diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-10-18 12:12:45 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-10-18 12:12:45 -0700 |
commit | e75437fb9322cf0ac707046a12d78a25f9d52ccf (patch) | |
tree | 959fbda9d606f500e5c554eb68984111a9e6b3b3 | |
parent | d3dc366bbaf07c125561e90d6da4bb147741101a (diff) | |
parent | b277da0a8a594308e17881f4926879bd5fca2a2d (diff) | |
download | lwn-e75437fb9322cf0ac707046a12d78a25f9d52ccf.tar.gz lwn-e75437fb9322cf0ac707046a12d78a25f9d52ccf.zip |
Merge branch 'for-3.18/drivers' of git://git.kernel.dk/linux-block
Pull block layer driver update from Jens Axboe:
"This is the block driver pull request for 3.18. Not a lot in there
this round, and nothing earth shattering.
- A round of drbd fixes from the linbit team, and an improvement in
asender performance.
- Removal of deprecated (and unused) IRQF_DISABLED flag in rsxx and
hd from Michael Opdenacker.
- Disable entropy collection from flash devices by default, from Mike
Snitzer.
- A small collection of xen blkfront/back fixes from Roger Pau Monné
and Vitaly Kuznetsov"
* 'for-3.18/drivers' of git://git.kernel.dk/linux-block:
block: disable entropy contributions for nonrot devices
xen, blkfront: factor out flush-related checks from do_blkif_request()
xen-blkback: fix leak on grant map error path
xen/blkback: unmap all persistent grants when frontend gets disconnected
rsxx: Remove deprecated IRQF_DISABLED
block: hd: remove deprecated IRQF_DISABLED
drbd: use RB_DECLARE_CALLBACKS() to define augment callbacks
drbd: compute the end before rb_insert_augmented()
drbd: Add missing newline in resync progress display in /proc/drbd
drbd: reduce lock contention in drbd_worker
drbd: Improve asender performance
drbd: Get rid of the WORK_PENDING macro
drbd: Get rid of the __no_warn and __cond_lock macros
drbd: Avoid inconsistent locking warning
drbd: Remove superfluous newline from "resync_extents" debugfs entry.
drbd: Use consistent names for all the bi_end_io callbacks
drbd: Use better variable names
30 files changed, 132 insertions, 147 deletions
diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c index d26a3fa63688..a2dfa169237d 100644 --- a/drivers/block/drbd/drbd_actlog.c +++ b/drivers/block/drbd/drbd_actlog.c @@ -158,14 +158,14 @@ static int _drbd_md_sync_page_io(struct drbd_device *device, if (bio_add_page(bio, device->md_io.page, size, 0) != size) goto out; bio->bi_private = device; - bio->bi_end_io = drbd_md_io_complete; + bio->bi_end_io = drbd_md_endio; bio->bi_rw = rw; if (!(rw & WRITE) && device->state.disk == D_DISKLESS && device->ldev == NULL) /* special case, drbd_md_read() during drbd_adm_attach(): no get_ldev */ ; else if (!get_ldev_if_state(device, D_ATTACHING)) { - /* Corresponding put_ldev in drbd_md_io_complete() */ + /* Corresponding put_ldev in drbd_md_endio() */ drbd_err(device, "ASSERT FAILED: get_ldev_if_state() == 1 in _drbd_md_sync_page_io()\n"); err = -ENODEV; goto out; diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index 426c97aef900..434c77dcc99e 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -941,7 +941,7 @@ static void drbd_bm_aio_ctx_destroy(struct kref *kref) } /* bv_page may be a copy, or may be the original */ -static void bm_async_io_complete(struct bio *bio, int error) +static void drbd_bm_endio(struct bio *bio, int error) { struct drbd_bm_aio_ctx *ctx = bio->bi_private; struct drbd_device *device = ctx->device; @@ -1027,7 +1027,7 @@ static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_ho * according to api. Do we want to assert that? */ bio_add_page(bio, page, len, 0); bio->bi_private = ctx; - bio->bi_end_io = bm_async_io_complete; + bio->bi_end_io = drbd_bm_endio; if (drbd_insert_fault(device, (rw & WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD)) { bio->bi_rw |= rw; @@ -1125,7 +1125,7 @@ static int bm_rw(struct drbd_device *device, const unsigned int flags, unsigned } /* - * We initialize ctx->in_flight to one to make sure bm_async_io_complete + * We initialize ctx->in_flight to one to make sure drbd_bm_endio * will not set ctx->done early, and decrement / test it here. If there * are still some bios in flight, we need to wait for them here. * If all IO is done already (or nothing had been submitted), there is diff --git a/drivers/block/drbd/drbd_debugfs.c b/drivers/block/drbd/drbd_debugfs.c index 5c20b18540b8..900d4d3272d1 100644 --- a/drivers/block/drbd/drbd_debugfs.c +++ b/drivers/block/drbd/drbd_debugfs.c @@ -695,7 +695,7 @@ static void resync_dump_detail(struct seq_file *m, struct lc_element *e) { struct bm_extent *bme = lc_entry(e, struct bm_extent, lce); - seq_printf(m, "%5d %s %s %s\n", bme->rs_left, + seq_printf(m, "%5d %s %s %s", bme->rs_left, test_bit(BME_NO_WRITES, &bme->flags) ? "NO_WRITES" : "---------", test_bit(BME_LOCKED, &bme->flags) ? "LOCKED" : "------", test_bit(BME_PRIORITY, &bme->flags) ? "PRIORITY" : "--------" diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index 1a000016ccdf..9b22f8f01b57 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -61,8 +61,6 @@ # 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 bool disable_sendpage; @@ -1483,7 +1481,7 @@ extern int drbd_khelper(struct drbd_device *device, char *cmd); /* drbd_worker.c */ /* bi_end_io handlers */ -extern void drbd_md_io_complete(struct bio *bio, int error); +extern void drbd_md_endio(struct bio *bio, int error); extern void drbd_peer_request_endio(struct bio *bio, int error); extern void drbd_request_endio(struct bio *bio, int error); extern int drbd_worker(struct drbd_thread *thi); @@ -2100,16 +2098,19 @@ static inline bool is_sync_state(enum drbd_conns connection_state) /** * get_ldev() - Increase the ref count on device->ldev. Returns 0 if there is no ldev - * @M: DRBD device. + * @_device: DRBD device. + * @_min_state: Minimum device state required for success. * * You have to call put_ldev() when finished working with device->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)) +#define get_ldev_if_state(_device, _min_state) \ + (_get_ldev_if_state((_device), (_min_state)) ? \ + ({ __acquire(x); true; }) : false) +#define get_ldev(_device) get_ldev_if_state(_device, D_INCONSISTENT) static inline void put_ldev(struct drbd_device *device) { - enum drbd_disk_state ds = device->state.disk; + enum drbd_disk_state disk_state = device->state.disk; /* We must check the state *before* the atomic_dec becomes visible, * or we have a theoretical race where someone hitting zero, * while state still D_FAILED, will then see D_DISKLESS in the @@ -2122,10 +2123,10 @@ static inline void put_ldev(struct drbd_device *device) __release(local); D_ASSERT(device, i >= 0); if (i == 0) { - if (ds == D_DISKLESS) + if (disk_state == D_DISKLESS) /* even internal references gone, safe to destroy */ drbd_device_post_work(device, DESTROY_DISK); - if (ds == D_FAILED) + if (disk_state == D_FAILED) /* all application IO references gone. */ if (!test_and_set_bit(GOING_DISKLESS, &device->flags)) drbd_device_post_work(device, GO_DISKLESS); diff --git a/drivers/block/drbd/drbd_interval.c b/drivers/block/drbd/drbd_interval.c index 89c497c630b4..51b25ad85251 100644 --- a/drivers/block/drbd/drbd_interval.c +++ b/drivers/block/drbd/drbd_interval.c @@ -37,40 +37,8 @@ compute_subtree_last(struct drbd_interval *node) return max; } -static void augment_propagate(struct rb_node *rb, struct rb_node *stop) -{ - while (rb != stop) { - struct drbd_interval *node = rb_entry(rb, struct drbd_interval, rb); - sector_t subtree_last = compute_subtree_last(node); - if (node->end == subtree_last) - break; - node->end = subtree_last; - rb = rb_parent(&node->rb); - } -} - -static void augment_copy(struct rb_node *rb_old, struct rb_node *rb_new) -{ - struct drbd_interval *old = rb_entry(rb_old, struct drbd_interval, rb); - struct drbd_interval *new = rb_entry(rb_new, struct drbd_interval, rb); - - new->end = old->end; -} - -static void augment_rotate(struct rb_node *rb_old, struct rb_node *rb_new) -{ - struct drbd_interval *old = rb_entry(rb_old, struct drbd_interval, rb); - struct drbd_interval *new = rb_entry(rb_new, struct drbd_interval, rb); - - new->end = old->end; - old->end = compute_subtree_last(old); -} - -static const struct rb_augment_callbacks augment_callbacks = { - augment_propagate, - augment_copy, - augment_rotate, -}; +RB_DECLARE_CALLBACKS(static, augment_callbacks, struct drbd_interval, rb, + sector_t, end, compute_subtree_last); /** * drbd_insert_interval - insert a new interval into a tree @@ -79,6 +47,7 @@ bool drbd_insert_interval(struct rb_root *root, struct drbd_interval *this) { struct rb_node **new = &root->rb_node, *parent = NULL; + sector_t this_end = this->sector + (this->size >> 9); BUG_ON(!IS_ALIGNED(this->size, 512)); @@ -87,6 +56,8 @@ drbd_insert_interval(struct rb_root *root, struct drbd_interval *this) rb_entry(*new, struct drbd_interval, rb); parent = *new; + if (here->end < this_end) + here->end = this_end; if (this->sector < here->sector) new = &(*new)->rb_left; else if (this->sector > here->sector) @@ -99,6 +70,7 @@ drbd_insert_interval(struct rb_root *root, struct drbd_interval *this) return false; } + this->end = this_end; rb_link_node(&this->rb, parent, new); rb_insert_augmented(&this->rb, root, &augment_callbacks); return true; diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 9b465bb68487..973c185c9cfe 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -1622,13 +1622,13 @@ int drbd_send_dblock(struct drbd_peer_device *peer_device, struct drbd_request * struct drbd_socket *sock; struct p_data *p; unsigned int dp_flags = 0; - int dgs; + int digest_size; int err; sock = &peer_device->connection->data; p = drbd_prepare_command(peer_device, sock); - dgs = peer_device->connection->integrity_tfm ? - crypto_hash_digestsize(peer_device->connection->integrity_tfm) : 0; + digest_size = peer_device->connection->integrity_tfm ? + crypto_hash_digestsize(peer_device->connection->integrity_tfm) : 0; if (!p) return -EIO; @@ -1659,9 +1659,9 @@ int drbd_send_dblock(struct drbd_peer_device *peer_device, struct drbd_request * /* our digest is still only over the payload. * TRIM does not carry any payload. */ - if (dgs) + if (digest_size) drbd_csum_bio(peer_device->connection->integrity_tfm, req->master_bio, p + 1); - err = __send_command(peer_device->connection, device->vnr, sock, P_DATA, sizeof(*p) + dgs, NULL, req->i.size); + err = __send_command(peer_device->connection, device->vnr, sock, P_DATA, sizeof(*p) + digest_size, NULL, req->i.size); if (!err) { /* For protocol A, we have to memcpy the payload into * socket buffers, as we may complete right away @@ -1674,23 +1674,23 @@ int drbd_send_dblock(struct drbd_peer_device *peer_device, struct drbd_request * * out ok after sending on this side, but does not fit on the * receiving side, we sure have detected corruption elsewhere. */ - if (!(req->rq_state & (RQ_EXP_RECEIVE_ACK | RQ_EXP_WRITE_ACK)) || dgs) + if (!(req->rq_state & (RQ_EXP_RECEIVE_ACK | RQ_EXP_WRITE_ACK)) || digest_size) err = _drbd_send_bio(peer_device, req->master_bio); else err = _drbd_send_zc_bio(peer_device, req->master_bio); /* double check digest, sometimes buffers have been modified in flight. */ - if (dgs > 0 && dgs <= 64) { + if (digest_size > 0 && digest_size <= 64) { /* 64 byte, 512 bit, is the largest digest size * currently supported in kernel crypto. */ unsigned char digest[64]; drbd_csum_bio(peer_device->connection->integrity_tfm, req->master_bio, digest); - if (memcmp(p + 1, digest, dgs)) { + if (memcmp(p + 1, digest, digest_size)) { drbd_warn(device, "Digest mismatch, buffer modified by upper layers during write: %llus +%u\n", (unsigned long long)req->i.sector, req->i.size); } - } /* else if (dgs > 64) { + } /* else if (digest_size > 64) { ... Be noisy about digest too large ... } */ } @@ -1711,13 +1711,13 @@ int drbd_send_block(struct drbd_peer_device *peer_device, enum drbd_packet cmd, struct drbd_socket *sock; struct p_data *p; int err; - int dgs; + int digest_size; sock = &peer_device->connection->data; p = drbd_prepare_command(peer_device, sock); - dgs = peer_device->connection->integrity_tfm ? - crypto_hash_digestsize(peer_device->connection->integrity_tfm) : 0; + digest_size = peer_device->connection->integrity_tfm ? + crypto_hash_digestsize(peer_device->connection->integrity_tfm) : 0; if (!p) return -EIO; @@ -1725,9 +1725,9 @@ int drbd_send_block(struct drbd_peer_device *peer_device, enum drbd_packet cmd, p->block_id = peer_req->block_id; p->seq_num = 0; /* unused */ p->dp_flags = 0; - if (dgs) + if (digest_size) drbd_csum_ee(peer_device->connection->integrity_tfm, peer_req, p + 1); - err = __send_command(peer_device->connection, device->vnr, sock, cmd, sizeof(*p) + dgs, NULL, peer_req->i.size); + err = __send_command(peer_device->connection, device->vnr, sock, cmd, sizeof(*p) + digest_size, NULL, peer_req->i.size); if (!err) err = _drbd_send_zc_ee(peer_device, peer_req); mutex_unlock(&sock->mutex); /* locked by drbd_prepare_command() */ diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c index 06e6147c7601..3b10fa6cb039 100644 --- a/drivers/block/drbd/drbd_proc.c +++ b/drivers/block/drbd/drbd_proc.c @@ -142,10 +142,12 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se (unsigned long) Bit2KB(rs_left >> 10), (unsigned long) Bit2KB(rs_total >> 10)); else - seq_printf(seq, "(%lu/%lu)K\n\t", + seq_printf(seq, "(%lu/%lu)K", (unsigned long) Bit2KB(rs_left), (unsigned long) Bit2KB(rs_total)); + seq_printf(seq, "\n\t"); + /* see drivers/md/md.c * We do not want to overflow, so the order of operands and * the * 100 / 100 trick are important. We do a +1 to be diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 9342b8da73ab..6960fb064731 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -1371,9 +1371,9 @@ int drbd_submit_peer_request(struct drbd_device *device, struct bio *bio; struct page *page = peer_req->pages; sector_t sector = peer_req->i.sector; - unsigned ds = peer_req->i.size; + unsigned data_size = peer_req->i.size; unsigned n_bios = 0; - unsigned nr_pages = (ds + PAGE_SIZE -1) >> PAGE_SHIFT; + unsigned nr_pages = (data_size + PAGE_SIZE -1) >> PAGE_SHIFT; int err = -ENOMEM; if (peer_req->flags & EE_IS_TRIM_USE_ZEROOUT) { @@ -1388,7 +1388,7 @@ int drbd_submit_peer_request(struct drbd_device *device, list_add_tail(&peer_req->w.list, &device->active_ee); spin_unlock_irq(&device->resource->req_lock); if (blkdev_issue_zeroout(device->ldev->backing_bdev, - sector, ds >> 9, GFP_NOIO)) + sector, data_size >> 9, GFP_NOIO)) peer_req->flags |= EE_WAS_ERROR; drbd_endio_write_sec_final(peer_req); return 0; @@ -1426,12 +1426,12 @@ next_bio: ++n_bios; if (rw & REQ_DISCARD) { - bio->bi_iter.bi_size = ds; + bio->bi_iter.bi_size = data_size; goto submit; } page_chain_for_each(page) { - unsigned len = min_t(unsigned, ds, PAGE_SIZE); + unsigned len = min_t(unsigned, data_size, PAGE_SIZE); if (!bio_add_page(bio, page, len, 0)) { /* A single page must always be possible! * But in case it fails anyways, @@ -1446,11 +1446,11 @@ next_bio: } goto next_bio; } - ds -= len; + data_size -= len; sector += len >> 9; --nr_pages; } - D_ASSERT(device, ds == 0); + D_ASSERT(device, data_size == 0); submit: D_ASSERT(device, page == NULL); @@ -1591,24 +1591,24 @@ read_in_block(struct drbd_peer_device *peer_device, u64 id, sector_t sector, const sector_t capacity = drbd_get_capacity(device->this_bdev); struct drbd_peer_request *peer_req; struct page *page; - int dgs, ds, err; - unsigned int data_size = pi->size; + int digest_size, err; + unsigned int data_size = pi->size, ds; void *dig_in = peer_device->connection->int_dig_in; void *dig_vv = peer_device->connection->int_dig_vv; unsigned long *data; struct p_trim *trim = (pi->cmd == P_TRIM) ? pi->data : NULL; - dgs = 0; + digest_size = 0; if (!trim && peer_device->connection->peer_integrity_tfm) { - dgs = crypto_hash_digestsize(peer_device->connection->peer_integrity_tfm); + digest_size = crypto_hash_digestsize(peer_device->connection->peer_integrity_tfm); /* * FIXME: Receive the incoming digest into the receive buffer * here, together with its struct p_data? */ - err = drbd_recv_all_warn(peer_device->connection, dig_in, dgs); + err = drbd_recv_all_warn(peer_device->connection, dig_in, digest_size); if (err) return NULL; - data_size -= dgs; + data_size -= digest_size; } if (trim) { @@ -1661,16 +1661,16 @@ read_in_block(struct drbd_peer_device *peer_device, u64 id, sector_t sector, ds -= len; } - if (dgs) { + if (digest_size) { drbd_csum_ee(peer_device->connection->peer_integrity_tfm, peer_req, dig_vv); - if (memcmp(dig_in, dig_vv, dgs)) { + if (memcmp(dig_in, dig_vv, digest_size)) { drbd_err(device, "Digest integrity check FAILED: %llus +%u\n", (unsigned long long)sector, data_size); drbd_free_peer_req(device, peer_req); return NULL; } } - device->recv_cnt += data_size>>9; + device->recv_cnt += data_size >> 9; return peer_req; } @@ -1708,17 +1708,17 @@ static int recv_dless_read(struct drbd_peer_device *peer_device, struct drbd_req struct bio_vec bvec; struct bvec_iter iter; struct bio *bio; - int dgs, err, expect; + int digest_size, err, expect; void *dig_in = peer_device->connection->int_dig_in; void *dig_vv = peer_device->connection->int_dig_vv; - dgs = 0; + digest_size = 0; if (peer_device->connection->peer_integrity_tfm) { - dgs = crypto_hash_digestsize(peer_device->connection->peer_integrity_tfm); - err = drbd_recv_all_warn(peer_device->connection, dig_in, dgs); + digest_size = crypto_hash_digestsize(peer_device->connection->peer_integrity_tfm); + err = drbd_recv_all_warn(peer_device->connection, dig_in, digest_size); if (err) return err; - data_size -= dgs; + data_size -= digest_size; } /* optimistically update recv_cnt. if receiving fails below, @@ -1738,9 +1738,9 @@ static int recv_dless_read(struct drbd_peer_device *peer_device, struct drbd_req data_size -= expect; } - if (dgs) { + if (digest_size) { drbd_csum_bio(peer_device->connection->peer_integrity_tfm, bio, dig_vv); - if (memcmp(dig_in, dig_vv, dgs)) { + if (memcmp(dig_in, dig_vv, digest_size)) { drbd_err(peer_device, "Digest integrity check FAILED. Broken NICs?\n"); return -EINVAL; } @@ -5561,6 +5561,7 @@ int drbd_asender(struct drbd_thread *thi) * rv < expected: "woken" by signal during receive * rv == 0 : "connection shut down by peer" */ +received_more: if (likely(rv > 0)) { received += rv; buf += rv; @@ -5636,6 +5637,11 @@ int drbd_asender(struct drbd_thread *thi) expect = header_size; cmd = NULL; } + if (test_bit(SEND_PING, &connection->flags)) + continue; + rv = drbd_recv_short(connection->meta.socket, buf, expect-received, MSG_DONTWAIT); + if (rv > 0) + goto received_more; } if (0) { diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index c67717d572d1..5a01c53dddeb 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -1645,6 +1645,6 @@ void request_timer_fn(unsigned long data) ? oldest_submit_jif + dt : now + et; nt = time_before(ent, dt) ? ent : dt; out: - spin_unlock_irq(&connection->resource->req_lock); + spin_unlock_irq(&device->resource->req_lock); mod_timer(&device->request_timer, nt); } diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c index c35c0f001bb7..84b11f887d73 100644 --- a/drivers/block/drbd/drbd_state.c +++ b/drivers/block/drbd/drbd_state.c @@ -136,50 +136,50 @@ enum drbd_role conn_highest_peer(struct drbd_connection *connection) enum drbd_disk_state conn_highest_disk(struct drbd_connection *connection) { - enum drbd_disk_state ds = D_DISKLESS; + enum drbd_disk_state disk_state = D_DISKLESS; struct drbd_peer_device *peer_device; int vnr; rcu_read_lock(); idr_for_each_entry(&connection->peer_devices, peer_device, vnr) { struct drbd_device *device = peer_device->device; - ds = max_t(enum drbd_disk_state, ds, device->state.disk); + disk_state = max_t(enum drbd_disk_state, disk_state, device->state.disk); } rcu_read_unlock(); - return ds; + return disk_state; } enum drbd_disk_state conn_lowest_disk(struct drbd_connection *connection) { - enum drbd_disk_state ds = D_MASK; + enum drbd_disk_state disk_state = D_MASK; struct drbd_peer_device *peer_device; int vnr; rcu_read_lock(); idr_for_each_entry(&connection->peer_devices, peer_device, vnr) { struct drbd_device *device = peer_device->device; - ds = min_t(enum drbd_disk_state, ds, device->state.disk); + disk_state = min_t(enum drbd_disk_state, disk_state, device->state.disk); } rcu_read_unlock(); - return ds; + return disk_state; } enum drbd_disk_state conn_highest_pdsk(struct drbd_connection *connection) { - enum drbd_disk_state ds = D_DISKLESS; + enum drbd_disk_state disk_state = D_DISKLESS; struct drbd_peer_device *peer_device; int vnr; rcu_read_lock(); idr_for_each_entry(&connection->peer_devices, peer_device, vnr) { struct drbd_device *device = peer_device->device; - ds = max_t(enum drbd_disk_state, ds, device->state.pdsk); + disk_state = max_t(enum drbd_disk_state, disk_state, device->state.pdsk); } rcu_read_unlock(); - return ds; + return disk_state; } enum drbd_conns conn_lowest_conn(struct drbd_connection *connection) diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 50776b362828..d2d1f97511bd 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -43,10 +43,10 @@ static int make_ov_request(struct drbd_device *, int); static int make_resync_request(struct drbd_device *, int); /* endio handlers: - * drbd_md_io_complete (defined here) + * drbd_md_endio (defined here) * drbd_request_endio (defined here) * drbd_peer_request_endio (defined here) - * bm_async_io_complete (defined in drbd_bitmap.c) + * drbd_bm_endio (defined in drbd_bitmap.c) * * For all these callbacks, note the following: * The callbacks will be called in irq context by the IDE drivers, @@ -65,7 +65,7 @@ rwlock_t global_state_lock; /* used for synchronous meta data and bitmap IO * submitted by drbd_md_sync_page_io() */ -void drbd_md_io_complete(struct bio *bio, int error) +void drbd_md_endio(struct bio *bio, int error) { struct drbd_device *device; @@ -1853,9 +1853,12 @@ static void drbd_ldev_destroy(struct drbd_device *device) device->resync = NULL; lc_destroy(device->act_log); device->act_log = NULL; - __no_warn(local, - drbd_free_ldev(device->ldev); - device->ldev = NULL;); + + __acquire(local); + drbd_free_ldev(device->ldev); + device->ldev = NULL; + __release(local); + clear_bit(GOING_DISKLESS, &device->flags); wake_up(&device->misc_wait); } @@ -1928,19 +1931,18 @@ void __update_timing_details( ++(*cb_nr); } -#define WORK_PENDING(work_bit, todo) (todo & (1UL << work_bit)) static void do_device_work(struct drbd_device *device, const unsigned long todo) { - if (WORK_PENDING(MD_SYNC, todo)) + if (test_bit(MD_SYNC, &todo)) do_md_sync(device); - if (WORK_PENDING(RS_DONE, todo) || - WORK_PENDING(RS_PROGRESS, todo)) - update_on_disk_bitmap(device, WORK_PENDING(RS_DONE, todo)); - if (WORK_PENDING(GO_DISKLESS, todo)) + if (test_bit(RS_DONE, &todo) || + test_bit(RS_PROGRESS, &todo)) + update_on_disk_bitmap(device, test_bit(RS_DONE, &todo)); + if (test_bit(GO_DISKLESS, &todo)) go_diskless(device); - if (WORK_PENDING(DESTROY_DISK, todo)) + if (test_bit(DESTROY_DISK, &todo)) drbd_ldev_destroy(device); - if (WORK_PENDING(RS_START, todo)) + if (test_bit(RS_START, &todo)) do_start_resync(device); } @@ -1992,22 +1994,13 @@ static bool dequeue_work_batch(struct drbd_work_queue *queue, struct list_head * return !list_empty(work_list); } -static bool dequeue_work_item(struct drbd_work_queue *queue, struct list_head *work_list) -{ - spin_lock_irq(&queue->q_lock); - if (!list_empty(&queue->q)) - list_move(queue->q.next, work_list); - spin_unlock_irq(&queue->q_lock); - return !list_empty(work_list); -} - static void wait_for_work(struct drbd_connection *connection, struct list_head *work_list) { DEFINE_WAIT(wait); struct net_conf *nc; int uncork, cork; - dequeue_work_item(&connection->sender_work, work_list); + dequeue_work_batch(&connection->sender_work, work_list); if (!list_empty(work_list)) return; @@ -2033,8 +2026,6 @@ static void wait_for_work(struct drbd_connection *connection, struct list_head * prepare_to_wait(&connection->sender_work.q_wait, &wait, TASK_INTERRUPTIBLE); spin_lock_irq(&connection->resource->req_lock); spin_lock(&connection->sender_work.q_lock); /* FIXME get rid of this one? */ - /* dequeue single item only, - * we still use drbd_queue_work_front() in some places */ if (!list_empty(&connection->sender_work.q)) list_splice_tail_init(&connection->sender_work.q, work_list); spin_unlock(&connection->sender_work.q_lock); /* FIXME get rid of this one? */ @@ -2121,7 +2112,7 @@ int drbd_worker(struct drbd_thread *thi) if (get_t_state(thi) != RUNNING) break; - while (!list_empty(&work_list)) { + if (!list_empty(&work_list)) { w = list_first_entry(&work_list, struct drbd_work, list); list_del_init(&w->list); update_worker_timing_details(connection, w->cb); @@ -2137,13 +2128,13 @@ int drbd_worker(struct drbd_thread *thi) update_worker_timing_details(connection, do_unqueued_work); do_unqueued_work(connection); } - while (!list_empty(&work_list)) { + if (!list_empty(&work_list)) { w = list_first_entry(&work_list, struct drbd_work, list); list_del_init(&w->list); update_worker_timing_details(connection, w->cb); w->cb(w, 1); - } - dequeue_work_batch(&connection->sender_work, &work_list); + } else + dequeue_work_batch(&connection->sender_work, &work_list); } while (!list_empty(&work_list) || test_bit(DEVICE_WORK_PENDING, &connection->flags)); rcu_read_lock(); diff --git a/drivers/block/hd.c b/drivers/block/hd.c index 8a290c08262f..3abb121825bc 100644 --- a/drivers/block/hd.c +++ b/drivers/block/hd.c @@ -694,16 +694,6 @@ static const struct block_device_operations hd_fops = { .getgeo = hd_getgeo, }; -/* - * This is the hard disk IRQ description. The IRQF_DISABLED in sa_flags - * means we run the IRQ-handler with interrupts disabled: this is bad for - * interrupt latency, but anything else has led to problems on some - * machines. - * - * We enable interrupts in some of the routines after making sure it's - * safe. - */ - static int __init hd_init(void) { int drive; @@ -761,7 +751,7 @@ static int __init hd_init(void) p->cyl, p->head, p->sect); } - if (request_irq(HD_IRQ, hd_interrupt, IRQF_DISABLED, "hd", NULL)) { + if (request_irq(HD_IRQ, hd_interrupt, 0, "hd", NULL)) { printk("hd: unable to get IRQ%d for the hard disk driver\n", HD_IRQ); goto out1; diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 6b7e8d0fba99..1bd5f523f8fd 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -3954,6 +3954,7 @@ skip_create_disk: /* Set device limits. */ set_bit(QUEUE_FLAG_NONROT, &dd->queue->queue_flags); + clear_bit(QUEUE_FLAG_ADD_RANDOM, &dd->queue->queue_flags); blk_queue_max_segments(dd->queue, MTIP_MAX_SG); blk_queue_physical_block_size(dd->queue, 4096); blk_queue_max_hw_sectors(dd->queue, 0xffff); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index fb31b8ee4372..4bc2a5cb9935 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -847,6 +847,7 @@ static int __init nbd_init(void) * Tell the block layer that we are not a rotational device */ queue_flag_set_unlocked(QUEUE_FLAG_NONROT, disk->queue); + queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, disk->queue); disk->queue->limits.discard_granularity = 512; disk->queue->limits.max_discard_sectors = UINT_MAX; disk->queue->limits.discard_zeroes_data = 0; diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index ac50a2931044..2671a3f02f0c 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -521,6 +521,7 @@ static int null_add_dev(void) nullb->q->queuedata = nullb; queue_flag_set_unlocked(QUEUE_FLAG_NONROT, nullb->q); + queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, nullb->q); disk = nullb->disk = alloc_disk_node(1, home_node); if (!disk) { diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c index 02351e217165..e2bb8afbeae5 100644 --- a/drivers/block/nvme-core.c +++ b/drivers/block/nvme-core.c @@ -1916,6 +1916,7 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid, ns->queue->queue_flags = QUEUE_FLAG_DEFAULT; queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, ns->queue); queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue); + queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, ns->queue); blk_queue_make_request(ns->queue, nvme_make_request); ns->dev = dev; ns->queue->queuedata = ns; diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c index 3265ce94d282..d8b2488aaade 100644 --- a/drivers/block/rsxx/core.c +++ b/drivers/block/rsxx/core.c @@ -837,7 +837,7 @@ static int rsxx_pci_probe(struct pci_dev *dev, "Failed to enable MSI\n"); } - st = request_irq(dev->irq, rsxx_isr, IRQF_DISABLED | IRQF_SHARED, + st = request_irq(dev->irq, rsxx_isr, IRQF_SHARED, DRIVER_NAME, card); if (st) { dev_err(CARD_TO_DEV(card), diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c index 2839d37e5af7..40ee7705df63 100644 --- a/drivers/block/rsxx/dev.c +++ b/drivers/block/rsxx/dev.c @@ -307,6 +307,7 @@ int rsxx_setup_dev(struct rsxx_cardinfo *card) blk_queue_physical_block_size(card->queue, RSXX_HW_BLK_SIZE); queue_flag_set_unlocked(QUEUE_FLAG_NONROT, card->queue); + queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, card->queue); if (rsxx_discard_supported(card)) { queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, card->queue); blk_queue_max_discard_sectors(card->queue, diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c index 8fcdcfb4b472..1e46eb2305c0 100644 --- a/drivers/block/skd_main.c +++ b/drivers/block/skd_main.c @@ -4426,6 +4426,7 @@ static int skd_cons_disk(struct skd_device *skdev) q->limits.discard_zeroes_data = 1; queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q); queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q); + queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, q); spin_lock_irqsave(&skdev->lock, flags); pr_debug("%s:%s:%d stopping %s queue\n", diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 64c60edcdfbc..63fc7f06a014 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -763,6 +763,7 @@ again: BUG_ON(new_map_idx >= segs_to_map); if (unlikely(map[new_map_idx].status != 0)) { pr_debug(DRV_PFX "invalid buffer -- could not remap it\n"); + put_free_pages(blkif, &pages[seg_idx]->page, 1); pages[seg_idx]->handle = BLKBACK_INVALID_HANDLE; ret |= 1; goto next; diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index 0b13b1c9a01e..630a489e757d 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -270,6 +270,9 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif) blkif->blk_rings.common.sring = NULL; } + /* Remove all persistent grants and the cache of ballooned pages. */ + xen_blkbk_free_caches(blkif); + return 0; } @@ -281,9 +284,6 @@ static void xen_blkif_free(struct xen_blkif *blkif) xen_blkif_disconnect(blkif); xen_vbd_free(&blkif->vbd); - /* Remove all persistent grants and the cache of ballooned pages. */ - xen_blkbk_free_caches(blkif); - /* Make sure everything is drained before shutting down */ BUG_ON(blkif->persistent_gnt_c != 0); BUG_ON(atomic_read(&blkif->persistent_gnt_in_use) != 0); diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 37af03e9d859..5ac312f6e0be 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -582,6 +582,14 @@ static inline void flush_requests(struct blkfront_info *info) notify_remote_via_irq(info->irq); } +static inline bool blkif_request_flush_valid(struct request *req, + struct blkfront_info *info) +{ + return ((req->cmd_type != REQ_TYPE_FS) || + ((req->cmd_flags & (REQ_FLUSH | REQ_FUA)) && + !info->flush_op)); +} + /* * do_blkif_request * read a block; request is in a request queue @@ -604,9 +612,7 @@ static void do_blkif_request(struct request_queue *rq) blk_start_request(req); - if ((req->cmd_type != REQ_TYPE_FS) || - ((req->cmd_flags & (REQ_FLUSH | REQ_FUA)) && - !info->flush_op)) { + if (blkif_request_flush_valid(req, info)) { __blk_end_request_all(req, -EIO); continue; } diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 3b850164c65c..0e63e8aa8279 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1031,6 +1031,7 @@ static int create_device(struct zram *zram, int device_id) set_capacity(zram->disk, 0); /* zram devices sort of resembles non-rotational disks */ queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zram->disk->queue); + queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, zram->disk->queue); /* * To ensure that we always get PAGE_SIZE aligned * and n*PAGE_SIZED sized I/O requests. diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c index ee880382e3bc..56b9708894a5 100644 --- a/drivers/ide/ide-disk.c +++ b/drivers/ide/ide-disk.c @@ -685,8 +685,10 @@ static void ide_disk_setup(ide_drive_t *drive) printk(KERN_INFO "%s: max request size: %dKiB\n", drive->name, queue_max_sectors(q) / 2); - if (ata_id_is_ssd(id)) + if (ata_id_is_ssd(id)) { queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q); + queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, q); + } /* calculate drive capacity, and select LBA if possible */ ide_disk_get_capacity(drive); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index d4713d098a39..4dd2bb7167f0 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -842,6 +842,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size, q->limits.logical_block_size = block_size; q->limits.physical_block_size = block_size; set_bit(QUEUE_FLAG_NONROT, &d->disk->queue->queue_flags); + clear_bit(QUEUE_FLAG_ADD_RANDOM, &d->disk->queue->queue_flags); set_bit(QUEUE_FLAG_DISCARD, &d->disk->queue->queue_flags); blk_queue_flush(q, REQ_FLUSH|REQ_FUA); diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index feea926e32f8..cfa6110632c3 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -210,6 +210,7 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, blk_queue_prep_rq(mq->queue, mmc_prep_request); queue_flag_set_unlocked(QUEUE_FLAG_NONROT, mq->queue); + queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, mq->queue); if (mmc_can_erase(card)) mmc_queue_setup_discard(mq->queue, card); diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 43e30992a369..d08229eb44d8 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -417,6 +417,7 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) blk_queue_logical_block_size(new->rq, tr->blksize); queue_flag_set_unlocked(QUEUE_FLAG_NONROT, new->rq); + queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, new->rq); if (tr->discard) { queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, new->rq); diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c index 76bed1743db1..56046ab39629 100644 --- a/drivers/s390/block/scm_blk.c +++ b/drivers/s390/block/scm_blk.c @@ -386,6 +386,7 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev) blk_queue_max_hw_sectors(rq, nr_max_blk << 3); /* 8 * 512 = blk_size */ blk_queue_max_segments(rq, nr_max_blk); queue_flag_set_unlocked(QUEUE_FLAG_NONROT, rq); + queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, rq); scm_blk_dev_cluster_setup(bdev); bdev->gendisk = alloc_disk(SCM_NR_PARTS); diff --git a/drivers/s390/block/xpram.c b/drivers/s390/block/xpram.c index 6969d39f1e2e..9e0de9c9a6fc 100644 --- a/drivers/s390/block/xpram.c +++ b/drivers/s390/block/xpram.c @@ -346,6 +346,7 @@ static int __init xpram_setup_blkdev(void) goto out; } queue_flag_set_unlocked(QUEUE_FLAG_NONROT, xpram_queues[i]); + queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, xpram_queues[i]); blk_queue_make_request(xpram_queues[i], xpram_make_request); blk_queue_logical_block_size(xpram_queues[i], 4096); } diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 7ee86028a535..cfba74cd8e8b 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2677,8 +2677,10 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp) rot = get_unaligned_be16(&buffer[4]); - if (rot == 1) + if (rot == 1) { queue_flag_set_unlocked(QUEUE_FLAG_NONROT, sdkp->disk->queue); + queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, sdkp->disk->queue); + } out: kfree(buffer); |