diff options
Diffstat (limited to 'drivers/block/drbd/drbd_state.c')
| -rw-r--r-- | drivers/block/drbd/drbd_state.c | 1856 |
1 files changed, 1856 insertions, 0 deletions
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c new file mode 100644 index 00000000000..53bf6182bac --- /dev/null +++ b/drivers/block/drbd/drbd_state.c @@ -0,0 +1,1856 @@ +/* + drbd_state.c + + 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 <philipp.reisner@linbit.com>. + Copyright (C) 2002-2008, Lars Ellenberg <lars.ellenberg@linbit.com>. + + Thanks to Carter Burden, Bart Grantham and Gennadiy Nerubayev + from Logicworks, Inc. for making SDP replication support possible. + + 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. + */ + +#include <linux/drbd_limits.h> +#include "drbd_int.h" +#include "drbd_req.h" + +/* in drbd_main.c */ +extern void tl_abort_disk_io(struct drbd_conf *mdev); + +struct after_state_chg_work { + struct drbd_work w; + union drbd_state os; + union drbd_state ns; + enum chg_state_flags flags; + struct completion *done; +}; + +enum sanitize_state_warnings { + NO_WARNING, + ABORTED_ONLINE_VERIFY, + ABORTED_RESYNC, + CONNECTION_LOST_NEGOTIATING, + IMPLICITLY_UPGRADED_DISK, + IMPLICITLY_UPGRADED_PDSK, +}; + +static int w_after_state_ch(struct drbd_work *w, int unused); +static void after_state_ch(struct drbd_conf *mdev, union drbd_state os, + union drbd_state ns, enum chg_state_flags flags); +static enum drbd_state_rv is_valid_state(struct drbd_conf *, union drbd_state); +static enum drbd_state_rv is_valid_soft_transition(union drbd_state, union drbd_state, struct drbd_tconn *); +static enum drbd_state_rv is_valid_transition(union drbd_state os, union drbd_state ns); +static union drbd_state sanitize_state(struct drbd_conf *mdev, union drbd_state ns, + enum sanitize_state_warnings *warn); + +static inline bool is_susp(union drbd_state s) +{ + return s.susp || s.susp_nod || s.susp_fen; +} + +bool conn_all_vols_unconf(struct drbd_tconn *tconn) +{ + struct drbd_conf *mdev; + bool rv = true; + int vnr; + + rcu_read_lock(); + idr_for_each_entry(&tconn->volumes, mdev, vnr) { + if (mdev->state.disk != D_DISKLESS || + mdev->state.conn != C_STANDALONE || + mdev->state.role != R_SECONDARY) { + rv = false; + break; + } + } + rcu_read_unlock(); + + return rv; +} + +/* Unfortunately the states where not correctly ordered, when + they where defined. therefore can not use max_t() here. */ +static enum drbd_role max_role(enum drbd_role role1, enum drbd_role role2) +{ + if (role1 == R_PRIMARY || role2 == R_PRIMARY) + return R_PRIMARY; + if (role1 == R_SECONDARY || role2 == R_SECONDARY) + return R_SECONDARY; + return R_UNKNOWN; +} +static enum drbd_role min_role(enum drbd_role role1, enum drbd_role role2) +{ + if (role1 == R_UNKNOWN || role2 == R_UNKNOWN) + return R_UNKNOWN; + if (role1 == R_SECONDARY || role2 == R_SECONDARY) + return R_SECONDARY; + return R_PRIMARY; +} + +enum drbd_role conn_highest_role(struct drbd_tconn *tconn) +{ + enum drbd_role role = R_UNKNOWN; + struct drbd_conf *mdev; + int vnr; + + rcu_read_lock(); + idr_for_each_entry(&tconn->volumes, mdev, vnr) + role = max_role(role, mdev->state.role); + rcu_read_unlock(); + + return role; +} + +enum drbd_role conn_highest_peer(struct drbd_tconn *tconn) +{ + enum drbd_role peer = R_UNKNOWN; + struct drbd_conf *mdev; + int vnr; + + rcu_read_lock(); + idr_for_each_entry(&tconn->volumes, mdev, vnr) + peer = max_role(peer, mdev->state.peer); + rcu_read_unlock(); + + return peer; +} + +enum drbd_disk_state conn_highest_disk(struct drbd_tconn *tconn) +{ + enum drbd_disk_state ds = D_DISKLESS; + struct drbd_conf *mdev; + int vnr; + + rcu_read_lock(); + idr_for_each_entry(&tconn->volumes, mdev, vnr) + ds = max_t(enum drbd_disk_state, ds, mdev->state.disk); + rcu_read_unlock(); + + return ds; +} + +enum drbd_disk_state conn_lowest_disk(struct drbd_tconn *tconn) +{ + enum drbd_disk_state ds = D_MASK; + struct drbd_conf *mdev; + int vnr; + + rcu_read_lock(); + idr_for_each_entry(&tconn->volumes, mdev, vnr) + ds = min_t(enum drbd_disk_state, ds, mdev->state.disk); + rcu_read_unlock(); + + return ds; +} + +enum drbd_disk_state conn_highest_pdsk(struct drbd_tconn *tconn) +{ + enum drbd_disk_state ds = D_DISKLESS; + struct drbd_conf *mdev; + int vnr; + + rcu_read_lock(); + idr_for_each_entry(&tconn->volumes, mdev, vnr) + ds = max_t(enum drbd_disk_state, ds, mdev->state.pdsk); + rcu_read_unlock(); + + return ds; +} + +enum drbd_conns conn_lowest_conn(struct drbd_tconn *tconn) +{ + enum drbd_conns conn = C_MASK; + struct drbd_conf *mdev; + int vnr; + + rcu_read_lock(); + idr_for_each_entry(&tconn->volumes, mdev, vnr) + conn = min_t(enum drbd_conns, conn, mdev->state.conn); + rcu_read_unlock(); + + return conn; +} + +static bool no_peer_wf_report_params(struct drbd_tconn *tconn) +{ + struct drbd_conf *mdev; + int vnr; + bool rv = true; + + rcu_read_lock(); + idr_for_each_entry(&tconn->volumes, mdev, vnr) + if (mdev->state.conn == C_WF_REPORT_PARAMS) { + rv = false; + break; + } + rcu_read_unlock(); + + return rv; +} + + +/** + * cl_wide_st_chg() - true if the state change is a cluster wide one + * @mdev: DRBD device. + * @os: old (current) state. + * @ns: new (wanted) state. + */ +static int cl_wide_st_chg(struct drbd_conf *mdev, + union drbd_state os, union drbd_state ns) +{ + return (os.conn >= C_CONNECTED && ns.conn >= C_CONNECTED && + ((os.role != R_PRIMARY && ns.role == R_PRIMARY) || + (os.conn != C_STARTING_SYNC_T && ns.conn == C_STARTING_SYNC_T) || + (os.conn != C_STARTING_SYNC_S && ns.conn == C_STARTING_SYNC_S) || + (os.disk != D_FAILED && ns.disk == D_FAILED))) || + (os.conn >= C_CONNECTED && ns.conn == C_DISCONNECTING) || + (os.conn == C_CONNECTED && ns.conn == C_VERIFY_S) || + (os.conn == C_CONNECTED && ns.conn == C_WF_REPORT_PARAMS); +} + +static union drbd_state +apply_mask_val(union drbd_state os, union drbd_state mask, union drbd_state val) +{ + union drbd_state ns; + ns.i = (os.i & ~mask.i) | val.i; + return ns; +} + +enum drbd_state_rv +drbd_change_state(struct drbd_conf *mdev, enum chg_state_flags f, + union drbd_state mask, union drbd_state val) +{ + unsigned long flags; + union drbd_state ns; + enum drbd_state_rv rv; + + spin_lock_irqsave(&mdev->tconn->req_lock, flags); + ns = apply_mask_val(drbd_read_state(mdev), mask, val); + rv = _drbd_set_state(mdev, ns, f, NULL); + spin_unlock_irqrestore(&mdev->tconn->req_lock, flags); + + return rv; +} + +/** + * drbd_force_state() - Impose a change which happens outside our control on our state + * @mdev: DRBD device. + * @mask: mask of state bits to change. + * @val: value of new state bits. + */ +void drbd_force_state(struct drbd_conf *mdev, + union drbd_state mask, union drbd_state val) +{ + drbd_change_state(mdev, CS_HARD, mask, val); +} + +static enum drbd_state_rv +_req_st_cond(struct drbd_conf *mdev, union drbd_state mask, + union drbd_state val) +{ + union drbd_state os, ns; + unsigned long flags; + enum drbd_state_rv rv; + + if (test_and_clear_bit(CL_ST_CHG_SUCCESS, &mdev->flags)) + return SS_CW_SUCCESS; + + if (test_and_clear_bit(CL_ST_CHG_FAIL, &mdev->flags)) + return SS_CW_FAILED_BY_PEER; + + spin_lock_irqsave(&mdev->tconn->req_lock, flags); + os = drbd_read_state(mdev); + ns = sanitize_state(mdev, apply_mask_val(os, mask, val), NULL); + rv = is_valid_transition(os, ns); + if (rv >= SS_SUCCESS) + rv = SS_UNKNOWN_ERROR; /* cont waiting, otherwise fail. */ + + if (!cl_wide_st_chg(mdev, os, ns)) + rv = SS_CW_NO_NEED; + if (rv == SS_UNKNOWN_ERROR) { + rv = is_valid_state(mdev, ns); + if (rv >= SS_SUCCESS) { + rv = is_valid_soft_transition(os, ns, mdev->tconn); + if (rv >= SS_SUCCESS) + rv = SS_UNKNOWN_ERROR; /* cont waiting, otherwise fail. */ + } + } + spin_unlock_irqrestore(&mdev->tconn->req_lock, flags); + + return rv; +} + +/** + * drbd_req_state() - Perform an eventually cluster wide state change + * @mdev: DRBD device. + * @mask: mask of state bits to change. + * @val: value of new state bits. + * @f: flags + * + * Should not be called directly, use drbd_request_state() or + * _drbd_request_state(). + */ +static enum drbd_state_rv +drbd_req_state(struct drbd_conf *mdev, union drbd_state mask, + union drbd_state val, enum chg_state_flags f) +{ + struct completion done; + unsigned long flags; + union drbd_state os, ns; + enum drbd_state_rv rv; + + init_completion(&done); + + if (f & CS_SERIALIZE) + mutex_lock(mdev->state_mutex); + + spin_lock_irqsave(&mdev->tconn->req_lock, flags); + os = drbd_read_state(mdev); + ns = sanitize_state(mdev, apply_mask_val(os, mask, val), NULL); + rv = is_valid_transition(os, ns); + if (rv < SS_SUCCESS) { + spin_unlock_irqrestore(&mdev->tconn->req_lock, flags); + goto abort; + } + + if (cl_wide_st_chg(mdev, os, ns)) { + rv = is_valid_state(mdev, ns); + if (rv == SS_SUCCESS) + rv = is_valid_soft_transition(os, ns, mdev->tconn); + spin_unlock_irqrestore(&mdev->tconn->req_lock, flags); + + if (rv < SS_SUCCESS) { + if (f & CS_VERBOSE) + print_st_err(mdev, os, ns, rv); + goto abort; + } + + if (drbd_send_state_req(mdev, mask, val)) { + rv = SS_CW_FAILED_BY_PEER; + if (f & CS_VERBOSE) + print_st_err(mdev, os, ns, rv); + goto abort; + } + + wait_event(mdev->state_wait, + (rv = _req_st_cond(mdev, mask, val))); + + if (rv < SS_SUCCESS) { + if (f & CS_VERBOSE) + print_st_err(mdev, os, ns, rv); + goto abort; + } + spin_lock_irqsave(&mdev->tconn->req_lock, flags); + ns = apply_mask_val(drbd_read_state(mdev), mask, val); + rv = _drbd_set_state(mdev, ns, f, &done); + } else { + rv = _drbd_set_state(mdev, ns, f, &done); + } + + spin_unlock_irqrestore(&mdev->tconn->req_lock, flags); + + if (f & CS_WAIT_COMPLETE && rv == SS_SUCCESS) { + D_ASSERT(current != mdev->tconn->worker.task); + wait_for_completion(&done); + } + +abort: + if (f & CS_SERIALIZE) + mutex_unlock(mdev->state_mutex); + + return rv; +} + +/** + * _drbd_request_state() - Request a state change (with flags) + * @mdev: DRBD device. + * @mask: mask of state bits to change. + * @val: value of new state bits. + * @f: flags + * + * Cousin of drbd_request_state(), useful with the CS_WAIT_COMPLETE + * flag, or when logging of failed state change requests is not desired. + */ +enum drbd_state_rv +_drbd_request_state(struct drbd_conf *mdev, union drbd_state mask, + union drbd_state val, enum chg_state_flags f) +{ + enum drbd_state_rv rv; + + wait_event(mdev->state_wait, + (rv = drbd_req_state(mdev, mask, val, f)) != SS_IN_TRANSIENT_STATE); + + return rv; +} + +static void print_st(struct drbd_conf *mdev, char *name, union drbd_state ns) +{ + dev_err(DEV, " %s = { cs:%s ro:%s/%s ds:%s/%s %c%c%c%c%c%c }\n", + name, + drbd_conn_str(ns.conn), + drbd_role_str(ns.role), + drbd_role_str(ns.peer), + drbd_disk_str(ns.disk), + drbd_disk_str(ns.pdsk), + is_susp(ns) ? 's' : 'r', + ns.aftr_isp ? 'a' : '-', + ns.peer_isp ? 'p' : '-', + ns.user_isp ? 'u' : '-', + ns.susp_fen ? 'F' : '-', + ns.susp_nod ? 'N' : '-' + ); +} + +void print_st_err(struct drbd_conf *mdev, union drbd_state os, + union drbd_state ns, enum drbd_state_rv err) +{ + if (err == SS_IN_TRANSIENT_STATE) + return; + dev_err(DEV, "State change failed: %s\n", drbd_set_st_err_str(err)); + print_st(mdev, " state", os); + print_st(mdev, "wanted", ns); +} + +static long print_state_change(char *pb, union drbd_state os, union drbd_state ns, + enum chg_state_flags flags) +{ + char *pbp; + pbp = pb; + *pbp = 0; + + if (ns.role != os.role && flags & CS_DC_ROLE) + pbp += sprintf(pbp, "role( %s -> %s ) ", + drbd_role_str(os.role), + drbd_role_str(ns.role)); + if (ns.peer != os.peer && flags & CS_DC_PEER) + pbp += sprintf(pbp, "peer( %s -> %s ) ", + drbd_role_str(os.peer), + drbd_role_str(ns.peer)); + if (ns.conn != os.conn && flags & CS_DC_CONN) + pbp += sprintf(pbp, "conn( %s -> %s ) ", + drbd_conn_str(os.conn), + drbd_conn_str(ns.conn)); + if (ns.disk != os.disk && flags & CS_DC_DISK) + pbp += sprintf(pbp, "disk( %s -> %s ) ", + drbd_disk_str(os.disk), + drbd_disk_str(ns.disk)); + if (ns.pdsk != os.pdsk && flags & CS_DC_PDSK) + pbp += sprintf(pbp, "pdsk( %s -> %s ) ", + drbd_disk_str(os.pdsk), + drbd_disk_str(ns.pdsk)); + + return pbp - pb; +} + +static void drbd_pr_state_change(struct drbd_conf *mdev, union drbd_state os, union drbd_state ns, + enum chg_state_flags flags) +{ + char pb[300]; + char *pbp = pb; + + pbp += print_state_change(pbp, os, ns, flags ^ CS_DC_MASK); + + if (ns.aftr_isp != os.aftr_isp) + pbp += sprintf(pbp, "aftr_isp( %d -> %d ) ", + os.aftr_isp, + ns.aftr_isp); + if (ns.peer_isp != os.peer_isp) + pbp += sprintf(pbp, "peer_isp( %d -> %d ) ", + os.peer_isp, + ns.peer_isp); + if (ns.user_isp != os.user_isp) + pbp += sprintf(pbp, "user_isp( %d -> %d ) ", + os.user_isp, + ns.user_isp); + + if (pbp != pb) + dev_info(DEV, "%s\n", pb); +} + +static void conn_pr_state_change(struct drbd_tconn *tconn, union drbd_state os, union drbd_state ns, + enum chg_state_flags flags) +{ + char pb[300]; + char *pbp = pb; + + pbp += print_state_change(pbp, os, ns, flags); + + if (is_susp(ns) != is_susp(os) && flags & CS_DC_SUSP) + pbp += sprintf(pbp, "susp( %d -> %d ) ", + is_susp(os), + is_susp(ns)); + + if (pbp != pb) + conn_info(tconn, "%s\n", pb); +} + + +/** + * is_valid_state() - Returns an SS_ error code if ns is not valid + * @mdev: DRBD device. + * @ns: State to consider. + */ +static enum drbd_state_rv +is_valid_state(struct drbd_conf *mdev, union drbd_state ns) +{ + /* See drbd_state_sw_errors in drbd_strings.c */ + + enum drbd_fencing_p fp; + enum drbd_state_rv rv = SS_SUCCESS; + struct net_conf *nc; + + rcu_read_lock(); + fp = FP_DONT_CARE; + if (get_ldev(mdev)) { + fp = rcu_dereference(mdev->ldev->disk_conf)->fencing; + put_ldev(mdev); + } + + nc = rcu_dereference(mdev->tconn->net_conf); + if (nc) { + if (!nc->two_primaries && ns.role == R_PRIMARY) { + if (ns.peer == R_PRIMARY) + rv = SS_TWO_PRIMARIES; + else if (conn_highest_peer(mdev->tconn) == R_PRIMARY) + rv = SS_O_VOL_PEER_PRI; + } + } + + if (rv <= 0) + /* already found a reason to abort */; + else if (ns.role == R_SECONDARY && mdev->open_cnt) + rv = SS_DEVICE_IN_USE; + + else if (ns.role == R_PRIMARY && ns.conn < C_CONNECTED && ns.disk < D_UP_TO_DATE) + rv = SS_NO_UP_TO_DATE_DISK; + + else if (fp >= FP_RESOURCE && + ns.role == R_PRIMARY && ns.conn < C_CONNECTED && ns.pdsk >= D_UNKNOWN) + rv = SS_PRIMARY_NOP; + + else if (ns.role == R_PRIMARY && ns.disk <= D_INCONSISTENT && ns.pdsk <= D_INCONSISTENT) + rv = SS_NO_UP_TO_DATE_DISK; + + else if (ns.conn > C_CONNECTED && ns.disk < D_INCONSISTENT) + rv = SS_NO_LOCAL_DISK; + + else if (ns.conn > C_CONNECTED && ns.pdsk < D_INCONSISTENT) + rv = SS_NO_REMOTE_DISK; + + else if (ns.conn > C_CONNECTED && ns.disk < D_UP_TO_DATE && ns.pdsk < D_UP_TO_DATE) + rv = SS_NO_UP_TO_DATE_DISK; + + else if ((ns.conn == C_CONNECTED || + ns.conn == C_WF_BITMAP_S || + ns.conn == C_SYNC_SOURCE || + ns.conn == C_PAUSED_SYNC_S) && + ns.disk == D_OUTDATED) + rv = SS_CONNECTED_OUTDATES; + + else if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && + (nc->verify_alg[0] == 0)) + rv = SS_NO_VERIFY_ALG; + + else if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && + mdev->tconn->agreed_pro_version < 88) + rv = SS_NOT_SUPPORTED; + + else if (ns.conn >= C_CONNECTED && ns.pdsk == D_UNKNOWN) + rv = SS_CONNECTED_OUTDATES; + + rcu_read_unlock(); + + return rv; +} + +/** + * is_valid_soft_transition() - Returns an SS_ error code if the state transition is not possible + * This function limits state transitions that may be declined by DRBD. I.e. + * user requests (aka soft transitions). + * @mdev: DRBD device. + * @ns: new state. + * @os: old state. + */ +static enum drbd_state_rv +is_valid_soft_transition(union drbd_state os, union drbd_state ns, struct drbd_tconn *tconn) +{ + enum drbd_state_rv rv = SS_SUCCESS; + + if ((ns.conn == C_STARTING_SYNC_T || ns.conn == C_STARTING_SYNC_S) && + os.conn > C_CONNECTED) + rv = SS_RESYNC_RUNNING; + + if (ns.conn == C_DISCONNECTING && os.conn == C_STANDALONE) + rv = SS_ALREADY_STANDALONE; + + if (ns.disk > D_ATTACHING && os.disk == D_DISKLESS) + rv = SS_IS_DISKLESS; + + if (ns.conn == C_WF_CONNECTION && os.conn < C_UNCONNECTED) + rv = SS_NO_NET_CONFIG; + + if (ns.disk == D_OUTDATED && os.disk < D_OUTDATED && os.disk != D_ATTACHING) + rv = SS_LOWER_THAN_OUTDATED; + + if (ns.conn == C_DISCONNECTING && os.conn == C_UNCONNECTED) + rv = SS_IN_TRANSIENT_STATE; + + /* if (ns.conn == os.conn && ns.conn == C_WF_REPORT_PARAMS) + rv = SS_IN_TRANSIENT_STATE; */ + + /* While establishing a connection only allow cstate to change. + Delay/refuse role changes, detach attach etc... */ + if (test_bit(STATE_SENT, &tconn->flags) && + !(os.conn == C_WF_REPORT_PARAMS || + (ns.conn == C_WF_REPORT_PARAMS && os.conn == C_WF_CONNECTION))) + rv = SS_IN_TRANSIENT_STATE; + + if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && os.conn < C_CONNECTED) + rv = SS_NEED_CONNECTION; + + if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && + ns.conn != os.conn && os.conn > C_CONNECTED) + rv = SS_RESYNC_RUNNING; + + if ((ns.conn == C_STARTING_SYNC_S || ns.conn == C_STARTING_SYNC_T) && + os.conn < C_CONNECTED) + rv = SS_NEED_CONNECTION; + + if ((ns.conn == C_SYNC_TARGET || ns.conn == C_SYNC_SOURCE) + && os.conn < C_WF_REPORT_PARAMS) + rv = SS_NEED_CONNECTION; /* No NetworkFailure -> SyncTarget etc... */ + + return rv; +} + +static enum drbd_state_rv +is_valid_conn_transition(enum drbd_conns oc, enum drbd_conns nc) +{ + /* no change -> nothing to do, at least for the connection part */ + if (oc == nc) + return SS_NOTHING_TO_DO; + + /* disconnect of an unconfigured connection does not make sense */ + if (oc == C_STANDALONE && nc == C_DISCONNECTING) + return SS_ALREADY_STANDALONE; + + /* from C_STANDALONE, we start with C_UNCONNECTED */ + if (oc == C_STANDALONE && nc != C_UNCONNECTED) + return SS_NEED_CONNECTION; + + /* When establishing a connection we need to go through WF_REPORT_PARAMS! + Necessary to do the right thing upon invalidate-remote on a disconnected resource */ + if (oc < C_WF_REPORT_PARAMS && nc >= C_CONNECTED) + return SS_NEED_CONNECTION; + + /* After a network error only C_UNCONNECTED or C_DISCONNECTING may follow. */ + if (oc >= C_TIMEOUT && oc <= C_TEAR_DOWN && nc != C_UNCONNECTED && nc != C_DISCONNECTING) + return SS_IN_TRANSIENT_STATE; + + /* After C_DISCONNECTING only C_STANDALONE may follow */ + if (oc == C_DISCONNECTING && nc != C_STANDALONE) + return SS_IN_TRANSIENT_STATE; + + return SS_SUCCESS; +} + + +/** + * is_valid_transition() - Returns an SS_ error code if the state transition is not possible + * This limits hard state transitions. Hard state transitions are facts there are + * imposed on DRBD by the environment. E.g. disk broke or network broke down. + * But those hard state transitions are still not allowed to do everything. + * @ns: new state. + * @os: old state. + */ +static enum drbd_state_rv +is_valid_transition(union drbd_state os, union drbd_state ns) +{ + enum drbd_state_rv rv; + + rv = is_valid_conn_transition(os.conn, ns.conn); + + /* we cannot fail (again) if we already detached */ + if (ns.disk == D_FAILED && os.disk == D_DISKLESS) + rv = SS_IS_DISKLESS; + + return rv; +} + +static void print_sanitize_warnings(struct drbd_conf *mdev, enum sanitize_state_warnings warn) +{ + static const char *msg_table[] = { + [NO_WARNING] = "", + [ABORTED_ONLINE_VERIFY] = "Online-verify aborted.", + [ABORTED_RESYNC] = "Resync aborted.", + [CONNECTION_LOST_NEGOTIATING] = "Connection lost while negotiating, no data!", + [IMPLICITLY_UPGRADED_DISK] = "Implicitly upgraded disk", + [IMPLICITLY_UPGRADED_PDSK] = "Implicitly upgraded pdsk", + }; + + if (warn != NO_WARNING) + dev_warn(DEV, "%s\n", msg_table[warn]); +} + +/** + * sanitize_state() - Resolves implicitly necessary additional changes to a state transition + * @mdev: DRBD device. + * @os: old state. + * @ns: new state. + * @warn_sync_abort: + * + * When we loose connection, we have to set the state of the peers disk (pdsk) + * to D_UNKNOWN. This rule and many more along those lines are in this function. + */ +static union drbd_state sanitize_state(struct drbd_conf *mdev, union drbd_state ns, + enum sanitize_state_warnings *warn) +{ + enum drbd_fencing_p fp; + enum drbd_disk_state disk_min, disk_max, pdsk_min, pdsk_max; + + if (warn) + *warn = NO_WARNING; + + fp = FP_DONT_CARE; + if (get_ldev(mdev)) { + rcu_read_lock(); + fp = rcu_dereference(mdev->ldev->disk_conf)->fencing; + rcu_read_unlock(); + put_ldev(mdev); + } + + /* Implications from connection to peer and peer_isp */ + if (ns.conn < C_CONNECTED) { + ns.peer_isp = 0; + ns.peer = R_UNKNOWN; + if (ns.pdsk > D_UNKNOWN || ns.pdsk < D_INCONSISTENT) + ns.pdsk = D_UNKNOWN; + } + + /* Clear the aftr_isp when becoming unconfigured */ + if (ns.conn == C_STANDALONE && ns.disk == D_DISKLESS && ns.role == R_SECONDARY) + ns.aftr_isp = 0; + + /* An implication of the disk states onto the connection state */ + /* Abort resync if a disk fails/detaches */ + if (ns.conn > C_CONNECTED && (ns.disk <= D_FAILED || ns.pdsk <= D_FAILED)) { + if (warn) + *warn = ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T ? + ABORTED_ONLINE_VERIFY : ABORTED_RESYNC; + ns.conn = C_CONNECTED; + } + + /* Connection breaks down before we finished "Negotiating" */ + if (ns.conn < C_CONNECTED && ns.disk == D_NEGOTIATING && + get_ldev_if_state(mdev, D_NEGOTIATING)) { + if (mdev->ed_uuid == mdev->ldev->md.uuid[UI_CURRENT]) { + ns.disk = mdev->new_state_tmp.disk; + ns.pdsk = mdev->new_state_tmp.pdsk; + } else { + if (warn) + *warn = CONNECTION_LOST_NEGOTIATING; + ns.disk = D_DISKLESS; + ns.pdsk = D_UNKNOWN; + } + put_ldev(mdev); + } + + /* D_CONSISTENT and D_OUTDATED vanish when we get connected */ + if (ns.conn >= C_CONNECTED && ns.conn < C_AHEAD) { + if (ns.disk == D_CONSISTENT || ns.disk == D_OUTDATED) + ns.disk = D_UP_TO_DATE; + if (ns.pdsk == D_CONSISTENT || ns.pdsk == D_OUTDATED) + ns.pdsk = D_UP_TO_DATE; + } + + /* Implications of the connection stat on the disk states */ + disk_min = D_DISKLESS; + disk_max = D_UP_TO_DATE; + pdsk_min = D_INCONSISTENT; + pdsk_max = D_UNKNOWN; + switch ((enum drbd_conns)ns.conn) { + case C_WF_BITMAP_T: + case C_PAUSED_SYNC_T: + case C_STARTING_SYNC_T: + case C_WF_SYNC_UUID: + case C_BEHIND: + disk_min = D_INCONSISTENT; + disk_max = D_OUTDATED; + pdsk_min = D_UP_TO_DATE; + pdsk_max = D_UP_TO_DATE; + break; + case C_VERIFY_S: + case C_VERIFY_T: + disk_min = D_UP_TO_DATE; + disk_max = D_UP_TO_DATE; + pdsk_min = D_UP_TO_DATE; + pdsk_max = D_UP_TO_DATE; + break; + case C_CONNECTED: + disk_min = D_DISKLESS; + disk_max = D_UP_TO_DATE; + pdsk_min = D_DISKLESS; + pdsk_max = D_UP_TO_DATE; + break; + case C_WF_BITMAP_S: + case C_PAUSED_SYNC_S: + case C_STARTING_SYNC_S: + case C_AHEAD: + disk_min = D_UP_TO_DATE; + disk_max = D_UP_TO_DATE; + pdsk_min = D_INCONSISTENT; + pdsk_max = D_CONSISTENT; /* D_OUTDATED would be nice. But explicit outdate necessary*/ + break; + case C_SYNC_TARGET: + disk_min = D_INCONSISTENT; + disk_max = D_INCONSISTENT; + pdsk_min = D_UP_TO_DATE; + pdsk_max = D_UP_TO_DATE; + break; + case C_SYNC_SOURCE: + disk_min = D_UP_TO_DATE; + disk_max = D_UP_TO_DATE; + pdsk_min = D_INCONSISTENT; + pdsk_max = D_INCONSISTENT; + break; + case C_STANDALONE: + 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_CONNECTION: + case C_WF_REPORT_PARAMS: + case C_MASK: + break; + } + if (ns.disk > disk_max) + ns.disk = disk_max; + + if (ns.disk < disk_min) { + if (warn) + *warn = IMPLICITLY_UPGRADED_DISK; + ns.disk = disk_min; + } + if (ns.pdsk > pdsk_max) + ns.pdsk = pdsk_max; + + if (ns.pdsk < pdsk_min) { + if (warn) + *warn = IMPLICITLY_UPGRADED_PDSK; + ns.pdsk = pdsk_min; + } + + if (fp == FP_STONITH && + (ns.role == R_PRIMARY && ns.conn < C_CONNECTED && ns.pdsk > D_OUTDATED)) + ns.susp_fen = 1; /* Suspend IO while fence-peer handler runs (peer lost) */ + + if (mdev->tconn->res_opts.on_no_data == OND_SUSPEND_IO && + (ns.role == R_PRIMARY && ns.disk < D_UP_TO_DATE && ns.pdsk < D_UP_TO_DATE)) + ns.susp_nod = 1; /* Suspend IO while no data available (no accessible data available) */ + + if (ns.aftr_isp || ns.peer_isp || ns.user_isp) { + if (ns.conn == C_SYNC_SOURCE) + ns.conn = C_PAUSED_SYNC_S; + if (ns.conn == C_SYNC_TARGET) + ns.conn = C_PAUSED_SYNC_T; + } else { + if (ns.conn == C_PAUSED_SYNC_S) + ns.conn = C_SYNC_SOURCE; + if (ns.conn == C_PAUSED_SYNC_T) + ns.conn = C_SYNC_TARGET; + } + + return ns; +} + +void drbd_resume_al(struct drbd_conf *mdev) +{ + if (test_and_clear_bit(AL_SUSPENDED, &mdev->flags)) + dev_info(DEV, "Resumed AL updates\n"); +} + +/* helper for __drbd_set_state */ +static void set_ov_position(struct drbd_conf *mdev, enum drbd_conns cs) +{ + if (mdev->tconn->agreed_pro_version < 90) + mdev->ov_start_sector = 0; + mdev->rs_total = drbd_bm_bits(mdev); + mdev->ov_position = 0; + if (cs == C_VERIFY_T) { + /* starting online verify from an arbitrary position + * does not fit well into the existing protocol. + * on C_VERIFY_T, we initialize ov_left and friends + * implicitly in receive_DataRequest once the + * first P_OV_REQUEST is received */ + mdev->ov_start_sector = ~(sector_t)0; + } else { + unsigned long bit = BM_SECT_TO_BIT(mdev->ov_start_sector); + if (bit >= mdev->rs_total) { + mdev->ov_start_sector = + BM_BIT_TO_SECT(mdev->rs_total - 1); + mdev->rs_total = 1; + } else + mdev->rs_total -= bit; + mdev->ov_position = mdev->ov_start_sector; + } + mdev->ov_left = mdev->rs_total; +} + +/** + * __drbd_set_state() - Set a new DRBD state + * @mdev: DRBD device. + * @ns: new state. + * @flags: Flags + * @done: Optional completion, that will get completed after the after_state_ch() finished + * + * Caller needs to hold req_lock, and global_state_lock. Do not call directly. + */ +enum drbd_state_rv +__drbd_set_state(struct drbd_conf *mdev, union drbd_state ns, + enum chg_state_flags flags, struct completion *done) +{ + union drbd_state os; + enum drbd_state_rv rv = SS_SUCCESS; + enum sanitize_state_warnings ssw; + struct after_state_chg_work *ascw; + + os = drbd_read_state(mdev); + + ns = sanitize_state(mdev, ns, &ssw); + if (ns.i == os.i) + return SS_NOTHING_TO_DO; + + rv = is_valid_transition(os, ns); + if (rv < SS_SUCCESS) + return rv; + + if (!(flags & CS_HARD)) { + /* pre-state-change checks ; only look at ns */ + /* See drbd_state_sw_errors in drbd_strings.c */ + + rv = is_valid_state(mdev, ns); + if (rv < SS_SUCCESS) { + /* If the old state was illegal as well, then let + this happen...*/ + + if (is_valid_state(mdev, os) == rv) + rv = is_valid_soft_transition(os, ns, mdev->tconn); + } else + rv = is_valid_soft_transition(os, ns, mdev->tconn); + } + + if (rv < SS_SUCCESS) { + if (flags & CS_VERBOSE) + print_st_err(mdev, os, ns, rv); + return rv; + } + + print_sanitize_warnings(mdev, ssw); + + drbd_pr_state_change(mdev, os, ns, flags); + + /* Display changes to the susp* flags that where caused by the call to + sanitize_state(). Only display it here if we where not called from + _conn_request_state() */ + if (!(flags & CS_DC_SUSP)) + conn_pr_state_change(mdev->tconn, os, ns, (flags & ~CS_DC_MASK) | CS_DC_SUSP); + + /* if we are going -> D_FAILED or D_DISKLESS, grab one extra reference + * on the ldev here, to be sure the transition -> D_DISKLESS resp. + * drbd_ldev_destroy() won't happen before our corresponding + * after_state_ch works run, where we put_ldev again. */ + if ((os.disk != D_FAILED && ns.disk == D_FAILED) || + (os.disk != D_DISKLESS && ns.disk == D_DISKLESS)) + atomic_inc(&mdev->local_cnt); + + mdev->state.i = ns.i; + mdev->tconn->susp = ns.susp; + mdev->tconn->susp_nod = ns.susp_nod; + mdev->tconn->susp_fen = ns.susp_fen; + + if (os.disk == D_ATTACHING && ns.disk >= D_NEGOTIATING) + drbd_print_uuids(mdev, "attached to UUIDs"); + + /* Wake up role changes, that were delayed because of connection establishing */ + if (os.conn == C_WF_REPORT_PARAMS && ns.conn != C_WF_REPORT_PARAMS && + no_peer_wf_report_params(mdev->tconn)) + clear_bit(STATE_SENT, &mdev->tconn->flags); + + wake_up(&mdev->misc_wait); + wake_up(&mdev->state_wait); + wake_up(&mdev->tconn->ping_wait); + + /* Aborted verify run, or we reached the stop sector. + * Log the last position, unless end-of-device. */ + if ((os.conn == C_VERIFY_S || os.conn == C_VERIFY_T) && + ns.conn <= C_CONNECTED) { + mdev->ov_start_sector = + BM_BIT_TO_SECT(drbd_bm_bits(mdev) - mdev->ov_left); + if (mdev->ov_left) + dev_info(DEV, "Online Verify reached sector %llu\n", + (unsigned long long)mdev->ov_start_sector); + } + + if ((os.conn == C_PAUSED_SYNC_T || os.conn == C_PAUSED_SYNC_S) && + (ns.conn == C_SYNC_TARGET || ns.conn == C_SYNC_SOURCE)) { + dev_info(DEV, "Syncer continues.\n"); + mdev->rs_paused += (long)jiffies + -(long)mdev->rs_mark_time[mdev->rs_last_mark]; + if (ns.conn == C_SYNC_TARGET) + mod_timer(&mdev->resync_timer, jiffies); + } + + if ((os.conn == C_SYNC_TARGET || os.conn == C_SYNC_SOURCE) && + (ns.conn == C_PAUSED_SYNC_T || ns.conn == C_PAUSED_SYNC_S)) { + dev_info(DEV, "Resync suspended\n"); + mdev->rs_mark_time[mdev->rs_last_mark] = jiffies; + } + + if (os.conn == C_CONNECTED && + (ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T)) { + unsigned long now = jiffies; + int i; + + set_ov_position(mdev, ns.conn); + mdev->rs_start = now; + mdev->rs_last_events = 0; + mdev->rs_last_sect_ev = 0; + mdev->ov_last_oos_size = 0; + mdev->ov_last_oos_start = 0; + + for (i = 0; i < DRBD_SYNC_MARKS; i++) { + mdev->rs_mark_left[i] = mdev->ov_left; + mdev->rs_mark_time[i] = now; + } + + drbd_rs_controller_reset(mdev); + + if (ns.conn == C_VERIFY_S) { + dev_info(DEV, "Starting Online Verify from sector %llu\n", + (unsigned long long)mdev->ov_position); + mod_timer(&mdev->resync_timer, jiffies); + } + } + + if (get_ldev(mdev)) { + u32 mdf = mdev->ldev->md.flags & ~(MDF_CONSISTENT|MDF_PRIMARY_IND| + MDF_CONNECTED_IND|MDF_WAS_UP_TO_DATE| + MDF_PEER_OUT_DATED|MDF_CRASHED_PRIMARY); + + mdf &= ~MDF_AL_CLEAN; + if (test_bit(CRASHED_PRIMARY, &mdev->flags)) + mdf |= MDF_CRASHED_PRIMARY; + if (mdev->state.role == R_PRIMARY || + (mdev->state.pdsk < D_INCONSISTENT && mdev->state.peer == R_PRIMARY)) + mdf |= MDF_PRIMARY_IND; + if (mdev->state.conn > C_WF_REPORT_PARAMS) + mdf |= MDF_CONNECTED_IND; + if (mdev->state.disk > D_INCONSISTENT) + mdf |= MDF_CONSISTENT; + if (mdev->state.disk > D_OUTDATED) + mdf |= MDF_WAS_UP_TO_DATE; + if (mdev->state.pdsk <= D_OUTDATED && mdev->state.pdsk >= D_INCONSISTENT) + mdf |= MDF_PEER_OUT_DATED; + if (mdf != mdev->ldev->md.flags) { + mdev->ldev->md.flags = mdf; + drbd_md_mark_dirty(mdev); + } + if (os.disk < D_CONSISTENT && ns.disk >= D_CONSISTENT) + drbd_set_ed_uuid(mdev, mdev->ldev->md.uuid[UI_CURRENT]); + put_ldev(mdev); + } + + /* Peer was forced D_UP_TO_DATE & R_PRIMARY, consider to resync */ + if (os.disk == D_INCONSISTENT && os.pdsk == D_INCONSISTENT && + os.peer == R_SECONDARY && ns.peer == R_PRIMARY) + set_bit(CONSIDER_RESYNC, &mdev->flags); + + /* Receiver should clean up itself */ + if (os.conn != C_DISCONNECTING && ns.conn == C_DISCONNECTING) + drbd_thread_stop_nowait(&mdev->tconn->receiver); + + /* Now the receiver finished cleaning up itself, it should die */ + if (os.conn != C_STANDALONE && ns.conn == C_STANDALONE) + drbd_thread_stop_nowait(&mdev->tconn->receiver); + + /* Upon network failure, we need to restart the receiver. */ + if (os.conn > C_WF_CONNECTION && + ns.conn <= C_TEAR_DOWN && ns.conn >= C_TIMEOUT) + drbd_thread_restart_nowait(&mdev->tconn->receiver); + + /* Resume AL writing if we get a connection */ + if (os.conn < C_CONNECTED && ns.conn >= C_CONNECTED) + drbd_resume_al(mdev); + + /* remember last attach time so request_timer_fn() won't + * kill newly established sessions while we are still trying to thaw + * previously frozen IO */ + if ((os.disk == D_ATTACHING || os.disk == D_NEGOTIATING) && + ns.disk > D_NEGOTIATING) + mdev->last_reattach_jif = jiffies; + + ascw = kmalloc(sizeof(*ascw), GFP_ATOMIC); + if (ascw) { + ascw->os = os; + ascw->ns = ns; + ascw->flags = flags; + ascw->w.cb = w_after_state_ch; + ascw->w.mdev = mdev; + ascw->done = done; + drbd_queue_work(&mdev->tconn->sender_work, &ascw->w); + } else { + dev_err(DEV, "Could not kmalloc an ascw\n"); + } + |