diff options
author | 2023-02-21 18:24:12 -0800 | |
---|---|---|
committer | 2023-02-21 18:24:12 -0800 | |
commit | 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch) | |
tree | cc5c2d0a898769fd59549594fedb3ee6f84e59a0 /drivers/net/vmxnet3/vmxnet3_ethtool.c | |
download | linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip |
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
Pull networking updates from Jakub Kicinski:
"Core:
- Add dedicated kmem_cache for typical/small skb->head, avoid having
to access struct page at kfree time, and improve memory use.
- Introduce sysctl to set default RPS configuration for new netdevs.
- Define Netlink protocol specification format which can be used to
describe messages used by each family and auto-generate parsers.
Add tools for generating kernel data structures and uAPI headers.
- Expose all net/core sysctls inside netns.
- Remove 4s sleep in netpoll if carrier is instantly detected on
boot.
- Add configurable limit of MDB entries per port, and port-vlan.
- Continue populating drop reasons throughout the stack.
- Retire a handful of legacy Qdiscs and classifiers.
Protocols:
- Support IPv4 big TCP (TSO frames larger than 64kB).
- Add IP_LOCAL_PORT_RANGE socket option, to control local port range
on socket by socket basis.
- Track and report in procfs number of MPTCP sockets used.
- Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
manager.
- IPv6: don't check net.ipv6.route.max_size and rely on garbage
collection to free memory (similarly to IPv4).
- Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).
- ICMP: add per-rate limit counters.
- Add support for user scanning requests in ieee802154.
- Remove static WEP support.
- Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
reporting.
- WiFi 7 EHT channel puncturing support (client & AP).
BPF:
- Add a rbtree data structure following the "next-gen data structure"
precedent set by recently added linked list, that is, by using
kfunc + kptr instead of adding a new BPF map type.
- Expose XDP hints via kfuncs with initial support for RX hash and
timestamp metadata.
- Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
better support decap on GRE tunnel devices not operating in collect
metadata.
- Improve x86 JIT's codegen for PROBE_MEM runtime error checks.
- Remove the need for trace_printk_lock for bpf_trace_printk and
bpf_trace_vprintk helpers.
- Extend libbpf's bpf_tracing.h support for tracing arguments of
kprobes/uprobes and syscall as a special case.
- Significantly reduce the search time for module symbols by
livepatch and BPF.
- Enable cpumasks to be used as kptrs, which is useful for tracing
programs tracking which tasks end up running on which CPUs in
different time intervals.
- Add support for BPF trampoline on s390x and riscv64.
- Add capability to export the XDP features supported by the NIC.
- Add __bpf_kfunc tag for marking kernel functions as kfuncs.
- Add cgroup.memory=nobpf kernel parameter option to disable BPF
memory accounting for container environments.
Netfilter:
- Remove the CLUSTERIP target. It has been marked as obsolete for
years, and we still have WARN splats wrt races of the out-of-band
/proc interface installed by this target.
- Add 'destroy' commands to nf_tables. They are identical to the
existing 'delete' commands, but do not return an error if the
referenced object (set, chain, rule...) did not exist.
Driver API:
- Improve cpumask_local_spread() locality to help NICs set the right
IRQ affinity on AMD platforms.
- Separate C22 and C45 MDIO bus transactions more clearly.
- Introduce new DCB table to control DSCP rewrite on egress.
- Support configuration of Physical Layer Collision Avoidance (PLCA)
Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
shared medium Ethernet.
- Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
preemption of low priority frames by high priority frames.
- Add support for controlling MACSec offload using netlink SET.
- Rework devlink instance refcounts to allow registration and
de-registration under the instance lock. Split the code into
multiple files, drop some of the unnecessarily granular locks and
factor out common parts of netlink operation handling.
- Add TX frame aggregation parameters (for USB drivers).
- Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
messages with notifications for debug.
- Allow offloading of UDP NEW connections via act_ct.
- Add support for per action HW stats in TC.
- Support hardware miss to TC action (continue processing in SW from
a specific point in the action chain).
- Warn if old Wireless Extension user space interface is used with
modern cfg80211/mac80211 drivers. Do not support Wireless
Extensions for Wi-Fi 7 devices at all. Everyone should switch to
using nl80211 interface instead.
- Improve the CAN bit timing configuration. Use extack to return
error messages directly to user space, update the SJW handling,
including the definition of a new default value that will benefit
CAN-FD controllers, by increasing their oscillator tolerance.
New hardware / drivers:
- Ethernet:
- nVidia BlueField-3 support (control traffic driver)
- Ethernet support for imx93 SoCs
- Motorcomm yt8531 gigabit Ethernet PHY
- onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
- Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
- Amlogic gxl MDIO mux
- WiFi:
- RealTek RTL8188EU (rtl8xxxu)
- Qualcomm Wi-Fi 7 devices (ath12k)
- CAN:
- Renesas R-Car V4H
Drivers:
- Bluetooth:
- Set Per Platform Antenna Gain (PPAG) for Intel controllers.
- Ethernet NICs:
- Intel (1G, igc):
- support TSN / Qbv / packet scheduling features of i226 model
- Intel (100G, ice):
- use GNSS subsystem instead of TTY
- multi-buffer XDP support
- extend support for GPIO pins to E823 devices
- nVidia/Mellanox:
- update the shared buffer configuration on PFC commands
- implement PTP adjphase function for HW offset control
- TC support for Geneve and GRE with VF tunnel offload
- more efficient crypto key management method
- multi-port eswitch support
- Netronome/Corigine:
- add DCB IEEE support
- support IPsec offloading for NFP3800
- Freescale/NXP (enetc):
- support XDP_REDIRECT for XDP non-linear buffers
- improve reconfig, avoid link flap and waiting for idle
- support MAC Merge layer
- Other NICs:
- sfc/ef100: add basic devlink support for ef100
- ionic: rx_push mode operation (writing descriptors via MMIO)
- bnxt: use the auxiliary bus abstraction for RDMA
- r8169: disable ASPM and reset bus in case of tx timeout
- cpsw: support QSGMII mode for J721e CPSW9G
- cpts: support pulse-per-second output
- ngbe: add an mdio bus driver
- usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
- r8152: handle devices with FW with NCM support
- amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
- virtio-net: support multi buffer XDP
- virtio/vsock: replace virtio_vsock_pkt with sk_buff
- tsnep: XDP support
- Ethernet high-speed switches:
- nVidia/Mellanox (mlxsw):
- add support for latency TLV (in FW control messages)
- Microchip (sparx5):
- separate explicit and implicit traffic forwarding rules, make
the implicit rules always active
- add support for egress DSCP rewrite
- IS0 VCAP support (Ingress Classification)
- IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
etc.)
- ES2 VCAP support (Egress Access Control)
- support for Per-Stream Filtering and Policing (802.1Q,
8.6.5.1)
- Ethernet embedded switches:
- Marvell (mv88e6xxx):
- add MAB (port auth) offload support
- enable PTP receive for mv88e6390
- NXP (ocelot):
- support MAC Merge layer
- support for the the vsc7512 internal copper phys
- Microchip:
- lan9303: convert to PHYLINK
- lan966x: support TC flower filter statistics
- lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
- lan937x: support Credit Based Shaper configuration
- ksz9477: support Energy Efficient Ethernet
- other:
- qca8k: convert to regmap read/write API, use bulk operations
- rswitch: Improve TX timestamp accuracy
- Intel WiFi (iwlwifi):
- EHT (Wi-Fi 7) rate reporting
- STEP equalizer support: transfer some STEP (connection to radio
on platforms with integrated wifi) related parameters from the
BIOS to the firmware.
- Qualcomm 802.11ax WiFi (ath11k):
- IPQ5018 support
- Fine Timing Measurement (FTM) responder role support
- channel 177 support
- MediaTek WiFi (mt76):
- per-PHY LED support
- mt7996: EHT (Wi-Fi 7) support
- Wireless Ethernet Dispatch (WED) reset support
- switch to using page pool allocator
- RealTek WiFi (rtw89):
- support new version of Bluetooth co-existance
- Mobile:
- rmnet: support TX aggregation"
* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
page_pool: add a comment explaining the fragment counter usage
net: ethtool: fix __ethtool_dev_mm_supported() implementation
ethtool: pse-pd: Fix double word in comments
xsk: add linux/vmalloc.h to xsk.c
sefltests: netdevsim: wait for devlink instance after netns removal
selftest: fib_tests: Always cleanup before exit
net/mlx5e: Align IPsec ASO result memory to be as required by hardware
net/mlx5e: TC, Set CT miss to the specific ct action instance
net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
net/mlx5: Refactor tc miss handling to a single function
net/mlx5: Kconfig: Make tc offload depend on tc skb extension
net/sched: flower: Support hardware miss to tc action
net/sched: flower: Move filter handle initialization earlier
net/sched: cls_api: Support hardware miss to tc action
net/sched: Rename user cookie and act cookie
sfc: fix builds without CONFIG_RTC_LIB
sfc: clean up some inconsistent indentings
net/mlx4_en: Introduce flexible array to silence overflow warning
net: lan966x: Fix possible deadlock inside PTP
net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
...
Diffstat (limited to 'drivers/net/vmxnet3/vmxnet3_ethtool.c')
-rw-r--r-- | drivers/net/vmxnet3/vmxnet3_ethtool.c | 1354 |
1 files changed, 1354 insertions, 0 deletions
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c new file mode 100644 index 000000000..18cf7c723 --- /dev/null +++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c @@ -0,0 +1,1354 @@ +/* + * Linux driver for VMware's vmxnet3 ethernet NIC. + * + * Copyright (C) 2008-2022, VMware, Inc. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; version 2 of the License and no later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for more + * details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Maintained by: pv-drivers@vmware.com + * + */ + + +#include "vmxnet3_int.h" +#include <net/vxlan.h> +#include <net/geneve.h> + +#define VXLAN_UDP_PORT 8472 + +struct vmxnet3_stat_desc { + char desc[ETH_GSTRING_LEN]; + int offset; +}; + + +/* per tq stats maintained by the device */ +static const struct vmxnet3_stat_desc +vmxnet3_tq_dev_stats[] = { + /* description, offset */ + { "Tx Queue#", 0 }, + { " TSO pkts tx", offsetof(struct UPT1_TxStats, TSOPktsTxOK) }, + { " TSO bytes tx", offsetof(struct UPT1_TxStats, TSOBytesTxOK) }, + { " ucast pkts tx", offsetof(struct UPT1_TxStats, ucastPktsTxOK) }, + { " ucast bytes tx", offsetof(struct UPT1_TxStats, ucastBytesTxOK) }, + { " mcast pkts tx", offsetof(struct UPT1_TxStats, mcastPktsTxOK) }, + { " mcast bytes tx", offsetof(struct UPT1_TxStats, mcastBytesTxOK) }, + { " bcast pkts tx", offsetof(struct UPT1_TxStats, bcastPktsTxOK) }, + { " bcast bytes tx", offsetof(struct UPT1_TxStats, bcastBytesTxOK) }, + { " pkts tx err", offsetof(struct UPT1_TxStats, pktsTxError) }, + { " pkts tx discard", offsetof(struct UPT1_TxStats, pktsTxDiscard) }, +}; + +/* per tq stats maintained by the driver */ +static const struct vmxnet3_stat_desc +vmxnet3_tq_driver_stats[] = { + /* description, offset */ + {" drv dropped tx total", offsetof(struct vmxnet3_tq_driver_stats, + drop_total) }, + { " too many frags", offsetof(struct vmxnet3_tq_driver_stats, + drop_too_many_frags) }, + { " giant hdr", offsetof(struct vmxnet3_tq_driver_stats, + drop_oversized_hdr) }, + { " hdr err", offsetof(struct vmxnet3_tq_driver_stats, + drop_hdr_inspect_err) }, + { " tso", offsetof(struct vmxnet3_tq_driver_stats, + drop_tso) }, + { " ring full", offsetof(struct vmxnet3_tq_driver_stats, + tx_ring_full) }, + { " pkts linearized", offsetof(struct vmxnet3_tq_driver_stats, + linearized) }, + { " hdr cloned", offsetof(struct vmxnet3_tq_driver_stats, + copy_skb_header) }, + { " giant hdr", offsetof(struct vmxnet3_tq_driver_stats, + oversized_hdr) }, +}; + +/* per rq stats maintained by the device */ +static const struct vmxnet3_stat_desc +vmxnet3_rq_dev_stats[] = { + { "Rx Queue#", 0 }, + { " LRO pkts rx", offsetof(struct UPT1_RxStats, LROPktsRxOK) }, + { " LRO byte rx", offsetof(struct UPT1_RxStats, LROBytesRxOK) }, + { " ucast pkts rx", offsetof(struct UPT1_RxStats, ucastPktsRxOK) }, + { " ucast bytes rx", offsetof(struct UPT1_RxStats, ucastBytesRxOK) }, + { " mcast pkts rx", offsetof(struct UPT1_RxStats, mcastPktsRxOK) }, + { " mcast bytes rx", offsetof(struct UPT1_RxStats, mcastBytesRxOK) }, + { " bcast pkts rx", offsetof(struct UPT1_RxStats, bcastPktsRxOK) }, + { " bcast bytes rx", offsetof(struct UPT1_RxStats, bcastBytesRxOK) }, + { " pkts rx OOB", offsetof(struct UPT1_RxStats, pktsRxOutOfBuf) }, + { " pkts rx err", offsetof(struct UPT1_RxStats, pktsRxError) }, +}; + +/* per rq stats maintained by the driver */ +static const struct vmxnet3_stat_desc +vmxnet3_rq_driver_stats[] = { + /* description, offset */ + { " drv dropped rx total", offsetof(struct vmxnet3_rq_driver_stats, + drop_total) }, + { " err", offsetof(struct vmxnet3_rq_driver_stats, + drop_err) }, + { " fcs", offsetof(struct vmxnet3_rq_driver_stats, + drop_fcs) }, + { " rx buf alloc fail", offsetof(struct vmxnet3_rq_driver_stats, + rx_buf_alloc_failure) }, +}; + +/* global stats maintained by the driver */ +static const struct vmxnet3_stat_desc +vmxnet3_global_stats[] = { + /* description, offset */ + { "tx timeout count", offsetof(struct vmxnet3_adapter, + tx_timeout_count) } +}; + + +void +vmxnet3_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) +{ + struct vmxnet3_adapter *adapter; + struct vmxnet3_tq_driver_stats *drvTxStats; + struct vmxnet3_rq_driver_stats *drvRxStats; + struct UPT1_TxStats *devTxStats; + struct UPT1_RxStats *devRxStats; + unsigned long flags; + int i; + + adapter = netdev_priv(netdev); + + /* Collect the dev stats into the shared area */ + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_STATS); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + + for (i = 0; i < adapter->num_tx_queues; i++) { + devTxStats = &adapter->tqd_start[i].stats; + drvTxStats = &adapter->tx_queue[i].stats; + stats->tx_packets += devTxStats->ucastPktsTxOK + + devTxStats->mcastPktsTxOK + + devTxStats->bcastPktsTxOK; + stats->tx_bytes += devTxStats->ucastBytesTxOK + + devTxStats->mcastBytesTxOK + + devTxStats->bcastBytesTxOK; + stats->tx_errors += devTxStats->pktsTxError; + stats->tx_dropped += drvTxStats->drop_total; + } + + for (i = 0; i < adapter->num_rx_queues; i++) { + devRxStats = &adapter->rqd_start[i].stats; + drvRxStats = &adapter->rx_queue[i].stats; + stats->rx_packets += devRxStats->ucastPktsRxOK + + devRxStats->mcastPktsRxOK + + devRxStats->bcastPktsRxOK; + + stats->rx_bytes += devRxStats->ucastBytesRxOK + + devRxStats->mcastBytesRxOK + + devRxStats->bcastBytesRxOK; + + stats->rx_errors += devRxStats->pktsRxError; + stats->rx_dropped += drvRxStats->drop_total; + stats->multicast += devRxStats->mcastPktsRxOK; + } +} + +static int +vmxnet3_get_sset_count(struct net_device *netdev, int sset) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + switch (sset) { + case ETH_SS_STATS: + return (ARRAY_SIZE(vmxnet3_tq_dev_stats) + + ARRAY_SIZE(vmxnet3_tq_driver_stats)) * + adapter->num_tx_queues + + (ARRAY_SIZE(vmxnet3_rq_dev_stats) + + ARRAY_SIZE(vmxnet3_rq_driver_stats)) * + adapter->num_rx_queues + + ARRAY_SIZE(vmxnet3_global_stats); + default: + return -EOPNOTSUPP; + } +} + + +/* This is a version 2 of the vmxnet3 ethtool_regs which goes hand in hand with + * the version 2 of the vmxnet3 support for ethtool(8) --register-dump. + * Therefore, if any registers are added, removed or modified, then a version + * bump and a corresponding change in the vmxnet3 support for ethtool(8) + * --register-dump would be required. + */ +static int +vmxnet3_get_regs_len(struct net_device *netdev) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + return ((9 /* BAR1 registers */ + + (1 + adapter->intr.num_intrs) + + (1 + adapter->num_tx_queues * 17 /* Tx queue registers */) + + (1 + adapter->num_rx_queues * 23 /* Rx queue registers */)) * + sizeof(u32)); +} + + +static void +vmxnet3_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + strscpy(drvinfo->driver, vmxnet3_driver_name, sizeof(drvinfo->driver)); + + strscpy(drvinfo->version, VMXNET3_DRIVER_VERSION_REPORT, + sizeof(drvinfo->version)); + + strscpy(drvinfo->bus_info, pci_name(adapter->pdev), + sizeof(drvinfo->bus_info)); +} + + +static void +vmxnet3_get_strings(struct net_device *netdev, u32 stringset, u8 *buf) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + int i, j; + + if (stringset != ETH_SS_STATS) + return; + + for (j = 0; j < adapter->num_tx_queues; j++) { + for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_dev_stats); i++) + ethtool_sprintf(&buf, vmxnet3_tq_dev_stats[i].desc); + for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_driver_stats); i++) + ethtool_sprintf(&buf, vmxnet3_tq_driver_stats[i].desc); + } + + for (j = 0; j < adapter->num_rx_queues; j++) { + for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_dev_stats); i++) + ethtool_sprintf(&buf, vmxnet3_rq_dev_stats[i].desc); + for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_driver_stats); i++) + ethtool_sprintf(&buf, vmxnet3_rq_driver_stats[i].desc); + } + + for (i = 0; i < ARRAY_SIZE(vmxnet3_global_stats); i++) + ethtool_sprintf(&buf, vmxnet3_global_stats[i].desc); +} + +netdev_features_t vmxnet3_fix_features(struct net_device *netdev, + netdev_features_t features) +{ + /* If Rx checksum is disabled, then LRO should also be disabled */ + if (!(features & NETIF_F_RXCSUM)) + features &= ~NETIF_F_LRO; + + return features; +} + +netdev_features_t vmxnet3_features_check(struct sk_buff *skb, + struct net_device *netdev, + netdev_features_t features) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + /* Validate if the tunneled packet is being offloaded by the device */ + if (VMXNET3_VERSION_GE_4(adapter) && + skb->encapsulation && skb->ip_summed == CHECKSUM_PARTIAL) { + u8 l4_proto = 0; + u16 port; + struct udphdr *udph; + + switch (vlan_get_protocol(skb)) { + case htons(ETH_P_IP): + l4_proto = ip_hdr(skb)->protocol; + break; + case htons(ETH_P_IPV6): + l4_proto = ipv6_hdr(skb)->nexthdr; + break; + default: + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); + } + + switch (l4_proto) { + case IPPROTO_UDP: + udph = udp_hdr(skb); + port = be16_to_cpu(udph->dest); + /* Check if offloaded port is supported */ + if (port != GENEVE_UDP_PORT && + port != IANA_VXLAN_UDP_PORT && + port != VXLAN_UDP_PORT) { + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); + } + break; + default: + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); + } + } + return features; +} + +static void vmxnet3_enable_encap_offloads(struct net_device *netdev, netdev_features_t features) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + if (VMXNET3_VERSION_GE_4(adapter)) { + netdev->hw_enc_features |= NETIF_F_SG | NETIF_F_RXCSUM | + NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_LRO; + if (features & NETIF_F_GSO_UDP_TUNNEL) + netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL; + if (features & NETIF_F_GSO_UDP_TUNNEL_CSUM) + netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM; + } + if (VMXNET3_VERSION_GE_7(adapter)) { + unsigned long flags; + + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_GENEVE_CHECKSUM_OFFLOAD)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_GENEVE_CHECKSUM_OFFLOAD; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_VXLAN_CHECKSUM_OFFLOAD)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_VXLAN_CHECKSUM_OFFLOAD; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_GENEVE_TSO)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_GENEVE_TSO; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_VXLAN_TSO)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_VXLAN_TSO; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_GENEVE_OUTER_CHECKSUM_OFFLOAD)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_GENEVE_OUTER_CHECKSUM_OFFLOAD; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_VXLAN_OUTER_CHECKSUM_OFFLOAD)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_VXLAN_OUTER_CHECKSUM_OFFLOAD; + } + + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DCR, adapter->dev_caps[0]); + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_DCR0_REG); + adapter->dev_caps[0] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + + if (!(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_GENEVE_CHECKSUM_OFFLOAD)) && + !(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_VXLAN_CHECKSUM_OFFLOAD)) && + !(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_GENEVE_TSO)) && + !(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_VXLAN_TSO))) { + netdev->hw_enc_features &= ~NETIF_F_GSO_UDP_TUNNEL; + } + if (!(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_GENEVE_OUTER_CHECKSUM_OFFLOAD)) && + !(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_VXLAN_OUTER_CHECKSUM_OFFLOAD))) { + netdev->hw_enc_features &= ~NETIF_F_GSO_UDP_TUNNEL_CSUM; + } + } +} + +static void vmxnet3_disable_encap_offloads(struct net_device *netdev) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + if (VMXNET3_VERSION_GE_4(adapter)) { + netdev->hw_enc_features &= ~(NETIF_F_SG | NETIF_F_RXCSUM | + NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_LRO | NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM); + } + if (VMXNET3_VERSION_GE_7(adapter)) { + unsigned long flags; + + adapter->dev_caps[0] &= ~(1UL << VMXNET3_CAP_GENEVE_CHECKSUM_OFFLOAD | + 1UL << VMXNET3_CAP_VXLAN_CHECKSUM_OFFLOAD | + 1UL << VMXNET3_CAP_GENEVE_TSO | + 1UL << VMXNET3_CAP_VXLAN_TSO | + 1UL << VMXNET3_CAP_GENEVE_OUTER_CHECKSUM_OFFLOAD | + 1UL << VMXNET3_CAP_VXLAN_OUTER_CHECKSUM_OFFLOAD); + + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DCR, adapter->dev_caps[0]); + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_DCR0_REG); + adapter->dev_caps[0] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + } +} + +int vmxnet3_set_features(struct net_device *netdev, netdev_features_t features) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + unsigned long flags; + netdev_features_t changed = features ^ netdev->features; + netdev_features_t tun_offload_mask = NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM; + u8 udp_tun_enabled = (netdev->features & tun_offload_mask) != 0; + + if (changed & (NETIF_F_RXCSUM | NETIF_F_LRO | + NETIF_F_HW_VLAN_CTAG_RX | tun_offload_mask)) { + if (features & NETIF_F_RXCSUM) + adapter->shared->devRead.misc.uptFeatures |= + UPT1_F_RXCSUM; + else + adapter->shared->devRead.misc.uptFeatures &= + ~UPT1_F_RXCSUM; + + /* update hardware LRO capability accordingly */ + if (features & NETIF_F_LRO) + adapter->shared->devRead.misc.uptFeatures |= + UPT1_F_LRO; + else + adapter->shared->devRead.misc.uptFeatures &= + ~UPT1_F_LRO; + + if (features & NETIF_F_HW_VLAN_CTAG_RX) + adapter->shared->devRead.misc.uptFeatures |= + UPT1_F_RXVLAN; + else + adapter->shared->devRead.misc.uptFeatures &= + ~UPT1_F_RXVLAN; + + if ((features & tun_offload_mask) != 0) { + vmxnet3_enable_encap_offloads(netdev, features); + adapter->shared->devRead.misc.uptFeatures |= + UPT1_F_RXINNEROFLD; + } else if ((features & tun_offload_mask) == 0 && + udp_tun_enabled) { + vmxnet3_disable_encap_offloads(netdev); + adapter->shared->devRead.misc.uptFeatures &= + ~UPT1_F_RXINNEROFLD; + } + + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_UPDATE_FEATURE); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + } + return 0; +} + +static void +vmxnet3_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats *stats, u64 *buf) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + unsigned long flags; + u8 *base; + int i; + int j = 0; + + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_STATS); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + + /* this does assume each counter is 64-bit wide */ + for (j = 0; j < adapter->num_tx_queues; j++) { + base = (u8 *)&adapter->tqd_start[j].stats; + *buf++ = (u64)j; + for (i = 1; i < ARRAY_SIZE(vmxnet3_tq_dev_stats); i++) + *buf++ = *(u64 *)(base + + vmxnet3_tq_dev_stats[i].offset); + + base = (u8 *)&adapter->tx_queue[j].stats; + for (i = 0; i < ARRAY_SIZE(vmxnet3_tq_driver_stats); i++) + *buf++ = *(u64 *)(base + + vmxnet3_tq_driver_stats[i].offset); + } + + for (j = 0; j < adapter->num_rx_queues; j++) { + base = (u8 *)&adapter->rqd_start[j].stats; + *buf++ = (u64) j; + for (i = 1; i < ARRAY_SIZE(vmxnet3_rq_dev_stats); i++) + *buf++ = *(u64 *)(base + + vmxnet3_rq_dev_stats[i].offset); + + base = (u8 *)&adapter->rx_queue[j].stats; + for (i = 0; i < ARRAY_SIZE(vmxnet3_rq_driver_stats); i++) + *buf++ = *(u64 *)(base + + vmxnet3_rq_driver_stats[i].offset); + } + + base = (u8 *)adapter; + for (i = 0; i < ARRAY_SIZE(vmxnet3_global_stats); i++) + *buf++ = *(u64 *)(base + vmxnet3_global_stats[i].offset); +} + + +/* This is a version 2 of the vmxnet3 ethtool_regs which goes hand in hand with + * the version 2 of the vmxnet3 support for ethtool(8) --register-dump. + * Therefore, if any registers are added, removed or modified, then a version + * bump and a corresponding change in the vmxnet3 support for ethtool(8) + * --register-dump would be required. + */ +static void +vmxnet3_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + u32 *buf = p; + int i = 0, j = 0; + + memset(p, 0, vmxnet3_get_regs_len(netdev)); + + regs->version = 2; + + /* Update vmxnet3_get_regs_len if we want to dump more registers */ + + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_VRRS); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_UVRS); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_DSAL); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_DSAH); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_MACL); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_MACH); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_ICR); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_ECR); + + buf[j++] = adapter->intr.num_intrs; + for (i = 0; i < adapter->intr.num_intrs; i++) { + buf[j++] = VMXNET3_READ_BAR0_REG(adapter, VMXNET3_REG_IMR + + i * VMXNET3_REG_ALIGN); + } + + buf[j++] = adapter->num_tx_queues; + for (i = 0; i < adapter->num_tx_queues; i++) { + struct vmxnet3_tx_queue *tq = &adapter->tx_queue[i]; + + buf[j++] = VMXNET3_READ_BAR0_REG(adapter, adapter->tx_prod_offset + + i * VMXNET3_REG_ALIGN); + + buf[j++] = VMXNET3_GET_ADDR_LO(tq->tx_ring.basePA); + buf[j++] = VMXNET3_GET_ADDR_HI(tq->tx_ring.basePA); + buf[j++] = tq->tx_ring.size; + buf[j++] = tq->tx_ring.next2fill; + buf[j++] = tq->tx_ring.next2comp; + buf[j++] = tq->tx_ring.gen; + + buf[j++] = VMXNET3_GET_ADDR_LO(tq->data_ring.basePA); + buf[j++] = VMXNET3_GET_ADDR_HI(tq->data_ring.basePA); + buf[j++] = tq->data_ring.size; + buf[j++] = tq->txdata_desc_size; + + buf[j++] = VMXNET3_GET_ADDR_LO(tq->comp_ring.basePA); + buf[j++] = VMXNET3_GET_ADDR_HI(tq->comp_ring.basePA); + buf[j++] = tq->comp_ring.size; + buf[j++] = tq->comp_ring.next2proc; + buf[j++] = tq->comp_ring.gen; + + buf[j++] = tq->stopped; + } + + buf[j++] = adapter->num_rx_queues; + for (i = 0; i < adapter->num_rx_queues; i++) { + struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i]; + + buf[j++] = VMXNET3_READ_BAR0_REG(adapter, adapter->rx_prod_offset + + i * VMXNET3_REG_ALIGN); + buf[j++] = VMXNET3_READ_BAR0_REG(adapter, adapter->rx_prod2_offset + + i * VMXNET3_REG_ALIGN); + + buf[j++] = VMXNET3_GET_ADDR_LO(rq->rx_ring[0].basePA); + buf[j++] = VMXNET3_GET_ADDR_HI(rq->rx_ring[0].basePA); + buf[j++] = rq->rx_ring[0].size; + buf[j++] = rq->rx_ring[0].next2fill; + buf[j++] = rq->rx_ring[0].next2comp; + buf[j++] = rq->rx_ring[0].gen; + + buf[j++] = VMXNET3_GET_ADDR_LO(rq->rx_ring[1].basePA); + buf[j++] = VMXNET3_GET_ADDR_HI(rq->rx_ring[1].basePA); + buf[j++] = rq->rx_ring[1].size; + buf[j++] = rq->rx_ring[1].next2fill; + buf[j++] = rq->rx_ring[1].next2comp; + buf[j++] = rq->rx_ring[1].gen; + + buf[j++] = VMXNET3_GET_ADDR_LO(rq->data_ring.basePA); + buf[j++] = VMXNET3_GET_ADDR_HI(rq->data_ring.basePA); + buf[j++] = rq->rx_ring[0].size; + buf[j++] = rq->data_ring.desc_size; + + buf[j++] = VMXNET3_GET_ADDR_LO(rq->comp_ring.basePA); + buf[j++] = VMXNET3_GET_ADDR_HI(rq->comp_ring.basePA); + buf[j++] = rq->comp_ring.size; + buf[j++] = rq->comp_ring.next2proc; + buf[j++] = rq->comp_ring.gen; + } +} + + +static void +vmxnet3_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + wol->supported = WAKE_UCAST | WAKE_ARP | WAKE_MAGIC; + wol->wolopts = adapter->wol; +} + + +static int +vmxnet3_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + if (wol->wolopts & (WAKE_PHY | WAKE_MCAST | WAKE_BCAST | + WAKE_MAGICSECURE)) { + return -EOPNOTSUPP; + } + + adapter->wol = wol->wolopts; + + device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol); + + return 0; +} + + +static int +vmxnet3_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *ecmd) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + ethtool_link_ksettings_zero_link_mode(ecmd, supported); + ethtool_link_ksettings_add_link_mode(ecmd, supported, 10000baseT_Full); + ethtool_link_ksettings_add_link_mode(ecmd, supported, 1000baseT_Full); + ethtool_link_ksettings_add_link_mode(ecmd, supported, TP); + ethtool_link_ksettings_zero_link_mode(ecmd, advertising); + ethtool_link_ksettings_add_link_mode(ecmd, advertising, TP); + ecmd->base.port = PORT_TP; + + if (adapter->link_speed) { + ecmd->base.speed = adapter->link_speed; + ecmd->base.duplex = DUPLEX_FULL; + } else { + ecmd->base.speed = SPEED_UNKNOWN; + ecmd->base.duplex = DUPLEX_UNKNOWN; + } + return 0; +} + +static void +vmxnet3_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kernel_param, + struct netlink_ext_ack *extack) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + param->rx_max_pending = VMXNET3_RX_RING_MAX_SIZE; + param->tx_max_pending = VMXNET3_TX_RING_MAX_SIZE; + param->rx_mini_max_pending = VMXNET3_VERSION_GE_3(adapter) ? + VMXNET3_RXDATA_DESC_MAX_SIZE : 0; + param->rx_jumbo_max_pending = VMXNET3_RX_RING2_MAX_SIZE; + + param->rx_pending = adapter->rx_ring_size; + param->tx_pending = adapter->tx_ring_size; + param->rx_mini_pending = VMXNET3_VERSION_GE_3(adapter) ? + adapter->rxdata_desc_size : 0; + param->rx_jumbo_pending = adapter->rx_ring2_size; +} + +static int +vmxnet3_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kernel_param, + struct netlink_ext_ack *extack) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + u32 new_tx_ring_size, new_rx_ring_size, new_rx_ring2_size; + u16 new_rxdata_desc_size; + u32 sz; + int err = 0; + + if (param->tx_pending == 0 || param->tx_pending > + VMXNET3_TX_RING_MAX_SIZE) + return -EINVAL; + + if (param->rx_pending == 0 || param->rx_pending > + VMXNET3_RX_RING_MAX_SIZE) + return -EINVAL; + + if (param->rx_jumbo_pending == 0 || + param->rx_jumbo_pending > VMXNET3_RX_RING2_MAX_SIZE) + return -EINVAL; + + /* if adapter not yet initialized, do nothing */ + if (adapter->rx_buf_per_pkt == 0) { + netdev_err(netdev, "adapter not completely initialized, " + "ring size cannot be changed yet\n"); + return -EOPNOTSUPP; + } + + if (VMXNET3_VERSION_GE_3(adapter)) { + if (param->rx_mini_pending > VMXNET3_RXDATA_DESC_MAX_SIZE) + return -EINVAL; + } else if (param->rx_mini_pending != 0) { + return -EINVAL; + } + + /* round it up to a multiple of VMXNET3_RING_SIZE_ALIGN */ + new_tx_ring_size = (param->tx_pending + VMXNET3_RING_SIZE_MASK) & + ~VMXNET3_RING_SIZE_MASK; + new_tx_ring_size = min_t(u32, new_tx_ring_size, + VMXNET3_TX_RING_MAX_SIZE); + if (new_tx_ring_size > VMXNET3_TX_RING_MAX_SIZE || (new_tx_ring_size % + VMXNET3_RING_SIZE_ALIGN) != 0) + return -EINVAL; + + /* ring0 has to be a multiple of + * rx_buf_per_pkt * VMXNET3_RING_SIZE_ALIGN + */ + sz = adapter->rx_buf_per_pkt * VMXNET3_RING_SIZE_ALIGN; + new_rx_ring_size = (param->rx_pending + sz - 1) / sz * sz; + new_rx_ring_size = min_t(u32, new_rx_ring_size, + VMXNET3_RX_RING_MAX_SIZE / sz * sz); + if (new_rx_ring_size > VMXNET3_RX_RING_MAX_SIZE || (new_rx_ring_size % + sz) != 0) + return -EINVAL; + + /* ring2 has to be a multiple of VMXNET3_RING_SIZE_ALIGN */ + new_rx_ring2_size = (param->rx_jumbo_pending + VMXNET3_RING_SIZE_MASK) & + ~VMXNET3_RING_SIZE_MASK; + new_rx_ring2_size = min_t(u32, new_rx_ring2_size, + VMXNET3_RX_RING2_MAX_SIZE); + + /* For v7 and later, keep ring size power of 2 for UPT */ + if (VMXNET3_VERSION_GE_7(adapter)) { + new_tx_ring_size = rounddown_pow_of_two(new_tx_ring_size); + new_rx_ring_size = rounddown_pow_of_two(new_rx_ring_size); + new_rx_ring2_size = rounddown_pow_of_two(new_rx_ring2_size); + } + + /* rx data ring buffer size has to be a multiple of + * VMXNET3_RXDATA_DESC_SIZE_ALIGN + */ + new_rxdata_desc_size = + (param->rx_mini_pending + VMXNET3_RXDATA_DESC_SIZE_MASK) & + ~VMXNET3_RXDATA_DESC_SIZE_MASK; + new_rxdata_desc_size = min_t(u16, new_rxdata_desc_size, + VMXNET3_RXDATA_DESC_MAX_SIZE); + + if (new_tx_ring_size == adapter->tx_ring_size && + new_rx_ring_size == adapter->rx_ring_size && + new_rx_ring2_size == adapter->rx_ring2_size && + new_rxdata_desc_size == adapter->rxdata_desc_size) { + return 0; + } + + /* + * Reset_work may be in the middle of resetting the device, wait for its + * completion. + */ + while (test_and_set_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state)) + usleep_range(1000, 2000); + + if (netif_running(netdev)) { + vmxnet3_quiesce_dev(adapter); + vmxnet3_reset_dev(adapter); + + /* recreate the rx queue and the tx queue based on the + * new sizes */ + vmxnet3_tq_destroy_all(adapter); + vmxnet3_rq_destroy_all(adapter); + + err = vmxnet3_create_queues(adapter, new_tx_ring_size, + new_rx_ring_size, new_rx_ring2_size, + adapter->txdata_desc_size, + new_rxdata_desc_size); + if (err) { + /* failed, most likely because of OOM, try default + * size */ + netdev_err(netdev, "failed to apply new sizes, " + "try the default ones\n"); + new_rx_ring_size = VMXNET3_DEF_RX_RING_SIZE; + new_rx_ring2_size = VMXNET3_DEF_RX_RING2_SIZE; + new_tx_ring_size = VMXNET3_DEF_TX_RING_SIZE; + new_rxdata_desc_size = VMXNET3_VERSION_GE_3(adapter) ? + VMXNET3_DEF_RXDATA_DESC_SIZE : 0; + + err = vmxnet3_create_queues(adapter, + new_tx_ring_size, + new_rx_ring_size, + new_rx_ring2_size, + adapter->txdata_desc_size, + new_rxdata_desc_size); + if (err) { + netdev_err(netdev, "failed to create queues " + "with default sizes. Closing it\n"); + goto out; + } + } + + err = vmxnet3_activate_dev(adapter); + if (err) + netdev_err(netdev, "failed to re-activate, error %d." + " Closing it\n", err); + } + adapter->tx_ring_size = new_tx_ring_size; + adapter->rx_ring_size = new_rx_ring_size; + adapter->rx_ring2_size = new_rx_ring2_size; + adapter->rxdata_desc_size = new_rxdata_desc_size; + +out: + clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state); + if (err) + vmxnet3_force_close(adapter); + + return err; +} + +static int +vmxnet3_get_rss_hash_opts(struct vmxnet3_adapter *adapter, + struct ethtool_rxnfc *info) +{ + enum Vmxnet3_RSSField rss_fields; + + if (netif_running(adapter->netdev)) { + unsigned long flags; + + spin_lock_irqsave(&adapter->cmd_lock, flags); + + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_GET_RSS_FIELDS); + rss_fields = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + } else { + rss_fields = adapter->rss_fields; + } + + info->data = 0; + + /* Report default options for RSS on vmxnet3 */ + switch (info->flow_type) { + case TCP_V4_FLOW: + case TCP_V6_FLOW: + info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3 | + RXH_IP_SRC | RXH_IP_DST; + break; + case UDP_V4_FLOW: + if (rss_fields & VMXNET3_RSS_FIELDS_UDPIP4) + info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + info->data |= RXH_IP_SRC | RXH_IP_DST; + break; + case AH_ESP_V4_FLOW: + case AH_V4_FLOW: + case ESP_V4_FLOW: + if (rss_fields & VMXNET3_RSS_FIELDS_ESPIP4) + info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + fallthrough; + case SCTP_V4_FLOW: + case IPV4_FLOW: + info->data |= RXH_IP_SRC | RXH_IP_DST; + break; + case UDP_V6_FLOW: + if (rss_fields & VMXNET3_RSS_FIELDS_UDPIP6) + info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + info->data |= RXH_IP_SRC | RXH_IP_DST; + break; + case AH_ESP_V6_FLOW: + case AH_V6_FLOW: + case ESP_V6_FLOW: + if (VMXNET3_VERSION_GE_6(adapter) && + (rss_fields & VMXNET3_RSS_FIELDS_ESPIP6)) + info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + fallthrough; + case SCTP_V6_FLOW: + case IPV6_FLOW: + info->data |= RXH_IP_SRC | RXH_IP_DST; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int +vmxnet3_set_rss_hash_opt(struct net_device *netdev, + struct vmxnet3_adapter *adapter, + struct ethtool_rxnfc *nfc) +{ + enum Vmxnet3_RSSField rss_fields = adapter->rss_fields; + + /* RSS does not support anything other than hashing + * to queues on src and dst IPs and ports + */ + if (nfc->data & ~(RXH_IP_SRC | RXH_IP_DST | + RXH_L4_B_0_1 | RXH_L4_B_2_3)) + return -EINVAL; + + switch (nfc->flow_type) { + case TCP_V4_FLOW: + case TCP_V6_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST) || + !(nfc->data & RXH_L4_B_0_1) || + !(nfc->data & RXH_L4_B_2_3)) + return -EINVAL; + break; + case UDP_V4_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST)) + return -EINVAL; + switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + case 0: + rss_fields &= ~VMXNET3_RSS_FIELDS_UDPIP4; + break; + case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + rss_fields |= VMXNET3_RSS_FIELDS_UDPIP4; + break; + default: + return -EINVAL; + } + break; + case UDP_V6_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST)) + return -EINVAL; + switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + case 0: + rss_fields &= ~VMXNET3_RSS_FIELDS_UDPIP6; + break; + case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + rss_fields |= VMXNET3_RSS_FIELDS_UDPIP6; + break; + default: + return -EINVAL; + } + break; + case ESP_V4_FLOW: + case AH_V4_FLOW: + case AH_ESP_V4_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST)) + return -EINVAL; + switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + case 0: + rss_fields &= ~VMXNET3_RSS_FIELDS_ESPIP4; + break; + case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + rss_fields |= VMXNET3_RSS_FIELDS_ESPIP4; + break; + default: + return -EINVAL; + } + break; + case ESP_V6_FLOW: + case AH_V6_FLOW: + case AH_ESP_V6_FLOW: + if (!VMXNET3_VERSION_GE_6(adapter)) + return -EOPNOTSUPP; + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST)) + return -EINVAL; + switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + case 0: + rss_fields &= ~VMXNET3_RSS_FIELDS_ESPIP6; + break; + case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + rss_fields |= VMXNET3_RSS_FIELDS_ESPIP6; + break; + default: + return -EINVAL; + } + break; + case SCTP_V4_FLOW: + case SCTP_V6_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST) || + (nfc->data & RXH_L4_B_0_1) || + (nfc->data & RXH_L4_B_2_3)) + return -EINVAL; + break; + default: + return -EINVAL; + } + + /* if we changed something we need to update flags */ + if (rss_fields != adapter->rss_fields) { + adapter->default_rss_fields = false; + if (netif_running(netdev)) { + struct Vmxnet3_DriverShared *shared = adapter->shared; + union Vmxnet3_CmdInfo *cmdInfo = &shared->cu.cmdInfo; + unsigned long flags; + + if (VMXNET3_VERSION_GE_7(adapter)) { + if ((rss_fields & VMXNET3_RSS_FIELDS_UDPIP4 || + rss_fields & VMXNET3_RSS_FIELDS_UDPIP6) && + vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_UDP_RSS)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_UDP_RSS; + } else { + adapter->dev_caps[0] &= ~(1UL << VMXNET3_CAP_UDP_RSS); + } + if ((rss_fields & VMXNET3_RSS_FIELDS_ESPIP4) && + vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_ESP_RSS_IPV4)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_ESP_RSS_IPV4; + } else { + adapter->dev_caps[0] &= ~(1UL << VMXNET3_CAP_ESP_RSS_IPV4); + } + if ((rss_fields & VMXNET3_RSS_FIELDS_ESPIP6) && + vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_ESP_RSS_IPV6)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_ESP_RSS_IPV6; + } else { + adapter->dev_caps[0] &= ~(1UL << VMXNET3_CAP_ESP_RSS_IPV6); + } + + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DCR, + adapter->dev_caps[0]); + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_GET_DCR0_REG); + adapter->dev_caps[0] = VMXNET3_READ_BAR1_REG(adapter, + VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + } + spin_lock_irqsave(&adapter->cmd_lock, flags); + cmdInfo->setRssFields = rss_fields; + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_SET_RSS_FIELDS); + + /* Not all requested RSS may get applied, so get and + * cache what was actually applied. + */ + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_GET_RSS_FIELDS); + adapter->rss_fields = + VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + } else { + /* When the device is activated, we will try to apply + * these rules and cache the applied value later. + */ + adapter->rss_fields = rss_fields; + } + } + return 0; +} + +static int +vmxnet3_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *info, + u32 *rules) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + int err = 0; + + switch (info->cmd) { + case ETHTOOL_GRXRINGS: + info->data = adapter->num_rx_queues; + break; + case ETHTOOL_GRXFH: + if (!VMXNET3_VERSION_GE_4(adapter)) { + err = -EOPNOTSUPP; + break; + } +#ifdef VMXNET3_RSS + if (!adapter->rss) { + err = -EOPNOTSUPP; + break; + } +#endif + err = vmxnet3_get_rss_hash_opts(adapter, info); + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + +static int +vmxnet3_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *info) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + int err = 0; + + if (!VMXNET3_VERSION_GE_4(adapter)) { + err = -EOPNOTSUPP; + goto done; + } +#ifdef VMXNET3_RSS + if (!adapter->rss) { + err = -EOPNOTSUPP; + goto done; + } +#endif + + switch (info->cmd) { + case ETHTOOL_SRXFH: + err = vmxnet3_set_rss_hash_opt(netdev, adapter, info); + break; + default: + err = -EOPNOTSUPP; + break; + } + +done: + return err; +} + +#ifdef VMXNET3_RSS +static u32 +vmxnet3_get_rss_indir_size(struct net_device *netdev) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + struct UPT1_RSSConf *rssConf = adapter->rss_conf; + + return rssConf->indTableSize; +} + +static int +vmxnet3_get_rss(struct net_device *netdev, u32 *p, u8 *key, u8 *hfunc) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + struct UPT1_RSSConf *rssConf = adapter->rss_conf; + unsigned int n = rssConf->indTableSize; + + if (hfunc) + *hfunc = ETH_RSS_HASH_TOP; + if (!p) + return 0; + if (n > UPT1_RSS_MAX_IND_TABLE_SIZE) + return 0; + while (n--) + p[n] = rssConf->indTable[n]; + return 0; + +} + +static int +vmxnet3_set_rss(struct net_device *netdev, const u32 *p, const u8 *key, + const u8 hfunc) +{ + unsigned int i; + unsigned long flags; + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + struct UPT1_RSSConf *rssConf = adapter->rss_conf; + + /* We do not allow change in unsupported parameters */ + if (key || + (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)) + return -EOPNOTSUPP; + if (!p) + return 0; + for (i = 0; i < rssConf->indTableSize; i++) + rssConf->indTable[i] = p[i]; + + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_UPDATE_RSSIDT); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + + return 0; + +} +#endif + +static int vmxnet3_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + if (!VMXNET3_VERSION_GE_3(adapter)) + return -EOPNOTSUPP; + + switch (adapter->coal_conf->coalMode) { + case VMXNET3_COALESCE_DISABLED: + /* struct ethtool_coalesce is already initialized to 0 */ + break; + case VMXNET3_COALESCE_ADAPT: + ec->use_adaptive_rx_coalesce = true; + break; + case VMXNET3_COALESCE_STATIC: + ec->tx_max_coalesced_frames = + adapter->coal_conf->coalPara.coalStatic.tx_comp_depth; + ec->rx_max_coalesced_frames = + adapter->coal_conf->coalPara.coalStatic.rx_depth; + break; + case VMXNET3_COALESCE_RBC: { + u32 rbc_rate; + + rbc_rate = adapter->coal_conf->coalPara.coalRbc.rbc_rate; + ec->rx_coalesce_usecs = VMXNET3_COAL_RBC_USECS(rbc_rate); + } + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int vmxnet3_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + struct Vmxnet3_DriverShared *shared = adapter->shared; + union Vmxnet3_CmdInfo *cmdInfo = &shared->cu.cmdInfo; + unsigned long flags; + + if (!VMXNET3_VERSION_GE_3(adapter)) + return -EOPNOTSUPP; + + if ((ec->rx_coalesce_usecs == 0) && + (ec->use_adaptive_rx_coalesce == 0) && + (ec->tx_max_coalesced_frames == 0) && + (ec->rx_max_coalesced_frames == 0)) { + memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf)); + adapter->coal_conf->coalMode = VMXNET3_COALESCE_DISABLED; + goto done; + } + + if (ec->rx_coalesce_usecs != 0) { + u32 rbc_rate; + + if ((ec->use_adaptive_rx_coalesce != 0) || + (ec->tx_max_coalesced_frames != 0) || + (ec->rx_max_coalesced_frames != 0)) { + return -EINVAL; + } + + rbc_rate = VMXNET3_COAL_RBC_RATE(ec->rx_coalesce_usecs); + if (rbc_rate < VMXNET3_COAL_RBC_MIN_RATE || + rbc_rate > VMXNET3_COAL_RBC_MAX_RATE) { + return -EINVAL; + } + + memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf)); + adapter->coal_conf->coalMode = VMXNET3_COALESCE_RBC; + adapter->coal_conf->coalPara.coalRbc.rbc_rate = rbc_rate; + goto done; + } + + if (ec->use_adaptive_rx_coalesce != 0) { + if (ec->tx_max_coalesced_frames != 0 || + ec->rx_max_coalesced_frames != 0) { + return -EINVAL; + } + memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf)); + adapter->coal_conf->coalMode = VMXNET3_COALESCE_ADAPT; + goto done; + } + + if ((ec->tx_max_coalesced_frames != 0) || + (ec->rx_max_coalesced_frames != 0)) { + if ((ec->tx_max_coalesced_frames > + VMXNET3_COAL_STATIC_MAX_DEPTH) || + (ec->rx_max_coalesced_frames > + VMXNET3_COAL_STATIC_MAX_DEPTH)) { + return -EINVAL; + } + + memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf)); + adapter->coal_conf->coalMode = VMXNET3_COALESCE_STATIC; + + adapter->coal_conf->coalPara.coalStatic.tx_comp_depth = + (ec->tx_max_coalesced_frames ? + ec->tx_max_coalesced_frames : + VMXNET3_COAL_STATIC_DEFAULT_DEPTH); + + adapter->coal_conf->coalPara.coalStatic.rx_depth = + (ec->rx_max_coalesced_frames ? + ec->rx_max_coalesced_frames : + VMXNET3_COAL_STATIC_DEFAULT_DEPTH); + + adapter->coal_conf->coalPara.coalStatic.tx_depth = + VMXNET3_COAL_STATIC_DEFAULT_DEPTH; + goto done; + } + +done: + adapter->default_coal_mode = false; + if (netif_running(netdev)) { + spin_lock_irqsave(&adapter->cmd_lock, flags); + cmdInfo->varConf.confVer = 1; + cmdInfo->varConf.confLen = + cpu_to_le32(sizeof(*adapter->coal_conf)); + cmdInfo->varConf.confPA = cpu_to_le64(adapter->coal_conf_pa); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_SET_COALESCE); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + } + + return 0; +} + +static void vmxnet3_get_channels(struct net_device *netdev, + struct ethtool_channels *ec) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + if (IS_ENABLED(CONFIG_PCI_MSI) && adapter->intr.type == VMXNET3_IT_MSIX) { + if (adapter->share_intr == VMXNET3_INTR_BUDDYSHARE) { + ec->combined_count = adapter->num_tx_queues; + } else { + ec->rx_count = adapter->num_rx_queues; + ec->tx_count = + adapter->share_intr == VMXNET3_INTR_TXSHARE ? + 1 : adapter->num_tx_queues; + } + } else { + ec->combined_count = 1; + } + + ec->other_count = 1; + + /* Number of interrupts cannot be changed on the fly */ + /* Just set maximums to actual values */ + ec->max_rx = ec->rx_count; + ec->max_tx = ec->tx_count; + ec->max_combined = ec->combined_count; + ec->max_other = ec->other_count; +} + +static const struct ethtool_ops vmxnet3_ethtool_ops = { + .supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS | + ETHTOOL_COALESCE_MAX_FRAMES | + ETHTOOL_COALESCE_USE_ADAPTIVE_RX, + .get_drvinfo = vmxnet3_get_drvinfo, + .get_regs_len = vmxnet3_get_regs_len, + .get_regs = vmxnet3_get_regs, + .get_wol = vmxnet3_get_wol, + .set_wol = vmxnet3_set_wol, + .get_link = ethtool_op_get_link, + .get_coalesce = vmxnet3_get_coalesce, + .set_coalesce = vmxnet3_set_coalesce, + .get_strings = vmxnet3_get_strings, + .get_sset_count = vmxnet3_get_sset_count, + .get_ethtool_stats = vmxnet3_get_ethtool_stats, + .get_ringparam = vmxnet3_get_ringparam, + .set_ringparam = vmxnet3_set_ringparam, + .get_rxnfc = vmxnet3_get_rxnfc, + .set_rxnfc = vmxnet3_set_rxnfc, +#ifdef VMXNET3_RSS + .get_rxfh_indir_size = vmxnet3_get_rss_indir_size, + .get_rxfh = vmxnet3_get_rss, + .set_rxfh = vmxnet3_set_rss, +#endif + .get_link_ksettings = vmxnet3_get_link_ksettings, + .get_channels = vmxnet3_get_channels, +}; + +void vmxnet3_set_ethtool_ops(struct net_device *netdev) +{ + netdev->ethtool_ops = &vmxnet3_ethtool_ops; +} |