linux_dsm_epyc7002/drivers/infiniband/hw
Eugenia Emantayev ddae0349fd net/mlx4: Change QP allocation scheme
When using BF (Blue-Flame), the QPN overrides the VLAN, CV, and SV fields
in the WQE. Thus, BF may only be used for QPNs with bits 6,7 unset.

The current Ethernet driver code reserves a Tx QP range with 256b alignment.

This is wrong because if there are more than 64 Tx QPs in use,
QPNs >= base + 65 will have bits 6/7 set.

This problem is not specific for the Ethernet driver, any entity that
tries to reserve more than 64 BF-enabled QPs should fail. Also, using
ranges is not necessary here and is wasteful.

The new mechanism introduced here will support reservation for
"Eth QPs eligible for BF" for all drivers: bare-metal, multi-PF, and VFs
(when hypervisors support WC in VMs). The flow we use is:

1. In mlx4_en, allocate Tx QPs one by one instead of a range allocation,
   and request "BF enabled QPs" if BF is supported for the function

2. In the ALLOC_RES FW command, change param1 to:
a. param1[23:0]  - number of QPs
b. param1[31-24] - flags controlling QPs reservation

Bit 31 refers to Eth blueflame supported QPs. Those QPs must have
bits 6 and 7 unset in order to be used in Ethernet.

Bits 24-30 of the flags are currently reserved.

When a function tries to allocate a QP, it states the required attributes
for this QP. Those attributes are considered "best-effort". If an attribute,
such as Ethernet BF enabled QP, is a must-have attribute, the function has
to check that attribute is supported before trying to do the allocation.

In a lower layer of the code, mlx4_qp_reserve_range masks out the bits
which are unsupported. If SRIOV is used, the PF validates those attributes
and masks out unsupported attributes as well. In order to notify VFs which
attributes are supported, the VF uses QUERY_FUNC_CAP command. This command's
mailbox is filled by the PF, which notifies which QP allocation attributes
it supports.

Signed-off-by: Eugenia Emantayev <eugenia@mellanox.co.il>
Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-11 14:47:35 -05:00
..
amso1100 Main set of InfiniBand/RDMA updates for 3.17 merge window: 2014-08-14 11:09:05 -06:00
cxgb3 RDMA/cxgb3: Remove a couple unneeded conditions 2014-05-28 10:04:00 -07:00
cxgb4 RDMA/cxgb4/cxgb4vf/csiostor: Cleanup macros/register defines related to PCIE, RSS and FW 2014-11-22 16:57:47 -05:00
ehca Merge branches 'core', 'cxgb4', 'ip-roce', 'iser', 'misc', 'mlx4', 'nes', 'ocrdma', 'qib', 'sgwrapper', 'srp' and 'usnic' into for-next 2014-04-03 08:30:17 -07:00
ipath [infiniband] remove pointless assignments 2014-10-09 02:39:15 -04:00
mlx4 net/mlx4: Change QP allocation scheme 2014-12-11 14:47:35 -05:00
mlx5 mlx5: Fix error flow in add_keys 2014-12-08 20:45:56 -05:00
mthca IB/mad: add new ioctl to ABI to support new registration options 2014-08-10 20:36:00 -07:00
nes infiniband: use pci_zalloc_consistent 2014-08-08 15:57:28 -07:00
ocrdma Main set of InfiniBand/RDMA updates for 3.18 merge window: 2014-10-19 12:29:23 -07:00
qib [infiniband] remove pointless assignments 2014-10-09 02:39:15 -04:00
usnic IOMMU Updates for Linux v3.18 2014-10-15 07:23:49 +02:00
Makefile IB: Allow build of hw/ and ulp/ subdirectories independently 2014-06-02 14:51:12 -07:00