/* drbd_int.h This file is part of DRBD by Philipp Reisner and Lars Ellenberg. Copyright (C) 2001-2008, LINBIT Information Technologies GmbH. Copyright (C) 1999-2008, Philipp Reisner . Copyright (C) 2002-2008, Lars Ellenberg . drbd is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2, or (at your option) any later version. drbd is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with drbd; see the file COPYING. If not, write to the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. */ #ifndef _DRBD_INT_H #define _DRBD_INT_H #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #ifdef __CHECKER__ # define __protected_by(x) __attribute__((require_context(x,1,999,"rdwr"))) # define __protected_read_by(x) __attribute__((require_context(x,1,999,"read"))) # define __protected_write_by(x) __attribute__((require_context(x,1,999,"write"))) # define __must_hold(x) __attribute__((context(x,1,1), require_context(x,1,999,"call"))) #else # define __protected_by(x) # define __protected_read_by(x) # define __protected_write_by(x) # define __must_hold(x) #endif #define __no_warn(lock, stmt) do { __acquire(lock); stmt; __release(lock); } while (0) /* module parameter, defined in drbd_main.c */ extern unsigned int minor_count; extern int disable_sendpage; extern int allow_oos; extern unsigned int cn_idx; #ifdef CONFIG_DRBD_FAULT_INJECTION extern int enable_faults; extern int fault_rate; extern int fault_devs; #endif extern char usermode_helper[]; #ifndef TRUE #define TRUE 1 #endif #ifndef FALSE #define FALSE 0 #endif /* I don't remember why XCPU ... * This is used to wake the asender, * and to interrupt sending the sending task * on disconnect. */ #define DRBD_SIG SIGXCPU /* This is used to stop/restart our threads. * Cannot use SIGTERM nor SIGKILL, since these * are sent out by init on runlevel changes * I choose SIGHUP for now. */ #define DRBD_SIGKILL SIGHUP /* All EEs on the free list should have ID_VACANT (== 0) * freshly allocated EEs get !ID_VACANT (== 1) * so if it says "cannot dereference null pointer at adress 0x00000001", * it is most likely one of these :( */ #define ID_IN_SYNC (4711ULL) #define ID_OUT_OF_SYNC (4712ULL) #define ID_SYNCER (-1ULL) #define ID_VACANT 0 #define is_syncer_block_id(id) ((id) == ID_SYNCER) struct drbd_conf; /* to shorten dev_warn(DEV, "msg"); and relatives statements */ #define DEV (disk_to_dev(mdev->vdisk)) #define D_ASSERT(exp) if (!(exp)) \ dev_err(DEV, "ASSERT( " #exp " ) in %s:%d\n", __FILE__, __LINE__) #define ERR_IF(exp) if (({ \ int _b = (exp) != 0; \ if (_b) dev_err(DEV, "%s: (%s) in %s:%d\n", \ __func__, #exp, __FILE__, __LINE__); \ _b; \ })) /* Defines to control fault insertion */ enum { DRBD_FAULT_MD_WR = 0, /* meta data write */ DRBD_FAULT_MD_RD = 1, /* read */ DRBD_FAULT_RS_WR = 2, /* resync */ DRBD_FAULT_RS_RD = 3, DRBD_FAULT_DT_WR = 4, /* data */ DRBD_FAULT_DT_RD = 5, DRBD_FAULT_DT_RA = 6, /* data read ahead */ DRBD_FAULT_BM_ALLOC = 7, /* bitmap allocation */ DRBD_FAULT_AL_EE = 8, /* alloc ee */ DRBD_FAULT_MAX, }; #ifdef CONFIG_DRBD_FAULT_INJECTION extern unsigned int _drbd_insert_fault(struct drbd_conf *mdev, unsigned int type); static inline int drbd_insert_fault(struct drbd_conf *mdev, unsigned int type) { return fault_rate && (enable_faults & (1< P_MAY_IGNORE) ... */ P_MAX_OPT_CMD = 0x101, /* special command ids for handshake */ P_HAND_SHAKE_M = 0xfff1, /* First Packet on the MetaSock */ P_HAND_SHAKE_S = 0xfff2, /* First Packet on the Socket */ P_HAND_SHAKE = 0xfffe /* FIXED for the next century! */ }; static inline const char *cmdname(enum drbd_packets cmd) { /* THINK may need to become several global tables * when we want to support more than * one PRO_VERSION */ static const char *cmdnames[] = { [P_DATA] = "Data", [P_DATA_REPLY] = "DataReply", [P_RS_DATA_REPLY] = "RSDataReply", [P_BARRIER] = "Barrier", [P_BITMAP] = "ReportBitMap", [P_BECOME_SYNC_TARGET] = "BecomeSyncTarget", [P_BECOME_SYNC_SOURCE] = "BecomeSyncSource", [P_UNPLUG_REMOTE] = "UnplugRemote", [P_DATA_REQUEST] = "DataRequest", [P_RS_DATA_REQUEST] = "RSDataRequest", [P_SYNC_PARAM] = "SyncParam", [P_SYNC_PARAM89] = "SyncParam89", [P_PROTOCOL] = "ReportProtocol", [P_UUIDS] = "ReportUUIDs", [P_SIZES] = "ReportSizes", [P_STATE] = "ReportState", [P_SYNC_UUID] = "ReportSyncUUID", [P_AUTH_CHALLENGE] = "AuthChallenge", [P_AUTH_RESPONSE] = "AuthResponse", [P_PING] = "Ping", [P_PING_ACK] = "PingAck", [P_RECV_ACK] = "RecvAck", [P_WRITE_ACK] = "WriteAck", [P_RS_WRITE_ACK] = "RSWriteAck", [P_DISCARD_ACK] = "DiscardAck", [P_NEG_ACK] = "NegAck", [P_NEG_DREPLY] = "NegDReply", [P_NEG_RS_DREPLY] = "NegRSDReply", [P_BARRIER_ACK] = "BarrierAck", [P_STATE_CHG_REQ] = "StateChgRequest", [P_STATE_CHG_REPLY] = "StateChgReply", [P_OV_REQUEST] = "OVRequest", [P_OV_REPLY] = "OVReply", [P_OV_RESULT] = "OVResult", [P_MAX_CMD] = NULL, }; if (cmd == P_HAND_SHAKE_M) return "HandShakeM"; if (cmd == P_HAND_SHAKE_S) return "HandShakeS"; if (cmd == P_HAND_SHAKE) return "HandShake"; if (cmd >= P_MAX_CMD) return "Unknown"; return cmdnames[cmd]; } /* for sending/receiving the bitmap, * possibly in some encoding scheme */ struct bm_xfer_ctx { /* "const" * stores total bits and long words * of the bitmap, so we don't need to * call the accessor functions over and again. */ unsigned long bm_bits; unsigned long bm_words; /* during xfer, current position within the bitmap */ unsigned long bit_offset; unsigned long word_offset; /* statistics; index: (h->command == P_BITMAP) */ unsigned packets[2]; unsigned bytes[2]; }; extern void INFO_bm_xfer_stats(struct drbd_conf *mdev, const char *direction, struct bm_xfer_ctx *c); static inline void bm_xfer_ctx_bit_to_word_offset(struct bm_xfer_ctx *c) { /* word_offset counts "native long words" (32 or 64 bit), * aligned at 64 bit. * Encoded packet may end at an unaligned bit offset. * In case a fallback clear text packet is transmitted in * between, we adjust this offset back to the last 64bit * aligned "native long word", which makes coding and decoding * the plain text bitmap much more convenient. */ #if BITS_PER_LONG == 64 c->word_offset = c->bit_offset >> 6; #elif BITS_PER_LONG == 32 c->word_offset = c->bit_offset >> 5; c->word_offset &= ~(1UL); #else # error "unsupported BITS_PER_LONG" #endif } #ifndef __packed #define __packed __attribute__((packed)) #endif /* This is the layout for a packet on the wire. * The byteorder is the network byte order. * (except block_id and barrier fields. * these are pointers to local structs * and have no relevance for the partner, * which just echoes them as received.) * * NOTE that the payload starts at a long aligned offset, * regardless of 32 or 64 bit arch! */ struct p_header { u32 magic; u16 command; u16 length; /* bytes of data after this header */ u8 payload[0]; } __packed; /* 8 bytes. packet FIXED for the next century! */ /* * short commands, packets without payload, plain p_header: * P_PING * P_PING_ACK * P_BECOME_SYNC_TARGET * P_BECOME_SYNC_SOURCE * P_UNPLUG_REMOTE */ /* * commands with out-of-struct payload: * P_BITMAP (no additional fields) * P_DATA, P_DATA_REPLY (see p_data) * P_COMPRESSED_BITMAP (see receive_compressed_bitmap) */ /* these defines must not be changed without changing the protocol version */ #define DP_HARDBARRIER 1 #define DP_RW_SYNC 2 #define DP_MAY_SET_IN_SYNC 4 struct p_data { struct p_header head; u64 sector; /* 64 bits sector number */ u64 block_id; /* to identify the request in protocol B&C */ u32 seq_num; u32 dp_flags; } __packed; /* * commands which share a struct: * p_block_ack: * P_RECV_ACK (proto B), P_WRITE_ACK (proto C), * P_DISCARD_ACK (proto C, two-primaries conflict detection) * p_block_req: * P_DATA_REQUEST, P_RS_DATA_REQUEST */ struct p_block_ack { struct p_header head; u64 sector; u64 block_id; u32 blksize; u32 seq_num; } __packed; struct p_block_req { struct p_header head; u64 sector; u64 block_id; u32 blksize; u32 pad; /* to multiple of 8 Byte */ } __packed; /* * commands with their own struct for additional fields: * P_HAND_SHAKE * P_BARRIER * P_BARRIER_ACK * P_SYNC_PARAM * ReportParams */ struct p_handshake { struct p_header head; /* 8 bytes */ u32 protocol_min; u32 feature_flags; u32 protocol_max; /* should be more than enough for future enhancements * for now, feature_flags and the reserverd array shall be zero. */ u32 _pad; u64 reserverd[7]; } __packed; /* 80 bytes, FIXED for the next century */ struct p_barrier { struct p_header head; u32 barrier; /* barrier number _handle_ only */ u32 pad; /* to multiple of 8 Byte */ } __packed; struct p_barrier_ack { struct p_header head; u32 barrier; u32 set_size; } __packed; struct p_rs_param { struct p_header head; u32 rate; /* Since protocol version 88 and higher. */ char verify_alg[0]; } __packed; struct p_rs_param_89 { struct p_header head; u32 rate; /* protocol version 89: */ char verify_alg[SHARED_SECRET_MAX]; char csums_alg[SHARED_SECRET_MAX]; } __packed; struct p_protocol { struct p_header head; u32 protocol; u32 after_sb_0p; u32 after_sb_1p; u32 after_sb_2p; u32 want_lose; u32 two_primaries; /* Since protocol version 87 and higher. */ char integrity_alg[0]; } __packed; struct p_uuids { struct p_header head; u64 uuid[UI_EXTENDED_SIZE]; } __packed; struct p_rs_uuid { struct p_header head; u64 uuid; } __packed; struct p_sizes { struct p_header head; u64 d_size; /* size of disk */ u64 u_size; /* user requested size */ u64 c_size; /* current exported size */ u32 max_segment_size; /* Maximal size of a BIO */ u32 queue_order_type; } __packed; struct p_state { struct p_header head; u32 state; } __packed; struct p_req_state { struct p_header head; u32 mask; u32 val; } __packed; struct p_req_state_reply { struct p_header head; u32 retcode; } __packed; struct p_drbd06_param { u64 size; u32 state; u32 blksize; u32 protocol; u32 version; u32 gen_cnt[5]; u32 bit_map_gen[5]; } __packed; struct p_discard { struct p_header head; u64 block_id; u32 seq_num; u32 pad; } __packed; /* Valid values for the encoding field. * Bump proto version when changing this. */ enum drbd_bitmap_code { /* RLE_VLI_Bytes = 0, * and other bit variants had been defined during * algorithm evaluation. */ RLE_VLI_Bits = 2, }; struct p_compressed_bm { struct p_header head; /* (encoding & 0x0f): actual encoding, see enum drbd_bitmap_code * (encoding & 0x80): polarity (set/unset) of first runlength * ((encoding >> 4) & 0x07): pad_bits, number of trailing zero bits * used to pad up to head.length bytes */ u8 encoding; u8 code[0]; } __packed; /* DCBP: Drbd Compressed Bitmap Packet ... */ static inline enum drbd_bitmap_code DCBP_get_code(struct p_compressed_bm *p) { return (enum drbd_bitmap_code)(p->encoding & 0x0f); } static inline void DCBP_set_code(struct p_compressed_bm *p, enum drbd_bitmap_code code) { BUG_ON(code & ~0xf); p->encoding = (p->encoding & ~0xf) | code; } static inline int DCBP_get_start(struct p_compressed_bm *p) { return (p->encoding & 0x80) != 0; } static inline void DCBP_set_start(struct p_compressed_bm *p, int set) { p->encoding = (p->encoding & ~0x80) | (set ? 0x80 : 0); } static inline int DCBP_get_pad_bits(struct p_compressed_bm *p) { return (p->encoding >> 4) & 0x7; } static inline void DCBP_set_pad_bits(struct p_compressed_bm *p, int n) { BUG_ON(n & ~0x7); p->encoding = (p->encoding & (~0x7 << 4)) | (n << 4); } /* one bitmap packet, including the p_header, * should fit within one _architecture independend_ page. * so we need to use the fixed size 4KiB page size * most architechtures have used for a long time. */ #define BM_PACKET_PAYLOAD_BYTES (4096 - sizeof(struct p_header)) #define BM_PACKET_WORDS (BM_PACKET_PAYLOAD_BYTES/sizeof(long)) #define BM_PACKET_VLI_BYTES_MAX (4096 - sizeof(struct p_compressed_bm)) #if (PAGE_SIZE < 4096) /* drbd_send_bitmap / receive_bitmap would break horribly */ #error "PAGE_SIZE too small" #endif union p_polymorph { struct p_header header; struct p_handshake handshake; struct p_data data; struct p_block_ack block_ack; struct p_barrier barrier; struct p_barrier_ack barrier_ack; struct p_rs_param_89 rs_param_89; struct p_protocol protocol; struct p_sizes sizes; struct p_uuids uuids; struct p_state state; struct p_req_state req_state; struct p_req_state_reply req_state_reply; struct p_block_req block_req; } __packed; /**********************************************************************/ enum drbd_thread_state { None, Running, Exiting, Restarting }; struct drbd_thread { spinlock_t t_lock; struct task_struct *task; struct completion stop; enum drbd_thread_state t_state; int (*function) (struct drbd_thread *); struct drbd_conf *mdev; int reset_cpu_mask; }; static inline enum drbd_thread_state get_t_state(struct drbd_thread *thi) { /* THINK testing the t_state seems to be uncritical in all cases * (but thread_{start,stop}), so we can read it *without* the lock. * --lge */ smp_rmb(); return thi->t_state; } /* * Having this as the first member of a struct provides sort of "inheritance". * "derived" structs can be "drbd_queue_work()"ed. * The callback should know and cast back to the descendant struct. * drbd_request and drbd_epoch_entry are descendants of drbd_work. */ struct drbd_work; typedef int (*drbd_work_cb)(struct drbd_conf *, struct drbd_work *, int cancel); struct drbd_work { struct list_head list; drbd_work_cb cb; }; struct drbd_tl_epoch; struct drbd_request { struct drbd_work w; struct drbd_conf *mdev; /* if local IO is not allowed, will be NULL. * if local IO _is_ allowed, holds the locally submitted bio clone, * or, after local IO completion, the ERR_PTR(error). * see drbd_endio_pri(). */ struct bio *private_bio; struct hlist_node colision; sector_t sector; unsigned int size; unsigned int epoch; /* barrier_nr */ /* barrier_nr: used to check on "completion" whether this req was in * the current epoch, and we therefore have to close it, * starting a new epoch... */ /* up to here, the struct layout is identical to drbd_epoch_entry; * we might be able to use that to our advantage... */ struct list_head tl_requests; /* ring list in the transfer log */ struct bio *master_bio; /* master bio pointer */ unsigned long rq_state; /* see comments above _req_mod() */ int seq_num; unsigned long start_time; }; struct drbd_tl_epoch { struct drbd_work w; struct list_head requests; /* requests before */ struct drbd_tl_epoch *next; /* pointer to the next barrier */ unsigned int br_number; /* the barriers identifier. */ int n_req; /* number of requests attached before this barrier */ }; struct drbd_request; /* These Tl_epoch_entries may be in one of 6 lists: active_ee .. data packet being written sync_ee .. syncer block being written done_ee .. block written, need to send P_WRITE_ACK read_ee .. [RS]P_DATA_REQUEST being read */ struct drbd_epoch { struct list_head list; unsigned int barrier_nr; atomic_t epoch_size; /* increased on every request added. */ atomic_t active; /* increased on every req. added, and dec on every finished. */ unsigned long flags; }; /* drbd_epoch flag bits */ enum { DE_BARRIER_IN_NEXT_EPOCH_ISSUED, DE_BARRIER_IN_NEXT_EPOCH_DONE, DE_CONTAINS_A_BARRIER, DE_HAVE_BARRIER_NUMBER, DE_IS_FINISHING, }; enum epoch_event { EV_PUT, EV_GOT_BARRIER_NR, EV_BARRIER_DONE, EV_BECAME_LAST, EV_CLEANUP = 32, /* used as flag */ }; struct drbd_epoch_entry { struct drbd_work w; struct drbd_conf *mdev; struct bio *private_bio; struct hlist_node colision; sector_t sector; unsigned int size; struct drbd_epoch *epoch; /* up to here, the struct layout is identical to drbd_request; * we might be able to use that to our advantage... */ unsigned int flags; u64 block_id; }; struct drbd_wq_barrier { struct drbd_work w; struct completion done; }; struct digest_info { int digest_size; void *digest; }; /* ee flag bits */ enum { __EE_CALL_AL_COMPLETE_IO, __EE_CONFLICT_PENDING, __EE_MAY_SET_IN_SYNC, __EE_IS_BARRIER, }; #define EE_CALL_AL_COMPLETE_IO (1<<__EE_CALL_AL_COMPLETE_IO) #define EE_CONFLICT_PENDING (1<<__EE_CONFLICT_PENDING) #define EE_MAY_SET_IN_SYNC (1<<__EE_MAY_SET_IN_SYNC) #define EE_IS_BARRIER (1<<__EE_IS_BARRIER) /* global flag bits */ enum { CREATE_BARRIER, /* next P_DATA is preceeded by a P_BARRIER */ SIGNAL_ASENDER, /* whether asender wants to be interrupted */ SEND_PING, /* whether asender should send a ping asap */ STOP_SYNC_TIMER, /* tell timer to cancel itself */ UNPLUG_QUEUED, /* only relevant with kernel 2.4 */ UNPLUG_REMOTE, /* sending a "UnplugRemote" could help */ MD_DIRTY, /* current uuids and flags not yet on disk */ DISCARD_CONCURRENT, /* Set on one node, cleared on the peer! */ USE_DEGR_WFC_T, /* degr-wfc-timeout instead of wfc-timeout. */ CLUSTER_ST_CHANGE, /* Cluster wide state change going on... */ CL_ST_CHG_SUCCESS, CL_ST_CHG_FAIL, CRASHED_PRIMARY, /* This node was a crashed primary. * Gets cleared when the state.conn * goes into C_CONNECTED state. */ WRITE_BM_AFTER_RESYNC, /* A kmalloc() during resync failed */ NO_BARRIER_SUPP, /* underlying block device doesn't implement barriers */ CONSIDER_RESYNC, MD_NO_BARRIER, /* meta data device does not support barriers, so don't even try */ SUSPEND_IO, /* suspend application io */ BITMAP_IO, /* suspend application io; once no more io in flight, start bitmap io */ BITMAP_IO_QUEUED, /* Started bitmap IO */ RESYNC_AFTER_NEG, /* Resync after online grow after the attach&negotiate finished. */ NET_CONGESTED, /* The data socket is congested */ CONFIG_PENDING, /* serialization of (re)configuration requests. * if set, also prevents the device from dying */ DEVICE_DYING, /* device became unconfigured, * but worker thread is still handling the cleanup. * reconfiguring (nl_disk_conf, nl_net_conf) is dissalowed, * while this is set. */ RESIZE_PENDING, /* Size change detected locally, waiting for the response from * the peer, if it changed there as well. */ }; struct drbd_bitmap; /* opaque for drbd_conf */ /* TODO sort members for performance * MAYBE group them further */ /* THINK maybe we actually want to use the default "event/%s" worker threads * or similar in linux 2.6, which uses per cpu data and threads. * * To be general, this might need a spin_lock member. * For now, please use the mdev->req_lock to protect list_head, * see drbd_queue_work below. */ struct drbd_work_queue { struct list_head q; struct semaphore s; /* producers up it, worker down()s it */ spinlock_t q_lock; /* to protect the list. */ }; struct drbd_socket { struct drbd_work_queue work; struct mutex mutex; struct socket *socket; /* this way we get our * send/receive buffers off the stack */ union p_polymorph sbuf; union p_polymorph rbuf; }; struct drbd_md { u64 md_offset; /* sector offset to 'super' block */ u64 la_size_sect; /* last agreed size, unit sectors */ u64 uuid[UI_SIZE]; u64 device_uuid; u32 flags; u32 md_size_sect; s32 al_offset; /* signed relative sector offset to al area */ s32 bm_offset; /* signed relative sector offset to bitmap */ /* u32 al_nr_extents; important for restoring the AL * is stored into sync_conf.al_extents, which in turn * gets applied to act_log->nr_elements */ }; /* for sync_conf and other types... */ #define NL_PACKET(name, number, fields) struct name { fields }; #define NL_INTEGER(pn,pr,member) int member; #define NL_INT64(pn,pr,member) __u64 member; #define NL_BIT(pn,pr,member) unsigned member:1; #define NL_STRING(pn,pr,member,len) unsigned char member[len]; int member ## _len; #include "linux/drbd_nl.h" struct drbd_backing_dev { struct block_device *backing_bdev; struct block_device *md_bdev; struct file *lo_file; struct file *md_file; struct drbd_md md; struct disk_conf dc; /* The user provided config... */ sector_t known_size; /* last known size of that backing device */ }; struct drbd_md_io { struct drbd_conf *mdev; struct completion event; int error; }; struct bm_io_work { struct drbd_work w; char *why; int (*io_fn)(struct drbd_conf *mdev); void (*done)(struct drbd_conf *mdev, int rv); }; enum write_ordering_e { WO_none, WO_drain_io, WO_bdev_flush, WO_bio_barrier }; struct drbd_conf { /* things that are stored as / read from meta data on disk */ unsigned long flags; /* configured by drbdsetup */ struct net_conf *net_conf; /* protected by get_net_conf() and put_net_conf() */ struct syncer_conf sync_conf; struct drbd_backing_dev *ldev __protected_by(local); sector_t p_size; /* partner's disk size */ struct request_queue *rq_queue; struct block_device *this_bdev; struct gendisk *vdisk; struct drbd_socket data; /* data/barrier/cstate/parameter packets */ struct drbd_socket meta; /* ping/ack (metadata) packets */ int agreed_pro_version; /* actually used protocol version */ unsigned long last_received; /* in jiffies, either socket */ unsigned int ko_count; struct drbd_work resync_work, unplug_work, md_sync_work; struct timer_list resync_timer; struct timer_list md_sync_timer; /* Used after attach while negotiating new disk state. */ union drbd_state new_state_tmp; union drbd_state state; wait_queue_head_t misc_wait; wait_queue_head_t state_wait; /* upon each state change. */ unsigned int send_cnt; unsigned int recv_cnt; unsigned int read_cnt; unsigned int writ_cnt; unsigned int al_writ_cnt; unsigned int bm_writ_cnt; atomic_t ap_bio_cnt; /* Requests we need to complete */ atomic_t ap_pending_cnt; /* AP data packets on the wire, ack expected */ atomic_t rs_pending_cnt; /* RS request/data packets on the wire */ atomic_t unacked_cnt; /* Need to send replys for */ atomic_t local_cnt; /* Waiting for local completion */ atomic_t net_cnt; /* Users of net_conf */ spinlock_t req_lock; struct drbd_tl_epoch *unused_spare_tle; /* for pre-allocation */ struct drbd_tl_epoch *newest_tle; struct drbd_tl_epoch *oldest_tle; struct list_head out_of_sequence_requests; struct hlist_head *tl_hash; unsigned int tl_hash_s; /* blocks to sync in this run [unit BM_BLOCK_SIZE] */ unsigned long rs_total; /* number of sync IOs that failed in this run */ unsigned long rs_failed; /* Syncer's start time [unit jiffies] */ unsigned long rs_start; /* cumulated time in PausedSyncX state [unit jiffies] */ unsigned long rs_paused; /* block not up-to-date at mark [unit BM_BLOCK_SIZE] */ unsigned long rs_mark_left; /* marks's time [unit jiffies] */ unsigned long rs_mark_time; /* skipped because csum was equeal [unit BM_BLOCK_SIZE] */ unsigned long rs_same_csum; /* where does the admin want us to start? (sector) */ sector_t ov_start_sector; /* where are we now? (sector) */ sector_t ov_position; /* Start sector of out of sync range (to merge printk reporting). */ sector_t ov_last_oos_start; /* size of out-of-sync range in sectors. */ sector_t ov_last_oos_size; unsigned long ov_left; /* in bits */ struct crypto_hash *csums_tfm; struct crypto_hash *verify_tfm; struct drbd_thread receiver; struct drbd_thread worker; struct drbd_thread asender; struct drbd_bitmap *bitmap; unsigned long bm_resync_fo; /* bit offset for drbd_bm_find_next */ /* Used to track operations of resync... */ struct lru_cache *resync; /* Number of locked elements in resync LRU */ unsigned int resync_locked; /* resync extent number waiting for application requests */ unsigned int resync_wenr; int open_cnt; u64 *p_uuid; struct drbd_epoch *current_epoch; spinlock_t epoch_lock; unsigned int epochs; enum write_ordering_e write_ordering; struct list_head active_ee; /* IO in progress */ struct list_head sync_ee; /* IO in progress */ struct list_head done_ee; /* send ack */ struct list_head read_ee; /* IO in progress */ struct list_head net_ee; /* zero-copy network send in progress */ struct hlist_head *ee_hash; /* is proteced by req_lock! */ unsigned int ee_hash_s; /* this one is protected by ee_lock, single thread */ struct drbd_epoch_entry *last_write_w_barrier; int next_barrier_nr; struct hlist_head *app_reads_hash; /* is proteced by req_lock */ struct list_head resync_reads; atomic_t pp_in_use; wait_queue_head_t ee_wait; struct page *md_io_page; /* one page buffer for md_io */ struct page *md_io_tmpp; /* for logical_block_size != 512 */ struct mutex md_io_mutex; /* protects the md_io_buffer */ spinlock_t al_lock; wait_queue_head_t al_wait; struct lru_cache *act_log; /* activity log */ unsigned int al_tr_number; int al_tr_cycle; int al_tr_pos; /* position of the next transaction in the journal */ struct crypto_hash *cram_hmac_tfm; struct crypto_hash *integrity_w_tfm; /* to be used by the worker thread */ struct crypto_hash *integrity_r_tfm; /* to be used by the receiver thread */ void *int_dig_out; void *int_dig_in; void *int_dig_vv; wait_queue_head_t seq_wait; atomic_t packet_seq; unsigned int peer_seq; spinlock_t peer_seq_lock; unsigned int minor; unsigned long comm_bm_set; /* communicated number of set bits. */ cpumask_var_t cpu_mask; struct bm_io_work bm_io_work; u64 ed_uuid; /* UUID of the exposed data */ struct mutex state_mutex; char congestion_reason; /* Why we where congested... */ }; static inline struct drbd_conf *minor_to_mdev(unsigned int minor) { struct drbd_conf *mdev; mdev = minor < minor_count ? minor_table[minor] : NULL; return mdev; } static inline unsigned int mdev_to_minor(struct drbd_conf *mdev) { return mdev->minor; } /* returns 1 if it was successfull, * returns 0 if there was no data socket. * so wherever you are going to use the data.socket, e.g. do * if (!drbd_get_data_sock(mdev)) * return 0; * CODE(); * drbd_put_data_sock(mdev); */ static inline int drbd_get_data_sock(struct drbd_conf *mdev) { mutex_lock(&mdev->data.mutex); /* drbd_disconnect() could have called drbd_free_sock() * while we were waiting in down()... */ if (unlikely(mdev->data.socket == NULL)) { mutex_unlock(&mdev->data.mutex); return 0; } return 1; } static inline void drbd_put_data_sock(struct drbd_conf *mdev) { mutex_unlock(&mdev->data.mutex); } /* * function declarations *************************/ /* drbd_main.c */ enum chg_state_flags { CS_HARD = 1, CS_VERBOSE = 2, CS_WAIT_COMPLETE = 4, CS_SERIALIZE = 8, CS_ORDERED = CS_WAIT_COMPLETE + CS_SERIALIZE, }; extern void drbd_init_set_defaults(struct drbd_conf *mdev); extern int drbd_change_state(struct drbd_conf *mdev, enum chg_state_flags f, union drbd_state mask, union drbd_state val); extern void drbd_force_state(struct drbd_conf *, union drbd_state, union drbd_state); extern int _drbd_request_state(struct drbd_conf *, union drbd_state, union drbd_state, enum chg_state_flags); extern int __drbd_set_state(struct drbd_conf *, union drbd_state, enum chg_state_flags, struct completion *done); extern void print_st_err(struct drbd_conf *, union drbd_state, union drbd_state, int); extern int drbd_thread_start(struct drbd_thread *thi); extern void _drbd_thread_stop(struct drbd_thread *thi, int restart, int wait); #ifdef CONFIG_SMP extern void drbd_thread_current_set_cpu(struct drbd_conf *mdev); extern void drbd_calc_cpu_mask(struct drbd_conf *mdev); #else #define drbd_thread_current_set_cpu(A) ({}) #define drbd_calc_cpu_mask(A) ({}) #endif extern void drbd_free_resources(struct drbd_conf *mdev); extern void tl_release(struct drbd_conf *mdev, unsigned int barrier_nr, unsigned int set_size); extern void tl_clear(struct drbd_conf *mdev); extern void _tl_add_barrier(struct drbd_conf *, struct drbd_tl_epoch *); extern void drbd_free_sock(struct drbd_conf *mdev); extern int drbd_send(struct drbd_conf *mdev, struct socket *sock, void *buf, size_t size, unsigned msg_flags); extern int drbd_send_protocol(struct drbd_conf *mdev); extern int drbd_send_uuids(struct drbd_conf *mdev); extern int drbd_send_uuids_skip_initial_sync(struct drbd_conf *mdev); extern int drbd_send_sync_uuid(struct drbd_conf *mdev, u64 val); extern int drbd_send_sizes(struct drbd_conf *mdev, int trigger_reply); extern int _drbd_send_state(struct drbd_conf *mdev); extern int drbd_send_state(struct drbd_conf *mdev); extern int _drbd_send_cmd(struct drbd_conf *mdev, struct socket *sock, enum drbd_packets cmd, struct p_header *h, size_t size, unsigned msg_flags); #define USE_DATA_SOCKET 1 #define USE_META_SOCKET 0 extern int drbd_send_cmd(struct drbd_conf *mdev, int use_data_socket, enum drbd_packets cmd, struct p_header *h, size_t size); extern int drbd_send_cmd2(struct drbd_conf *mdev, enum drbd_packets cmd, char *data, size_t size); extern int drbd_send_sync_param(struct drbd_conf *mdev, struct syncer_conf *sc); extern int drbd_send_b_ack(struct drbd_conf *mdev, u32 barrier_nr, u32 set_size); extern int drbd_send_ack(struct drbd_conf *mdev, enum drbd_packets cmd, struct drbd_epoch_entry *e); extern int drbd_send_ack_rp(struct drbd_conf *mdev, enum drbd_packets cmd, struct p_block_req *rp); extern int drbd_send_ack_dp(struct drbd_conf *mdev, enum drbd_packets cmd, struct p_data *dp); extern int drbd_send_ack_ex(struct drbd_conf *mdev, enum drbd_packets cmd, sector_t sector, int blksize, u64 block_id); extern int drbd_send_block(struct drbd_conf *mdev, enum drbd_packets cmd, struct drbd_epoch_entry *e); extern int drbd_send_dblock(struct drbd_conf *mdev, struct drbd_request *req); extern int _drbd_send_barrier(struct drbd_conf *mdev, struct drbd_tl_epoch *barrier); extern int drbd_send_drequest(struct drbd_conf *mdev, int cmd, sector_t sector, int size, u64 block_id); extern int drbd_send_drequest_csum(struct drbd_conf *mdev, sector_t sector,int size, void *digest, int digest_size, enum drbd_packets cmd); extern int drbd_send_ov_request(struct drbd_conf *mdev,sector_t sector,int size); extern int drbd_send_bitmap(struct drbd_conf *mdev); extern int _drbd_send_bitmap(struct drbd_conf *mdev); extern int drbd_send_sr_reply(struct drbd_conf *mdev, int retcode); extern void drbd_free_bc(struct drbd_backing_dev *ldev); extern void drbd_mdev_cleanup(struct drbd_conf *mdev); /* drbd_meta-data.c (still in drbd_main.c) */ extern void drbd_md_sync(struct drbd_conf *mdev); extern int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev); /* maybe define them below as inline? */ extern void drbd_uuid_set(struct drbd_conf *mdev, int idx, u64 val) __must_hold(local); extern void _drbd_uuid_set(struct drbd_conf *mdev, int idx, u64 val) __must_hold(local); extern void drbd_uuid_new_current(struct drbd_conf *mdev) __must_hold(local); extern void _drbd_uuid_new_current(struct drbd_conf *mdev) __must_hold(local); extern void drbd_uuid_set_bm(struct drbd_conf *mdev, u64 val) __must_hold(local); extern void drbd_md_set_flag(struct drbd_conf *mdev, int flags) __must_hold(local); extern void drbd_md_clear_flag(struct drbd_conf *mdev, int flags)__must_hold(local); extern int drbd_md_test_flag(struct drbd_backing_dev *, int); extern void drbd_md_mark_dirty(struct drbd_conf *mdev); extern void drbd_queue_bitmap_io(struct drbd_conf *mdev, int (*io_fn)(struct drbd_conf *), void (*done)(struct drbd_conf *, int), char *why); extern int drbd_bmio_set_n_write(struct drbd_conf *mdev); extern int drbd_bmio_clear_n_write(struct drbd_conf *mdev); extern int drbd_bitmap_io(struct drbd_conf *mdev, int (*io_fn)(struct drbd_conf *), char *why); /* Meta data layout We reserve a 128MB Block (4k aligned) * either at the end of the backing device * or on a seperate meta data device. */ #define MD_RESERVED_SECT (128LU << 11) /* 128 MB, unit sectors */ /* The following numbers are sectors */ #define MD_AL_OFFSET 8 /* 8 Sectors after start of meta area */ #define MD_AL_MAX_SIZE 64 /* = 32 kb LOG ~ 3776 extents ~ 14 GB Storage */ /* Allows up to about 3.8TB */ #define MD_BM_OFFSET (MD_AL_OFFSET + MD_AL_MAX_SIZE) /* Since the smalles IO unit is usually 512 byte */ #define MD_SECTOR_SHIFT 9 #define MD_SECTOR_SIZE (1< we need 32 KB bitmap. * Bit 0 ==> local node thinks this block is binary identical on both nodes * Bit 1 ==> local node thinks this block needs to be synced. */ #define BM_BLOCK_SHIFT 12 /* 4k per bit */ #define BM_BLOCK_SIZE (1<>(BM_BLOCK_SHIFT-9)) #define BM_BIT_TO_SECT(x) ((sector_t)(x)<<(BM_BLOCK_SHIFT-9)) #define BM_SECT_PER_BIT BM_BIT_TO_SECT(1) /* bit to represented kilo byte conversion */ #define Bit2KB(bits) ((bits)<<(BM_BLOCK_SHIFT-10)) /* in which _bitmap_ extent (resp. sector) the bit for a certain * _storage_ sector is located in */ #define BM_SECT_TO_EXT(x) ((x)>>(BM_EXT_SHIFT-9)) /* how much _storage_ sectors we have per bitmap sector */ #define BM_EXT_TO_SECT(x) ((sector_t)(x) << (BM_EXT_SHIFT-9)) #define BM_SECT_PER_EXT BM_EXT_TO_SECT(1) /* in one sector of the bitmap, we have this many activity_log extents. */ #define AL_EXT_PER_BM_SECT (1 << (BM_EXT_SHIFT - AL_EXTENT_SHIFT)) #define BM_WORDS_PER_AL_EXT (1 << (AL_EXTENT_SHIFT-BM_BLOCK_SHIFT-LN2_BPL)) #define BM_BLOCKS_PER_BM_EXT_B (BM_EXT_SHIFT - BM_BLOCK_SHIFT) #define BM_BLOCKS_PER_BM_EXT_MASK ((1<ov_last_oos_size) { dev_err(DEV, "Out of sync: start=%llu, size=%lu (sectors)\n", (unsigned long long)mdev->ov_last_oos_start, (unsigned long)mdev->ov_last_oos_size); } mdev->ov_last_oos_size=0; } extern void drbd_csum(struct drbd_conf *, struct crypto_hash *, struct bio *, void *); /* worker callbacks */ extern int w_req_cancel_conflict(struct drbd_conf *, struct drbd_work *, int); extern int w_read_retry_remote(struct drbd_conf *, struct drbd_work *, int); extern int w_e_end_data_req(struct drbd_conf *, struct drbd_work *, int); extern int w_e_end_rsdata_req(struct drbd_conf *, struct drbd_work *, int); extern int w_e_end_csum_rs_req(struct drbd_conf *, struct drbd_work *, int); extern int w_e_end_ov_reply(struct drbd_conf *, struct drbd_work *, int); extern int w_e_end_ov_req(struct drbd_conf *, struct drbd_work *, int); extern int w_ov_finished(struct drbd_conf *, struct drbd_work *, int); extern int w_resync_inactive(struct drbd_conf *, struct drbd_work *, int); extern int w_resume_next_sg(struct drbd_conf *, struct drbd_work *, int); extern int w_io_error(struct drbd_conf *, struct drbd_work *, int); extern int w_send_write_hint(struct drbd_conf *, struct drbd_work *, int); extern int w_make_resync_request(struct drbd_conf *, struct drbd_work *, int); extern int w_send_dblock(struct drbd_conf *, struct drbd_work *, int); extern int w_send_barrier(struct drbd_conf *, struct drbd_work *, int); extern int w_send_read_req(struct drbd_conf *, struct drbd_work *, int); extern int w_prev_work_done(struct drbd_conf *, struct drbd_work *, int); extern int w_e_reissue(struct drbd_conf *, struct drbd_work *, int); extern void resync_timer_fn(unsigned long data); /* drbd_receiver.c */ extern int drbd_release_ee(struct drbd_conf *mdev, struct list_head *list); extern struct drbd_epoch_entry *drbd_alloc_ee(struct drbd_conf *mdev, u64 id, sector_t sector, unsigned int data_size, gfp_t gfp_mask) __must_hold(local); extern void drbd_free_ee(struct drbd_conf *mdev, struct drbd_epoch_entry *e); extern void drbd_wait_ee_list_empty(struct drbd_conf *mdev, struct list_head *head); extern void _drbd_wait_ee_list_empty(struct drbd_conf *mdev, struct list_head *head); extern void drbd_set_recv_tcq(struct drbd_conf *mdev, int tcq_enabled); extern void _drbd_clear_done_ee(struct drbd_conf *mdev, struct list_head *to_be_freed); extern void drbd_flush_workqueue(struct drbd_conf *mdev); /* yes, there is kernel_setsockopt, but only since 2.6.18. we don't need to * mess with get_fs/set_fs, we know we are KERNEL_DS always. */ static inline int drbd_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) { int err; if (level == SOL_SOCKET) err = sock_setsockopt(sock, level, optname, optval, optlen); else err = sock->ops->setsockopt(sock, level, optname, optval, optlen); return err; } static inline void drbd_tcp_cork(struct socket *sock) { int __user val = 1; (void) drbd_setsockopt(sock, SOL_TCP, TCP_CORK, (char __user *)&val, sizeof(val)); } static inline void drbd_tcp_uncork(struct socket *sock) { int __user val = 0; (void) drbd_setsockopt(sock, SOL_TCP, TCP_CORK, (char __user *)&val, sizeof(val)); } static inline void drbd_tcp_nodelay(struct socket *sock) { int __user val = 1; (void) drbd_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char __user *)&val, sizeof(val)); } static inline void drbd_tcp_quickack(struct socket *sock) { int __user val = 1; (void) drbd_setsockopt(sock, SOL_TCP, TCP_QUICKACK, (char __user *)&val, sizeof(val)); } void drbd_bump_write_ordering(struct drbd_conf *mdev, enum write_ordering_e wo); /* drbd_proc.c */ extern struct proc_dir_entry *drbd_proc; extern struct file_operations drbd_proc_fops; extern const char *drbd_conn_str(enum drbd_conns s); extern const char *drbd_role_str(enum drbd_role s); /* drbd_actlog.c */ extern void drbd_al_begin_io(struct drbd_conf *mdev, sector_t sector); extern void drbd_al_complete_io(struct drbd_conf *mdev, sector_t sector); extern void drbd_rs_complete_io(struct drbd_conf *mdev, sector_t sector); extern int drbd_rs_begin_io(struct drbd_conf *mdev, sector_t sector); extern int drbd_try_rs_begin_io(struct drbd_conf *mdev, sector_t sector); extern void drbd_rs_cancel_all(struct drbd_conf *mdev); extern int drbd_rs_del_all(struct drbd_conf *mdev); extern void drbd_rs_failed_io(struct drbd_conf *mdev, sector_t sector, int size); extern int drbd_al_read_log(struct drbd_conf *mdev, struct drbd_backing_dev *); extern void __drbd_set_in_sync(struct drbd_conf *mdev, sector_t sector, int size, const char *file, const unsigned int line); #define drbd_set_in_sync(mdev, sector, size) \ __drbd_set_in_sync(mdev, sector, size, __FILE__, __LINE__) extern void __drbd_set_out_of_sync(struct drbd_conf *mdev, sector_t sector, int size, const char *file, const unsigned int line); #define drbd_set_out_of_sync(mdev, sector, size) \ __drbd_set_out_of_sync(mdev, sector, size, __FILE__, __LINE__) extern void drbd_al_apply_to_bm(struct drbd_conf *mdev); extern void drbd_al_to_on_disk_bm(struct drbd_conf *mdev); extern void drbd_al_shrink(struct drbd_conf *mdev); /* drbd_nl.c */ void drbd_nl_cleanup(void); int __init drbd_nl_init(void); void drbd_bcast_state(struct drbd_conf *mdev, union drbd_state); void drbd_bcast_sync_progress(struct drbd_conf *mdev); void drbd_bcast_ee(struct drbd_conf *mdev, const char *reason, const int dgs, const char* seen_hash, const char* calc_hash, const struct drbd_epoch_entry* e); /** * DOC: DRBD State macros * * These macros are used to express state changes in easily readable form. * * The NS macros expand to a mask and a value, that can be bit ored onto the * current state as soon as the spinlock (req_lock) was taken. * * The _NS macros are used for state functions that get called with the * spinlock. These macros expand directly to the new state value. * * Besides the basic forms NS() and _NS() additional _?NS[23] are defined * to express state changes that affect more than one aspect of the state. * * E.g. NS2(conn, C_CONNECTED, peer, R_SECONDARY) * Means that the network connection was established and that the peer * is in secondary role. */ #define role_MASK R_MASK #define peer_MASK R_MASK #define disk_MASK D_MASK #define pdsk_MASK D_MASK #define conn_MASK C_MASK #define susp_MASK 1 #define user_isp_MASK 1 #define aftr_isp_MASK 1 #define NS(T, S) \ ({ union drbd_state mask; mask.i = 0; mask.T = T##_MASK; mask; }), \ ({ union drbd_state val; val.i = 0; val.T = (S); val; }) #define NS2(T1, S1, T2, S2) \ ({ union drbd_state mask; mask.i = 0; mask.T1 = T1##_MASK; \ mask.T2 = T2##_MASK; mask; }), \ ({ union drbd_state val; val.i = 0; val.T1 = (S1); \ val.T2 = (S2); val; }) #define NS3(T1, S1, T2, S2, T3, S3) \ ({ union drbd_state mask; mask.i = 0; mask.T1 = T1##_MASK; \ mask.T2 = T2##_MASK; mask.T3 = T3##_MASK; mask; }), \ ({ union drbd_state val; val.i = 0; val.T1 = (S1); \ val.T2 = (S2); val.T3 = (S3); val; }) #define _NS(D, T, S) \ D, ({ union drbd_state __ns; __ns.i = D->state.i; __ns.T = (S); __ns; }) #define _NS2(D, T1, S1, T2, S2) \ D, ({ union drbd_state __ns; __ns.i = D->state.i; __ns.T1 = (S1); \ __ns.T2 = (S2); __ns; }) #define _NS3(D, T1, S1, T2, S2, T3, S3) \ D, ({ union drbd_state __ns; __ns.i = D->state.i; __ns.T1 = (S1); \ __ns.T2 = (S2); __ns.T3 = (S3); __ns; }) /* * inline helper functions *************************/ static inline void drbd_state_lock(struct drbd_conf *mdev) { wait_event(mdev->misc_wait, !test_and_set_bit(CLUSTER_ST_CHANGE, &mdev->flags)); } static inline void drbd_state_unlock(struct drbd_conf *mdev) { clear_bit(CLUSTER_ST_CHANGE, &mdev->flags); wake_up(&mdev->misc_wait); } static inline int _drbd_set_state(struct drbd_conf *mdev, union drbd_state ns, enum chg_state_flags flags, struct completion *done) { int rv; read_lock(&global_state_lock); rv = __drbd_set_state(mdev, ns, flags, done); read_unlock(&global_state_lock); return rv; } /** * drbd_request_state() - Reqest a state change * @mdev: DRBD device. * @mask: mask of state bits to change. * @val: value of new state bits. * * This is the most graceful way of requesting a state change. It is verbose * quite verbose in case the state change is not possible, and all those * state changes are globally serialized. */ static inline int drbd_request_state(struct drbd_conf *mdev, union drbd_state mask, union drbd_state val) { return _drbd_request_state(mdev, mask, val, CS_VERBOSE + CS_ORDERED); } #define __drbd_chk_io_error(m,f) __drbd_chk_io_error_(m,f, __func__) static inline void __drbd_chk_io_error_(struct drbd_conf *mdev, int forcedetach, const char *where) { switch (mdev->ldev->dc.on_io_error) { case EP_PASS_ON: if (!forcedetach) { if (printk_ratelimit()) dev_err(DEV, "Local IO failed in %s." "Passing error on...\n", where); break; } /* NOTE fall through to detach case if forcedetach set */ case EP_DETACH: case EP_CALL_HELPER: if (mdev->state.disk > D_FAILED) { _drbd_set_state(_NS(mdev, disk, D_FAILED), CS_HARD, NULL); dev_err(DEV, "Local IO failed in %s." "Detaching...\n", where); } break; } } /** * drbd_chk_io_error: Handle the on_io_error setting, should be called from all io completion handlers * @mdev: DRBD device. * @error: Error code passed to the IO completion callback * @forcedetach: Force detach. I.e. the error happened while accessing the meta data * * See also drbd_main.c:after_state_ch() if (os.disk > D_FAILED && ns.disk == D_FAILED) */ #define drbd_chk_io_error(m,e,f) drbd_chk_io_error_(m,e,f, __func__) static inline void drbd_chk_io_error_(struct drbd_conf *mdev, int error, int forcedetach, const char *where) { if (error) { unsigned long flags; spin_lock_irqsave(&mdev->req_lock, flags); __drbd_chk_io_error_(mdev, forcedetach, where); spin_unlock_irqrestore(&mdev->req_lock, flags); } } /** * drbd_md_first_sector() - Returns the first sector number of the meta data area * @bdev: Meta data block device. * * BTW, for internal meta data, this happens to be the maximum capacity * we could agree upon with our peer node. */ static inline sector_t drbd_md_first_sector(struct drbd_backing_dev *bdev) { switch (bdev->dc.meta_dev_idx) { case DRBD_MD_INDEX_INTERNAL: case DRBD_MD_INDEX_FLEX_INT: return bdev->md.md_offset + bdev->md.bm_offset; case DRBD_MD_INDEX_FLEX_EXT: default: return bdev->md.md_offset; } } /** * drbd_md_last_sector() - Return the last sector number of the meta data area * @bdev: Meta data block device. */ static inline sector_t drbd_md_last_sector(struct drbd_backing_dev *bdev) { switch (bdev->dc.meta_dev_idx) { case DRBD_MD_INDEX_INTERNAL: case DRBD_MD_INDEX_FLEX_INT: return bdev->md.md_offset + MD_AL_OFFSET - 1; case DRBD_MD_INDEX_FLEX_EXT: default: return bdev->md.md_offset + bdev->md.md_size_sect; } } /* Returns the number of 512 byte sectors of the device */ static inline sector_t drbd_get_capacity(struct block_device *bdev) { /* return bdev ? get_capacity(bdev->bd_disk) : 0; */ return bdev ? bdev->bd_inode->i_size >> 9 : 0; } /** * drbd_get_max_capacity() - Returns the capacity we announce to out peer * @bdev: Meta data block device. * * returns the capacity we announce to out peer. we clip ourselves at the * various MAX_SECTORS, because if we don't, current implementation will * oops sooner or later */ static inline sector_t drbd_get_max_capacity(struct drbd_backing_dev *bdev) { sector_t s; switch (bdev->dc.meta_dev_idx) { case DRBD_MD_INDEX_INTERNAL: case DRBD_MD_INDEX_FLEX_INT: s = drbd_get_capacity(bdev->backing_bdev) ? min_t(sector_t, DRBD_MAX_SECTORS_FLEX, drbd_md_first_sector(bdev)) : 0; break; case DRBD_MD_INDEX_FLEX_EXT: s = min_t(sector_t, DRBD_MAX_SECTORS_FLEX, drbd_get_capacity(bdev->backing_bdev)); /* clip at maximum size the meta device can support */ s = min_t(sector_t, s, BM_EXT_TO_SECT(bdev->md.md_size_sect - bdev->md.bm_offset)); break; default: s = min_t(sector_t, DRBD_MAX_SECTORS, drbd_get_capacity(bdev->backing_bdev)); } return s; } /** * drbd_md_ss__() - Return the sector number of our meta data super block * @mdev: DRBD device. * @bdev: Meta data block device. */ static inline sector_t drbd_md_ss__(struct drbd_conf *mdev, struct drbd_backing_dev *bdev) { switch (bdev->dc.meta_dev_idx) { default: /* external, some index */ return MD_RESERVED_SECT * bdev->dc.meta_dev_idx; case DRBD_MD_INDEX_INTERNAL: /* with drbd08, internal meta data is always "flexible" */ case DRBD_MD_INDEX_FLEX_INT: /* sizeof(struct md_on_disk_07) == 4k * position: last 4k aligned block of 4k size */ if (!bdev->backing_bdev) { if (__ratelimit(&drbd_ratelimit_state)) { dev_err(DEV, "bdev->backing_bdev==NULL\n"); dump_stack(); } return 0; } return (drbd_get_capacity(bdev->backing_bdev) & ~7ULL) - MD_AL_OFFSET; case DRBD_MD_INDEX_FLEX_EXT: return 0; } } static inline void _drbd_queue_work(struct drbd_work_queue *q, struct drbd_work *w) { list_add_tail(&w->list, &q->q); up(&q->s); } static inline void drbd_queue_work_front(struct drbd_work_queue *q, struct drbd_work *w) { unsigned long flags; spin_lock_irqsave(&q->q_lock, flags); list_add(&w->list, &q->q); up(&q->s); /* within the spinlock, see comment near end of drbd_worker() */ spin_unlock_irqrestore(&q->q_lock, flags); } static inline void drbd_queue_work(struct drbd_work_queue *q, struct drbd_work *w) { unsigned long flags; spin_lock_irqsave(&q->q_lock, flags); list_add_tail(&w->list, &q->q); up(&q->s); /* within the spinlock, see comment near end of drbd_worker() */ spin_unlock_irqrestore(&q->q_lock, flags); } static inline void wake_asender(struct drbd_conf *mdev) { if (test_bit(SIGNAL_ASENDER, &mdev->flags)) force_sig(DRBD_SIG, mdev->asender.task); } static inline void request_ping(struct drbd_conf *mdev) { set_bit(SEND_PING, &mdev->flags); wake_asender(mdev); } static inline int drbd_send_short_cmd(struct drbd_conf *mdev, enum drbd_packets cmd) { struct p_header h; return drbd_send_cmd(mdev, USE_DATA_SOCKET, cmd, &h, sizeof(h)); } static inline int drbd_send_ping(struct drbd_conf *mdev) { struct p_header h; return drbd_send_cmd(mdev, USE_META_SOCKET, P_PING, &h, sizeof(h)); } static inline int drbd_send_ping_ack(struct drbd_conf *mdev) { struct p_header h; return drbd_send_cmd(mdev, USE_META_SOCKET, P_PING_ACK, &h, sizeof(h)); } static inline void drbd_thread_stop(struct drbd_thread *thi) { _drbd_thread_stop(thi, FALSE, TRUE); } static inline void drbd_thread_stop_nowait(struct drbd_thread *thi) { _drbd_thread_stop(thi, FALSE, FALSE); } static inline void drbd_thread_restart_nowait(struct drbd_thread *thi) { _drbd_thread_stop(thi, TRUE, FALSE); } /* counts how many answer packets packets we expect from our peer, * for either explicit application requests, * or implicit barrier packets as necessary. * increased: * w_send_barrier * _req_mod(req, queue_for_net_write or queue_for_net_read); * it is much easier and equally valid to count what we queue for the * worker, even before it actually was queued or send. * (drbd_make_request_common; recovery path on read io-error) * decreased: * got_BarrierAck (respective tl_clear, tl_clear_barrier) * _req_mod(req, data_received) * [from receive_DataReply] * _req_mod(req, write_acked_by_peer or recv_acked_by_peer or neg_acked) * [from got_BlockAck (P_WRITE_ACK, P_RECV_ACK)] * for some reason it is NOT decreased in got_NegAck, * but in the resulting cleanup code from report_params. * we should try to remember the reason for that... * _req_mod(req, send_failed or send_canceled) * _req_mod(req, connection_lost_while_pending) * [from tl_clear_barrier] */ static inline void inc_ap_pending(struct drbd_conf *mdev) { atomic_inc(&mdev->ap_pending_cnt); } #define ERR_IF_CNT_IS_NEGATIVE(which) \ if (atomic_read(&mdev->which) < 0) \ dev_err(DEV, "in %s:%d: " #which " = %d < 0 !\n", \ __func__ , __LINE__ , \ atomic_read(&mdev->which)) #define dec_ap_pending(mdev) do { \ typecheck(struct drbd_conf *, mdev); \ if (atomic_dec_and_test(&mdev->ap_pending_cnt)) \ wake_up(&mdev->misc_wait); \ ERR_IF_CNT_IS_NEGATIVE(ap_pending_cnt); } while (0) /* counts how many resync-related answers we still expect from the peer * increase decrease * C_SYNC_TARGET sends P_RS_DATA_REQUEST (and expects P_RS_DATA_REPLY) * C_SYNC_SOURCE sends P_RS_DATA_REPLY (and expects P_WRITE_ACK whith ID_SYNCER) * (or P_NEG_ACK with ID_SYNCER) */ static inline void inc_rs_pending(struct drbd_conf *mdev) { atomic_inc(&mdev->rs_pending_cnt); } #define dec_rs_pending(mdev) do { \ typecheck(struct drbd_conf *, mdev); \ atomic_dec(&mdev->rs_pending_cnt); \ ERR_IF_CNT_IS_NEGATIVE(rs_pending_cnt); } while (0) /* counts how many answers we still need to send to the peer. * increased on * receive_Data unless protocol A; * we need to send a P_RECV_ACK (proto B) * or P_WRITE_ACK (proto C) * receive_RSDataReply (recv_resync_read) we need to send a P_WRITE_ACK * receive_DataRequest (receive_RSDataRequest) we need to send back P_DATA * receive_Barrier_* we need to send a P_BARRIER_ACK */ static inline void inc_unacked(struct drbd_conf *mdev) { atomic_inc(&mdev->unacked_cnt); } #define dec_unacked(mdev) do { \ typecheck(struct drbd_conf *, mdev); \ atomic_dec(&mdev->unacked_cnt); \ ERR_IF_CNT_IS_NEGATIVE(unacked_cnt); } while (0) #define sub_unacked(mdev, n) do { \ typecheck(struct drbd_conf *, mdev); \ atomic_sub(n, &mdev->unacked_cnt); \ ERR_IF_CNT_IS_NEGATIVE(unacked_cnt); } while (0) static inline void put_net_conf(struct drbd_conf *mdev) { if (atomic_dec_and_test(&mdev->net_cnt)) wake_up(&mdev->misc_wait); } /** * get_net_conf() - Increase ref count on mdev->net_conf; Returns 0 if nothing there * @mdev: DRBD device. * * You have to call put_net_conf() when finished working with mdev->net_conf. */ static inline int get_net_conf(struct drbd_conf *mdev) { int have_net_conf; atomic_inc(&mdev->net_cnt); have_net_conf = mdev->state.conn >= C_UNCONNECTED; if (!have_net_conf) put_net_conf(mdev); return have_net_conf; } /** * get_ldev() - Increase the ref count on mdev->ldev. Returns 0 if there is no ldev * @M: DRBD device. * * You have to call put_ldev() when finished working with mdev->ldev. */ #define get_ldev(M) __cond_lock(local, _get_ldev_if_state(M,D_INCONSISTENT)) #define get_ldev_if_state(M,MINS) __cond_lock(local, _get_ldev_if_state(M,MINS)) static inline void put_ldev(struct drbd_conf *mdev) { __release(local); if (atomic_dec_and_test(&mdev->local_cnt)) wake_up(&mdev->misc_wait); D_ASSERT(atomic_read(&mdev->local_cnt) >= 0); } #ifndef __CHECKER__ static inline int _get_ldev_if_state(struct drbd_conf *mdev, enum drbd_disk_state mins) { int io_allowed; atomic_inc(&mdev->local_cnt); io_allowed = (mdev->state.disk >= mins); if (!io_allowed) put_ldev(mdev); return io_allowed; } #else extern int _get_ldev_if_state(struct drbd_conf *mdev, enum drbd_disk_state mins); #endif /* you must have an "get_ldev" reference */ static inline void drbd_get_syncer_progress(struct drbd_conf *mdev, unsigned long *bits_left, unsigned int *per_mil_done) { /* * this is to break it at compile time when we change that * (we may feel 4TB maximum storage per drbd is not enough) */ typecheck(unsigned long, mdev->rs_total); /* note: both rs_total and rs_left are in bits, i.e. in * units of BM_BLOCK_SIZE. * for the percentage, we don't care. */ *bits_left = drbd_bm_total_weight(mdev) - mdev->rs_failed; /* >> 10 to prevent overflow, * +1 to prevent division by zero */ if (*bits_left > mdev->rs_total) { /* doh. maybe a logic bug somewhere. * may also be just a race condition * between this and a disconnect during sync. * for now, just prevent in-kernel buffer overflow. */ smp_rmb(); dev_warn(DEV, "cs:%s rs_left=%lu > rs_total=%lu (rs_failed %lu)\n", drbd_conn_str(mdev->state.conn), *bits_left, mdev->rs_total, mdev->rs_failed); *per_mil_done = 0; } else { /* make sure the calculation happens in long context */ unsigned long tmp = 1000UL - (*bits_left >> 10)*1000UL / ((mdev->rs_total >> 10) + 1UL); *per_mil_done = tmp; } } /* this throttles on-the-fly application requests * according to max_buffers settings; * maybe re-implement using semaphores? */ static inline int drbd_get_max_buffers(struct drbd_conf *mdev) { int mxb = 1000000; /* arbitrary limit on open requests */ if (get_net_conf(mdev)) { mxb = mdev->net_conf->max_buffers; put_net_conf(mdev); } return mxb; } static inline int drbd_state_is_stable(union drbd_state s) { /* DO NOT add a default clause, we want the compiler to warn us * for any newly introduced state we may have forgotten to add here */ switch ((enum drbd_conns)s.conn) { /* new io only accepted when there is no connection, ... */ case C_STANDALONE: case C_WF_CONNECTION: /* ... or there is a well established connection. */ case C_CONNECTED: case C_SYNC_SOURCE: case C_SYNC_TARGET: case C_VERIFY_S: case C_VERIFY_T: case C_PAUSED_SYNC_S: case C_PAUSED_SYNC_T: /* maybe stable, look at the disk state */ break; /* no new io accepted during tansitional states * like handshake or teardown */ case C_DISCONNECTING: case C_UNCONNECTED: case C_TIMEOUT: case C_BROKEN_PIPE: case C_NETWORK_FAILURE: case C_PROTOCOL_ERROR: case C_TEAR_DOWN: case C_WF_REPORT_PARAMS: case C_STARTING_SYNC_S: case C_STARTING_SYNC_T: case C_WF_BITMAP_S: case C_WF_BITMAP_T: case C_WF_SYNC_UUID: case C_MASK: /* not "stable" */ return 0; } switch ((enum drbd_disk_state)s.disk) { case D_DISKLESS: case D_INCONSISTENT: case D_OUTDATED: case D_CONSISTENT: case D_UP_TO_DATE: /* disk state is stable as well. */ break; /* no new io accepted during tansitional states */ case D_ATTACHING: case D_FAILED: case D_NEGOTIATING: case D_UNKNOWN: case D_MASK: /* not "stable" */ return 0; } return 1; } static inline int __inc_ap_bio_cond(struct drbd_conf *mdev) { int mxb = drbd_get_max_buffers(mdev); if (mdev->state.susp) return 0; if (test_bit(SUSPEND_IO, &mdev->flags)) return 0; /* to avoid potential deadlock or bitmap corruption, * in various places, we only allow new application io * to start during "stable" states. */ /* no new io accepted when attaching or detaching the disk */ if (!drbd_state_is_stable(mdev->state)) return 0; /* since some older kernels don't have atomic_add_unless, * and we are within the spinlock anyways, we have this workaround. */ if (atomic_read(&mdev->ap_bio_cnt) > mxb) return 0; if (test_bit(BITMAP_IO, &mdev->flags)) return 0; return 1; } /* I'd like to use wait_event_lock_irq, * but I'm not sure when it got introduced, * and not sure when it has 3 or 4 arguments */ static inline void inc_ap_bio(struct drbd_conf *mdev, int one_or_two) { /* compare with after_state_ch, * os.conn != C_WF_BITMAP_S && ns.conn == C_WF_BITMAP_S */ DEFINE_WAIT(wait); /* we wait here * as long as the device is suspended * until the bitmap is no longer on the fly during connection * handshake as long as we would exeed the max_buffer limit. * * to avoid races with the reconnect code, * we need to atomic_inc within the spinlock. */ spin_lock_irq(&mdev->req_lock); while (!__inc_ap_bio_cond(mdev)) { prepare_to_wait(&mdev->misc_wait, &wait, TASK_UNINTERRUPTIBLE); spin_unlock_irq(&mdev->req_lock); schedule(); finish_wait(&mdev->misc_wait, &wait); spin_lock_irq(&mdev->req_lock); } atomic_add(one_or_two, &mdev->ap_bio_cnt); spin_unlock_irq(&mdev->req_lock); } static inline void dec_ap_bio(struct drbd_conf *mdev) { int mxb = drbd_get_max_buffers(mdev); int ap_bio = atomic_dec_return(&mdev->ap_bio_cnt); D_ASSERT(ap_bio >= 0); /* this currently does wake_up for every dec_ap_bio! * maybe rather introduce some type of hysteresis? * e.g. (ap_bio == mxb/2 || ap_bio == 0) ? */ if (ap_bio < mxb) wake_up(&mdev->misc_wait); if (ap_bio == 0 && test_bit(BITMAP_IO, &mdev->flags)) { if (!test_and_set_bit(BITMAP_IO_QUEUED, &mdev->flags)) drbd_queue_work(&mdev->data.work, &mdev->bm_io_work.w); } } static inline void drbd_set_ed_uuid(struct drbd_conf *mdev, u64 val) { mdev->ed_uuid = val; } static inline int seq_cmp(u32 a, u32 b) { /* we assume wrap around at 32bit. * for wrap around at 24bit (old atomic_t), * we'd have to * a <<= 8; b <<= 8; */ return (s32)(a) - (s32)(b); } #define seq_lt(a, b) (seq_cmp((a), (b)) < 0) #define seq_gt(a, b) (seq_cmp((a), (b)) > 0) #define seq_ge(a, b) (seq_cmp((a), (b)) >= 0) #define seq_le(a, b) (seq_cmp((a), (b)) <= 0) /* CAUTION: please no side effects in arguments! */ #define seq_max(a, b) ((u32)(seq_gt((a), (b)) ? (a) : (b))) static inline void update_peer_seq(struct drbd_conf *mdev, unsigned int new_seq) { unsigned int m; spin_lock(&mdev->peer_seq_lock); m = seq_max(mdev->peer_seq, new_seq); mdev->peer_seq = m; spin_unlock(&mdev->peer_seq_lock); if (m == new_seq) wake_up(&mdev->seq_wait); } static inline void drbd_update_congested(struct drbd_conf *mdev) { struct sock *sk = mdev->data.socket->sk; if (sk->sk_wmem_queued > sk->sk_sndbuf * 4 / 5) set_bit(NET_CONGESTED, &mdev->flags); } static inline int drbd_queue_order_type(struct drbd_conf *mdev) { /* sorry, we currently have no working implementation * of distributed TCQ stuff */ #ifndef QUEUE_ORDERED_NONE #define QUEUE_ORDERED_NONE 0 #endif return QUEUE_ORDERED_NONE; } static inline void drbd_blk_run_queue(struct request_queue *q) { if (q && q->unplug_fn) q->unplug_fn(q); } static inline void drbd_kick_lo(struct drbd_conf *mdev) { if (get_ldev(mdev)) { drbd_blk_run_queue(bdev_get_queue(mdev->ldev->backing_bdev)); put_ldev(mdev); } } static inline void drbd_md_flush(struct drbd_conf *mdev) { int r; if (test_bit(MD_NO_BARRIER, &mdev->flags)) return; r = blkdev_issue_flush(mdev->ldev->md_bdev, NULL); if (r) { set_bit(MD_NO_BARRIER, &mdev->flags); dev_err(DEV, "meta data flush failed with status %d, disabling md-flushes\n", r); } } #endif