.  A sync request clears this bit, and * when we find it set with no buffers locked, we know the sync is * complete. * * Buffers for the md device that arrive via make_request are attached * to the appropriate stripe in one of two lists linked on b_reqnext. * One list (bh_read) for read requests, one (bh_write) for write. * There should never be more than one buffer on the two lists * together, but we are not guaranteed of that so we allow for more. * * If a buffer is on the read list when the associated cache buffer is * Uptodate, the data is copied into the read buffer and it's b_end_io * routine is called.  This may happen in the end_request routine only * if the buffer has just successfully been read.  end_request should * remove the buffers from the list and then set the Uptodate bit on * the buffer.  Other threads may do this only if they first check * that the Uptodate bit is set.  Once they have checked that they may * take buffers off the read queue. * * When a buffer on the write list is committed for write it is copied * into the cache buffer, which is then marked dirty, and moved onto a * third list, the written list (bh_written).  Once both the parity * block and the cached buffer are successfully written, any buffer on * a written list can be returned with b_end_io. * * The write list and read list both act as fifos.  The read list, * write list and written list are protected by the device_lock. * The device_lock is only for list manipulations and will only be * held for a very short time.  It can be claimed from interrupts. * * * Stripes in the stripe cache can be on one of two lists (or on * neither).  The "inactive_list" contains stripes which are not * currently being used for any request.  They can freely be reused * for another stripe.  The "handle_list" contains stripes that need * to be handled in some way.  Both of these are fifo queues.  Each * stripe is also (potentially) linked to a hash bucket in the hash * table so that it can be found by sector number.  Stripes that are * not hashed must be on the inactive_list, and will normally be at * the front.  All stripes start life this way. * * The inactive_list, handle_list and hash bucket lists are all protected by the * device_lock. *  - stripes have a reference counter. If count==0, they are on a list. *  - If a stripe might need handling, STRIPE_HANDLE is set. *  - When refcount reaches zero, then if STRIPE_HANDLE it is put on *    handle_list else inactive_list * * This, combined with the fact that STRIPE_HANDLE is only ever * cleared while a stripe has a non-zero count means that if the * refcount is 0 and STRIPE_HANDLE is set, then it is on the * handle_list and if recount is 0 and STRIPE_HANDLE is not set, then * the stripe is on inactive_list. * * The possible transitions are: *  activate an unhashed/inactive stripe (get_active_stripe()) *     lockdev check-hash unlink-stripe cnt++ clean-stripe hash-stripe unlockdev *  activate a hashed, possibly active stripe (get_active_stripe()) *     lockdev check-hash if(!cnt++)unlink-stripe unlockdev *  attach a request to an active stripe (add_stripe_bh()) *     lockdev attach-buffer unlockdev *  handle a stripe (handle_stripe()) *     setSTRIPE_ACTIVE,  clrSTRIPE_HANDLE ... *		(lockdev check-buffers unlockdev) .. *		change-state .. *		record io/ops needed clearSTRIPE_ACTIVE schedule io/ops *  release an active stripe (release_stripe()) *     lockdev if (!--cnt) { if  STRIPE_HANDLE, add to handle_list else add to inactive-list } unlockdev * * The refcount counts each thread that have activated the stripe, * plus raid5d if it is handling it, plus one for each active request * on a cached buffer, and plus one if the stripe is undergoing stripe * operations. * * The stripe operations are: * -copying data between the stripe cache and user application buffers * -computing blocks to save a disk access, or to recover a missing block * -updating the parity on a write operation (reconstruct write and *  read-modify-write) * -checking parity correctness * -running i/o to disk * These operations are carried out by raid5_run_ops which uses the async_tx * api to (optionally) offload operations to dedicated hardware engines. * When requesting an operation handle_stripe sets the pending bit for the * operation and increments the count.  raid5_run_ops is then run whenever * the count is non-zero. * There are some critical dependencies between the operations that prevent some * from being requested while another is in flight. * 1/ Parity check operations destroy the in cache version of the parity block, *    so we prevent parity dependent operations like writes and compute_blocks *    from starting while a check is in progress.  Some dma engines can perform *    the check without damaging the parity block, in these cases the parity *    block is re-marked up to date (assuming the check was successful) and is *    not re-read from disk. * 2/ When a write operation is requested we immediately lock the affected *    blocks, and mark them as not up to date.  This causes new read requests *    to be held off, as well as parity checks and compute block operations. * 3/ Once a compute block operation has been requested handle_stripe treats *    that block as if it is up to date.  raid5_run_ops guaruntees that any *    operation that is dependent on the compute block result is initiated after *    the compute block completes. */ /* * Operations state - intermediate states that are visible outside of  *   STRIPE_ACTIVE. * In general _idle indicates nothing is running, _run indicates a data * processing operation is active, and _result means the data processing result * is stable and can be acted upon.  For simple operations like biofill and * compute that only have an _idle and _run state they are indicated with * sh->state flags (STRIPE_BIOFILL_RUN and STRIPE_COMPUTE_RUN) *//** * enum check_states - handles syncing / repairing a stripe * @check_state_idle - check operations are quiesced * @check_state_run - check operation is running * @check_state_result - set outside lock when check result is valid * @check_state_compute_run - check failed and we are repairing * @check_state_compute_result - set outside lock when compute result is valid */enum check_states {	check_state_idle = 0,	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,}; /** * enum reconstruct_states - handles writing or expanding a stripe */enum reconstruct_states {	reconstruct_state_idle = 0,	reconstruct_state_prexor_drain_run,	/* prexor-write */	reconstruct_state_drain_run,		/* write */	reconstruct_state_run,			/* expand */	reconstruct_state_prexor_drain_result,	reconstruct_state_drain_result,	reconstruct_state_result,}; struct stripe_head {	struct hlist_node	hash;	struct list_head	lru;	      /* inactive_list or handle_list */	struct r5conf		*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 */	int			bm_seq;	/* sequence number for bitmap flushes */	int			disks;		/* disks in stripe */	enum check_states	check_state;	enum reconstruct_states reconstruct_state;	/**	 * 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, 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 {		/* rreq and rvec are used for the replacement device when		 * writing data to both devices.		 */		struct bio	req, rreq;		struct bio_vec	vec, rvec;		struct page	*page;		struct bio	*toread, *read, *towrite, *written;		sector_t	sector;			/* sector of this page */		unsigned long	flags;	} dev[1]; /* allocated with extra space depending of RAID geometry */}; /* stripe_head_state - collects and tracks the dynamic state of a stripe_head *     for handle_stripe. */struct stripe_head_state {	/* 'syncing' means that we need to read all devices, either	 * to check/correct parity, or to reconstruct a missing device.	 * 'replacing' means we are replacing one or more drives and	 * the source is valid at this point so we don't need to	 * read all devices, just the replacement targets.	 */	int syncing, expanding, expanded, replacing;	int locked, uptodate, to_read, to_write, failed, written;	int to_fill, compute, req_compute, non_overwrite;	int failed_num[2];	int p_failed, q_failed;	int dec_preread_active;	unsigned long ops_request; 	struct bio *return_bi;	struct md_rdev *blocked_rdev;	int handle_bad_blocks;}; /* Flags for struct r5dev.flags */enum r5dev_flags {	R5_UPTODATE,	/* page contains current data */	R5_LOCKED,	/* IO has been submitted on "req" */	R5_DOUBLE_LOCKED,/* Cannot clear R5_LOCKED until 2 writes complete */	R5_OVERWRITE,	/* towrite covers whole page *//* and some that are internal to handle_stripe */	R5_Insync,	/* rdev && rdev->in_sync at start */	R5_Wantread,	/* want to schedule a read */	R5_Wantwrite,	R5_Overlap,	/* There is a pending overlapping request			 * on this block */	R5_ReadError,	/* seen a read error here recently */	R5_ReWrite,	/* have tried to over-write the readerror */ 	R5_Expanded,	/* This block now has post-expand data */	R5_Wantcompute,	/* compute_block in progress treat as			 * uptodate			 */	R5_Wantfill,	/* dev->toread contains a bio that needs			 * filling			 */	R5_Wantdrain,	/* dev->towrite needs to be drained */	R5_WantFUA,	/* Write should be FUA */	R5_SyncIO,	/* The IO is sync */	R5_WriteError,	/* got a write error - need to record it */	R5_MadeGood,	/* A bad block has been fixed by writing to it */	R5_ReadRepl,	/* Will/did read from replacement rather than orig */	R5_MadeGoodRepl,/* A bad block on the replacement device has been			 * fixed by writing to it */	R5_NeedReplace,	/* This device has a replacement which is not			 * up-to-date at this stripe. */	R5_WantReplace, /* We need to update the replacement, we have read			 * data in, and now is a good time to write it out.			 */}; /* * Stripe state */enum {	STRIPE_ACTIVE,	STRIPE_HANDLE,	STRIPE_SYNC_REQUESTED,	STRIPE_SYNCING,	STRIPE_INSYNC,	STRIPE_PREREAD_ACTIVE,	STRIPE_DELAYED,	STRIPE_DEGRADED,	STRIPE_BIT_DELAY,	STRIPE_EXPANDING,	STRIPE_EXPAND_SOURCE,	STRIPE_EXPAND_READY,	STRIPE_IO_STARTED,	/* do not count towards 'bypass_count' */	STRIPE_FULL_WRITE,	/* all blocks are set to be overwritten */	STRIPE_BIOFILL_RUN,	STRIPE_COMPUTE_RUN,	STRIPE_OPS_REQ_PENDING,}; /* * Operation request flags */enum {	STRIPE_OP_BIOFILL,	STRIPE_OP_COMPUTE_BLK,	STRIPE_OP_PREXOR,	STRIPE_OP_BIODRAIN,	STRIPE_OP_RECONSTRUCT,	STRIPE_OP_CHECK,};/* * Plugging: * * To improve write throughput, we need to delay the handling of some * stripes until there has been a chance that several write requests * for the one stripe have all been collected. * In particular, any write request that would require pre-reading * is put on a "delayed" queue until there are no stripes currently * in a pre-read phase.  Further, if the "delayed" queue is empty when * a stripe is put on it then we "plug" the queue and do not process it * until an unplug call is made. (the unplug_io_fn() is called). * * When preread is initiated on a stripe, we set PREREAD_ACTIVE and add * it to the count of prereading stripes. * When write is initiated, or the stripe refcnt == 0 (just in case) we * clear the PREREAD_ACTIVE flag and decrement the count * Whenever the 'handle' queue is empty and the device is not plugged, we * move any strips from delayed to handle and clear the DELAYED flag and set * PREREAD_ACTIVE. * In stripe_handle, if we find pre-reading is necessary, we do it if * PREREAD_ACTIVE is set, else we set DELAYED which will send it to the delayed queue. * HANDLE gets cleared if stripe_handle leaves nothing locked. */  struct disk_info {	struct md_rdev	*rdev, *replacement;}; struct r5conf {	struct hlist_head	*stripe_hashtbl;	struct mddev		*mddev;	int			chunk_sectors;	int			level, algorithm;	int			max_degraded;	int			raid_disks;	int			max_nr_stripes; 	/* 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 */	long long		min_offset_diff; /* minimum difference between						  * data_offset and						  * new_data_offset across all						  * devices.  May be negative,						  * but is closest to zero.						  */ 	struct list_head	handle_list; /* stripes needing handling */	struct list_head	hold_list; /* preread ready stripes */	struct list_head	delayed_list; /* stripes that have plugged requests */	struct list_head	bitmap_list; /* stripes delaying awaiting bitmap update */	struct bio		*retry_read_aligned; /* currently retrying aligned bios   */	struct bio		*retry_read_aligned_list; /* aligned bios retry list  */	atomic_t		preread_active_stripes; /* stripes with scheduled io */	atomic_t		active_aligned_reads;	atomic_t		pending_full_writes; /* full write backlog */	int			bypass_count; /* bypassed prereads */	int			bypass_threshold; /* preread nice */	struct list_head	*last_hold; /* detect hold_list promotions */ 	atomic_t		reshape_stripes; /* stripes with pending writes for reshape */	/* unfortunately we need two cache names as we temporarily have	 * two caches.	 */	int			active_name;	char			cache_name[2][32];	struct kmem_cache		*slab_cache; /* for allocating stripes */ 	int			seq_flush, seq_write;	int			quiesce; 	int			fullsync;  /* set to 1 if a full sync is needed,					    * (fresh device added).					    * Cleared when a sync completes.					    */	int			recovery_disabled;	/* 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	 */	atomic_t		active_stripes;	struct list_head	inactive_list;	wait_queue_head_t	wait_for_stripe;	wait_queue_head_t	wait_for_overlap;	int			inactive_blocked;	/* release of inactive stripes blocked,							 * waiting for 25% to be free							 */	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 md_thread	*thread;}; /* * Our supported algorithms */#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

Lines 1–500 of 526. Load more