Currently, updating binding table (add service binding to
name table/withdraw a service binding) is being sent over replicast.
However, if we are scaling up clusters to > 100 nodes/containers this
method is less affection because of looping through nodes in a cluster one
by one.
It is worth to use broadcast to update a binding service. This way, the
binding table can be updated on all peer nodes in one shot.
Broadcast is used when all peer nodes, as indicated by a new capability
flag TIPC_NAMED_BCAST, support reception of this message type.
Four problems need to be considered when introducing this feature.
1) When establishing a link to a new peer node we still update this by a
unicast 'bulk' update. This may lead to race conditions, where a later
broadcast publication/withdrawal bypass the 'bulk', resulting in
disordered publications, or even that a withdrawal may arrive before the
corresponding publication. We solve this by adding an 'is_last_bulk' bit
in the last bulk messages so that it can be distinguished from all other
messages. Only when this message has arrived do we open up for reception
of broadcast publications/withdrawals.
2) When a first legacy node is added to the cluster all distribution
will switch over to use the legacy 'replicast' method, while the
opposite happens when the last legacy node leaves the cluster. This
entails another risk of message disordering that has to be handled. We
solve this by adding a sequence number to the broadcast/replicast
messages, so that disordering can be discovered and corrected. Note
however that we don't need to consider potential message loss or
duplication at this protocol level.
3) Bulk messages don't contain any sequence numbers, and will always
arrive in order. Hence we must exempt those from the sequence number
control and deliver them unconditionally. We solve this by adding a new
'is_bulk' bit in those messages so that they can be recognized.
4) Legacy messages, which don't contain any new bits or sequence
numbers, but neither can arrive out of order, also need to be exempt
from the initial synchronization and sequence number check, and
delivered unconditionally. Therefore, we add another 'is_not_legacy' bit
to all new messages so that those can be distinguished from legacy
messages and the latter delivered directly.
v1->v2:
- fix warning issue reported by kbuild test robot <lkp@intel.com>
- add santiy check to drop the publication message with a sequence
number that is lower than the agreed synch point
Signed-off-by: kernel test robot <lkp@intel.com>
Signed-off-by: Hoang Huu Le <hoang.h.le@dektech.com.au>
Acked-by: Jon Maloy <jmaloy@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, TIPC transports intra-node user data messages directly
socket to socket, hence shortcutting all the lower layers of the
communication stack. This gives TIPC very good intra node performance,
both regarding throughput and latency.
We now introduce a similar mechanism for TIPC data traffic across
network namespaces located in the same kernel. On the send path, the
call chain is as always accompanied by the sending node's network name
space pointer. However, once we have reliably established that the
receiving node is represented by a namespace on the same host, we just
replace the namespace pointer with the receiving node/namespace's
ditto, and follow the regular socket receive patch though the receiving
node. This technique gives us a throughput similar to the node internal
throughput, several times larger than if we let the traffic go though
the full network stacks. As a comparison, max throughput for 64k
messages is four times larger than TCP throughput for the same type of
traffic.
To meet any security concerns, the following should be noted.
- All nodes joining a cluster are supposed to have been be certified
and authenticated by mechanisms outside TIPC. This is no different for
nodes/namespaces on the same host; they have to auto discover each
other using the attached interfaces, and establish links which are
supervised via the regular link monitoring mechanism. Hence, a kernel
local node has no other way to join a cluster than any other node, and
have to obey to policies set in the IP or device layers of the stack.
- Only when a sender has established with 100% certainty that the peer
node is located in a kernel local namespace does it choose to let user
data messages, and only those, take the crossover path to the receiving
node/namespace.
- If the receiving node/namespace is removed, its namespace pointer
is invalidated at all peer nodes, and their neighbor link monitoring
will eventually note that this node is gone.
- To ensure the "100% certainty" criteria, and prevent any possible
spoofing, received discovery messages must contain a proof that the
sender knows a common secret. We use the hash mix of the sending
node/namespace for this purpose, since it can be accessed directly by
all other namespaces in the kernel. Upon reception of a discovery
message, the receiver checks this proof against all the local
namespaces'hash_mix:es. If it finds a match, that, along with a
matching node id and cluster id, this is deemed sufficient proof that
the peer node in question is in a local namespace, and a wormhole can
be opened.
- We should also consider that TIPC is intended to be a cluster local
IPC mechanism (just like e.g. UNIX sockets) rather than a network
protocol, and hence we think it can justified to allow it to shortcut the
lower protocol layers.
Regarding traceability, we should notice that since commit 6c9081a391
("tipc: add loopback device tracking") it is possible to follow the node
internal packet flow by just activating tcpdump on the loopback
interface. This will be true even for this mechanism; by activating
tcpdump on the involved nodes' loopback interfaces their inter-name
space messaging can easily be tracked.
v2:
- update 'net' pointer when node left/rejoined
v3:
- grab read/write lock when using node ref obj
v4:
- clone traffics between netns to loopback
Suggested-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Hoang Le <hoang.h.le@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
The policy for handling the skb list locks on the send and receive paths
is simple.
- On the send path we never need to grab the lock on the 'xmitq' list
when the destination is an exernal node.
- On the receive path we always need to grab the lock on the 'inputq'
list, irrespective of source node.
However, when transmitting node local messages those will eventually
end up on the receive path of a local socket, meaning that the argument
'xmitq' in tipc_node_xmit() will become the 'ínputq' argument in the
function tipc_sk_rcv(). This has been handled by always initializing
the spinlock of the 'xmitq' list at message creation, just in case it
may end up on the receive path later, and despite knowing that the lock
in most cases never will be used.
This approach is inaccurate and confusing, and has also concealed the
fact that the stated 'no lock grabbing' policy for the send path is
violated in some cases.
We now clean up this by never initializing the lock at message creation,
instead doing this at the moment we find that the message actually will
enter the receive path. At the same time we fix the four locations
where we incorrectly access the spinlock on the send/error path.
This patch also reverts commit d12cffe932 ("tipc: ensure head->lock
is initialised") which has now become redundant.
CC: Eric Dumazet <edumazet@google.com>
Reported-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
tipc_named_node_up() creates a skb list. It passes the list to
tipc_node_xmit() which has some code paths that can call
skb_queue_purge() which relies on the list->lock being initialised.
The spin_lock is only needed if the messages end up on the receive path
but when the list is created in tipc_named_node_up() we don't
necessarily know if it is going to end up there.
Once all the skb list users are updated in tipc it will then be possible
to update them to use the unlocked variants of the skb list functions
and initialise the lock when we know the message will follow the receive
path.
Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We have seen the following race scenario:
1) named_distribute() builds a "bulk" message, containing a PUBLISH
item for a certain publication. This is based on the contents of
the binding tables's 'cluster_scope' list.
2) tipc_named_withdraw() removes the same publication from the list,
bulds a WITHDRAW message and distributes it to all cluster nodes.
3) tipc_named_node_up(), which was calling named_distribute(), sends
out the bulk message built under 1)
4) The WITHDRAW message arrives at the just detected node, finds
no corresponding publication, and is dropped.
5) The PUBLISH item arrives at the same node, is added to its binding
table, and remains there forever.
This arrival disordering was earlier taken care of by the backlog queue,
originally added for a different purpose, which was removed in the
commit referred to below, but we now need a different solution.
In this commit, we replace the rcu lock protecting the 'cluster_scope'
list with a regular RW lock which comprises even the sending of the
bulk message. This both guarantees both the list integrity and the
message sending order. We will later add a commit which cleans up
this code further.
Note that this commit needs recently added commit d3092b2efc ("tipc:
fix unsafe rcu locking when accessing publication list") to apply
cleanly.
Fixes: 37922ea4a3 ("tipc: permit overlapping service ranges in name table")
Reported-by: Tuong Lien Tong <tuong.t.lien@dektech.com.au>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The binding table's 'cluster_scope' list is rcu protected to handle
races between threads changing the list and those traversing the list at
the same moment. We have now found that the function named_distribute()
uses the regular list_for_each() macro to traverse the said list.
Likewise, the function tipc_named_withdraw() is removing items from the
same list using the regular list_del() call. When these two functions
execute in parallel we see occasional crashes.
This commit fixes this by adding the missing _rcu() suffixes.
Signed-off-by: Tung Nguyen <tung.q.nguyen@dektech.com.au>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With the new RB tree structure for service ranges it becomes possible to
solve an old problem; - we can now allow overlapping service ranges in
the table.
When inserting a new service range to the tree, we use 'lower' as primary
key, and when necessary 'upper' as secondary key.
Since there may now be multiple service ranges matching an indicated
'lower' value, we must also add the 'upper' value to the functions
used for removing publications, so that the correct, corresponding
range item can be found.
These changes guarantee that a well-formed publication/withdrawal item
from a peer node never will be rejected, and make it possible to
eliminate the problematic backlog functionality we currently have for
handling such cases.
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We add a 128-bit node identity, as an alternative to the currently used
32-bit node address.
For the sake of compatibility and to minimize message header changes
we retain the existing 32-bit address field. When not set explicitly by
the user, this field will be filled with a hash value generated from the
much longer node identity, and be used as a shorthand value for the
latter.
We permit either the address or the identity to be set by configuration,
but not both, so when the address value is set by a legacy user the
corresponding 128-bit node identity is generated based on the that value.
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As a preparation to changing the addressing structure of TIPC we replace
all direct accesses to the tipc_net::own_addr field with the function
dedicated for this, tipc_own_addr().
There are no changes to program logics in this commit.
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We rename some lists and fields in struct publication both to make
the naming more consistent and to better reflect their roles. We
also update the descriptions of those lists.
node_list -> local_publ
cluster_list -> all_publ
pport_list -> binding_sock
ref -> port
There are no functional changes in this commit.
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The size of struct publication can be reduced further. Membership in
lists 'nodesub_list' and 'local_list' is mutually exlusive, in that
remote publications use the former and local publications the latter.
We replace the two lists with one single, named 'binding_node' which
reflects what it really is.
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As a consequence of the previous commit we nan now eliminate zone scope
related lists in the name table. We start with name_table::publ_list[3],
which can now be replaced with two lists, one for node scope publications
and one for cluster scope publications.
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Until now, we allocate memory always with GFP_ATOMIC flag.
When the system is under memory pressure and a user tries to send,
the send fails due to low memory. However, the user application
can wait for free memory if we allocate it using GFP_KERNEL flag.
In this commit, we use allocate memory with GFP_KERNEL for all user
allocation.
Reported-by: Rune Torgersen <runet@innovsys.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In commit 2d18ac4ba7 ("tipc: extend broadcast link initialization
criteria") we tried to fix a problem with the initial synchronization
of broadcast link acknowledge values. Unfortunately that solution is
not sufficient to solve the issue.
We have seen it happen that LINK_PROTOCOL/STATE packets with a valid
non-zero unicast acknowledge number may bypass BCAST_PROTOCOL
initialization, NAME_DISTRIBUTOR and other STATE packets with invalid
broadcast acknowledge numbers, leading to premature opening of the
broadcast link. When the bypassed packets finally arrive, they are
inadvertently accepted, and the already correctly initialized
acknowledge number in the broadcast receive link is overwritten by
the invalid (zero) value of the said packets. After this the broadcast
link goes stale.
We now fix this by marking the packets where we know the acknowledge
value is or may be invalid, and then ignoring the acks from those.
To this purpose, we claim an unused bit in the header to indicate that
the value is invalid. We set the bit to 1 in the initial BCAST_PROTOCOL
synchronization packet and all initial ("bulk") NAME_DISTRIBUTOR
packets, plus those LINK_PROTOCOL packets sent out before the broadcast
links are fully synchronized.
This minor protocol update is fully backwards compatible.
Reported-by: John Thompson <thompa.atl@gmail.com>
Tested-by: John Thompson <thompa.atl@gmail.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In a dual bearer configuration, if the second tipc link becomes
active while the first link still has pending nametable "bulk"
updates, it randomly leads to reset of the second link.
When a link is established, the function named_distribute(),
fills the skb based on node mtu (allows room for TUNNEL_PROTOCOL)
with NAME_DISTRIBUTOR message for each PUBLICATION.
However, the function named_distribute() allocates the buffer by
increasing the node mtu by INT_H_SIZE (to insert NAME_DISTRIBUTOR).
This consumes the space allocated for TUNNEL_PROTOCOL.
When establishing the second link, the link shall tunnel all the
messages in the first link queue including the "bulk" update.
As size of the NAME_DISTRIBUTOR messages while tunnelling, exceeds
the link mtu the transmission fails (-EMSGSIZE).
Thus, the synch point based on the message count of the tunnel
packets is never reached leading to link timeout.
In this commit, we adjust the size of name distributor message so that
they can be tunnelled.
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Parthasarathy Bhuvaragan <parthasarathy.bhuvaragan@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If a peer node becomes unavailable, in addition to removing the
nametable entries from this node we also need to purge all deferred
updates associated with this node.
Signed-off-by: Erik Hugne <erik.hugne@gmail.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Nametable updates received from the network that cannot be applied
immediately are placed on a defer queue. This queue is global to the
TIPC module, which might cause problems when using TIPC in containers.
To prevent nametable updates from escaping into the wrong namespace,
we make the queue pernet instead.
Signed-off-by: Erik Hugne <erik.hugne@gmail.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The file name_distr.c currently contains three functions,
named_cluster_distribute(), tipc_publ_subcscribe() and
tipc_publ_unsubscribe() that all directly access fields in
struct tipc_node. We want to eliminate such dependencies, so
we move those functions to the file node.c and rename them to
tipc_node_broadcast(), tipc_node_subscribe() and tipc_node_unsubscribe()
respectively.
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In commit 5cbb28a4bf ("tipc: linearize arriving NAME_DISTR
and LINK_PROTO buffers") we added linearization of NAME_DISTRIBUTOR,
LINK_PROTOCOL/RESET and LINK_PROTOCOL/ACTIVATE to the function
tipc_udp_recv(). The location of the change was selected in order
to make the commit easily appliable to 'net' and 'stable'.
We now move this linearization to where it should be done, in the
functions tipc_named_rcv() and tipc_link_proto_rcv() respectively.
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Correct synchronization of the broadcast link at first contact between
two nodes is dependent on the assumption that the binding table "bulk"
update passes via the same link as the initial broadcast syncronization
message, i.e., via the first link that is established.
This is not guaranteed in the current implementation. If two link
come up very close to each other in time, the "bulk" may quite well
pass via the second link, and hence void the guarantee of a correct
initial synchronization before the broadcast link is opened.
This commit makes two small changes to strengthen this guarantee.
1) We let the second established link occupy slot 1 of the
"active_links" array, while the first link will retain slot 0.
(This is in reality a cosmetic change, we could just as well keep
the current, opposite order)
2) We let the name distributor always use link selector/slot 0 when
it sends it binding table updates.
The extra traffic bias on the first link caused by this change should
be negligible, since binding table updates constitutes a very small
fraction of the total traffic.
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>
Currently, message sending is performed through a deep call chain,
where the node spinlock is grabbed and held during a significant
part of the transmission time. This is clearly detrimental to
overall throughput performance; it would be better if we could send
the message after the spinlock has been released.
In this commit, we do instead let the call revert on the stack after
the buffer chain has been added to the transmission queue, whereafter
clones of the buffers are transmitted to the device layer outside the
spinlock scope.
As a further step in our effort to separate the roles of the node
and link entities we also move the function tipc_link_xmit() to
node.c, and rename it to tipc_node_xmit().
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
struct 'tipc_node' currently contains two arrays for link attributes,
one for the link pointers, and one for the usable link MTUs.
We now group those into a new struct 'tipc_link_entry', and intoduce
one single array consisting of such enties. Apart from being a cosmetic
improvement, this is a starting point for the strict master-slave
relation between node and link that we will introduce in the following
commits.
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
TIPC node hash node table is protected with rcu lock on read side.
tipc_node_find() is used to look for a node object with node address
through iterating the hash node table. As the entire process of what
tipc_node_find() traverses the table is guarded with rcu read lock,
it's safe for us. However, when callers use the node object returned
by tipc_node_find(), there is no rcu read lock applied. Therefore,
this is absolutely unsafe for callers of tipc_node_find().
Now we introduce a reference counter for node structure. Before
tipc_node_find() returns node object to its caller, it first increases
the reference counter. Accordingly, after its caller used it up,
it decreases the counter again. This can prevent a node being used by
one thread from being freed by another thread.
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericson.com>
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The TIPC name distributor pushes topology updates to the cluster
neighbors. Currently this is done in a unicast manner, and the
skb holding the update is cloned for each cluster member. This
is unnecessary, as we only modify the destnode field in the header
so we change it to do pskb_copy instead.
Signed-off-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 handles message cardinality and sequencing at the link layer,
before passing messages upwards to the destination sockets. During the
upcall from link to socket no locks are held. It is therefore possible,
and we see it happen occasionally, that messages arriving in different
threads and delivered in sequence still bypass each other before they
reach the destination socket. This must not happen, since it violates
the sequentiality guarantee.
We solve this by adding a new input buffer queue to the link structure.
Arriving messages are added safely to the tail of that queue by the
link, while the head of the queue is consumed, also safely, by the
receiving socket. Sequentiality is secured per socket by only allowing
buffers to be dequeued inside the socket lock. Since there may be multiple
simultaneous readers of the queue, we use a 'filter' parameter to reduce
the risk that they peek the same buffer from the queue, hence also
reducing the risk of contention on the receiving socket locks.
This solves the sequentiality problem, and seems to cause no measurable
performance degradation.
A nice side effect of this change is that lock handling in the functions
tipc_rcv() and tipc_bcast_rcv() now becomes uniform, something that
will enable future simplifications of those functions.
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The most common usage of namespace information is when we fetch the
own node addess from the net structure. This leads to a lot of
passing around of a parameter of type 'struct net *' between
functions just to make them able to obtain this address.
However, in many cases this is unnecessary. The own node address
is readily available as a member of both struct tipc_sock and
tipc_link, and can be fetched from there instead.
The fact that the vast majority of functions in socket.c and link.c
anyway are maintaining a pointer to their respective base structures
makes this option even more compelling.
In this commit, we introduce the inline functions tsk_own_node()
and link_own_node() to make it easy for functions to fetch the node
address from those structs instead of having to pass along and
dereference the namespace struct.
In particular, we make calls to the msg_xx() functions in msg.{h,c}
context independent by directly passing them the own node address
as parameter when needed. Those functions should be regarded as
leaves in the code dependency tree, and it is hence desirable to
keep them namspace unaware.
Apart from a potential positive effect on cache behavior, these
changes make it easier to introduce the changes that will follow
later in this series.
Reviewed-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If net namespace is supported in tipc, each namespace will be treated
as a separate tipc node. Therefore, every namespace must own its
private tipc node address. This means the "tipc_own_addr" global
variable of node address must be moved to tipc_net structure to
satisfy the requirement. It's turned out that users also can assign
node address for every namespace.
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Tested-by: Tero Aho <Tero.Aho@coriant.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
TIPC name table is used to store the mapping relationship between
TIPC service name and socket port ID. When tipc supports namespace,
it allows users to publish service names only owned by a certain
namespace. Therefore, every namespace must have its private name
table to prevent service names published to one namespace from being
contaminated by other service names in another namespace. Therefore,
The name table global variable (ie, nametbl) and its lock must be
moved to tipc_net structure, and a parameter of namespace must be
added for necessary functions so that they can obtain name table
variable defined in tipc_net structure.
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Tested-by: Tero Aho <Tero.Aho@coriant.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Global variables associated with node table are below:
- node table list (node_htable)
- node hash table list (tipc_node_list)
- node table lock (node_list_lock)
- node number counter (tipc_num_nodes)
- node link number counter (tipc_num_links)
To make node table support namespace, above global variables must be
moved to tipc_net structure in order to keep secret for different
namespaces. As a consequence, these variables are allocated and
initialized when namespace is created, and deallocated when namespace
is destroyed. After the change, functions associated with these
variables have to utilize a namespace pointer to access them. So
adding namespace pointer as a parameter of these functions is the
major change made in the commit.
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Tested-by: Tero Aho <Tero.Aho@coriant.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Convert tipc name table read-write lock to RCU. After this change,
a new spin lock is used to protect name table on write side while
RCU is applied on read side.
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>
Tested-by: Erik Hugne <erik.hugne@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Name table locking policy is going to be adjusted from read-write
lock protection to RCU lock protection in the future commits. But
its essential precondition is to convert the allocation way of name
table from static to dynamic mode.
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>
Tested-by: Erik Hugne <erik.hugne@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The size variable is introduced in publ_list struct to help us exactly
calculate SKB buffer sizes needed by publications when all publications
in name table are delivered in bulk in named_distribute(). But if
publication SKB buffer size is assumed to MTU, the size variable in
publ_list struct can be completely eliminated at the cost of wasting
a bit memory space for last SKB.
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Tero Aho <tero.aho@coriant.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Tested-by: Erik Hugne <erik.hugne@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use standard SKB list APIs associated with struct sk_buff_head to
manage socket outgoing packet chain and name table outgoing packet
chain, having relevant code simpler and more readable.
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>
The node subscribe infrastructure represents a virtual base class, so
its users, such as struct tipc_port and struct publication, can derive
its implemented functionalities. However, after the removal of struct
tipc_port, struct publication is left as its only single user now. So
defining an abstract infrastructure for one user becomes no longer
reasonable. If corresponding new functions associated with the
infrastructure are moved to name_table.c file, the node subscription
infrastructure can be removed as well.
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>
This fixes the following sparse warnings:
sparse: symbol 'tipc_update_nametbl' was not declared. Should it be static?
Also, the function is changed to return bool upon success, rather than a
potentially freed pointer.
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>
TIPC name table updates are distributed asynchronously in a cluster,
entailing a risk of certain race conditions. E.g., if two nodes
simultaneously issue conflicting (overlapping) publications, this may
not be detected until both publications have reached a third node, in
which case one of the publications will be silently dropped on that
node. Hence, we end up with an inconsistent name table.
In most cases this conflict is just a temporary race, e.g., one
node is issuing a publication under the assumption that a previous,
conflicting, publication has already been withdrawn by the other node.
However, because of the (rtt related) distributed update delay, this
may not yet hold true on all nodes. The symptom of this failure is a
syslog message: "tipc: Cannot publish {%u,%u,%u}, overlap error".
In this commit we add a resiliency queue at the receiving end of
the name table distributor. When insertion of an arriving publication
fails, we retain it in this queue for a short amount of time, assuming
that another update will arrive very soon and clear the conflict. If so
happens, we insert the publication, otherwise we drop it.
The (configurable) retention value defaults to 2000 ms. Knowing from
experience that the situation described above is extremely rare, there
is no risk that the queue will accumulate any large number of items.
Signed-off-by: Erik Hugne <erik.hugne@ericsson.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We need to perform the same actions when processing deferred name
table updates, so this functionality is moved to a separate
function.
Signed-off-by: Erik Hugne <erik.hugne@ericsson.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After the previous commit, we can now give the functions with temporary
names, such as tipc_link_xmit2(), tipc_msg_build2() etc., their proper
names.
There are no functional changes in this commit.
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>
Postpone the actions of delivering name tables until after node
lock is released, avoiding to do it under asynchronous context.
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>
Although we obtain node lock with tipc_node_lock() in most time, there
are still places where we directly use native spin lock interface
to grab node lock. But as we will do more jobs in the future when node
lock is released, we should ensure that tipc_node_lock() is always
called when node lock is taken.
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 a89778d8ba ("tipc: add support
for link state subscriptions") introduced below possible deadlock
scenario:
CPU0 CPU1
T0: tipc_publish() link_timeout()
T1: tipc_nametbl_publish() [grab node lock]*
T2: [grab nametbl write lock]* link_state_event()
T3: named_cluster_distribute() link_activate()
T4: [grab node lock]* tipc_node_link_up()
T5: tipc_nametbl_publish()
T6: [grab nametble write lock]*
The opposite order of holding nametbl write lock and node lock on
above two different paths may result in a deadlock. If we move the
the delivery of named messages via link out of name nametbl lock,
the reverse order of holding locks will be eliminated, as a result,
the deadlock will be killed as well.
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Erik Hugne <erik.hugne@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>
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>
The 'tipc_node_list' is guarded by tipc_net_lock and 'links' array
defined in 'tipc_node' structure is protected by node lock as well.
Without acquiring the two locks in named_cluster_distribute() a fatal
oops may happen in case that a destroyed link might be got and then
accessed. Therefore, above mentioned two locks must be held in
named_cluster_distribute() to prevent the issue from happening
accidentally.
As 'links' array in node struct must be protected by node lock,
we have to move the code of selecting an active link from
tipc_link_xmit() to named_cluster_distribute() and then call
__tipc_link_xmit() with the selected link to deliver name messages.
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>
As the variable:node is currently defined to u32 type, it is
unnecessary to cast its type to u32 again when using it.
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
