Merge tag 'for-4.21/block-20190102' of git://git.kernel.dk/linux-block

Pull more block updates from Jens Axboe:

 - Dead code removal for loop/sunvdc (Chengguang)

 - Mark BIDI support for bsg as deprecated, logging a single dmesg
   warning if anyone is actually using it (Christoph)

 - blkcg cleanup, killing a dead function and making the tryget_closest
   variant easier to read (Dennis)

 - Floppy fixes, one fixing a regression in swim3 (Finn)

 - lightnvm use-after-free fix (Gustavo)

 - gdrom leak fix (Wenwen)

 - a set of drbd updates (Lars, Luc, Nathan, Roland)

* tag 'for-4.21/block-20190102' of git://git.kernel.dk/linux-block: (28 commits)
  block/swim3: Fix regression on PowerBook G3
  block/swim3: Fix -EBUSY error when re-opening device after unmount
  block/swim3: Remove dead return statement
  block/amiflop: Don't log error message on invalid ioctl
  gdrom: fix a memory leak bug
  lightnvm: pblk: fix use-after-free bug
  block: sunvdc: remove redundant code
  block: loop: remove redundant code
  bsg: deprecate BIDI support in bsg
  blkcg: remove unused __blkg_release_rcu()
  blkcg: clean up blkg_tryget_closest()
  drbd: Change drbd_request_detach_interruptible's return type to int
  drbd: Avoid Clang warning about pointless switch statment
  drbd: introduce P_ZEROES (REQ_OP_WRITE_ZEROES on the "wire")
  drbd: skip spurious timeout (ping-timeo) when failing promote
  drbd: don't retry connection if peers do not agree on "authentication" settings
  drbd: fix print_st_err()'s prototype to match the definition
  drbd: avoid spurious self-outdating with concurrent disconnect / down
  drbd: do not block when adjusting "disk-options" while IO is frozen
  drbd: fix comment typos
  ...

1 files changed, 107 insertions, 26 deletions

diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index d15703b1ffe8..f2471172a961 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -127,6 +127,35 @@ static int drbd_msg_put_info(struct sk_buff *skb, const char *info)
 	return 0;
 }
 
+__printf(2, 3)
+static int drbd_msg_sprintf_info(struct sk_buff *skb, const char *fmt, ...)
+{
+	va_list args;
+	struct nlattr *nla, *txt;
+	int err = -EMSGSIZE;
+	int len;
+
+	nla = nla_nest_start(skb, DRBD_NLA_CFG_REPLY);
+	if (!nla)
+		return err;
+
+	txt = nla_reserve(skb, T_info_text, 256);
+	if (!txt) {
+		nla_nest_cancel(skb, nla);
+		return err;
+	}
+	va_start(args, fmt);
+	len = vscnprintf(nla_data(txt), 256, fmt, args);
+	va_end(args);
+
+	/* maybe: retry with larger reserve, if truncated */
+	txt->nla_len = nla_attr_size(len+1);
+	nlmsg_trim(skb, (char*)txt + NLA_ALIGN(txt->nla_len));
+	nla_nest_end(skb, nla);
+
+	return 0;
+}
+
 /* This would be a good candidate for a "pre_doit" hook,
  * and per-family private info->pointers.
  * But we need to stay compatible with older kernels.
@@ -668,14 +697,15 @@ drbd_set_role(struct drbd_device *const device, enum drbd_role new_role, int for
 		if (rv == SS_TWO_PRIMARIES) {
 			/* Maybe the peer is detected as dead very soon...
 			   retry at most once more in this case. */
-			int timeo;
-			rcu_read_lock();
-			nc = rcu_dereference(connection->net_conf);
-			timeo = nc ? (nc->ping_timeo + 1) * HZ / 10 : 1;
-			rcu_read_unlock();
-			schedule_timeout_interruptible(timeo);
-			if (try < max_tries)
+			if (try < max_tries) {
+				int timeo;
 				try = max_tries - 1;
+				rcu_read_lock();
+				nc = rcu_dereference(connection->net_conf);
+				timeo = nc ? (nc->ping_timeo + 1) * HZ / 10 : 1;
+				rcu_read_unlock();
+				schedule_timeout_interruptible(timeo);
+			}
 			continue;
 		}
 		if (rv < SS_SUCCESS) {
@@ -921,7 +951,6 @@ drbd_determine_dev_size(struct drbd_device *device, enum dds_flags flags, struct
 	} prev;
 	sector_t u_size, size;
 	struct drbd_md *md = &device->ldev->md;
-	char ppb[10];
 	void *buffer;
 
 	int md_moved, la_size_changed;
@@ -999,8 +1028,6 @@ drbd_determine_dev_size(struct drbd_device *device, enum dds_flags flags, struct
 		/* racy, see comments above. */
 		drbd_set_my_capacity(device, size);
 		md->la_size_sect = size;
-		drbd_info(device, "size = %s (%llu KB)\n", ppsize(ppb, size>>1),
-		     (unsigned long long)size>>1);
 	}
 	if (rv <= DS_ERROR)
 		goto err_out;
@@ -1234,6 +1261,21 @@ static void fixup_discard_if_not_supported(struct request_queue *q)
 	}
 }
 
+static void fixup_write_zeroes(struct drbd_device *device, struct request_queue *q)
+{
+	/* Fixup max_write_zeroes_sectors after blk_queue_stack_limits():
+	 * if we can handle "zeroes" efficiently on the protocol,
+	 * we want to do that, even if our backend does not announce
+	 * max_write_zeroes_sectors itself. */
+	struct drbd_connection *connection = first_peer_device(device)->connection;
+	/* If the peer announces WZEROES support, use it.  Otherwise, rather
+	 * send explicit zeroes than rely on some discard-zeroes-data magic. */
+	if (connection->agreed_features & DRBD_FF_WZEROES)
+		q->limits.max_write_zeroes_sectors = DRBD_MAX_BBIO_SECTORS;
+	else
+		q->limits.max_write_zeroes_sectors = 0;
+}
+
 static void decide_on_write_same_support(struct drbd_device *device,
 			struct request_queue *q,
 			struct request_queue *b, struct o_qlim *o,
@@ -1344,6 +1386,7 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi
 		}
 	}
 	fixup_discard_if_not_supported(q);
+	fixup_write_zeroes(device, q);
 }
 
 void drbd_reconsider_queue_parameters(struct drbd_device *device, struct drbd_backing_dev *bdev, struct o_qlim *o)
@@ -1514,6 +1557,30 @@ static void sanitize_disk_conf(struct drbd_device *device, struct disk_conf *dis
 	}
 }
 
+static int disk_opts_check_al_size(struct drbd_device *device, struct disk_conf *dc)
+{
+	int err = -EBUSY;
+
+	if (device->act_log &&
+	    device->act_log->nr_elements == dc->al_extents)
+		return 0;
+
+	drbd_suspend_io(device);
+	/* If IO completion is currently blocked, we would likely wait
+	 * "forever" for the activity log to become unused. So we don't. */
+	if (atomic_read(&device->ap_bio_cnt))
+		goto out;
+
+	wait_event(device->al_wait, lc_try_lock(device->act_log));
+	drbd_al_shrink(device);
+	err = drbd_check_al_size(device, dc);
+	lc_unlock(device->act_log);
+	wake_up(&device->al_wait);
+out:
+	drbd_resume_io(device);
+	return err;
+}
+
 int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
 {
 	struct drbd_config_context adm_ctx;
@@ -1576,15 +1643,12 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	drbd_suspend_io(device);
-	wait_event(device->al_wait, lc_try_lock(device->act_log));
-	drbd_al_shrink(device);
-	err = drbd_check_al_size(device, new_disk_conf);
-	lc_unlock(device->act_log);
-	wake_up(&device->al_wait);
-	drbd_resume_io(device);
-
+	err = disk_opts_check_al_size(device, new_disk_conf);
 	if (err) {
+		/* Could be just "busy". Ignore?
+		 * Introduce dedicated error code? */
+		drbd_msg_put_info(adm_ctx.reply_skb,
+			"Try again without changing current al-extents setting");
 		retcode = ERR_NOMEM;
 		goto fail_unlock;
 	}
@@ -1934,9 +1998,9 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	if (device->state.conn < C_CONNECTED &&
-	    device->state.role == R_PRIMARY && device->ed_uuid &&
-	    (device->ed_uuid & ~((u64)1)) != (nbc->md.uuid[UI_CURRENT] & ~((u64)1))) {
+	if (device->state.pdsk != D_UP_TO_DATE && device->ed_uuid &&
+	    (device->state.role == R_PRIMARY || device->state.peer == R_PRIMARY) &&
+            (device->ed_uuid & ~((u64)1)) != (nbc->md.uuid[UI_CURRENT] & ~((u64)1))) {
 		drbd_err(device, "Can only attach to data with current UUID=%016llX\n",
 		    (unsigned long long)device->ed_uuid);
 		retcode = ERR_DATA_NOT_CURRENT;
@@ -1950,11 +2014,21 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	/* Prevent shrinking of consistent devices ! */
-	if (drbd_md_test_flag(nbc, MDF_CONSISTENT) &&
-	    drbd_new_dev_size(device, nbc, nbc->disk_conf->disk_size, 0) < nbc->md.la_size_sect) {
-		drbd_warn(device, "refusing to truncate a consistent device\n");
-		retcode = ERR_DISK_TOO_SMALL;
-		goto force_diskless_dec;
+	{
+	unsigned long long nsz = drbd_new_dev_size(device, nbc, nbc->disk_conf->disk_size, 0);
+	unsigned long long eff = nbc->md.la_size_sect;
+	if (drbd_md_test_flag(nbc, MDF_CONSISTENT) && nsz < eff) {
+		if (nsz == nbc->disk_conf->disk_size) {
+			drbd_warn(device, "truncating a consistent device during attach (%llu < %llu)\n", nsz, eff);
+		} else {
+			drbd_warn(device, "refusing to truncate a consistent device (%llu < %llu)\n", nsz, eff);
+			drbd_msg_sprintf_info(adm_ctx.reply_skb,
+				"To-be-attached device has last effective > current size, and is consistent\n"
+				"(%llu > %llu sectors). Refusing to attach.", eff, nsz);
+			retcode = ERR_IMPLICIT_SHRINK;
+			goto force_diskless_dec;
+		}
+	}
 	}
 
 	lock_all_resources();
@@ -2654,8 +2728,10 @@ out:
 
 static enum drbd_state_rv conn_try_disconnect(struct drbd_connection *connection, bool force)
 {
+	enum drbd_conns cstate;
 	enum drbd_state_rv rv;
 
+repeat:
 	rv = conn_request_state(connection, NS(conn, C_DISCONNECTING),
 			force ? CS_HARD : 0);
 
@@ -2673,6 +2749,11 @@ static enum drbd_state_rv conn_try_disconnect(struct drbd_connection *connection
 
 		break;
 	case SS_CW_FAILED_BY_PEER:
+		spin_lock_irq(&connection->resource->req_lock);
+		cstate = connection->cstate;
+		spin_unlock_irq(&connection->resource->req_lock);
+		if (cstate <= C_WF_CONNECTION)
+			goto repeat;
 		/* The peer probably wants to see us outdated. */
 		rv = conn_request_state(connection, NS2(conn, C_DISCONNECTING,
 							disk, D_OUTDATED), 0);