Commit fcd2b0da authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'rds-ha-failover-fixes' 



Sowmini Varadhan says:

====================
RDS: TCP: HA/Failover fixes

This series contains a set of fixes for bugs exposed when
we ran the following in a loop between a test machine pair:

 while (1); do
   # modprobe rds-tcp on test nodes
   # run rds-stress in bi-dir mode between test machine pair
   # modprobe -r rds-tcp on test nodes
 done

rds-stress in bi-dir mode will cause both nodes to initiate
RDS-TCP connections at almost the same instant, exposing the
bugs fixed in this series.

Without the fixes, rds-stress reports sporadic packet drops,
and packets arriving out of sequence. After the fixes,we have
been able to run the  test overnight, without any issues.

Each patch has a detailed description of the root-cause fixed
by the patch.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents b3e51069 1a0e100f

net/rds/af_rds.c

+4 −0
Original line number Diff line number Diff line
@@ -605,10 +605,14 @@ static void rds_exit(void) 
}

module_exit(rds_exit);



u32 rds_gen_num;



static int rds_init(void)

{

	int ret;



	net_get_random_once(&rds_gen_num, sizeof(rds_gen_num));



	ret = rds_bind_lock_init();

	if (ret)

		goto out;

net/rds/connection.c

+3 −0
Original line number Diff line number Diff line
@@ -269,6 +269,8 @@ static struct rds_connection *__rds_conn_create(struct net *net, 
			kmem_cache_free(rds_conn_slab, conn);

			conn = found;

		} else {

			conn->c_my_gen_num = rds_gen_num;

			conn->c_peer_gen_num = 0;

			hlist_add_head_rcu(&conn->c_hash_node, head);

			rds_cong_add_conn(conn);

			rds_conn_count++;
@@ -681,6 +683,7 @@ void rds_conn_path_connect_if_down(struct rds_conn_path *cp) 
	    !test_and_set_bit(RDS_RECONNECT_PENDING, &cp->cp_flags))

		queue_delayed_work(rds_wq, &cp->cp_conn_w, 0);

}

EXPORT_SYMBOL_GPL(rds_conn_path_connect_if_down);



void rds_conn_connect_if_down(struct rds_connection *conn)

{

net/rds/message.c

+1 −0
Original line number Diff line number Diff line
@@ -42,6 +42,7 @@ static unsigned int rds_exthdr_size[__RDS_EXTHDR_MAX] = { 
[RDS_EXTHDR_RDMA]	= sizeof(struct rds_ext_header_rdma),

[RDS_EXTHDR_RDMA_DEST]	= sizeof(struct rds_ext_header_rdma_dest),

[RDS_EXTHDR_NPATHS]	= sizeof(u16),

[RDS_EXTHDR_GEN_NUM]	= sizeof(u32),

};

net/rds/rds.h

+7 −1
Original line number Diff line number Diff line
@@ -151,6 +151,9 @@ struct rds_connection { 


	struct rds_conn_path	c_path[RDS_MPATH_WORKERS];

	wait_queue_head_t	c_hs_waitq; /* handshake waitq */



	u32			c_my_gen_num;

	u32			c_peer_gen_num;

};



static inline
@@ -243,7 +246,8 @@ struct rds_ext_header_rdma_dest { 
/* Extension header announcing number of paths.

 * Implicit length = 2 bytes.

 */

#define RDS_EXTHDR_NPATHS	4

#define RDS_EXTHDR_NPATHS	5

#define RDS_EXTHDR_GEN_NUM	6



#define __RDS_EXTHDR_MAX	16 /* for now */
@@ -338,6 +342,7 @@ static inline u32 rds_rdma_cookie_offset(rds_rdma_cookie_t cookie) 
#define RDS_MSG_RETRANSMITTED	5

#define RDS_MSG_MAPPED		6

#define RDS_MSG_PAGEVEC		7

#define RDS_MSG_FLUSH		8



struct rds_message {

	atomic_t		m_refcount;
@@ -664,6 +669,7 @@ void rds_cong_exit(void); 
struct rds_message *rds_cong_update_alloc(struct rds_connection *conn);



/* conn.c */

extern u32 rds_gen_num;

int rds_conn_init(void);

void rds_conn_exit(void);

struct rds_connection *rds_conn_create(struct net *net,

net/rds/recv.c

+36 −0
Original line number Diff line number Diff line
@@ -120,6 +120,36 @@ static void rds_recv_rcvbuf_delta(struct rds_sock *rs, struct sock *sk, 
	/* do nothing if no change in cong state */

}



static void rds_conn_peer_gen_update(struct rds_connection *conn,

				     u32 peer_gen_num)

{

	int i;

	struct rds_message *rm, *tmp;

	unsigned long flags;



	WARN_ON(conn->c_trans->t_type != RDS_TRANS_TCP);

	if (peer_gen_num != 0) {

		if (conn->c_peer_gen_num != 0 &&

		    peer_gen_num != conn->c_peer_gen_num) {

			for (i = 0; i < RDS_MPATH_WORKERS; i++) {

				struct rds_conn_path *cp;



				cp = &conn->c_path[i];

				spin_lock_irqsave(&cp->cp_lock, flags);

				cp->cp_next_tx_seq = 1;

				cp->cp_next_rx_seq = 0;

				list_for_each_entry_safe(rm, tmp,

							 &cp->cp_retrans,

							 m_conn_item) {

					set_bit(RDS_MSG_FLUSH, &rm->m_flags);

				}

				spin_unlock_irqrestore(&cp->cp_lock, flags);

			}

		}

		conn->c_peer_gen_num = peer_gen_num;

	}

}



/*

 * Process all extension headers that come with this message.

 */
@@ -163,7 +193,9 @@ static void rds_recv_hs_exthdrs(struct rds_header *hdr, 
	union {

		struct rds_ext_header_version version;

		u16 rds_npaths;

		u32 rds_gen_num;

	} buffer;

	u32 new_peer_gen_num = 0;



	while (1) {

		len = sizeof(buffer);
@@ -176,6 +208,9 @@ static void rds_recv_hs_exthdrs(struct rds_header *hdr, 
			conn->c_npaths = min_t(int, RDS_MPATH_WORKERS,

					       buffer.rds_npaths);

			break;

		case RDS_EXTHDR_GEN_NUM:

			new_peer_gen_num = buffer.rds_gen_num;

			break;

		default:

			pr_warn_ratelimited("ignoring unknown exthdr type "

					     "0x%x\n", type);
@@ -183,6 +218,7 @@ static void rds_recv_hs_exthdrs(struct rds_header *hdr, 
	}

	/* if RDS_EXTHDR_NPATHS was not found, default to a single-path */

	conn->c_npaths = max_t(int, conn->c_npaths, 1);

	rds_conn_peer_gen_update(conn, new_peer_gen_num);

}



/* rds_start_mprds() will synchronously start multiple paths when appropriate.

CRA Git | Maintained and supported by SUSTech CRA and CCSE