The SRP initiator allows to set max_sectors to a value that exceeds
the largest amount of data that can be mapped at once with an mlx4
HCA using fast registration and a page size of 4 KB. Hence modify
ib_map_mr_sg() such that it can map partial sg-elements. If an
sg-element has been mapped partially, let the caller know
which fraction has been mapped by adjusting *sg_offset.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Tested-by: NLaurence Oberman <loberman@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Signed-off-by: NChristoph Hellwig <hch@lst.de>
Tested-by: NSteve Wise <swise@opengridcomputing.com>
Reviewed-by: NBart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: NSagi Grimberg <sagi@grimberg.me>
Reviewed-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Return the value from a call of the ocrdma_mbx_modify_qp() function
without using an extra assignment for the local variable "status".
Signed-off-by: NMarkus Elfring <elfring@users.sourceforge.net>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The variable "status" will be set to an appropriate value a bit later.
Thus let us omit the explicit initialisation at the beginning.
Signed-off-by: NMarkus Elfring <elfring@users.sourceforge.net>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

This patch adds following changes to support RoCE-v2
in the UD path.

 * During AH creation GID-type is resolved for a given gid-index.
 * Based on GID-type protocol header is built.
 * Work completion reports network header type and set
   IB_WC_WITH_NETWORK_HDR_TYPE flag in wc->wc_flags to indicate
   that the network header type is valid.
Signed-off-by: NSomnath Kotur <somnath.kotur@avagotech.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@avagotech.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Today ocrdma driver defer arming the CQ till poll is called.
This was used to prevent calling poll-cq on an armed CQ.

Recently a set of new CQ API has been introduced into the linux
kernel. The implementation of this API guarantees that a given
CQ is never armed before calling poll on it. Most of the kernel
ULPs have already moved to use this new API or have a code where
poll is called before arming the CQ.

Thus, the above workaround in ocrdma is not needed anymore.
This patch removes the additional logic to deffer arm till poll
is called. This patch adds a simple scheme where ib_req_notify_cq()
will actually arm the cq.
Signed-off-by: NDevesh Sharma <devesh.sharma@broadcom.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Currently returning the pkey value instead of pkey index.
pkey index is always zero since ocrdma supports only default
pkey.
Signed-off-by: NSelvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

max_sge_rd is used by some of the ULPs to calculate the maximum
number of SGEs that can be used for RDMA READ. Populating this
value in the response of query_device verb. Also, avoid checking
the max_srq_sge while populating max_sge.
Signed-off-by: NSelvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Recently Dough Ledford reported a deadlock happening
between ocrdma-load sequence and NetworkManager service
issuing "open" on be2net interface.

The deadlock happens when any be2net hook (e.g. open/close) is called
in parallel to insmod ocrdma.ko.

A. be2net is sending administrative open/close event to ocrdma holding
   device_list_mutex. It does this from ndo_open/ndo_stop hooks of be2net.
   So sequence of locks is rtnl_lock---> device_list lock

B.  When new ocrdma roce device gets registered, infiniband stack now
    takes rtnl_lock in ib_register_device() in GID initialization routines.
    So sequence of locks in this path is device_list lock ---> rtnl_lock.

This improper locking sequence causes deadlock.

With this patch we stop using administrative open and close events
injected by be2net driver. These events were used to dispatch PORT_ACTIVE
and PORT_ERROR events to the IB-stack. This patch implements a logic
to receive async-link-events generated from CNA whenever link-state-change
is detected. Now on, these async-events will be used to dispatch
PORT_ACTIVE and PORT_ERROR events to IB-stack.

Depending on async-events from CNA removes the need to hold device-list-mutex
and thus breaks the busy-wait scenario.
Reported-by: NDoug Ledford <dledford@redhat.com>
CC: Sathya Perla <sathya.perla@avagotech.com>
Signed-off-by: NPadmanabh Ratnakar <padmanabh.ratnakar@avagotech.com>
Signed-off-by: NSelvin Xavier <selvin.xavier@avagotech.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@avagotech.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Recently Dough Ledford reported a deadlock happening
between ocrdma-load sequence and NetworkManager service
issuing "open" on be2net interface.

The deadlock happens when any be2net hook (e.g. open/close) is called
in parallel to insmod ocrdma.ko.

A. be2net is sending administrative open/close event to ocrdma holding
   device_list_mutex. It does this from ndo_open/ndo_stop hooks of be2net.
   So sequence of locks is rtnl_lock---> device_list lock

B.  When new ocrdma roce device gets registered, infiniband stack now
    takes rtnl_lock in ib_register_device() in GID initialization routines.
    So sequence of locks in this path is device_list lock ---> rtnl_lock.

This improper locking sequence causes deadlock.

With this patch we stop using administrative open and close events
injected by be2net driver. These events were used to dispatch PORT_ACTIVE
and PORT_ERROR events to the IB-stack. This patch implements a logic
to receive async-link-events generated from CNA whenever link-state-change
is detected. Now on, these async-events will be used to dispatch
PORT_ACTIVE and PORT_ERROR events to IB-stack.

Depending on async-events from CNA removes the need to hold device-list-mutex
and thus breaks the busy-wait scenario.
Reported-by: NDoug Ledford <dledford@redhat.com>
CC: Sathya Perla <sathya.perla@avagotech.com>
Signed-off-by: NPadmanabh Ratnakar <padmanabh.ratnakar@avagotech.com>
Signed-off-by: NSelvin Xavier <selvin.xavier@avagotech.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@avagotech.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

We have stopped using phys MRs in the kernel a while ago, so let's
remove all the cruft used to implement them.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NSagi Grimberg <sagig@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com> [core]
Reviewed-By: Devesh Sharma<devesh.sharma@avagotech.com> [ocrdma]
Reviewed-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

No ULP uses it anymore, go ahead and remove it.
Signed-off-by: NSagi Grimberg <sagig@mellanox.com>
Acked-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Support the new memory registration API by allocating a
private page list array in ocrdma_mr and populate it when
ocrdma_map_mr_sg is invoked. Also, support IB_WR_REG_MR
by duplicating IB_WR_FAST_REG_MR, but take the needed
information from different places:
- page_size, iova, length, access flags (ib_mr)
- page array (ocrdma_mr)
- key (ib_reg_wr)

The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.
Signed-off-by: NSagi Grimberg <sagig@mellanox.com>
Acked-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Adding an ability to query the IB cache by a netdev and get the
attributes of a GID. These parameters are necessary in order to
successfully resolve the required GID (when the netdevice is known)
and get the Ethernet L2 attributes from a GID.
Signed-off-by: NMatan Barak <matanb@mellanox.com>
Reviewed-By: NDevesh Sharma <devesh.sharma@avagotech.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Changing CQ-Doorbell(DB) logic to prevent DB floods, it is supposed to be
pressed only if any hw CQE is polled. If cq-arm was requested
previously then don't bother about number of hw CQEs polled and
arm the CQ.
Signed-off-by: NDevesh Sharma <devesh.sharma@avagotech.com>
Signed-off-by: NSelvin Xavier <selvin.xavier@avagotech.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

This patch split up struct ib_send_wr so that all non-trivial verbs
use their own structure which embedds struct ib_send_wr.  This dramaticly
shrinks the size of a WR for most common operations:

sizeof(struct ib_send_wr) (old):	96

sizeof(struct ib_send_wr):		48
sizeof(struct ib_rdma_wr):		64
sizeof(struct ib_atomic_wr):		96
sizeof(struct ib_ud_wr):		88
sizeof(struct ib_fast_reg_wr):		88
sizeof(struct ib_bind_mw_wr):		96
sizeof(struct ib_sig_handover_wr):	80

And with Sagi's pending MR rework the fast registration WR will also be
down to a reasonable size:

sizeof(struct ib_fastreg_wr):		64
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com> [srp, srpt]
Reviewed-by: Chuck Lever <chuck.lever@oracle.com> [sunrpc]
Tested-by: NHaggai Eran <haggaie@mellanox.com>
Tested-by: NSagi Grimberg <sagig@mellanox.com>
Tested-by: NSteve Wise <swise@opengridcomputing.com>

1.Change query_gid hook to return value from IB/Core GID
  management APIs.
2.Get rid of all the netdev notifier chain subscription code as well
  as maintenance of SGID Table in memory.
3.Implement get_netdev hook in driver.
Signed-off-by: NSomnath Kotur <somnath.kotur@avagotech.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@avagotech.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Signed-off-by: NSagi Grimberg <sagig@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Change of license from GPLv2 to dual-license (GPLv2 and BSD 2-Clause)

All contributors were contacted off-list and permission to make this
change was received.  The complete list of contributors are Cc:ed here.

Cc: Tejun Heo <tj@kernel.org>
Cc: Duan Jiong <duanj.fnst@cn.fujitsu.com>
Cc: Roland Dreier <roland@purestorage.com>
Cc: Jes Sorensen <Jes.Sorensen@redhat.com>
Cc: Sasha Levin <levinsasha928@gmail.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Colin Ian King <colin.king@canonical.com>
Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Cc: Moni Shoua <monis@mellanox.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Li RongQing <roy.qing.li@gmail.com>
Cc: Devendra Naga <devendra.aaru@gmail.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@avagotech.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Vendors should be able to pass vendor specific data to/from
user-space via query_device uverb. In order to do this,
we need to pass the vendors' specific udata.
Signed-off-by: NMatan Barak <matanb@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Add a new ib_cq_init_attr structure which contains the
previous cqe (minimum number of CQ entries) and comp_vector
(completion vector) in addition to a new flags field.
All vendors' create_cq callbacks are changed in order
to work with the new API.

This commit does not change any functionality.
Signed-off-by: NMatan Barak <matanb@mellanox.com>
Signed-off-by: NOr Gerlitz <ogerlitz@mellanox.com>
Reviewed-By: Devesh Sharma <devesh.sharma@avagotech.com> to patch #2
Signed-off-by: NDoug Ledford <dledford@redhat.com>

A reorganisation of the PD allocation and deallocation in commit
9ba1377d ("RDMA/ocrdma: Move PD resource management to driver.")
introduced a double free on pd, as detected by static analysis by
smatch:

drivers/infiniband/hw/ocrdma/ocrdma_verbs.c:682 ocrdma_alloc_pd()
  error: double free of 'pd'^

The original call to ocrdma_mbx_dealloc_pd() (which does not kfree
pd) was replaced with a call to _ocrdma_dealloc_pd() (which does
kfree pd).  The kfree following this call causes the double free,
so just remove it to fix the problem.

Fixes: 9ba1377d ("RDMA/ocrdma: Move PD resource management to driver.")
Signed-off-by: NColin Ian King <colin.king@canonical.com>
Acked-By: NDevesh Sharma <devesh.sharma@avagotech.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

If ocrdma_get_pd_num() fails, then we need to free the pd struct we allocated.

This was detected by Coverity (CID 1271245).
Signed-off-by: NRoland Dreier <roland@purestorage.com>
Acked-By: NDevesh Sharma <devesh.sharma@avagotech.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Remove query_protocol callback

Use the new Core Capability bits for:

rdma_protocol_*
rdma_cap_ib_mad
rdma_cap_ib_smi
rdma_cap_ib_cm
rdma_cap_iw_cm
rdma_cap_ib_sa
rdma_cap_ib_mcast
rdma_cap_af_ib
rdma_cap_eth_ah
Signed-off-by: NIra Weiny <ira.weiny@intel.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Add new callback query_protocol() and implement for each HW.

Mapping List:
		node-type	link-layer	transport	protocol
nes		RNIC		ETH		IWARP		IWARP
amso1100	RNIC		ETH		IWARP		IWARP
cxgb3   	RNIC		ETH		IWARP		IWARP
cxgb4   	RNIC		ETH		IWARP		IWARP
usnic   	USNIC_UDP	ETH		USNIC_UDP	USNIC_UDP
ocrdma  	IB_CA		ETH		IB		IBOE
mlx4    	IB_CA		IB/ETH		IB		IB/IBOE
mlx5    	IB_CA		IB		IB		IB
ehca    	IB_CA		IB		IB		IB
ipath   	IB_CA		IB		IB		IB
mthca   	IB_CA		IB		IB		IB
qib     	IB_CA		IB		IB		IB
Signed-off-by: NMichael Wang <yun.wang@profitbricks.com>
Reviewed-by: NIra Weiny <ira.weiny@intel.com>
Tested-by: NIra Weiny <ira.weiny@intel.com>
Reviewed-by: NSean Hefty <sean.hefty@intel.com>
Reviewed-by: NJason Gunthorpe <jgunthorpe@obsidianresearch.com>
Tested-by: NDoug Ledford <dledford@redhat.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

If DPP PDs are not supported by the FW, allocate only normal PDs.
Signed-off-by: NMitesh Ahuja <mitesh.ahuja@avagotech.com>
Signed-off-by: NPadmanabh Ratnakar <padmanabh.ratnakar@avagotech.com>
Signed-off-by: NSelvin Xavier <selvin.xavier@avagotech.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Don't move QP to error state, if QP is in reset state during QP
destroy operation.
Signed-off-by: NDevesh Sharma <devesh.sharma@avagotech.com>
Signed-off-by: NSelvin Xavier <selvin.xavier@avagotech.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

The ->sgid_tbl[] array has OCRDMA_MAX_SGID number of elements so this
test is off by one.  ->sgid_tbl is allocated in ocrdma_alloc_resources().
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Acked-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

In the expressions idx/32 and idx%32, both idx and 32 have signed
type, and unfortunately the C standard prescribes rounding to 0, so
unless gcc can prove that idx is non-negative, these cannot be
implemented as simple shift respectively mask operations. Help gcc by
changing the type of idx to unsigned - this cuts another few
instructions from the generated code.
Signed-off-by: NRasmus Villemoes <linux@rasmusvillemoes.dk>
Acked-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

gcc emits a surprising amount of code in order to flip a bit. One
would think that a single instruction is enough.

$ scripts/bloat-o-meter /tmp/ocrdma_verbs.o drivers/infiniband/hw/ocrdma/ocrdma_verbs.o
add/remove: 0/0 grow/shrink: 0/3 up/down: 0/-142 (-142)
function                                     old     new   delta
ocrdma_post_srq_recv                         498     460     -38
ocrdma_poll_cq                              2010    1962     -48
ocrdma_discard_cqes                          495     439     -56

All three calls of ocrdma_srq_toggle_bit happen within spinlocks, so
saving a few useless instructions might be worthwhile.
Signed-off-by: NRasmus Villemoes <linux@rasmusvillemoes.dk>
Acked-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

For the AH that describs a VLAN interface details, vlan present bit
needs to be set during posting a WQE. This patch adds the code to
allow it happening.
Signed-off-by: NMitesh Ahuja <mitesh.ahuja@emulex.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Use get_ocrdma_dev(ocrdma_qp->ibqp.device) function to access ocrdma
device pointer.
Signed-off-by: NMitesh Ahuja <mitesh.ahuja@emulex.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Remove support for RDMA-READ-WITH-INVALIDATE from ocrdma driver.
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NMitesh Ahuja <mitesh.ahuja@emulex.com>
Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

1. Cleanup sequence in ocrdma_remove(). The device should be
   unregistered from IB stack before any device specific cleanup.
2. Always return success in the resource destroy path. In case destroy
   command returns error, IB stack will trigger cleanup again while
   closing the uverbs device causing kernel panic BUG_ON().
Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NMitesh Ahuja <mitesh.ahuja@emulex.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Fix ocrdma_query_qp to refelect correct qp state based on FW.
Signed-off-by: NMitesh Ahuja <mitesh.ahuja@emulex.com>
Signed-off-by: NPadmanabh Ratnakar <padmanabh.ratnakar@emulex.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

1. Add statistics counters for error cqes.
2. Add file ("reset_stats") to reset rdma stats in Debugfs.
Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NMitesh Ahuja <mitesh.ahuja@emulex.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Move PD allocation and deallocation from firmware to driver.  At
driver load time all the PDs will be requested from firmware and their
management will be handled by driver to reduce mailbox commands
overhead at runtime.
Signed-off-by: NMitesh Ahuja <mitesh.ahuja@emulex.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NSelvin Xavier <selvin.xavier@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

In order to allow umems that do not pin memory, we need the umem to
keep track of its region's address.

This makes the offset field redundant, and so this patch removes it.
Signed-off-by: NHaggai Eran <haggaie@mellanox.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

Signed-off-by: NMitesh Ahuja <mitesh.ahuja@emulex.com>
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>

In some platforms, when iommu is enabled, the bus address returned by
dma_alloc_coherent is different than the physical address.  ocrdma
should use physical address for mmap-ing the queue memory for the
applications.

This patch adds the use of virt_to_phys() at all such places where
kernel buffer is mapped to user process context.
Signed-off-by: NDevesh Sharma <devesh.sharma@emulex.com>
Signed-off-by: NRoland Dreier <roland@purestorage.com>