Pull networking fixes from Jakub Kicinski:
"Including fixes from bpf, can and netfilter.
Current release - regressions:
- bpf: do not reject when the stack read size is different from the
tracked scalar size
- net: fix premature exit from NAPI state polling in napi_disable()
- riscv, bpf: fix RV32 broken build, and silence RV64 warning
Current release - new code bugs:
- net: fix possible NULL deref in sock_reserve_memory
- amt: fix error return code in amt_init(); fix stopping the
workqueue
- ax88796c: use the correct ioctl callback
Previous releases - always broken:
- bpf: stop caching subprog index in the bpf_pseudo_func insn
- security: fixups for the security hooks in sctp
- nfc: add necessary privilege flags in netlink layer, limit
operations to admin only
- vsock: prevent unnecessary refcnt inc for non-blocking connect
- net/smc: fix sk_refcnt underflow on link down and fallback
- nfnetlink_queue: fix OOB when mac header was cleared
- can: j1939: ignore invalid messages per standard
- bpf, sockmap:
- fix race in ingress receive verdict with redirect to self
- fix incorrect sk_skb data_end access when src_reg = dst_reg
- strparser, and tls are reusing qdisc_skb_cb and colliding
- ethtool: fix ethtool msg len calculation for pause stats
- vlan: fix a UAF in vlan_dev_real_dev() when ref-holder tries to
access an unregistering real_dev
- udp6: make encap_rcv() bump the v6 not v4 stats
- drv: prestera: add explicit padding to fix m68k build
- drv: felix: fix broken VLAN-tagged PTP under VLAN-aware bridge
- drv: mvpp2: fix wrong SerDes reconfiguration order
Misc & small latecomers:
- ipvs: auto-load ipvs on genl access
- mctp: sanity check the struct sockaddr_mctp padding fields
- libfs: support RENAME_EXCHANGE in simple_rename()
- avoid double accounting for pure zerocopy skbs"
* tag 'net-5.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (123 commits)
selftests/net: udpgso_bench_rx: fix port argument
net: wwan: iosm: fix compilation warning
cxgb4: fix eeprom len when diagnostics not implemented
net: fix premature exit from NAPI state polling in napi_disable()
net/smc: fix sk_refcnt underflow on linkdown and fallback
net/mlx5: Lag, fix a potential Oops with mlx5_lag_create_definer()
gve: fix unmatched u64_stats_update_end()
net: ethernet: lantiq_etop: Fix compilation error
selftests: forwarding: Fix packet matching in mirroring selftests
vsock: prevent unnecessary refcnt inc for nonblocking connect
net: marvell: mvpp2: Fix wrong SerDes reconfiguration order
net: ethernet: ti: cpsw_ale: Fix access to un-initialized memory
net: stmmac: allow a tc-taprio base-time of zero
selftests: net: test_vxlan_under_vrf: fix HV connectivity test
net: hns3: allow configure ETS bandwidth of all TCs
net: hns3: remove check VF uc mac exist when set by PF
net: hns3: fix some mac statistics is always 0 in device version V2
net: hns3: fix kernel crash when unload VF while it is being reset
net: hns3: sync rx ring head in echo common pull
net: hns3: fix pfc packet number incorrect after querying pfc parameters
...
There is a minus character missing from ERR_PTR(ENOMEM) so if this
allocation fails it will lead to an Oops in the caller.
Fixes: dc48516ec7 ("net/mlx5: Lag, add support to create definers for LAG")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull gpio updates from Bartosz Golaszewski:
"We have a single new driver, new features in others and some cleanups
all over the place.
Nothing really stands out and it is all relatively small.
- new driver: gpio-modepin (plus relevant change in zynqmp firmware)
- add interrupt support to gpio-virtio
- enable the 'gpio-line-names' property in the DT bindings for
gpio-rockchip
- use the subsystem helpers where applicable in gpio-uniphier instead
of accessing IRQ structures directly
- code shrink in gpio-xilinx
- add interrupt to gpio-mlxbf2 (and include the removal of custom
interrupt code from the mellanox ethernet driver)
- support multiple interrupts per bank in gpio-tegra186 (and force
one interrupt per bank in older models)
- fix GPIO line IRQ offset calculation in gpio-realtek-otto
- drop unneeded MODULE_ALIAS expansions in multiple drivers
- code cleanup in gpio-aggregator
- minor improvements in gpio-max730x and gpio-mc33880
- Kconfig cleanups"
* tag 'gpio-updates-for-v5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux:
virtio_gpio: drop packed attribute
gpio: virtio: Add IRQ support
gpio: realtek-otto: fix GPIO line IRQ offset
gpio: clean up Kconfig file
net: mellanox: mlxbf_gige: Replace non-standard interrupt handling
gpio: mlxbf2: Introduce IRQ support
gpio: mc33880: Drop if with an always false condition
gpio: max730x: Make __max730x_remove() return void
gpio: aggregator: Wrap access to gpiochip_fwd.tmp[]
gpio: modepin: Add driver support for modepin GPIO controller
dt-bindings: gpio: zynqmp: Add binding documentation for modepin
firmware: zynqmp: Add MMIO read and write support for PS_MODE pin
gpio: tps65218: drop unneeded MODULE_ALIAS
gpio: max77620: drop unneeded MODULE_ALIAS
gpio: xilinx: simplify getting .driver_data
gpio: tegra186: Support multiple interrupts per bank
gpio: tegra186: Force one interrupt per bank
gpio: uniphier: Use helper functions to get private data from IRQ data
gpio: uniphier: Use helper function to get IRQ hardware number
dt-bindings: gpio: add gpio-line-names to rockchip,gpio-bank.yaml
Pull pci updates from Bjorn Helgaas:
"Enumeration:
- Conserve IRQs by setting up portdrv IRQs only when there are users
(Jan Kiszka)
- Rework and simplify _OSC negotiation for control of PCIe features
(Joerg Roedel)
- Remove struct pci_dev.driver pointer since it's redundant with the
struct device.driver pointer (Uwe Kleine-König)
Resource management:
- Coalesce contiguous host bridge apertures from _CRS to accommodate
BARs that cover more than one aperture (Kai-Heng Feng)
Sysfs:
- Check CAP_SYS_ADMIN before parsing user input (Krzysztof
Wilczyński)
- Return -EINVAL consistently from "store" functions (Krzysztof
Wilczyński)
- Use sysfs_emit() in endpoint "show" functions to avoid buffer
overruns (Kunihiko Hayashi)
PCIe native device hotplug:
- Ignore Link Down/Up caused by resets during error recovery so
endpoint drivers can remain bound to the device (Lukas Wunner)
Virtualization:
- Avoid bus resets on Atheros QCA6174, where they hang the device
(Ingmar Klein)
- Work around Pericom PI7C9X2G switch packet drop erratum by using
store and forward mode instead of cut-through (Nathan Rossi)
- Avoid trying to enable AtomicOps on VFs; the PF setting applies to
all VFs (Selvin Xavier)
MSI:
- Document that /sys/bus/pci/devices/.../irq contains the legacy INTx
interrupt or the IRQ of the first MSI (not MSI-X) vector (Barry
Song)
VPD:
- Add pci_read_vpd_any() and pci_write_vpd_any() to access anywhere
in the possible VPD space; use these to simplify the cxgb3 driver
(Heiner Kallweit)
Peer-to-peer DMA:
- Add (not subtract) the bus offset when calculating DMA address
(Wang Lu)
ASPM:
- Re-enable LTR at Downstream Ports so they don't report Unsupported
Requests when reset or hot-added devices send LTR messages
(Mingchuang Qiao)
Apple PCIe controller driver:
- Add driver for Apple M1 PCIe controller (Alyssa Rosenzweig, Marc
Zyngier)
Cadence PCIe controller driver:
- Return success when probe succeeds instead of falling into error
path (Li Chen)
HiSilicon Kirin PCIe controller driver:
- Reorganize PHY logic and add support for external PHY drivers
(Mauro Carvalho Chehab)
- Support PERST# GPIOs for HiKey970 external PEX 8606 bridge (Mauro
Carvalho Chehab)
- Add Kirin 970 support (Mauro Carvalho Chehab)
- Make driver removable (Mauro Carvalho Chehab)
Intel VMD host bridge driver:
- If IOMMU supports interrupt remapping, leave VMD MSI-X remapping
enabled (Adrian Huang)
- Number each controller so we can tell them apart in
/proc/interrupts (Chunguang Xu)
- Avoid building on UML because VMD depends on x86 bare metal APIs
(Johannes Berg)
Marvell Aardvark PCIe controller driver:
- Define macros for PCI_EXP_DEVCTL_PAYLOAD_* (Pali Rohár)
- Set Max Payload Size to 512 bytes per Marvell spec (Pali Rohár)
- Downgrade PIO Response Status messages to debug level (Marek Behún)
- Preserve CRS SV (Config Request Retry Software Visibility) bit in
emulated Root Control register (Pali Rohár)
- Fix issue in configuring reference clock (Pali Rohár)
- Don't clear status bits for masked interrupts (Pali Rohár)
- Don't mask unused interrupts (Pali Rohár)
- Avoid code repetition in advk_pcie_rd_conf() (Marek Behún)
- Retry config accesses on CRS response (Pali Rohár)
- Simplify emulated Root Capabilities initialization (Pali Rohár)
- Fix several link training issues (Pali Rohár)
- Fix link-up checking via LTSSM (Pali Rohár)
- Fix reporting of Data Link Layer Link Active (Pali Rohár)
- Fix emulation of W1C bits (Marek Behún)
- Fix MSI domain .alloc() method to return zero on success (Marek
Behún)
- Read entire 16-bit MSI vector in MSI handler, not just low 8 bits
(Marek Behún)
- Clear Root Port I/O Space, Memory Space, and Bus Master Enable bits
at startup; PCI core will set those as necessary (Pali Rohár)
- When operating as a Root Port, set class code to "PCI Bridge"
instead of the default "Mass Storage Controller" (Pali Rohár)
- Add emulation for PCI_BRIDGE_CTL_BUS_RESET since aardvark doesn't
implement this per spec (Pali Rohár)
- Add emulation of option ROM BAR since aardvark doesn't implement
this per spec (Pali Rohár)
MediaTek MT7621 PCIe controller driver:
- Add MediaTek MT7621 PCIe host controller driver and DT binding
(Sergio Paracuellos)
Qualcomm PCIe controller driver:
- Add SC8180x compatible string (Bjorn Andersson)
- Add endpoint controller driver and DT binding (Manivannan
Sadhasivam)
- Restructure to use of_device_get_match_data() (Prasad Malisetty)
- Add SC7280-specific pcie_1_pipe_clk_src handling (Prasad Malisetty)
Renesas R-Car PCIe controller driver:
- Remove unnecessary includes (Geert Uytterhoeven)
Rockchip DesignWare PCIe controller driver:
- Add DT binding (Simon Xue)
Socionext UniPhier Pro5 controller driver:
- Serialize INTx masking/unmasking (Kunihiko Hayashi)
Synopsys DesignWare PCIe controller driver:
- Run dwc .host_init() method before registering MSI interrupt
handler so we can deal with pending interrupts left by bootloader
(Bjorn Andersson)
- Clean up Kconfig dependencies (Andy Shevchenko)
- Export symbols to allow more modular drivers (Luca Ceresoli)
TI DRA7xx PCIe controller driver:
- Allow host and endpoint drivers to be modules (Luca Ceresoli)
- Enable external clock if present (Luca Ceresoli)
TI J721E PCIe driver:
- Disable PHY when probe fails after initializing it (Christophe
JAILLET)
MicroSemi Switchtec management driver:
- Return error to application when command execution fails because an
out-of-band reset has cleared the device BARs, Memory Space Enable,
etc (Kelvin Cao)
- Fix MRPC error status handling issue (Kelvin Cao)
- Mask out other bits when reading of management VEP instance ID
(Kelvin Cao)
- Return EOPNOTSUPP instead of ENOTSUPP from sysfs show functions
(Kelvin Cao)
- Add check of event support (Logan Gunthorpe)
Miscellaneous:
- Remove unused pci_pool wrappers, which have been replaced by
dma_pool (Cai Huoqing)
- Use 'unsigned int' instead of bare 'unsigned' (Krzysztof
Wilczyński)
- Use kstrtobool() directly, sans strtobool() wrapper (Krzysztof
Wilczyński)
- Fix some sscanf(), sprintf() format mismatches (Krzysztof
Wilczyński)
- Update PCI subsystem information in MAINTAINERS (Krzysztof
Wilczyński)
- Correct some misspellings (Krzysztof Wilczyński)"
* tag 'pci-v5.16-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci: (137 commits)
PCI: Add ACS quirk for Pericom PI7C9X2G switches
PCI: apple: Configure RID to SID mapper on device addition
iommu/dart: Exclude MSI doorbell from PCIe device IOVA range
PCI: apple: Implement MSI support
PCI: apple: Add INTx and per-port interrupt support
PCI: kirin: Allow removing the driver
PCI: kirin: De-init the dwc driver
PCI: kirin: Disable clkreq during poweroff sequence
PCI: kirin: Move the power-off code to a common routine
PCI: kirin: Add power_off support for Kirin 960 PHY
PCI: kirin: Allow building it as a module
PCI: kirin: Add MODULE_* macros
PCI: kirin: Add Kirin 970 compatible
PCI: kirin: Support PERST# GPIOs for HiKey970 external PEX 8606 bridge
PCI: apple: Set up reference clocks when probing
PCI: apple: Add initial hardware bring-up
PCI: of: Allow matching of an interrupt-map local to a PCI device
of/irq: Allow matching of an interrupt-map local to an interrupt controller
irqdomain: Make of_phandle_args_to_fwspec() generally available
PCI: Do not enable AtomicOps on VFs
...
Pull rdma updates from Jason Gunthorpe:
"A typical collection of patches this cycle, mostly fixing with a few
new features:
- Fixes from static tools. clang warnings, dead code, unused
variable, coccinelle sweeps, etc
- Driver bug fixes and minor improvements in rxe, bnxt_re, hfi1,
mlx5, irdma, qedr
- rtrs ULP bug fixes an improvments
- Additional counters for bnxt_re
- Support verbs CQ notifications in EFA
- Continued reworking and fixing of rxe
- netlink control to enable/disable optional device counters
- rxe now can use AH objects for its UD path, fixing various bugs in
the process
- Add DMABUF support to EFA"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (103 commits)
RDMA/core: Require the driver to set the IOVA correctly during rereg_mr
RDMA/bnxt_re: Remove unsupported bnxt_re_modify_ah callback
RDMA/irdma: optimize rx path by removing unnecessary copy
RDMA/qed: Use helper function to set GUIDs
RDMA/hns: Use the core code to manage the fixed mmap entries
IB/opa_vnic: Rebranding of OPA VNIC driver to Cornelis Networks
IB/qib: Rebranding of qib driver to Cornelis Networks
IB/hfi1: Rebranding of hfi1 driver to Cornelis Networks
RDMA/bnxt_re: Use helper function to set GUIDs
RDMA/bnxt_re: Fix kernel panic when trying to access bnxt_re_stat_descs
RDMA/qedr: Fix NULL deref for query_qp on the GSI QP
RDMA/hns: Modify the value of MAX_LP_MSG_LEN to meet hardware compatibility
RDMA/hns: Fix initial arm_st of CQ
RDMA/rxe: Make rxe_type_info static const
RDMA/rxe: Use 'bitmap_zalloc()' when applicable
RDMA/rxe: Save a few bytes from struct rxe_pool
RDMA/irdma: Remove the unused variable local_qp
RDMA/core: Fix missed initialization of rdma_hw_stats::lock
RDMA/efa: Add support for dmabuf memory regions
RDMA/umem: Allow pinned dmabuf umem usage
...
When performing route device lookup for decap action, support
the case of ovs internal port as the lookup result.
In such case, an internal port struct is mapped and attached
to the flow attributes so that the source port matching of the
rule will match on the internal port's metadata value.
Signed-off-by: Ariel Levkovich <lariel@nvidia.com>
Reviewed-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Adjust termination table logic to handle rules which
involve internal port as filter or forwarding device.
For cases where the rule forwards from internal port
to uplink, always choose to go via termination table.
This is because it is not known from where the packet
originally arrived to the internal port and it is possible
that it came from the uplink itself, in which case
a term table is required to perform hairpin.
If the packet arrived from a vport, going via term
table has no effect.
For cases where the rule forwards to an internal port
from uplink the rep pointer will point to the uplink rep,
avoid going via termination table as it is not required.
Signed-off-by: Ariel Levkovich <lariel@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Register callbacks for tc blocks of ovs internal port devices.
This allows an indirect offloading rules that apply on
such devices as the filter device.
In case a rule is added to a tc block of an internal port,
the mlx5 driver will implicitly add a matching on the internal
port's unique vport metadata value to the rule's matching list.
Therefore, only packets that previously hit a rule that redirects
to an internal port and got the vport metadata overwritten to the
internal port's unique metadata, can match on such indirect rule.
Offloading of both ingress and egress tc blocks of internal ports
is supported as opposed to other devices where only ingress block
offloading is supported.
Signed-off-by: Ariel Levkovich <lariel@nvidia.com>
Reviewed-by: Paul Blakey <paulb@nvidia.com>
Reviewed-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
When pefroming encap action, a route lookup is performed
to find the routing device the packet should be forwarded
to after the encapsulation. This is the device that has the
local tunnel ip address.
This change adds support to offload an encap rule where the
route device ends up being an ovs internal port.
In such case, the driver will add a HW rule that will encapsulate
the packet with the tunnel header and will overwrite the vport
metadata in reg_c0 to the internal port metadata value.
Finally, the packet will be forwarded to the root table to be
processed again with the indication that it came from an internal
port.
Signed-off-by: Ariel Levkovich <lariel@nvidia.com>
Reviewed-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Allow offloading rules that redirect to ovs internal port
ingress and egress.
To support redirect to ingress device, offloading of REDIRECT_INGRESS
action is added.
When a tc rule redirects to ovs internal port, the hw rule will
overwrite the input vport value in reg_c0 with a new vport metadata
value that is mapped for this internal port using the internal
port mapping api that is introduce in previous patches.
After that the hw rule will redirect the packet to the root table
to continue processing with the new vport metadata value.
The new vport metadata value indicates that this packet is now
arriving through an internal port and therefore should be processed
using rules that apply on the same internal port as the filter device.
Therefore, following rules that apply on this internal port will have
to match on the same vport metadata value as part of their matching
keys to make sure the packet belongs to the internal port.
Signed-off-by: Ariel Levkovich <lariel@nvidia.com>
Reviewed-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Setting the skb packet type field to host is usually
done when performing forwarding to ingress device.
This is required since the receive handling that is used
by the redirect to ingress action checks whether the packet
doesn't belong to this host and drops the packet in such case.
In order to be able to offload action redirect ingress, tc offload
code needs to accept the skbedit ptype action as well.
There's no special handling in HW for such action since it will
be followed by a redirect action and therefore, this code
only allows us to accept such action in the actions list but
not performing anything specific in HW for it.
Signed-off-by: Ariel Levkovich <lariel@nvidia.com>
Reviewed-by: Paul Blakey <paulb@nvidia.com>
Reviewed-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Adding infrastructure to map ovs internal port device to vport
match metadata to support offload of rules with internal port as
the filter device or as the destination device.
The infrastructure allows adding and removing internal port device
to an eswitch database and getting a unique vport metadata value to
be placed and match on in reg_c0 when offloading rules that are coming
from or going to an internal port.
The new int port metadata can be written to the source port register
in HW to indicate that current source port of the packet is the
internal port and not one of the actual HW vports (uplink or VF).
Using this method, it is possible to offload TC rules with an OVS
internal port as their destination port (overwriting the src vport
register) or as the filter port (matching on the value of the src
vport register and making sure it matches to the internal port's
value).
There is also a need to handle a miss case where the packet's
src port value was changed in HW to an internal port but a following
rule which matches on this new src port value wasn't found in HW.
In such case, the packet will be forwarded to the driver with
metadata which allows driver to restore the info of the internal
port's netdevice. Once this info is restored, the uplink driver
can forward the packet to the relevant netdevice in SW.
Signed-off-by: Ariel Levkovich <lariel@nvidia.com>
Reviewed-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Rename tun_dev to fwd_dev within mlx5e_tc_update_priv struct
since future implementation may introduce other device types
which the handler is forwarding to.
Signed-off-by: Ariel Levkovich <lariel@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Move the ownership of skb forwarding to network stack to the
tc update_skb handler as different cases will require different
handling of the skb.
While the tc handler will take care of the various cases and
properly handle the handover of the skb to the network stack
and freeing the skb, the main rx handler will be kept clean
from branches and usage of flags.
Signed-off-by: Ariel Levkovich <lariel@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
When a matcher is being built, we "consume" (clear) mask fields one by one,
and to verify that we do support all the required fields we check if the
whole mask was consumed, else the matching request includes unsupported
fields.
Signed-off-by: Muhammad Sammar <muhammads@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
CT creates a counter for each CT rule, and for each such counter,
fs_counters tries to queue mlx5_fc_stats_work() work again via
mod_delayed_work(0) call to refresh all counters. This call has a
large performance impact when reaching high insertion rate and
accounts for ~8% of the insertion time when using software steering.
Allow skipping the refresh of all counters during counter creation.
Change CT to use this refresh skipping for it's counters.
Signed-off-by: Paul Blakey <paulb@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Reviewed-by: Oz Shlomo <ozsh@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Part of code that is related solely to IPsec is always compiled in the
driver code regardless if the IPsec functionality is enabled or disabled
in the driver code, this will add unnecessary branch in case IPsec is
disabled at Tx data path.
Move IPsec related code to IPsec related file such that in case of IPsec
is disabled and because of unlikely macro the compiler should be able to
optimize and omit the checksum IPsec code all together from Tx data path
Signed-off-by: Raed Salem <raeds@nvidia.com>
Reviewed-by: Emeel Hakim <ehakim@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
ignore_flow_level isn't supported for VFs, and so it causes
post_act and ct to warn about it.
Instead of disabling CT for VFs, and a driver update will be need
to enable CT again once firmware support this, remove this warning
specifically for VFs. This way, it could be automatically enabled on
future firmwares where VFs support ignore_flow_level capability.
Signed-off-by: Paul Blakey <paulb@nvidia.com>
Reviewed-by: Maor Dickman <maord@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Clang warns:
drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c:635:34: error: variable 'esw' is uninitialized when used here [-Werror,-Wuninitialized]
mlx5_eswitch_del_offloaded_rule(esw, sample_flow->pre_rule, sample_flow->pre_attr);
^~~
drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c:626:26: note: initialize the variable 'esw' to silence this warning
struct mlx5_eswitch *esw;
^
= NULL
1 error generated.
It appears that the assignment should have been shuffled instead of
removed outright like in mlx5e_tc_sample_offload(). Add it back so there
is no use of esw uninitialized.
Fixes: a64c5edbd2 ("net/mlx5: Remove unnecessary checks for slow path flag")
Link: https://github.com/ClangBuiltLinux/linux/issues/1494
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Since the GPIO driver (gpio-mlxbf2.c) supports interrupt handling,
replace the custom routine with simple IRQ request.
Signed-off-by: Asmaa Mnebhi <asmaa@nvidia.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Bartosz Golaszewski <brgl@bgdev.pl>
The Spectrum ASIC allows configuration of maximum shaper on all levels of
the scheduling hierarchy: TCs, subgroups, groups and also ports. Currently,
TBF always configures a subgroup. But a user could reasonably express the
intent to configure port shaper by putting TBF to a root position, around
ETS / PRIO. Accept this usage and offload appropriately.
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit introduces HW-GRO offload by using the SHAMPO feature
- Add set feature handler for HW-GRO.
Signed-off-by: Ben Ben-Ishay <benishay@nvidia.com>
Signed-off-by: Khalid Manaa <khalidm@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
This patch adds HW_GRO counters to RX packets statistics:
- gro_match_packets: counter of received packets with set match flag.
- gro_packets: counter of received packets over the HW_GRO feature,
this counter is increased by one for every received
HW_GRO cqe.
- gro_bytes: counter of received bytes over the HW_GRO feature,
this counter is increased by the received bytes for every
received HW_GRO cqe.
- gro_skbs: counter of built HW_GRO skbs,
increased by one when we flush HW_GRO skb
(when we call a napi_gro_receive with hw_gro skb).
- gro_large_hds: counter of received packets with large headers size,
in case the packet needs new SKB, the driver will allocate
new one and will not use the headers entry to build it.
Signed-off-by: Khalid Manaa <khalidm@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
this patch updates the SHAMPO CQE handler to support HW_GRO,
changes in the SHAMPO CQE handler:
- CQE match and flush fields are used to determine if to build new skb
using the new received packet,
or to add the received packet data to the existing RQ.hw_gro_skb,
also this fields are used to determine when to flush the skb.
- in the end of the function mlx5e_poll_rx_cq the RQ.hw_gro_skb is flushed.
Signed-off-by: Khalid Manaa <khalidm@nvidia.com>
Signed-off-by: Ben Ben-Ishay <benishay@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
The header buffer is used to store the headers of the rx packets.
The header buffer size deduced from WorkQueue size + restriction
of max packets per WorkQueueElement.
This commit adds the functionality for posting/updating memory for
the header buffer during the posting/updating of WQEs.
Signed-off-by: Ben Ben-Ishay <benishay@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
This patch adds the new CQE SHAMPO fields:
- flush: indicates that we must close the current session and pass the SKB
to the network stack.
- match: indicates that the current packet matches the oppened session,
the packet will be merge into the current SKB.
- header_size: the size of the packet headers that written into the headers
buffer.
- header_entry_index: the entry index in the headers buffer.
- data_offset: packets data offset in the WQE.
Also new cqe handler is added to handle SHAMPO packets:
- The new handler uses CQE SHAMPO fields to build the SKB.
CQE's Flush and match fields are not used in this patch, packets are not
merged in this patch.
Signed-off-by: Khalid Manaa <khalidm@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
This commit introduces the control path infrastructure for SHAMPO feature.
SHAMPO feature enables packet stitching by splitting packets to
header and payload, the header is placed on a dedicated buffer
and the payload on the RX ring, this allows stitching the data part
of a flow together continuously in the receive buffer.
SHAMPO feature is implemented as linked list striding RQ feature.
To support packets splitting and payload stitching:
- Enlarge the ICOSQ and the correspond CQ to support the header buffer
memory regions.
- Add support to create linked list striding RQ with SHAMPO feature set
in the open_rq function.
- Add deallocation function and corresponded calls for SHAMPO header
buffer.
- Add mlx5e_create_umr_klm_mkey to support KLM mkey for the header
buffer.
- Rename mlx5e_create_umr_mkey to mlx5e_create_umr_mtt_mkey.
Signed-off-by: Ben Ben-Ishay <benishay@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
This commit adds the needed definitions for using the klm_umr_wqe.
UMR stands for user-mode memory registration, is a mechanism to alter
address translation properties of MKEY by posting WorkQueueElement
aka WQE on send queue.
MKEY stands for memory key, MKEY are used to describe a region in memory that
can be later used by HW.
KLM stands for {Key, Length, MemVa}, KLM_MKEY is indirect MKEY that enables
to map multiple memory spaces with different sizes in unified MKEY.
klm_umr_wqe is a UMR that use to update a KLM_MKEY.
SHAMPO feature uses KLM_MKEY for memory registration of his header buffer.
Signed-off-by: Ben Ben-Ishay <benishay@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
This series introduces new packet merge type, therefore rename lro
functions to packet merge to support the new merge type:
- Generalize + rename mlx5e_build_tir_ctx_lro to
mlx5e_build_tir_ctx_packet_merge.
- Rename mlx5e_modify_tirs_lro to mlx5e_modify_tirs_packet_merge.
- Rename lro bit in mlx5_ifc_modify_tir_bitmask_bits to packet_merge.
- Rename lro_en in mlx5e_params to packet_merge_type type and combine
packet_merge params into one struct mlx5e_packet_merge_param.
Signed-off-by: Khalid Manaa <khalidm@nvidia.com>
Signed-off-by: Ben Ben-Ishay <benishay@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
This commit adds SHAMPO bit to hca_cap and SHAMPO capabilities structure,
SHAMPO related HW spec hardware fields and enumerations.
SHAMPO stands for: split headers and merge payload offload.
SHAMPO new fields:
WQ:
- headers_mkey: mkey that represents the headers buffer, where the packets
headers will be written by the HW.
- shampo_enable: flag to verify if the WQ supports SHAMPO feature.
- log_reservation_size: the log of the reservation size where the data of
the packet will be written by the HW.
- log_max_num_of_packets_per_reservation: log of the maximum number of
packets that can be written to the same reservation.
- log_headers_entry_size: log of the header entry size of the headers buffer.
- log_headers_buffer_entry_num: log of the entries number of the headers buffer.
RQ:
- shampo_no_match_alignment_granularity: the HW alignment granularity
in case the received packet doesn't match the current session.
- shampo_match_criteria_type: the type of match criteria.
- reservation_timeout: the maximum time that the HW will hold the
reservation.
mlx5_ifc_shampo_cap_bits, the capabilities of the SHAMPO feature:
- shampo_log_max_reservation_size: the maximum allowed value of the field
WQ.log_reservation_size.
- log_reservation_size: the minimum allowed value of the field
WQ.log_reservation_size.
- shampo_min_mss_size: the minimum payload size of packet that can open
a new session or be merged to a session.
- shampo_max_log_headers_entry_size: the maximum allowed value of the field
WQ.log_headers_entry_size
Signed-off-by: Ben Ben-Ishay <benishay@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
TIR stands for transport interface receive, the TIR object is
responsible for performing all transport related operations on
the receive side like packet processing, demultiplexing the packets
to different RQ's, etc.
lro_timeout is a field in the TIR that is used to set the timeout for lro
session, this series introduces new packet merge type, therefore rename
lro_timeout to packet_merge_timeout for all packet merge types.
Signed-off-by: Ben Ben-Ishay <benishay@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Expose via devlink-resource the maximum number of RIF MAC profiles and
their current occupancy, so it can be used for debug and writing generic
tests, like in the next patch.
Example for Spectrum-2 output:
$ devlink resource show pci/0000:06:00.0
...
name rif_mac_profiles size 4 occ 0 unit entry dpipe_tables none
Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, mlxsw enforces that all the router interfaces (RIFs) have the
same MAC prefix.
Relax this limitation by using RIF MAC profiles. Each profile is
associated with a particular MAC prefix and multiple RIFs can use the
same profile. Therefore, the number of possible MAC prefixes is no
longer one, but the number of profiles supported by the device.
Store the profiles in an IDR and reference count them according to the
number of RIFs using them.
Associate a RIF with a profile when the RIF is created and remove the
association when the RIF is deleted.
Change the association following 'NETDEV_CHANGEADDR' events, except when
only one RIF is using the profile. In which case, change the MAC prefix
of the profile itself instead of associating the RIF with a new profile.
Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The next patch will set the MAC profile of a router interface (RIF) as
part of its configure() callback. The operation can fail in case the
maximum number of profiles was exceeded.
Add extack to mlxsw_sp_rif_ops::configure() in order to communicate such
failures to user space.
In addition, the MAC profile of a RIF can change following a
'NETDEV_CHANGEADDR' notification. Propagate extack to
mlxsw_sp_router_port_change_event() so that failures could be
communicated in this path as well.
No functional changes intended.
Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a resource identifier for maximum RIF MAC profiles so that it could
be later used to query the information from firmware.
Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add MAC profile ID field to RITR register so that it could be used for
associating a RIF with a MAC profile ID by a later patch.
Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When the driver fails to allocate a new Rx buffer, it passes an empty Rx
descriptor (contains zero address and size) to the device and marks it
as invalid by setting the skb pointer in the descriptor's metadata to
NULL.
After processing enough Rx descriptors, the driver will try to process
the invalid descriptor, but will return immediately seeing that the skb
pointer is NULL. Since the driver no longer passes new Rx descriptors to
the device, the Rx queue will eventually become full and the device will
start to drop packets.
Fix this by recycling the received packet if allocation of the new
packet failed. This means that allocation is no longer performed at the
end of the Rx routine, but at the start, before tearing down the DMA
mapping of the received packet.
Remove the comment about the descriptor being zeroed as it is no longer
correct. This is OK because we either use the descriptor as-is (when
recycling) or overwrite its address and size fields with that of the
newly allocated Rx buffer.
The issue was discovered when a process ("perf") consumed too much
memory and put the system under memory pressure. It can be reproduced by
injecting slab allocation failures [1]. After the fix, the Rx queue no
longer comes to a halt.
[1]
# echo 10 > /sys/kernel/debug/failslab/times
# echo 1000 > /sys/kernel/debug/failslab/interval
# echo 100 > /sys/kernel/debug/failslab/probability
FAULT_INJECTION: forcing a failure.
name failslab, interval 1000, probability 100, space 0, times 8
[...]
Call Trace:
<IRQ>
dump_stack_lvl+0x34/0x44
should_fail.cold+0x32/0x37
should_failslab+0x5/0x10
kmem_cache_alloc_node+0x23/0x190
__alloc_skb+0x1f9/0x280
__netdev_alloc_skb+0x3a/0x150
mlxsw_pci_rdq_skb_alloc+0x24/0x90
mlxsw_pci_cq_tasklet+0x3dc/0x1200
tasklet_action_common.constprop.0+0x9f/0x100
__do_softirq+0xb5/0x252
irq_exit_rcu+0x7a/0xa0
common_interrupt+0x83/0xa0
</IRQ>
asm_common_interrupt+0x1e/0x40
RIP: 0010:cpuidle_enter_state+0xc8/0x340
[...]
mlxsw_spectrum2 0000:06:00.0: Failed to alloc skb for RDQ
Fixes: eda6500a98 ("mlxsw: Add PCI bus implementation")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/20211024064014.1060919-1-idosch@idosch.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Currently, max_macs is taking 70Kbytes of memory per function. This
size is not needed in all use cases, and is critical with large scale.
Hence, allow user to configure the number of max_macs.
For example, to reduce the number of max_macs to 1, execute::
$ devlink dev param set pci/0000:00:0b.0 name max_macs value 1 \
cmode driverinit
$ devlink dev reload pci/0000:00:0b.0
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Event EQ is an EQ which received the notification of almost all the
events generated by the NIC.
Currently, each event EQ is taking 512KB of memory. This size is not
needed in most use cases, and is critical with large scale. Hence,
allow user to configure the size of the event EQ.
For example to reduce event EQ size to 64, execute::
$ devlink resource set pci/0000:00:0b.0 path /event_eq_size/ size 64
$ devlink dev reload pci/0000:00:0b.0
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Currently, each I/O EQ is taking 128KB of memory. This size
is not needed in all use cases, and is critical with large scale.
Hence, allow user to configure the size of I/O EQs.
For example, to reduce I/O EQ size to 64, execute:
$ devlink resource set pci/0000:00:0b.0 path /io_eq_size/ size 64
$ devlink dev reload pci/0000:00:0b.0
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
The SWITCHDEV_FDB_ADD_TO_DEVICE is used for both adding new and replacing
existing entry. Implement support for replacing existing FDB entries in
mlx5 offload code.
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Paul Blakey <paulb@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Following two patterns in bridge code are used in multiple places where
similar code is duplicated:
- Lookup FDB entry from hashtable by address+vid pair.
- Notify software bridge and then delete existing FDB entry.
In order to improve code quality and prepare for following patch series
that also uses described patterns, extract the codes to dedicated helper
functions.
This commit doesn't change functionality.
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Paul Blakey <paulb@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
