Pull rdma updates from Jason Gunthorpe:
"The usual collection of driver changes, more core infrastructure
updates that typical this cycle:
- Minor cleanups and kernel-doc fixes in bnxt_re, hns, rdmavt, efa,
ocrdma, erdma, rtrs, hfi1, ionic, and pvrdma
- New udata validation framework and driver updates
- Modernize CQ creation interface in mlx4 and mlx5, manage CQ umem in
core
- Promote UMEM to a core component, split out DMA block iterator
logic
- Introduce FRMR pools with aging, statistics, pinned handles, and
netlink control and use it in mlx5
- Add PCIe TLP emulation support in mlx5
- Extend umem to work with revocable pinned dmabuf's and use it in
irdma
- More net namespace improvements for rxe
- GEN4 hardware support in irdma
- First steps to MW and UC support in mana_ib
- Support for CQ umem and doorbells in bnxt_re
- Drop opa_vnic driver from hfi1
Fixes:
- IB/core zero dmac neighbor resolution race
- GID table memory free
- rxe pad/ICRC validation and r_key async errors
- mlx4 external umem for CQ
- umem DMA attributes on unmap
- mana_ib RX steering on RSS QP destroy"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (116 commits)
RDMA/core: Fix user CQ creation for drivers without create_cq
RDMA/ionic: bound node_desc sysfs read with %.64s
IB/core: Fix zero dmac race in neighbor resolution
RDMA/mana_ib: Support memory windows
RDMA/rxe: Validate pad and ICRC before payload_size() in rxe_rcv
RDMA/core: Prefer NLA_NUL_STRING
RDMA/core: Fix memory free for GID table
RDMA/hns: Remove the duplicate calls to ib_copy_validate_udata_in()
RDMA: Remove redundant = {} for udata req structs
RDMA/irdma: Add missing comp_mask check in alloc_ucontext
RDMA/hns: Add missing comp_mask check in create_qp
RDMA/mlx5: Pull comp_mask validation into ib_copy_validate_udata_in_cm()
RDMA: Use ib_copy_validate_udata_in_cm() for zero comp_mask
RDMA/hns: Use ib_copy_validate_udata_in()
RDMA/mlx4: Use ib_copy_validate_udata_in() for QP
RDMA/mlx4: Use ib_copy_validate_udata_in()
RDMA/mlx5: Use ib_copy_validate_udata_in() for MW
RDMA/mlx5: Use ib_copy_validate_udata_in() for SRQ
RDMA/pvrdma: Use ib_copy_validate_udata_in() for srq
RDMA: Use ib_copy_validate_udata_in() for implicit full structs
...
When an RSS QP is destroyed (e.g. DPDK exit), mana_ib_destroy_qp_rss()
destroys the RX WQ objects but does not disable vPort RX steering in
firmware. This leaves stale steering configuration that still points to
the destroyed RX objects.
If traffic continues to arrive (e.g. peer VM is still transmitting) and
the VF interface is subsequently brought up (mana_open), the firmware
may deliver completions using stale CQ IDs from the old RX objects.
These CQ IDs can be reused by the ethernet driver for new TX CQs,
causing RX completions to land on TX CQs:
WARNING: mana_poll_tx_cq+0x1b8/0x220 [mana] (is_sq == false)
WARNING: mana_gd_process_eq_events+0x209/0x290 (cq_table lookup fails)
Fix this by disabling vPort RX steering before destroying RX WQ objects.
Note that mana_fence_rqs() cannot be used here because the fence
completion is delivered on the CQ, which is polled by user-mode (e.g.
DPDK) and not visible to the kernel driver.
Refactor the disable logic into a shared mana_disable_vport_rx() in
mana_en, exported for use by mana_ib, replacing the duplicate code.
The ethernet driver's mana_dealloc_queues() is also updated to call
this common function.
Fixes: 0266a17763 ("RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter")
Cc: stable@vger.kernel.org
Signed-off-by: Long Li <longli@microsoft.com>
Link: https://patch.msgid.link/20260325194100.1929056-1-longli@microsoft.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Set the default number of queues per vPort to MANA_DEF_NUM_QUEUES (16),
as 16 queues can achieve optimal throughput for typical workloads. The
actual number of queues may be lower if it exceeds the hardware reported
limit. Users can increase the number of queues up to max_queues via
ethtool if needed.
Signed-off-by: Long Li <longli@microsoft.com>
Link: https://patch.msgid.link/20260323194925.1766385-1-longli@microsoft.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Our NIC can have up to 4 RX packets on 1 CQE. To support this feature,
check and process the type CQE_RX_COALESCED_4. The default setting is
disabled, to avoid possible regression on latency.
And, add ethtool handler to switch this feature. To turn it on, run:
ethtool -C <nic> rx-cqe-frames 4
To turn it off:
ethtool -C <nic> rx-cqe-frames 1
The rx-cqe-nsec is the time out value in nanoseconds after the first
packet arrival in a coalesced CQE to be sent. It's read-only for this
NIC.
Reviewed-by: Long Li <longli@microsoft.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Link: https://patch.msgid.link/20260317191826.1346111-3-haiyangz@linux.microsoft.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
As a part of MANA hardening for CVM, add validation for the doorbell
ID (db_id) received from hardware in the GDMA_REGISTER_DEVICE response
to prevent out-of-bounds memory access when calculating the doorbell
page address.
In mana_gd_ring_doorbell(), the doorbell page address is calculated as:
addr = db_page_base + db_page_size * db_index
= (bar0_va + db_page_off) + db_page_size * db_index
A hardware could return values that cause this address to fall outside
the BAR0 MMIO region. In Confidential VM environments, hardware responses
cannot be fully trusted.
Add the following validations:
- Store the BAR0 size (bar0_size) in gdma_context during probe.
- Validate the doorbell page offset (db_page_off) read from device
registers does not exceed bar0_size during initialization, converting
mana_gd_init_registers() to return an error code.
- Validate db_id from GDMA_REGISTER_DEVICE response against the
maximum number of doorbell pages that fit within BAR0.
Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Link: https://patch.msgid.link/20260306211212.543376-1-ernis@linux.microsoft.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The GF stats periodic query is used as mechanism to monitor HWC health
check. If this HWC command times out, it is a strong indication that
the device/SoC is in a faulty state and requires recovery.
Today, when a timeout is detected, the driver marks
hwc_timeout_occurred, clears cached stats, and stops rescheduling the
periodic work. However, the device itself is left in the same failing
state.
Extend the timeout handling path to trigger the existing MANA VF
recovery service by queueing a GDMA_EQE_HWC_RESET_REQUEST work item.
This is expected to initiate the appropriate recovery flow by suspende
resume first and if it fails then trigger a bus rescan.
This change is intentionally limited to HWC command timeouts and does
not trigger recovery for errors reported by the SoC as a normal command
response.
Signed-off-by: Dipayaan Roy <dipayanroy@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/aaFShvKnwR5FY8dH@linuxonhyperv3.guj3yctzbm1etfxqx2vob5hsef.xx.internal.cloudapp.net
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Pull rdma updates from Jason Gunthorpe:
"Usual smallish cycle. The NFS biovec work to push it down into RDMA
instead of indirecting through a scatterlist is pretty nice to see,
been talked about for a long time now.
- Various code improvements in irdma, rtrs, qedr, ocrdma, irdma, rxe
- Small driver improvements and minor bug fixes to hns, mlx5, rxe,
mana, mlx5, irdma
- Robusness improvements in completion processing for EFA
- New query_port_speed() verb to move past limited IBA defined speed
steps
- Support for SG_GAPS in rts and many other small improvements
- Rare list corruption fix in iwcm
- Better support different page sizes in rxe
- Device memory support for mana
- Direct bio vec to kernel MR for use by NFS-RDMA
- QP rate limiting for bnxt_re
- Remote triggerable NULL pointer crash in siw
- DMA-buf exporter support for RDMA mmaps like doorbells"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (66 commits)
RDMA/mlx5: Implement DMABUF export ops
RDMA/uverbs: Add DMABUF object type and operations
RDMA/uverbs: Support external FD uobjects
RDMA/siw: Fix potential NULL pointer dereference in header processing
RDMA/umad: Reject negative data_len in ib_umad_write
IB/core: Extend rate limit support for RC QPs
RDMA/mlx5: Support rate limit only for Raw Packet QP
RDMA/bnxt_re: Report QP rate limit in debugfs
RDMA/bnxt_re: Report packet pacing capabilities when querying device
RDMA/bnxt_re: Add support for QP rate limiting
MAINTAINERS: Drop RDMA files from Hyper-V section
RDMA/uverbs: Add __GFP_NOWARN to ib_uverbs_unmarshall_recv() kmalloc
svcrdma: use bvec-based RDMA read/write API
RDMA/core: add rdma_rw_max_sge() helper for SQ sizing
RDMA/core: add MR support for bvec-based RDMA operations
RDMA/core: use IOVA-based DMA mapping for bvec RDMA operations
RDMA/core: add bio_vec based RDMA read/write API
RDMA/irdma: Use kvzalloc for paged memory DMA address array
RDMA/rxe: Fix race condition in QP timer handlers
RDMA/mana_ib: Add device‑memory support
...
Report standard counter stats->rx_missed_errors
using hc_rx_discards_no_wqe from the hardware.
Add a global workqueue to periodically run
mana_query_gf_stats every 2 seconds to get the latest
info in eth_stats and define a driver capability flag
to notify hardware of the periodic queries.
To avoid repeated failures and log flooding, the workqueue
is not rescheduled if mana_query_gf_stats fails on HWC timeout
error and the stats are reset to 0. Other errors are transient
which will not need a VF reset for recovery.
Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Link: https://patch.msgid.link/1763120599-6331-3-git-send-email-ernis@linux.microsoft.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Move hardware counter (HC) statistics from mana_port_context to
mana_context to enable sharing stats across multiple network ports
on the same MANA VF. Previously, each network port queried
hardware counters independently using MANA_QUERY_GF_STAT command
(GF = Generic Function stats from GDMA hardware), resulting in
redundant queries when multiple ports existed on the same device.
Isolate hardware counter stats by introducing mana_ethtool_hc_stats
in mana_context and update the code to ensure all stats are properly
reported via ethtool -S <interface>, maintaining consistency with
previous behavior.
Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Link: https://patch.msgid.link/1763120599-6331-2-git-send-email-ernis@linux.microsoft.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Handle the NIC hardware link state events received from the HW
channel, then set the proper link state accordingly.
And, add a feature bit, GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE,
to inform the NIC hardware this handler exists.
Our MANA NIC only sends out the link state down/up messages
when we need to let the VM rerun DHCP client and change IP
address. So, add netif_carrier_on() in the probe(), let the NIC
show the right initial state in /sys/class/net/ethX/operstate.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Link: https://patch.msgid.link/1761770601-16920-1-git-send-email-haiyangz@linux.microsoft.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This patch enhances RX buffer handling in the mana driver by allocating
pages from a page pool and slicing them into MTU-sized fragments, rather
than dedicating a full page per packet. This approach is especially
beneficial on systems with large base page sizes like 64KB.
Key improvements:
- Proper integration of page pool for RX buffer allocations.
- MTU-sized buffer slicing to improve memory utilization.
- Reduce overall per Rx queue memory footprint.
- Automatic fallback to full-page buffers when:
* Jumbo frames are enabled (MTU > PAGE_SIZE / 2).
* The XDP path is active, to avoid complexities with fragment reuse.
Testing on VMs with 64KB pages shows around 200% throughput improvement.
Memory efficiency is significantly improved due to reduced wastage in page
allocations. Example: We are now able to fit 35 rx buffers in a single 64kb
page for MTU size of 1500, instead of 1 rx buffer per page previously.
Tested:
- iperf3, iperf2, and nttcp benchmarks.
- Jumbo frames with MTU 9000.
- Native XDP programs (XDP_PASS, XDP_DROP, XDP_TX, XDP_REDIRECT) for
testing the XDP path in driver.
- Memory leak detection (kmemleak).
- Driver load/unload, reboot, and stress scenarios.
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Saurabh Sengar <ssengar@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Dipayaan Roy <dipayanroy@linux.microsoft.com>
Link: https://patch.msgid.link/20250814140410.GA22089@linuxonhyperv3.guj3yctzbm1etfxqx2vob5hsef.xx.internal.cloudapp.net
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Allow mana ethtool get_link_ksettings operation to report
the maximum speed supported by the SKU in mbps.
The driver retrieves this information by issuing a
HWC command to the hardware via mana_query_link_cfg(),
which retrieves the SKU's maximum supported speed.
These APIs when invoked on hardware that are older/do
not support these APIs, the speed would be reported as UNKNOWN.
Before:
$ethtool enP30832s1
> Settings for enP30832s1:
Supported ports: [ ]
Supported link modes: Not reported
Supported pause frame use: No
Supports auto-negotiation: No
Supported FEC modes: Not reported
Advertised link modes: Not reported
Advertised pause frame use: No
Advertised auto-negotiation: No
Advertised FEC modes: Not reported
Speed: Unknown!
Duplex: Full
Auto-negotiation: off
Port: Other
PHYAD: 0
Transceiver: internal
Link detected: yes
After:
$ethtool enP30832s1
> Settings for enP30832s1:
Supported ports: [ ]
Supported link modes: Not reported
Supported pause frame use: No
Supports auto-negotiation: No
Supported FEC modes: Not reported
Advertised link modes: Not reported
Advertised pause frame use: No
Advertised auto-negotiation: No
Advertised FEC modes: Not reported
Speed: 16000Mb/s
Duplex: Full
Auto-negotiation: off
Port: Other
PHYAD: 0
Transceiver: internal
Link detected: yes
Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Reviewed-by: Saurabh Singh Sengar <ssengar@linux.microsoft.com>
Reviewed-by: Long Li <longli@microsoft.com>
Link: https://patch.msgid.link/1750144656-2021-4-git-send-email-ernis@linux.microsoft.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Introduce support for net_shaper_ops in the MANA driver,
enabling configuration of rate limiting on the MANA NIC.
To apply rate limiting, the driver issues a HWC command via
mana_set_bw_clamp() and updates the corresponding shaper object
in the net_shaper cache. If an error occurs during this process,
the driver restores the previous speed by querying the current link
configuration using mana_query_link_cfg().
The minimum supported bandwidth is 100 Mbps, and only values that are
exact multiples of 100 Mbps are allowed. Any other values are rejected.
To remove a shaper, the driver resets the bandwidth to the maximum
supported by the SKU using mana_set_bw_clamp() and clears the
associated cache entry. If an error occurs during this process,
the shaper details are retained.
On the hardware that does not support these APIs, the net-shaper
calls to set speed would fail.
Set the speed:
./tools/net/ynl/pyynl/cli.py \
--spec Documentation/netlink/specs/net_shaper.yaml \
--do set --json '{"ifindex":'$IFINDEX',
"handle":{"scope": "netdev", "id":'$ID' },
"bw-max": 200000000 }'
Get the shaper details:
./tools/net/ynl/pyynl/cli.py \
--spec Documentation/netlink/specs/net_shaper.yaml \
--do get --json '{"ifindex":'$IFINDEX',
"handle":{"scope": "netdev", "id":'$ID' }}'
> {'bw-max': 200000000,
> 'handle': {'scope': 'netdev'},
> 'ifindex': $IFINDEX,
> 'metric': 'bps'}
Delete the shaper object:
./tools/net/ynl/pyynl/cli.py \
--spec Documentation/netlink/specs/net_shaper.yaml \
--do delete --json '{"ifindex":'$IFINDEX',
"handle":{"scope": "netdev","id":'$ID' }}'
Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Reviewed-by: Saurabh Singh Sengar <ssengar@linux.microsoft.com>
Reviewed-by: Long Li <longli@microsoft.com>
Link: https://patch.msgid.link/1750144656-2021-3-git-send-email-ernis@linux.microsoft.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Shradha Gupta says:
====================
Allow dyn MSI-X vector allocation of MANA
In this patchset we want to enable the MANA driver to be able to
allocate MSI-X vectors in PCI dynamically.
The first patch exports pci_msix_prepare_desc() in PCI to be able to
correctly prepare descriptors for dynamically added MSI-X vectors.
The second patch adds the support of dynamic vector allocation in
pci-hyperv PCI controller by enabling the MSI_FLAG_PCI_MSIX_ALLOC_DYN
flag and using the pci_msix_prepare_desc() exported in first patch.
The third patch adds a detailed description of the irq_setup(), to
help understand the function design better.
The fourth patch is a preparation patch for mana changes to support
dynamic IRQ allocation. It contains changes in irq_setup() to allow
skipping first sibling CPU sets, in case certain IRQs are already
affinitized to them.
The fifth patch has the changes in MANA driver to be able to allocate
MSI-X vectors dynamically. If the support does not exist it defaults to
older behavior.
* 'shradha_v6.16-rc1' of https://github.com/shradhagupta6/linux:
net: mana: Allocate MSI-X vectors dynamically
net: mana: Allow irq_setup() to skip cpus for affinity
net: mana: explain irq_setup() algorithm
PCI: hv: Allow dynamic MSI-X vector allocation
PCI/MSI: Export pci_msix_prepare_desc() for dynamic MSI-X allocations
====================
Link: https://patch.msgid.link/1749650984-9193-1-git-send-email-shradhagupta@linux.microsoft.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Currently, the MANA driver allocates MSI-X vectors statically based on
MANA_MAX_NUM_QUEUES and num_online_cpus() values and in some cases ends
up allocating more vectors than it needs. This is because, by this time
we do not have a HW channel and do not know how many IRQs should be
allocated.
To avoid this, we allocate 1 MSI-X vector during the creation of HWC and
after getting the value supported by hardware, dynamically add the
remaining MSI-X vectors.
Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Dipayaan Roy
Linus Torvalds
Konstantin Taranov
Long Li
Haiyang Zhang
Erni Sri Satya Vennela
Aditya Garg
Jakub Kicinski
Shradha Gupta