DRBD updates for 4.21

index 61c392752fe4..1b9822f264d2 100644
@@ -3364,7 +3364,7 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_peer_device *peer_device,
 	enum drbd_conns rv = C_MASK;
 	enum drbd_disk_state mydisk;
 	struct net_conf *nc;
-	int hg, rule_nr, rr_conflict, tentative;
+	int hg, rule_nr, rr_conflict, tentative, always_asbp;
 
 	mydisk = device->state.disk;
 	if (mydisk == D_NEGOTIATING)

@@ -3415,8 +3415,12 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_peer_device *peer_device,
 
 	rcu_read_lock();
 	nc = rcu_dereference(peer_device->connection->net_conf);
+	always_asbp = nc->always_asbp;
+	rr_conflict = nc->rr_conflict;
+	tentative = nc->tentative;
+	rcu_read_unlock();
 
-	if (hg == 100 || (hg == -100 && nc->always_asbp)) {
+	if (hg == 100 || (hg == -100 && always_asbp)) {
 		int pcount = (device->state.role == R_PRIMARY)
 			   + (peer_role == R_PRIMARY);
 		int forced = (hg == -100);

@@ -3455,9 +3459,6 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_peer_device *peer_device,
 			     "Sync from %s node\n",
 			     (hg < 0) ? "peer" : "this");
 	}
-	rr_conflict = nc->rr_conflict;
-	tentative = nc->tentative;
-	rcu_read_unlock();
 
 	if (hg == -100) {
 		/* FIXME this log message is not correct if we end up here

index 0813c654c893..18d53fe60d1d 100644
@@ -2109,9 +2109,8 @@ static int w_after_conn_state_ch(struct drbd_work *w, int unused)
 			spin_unlock_irq(&connection->resource->req_lock);
 		}
 	}
-	kref_put(&connection->kref, drbd_destroy_connection);
-
 	conn_md_sync(connection);
+	kref_put(&connection->kref, drbd_destroy_connection);
 
 	return 0;
 }

index 1e47db57b9d2..ab718582a092 100644
@@ -1609,13 +1609,7 @@ static inline void drbd_tcp_quickack(struct socket *sock)
 }
 
 /* sets the number of 512 byte sectors of our virtual device */
-static inline void drbd_set_my_capacity(struct drbd_device *device,
-					sector_t size)
-{
-	/* set_capacity(device->this_bdev->bd_disk, size); */
-	set_capacity(device->vdisk, size);
-	device->this_bdev->bd_inode->i_size = (loff_t)size << 9;
-}
+void drbd_set_my_capacity(struct drbd_device *device, sector_t size);
 
 /*
  * used to submit our private bio

index f973a2a845c8..f9b4228cc2d9 100644
@@ -2034,6 +2034,21 @@ void drbd_init_set_defaults(struct drbd_device *device)
 	device->local_max_bio_size = DRBD_MAX_BIO_SIZE_SAFE;
 }
 
+static void _drbd_set_my_capacity(struct drbd_device *device, sector_t size)
+{
+	/* set_capacity(device->this_bdev->bd_disk, size); */
+	set_capacity(device->vdisk, size);
+	device->this_bdev->bd_inode->i_size = (loff_t)size << 9;
+}
+
+void drbd_set_my_capacity(struct drbd_device *device, sector_t size)
+{
+	char ppb[10];
+	_drbd_set_my_capacity(device, size);
+	drbd_info(device, "size = %s (%llu KB)\n",
+		ppsize(ppb, size>>1), (unsigned long long)size>>1);
+}
+
 void drbd_device_cleanup(struct drbd_device *device)
 {
 	int i;

@@ -2059,7 +2074,7 @@ void drbd_device_cleanup(struct drbd_device *device)
 	}
 	D_ASSERT(device, first_peer_device(device)->connection->net_conf == NULL);
 
-	drbd_set_my_capacity(device, 0);
+	_drbd_set_my_capacity(device, 0);
 	if (device->bitmap) {
 		/* maybe never allocated. */
 		drbd_bm_resize(device, 0, 1);

index d15703b1ffe8..d02d38fd1288 100644
@@ -921,7 +921,6 @@ 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 +998,6 @@ 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;

index 1b9822f264d2..fbf30fe45862 100644
@@ -3981,6 +3981,7 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info
 	struct o_qlim *o = (connection->agreed_features & DRBD_FF_WSAME) ? p->qlim : NULL;
 	enum determine_dev_size dd = DS_UNCHANGED;
 	sector_t p_size, p_usize, p_csize, my_usize;
+	sector_t new_size, cur_size;
 	int ldsc = 0; /* local disk size changed */
 	enum dds_flags ddsf;
 

@@ -3988,6 +3989,7 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info
 	if (!peer_device)
 		return config_unknown_volume(connection, pi);
 	device = peer_device->device;
+	cur_size = drbd_get_capacity(device->this_bdev);
 
 	p_size = be64_to_cpu(p->d_size);
 	p_usize = be64_to_cpu(p->u_size);

@@ -3998,7 +4000,6 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info
 	device->p_size = p_size;
 
 	if (get_ldev(device)) {
-		sector_t new_size, cur_size;
 		rcu_read_lock();
 		my_usize = rcu_dereference(device->ldev->disk_conf)->disk_size;
 		rcu_read_unlock();

@@ -4016,7 +4017,6 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info
 		/* Never shrink a device with usable data during connect.
 		   But allow online shrinking if we are connected. */
 		new_size = drbd_new_dev_size(device, device->ldev, p_usize, 0);
-		cur_size = drbd_get_capacity(device->this_bdev);
 		if (new_size < cur_size &&
 		    device->state.disk >= D_OUTDATED &&
 		    device->state.conn < C_CONNECTED) {

@@ -4081,9 +4081,36 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info
 		 *
 		 * However, if he sends a zero current size,
 		 * take his (user-capped or) backing disk size anyways.
+		 *
+		 * Unless of course he does not have a disk himself.
+		 * In which case we ignore this completely.
 		 */
+		sector_t new_size = p_csize ?: p_usize ?: p_size;
 		drbd_reconsider_queue_parameters(device, NULL, o);
-		drbd_set_my_capacity(device, p_csize ?: p_usize ?: p_size);
+		if (new_size == 0) {
+			/* Ignore, peer does not know nothing. */
+		} else if (new_size == cur_size) {
+			/* nothing to do */
+		} else if (cur_size != 0 && p_size == 0) {
+			drbd_warn(device, "Ignored diskless peer device size (peer:%llu != me:%llu sectors)!\n",
+					(unsigned long long)new_size, (unsigned long long)cur_size);
+		} else if (new_size < cur_size && device->state.role == R_PRIMARY) {
+			drbd_err(device, "The peer's device size is too small! (%llu < %llu sectors); demote me first!\n",
+					(unsigned long long)new_size, (unsigned long long)cur_size);
+			conn_request_state(peer_device->connection, NS(conn, C_DISCONNECTING), CS_HARD);
+			return -EIO;
+		} else {
+			/* I believe the peer, if
+			 *  - I don't have a current size myself
+			 *  - we agree on the size anyways
+			 *  - I do have a current size, am Secondary,
+			 *    and he has the only disk
+			 *  - I do have a current size, am Primary,
+			 *    and he has the only disk,
+			 *    which is larger than my current size
+			 */
+			drbd_set_my_capacity(device, new_size);
+		}
 	}
 
 	if (get_ldev(device)) {

index fbf30fe45862..0a9f3c65f70a 100644
@@ -4170,7 +4170,7 @@ static int receive_uuids(struct drbd_connection *connection, struct packet_info
 	kfree(device->p_uuid);
 	device->p_uuid = p_uuid;
 
-	if (device->state.conn < C_CONNECTED &&
+	if ((device->state.conn < C_CONNECTED || device->state.pdsk == D_DISKLESS) &&
 	    device->state.disk < D_INCONSISTENT &&
 	    device->state.role == R_PRIMARY &&
 	    (device->ed_uuid & ~((u64)1)) != (p_uuid[UI_CURRENT] & ~((u64)1))) {

index d02d38fd1288..e4774f720de5 100644
@@ -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.

@@ -1947,11 +1976,21 @@ 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();

index 0a9f3c65f70a..85e3d846a23a 100644
@@ -4014,12 +4014,13 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info
 		if (device->state.conn == C_WF_REPORT_PARAMS)
 			p_usize = min_not_zero(my_usize, p_usize);
 
-		/* Never shrink a device with usable data during connect.
-		   But allow online shrinking if we are connected. */
+		/* Never shrink a device with usable data during connect,
+		 * or "attach" on the peer.
+		 * But allow online shrinking if we are connected. */
 		new_size = drbd_new_dev_size(device, device->ldev, p_usize, 0);
 		if (new_size < cur_size &&
 		    device->state.disk >= D_OUTDATED &&
-		    device->state.conn < C_CONNECTED) {
+		    (device->state.conn < C_CONNECTED || device->state.pdsk == D_DISKLESS)) {
 			drbd_err(device, "The peer's disk size is too small! (%llu < %llu sectors)\n",
 					(unsigned long long)new_size, (unsigned long long)cur_size);
 			conn_request_state(peer_device->connection, NS(conn, C_DISCONNECTING), CS_HARD);

@@ -4047,8 +4048,8 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info
 			synchronize_rcu();
 			kfree(old_disk_conf);
 
-			drbd_info(device, "Peer sets u_size to %lu sectors\n",
-				 (unsigned long)my_usize);
+			drbd_info(device, "Peer sets u_size to %lu sectors (old: %lu)\n",
+				 (unsigned long)p_usize, (unsigned long)my_usize);
 		}
 
 		put_ldev(device);

index e4774f720de5..4b934e543e2d 100644
@@ -1960,9 +1960,9 @@ 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;

index 85e3d846a23a..76d74b2122d6 100644
@@ -4397,6 +4397,25 @@ static int receive_state(struct drbd_connection *connection, struct packet_info
 	if (peer_state.conn == C_AHEAD)
 		ns.conn = C_BEHIND;
 
+	/* TODO:
+	 * if (primary and diskless and peer uuid != effective uuid)
+	 *     abort attach on peer;
+	 *
+	 * If this node does not have good data, was already connected, but
+	 * the peer did a late attach only now, trying to "negotiate" with me,
+	 * AND I am currently Primary, possibly frozen, with some specific
+	 * "effective" uuid, this should never be reached, really, because
+	 * we first send the uuids, then the current state.
+	 *
+	 * In this scenario, we already dropped the connection hard
+	 * when we received the unsuitable uuids (receive_uuids().
+	 *
+	 * Should we want to change this, that is: not drop the connection in
+	 * receive_uuids() already, then we would need to add a branch here
+	 * that aborts the attach of "unsuitable uuids" on the peer in case
+	 * this node is currently Diskless Primary.
+	 */
+
 	if (device->p_uuid && peer_state.disk >= D_NEGOTIATING &&
 	    get_ldev_if_state(device, D_NEGOTIATING)) {
 		int cr; /* consider resync */

index 76d74b2122d6..3a0fe357b68b 100644
@@ -4428,7 +4428,7 @@ static int receive_state(struct drbd_connection *connection, struct packet_info
 		       (peer_state.disk == D_NEGOTIATING ||
 			os.disk == D_NEGOTIATING));
 		/* if we have both been inconsistent, and the peer has been
-		 * forced to be UpToDate with --overwrite-data */
+		 * forced to be UpToDate with --force */
 		cr |= test_bit(CONSIDER_RESYNC, &device->flags);
 		/* if we had been plain connected, and the admin requested to
 		 * start a sync by "invalidate" or "invalidate-remote" */

index 18d53fe60d1d..883155657273 100644
@@ -1124,7 +1124,7 @@ static union drbd_state sanitize_state(struct drbd_device *device, union drbd_st
 			ns.pdsk = D_UP_TO_DATE;
 	}
 
-	/* Implications of the connection stat on the disk states */
+	/* Implications of the connection state on the disk states */
 	disk_min = D_DISKLESS;
 	disk_max = D_UP_TO_DATE;
 	pdsk_min = D_INCONSISTENT;

index 4b934e543e2d..1958eb33b643 100644
@@ -1540,6 +1540,30 @@ 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;

@@ -1602,15 +1626,12 @@ 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;
 	}

index 1958eb33b643..82915880c5e9 100644
@@ -2711,8 +2711,10 @@ int drbd_adm_connect(struct sk_buff *skb, struct genl_info *info)
 
 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);
 

@@ -2730,6 +2732,11 @@ 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);

index ea58301d0895..b2a390ba73a0 100644
@@ -131,7 +131,7 @@ extern enum drbd_state_rv _drbd_set_state(struct drbd_device *, union drbd_state
 					  enum chg_state_flags,
 					  struct completion *done);
 extern void print_st_err(struct drbd_device *, union drbd_state,
-			union drbd_state, int);
+			union drbd_state, enum drbd_state_rv);
 
 enum drbd_state_rv
 _conn_request_state(struct drbd_connection *connection, union drbd_state mask, union drbd_state val,

index 3a0fe357b68b..02a327891568 100644
@@ -5332,7 +5332,7 @@ static int drbd_do_auth(struct drbd_connection *connection)
 	if (pi.cmd != P_AUTH_CHALLENGE) {
 		drbd_err(connection, "expected AuthChallenge packet, received: %s (0x%04x)\n",
 			 cmdname(pi.cmd), pi.cmd);
-		rv = 0;
+		rv = -1;
 		goto fail;
 	}
 

index 82915880c5e9..bfe1b0062d62 100644
@@ -697,14 +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) {

index 5d5e8d6a8a56..f13b48ff5f43 100644
@@ -237,6 +237,8 @@ static void seq_print_peer_request_flags(struct seq_file *m, struct drbd_peer_re
 	seq_print_rq_state_bit(m, f & EE_CALL_AL_COMPLETE_IO, &sep, "in-AL");
 	seq_print_rq_state_bit(m, f & EE_SEND_WRITE_ACK, &sep, "C");
 	seq_print_rq_state_bit(m, f & EE_MAY_SET_IN_SYNC, &sep, "set-in-sync");
+	seq_print_rq_state_bit(m, f & EE_TRIM, &sep, "trim");
+	seq_print_rq_state_bit(m, f & EE_ZEROOUT, &sep, "zero-out");
 	seq_print_rq_state_bit(m, f & EE_WRITE_SAME, &sep, "write-same");
 	seq_putc(m, '\n');
 }

index ab718582a092..000a2f4c0e92 100644
@@ -430,7 +430,11 @@ enum {
 	__EE_MAY_SET_IN_SYNC,
 
 	/* is this a TRIM aka REQ_OP_DISCARD? */
-	__EE_IS_TRIM,
+	__EE_TRIM,
+	/* explicit zero-out requested, or
+	 * our lower level cannot handle trim,
+	 * and we want to fall back to zeroout instead */
+	__EE_ZEROOUT,
 
 	/* In case a barrier failed,
 	 * we need to resubmit without the barrier flag. */

@@ -472,7 +476,8 @@ enum {
 };
 #define EE_CALL_AL_COMPLETE_IO (1<<__EE_CALL_AL_COMPLETE_IO)
 #define EE_MAY_SET_IN_SYNC     (1<<__EE_MAY_SET_IN_SYNC)
-#define EE_IS_TRIM             (1<<__EE_IS_TRIM)
+#define EE_TRIM                (1<<__EE_TRIM)
+#define EE_ZEROOUT             (1<<__EE_ZEROOUT)
 #define EE_RESUBMITTED         (1<<__EE_RESUBMITTED)
 #define EE_WAS_ERROR           (1<<__EE_WAS_ERROR)
 #define EE_HAS_DIGEST          (1<<__EE_HAS_DIGEST)

@@ -1556,6 +1561,8 @@ extern void start_resync_timer_fn(struct timer_list *t);
 extern void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req);
 
 /* drbd_receiver.c */
+extern int drbd_issue_discard_or_zero_out(struct drbd_device *device,
+		sector_t start, unsigned int nr_sectors, int flags);
 extern int drbd_receiver(struct drbd_thread *thi);
 extern int drbd_ack_receiver(struct drbd_thread *thi);
 extern void drbd_send_ping_wf(struct work_struct *ws);

index f9b4228cc2d9..714eb64fabfd 100644
@@ -1668,7 +1668,11 @@ static u32 bio_flags_to_wire(struct drbd_connection *connection,
 			(bio->bi_opf & REQ_PREFLUSH ? DP_FLUSH : 0) |
 			(bio_op(bio) == REQ_OP_WRITE_SAME ? DP_WSAME : 0) |
 			(bio_op(bio) == REQ_OP_DISCARD ? DP_DISCARD : 0) |
-			(bio_op(bio) == REQ_OP_WRITE_ZEROES ? DP_DISCARD : 0);
+			(bio_op(bio) == REQ_OP_WRITE_ZEROES ?
+			  ((connection->agreed_features & DRBD_FF_WZEROES) ?
+			   (DP_ZEROES |(!(bio->bi_opf & REQ_NOUNMAP) ? DP_DISCARD : 0))
+			   : DP_DISCARD)
+			: 0);
 	else
 		return bio->bi_opf & REQ_SYNC ? DP_RW_SYNC : 0;
 }

@@ -1712,10 +1716,11 @@ int drbd_send_dblock(struct drbd_peer_device *peer_device, struct drbd_request *
 	}
 	p->dp_flags = cpu_to_be32(dp_flags);
 
-	if (dp_flags & DP_DISCARD) {
+	if (dp_flags & (DP_DISCARD|DP_ZEROES)) {
+		enum drbd_packet cmd = (dp_flags & DP_ZEROES) ? P_ZEROES : P_TRIM;
 		struct p_trim *t = (struct p_trim*)p;
 		t->size = cpu_to_be32(req->i.size);
-		err = __send_command(peer_device->connection, device->vnr, sock, P_TRIM, sizeof(*t), NULL, 0);
+		err = __send_command(peer_device->connection, device->vnr, sock, cmd, sizeof(*t), NULL, 0);
 		goto out;
 	}
 	if (dp_flags & DP_WSAME) {

index bfe1b0062d62..f2471172a961 100644
@@ -1261,6 +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,

@@ -1371,6 +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)

65 lines not on this page · raw message

266 lines not on this page · raw message

index 1c4da17e902e..643a04af213b 100644
@@ -63,7 +63,7 @@ static struct drbd_request *drbd_req_new(struct drbd_device *device, struct bio
 	drbd_req_make_private_bio(req, bio_src);
 	req->rq_state = (bio_data_dir(bio_src) == WRITE ? RQ_WRITE : 0)
 		      | (bio_op(bio_src) == REQ_OP_WRITE_SAME ? RQ_WSAME : 0)
-		      | (bio_op(bio_src) == REQ_OP_WRITE_ZEROES ? RQ_UNMAP : 0)
+		      | (bio_op(bio_src) == REQ_OP_WRITE_ZEROES ? RQ_ZEROES : 0)
 		      | (bio_op(bio_src) == REQ_OP_DISCARD ? RQ_UNMAP : 0);
 	req->device = device;
 	req->master_bio = bio_src;

@@ -1155,12 +1155,11 @@ static int drbd_process_write_request(struct drbd_request *req)
 	return remote;
 }
 
-static void drbd_process_discard_req(struct drbd_request *req)
+static void drbd_process_discard_or_zeroes_req(struct drbd_request *req, int flags)
 {
-	struct block_device *bdev = req->device->ldev->backing_bdev;
-
-	if (blkdev_issue_zeroout(bdev, req->i.sector, req->i.size >> 9,
-			GFP_NOIO, 0))
+	int err = drbd_issue_discard_or_zero_out(req->device,
+				req->i.sector, req->i.size >> 9, flags);
+	if (err)
 		req->private_bio->bi_status = BLK_STS_IOERR;
 	bio_endio(req->private_bio);
 }

@@ -1189,9 +1188,11 @@ drbd_submit_req_private_bio(struct drbd_request *req)
 	if (get_ldev(device)) {
 		if (drbd_insert_fault(device, type))
 			bio_io_error(bio);
-		else if (bio_op(bio) == REQ_OP_WRITE_ZEROES ||
-			 bio_op(bio) == REQ_OP_DISCARD)
-			drbd_process_discard_req(req);
+		else if (bio_op(bio) == REQ_OP_WRITE_ZEROES)
+			drbd_process_discard_or_zeroes_req(req, EE_ZEROOUT |
+			    ((bio->bi_opf & REQ_NOUNMAP) ? 0 : EE_TRIM));
+		else if (bio_op(bio) == REQ_OP_DISCARD)
+			drbd_process_discard_or_zeroes_req(req, EE_TRIM);
 		else
 			generic_make_request(bio);
 		put_ldev(device);

index 94c654020f0f..c2f569d2661b 100644
@@ -208,6 +208,7 @@ enum drbd_req_state_bits {
 	__RQ_WRITE,
 	__RQ_WSAME,
 	__RQ_UNMAP,
+	__RQ_ZEROES,
 
 	/* Should call drbd_al_complete_io() for this request... */
 	__RQ_IN_ACT_LOG,

@@ -253,6 +254,7 @@ enum drbd_req_state_bits {
 #define RQ_WRITE           (1UL << __RQ_WRITE)
 #define RQ_WSAME           (1UL << __RQ_WSAME)
 #define RQ_UNMAP           (1UL << __RQ_UNMAP)
+#define RQ_ZEROES          (1UL << __RQ_ZEROES)
 #define RQ_IN_ACT_LOG      (1UL << __RQ_IN_ACT_LOG)
 #define RQ_UNPLUG          (1UL << __RQ_UNPLUG)
 #define RQ_POSTPONED	   (1UL << __RQ_POSTPONED)

index 99255d0c9e2f..268ef0c5d4ab 100644
@@ -153,7 +153,7 @@ void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req) __releases(l
 	do_wake = list_empty(block_id == ID_SYNCER ? &device->sync_ee : &device->active_ee);
 
 	/* FIXME do we want to detach for failed REQ_OP_DISCARD?
-	 * ((peer_req->flags & (EE_WAS_ERROR|EE_IS_TRIM)) == EE_WAS_ERROR) */
+	 * ((peer_req->flags & (EE_WAS_ERROR|EE_TRIM)) == EE_WAS_ERROR) */
 	if (peer_req->flags & EE_WAS_ERROR)
 		__drbd_chk_io_error(device, DRBD_WRITE_ERROR);
 

index 2d0259327721..a19d98367f08 100644
@@ -51,7 +51,7 @@
 #endif
 
 extern const char *drbd_buildtag(void);
-#define REL_VERSION "8.4.10"
+#define REL_VERSION "8.4.11"
 #define API_VERSION 1
 #define PRO_VERSION_MIN 86
 #define PRO_VERSION_MAX 101

index 5972e4969197..eeae59d3ceb7 100644
@@ -191,6 +191,7 @@ static inline void ct_assert_unique_operations(void)
 {
 	switch (0) {
 #include GENL_MAGIC_INCLUDE_FILE
+	case 0:
 		;
 	}
 }

@@ -209,6 +210,7 @@ static inline void ct_assert_unique_top_level_attributes(void)
 {
 	switch (0) {
 #include GENL_MAGIC_INCLUDE_FILE
+	case 0:
 		;
 	}
 }

@@ -218,7 +220,8 @@ static inline void ct_assert_unique_top_level_attributes(void)
 static inline void ct_assert_unique_ ## s_name ## _attributes(void)	\
 {									\
 	switch (0) {							\
-		s_fields						\
+	s_fields							\
+	case 0:								\
 			;						\
 	}								\
 }

index 883155657273..2b4c0db5d867 100644
@@ -688,11 +688,9 @@ request_detach(struct drbd_device *device)
 			CS_VERBOSE | CS_ORDERED | CS_INHIBIT_MD_IO);
 }
 
-enum drbd_state_rv
-drbd_request_detach_interruptible(struct drbd_device *device)
+int drbd_request_detach_interruptible(struct drbd_device *device)
 {
-	enum drbd_state_rv rv;
-	int ret;
+	int ret, rv;
 
 	drbd_suspend_io(device); /* so no-one is stuck in drbd_al_begin_io */
 	wait_event_interruptible(device->state_wait,

index b2a390ba73a0..f87371e55e68 100644
@@ -162,8 +162,7 @@ static inline int drbd_request_state(struct drbd_device *device,
 }
 
 /* for use in adm_detach() (drbd_adm_detach(), drbd_adm_down()) */
-enum drbd_state_rv
-drbd_request_detach_interruptible(struct drbd_device *device);
+int drbd_request_detach_interruptible(struct drbd_device *device);
 
 enum drbd_role conn_highest_role(struct drbd_connection *connection);
 enum drbd_role conn_highest_peer(struct drbd_connection *connection);