[Hyper-V] Mellanox VF driver does not support >16 vCPUs
Bug #1667007 reported by
Joshua R. Poulson
This bug report is a duplicate of:
Bug #1667527: [Hyper-V] pci-hyperv: Use device serial number as PCI domain.
Edit
Remove
This bug affects 1 person
Affects | Status | Importance | Assigned to | Milestone | |
---|---|---|---|---|---|
linux (Ubuntu) |
In Progress
|
Medium
|
Unassigned | ||
Xenial |
In Progress
|
Medium
|
Unassigned |
Bug Description
In the course of enabling SR-IOV on Azure, discovered that the Mellanox Driver with 16 or more vCPUs fails. Mellanox has submitted the following patch upstream to correct this problem.
Prerequisite: https:/
I will post the upstream commit once it lands.
Changed in linux (Ubuntu): | |
status: | Incomplete → Confirmed |
Changed in linux (Ubuntu): | |
importance: | Undecided → Medium |
Changed in linux (Ubuntu Xenial): | |
importance: | Undecided → Medium |
status: | New → In Progress |
Changed in linux (Ubuntu): | |
status: | Confirmed → In Progress |
assignee: | nobody → Joseph Salisbury (jsalisbury) |
Changed in linux (Ubuntu Xenial): | |
assignee: | nobody → Joseph Salisbury (jsalisbury) |
tags: | added: kernel-da-key kernel-hyper-v xenial |
tags: | added: patch |
To post a comment you must log in.
(lkml)
From: Jack Morgenstein <email address hidden>
When creating EQs to handle CQ completion events for the PF
or for VFs, we create enough EQE entries to handle completions
for the max number of CQs that can use that EQ.
When SRIOV is activated, the max number of CQs a VF (or the PF) can
obtain is its CQ quota (determined by the Hypervisor resource tracker).
Therefore, when creating an EQ, the number of EQE entries that the VF
should request for that EQ is the CQ quota value (and not the total
number of CQs available in the FW).
Under SRIOV, the PF, also must use its CQ quota, because
the resource tracker also controls how many CQs the PF can obtain.
Using the FW total CQs instead of the CQ quota when creating EQs resulted
wasting MTT entries, due to allocating more EQEs than were needed.
Fixes: 5a0d0a6161ae ("mlx4: Structures and init/teardown for VF resource quotas")
Signed-off-by: Jack Morgenstein <email address hidden>
Reported-by: Dexuan Cui <email address hidden>
Signed-off-by: Tariq Toukan <email address hidden>