Move cma.c's internal definition of enum cma_state to enum rdma_cm_state
in an exported header so that it can be exported via RDMA netlink.
Signed-off-by: Nir Muchtar <nirm@voltaire.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
Add basic RDMA netlink infrastructure that allows for registration of
RDMA clients for which data is to be exported and supplies message
construction callbacks.
Signed-off-by: Nir Muchtar <nirm@voltaire.com>
[ Reorganize a few things, add CONFIG_NET dependency. - Roland ]
Signed-off-by: Roland Dreier <roland@purestorage.com>
The IW_CM_EVENT_STATUS_xxx values were used in only a couple of places;
cma.c uses -Exxx values instead, and so do the amso1100, cxgb3 and cxgb4
drivers -- only nes was using the enum values (with the mild consequence
that all nes connection failures were treated as generic errors rather
than reported as timeouts or rejections).
We can fix this confusion by getting rid of enum iw_cm_event_status and
using a plain int for struct iw_cm_event.status, and converting nes to
use -Exxx as the other iWARP drivers do.
This also gets rid of the warning
drivers/infiniband/core/cma.c: In function 'cma_iw_handler':
drivers/infiniband/core/cma.c:1333:3: warning: case value '4294967185' not in enumerated type 'enum iw_cm_event_status'
drivers/infiniband/core/cma.c:1336:3: warning: case value '4294967186' not in enumerated type 'enum iw_cm_event_status'
drivers/infiniband/core/cma.c:1332:3: warning: case value '4294967192' not in enumerated type 'enum iw_cm_event_status'
Signed-off-by: Roland Dreier <roland@purestorage.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Sean Hefty <sean.hefty@intel.com>
Reviewed-by: Faisal Latif <faisal.latif@intel.com>
Lustre requires that clients bind to a privileged port number before
connecting to a remote server. On larger clusters (typically more
than about 1000 nodes), the number of privileged ports is exhausted,
resulting in lustre being unusable.
To handle this, we add support for reusable addresses to the rdma_cm.
This mimics the behavior of the socket option SO_REUSEADDR. A user
may set an rdma_cm_id to reuse an address before calling
rdma_bind_addr() (explicitly or implicitly). If set, other
rdma_cm_id's may be bound to the same address, provided that they all
have reuse enabled, and there are no active listens.
If rdma_listen() is called on an rdma_cm_id that has reuse enabled, it
will only succeed if there are no other id's bound to that same
address. The reuse option is exported to user space. The behavior of
the kernel reuse implementation was verified against that given by
sockets.
This patch is derived from a path by Ira Weiny <weiny2@llnl.gov>
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
cma_use_port() assumes that the sockaddr is an IPv4 address. Since
IPv6 addressing is supported (and also to support other address
families) make the code more generic in its address handling.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
Commit b23dd4fe42 ("ipv4: Make output route lookup return rtable
directly") resulted in leaving ret uninitialized, where it may later
be returned.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6: (1480 commits)
bonding: enable netpoll without checking link status
xfrm: Refcount destination entry on xfrm_lookup
net: introduce rx_handler results and logic around that
bonding: get rid of IFF_SLAVE_INACTIVE netdev->priv_flag
bonding: wrap slave state work
net: get rid of multiple bond-related netdevice->priv_flags
bonding: register slave pointer for rx_handler
be2net: Bump up the version number
be2net: Copyright notice change. Update to Emulex instead of ServerEngines
e1000e: fix kconfig for crc32 dependency
netfilter ebtables: fix xt_AUDIT to work with ebtables
xen network backend driver
bonding: Improve syslog message at device creation time
bonding: Call netif_carrier_off after register_netdevice
bonding: Incorrect TX queue offset
net_sched: fix ip_tos2prio
xfrm: fix __xfrm_route_forward()
be2net: Fix UDP packet detected status in RX compl
Phonet: fix aligned-mode pipe socket buffer header reserve
netxen: support for GbE port settings
...
Fix up conflicts in drivers/staging/brcm80211/brcmsmac/wl_mac80211.c
with the staging updates.
rdma_destroy_id currently uses the global rdma cm 'lock' to test if an
rdma_cm_id has been bound to a device. This prevents an active
address resolution callback handler from assigning a device to the
rdma_cm_id after rdma_destroy_id checks for one.
Instead, we can replace the use of the global lock around the check to
the rdma_cm_id device pointer by setting the id state to destroying,
then flushing all active callbacks. The latter is accomplished by
acquiring and releasing the handler_mutex. Any active handler will
complete first, and any newly scheduled handlers will find the
rdma_cm_id in an invalid state.
In addition to optimizing the current locking scheme, the use of the
rdma_cm_id mutex is a more intuitive synchronization mechanism than
that of the global lock. These changes are based on feedback from
Doug Ledford <dledford@redhat.com> while he was trying to debug a
crash in the rdma cm destroy path.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
This problem was reported by Moni Shoua <monis@mellanox.com> and Amir
Vadai <amirv@mellanox.com>:
When destroying a cm_id from a context of a work queue and if
the lap_state of this cm_id is IB_CM_LAP_SENT, we need to
release the reference of this id that was taken upon the send
of the LAP message. Otherwise, if the expected APR message
gets lost, it is only after a long time that the reference
will be released, while during that the work handler thread is
not available to process other things.
It turns out that we need to cancel any pending LAP messages whenever
we transition out of the IB_CM_ESTABLISH state. This occurs when
disconnecting - either sending or receiving a DREQ. It can also
happen in a corner case where we receive a REJ message after sending
an RTU, followed by a LAP. Add checks and cancel any outstanding LAP
messages in these three cases.
Canceling the LAP when sending a DREQ fixes the destroy problem
reported by Moni. When a cm_id is destroyed in the IB_CM_ESTABLISHED
state, it sends a DREQ to the remote side to notify the peer that the
connection is going away.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
When processing a SIDR REQ, the ib_cm allocates a new cm_id. The
refcount of the cm_id is initialized to 1. However, cm_process_work
will decrement the refcount after invoking all callbacks. The result
is that the cm_id will end up with refcount set to 0 by the end of the
sidr req handler.
If a user tries to destroy the cm_id, the destruction will proceed,
under the incorrect assumption that no other threads are referencing
the cm_id. This can lead to a crash when the cm callback thread tries
to access the cm_id.
This problem was noticed as part of a larger investigation with kernel
crashes in the rdma_cm when running on a real time OS.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Acked-by: Doug Ledford <dledford@redhat.com>
Cc: <stable@kernel.org>
Signed-off-by: Roland Dreier <roland@purestorage.com>
Doug Ledford and Red Hat reported a crash when running the rdma_cm on
a real-time OS. The crash has the following call trace:
cm_process_work
cma_req_handler
cma_disable_callback
rdma_create_id
kzalloc
init_completion
cma_get_net_info
cma_save_net_info
cma_any_addr
cma_zero_addr
rdma_translate_ip
rdma_copy_addr
cma_acquire_dev
rdma_addr_get_sgid
ib_find_cached_gid
cma_attach_to_dev
ucma_event_handler
kzalloc
ib_copy_ah_attr_to_user
cma_comp
[ preempted ]
cma_write
copy_from_user
ucma_destroy_id
copy_from_user
_ucma_find_context
ucma_put_ctx
ucma_free_ctx
rdma_destroy_id
cma_exch
cma_cancel_operation
rdma_node_get_transport
rt_mutex_slowunlock
bad_area_nosemaphore
oops_enter
They were able to reproduce the crash multiple times with the
following details:
Crash seems to always happen on the:
mutex_unlock(&conn_id->handler_mutex);
as conn_id looks to have been freed during this code path.
An examination of the code shows that a race exists in the request
handlers. When a new connection request is received, the rdma_cm
allocates a new connection identifier. This identifier has a single
reference count on it. If a user calls rdma_destroy_id() from another
thread after receiving a callback, rdma_destroy_id will proceed to
destroy the id and free the associated memory. However, the request
handlers may still be in the process of running. When control returns
to the request handlers, they can attempt to access the newly created
identifiers.
Fix this by holding a reference on the newly created rdma_cm_id until
the request handler is through accessing it.
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Acked-by: Doug Ledford <dledford@redhat.com>
Cc: <stable@kernel.org>
Signed-off-by: Roland Dreier <roland@purestorage.com>
I intend to turn struct flowi into a union of AF specific flowi
structs. There will be a common structure that each variant includes
first, much like struct sock_common.
This is the first step to move in that direction.
Signed-off-by: David S. Miller <davem@davemloft.net>
The idea here is this minimizes the number of places one has to edit
in order to make changes to how flows are defined and used.
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit f06267104d ("RDMA: Update workqueue usage") introduced ib_wq
and removed the use of flush_scheduled_work(); however, during the merge
process one chunk was lost in ib_sa_remove_one(). Fix it.
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Roland Dreier <roland@purestorage.com>
For iWARP rdma_cm ids, the "route" information is the L2 src and
next hop addresses.
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
* ib_wq is added, which is used as the common workqueue for infiniband
instead of the system workqueue. All system workqueue usages
including flush_scheduled_work() callers are converted to use and
flush ib_wq.
* cancel_delayed_work() + flush_scheduled_work() converted to
cancel_delayed_work_sync().
* qib_wq is removed and ib_wq is used instead.
This is to prepare for deprecation of flush_scheduled_work().
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
In ib_uverbs_poll_cq() code there is a potential integer overflow if
userspace passes in a large cmd.ne. The calls to kmalloc() would
allocate smaller buffers than intended, leading to memory corruption.
There iss also an information leak if resp wasn't all used.
Unprivileged userspace may call this function, although only if an
RDMA device that uses this function is present.
Fix this by copying CQ entries one at a time, which avoids the
allocation entirely, and also by moving this copying into a function
that makes sure to initialize all memory copied to userspace.
Special thanks to Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
for his help and advice.
Cc: <stable@kernel.org>
Signed-off-by: Dan Carpenter <error27@gmail.com>
[ Monkey around with things a bit to avoid bad code generation by gcc
when designated initializers are used. - Roland ]
Signed-off-by: Roland Dreier <rolandd@cisco.com>
ib_ucm_init_qp_attr() and ucma_init_qp_attr() pass struct ib_uverbs_qp_attr
with reserved, qp_state, {ah_attr,alt_ah_attr}{reserved,->grh.reserved}
fields uninitialized to copy_to_user(). This leads to leaking of
contents of kernel stack memory to userspace.
Signed-off-by: Vasiliy Kulikov <segoon@openwall.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
dev_base_lock is the legacy way to lock the device list, and is planned
to disappear. (writers hold RTNL, readers hold RCU lock)
Convert rdma_translate_ip() and update_ipv6_gids() to RCU locking.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It seems idev field in struct rtable has no special purpose, but adding
extra atomic ops.
We hold refcounts on the device itself (using percpu data, so pretty
cheap in current kernel).
infiniband case is solved using dst.dev instead of idev->dev
Removal of this field means routing without route cache is now using
shared data, percpu data, and only potential contention is a pair of
atomic ops on struct neighbour per forwarded packet.
About 5% speedup on routing test.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Roland Dreier <rolandd@cisco.com>
Cc: Sean Hefty <sean.hefty@intel.com>
Cc: Hal Rosenstock <hal.rosenstock@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since an IB transport port may use either IB or Ethernet as its link layer,
add the file /sys/class/infiniband/<device>/ports/<port_num>/link_layer to
show the link layer for the port.
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Add 802.1q VLAN support to IBoE. The VLAN tag is encoded within the
GID derived from a link local address in the following way:
GID[11] GID[12] contain the VLAN ID when the GID contains a VLAN.
The 3 bits user priority field of the packets are identical to the 3
bits of the SL.
In case of rdma_cm apps, the TOS field is used to generate the SL
field by doing a shift right of 5 bits effectively taking to 3 MS bits
of the TOS field.
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
For iWARP connections, the connect request is carried in a TCP payload
on an already established TCP connection. So if the ucma's backlog is
full, the connection request is transmitted and acked at the TCP level
by the time the connect request gets dropped in the ucma. The end
result is the connection gets rejected by the iWARP provider.
Further, a 32 node 256NP OpenMPI job will generate > 128 connect
requests on some ranks.
This patch increases the default max backlog to 1024, and adds a
sysctl variable so the backlog can be adjusted at run time.
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Add support for packing IBoE packet headers.
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
[ Clean up and fix ib_ud_header_init() a bit. - Roland ]
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Add support for IBoE device binding and IP --> GID resolution. Path
resolving and multicast joining are implemented within cma.c by
filling in the responses and running callbacks in the CMA work queue.
IP --> GID resolution always yields IPv6 link local addresses; remote
GIDs are derived from the destination MAC address of the remote port.
Multicast GIDs are always mapped to multicast MACs as is done in IPv6.
(IPv4 multicast is enabled by translating IPv4 multicast addresses to
IPv6 multicast as described in
<http://www.mail-archive.com/ipng@sunroof.eng.sun.com/msg02134.html>.)
Some helper functions are added to ib_addr.h.
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Since IBoE is using Ethernet as its link layer, there is no central
management entity so there is need for QP0. QP1 is still needed since
it handles communications between CM agents. This patch will skip QP0
and create only QP1 for IBoE ports.
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
A process can get stuck in an uninterruptible wait in the
kernel while destroying a cm_id when iw_cm_connect() fails:
For example, When creation of a PD fails but the user continues with
an attempt to connect to the server without checking the return value,
in iw_cm_connect() a NULL qp is found so the call fails. However the
IWCM_F_CONNECT_WAIT bit is not cleared. destroy_cm_id() then waits
forever for IWCM_F_CONNECT_WAIT to be cleared.
The same problem exists on the passive side with the accept call.
Fix this by clearing the bit and waking up any waiters in the
appropriate spots.
Signed-off-by: Animesh Trivedi <atr@zurich.ibm.com>
Acked-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Get rid of init_MUTEX[_LOCKED]() and use sema_init() instead.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
This patch allows ports to have different link layers:
IB_LINK_LAYER_INFINIBAND or IB_LINK_LAYER_ETHERNET. This is required
for adding IBoE (InfiniBand-over-Ethernet, aka RoCE) support. For
devices that do not provide an implementation for querying the link
layer property of a port, we return a default value based on the
transport: RMA_TRANSPORT_IB nodes will return IB_LINK_LAYER_INFINIBAND
and RDMA_TRANSPORT_IWARP nodes will return IB_LINK_LAYER_ETHERNET.
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (42 commits)
IB/qib: Add missing <linux/slab.h> include
IB/ehca: Drop unnecessary NULL test
RDMA/nes: Fix confusing if statement indentation
IB/ehca: Init irq tasklet before irq can happen
RDMA/nes: Fix misindented code
RDMA/nes: Fix showing wqm_quanta
RDMA/nes: Get rid of "set but not used" variables
RDMA/nes: Read firmware version from correct place
IB/srp: Export req_lim via sysfs
IB/srp: Make receive buffer handling more robust
IB/srp: Use print_hex_dump()
IB: Rename RAW_ETY to RAW_ETHERTYPE
RDMA/nes: Fix two sparse warnings
RDMA/cxgb3: Make needlessly global iwch_l2t_send() static
IB/iser: Make needlessly global iser_alloc_rx_descriptors() static
RDMA/cxgb4: Add timeouts when waiting for FW responses
IB/qib: Fix race between qib_error_qp() and receive packet processing
IB/qib: Limit the number of packets processed per interrupt
IB/qib: Allow writes to the diag_counters to be able to clear them
IB/qib: Set cfgctxts to number of CPUs by default
...
Change abbreviated IB_QPT_RAW_ETY to IB_QPT_RAW_ETHERTYPE to make
the special QP type easier to understand.
cf http://www.mail-archive.com/linux-rdma@vger.kernel.org/msg04530.html
Signed-off-by: Aleksey Senin <alekseys@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
NULL pointer dereferences in ib_cm_init_qp_attr() were seen by some
users. From a crash dump, I determined that we died in
cm_init_qp_rts_attr() (it's inlined, so it doesn't show up in the
traceback) on the line labeled below:
static int cm_init_qp_rts_attr(struct cm_id_private *cm_id_priv,
struct ib_qp_attr *qp_attr,
int *qp_attr_mask)
{
........
if (cm_id_priv->id.lap_state == IB_CM_LAP_UNINIT) {
.....
} else {
*qp_attr_mask = IB_QP_ALT_PATH | IB_QP_PATH_MIG_STATE;
qp_attr->alt_port_num = cm_id_priv->alt_av.port->port_num; <-die
The problem is that the rdma_cm can call ib_send_cm_mra() after a
connection has been established. The ib_cm incorrectly assumes that
the MRA is in response to a LAP (load alternate path) message, even
though no LAP message has been received. The ib_cm needs to check the
lap_state before sending an MRA if the cm_id state is established.
Reported-by: Arthur Kepner <akepner@sgi.com>
Reported-by: Josh England <jjengla@gmail.com>
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
remove useless union keyword in rtable, rt6_info and dn_route.
Since there is only one member in a union, the union keyword isn't useful.
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use memdup_user when user data is immediately copied into the
allocated region.
The semantic patch that makes this change is as follows:
(http://coccinelle.lip6.fr/)
// <smpl>
@@
expression from,to,size,flag;
position p;
identifier l1,l2;
@@
- to = \(kmalloc@p\|kzalloc@p\)(size,flag);
+ to = memdup_user(from,size);
if (
- to==NULL
+ IS_ERR(to)
|| ...) {
<+... when != goto l1;
- -ENOMEM
+ PTR_ERR(to)
...+>
}
- if (copy_from_user(to, from, size) != 0) {
- <+... when != goto l2;
- -EFAULT
- ...+>
- }
// </smpl>
Signed-off-by: Julia Lawall <julia@diku.dk>
Add a new parameter to ib_register_device() so that low-level device
drivers can pass in a pointer to a callback function that will be
called for each port that is registered in sysfs. This allows
low-level device drivers to create files in
/sys/class/infiniband/<hca>/ports/<N>/
without having to poke through the internals of the RDMA sysfs handling.
There is no need for an unregister function since the kobject
reference will go to zero when ib_unregister_device() is called.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Use kmemdup when some other buffer is immediately copied into the
allocated region.
A simplified version of the semantic patch that makes this change is as
follows: (http://coccinelle.lip6.fr/)
// <smpl>
@@
expression from,to,size,flag;
statement S;
@@
- to = \(kmalloc\|kzalloc\)(size,flag);
+ to = kmemdup(from,size,flag);
if (to==NULL || ...) S
- memcpy(to, from, size);
// </smpl>
Signed-off-by: Julia Lawall <julia@diku.dk>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Randomize local port allocation in the way sctp_get_port_local() does.
Update rover at the end of loop since we're likely to pick a valid port
on the first try.
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Reviewed-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Nir Muchtar