diff options
Diffstat (limited to 'drivers/block/drbd')
| -rw-r--r-- | drivers/block/drbd/drbd_actlog.c | 8 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_bitmap.c | 19 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_int.h | 45 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_main.c | 97 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_nl.c | 40 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_proc.c | 3 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_receiver.c | 38 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_req.c | 45 | ||||
| -rw-r--r-- | drivers/block/drbd/drbd_worker.c | 12 |
9 files changed, 216 insertions, 91 deletions
diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c index e54e31b02b8..3fbef018ce5 100644 --- a/drivers/block/drbd/drbd_actlog.c +++ b/drivers/block/drbd/drbd_actlog.c @@ -411,7 +411,7 @@ w_al_write_transaction(struct drbd_conf *mdev, struct drbd_work *w, int unused) + mdev->ldev->md.al_offset + mdev->al_tr_pos; if (!drbd_md_sync_page_io(mdev, mdev->ldev, sector, WRITE)) - drbd_chk_io_error(mdev, 1, true); + drbd_chk_io_error(mdev, 1, DRBD_META_IO_ERROR); if (++mdev->al_tr_pos > div_ceil(mdev->act_log->nr_elements, AL_EXTENTS_PT)) @@ -876,7 +876,11 @@ int __drbd_set_out_of_sync(struct drbd_conf *mdev, sector_t sector, int size, unsigned int enr, count = 0; struct lc_element *e; - if (size <= 0 || (size & 0x1ff) != 0 || size > DRBD_MAX_BIO_SIZE) { + /* this should be an empty REQ_FLUSH */ + if (size == 0) + return 0; + + if (size < 0 || (size & 0x1ff) != 0 || size > DRBD_MAX_BIO_SIZE) { dev_err(DEV, "sector: %llus, size: %d\n", (unsigned long long)sector, size); return 0; diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index fcb956bb4b4..d8456649674 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -889,6 +889,7 @@ struct bm_aio_ctx { unsigned int done; unsigned flags; #define BM_AIO_COPY_PAGES 1 +#define BM_WRITE_ALL_PAGES 2 int error; struct kref kref; }; @@ -1059,7 +1060,8 @@ static int bm_rw(struct drbd_conf *mdev, int rw, unsigned flags, unsigned lazy_w if (lazy_writeout_upper_idx && i == lazy_writeout_upper_idx) break; if (rw & WRITE) { - if (bm_test_page_unchanged(b->bm_pages[i])) { + if (!(flags & BM_WRITE_ALL_PAGES) && + bm_test_page_unchanged(b->bm_pages[i])) { dynamic_dev_dbg(DEV, "skipped bm write for idx %u\n", i); continue; } @@ -1096,7 +1098,7 @@ static int bm_rw(struct drbd_conf *mdev, int rw, unsigned flags, unsigned lazy_w if (ctx->error) { dev_alert(DEV, "we had at least one MD IO ERROR during bitmap IO\n"); - drbd_chk_io_error(mdev, 1, true); + drbd_chk_io_error(mdev, 1, DRBD_META_IO_ERROR); err = -EIO; /* ctx->error ? */ } @@ -1141,6 +1143,17 @@ int drbd_bm_write(struct drbd_conf *mdev) __must_hold(local) } /** + * drbd_bm_write_all() - Write the whole bitmap to its on disk location. + * @mdev: DRBD device. + * + * Will write all pages. + */ +int drbd_bm_write_all(struct drbd_conf *mdev) __must_hold(local) +{ + return bm_rw(mdev, WRITE, BM_WRITE_ALL_PAGES, 0); +} + +/** * drbd_bm_lazy_write_out() - Write bitmap pages 0 to @upper_idx-1, if they have changed. * @mdev: DRBD device. * @upper_idx: 0: write all changed pages; +ve: page index to stop scanning for changed pages @@ -1212,7 +1225,7 @@ int drbd_bm_write_page(struct drbd_conf *mdev, unsigned int idx) __must_hold(loc wait_until_done_or_disk_failure(mdev, mdev->ldev, &ctx->done); if (ctx->error) - drbd_chk_io_error(mdev, 1, true); + drbd_chk_io_error(mdev, 1, DRBD_META_IO_ERROR); /* that should force detach, so the in memory bitmap will be * gone in a moment as well. */ diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index 02f013a073a..b953cc7c9c0 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -813,7 +813,6 @@ enum { SIGNAL_ASENDER, /* whether asender wants to be interrupted */ SEND_PING, /* whether asender should send a ping asap */ - 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! */ @@ -824,7 +823,6 @@ enum { CRASHED_PRIMARY, /* This node was a crashed primary. * Gets cleared when the state.conn * goes into C_CONNECTED state. */ - NO_BARRIER_SUPP, /* underlying block device doesn't implement barriers */ CONSIDER_RESYNC, MD_NO_FUA, /* Users wants us to not use FUA/FLUSH on meta data dev */ @@ -834,6 +832,7 @@ enum { BITMAP_IO_QUEUED, /* Started bitmap IO */ GO_DISKLESS, /* Disk is being detached, on io-error or admin request. */ WAS_IO_ERROR, /* Local disk failed returned IO error */ + FORCE_DETACH, /* Force-detach from local disk, aborting any pending local IO */ RESYNC_AFTER_NEG, /* Resync after online grow after the attach&negotiate finished. */ NET_CONGESTED, /* The data socket is congested */ @@ -851,6 +850,13 @@ enum { AL_SUSPENDED, /* Activity logging is currently suspended. */ AHEAD_TO_SYNC_SOURCE, /* Ahead -> SyncSource queued */ STATE_SENT, /* Do not change state/UUIDs while this is set */ + + CALLBACK_PENDING, /* Whether we have a call_usermodehelper(, UMH_WAIT_PROC) + * pending, from drbd worker context. + * If set, bdi_write_congested() returns true, + * so shrink_page_list() would not recurse into, + * and potentially deadlock on, this drbd worker. + */ }; struct drbd_bitmap; /* opaque for drbd_conf */ @@ -1130,8 +1136,8 @@ struct drbd_conf { int rs_in_flight; /* resync sectors in flight (to proxy, in proxy and from proxy) */ int rs_planed; /* resync sectors already planned */ atomic_t ap_in_flight; /* App sectors in flight (waiting for ack) */ - int peer_max_bio_size; - int local_max_bio_size; + unsigned int peer_max_bio_size; + unsigned int local_max_bio_size; }; static inline struct drbd_conf *minor_to_mdev(unsigned int minor) @@ -1435,9 +1441,9 @@ struct bm_extent { * hash table. */ #define HT_SHIFT 8 #define DRBD_MAX_BIO_SIZE (1U<<(9+HT_SHIFT)) -#define DRBD_MAX_BIO_SIZE_SAFE (1 << 12) /* Works always = 4k */ +#define DRBD_MAX_BIO_SIZE_SAFE (1U << 12) /* Works always = 4k */ -#define DRBD_MAX_SIZE_H80_PACKET (1 << 15) /* The old header only allows packets up to 32Kib data */ +#define DRBD_MAX_SIZE_H80_PACKET (1U << 15) /* The old header only allows packets up to 32Kib data */ /* Number of elements in the app_reads_hash */ #define APP_R_HSIZE 15 @@ -1463,6 +1469,7 @@ extern int drbd_bm_e_weight(struct drbd_conf *mdev, unsigned long enr); extern int drbd_bm_write_page(struct drbd_conf *mdev, unsigned int idx) __must_hold(local); extern int drbd_bm_read(struct drbd_conf *mdev) __must_hold(local); extern int drbd_bm_write(struct drbd_conf *mdev) __must_hold(local); +extern int drbd_bm_write_all(struct drbd_conf *mdev) __must_hold(local); extern int drbd_bm_write_copy_pages(struct drbd_conf *mdev) __must_hold(local); extern unsigned long drbd_bm_ALe_set_all(struct drbd_conf *mdev, unsigned long al_enr); @@ -1840,12 +1847,20 @@ static inline int drbd_request_state(struct drbd_conf *mdev, return _drbd_request_state(mdev, mask, val, CS_VERBOSE + CS_ORDERED); } +enum drbd_force_detach_flags { + DRBD_IO_ERROR, + DRBD_META_IO_ERROR, + DRBD_FORCE_DETACH, +}; + #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) +static inline void __drbd_chk_io_error_(struct drbd_conf *mdev, + enum drbd_force_detach_flags forcedetach, + const char *where) { switch (mdev->ldev->dc.on_io_error) { case EP_PASS_ON: - if (!forcedetach) { + if (forcedetach == DRBD_IO_ERROR) { if (__ratelimit(&drbd_ratelimit_state)) dev_err(DEV, "Local IO failed in %s.\n", where); if (mdev->state.disk > D_INCONSISTENT) @@ -1856,6 +1871,8 @@ static inline void __drbd_chk_io_error_(struct drbd_conf *mdev, int forcedetach, case EP_DETACH: case EP_CALL_HELPER: set_bit(WAS_IO_ERROR, &mdev->flags); + if (forcedetach == DRBD_FORCE_DETACH) + set_bit(FORCE_DETACH, &mdev->flags); if (mdev->state.disk > D_FAILED) { _drbd_set_state(_NS(mdev, disk, D_FAILED), CS_HARD, NULL); dev_err(DEV, @@ -1875,7 +1892,7 @@ static inline void __drbd_chk_io_error_(struct drbd_conf *mdev, int forcedetach, */ #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) + int error, enum drbd_force_detach_flags forcedetach, const char *where) { if (error) { unsigned long flags; @@ -2405,15 +2422,17 @@ static inline void dec_ap_bio(struct drbd_conf *mdev) int ap_bio = atomic_dec_return(&mdev->ap_bio_cnt); D_ASSERT(ap_bio >= 0); + + 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); + } + /* 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 int drbd_set_ed_uuid(struct drbd_conf *mdev, u64 val) diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 920ede2829d..f93a0320e95 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -79,6 +79,7 @@ static int w_md_sync(struct drbd_conf *mdev, struct drbd_work *w, int unused); static void md_sync_timer_fn(unsigned long data); static int w_bitmap_io(struct drbd_conf *mdev, struct drbd_work *w, int unused); static int w_go_diskless(struct drbd_conf *mdev, struct drbd_work *w, int unused); +static void _tl_clear(struct drbd_conf *mdev); MODULE_AUTHOR("Philipp Reisner <phil@linbit.com>, " "Lars Ellenberg <lars@linbit.com>"); @@ -432,19 +433,10 @@ static void _tl_restart(struct drbd_conf *mdev, enum drbd_req_event what) /* Actions operating on the disk state, also want to work on requests that got barrier acked. */ - switch (what) { - case fail_frozen_disk_io: - case restart_frozen_disk_io: - list_for_each_safe(le, tle, &mdev->barrier_acked_requests) { - req = list_entry(le, struct drbd_request, tl_requests); - _req_mod(req, what); - } - case connection_lost_while_pending: - case resend: - break; - default: - dev_err(DEV, "what = %d in _tl_restart()\n", what); + list_for_each_safe(le, tle, &mdev->barrier_acked_requests) { + req = list_entry(le, struct drbd_request, tl_requests); + _req_mod(req, what); } } @@ -459,11 +451,16 @@ static void _tl_restart(struct drbd_conf *mdev, enum drbd_req_event what) */ void tl_clear(struct drbd_conf *mdev) { + spin_lock_irq(&mdev->req_lock); + _tl_clear(mdev); + spin_unlock_irq(&mdev->req_lock); +} + +static void _tl_clear(struct drbd_conf *mdev) +{ struct list_head *le, *tle; struct drbd_request *r; - spin_lock_irq(&mdev->req_lock); - _tl_restart(mdev, connection_lost_while_pending); /* we expect this list to be empty. */ @@ -482,7 +479,6 @@ void tl_clear(struct drbd_conf *mdev) memset(mdev->app_reads_hash, 0, APP_R_HSIZE*sizeof(void *)); - spin_unlock_irq(&mdev->req_lock); } void tl_restart(struct drbd_conf *mdev, enum drbd_req_event what) @@ -1476,12 +1472,12 @@ static void after_state_ch(struct drbd_conf *mdev, union drbd_state os, if (ns.susp_fen) { /* case1: The outdate peer handler is successful: */ if (os.pdsk > D_OUTDATED && ns.pdsk <= D_OUTDATED) { - tl_clear(mdev); if (test_bit(NEW_CUR_UUID, &mdev->flags)) { drbd_uuid_new_current(mdev); clear_bit(NEW_CUR_UUID, &mdev->flags); } spin_lock_irq(&mdev->req_lock); + _tl_clear(mdev); _drbd_set_state(_NS(mdev, susp_fen, 0), CS_VERBOSE, NULL); spin_unlock_irq(&mdev->req_lock); } @@ -1514,6 +1510,13 @@ static void after_state_ch(struct drbd_conf *mdev, union drbd_state os, /* Do not change the order of the if above and the two below... */ if (os.pdsk == D_DISKLESS && ns.pdsk > D_DISKLESS) { /* attach on the peer */ + /* we probably will start a resync soon. + * make sure those things are properly reset. */ + mdev->rs_total = 0; + mdev->rs_failed = 0; + atomic_set(&mdev->rs_pending_cnt, 0); + drbd_rs_cancel_all(mdev); + drbd_send_uuids(mdev); drbd_send_state(mdev, ns); } @@ -1630,9 +1633,24 @@ static void after_state_ch(struct drbd_conf *mdev, union drbd_state os, eh = mdev->ldev->dc.on_io_error; was_io_error = test_and_clear_bit(WAS_IO_ERROR, &mdev->flags); - /* Immediately allow completion of all application IO, that waits - for completion from the local disk. */ - tl_abort_disk_io(mdev); + if (was_io_error && eh == EP_CALL_HELPER) + drbd_khelper(mdev, "local-io-error"); + + /* Immediately allow completion of all application IO, + * that waits for completion from the local disk, + * if this was a force-detach due to disk_timeout + * or administrator request (drbdsetup detach --force). + * Do NOT abort otherwise. + * Aborting local requests may cause serious problems, + * if requests are completed to upper layers already, + * and then later the already submitted local bio completes. + * This can cause DMA into former bio pages that meanwhile + * have been re-used for other things. + * So aborting local requests may cause crashes, + * or even worse, silent data corruption. + */ + if (test_and_clear_bit(FORCE_DETACH, &mdev->flags)) + tl_abort_disk_io(mdev); /* current state still has to be D_FAILED, * there is only one way out: to D_DISKLESS, @@ -1653,9 +1671,6 @@ static void after_state_ch(struct drbd_conf *mdev, union drbd_state os, drbd_md_sync(mdev); } put_ldev(mdev); - - if (was_io_error && eh == EP_CALL_HELPER) - drbd_khelper(mdev, "local-io-error"); } /* second half of local IO error, failure to attach, @@ -1669,10 +1684,6 @@ static void after_state_ch(struct drbd_conf *mdev, union drbd_state os, "ASSERT FAILED: disk is %s while going diskless\n", drbd_disk_str(mdev->state.disk)); - mdev->rs_total = 0; - mdev->rs_failed = 0; - atomic_set(&mdev->rs_pending_cnt, 0); - if (ns.conn >= C_CONNECTED) drbd_send_state(mdev, ns); @@ -2194,7 +2205,8 @@ int drbd_send_sizes(struct drbd_conf *mdev, int trigger_reply, enum dds_flags fl { struct p_sizes p; sector_t d_size, u_size; - int q_order_type, max_bio_size; + int q_order_type; + unsigned int max_bio_size; int ok; if (get_ldev_if_state(mdev, D_NEGOTIATING)) { @@ -2203,7 +2215,7 @@ int drbd_send_sizes(struct drbd_conf *mdev, int trigger_reply, enum dds_flags fl u_size = mdev->ldev->dc.disk_size; q_order_type = drbd_queue_order_type(mdev); max_bio_size = queue_max_hw_sectors(mdev->ldev->backing_bdev->bd_disk->queue) << 9; - max_bio_size = min_t(int, max_bio_size, DRBD_MAX_BIO_SIZE); + max_bio_size = min(max_bio_size, DRBD_MAX_BIO_SIZE); put_ldev(mdev); } else { d_size = 0; @@ -2214,7 +2226,7 @@ int drbd_send_sizes(struct drbd_conf *mdev, int trigger_reply, enum dds_flags fl /* Never allow old drbd (up to 8.3.7) to see more than 32KiB */ if (mdev->agreed_pro_version <= 94) - max_bio_size = min_t(int, max_bio_size, DRBD_MAX_SIZE_H80_PACKET); + max_bio_size = min(max_bio_size, DRBD_MAX_SIZE_H80_PACKET); p.d_size = cpu_to_be64(d_size); p.u_size = cpu_to_be64(u_size); @@ -3521,9 +3533,9 @@ static void drbd_cleanup(void) } /** - * drbd_congested() - Callback for pdflush + * drbd_congested() - Callback for the flusher thread * @congested_data: User data - * @bdi_bits: Bits pdflush is currently interested in + * @bdi_bits: Bits the BDI flusher thread is currently interested in * * Returns 1<<BDI_async_congested and/or 1<<BDI_sync_congested if we are congested. */ @@ -3541,6 +3553,22 @@ static int drbd_congested(void *congested_data, int bdi_bits) goto out; } + if (test_bit(CALLBACK_PENDING, &mdev->flags)) { + r |= (1 << BDI_async_congested); + /* Without good local data, we would need to read from remote, + * and that would need the worker thread as well, which is + * currently blocked waiting for that usermode helper to + * finish. + */ + if (!get_ldev_if_state(mdev, D_UP_TO_DATE)) + r |= (1 << BDI_sync_congested); + else + put_ldev(mdev); + r &= bdi_bits; + reason = 'c'; + goto out; + } + if (get_ldev(mdev)) { q = bdev_get_queue(mdev->ldev->backing_bdev); r = bdi_congested(&q->backing_dev_info, bdi_bits); @@ -3604,6 +3632,7 @@ struct drbd_conf *drbd_new_device(unsigned int minor) q->backing_dev_info.congested_data = mdev; blk_queue_make_request(q, drbd_make_request); + blk_queue_flush(q, REQ_FLUSH | REQ_FUA); /* Setting the max_hw_sectors to an odd value of 8kibyte here This triggers a max_bio_size message upon first attach or connect */ blk_queue_max_hw_sectors(q, DRBD_MAX_BIO_SIZE_SAFE >> 8); @@ -3870,7 +3899,7 @@ void drbd_md_sync(struct drbd_conf *mdev) if (!drbd_md_sync_page_io(mdev, mdev->ldev, sector, WRITE)) { /* this was a try anyways ... */ dev_err(DEV, "meta data update failed!\n"); - drbd_chk_io_error(mdev, 1, true); + drbd_chk_io_error(mdev, 1, DRBD_META_IO_ERROR); } /* Update mdev->ldev->md.la_size_sect, @@ -3950,9 +3979,9 @@ int drbd_md_read(struct drbd_conf *mdev, struct drbd_backing_dev *bdev) spin_lock_irq(&mdev->req_lock); if (mdev->state.conn < C_CONNECTED) { - int peer; + unsigned int peer; peer = be32_to_cpu(buffer->la_peer_max_bio_size); - peer = max_t(int, peer, DRBD_MAX_BIO_SIZE_SAFE); + peer = max(peer, DRBD_MAX_BIO_SIZE_SAFE); mdev->peer_max_bio_size = peer; } spin_unlock_irq(&mdev->req_lock); diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 6d4de6a72e8..edb490aad8b 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -147,6 +147,9 @@ int drbd_khelper(struct drbd_conf *mdev, char *cmd) char *argv[] = {usermode_helper, cmd, mb, NULL }; int ret; + if (current == mdev->worker.task) + set_bit(CALLBACK_PENDING, &mdev->flags); + snprintf(mb, 12, "minor-%d", mdev_to_minor(mdev)); if (get_net_conf(mdev)) { @@ -189,6 +192,9 @@ int drbd_khelper(struct drbd_conf *mdev, char *cmd) usermode_helper, cmd, mb, (ret >> 8) & 0xff, ret); + if (current == mdev->worker.task) + clear_bit(CALLBACK_PENDING, &mdev->flags); + if (ret < 0) /* Ignore any ERRNOs we got. */ ret = 0; @@ -668,8 +674,8 @@ enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *mdev, enum dds la_size_changed && md_moved ? "size changed and md moved" : la_size_changed ? "size changed" : "md moved"); /* next line implicitly does drbd_suspend_io()+drbd_resume_io() */ - err = drbd_bitmap_io(mdev, &drbd_bm_write, - "size changed", BM_LOCKED_MASK); + err = drbd_bitmap_io(mdev, md_moved ? &drbd_bm_write_all : &drbd_bm_write, + "size changed", BM_LOCKED_MASK); if (err) { rv = dev_size_error; goto out; @@ -795,8 +801,8 @@ static int drbd_check_al_size(struct drbd_conf *mdev) static void drbd_setup_queue_param(struct drbd_conf *mdev, unsigned int max_bio_size) { struct request_queue * const q = mdev->rq_queue; - int max_hw_sectors = max_bio_size >> 9; - int max_segments = 0; + unsigned int max_hw_sectors = max_bio_size >> 9; + unsigned int max_segments = 0; if (get_ldev_if_state(mdev, D_ATTACHING)) { struct request_queue * const b = mdev->ldev->backing_bdev->bd_disk->queue; @@ -829,7 +835,7 @@ static void drbd_setup_queue_param(struct drbd_conf *mdev, unsigned int max_bio_ void drbd_reconsider_max_bio_size(struct drbd_conf *mdev) { - int now, new, local, peer; + unsigned int now, new, local, peer; now = queue_max_hw_sectors(mdev->rq_queue) << 9; local = mdev->local_max_bio_size; /* Eventually last known value, from volatile memory */ @@ -840,13 +846,14 @@ void drbd_reconsider_max_bio_size(struct drbd_conf *mdev) mdev->local_max_bio_size = local; put_ldev(mdev); } + local = min(local, DRBD_MAX_BIO_SIZE); /* We may ignore peer limits if the peer is modern enough. Because new from 8.3.8 onwards the peer can use multiple BIOs for a single peer_request */ if (mdev->state.conn >= C_CONNECTED) { if (mdev->agreed_pro_version < 94) { - peer = min_t(int, mdev->peer_max_bio_size, DRBD_MAX_SIZE_H80_PACKET); + peer = min(mdev->peer_max_bio_size, DRBD_MAX_SIZE_H80_PACKET); /* Correct old drbd (up to 8.3.7) if it believes it can do more than 32KiB */ } else if (mdev->agreed_pro_version == 94) peer = DRBD_MAX_SIZE_H80_PACKET; @@ -854,10 +861,10 @@ void drbd_reconsider_max_bio_size(struct drbd_conf *mdev) peer = DRBD_MAX_BIO_SIZE; } - new = min_t(int, local, peer); + new = min(local, peer); if (mdev->state.role == R_PRIMARY && new < now) - dev_err(DEV, "ASSERT FAILED new < now; (%d < %d)\n", new, now); + dev_err(DEV, "ASSERT FAILED new < now; (%u < %u)\n", new, now); if (new != now) dev_info(DEV, "max BIO size = %u\n", new); @@ -950,6 +957,14 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp * to realize a "hot spare" feature (not that I'd recommend that) */ wait_event(mdev->misc_wait, !atomic_read(&mdev->local_cnt)); + /* make sure there is no leftover from previous force-detach attempts */ + clear_bit(FORCE_DETACH, &mdev->flags); + + /* and no leftover from previously aborted resync or verify, either */ + mdev->rs_total = 0; + mdev->rs_failed = 0; + atomic_set(&mdev->rs_pending_cnt, 0); + /* allocation not in the IO path, cqueue thread context */ nbc = kzalloc(sizeof(struct drbd_backing_dev), GFP_KERNEL); if (!nbc) { @@ -1345,6 +1360,7 @@ static int drbd_nl_detach(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp, } if (dt.detach_force) { + set_bit(FORCE_DETACH, &mdev->flags); drbd_force_state(mdev, NS(disk, D_FAILED)); reply->ret_code = SS_SUCCESS; goto out; @@ -1962,9 +1978,11 @@ static int drbd_nl_invalidate(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nl int retcode; /* If there is still bitmap IO pending, probably because of a previous - * resync just being finished, wait for it before requesting a new resync. */ + * resync just being finished, wait for it before requesting a new resync. + * Also wait for it's after_state_ch(). */ drbd_suspend_io(mdev); wait_event(mdev->misc_wait, !test_bit(BITMAP_IO, &mdev->flags)); + drbd_flush_workqueue(mdev); retcode = _drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_T), CS_ORDERED); @@ -2003,9 +2021,11 @@ static int drbd_nl_invalidate_peer(struct drbd_conf *mdev, struct drbd_nl_cfg_re int retcode; /* If there is still bitmap IO pending, probably because of a previous - * resync just being finished, wait for it before requesting a new resync. */ + * resync just being finished, wait for it before requesting a new resync. + * Also wait for it's after_state_ch(). */ drbd_suspend_io(mdev); wait_event(mdev->misc_wait, !test_bit(BITMAP_IO, &mdev->flags)); + drbd_flush_workqueue(mdev); retcode = _drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S), CS_ORDERED); diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c index 869bada2ed0..5496104f90b 100644 --- a/drivers/block/drbd/drbd_proc.c +++ b/drivers/block/drbd/drbd_proc.c @@ -245,6 +245,9 @@ static int drbd_seq_show(struct seq_file *seq, void *v) mdev->state.role == R_SECONDARY) { seq_printf(seq, "%2d: cs:Unconfigured\n", i); } else { + /* reset mdev->congestion_reason */ + bdi_rw_congested(&mdev->rq_queue->backing_dev_info); + seq_printf(seq, "%2d: cs:%s ro:%s/%s ds:%s/%s %c %c%c%c%c%c%c\n" " ns:%u nr:%u dw:%u dr:%u al:%u bm:%u " diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index ea4836e0ae9..c74ca2df743 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -277,6 +277,9 @@ static void drbd_pp_free(struct drbd_conf *mdev, struct page *page, int is_net) atomic_t *a = is_net ? &mdev->pp_in_use_by_net : &mdev->pp_in_use; int i; + if (page == NULL) + return; + if (drbd_pp_vacant > (DRBD_MAX_BIO_SIZE/PAGE_SIZE)*minor_count) i = page_chain_free(page); else { @@ -316,7 +319,7 @@ struct drbd_epoch_entry *drbd_alloc_ee(struct drbd_conf *mdev, gfp_t gfp_mask) __must_hold(local) { struct drbd_epoch_entry *e; - struct page *page; + struct page *page = NULL; unsigned nr_pages = (data_size + PAGE_SIZE -1) >> PAGE_SHIFT; if (drbd_insert_fault(mdev, DRBD_FAULT_AL_EE)) @@ -329,9 +332,11 @@ struct drbd_epoch_entry *drbd_alloc_ee(struct drbd_conf *mdev, return NULL; } - page = drbd_pp_alloc(mdev, nr_pages, (gfp_mask & __GFP_WAIT)); - if (!page) - goto fail; + if (data_size) { + page = drbd_pp_alloc(mdev, nr_pages, (gfp_mask & __GFP_WAIT)); + if (!page) + goto fail; + } INIT_HLIST_NODE(&e->collision); e->epoch = NULL; @@ -1270,7 +1275,6 @@ read_in_block(struct drbd_conf *mdev, u64 id, sector_t sector, int data_size) __ data_size -= dgs; - ERR_IF(data_size == 0) return NULL; ERR_IF(data_size & 0x1ff) return NULL; ERR_IF(data_size > DRBD_MAX_BIO_SIZE) return NULL; @@ -1291,6 +1295,9 @@ read_in_block(struct drbd_conf *mdev, u64 id, sector_t sector, int data_size) __ if (!e) return NULL; + if (!data_size) + return e; + ds = data_size; page = e->pages; page_chain_for_each(page) { @@ -1715,6 +1722,10 @@ static int receive_Data(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned dp_flags = be32_to_cpu(p->dp_flags); rw |= wire_flags_to_bio(mdev, dp_flags); + if (e->pages == NULL) { + D_ASSERT(e->size == 0); + D_ASSERT(dp_flags & DP_FLUSH); + } if (dp_flags & DP_MAY_SET_IN_SYNC) e->flags |= EE_MAY_SET_IN_SYNC; @@ -3801,11 +3812,18 @@ void drbd_free_tl_hash(struct drbd_conf *mdev) mdev->ee_hash = NULL; mdev->ee_hash_s = 0; - /* paranoia code */ - for (h = mdev->tl_hash; h < mdev->tl_hash + mdev->tl_hash_s; h++) - if (h->first) - dev_err(DEV, "ASSERT FAILED tl_hash[%u] == %p, expected NULL\n", - (int)(h - mdev->tl_hash), h->first); + /* We may not have had the chance to wait for all locally pending + * application requests. The hlist_add_fake() prevents access after + * free on master bio completion. */ + for (h = mdev->tl_hash; h < mdev->tl_hash + mdev->tl_hash_s; h++) { + struct drbd_request *req; + struct hlist_node *pos, *n; + hlist_for_each_entry_safe(req, pos, n, h, collision) { + hlist_del_init(&req->collision); + hlist_add_fake(&req->collision); + } + } + kfree(mdev->tl_hash); mdev->tl_hash = NULL; mdev->tl_hash_s = 0; diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 8e93a6ac9bb..01b2ac641c7 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -455,7 +455,7 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what, req->rq_state |= RQ_LOCAL_COMPLETED; req->rq_state &= ~RQ_LOCAL_PENDING; - __drbd_chk_io_error(mdev, false); + __drbd_chk_io_error(mdev, DRBD_IO_ERROR); _req_may_be_done_not_susp(req, m); break; @@ -477,7 +477,7 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what, break; } - __drbd_chk_io_error(mdev, false); + __drbd_chk_io_error(mdev, DRBD_IO_ERROR); goto_queue_for_net_read: @@ -695,6 +695,12 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what, break; case resend: + /* Simply complete (local only) READs. */ + if (!(req->rq_state & RQ_WRITE) && !req->w.cb) { + _req_may_be_done(req, m); + break; + } + /* If RQ_NET_OK is already set, we got a P_WRITE_ACK or P_RECV_ACK before the connection loss (B&C only); only P_BARRIER_ACK was missing. Trowing them out of the TL here by pretending we got a BARRIER_ACK @@ -834,7 +840,15 @@ static int drbd_make_request_common(struct drbd_conf *mdev, struct bio *bio, uns req->private_bio = NULL; } if (rw == WRITE) { - remote = 1; + /* Need to replicate writes. Unless it is an empty flush, + * which is better mapped to a DRBD P_BARRIER packet, + * also for drbd wire protocol compatibility reasons. */ + if (unlikely(size == 0)) { + /* The only size==0 bios we expect are empty flushes. */ + D_ASSERT(bio->bi_rw & REQ_FLUSH); + remote = 0; + } else + remote = 1; } else { /* READ || READA */ if (local) { @@ -870,8 +884,11 @@ static int drbd_make_request_common(struct drbd_conf *mdev, struct bio *bio, uns * extent. This waits for any resync activity in the corresponding * resync extent to finish, and, if necessary, pulls in the target * extent into the activity log, which involves further disk io because - * of transactional on-disk meta data updates. */ - if (rw == WRITE && local && !test_bit(AL_SUSPENDED, &mdev->flags)) { + * of transactional on-disk meta data updates. + * Empty flushes don't need to go into the activity log, they can only + * flush data for pending writes which are already in there. */ + if (rw == WRITE && local && size + && !test_bit(AL_SUSPENDED, &mdev->flags)) { req->rq_state |= RQ_IN_ACT_LOG; drbd_al_begin_io(mdev, sector); } @@ -994,7 +1011,10 @@ allocate_barrier: if (rw == WRITE && _req_conflicts(req)) goto fail_conflicting; - list_add_tail(&req->tl_requests, &mdev->newest_tle->requests); + /* no point in adding empty flushes to the transfer log, + * they are mapped to drbd barriers already. */ + if (likely(size!=0)) + list_add_tail(&req->tl_requests, &mdev->newest_tle->requests); /* NOTE remote first: to get the concurrent write detection right, * we must register the request before start of local IO. */ @@ -1014,6 +1034,14 @@ allocate_barrier: mdev->net_conf->on_congestion != OC_BLOCK && mdev->agreed_pro_version >= 96) maybe_pull_ahead(mdev); + /* If this was a flush, queue a drbd barrier/start a new epoch. + * Unless the current epoch was empty anyways, or we are not currently + * replicating, in which case there is no point. */ + if (unlikely(bio->bi_rw & REQ_FLUSH) + && mdev->newest_tle->n_writes + && drbd_should_do_remote(mdev->state)) + queue_barrier(mdev); + spin_unlock_irq(&mdev->req_lock); kfree(b); /* if someone else has beaten us to it... */ @@ -1111,13 +1139,12 @@ void drbd_make_request(struct request_queue *q, struct bio *bio) /* * what we "blindly" assume: */ - D_ASSERT(bio->bi_size > 0); D_ASSERT((bio->bi_size & 0x1ff) == 0); /* to make some things easier, force alignment of requests within the * granularity of our hash tables */ s_enr = bio->bi_sector >> HT_SHIFT; - e_enr = (bio->bi_sector+(bio->bi_size>>9)-1) >> HT_SHIFT; + e_enr = bio->bi_size ? (bio->bi_sector+(bio->bi_size>>9)-1) >> HT_SHIFT : s_enr; if (likely(s_enr == e_enr)) { do { @@ -1275,7 +1302,7 @@ void request_timer_fn(unsigned long data) time_after(now, req->start_time + dt) && !time_in_range(now, mdev->last_reattach_jif, mdev->last_reattach_jif + dt)) { dev_warn(DEV, "Local backing device failed to meet the disk-timeout\n"); - __drbd_chk_io_error(mdev, 1); + __drbd_chk_io_error(mdev, DRBD_FORCE_DETACH); } nt = (time_after(now, req->start_time + et) ? now : req->start_time) + et; spin_unlock_irq(&mdev->req_lock); diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 620c70ff223..6bce2cc179d 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -111,7 +111,7 @@ void drbd_endio_read_sec_final(struct drbd_epoch_entry *e) __releases(local) if (list_empty(&mdev->read_ee)) wake_up(&mdev->ee_wait); if (test_bit(__EE_WAS_ERROR, &e->flags)) - __drbd_chk_io_error(mdev, false); + __drbd_chk_io_error(mdev, DRBD_IO_ERROR); spin_unlock_irqrestore(&mdev->req_lock, flags); drbd_queue_work(&mdev->data.work, &e->w); @@ -154,7 +154,7 @@ static void drbd_endio_write_sec_final(struct drbd_epoch_entry *e) __releases(lo : list_empty(&mdev->active_ee); if (test_bit(__EE_WAS_ERROR, &e->flags)) - __drbd_chk_io_error(mdev, false); + __drbd_chk_io_error(mdev, DRBD_IO_ERROR); spin_unlock_irqrestore(&mdev->req_lock, flags); if (is_syncer_req) @@ -1501,14 +1501,6 @@ void drbd_start_resync(struct drbd_conf *mdev, enum drbd_conns side) return; } - if (mdev->state.conn < C_AHEAD) { - /* In case a previous resync run was aborted by an IO error/detach on the peer. */ - drbd_rs_cancel_all(mdev); - /* This should be done when we abort the resync. We definitely do not - want to have this for connections going back and forth between - Ahead/Behind and SyncSource/SyncTarget */ - } - if (side == C_SYNC_TARGET) { /* Since application IO was locked out during C_WF_BITMAP_T and C_WF_SYNC_UUID we are still unmodified. Before going to C_SYNC_TARGET |