Merge tag 'for-5.13/drivers-2021-04-27' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:

 - MD changes via Song:
        - raid5 POWER fix
        - raid1 failure fix
        - UAF fix for md cluster
        - mddev_find_or_alloc() clean up
        - Fix NULL pointer deref with external bitmap
        - Performance improvement for raid10 discard requests
        - Fix missing information of /proc/mdstat

 - rsxx const qualifier removal (Arnd)

 - Expose allocated brd pages (Calvin)

 - rnbd via Gioh Kim:
        - Change maintainer
        - Change domain address of maintainers' email
        - Add polling IO mode and document update
        - Fix memory leak and some bug detected by static code analysis
          tools
        - Code refactoring

 - Series of floppy cleanups/fixes (Denis)

 - s390 dasd fixes (Julian)

 - kerneldoc fixes (Lee)

 - null_blk double free (Lv)

 - null_blk virtual boundary addition (Max)

 - Remove xsysace driver (Michal)

 - umem driver removal (Davidlohr)

 - ataflop fixes (Dan)

 - Revalidate disk removal (Christoph)

 - Bounce buffer cleanups (Christoph)

 - Mark lightnvm as deprecated (Christoph)

 - mtip32xx init cleanups (Shixin)

 - Various fixes (Tian, Gustavo, Coly, Yang, Zhang, Zhiqiang)

* tag 'for-5.13/drivers-2021-04-27' of git://git.kernel.dk/linux-block: (143 commits)
  async_xor: increase src_offs when dropping destination page
  drivers/block/null_blk/main: Fix a double free in null_init.
  md/raid1: properly indicate failure when ending a failed write request
  md-cluster: fix use-after-free issue when removing rdev
  nvme: introduce generic per-namespace chardev
  nvme: cleanup nvme_configure_apst
  nvme: do not try to reconfigure APST when the controller is not live
  nvme: add 'kato' sysfs attribute
  nvme: sanitize KATO setting
  nvmet: avoid queuing keep-alive timer if it is disabled
  brd: expose number of allocated pages in debugfs
  ataflop: fix off by one in ataflop_probe()
  ataflop: potential out of bounds in do_format()
  drbd: Fix fall-through warnings for Clang
  block/rnbd: Use strscpy instead of strlcpy
  block/rnbd-clt-sysfs: Remove copy buffer overlap in rnbd_clt_get_path_name
  block/rnbd-clt: Remove max_segment_size
  block/rnbd-clt: Generate kobject_uevent when the rnbd device state changes
  block/rnbd-srv: Remove unused arguments of rnbd_srv_rdma_ev
  Documentation/ABI/rnbd-clt: Add description for nr_poll_queues
  ...

5 files changed, 62 insertions, 32 deletions

diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index 6734329cca33..b74a872387c4 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -103,11 +103,11 @@ static inline void __rtrs_put_permit(struct rtrs_clt *clt,
  *    up earlier.
  *
  * Context:
- *    Can sleep if @wait == RTRS_TAG_WAIT
+ *    Can sleep if @wait == RTRS_PERMIT_WAIT
  */
 struct rtrs_permit *rtrs_clt_get_permit(struct rtrs_clt *clt,
 					  enum rtrs_clt_con_type con_type,
-					  int can_wait)
+					  enum wait_type can_wait)
 {
 	struct rtrs_permit *permit;
 	DEFINE_WAIT(wait);
@@ -174,7 +174,7 @@ struct rtrs_clt_con *rtrs_permit_to_clt_con(struct rtrs_clt_sess *sess,
 	int id = 0;
 
 	if (likely(permit->con_type == RTRS_IO_CON))
-		id = (permit->cpu_id % (sess->s.con_num - 1)) + 1;
+		id = (permit->cpu_id % (sess->s.irq_con_num - 1)) + 1;
 
 	return to_clt_con(sess->s.con[id]);
 }
@@ -1400,23 +1400,29 @@ static void rtrs_clt_close_work(struct work_struct *work);
 static struct rtrs_clt_sess *alloc_sess(struct rtrs_clt *clt,
 					 const struct rtrs_addr *path,
 					 size_t con_num, u16 max_segments,
-					 size_t max_segment_size)
+					 u32 nr_poll_queues)
 {
 	struct rtrs_clt_sess *sess;
 	int err = -ENOMEM;
 	int cpu;
+	size_t total_con;
 
 	sess = kzalloc(sizeof(*sess), GFP_KERNEL);
 	if (!sess)
 		goto err;
 
-	/* Extra connection for user messages */
-	con_num += 1;
-
-	sess->s.con = kcalloc(con_num, sizeof(*sess->s.con), GFP_KERNEL);
+	/*
+	 * irqmode and poll
+	 * +1: Extra connection for user messages
+	 */
+	total_con = con_num + nr_poll_queues + 1;
+	sess->s.con = kcalloc(total_con, sizeof(*sess->s.con), GFP_KERNEL);
 	if (!sess->s.con)
 		goto err_free_sess;
 
+	sess->s.con_num = total_con;
+	sess->s.irq_con_num = con_num + 1;
+
 	sess->stats = kzalloc(sizeof(*sess->stats), GFP_KERNEL);
 	if (!sess->stats)
 		goto err_free_con;
@@ -1435,9 +1441,8 @@ static struct rtrs_clt_sess *alloc_sess(struct rtrs_clt *clt,
 		memcpy(&sess->s.src_addr, path->src,
 		       rdma_addr_size((struct sockaddr *)path->src));
 	strlcpy(sess->s.sessname, clt->sessname, sizeof(sess->s.sessname));
-	sess->s.con_num = con_num;
 	sess->clt = clt;
-	sess->max_pages_per_mr = max_segments * max_segment_size >> 12;
+	sess->max_pages_per_mr = max_segments;
 	init_waitqueue_head(&sess->state_wq);
 	sess->state = RTRS_CLT_CONNECTING;
 	atomic_set(&sess->connected_cnt, 0);
@@ -1576,9 +1581,14 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
 	}
 	cq_size = max_send_wr + max_recv_wr;
 	cq_vector = con->cpu % sess->s.dev->ib_dev->num_comp_vectors;
-	err = rtrs_cq_qp_create(&sess->s, &con->c, sess->max_send_sge,
-				 cq_vector, cq_size, max_send_wr,
-				 max_recv_wr, IB_POLL_SOFTIRQ);
+	if (con->c.cid >= sess->s.irq_con_num)
+		err = rtrs_cq_qp_create(&sess->s, &con->c, sess->max_send_sge,
+					cq_vector, cq_size, max_send_wr,
+					max_recv_wr, IB_POLL_DIRECT);
+	else
+		err = rtrs_cq_qp_create(&sess->s, &con->c, sess->max_send_sge,
+					cq_vector, cq_size, max_send_wr,
+					max_recv_wr, IB_POLL_SOFTIRQ);
 	/*
 	 * In case of error we do not bother to clean previous allocations,
 	 * since destroy_con_cq_qp() must be called.
@@ -2528,7 +2538,6 @@ static struct rtrs_clt *alloc_clt(const char *sessname, size_t paths_num,
 				  void	(*link_ev)(void *priv,
 						   enum rtrs_clt_link_ev ev),
 				  unsigned int max_segments,
-				  size_t max_segment_size,
 				  unsigned int reconnect_delay_sec,
 				  unsigned int max_reconnect_attempts)
 {
@@ -2558,7 +2567,6 @@ static struct rtrs_clt *alloc_clt(const char *sessname, size_t paths_num,
 	clt->port = port;
 	clt->pdu_sz = pdu_sz;
 	clt->max_segments = max_segments;
-	clt->max_segment_size = max_segment_size;
 	clt->reconnect_delay_sec = reconnect_delay_sec;
 	clt->max_reconnect_attempts = max_reconnect_attempts;
 	clt->priv = priv;
@@ -2628,9 +2636,9 @@ static void free_clt(struct rtrs_clt *clt)
  * @pdu_sz: Size of extra payload which can be accessed after permit allocation.
  * @reconnect_delay_sec: time between reconnect tries
  * @max_segments: Max. number of segments per IO request
- * @max_segment_size: Max. size of one segment
  * @max_reconnect_attempts: Number of times to reconnect on error before giving
  *			    up, 0 for * disabled, -1 for forever
+ * @nr_poll_queues: number of polling mode connection using IB_POLL_DIRECT flag
  *
  * Starts session establishment with the rtrs_server. The function can block
  * up to ~2000ms before it returns.
@@ -2643,8 +2651,7 @@ struct rtrs_clt *rtrs_clt_open(struct rtrs_clt_ops *ops,
 				 size_t paths_num, u16 port,
 				 size_t pdu_sz, u8 reconnect_delay_sec,
 				 u16 max_segments,
-				 size_t max_segment_size,
-				 s16 max_reconnect_attempts)
+				 s16 max_reconnect_attempts, u32 nr_poll_queues)
 {
 	struct rtrs_clt_sess *sess, *tmp;
 	struct rtrs_clt *clt;
@@ -2652,7 +2659,7 @@ struct rtrs_clt *rtrs_clt_open(struct rtrs_clt_ops *ops,
 
 	clt = alloc_clt(sessname, paths_num, port, pdu_sz, ops->priv,
 			ops->link_ev,
-			max_segments, max_segment_size, reconnect_delay_sec,
+			max_segments, reconnect_delay_sec,
 			max_reconnect_attempts);
 	if (IS_ERR(clt)) {
 		err = PTR_ERR(clt);
@@ -2662,7 +2669,7 @@ struct rtrs_clt *rtrs_clt_open(struct rtrs_clt_ops *ops,
 		struct rtrs_clt_sess *sess;
 
 		sess = alloc_sess(clt, &paths[i], nr_cpu_ids,
-				  max_segments, max_segment_size);
+				  max_segments, nr_poll_queues);
 		if (IS_ERR(sess)) {
 			err = PTR_ERR(sess);
 			goto close_all_sess;
@@ -2887,6 +2894,31 @@ int rtrs_clt_request(int dir, struct rtrs_clt_req_ops *ops,
 }
 EXPORT_SYMBOL(rtrs_clt_request);
 
+int rtrs_clt_rdma_cq_direct(struct rtrs_clt *clt, unsigned int index)
+{
+	int cnt;
+	struct rtrs_con *con;
+	struct rtrs_clt_sess *sess;
+	struct path_it it;
+
+	rcu_read_lock();
+	for (path_it_init(&it, clt);
+	     (sess = it.next_path(&it)) && it.i < it.clt->paths_num; it.i++) {
+		if (READ_ONCE(sess->state) != RTRS_CLT_CONNECTED)
+			continue;
+
+		con = sess->s.con[index + 1];
+		cnt = ib_process_cq_direct(con->cq, -1);
+		if (cnt)
+			break;
+	}
+	path_it_deinit(&it);
+	rcu_read_unlock();
+
+	return cnt;
+}
+EXPORT_SYMBOL(rtrs_clt_rdma_cq_direct);
+
 /**
  * rtrs_clt_query() - queries RTRS session attributes
  *@clt: session pointer
@@ -2915,8 +2947,7 @@ int rtrs_clt_create_path_from_sysfs(struct rtrs_clt *clt,
 	struct rtrs_clt_sess *sess;
 	int err;
 
-	sess = alloc_sess(clt, addr, nr_cpu_ids, clt->max_segments,
-			  clt->max_segment_size);
+	sess = alloc_sess(clt, addr, nr_cpu_ids, clt->max_segments, 0);
 	if (IS_ERR(sess))
 		return PTR_ERR(sess);
 
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.h b/drivers/infiniband/ulp/rtrs/rtrs-clt.h
index 692bc83e1f09..98ba5d0a48b8 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.h
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.h
@@ -166,7 +166,6 @@ struct rtrs_clt {
 	unsigned int		max_reconnect_attempts;
 	unsigned int		reconnect_delay_sec;
 	unsigned int		max_segments;
-	size_t			max_segment_size;
 	void			*permits;
 	unsigned long		*permits_map;
 	size_t			queue_depth;
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-pri.h b/drivers/infiniband/ulp/rtrs/rtrs-pri.h
index 8caad0a2322b..00eb45053339 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-pri.h
+++ b/drivers/infiniband/ulp/rtrs/rtrs-pri.h
@@ -101,6 +101,7 @@ struct rtrs_sess {
 	uuid_t			uuid;
 	struct rtrs_con	**con;
 	unsigned int		con_num;
+	unsigned int		irq_con_num;
 	unsigned int		recon_cnt;
 	struct rtrs_ib_dev	*dev;
 	int			dev_ref;
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
index d071809e3ed2..f7aa2a7e7442 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
@@ -998,7 +998,7 @@ static void process_read(struct rtrs_srv_con *con,
 	usr_len = le16_to_cpu(msg->usr_len);
 	data_len = off - usr_len;
 	data = page_address(srv->chunks[buf_id]);
-	ret = ctx->ops.rdma_ev(srv, srv->priv, id, READ, data, data_len,
+	ret = ctx->ops.rdma_ev(srv->priv, id, READ, data, data_len,
 			   data + data_len, usr_len);
 
 	if (unlikely(ret)) {
@@ -1051,7 +1051,7 @@ static void process_write(struct rtrs_srv_con *con,
 	usr_len = le16_to_cpu(req->usr_len);
 	data_len = off - usr_len;
 	data = page_address(srv->chunks[buf_id]);
-	ret = ctx->ops.rdma_ev(srv, srv->priv, id, WRITE, data, data_len,
+	ret = ctx->ops.rdma_ev(srv->priv, id, WRITE, data, data_len,
 			   data + data_len, usr_len);
 	if (unlikely(ret)) {
 		rtrs_err_rl(s,
diff --git a/drivers/infiniband/ulp/rtrs/rtrs.h b/drivers/infiniband/ulp/rtrs/rtrs.h
index 8738e90e715a..bebaa94c4728 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs.h
+++ b/drivers/infiniband/ulp/rtrs/rtrs.h
@@ -58,14 +58,13 @@ struct rtrs_clt *rtrs_clt_open(struct rtrs_clt_ops *ops,
 				 size_t path_cnt, u16 port,
 				 size_t pdu_sz, u8 reconnect_delay_sec,
 				 u16 max_segments,
-				 size_t max_segment_size,
-				 s16 max_reconnect_attempts);
+				 s16 max_reconnect_attempts, u32 nr_poll_queues);
 
 void rtrs_clt_close(struct rtrs_clt *sess);
 
-enum {
+enum wait_type {
 	RTRS_PERMIT_NOWAIT = 0,
-	RTRS_PERMIT_WAIT   = 1,
+	RTRS_PERMIT_WAIT   = 1
 };
 
 /**
@@ -81,7 +80,7 @@ enum rtrs_clt_con_type {
 
 struct rtrs_permit *rtrs_clt_get_permit(struct rtrs_clt *sess,
 				    enum rtrs_clt_con_type con_type,
-				    int wait);
+				    enum wait_type wait);
 
 void rtrs_clt_put_permit(struct rtrs_clt *sess, struct rtrs_permit *permit);
 
@@ -103,6 +102,7 @@ int rtrs_clt_request(int dir, struct rtrs_clt_req_ops *ops,
 		     struct rtrs_clt *sess, struct rtrs_permit *permit,
 		     const struct kvec *vec, size_t nr, size_t len,
 		     struct scatterlist *sg, unsigned int sg_cnt);
+int rtrs_clt_rdma_cq_direct(struct rtrs_clt *clt, unsigned int index);
 
 /**
  * rtrs_attrs - RTRS session attributes
@@ -138,7 +138,6 @@ struct rtrs_srv_ops {
 	 *			message for the data transfer will be sent to
 	 *			the client.
 
-	 *	@sess:		Session
 	 *	@priv:		Private data set by rtrs_srv_set_sess_priv()
 	 *	@id:		internal RTRS operation id
 	 *	@dir:		READ/WRITE
@@ -152,7 +151,7 @@ struct rtrs_srv_ops {
 	 *	@usr:		The extra user message sent by the client (%vec)
 	 *	@usrlen:	Size of the user message
 	 */
-	int (*rdma_ev)(struct rtrs_srv *sess, void *priv,
+	int (*rdma_ev)(void *priv,
 		       struct rtrs_srv_op *id, int dir,
 		       void *data, size_t datalen, const void *usr,
 		       size_t usrlen);