One aim of commit 50100a5e39 ("tipc:
use pseudo message to wake up sockets after link congestion") was
to handle link congestion abatement in a uniform way for both unicast
and multicast transmit. However, the latter doesn't work correctly,
and has been broken since the referenced commit was applied.
If a user now sends a burst of multicast messages that is big
enough to cause broadcast link congestion, it will be put to sleep,
and not be waked up when the congestion abates as it should be.
This has two reasons. First, the flag that is used, TIPC_WAKEUP_USERS,
is set correctly, but in the wrong field. Instead of setting it in the
'action_flags' field of the arrival node struct, it is by mistake set
in the dummy node struct that is owned by the broadcast link, where it
will never tested for. Second, we cannot use the same flag for waking
up unicast and multicast users, since the function tipc_node_unlock()
needs to pick the wakeup pseudo messages to deliver from different
queues. It must hence be able to distinguish between the two cases.
This commit solves this problem by adding a new flag
TIPC_WAKEUP_BCAST_USERS, and a new function tipc_bclink_wakeup_user().
The latter is to be called by tipc_node_unlock() when the named flag,
now set in the correct field, is encountered.
v2: using explicit 'unsigned int' declaration instead of 'uint', as
per comment from David Miller.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In the current implementation, each 'struct tipc_node' instance keeps
a linked list of those ports/sockets that are connected to the node
represented by that struct. The purpose of this is to let the node
object know which sockets to alert when it loses contact with its peer
node, i.e., which sockets need to have their connections aborted.
This entails an unwanted direct reference from the node structure
back to the port/socket structure, and a need to grab port_lock
when we have to make an upcall to the port. We want to get rid of
this unecessary BH entry point into the socket, and also eliminate
its use of port_lock.
In this commit, we instead let the node struct keep list of "connected
socket" structs, which each represents a connected socket, but is
allocated independently by the node at the moment of connection. If
the node loses contact with its peer node, the list is traversed, and
a "connection abort" message is created for each entry in the list. The
message is sent to it respective connected socket using the ordinary
data path, and the receiving socket aborts its connections upon reception
of the message.
This enables us to get rid of the direct reference from 'struct node' to
´struct port', and another unwanted BH access point to the latter.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The current link implementation keeps a linked list of blocked ports/
sockets that is populated when there is link congestion. The purpose
of this is to let the link know which users to wake up when the
congestion abates.
This adds unnecessary complexity to the data structure and the code,
since it forces us to involve the link each time we want to delete
a socket. It also forces us to grab the spinlock port_lock within
the scope of node_lock. We want to get rid of this direct dependence,
as well as the deadlock hazard resulting from the usage of port_lock.
In this commit, we instead let the link keep list of a "wakeup" pseudo
messages for use in such situations. Those messages are sent to the
pending sockets via the ordinary message reception path, and wake up
the socket's owner when they are received.
This enables us to get rid of the 'waiting_ports' linked lists in struct
tipc_port that manifest this direct reference. As a consequence, we can
eliminate another BH entry into the socket, and hence the need to grab
port_lock. This is a further step in our effort to remove port_lock
altogether.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In a previous commit series ("tipc: new unicast transmission code")
we introduced a new message sending function, tipc_link_xmit2(),
and moved the unicast data users over to use that function. We now
let the internal name table distributor do the same.
The interaction between the name distributor and the node/link
layer also becomes significantly simpler, so we can eliminate
the function tipc_link_names_xmit().
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Message fragmentation is currently performed at link level, inside
the protection of node_lock. This potentially binds up the sending
link structure for a long time, instead of letting it do other tasks,
such as handle reception of new packets.
In this commit, we make the MTUs of each active link become easily
accessible from the socket level, i.e., without taking any spinlock
or dereferencing the target link pointer. This way, we make it possible
to perform fragmentation in the sending socket, before sending the
whole fragment chain to the link for transport.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The function tipc_link_frag_rcv() is in reality a re-entrant generic
message reassemby function that has nothing in particular to do with
the link, where it is defined now. This becomes obvious when we see
the need to call the function from other places in the code.
In this commit rename it to tipc_buf_append() and move it to the file
msg.c. We also simplify its signature by moving the tail pointer to
the control block of the head buffer, hence making the head buffer
self-contained.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Each node action flag should be set or cleared separately, instead
we now set the whole flags variable in one shot, and it's turned
out to be hard to see which other flags are affected. Therefore,
for instance, we explicitly clear TIPC_WAIT_OWN_LINKS_DOWN bit in
node_lost_contact().
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Rename node flags to action_flags as well as its enum names so
that they can reflect its real meanings.
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since previously what all publications pertaining to the lost node
were removed from name table was finished in tasklet context
asynchronously, we need to TIPC_NAMES_GONE flag indicating whether
the node cleanup work is finished or not. But now as the cleanup work
has been finished when node lock is released, the flag becomes
meaningless for us.
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Postpone the actions of notifying subscriptions until after node lock
is released, avoiding to asynchronously execute registered handlers
when node is lost.
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 78acb1f9b8 ("tipc: add
ioctl to fetch link names") introduced a buffer overflow bug where
specially crafted ioctl requests could cause out-of-bounds indexing
of the node->links array. This was caused by an incorrect check vs
MAX_BEARERS, and the static code checker complaint is:
net/tipc/node.c:459 tipc_node_get_linkname() error: buffer overflow 'node->links' 2 <= 2
Signed-off-by: Erik Hugne <erik.hugne@ericsson.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We add a new ioctl for AF_TIPC that can be used to fetch the
logical name for a link to a remote node on a given bearer. This
should be used in combination with link state subscriptions.
The logical name size limit definitions are moved to tipc.h, as
they are now also needed by the new ioctl.
Signed-off-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When links are established over a bearer plane, we create a node
local publication containing information about the peer node and
bearer plane. This allows TIPC applications to use the standard
TIPC topology server subscription mechanism to get notifications
when a link goes up or down.
Signed-off-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now tipc routing hierarchy comprises the structures 'node', 'link'and
'bearer'. The whole hierarchy is protected by a big read/write lock,
tipc_net_lock, to ensure that nothing is added or removed while code
is accessing any of these structures. Obviously the locking policy
makes node, link and bearer components closely bound together so that
their relationship becomes unnecessarily complex. In the worst case,
such locking policy not only has a negative influence on performance,
but also it's prone to lead to deadlock occasionally.
In order o decouple the complex relationship between bearer and node
as well as link, the locking policy is adjusted as follows:
- Bearer level
RTNL lock is used on update side, and RCU is used on read side.
Meanwhile, all bearer instances including broadcast bearer are
saved into bearer_list array.
- Node and link level
All node instances are saved into two tipc_node_list and node_htable
lists. The two lists are protected by node_list_lock on write side,
and they are guarded with RCU lock on read side. All members in node
structure including link instances are protected by node spin lock.
- The relationship between bearer and node
When link accesses bearer, it first needs to find the bearer with
its bearer identity from the bearer_list array. When bearer accesses
node, it can iterate the node_htable hash list with the node
address to find the corresponding node.
In the new locking policy, every component has its private locking
solution and the relationship between bearer and node is very simple,
that is, they can find each other with node address or bearer identity
from node_htable hash list or bearer_list array.
Until now above all changes have been done, so tipc_net_lock can be
removed safely.
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Tested-by: Erik Hugne <erik.hugne@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently on both paths of message transmission and reception, the
read lock of tipc_net_lock must be held before bearer is accessed,
while the write lock of tipc_net_lock has to be taken before bearer
is configured. Although it can ensure that bearer is always valid on
the two data paths, link and bearer is closely bound together.
So as the part of effort of removing tipc_net_lock, the locking
policy of bearer protection will be adjusted as below: on the two
data paths, RCU is used, and on the configuration path of bearer,
RTNL lock is applied.
Now RCU just covers the path of message reception. To make it possible
to protect the path of message transmission with RCU, link should not
use its stored bearer pointer to access bearer, but it should use the
bearer identity of its attached bearer as index to get bearer instance
from bearer_list array, which can help us decouple the relationship
between bearer and link. As a result, bearer on the path of message
transmission can be safely protected by RCU when we access bearer_list
array within RCU lock protection.
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Tested-by: Erik Hugne <erik.hugne@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Without properly implicit or explicit read memory barrier, it's
unsafe to read an atomic variable with atomic_read() from another
thread which is different with the thread of changing the atomic
variable with atomic_inc() or atomic_dec(). So a stale tipc_num_links
may be got with atomic_read() in tipc_node_get_links(). If the
tipc_num_links variable type is converted from atomic to unsigned
integer and node list lock is used to protect it, the issue would
be avoided.
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As tipc_node_list is protected by rcu read lock on read side, it's
unnecessary to hold node_list_lock to protect tipc_node_list in
tipc_node_get_links(). Instead, node_list_lock should just protects
tipc_num_nodes in the function.
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Convert tipc_node_list list and node_htable hash list to RCU lists.
On read side, the two lists are protected with RCU read lock, and
on update side, node_list_lock is applied to them.
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When a node is created, tipc_net_lock read lock is first held and
then node_create_lock is grabbed in order to prevent the same node
from being created and inserted into both node list and hlist twice.
But when we query node from the two node lists, we only hold
tipc_net_lock read lock without grabbing node_create_lock. Obviously
this locking policy is unable to guarantee that the two node lists
are always synchronized especially when the operation of changing
and accessing them occurs in different contexts like currently doing.
Therefore, rename node_create_lock to node_list_lock to protect the
two node lists, that is, whenever node is inserted into them or node
is queried from them, the node_list_lock should be always held. As a
result, tipc_net_lock read lock becomes redundant and then can be
removed from the node query functions.
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
tipc_node_create routine doesn't need to check whether a node
object specified with a node address exists or not because its
caller(ie, tipc_disc_recv_msg routine) has checked this before
calling it.
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Rename the following functions, which are shorter and more in line
with common naming practice in the network subsystem.
tipc_bclink_send_msg->tipc_bclink_xmit
tipc_bclink_recv_pkt->tipc_bclink_rcv
tipc_disc_recv_msg->tipc_disc_rcv
tipc_link_send_proto_msg->tipc_link_proto_xmit
link_recv_proto_msg->tipc_link_proto_rcv
link_send_sections_long->tipc_link_iovec_long_xmit
tipc_link_send_sections_fast->tipc_link_iovec_xmit_fast
tipc_link_send_sync->tipc_link_sync_xmit
tipc_link_recv_sync->tipc_link_sync_rcv
tipc_link_send_buf->__tipc_link_xmit
tipc_link_send->tipc_link_xmit
tipc_link_send_names->tipc_link_names_xmit
tipc_named_recv->tipc_named_rcv
tipc_link_recv_bundle->tipc_link_bundle_rcv
tipc_link_dup_send_queue->tipc_link_dup_queue_xmit
link_send_long_buf->tipc_link_frag_xmit
tipc_multicast->tipc_port_mcast_xmit
tipc_port_recv_mcast->tipc_port_mcast_rcv
tipc_port_reject_sections->tipc_port_iovec_reject
tipc_port_recv_proto_msg->tipc_port_proto_rcv
tipc_connect->tipc_port_connect
__tipc_connect->__tipc_port_connect
__tipc_disconnect->__tipc_port_disconnect
tipc_disconnect->tipc_port_disconnect
tipc_shutdown->tipc_port_shutdown
tipc_port_recv_msg->tipc_port_rcv
tipc_port_recv_sections->tipc_port_iovec_rcv
release->tipc_release
accept->tipc_accept
bind->tipc_bind
get_name->tipc_getname
poll->tipc_poll
send_msg->tipc_sendmsg
send_packet->tipc_send_packet
send_stream->tipc_send_stream
recv_msg->tipc_recvmsg
recv_stream->tipc_recv_stream
connect->tipc_connect
listen->tipc_listen
shutdown->tipc_shutdown
setsockopt->tipc_setsockopt
getsockopt->tipc_getsockopt
Above changes have no impact on current users of the functions.
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In commit 7d33939f47
("tipc: delay delete of link when failover is needed") we
introduced a loop for finding and removing a link pointer
in an array. The removal is done after we have left the loop,
giving the impression that one may remove the wrong pointer
if no matching element is found.
This is not really a bug, since we know that there will always
be a matching element, but it looks wrong, and causes a smatch
warning.
We fix this loop with this commit.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When a bearer is disabled, all its attached links are deleted.
Ideally, we should do link failover to redundant links on other bearers,
if there are any, in such cases. This would be consistent with current
behavior when a link is reset, but not deleted. However, due to the
complexity involved, and the (wrongly) perceived low demand for this
feature, it was never implemented until now.
We mark the doomed link for deletion with a new flag, but wait until the
failover process is finished before we actually delete it. With the
improved link tunnelling/failover code introduced earlier in this commit
series, it is now easy to identify a spot in the code where the failover
is finished and it is safe to delete the marked link. Moreover, the test
for the flag and the deletion can be done synchronously, and outside the
most time critical data path.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
