| Message ID | 20200528020707.10036-3-doshir@vmware.com |
|---|---|
| State | Changes Requested |
| Delegated to: | David Miller |
| Headers | show |
| Series | vmxnet3: upgrade to version 4 | expand |
On Wed, May 27, 2020 at 07:07:04PM -0700, Ronak Doshi wrote: > With vmxnet3 version 4, the emulation supports multiqueue(RSS) for > UDP and ESP traffic. A guest can enable/disable RSS for UDP/ESP over > IPv4/IPv6 by issuing commands introduced in this patch. ESP ipv6 is > not yet supported in this patch. > > This patch implements get_rss_hash_opts and set_rss_hash_opts > methods to allow querying and configuring different Rx flow hash > configurations. > > Signed-off-by: Ronak Doshi <doshir@vmware.com> > --- [...] > diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c > index 1163eca7aba5..ceedf63020cb 100644 > --- a/drivers/net/vmxnet3/vmxnet3_ethtool.c > +++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c > @@ -665,18 +665,236 @@ vmxnet3_set_ringparam(struct net_device *netdev, > 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: > + if (rss_fields & VMXNET3_RSS_FIELDS_TCPIP4) > + 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 | > + RXH_IP_SRC | RXH_IP_DST; > + break; In both cases above (and also in the two for IPv6 below) you set info->data to either 0 or all four bits, depending on the value of corresponding flag in rss_fields. But in vmxnet3_set_rss_hash_opt() you have different mapping: - for TCP, you only accept all four bits (no other value) and don't touch rss_fields at all - for UDP, you allow either all four bits (and set the flag) or the two IP related bits (and clear the flag) The UDPv4/UDPv6 behaviour of vmxnet3_set_rss_hash_opt() seems to be the correct one but you should be consistent between get and set handlers. > + 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; If this fallthrough is intentional (it seems to be), it should be marked. Michal > + case SCTP_V4_FLOW: > + case IPV4_FLOW: > + info->data |= RXH_IP_SRC | RXH_IP_DST; > + break; > + case TCP_V6_FLOW: > + if (rss_fields & VMXNET3_RSS_FIELDS_TCPIP6) > + info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3 | > + 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 | > + RXH_IP_SRC | RXH_IP_DST; > + break; > + case AH_ESP_V6_FLOW: > + case AH_V6_FLOW: > + case ESP_V6_FLOW: > + 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: > + 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; > + > + 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; > - return 0; > + break; > + case ETHTOOL_GRXFH: > + if (!VMXNET3_VERSION_GE_4(adapter)) { > + err = -EOPNOTSUPP; > + break; > + } > + err = vmxnet3_get_rss_hash_opts(adapter, info); > + break; > + default: > + err = -EOPNOTSUPP; > + break; > } > - return -EOPNOTSUPP; > + > + 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; > + } > + > + 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 > @@ -887,6 +1105,7 @@ static const struct ethtool_ops vmxnet3_ethtool_ops = { > .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, > diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h > index e803ffad75d6..d52ccc3eeba2 100644 > --- a/drivers/net/vmxnet3/vmxnet3_int.h > +++ b/drivers/net/vmxnet3/vmxnet3_int.h > @@ -377,6 +377,8 @@ struct vmxnet3_adapter { > u16 rxdata_desc_size; > > bool rxdataring_enabled; > + bool default_rss_fields; > + enum Vmxnet3_RSSField rss_fields; > > struct work_struct work; > > @@ -438,6 +440,8 @@ struct vmxnet3_adapter { > > #define VMXNET3_COAL_RBC_RATE(usecs) (1000000 / usecs) > #define VMXNET3_COAL_RBC_USECS(rbc_rate) (1000000 / rbc_rate) > +#define VMXNET3_RSS_FIELDS_DEFAULT (VMXNET3_RSS_FIELDS_TCPIP4 | \ > + VMXNET3_RSS_FIELDS_TCPIP6) > > int > vmxnet3_quiesce_dev(struct vmxnet3_adapter *adapter); > -- > 2.11.0 >
Hi Ronak,
I love your patch! Perhaps something to improve:
[auto build test WARNING on net-next/master]
[also build test WARNING on sparc-next/master linus/master ipvs/master v5.7-rc7 next-20200526]
[if your patch is applied to the wrong git tree, please drop us a note to help
improve the system. BTW, we also suggest to use '--base' option to specify the
base tree in git format-patch, please see https://stackoverflow.com/a/37406982]
url: https://github.com/0day-ci/linux/commits/Ronak-Doshi/vmxnet3-upgrade-to-version-4/20200528-112935
base: https://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git 50ce4c099bebf56be86c9448f7f4bcd34f33663c
config: alpha-allyesconfig (attached as .config)
compiler: alpha-linux-gcc (GCC) 9.3.0
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-9.3.0 make.cross ARCH=alpha
If you fix the issue, kindly add following tag as appropriate
Reported-by: kbuild test robot <lkp@intel.com>
All warnings (new ones prefixed by >>, old ones prefixed by <<):
drivers/net/vmxnet3/vmxnet3_ethtool.c: In function 'vmxnet3_get_rss_hash_opts':
>> drivers/net/vmxnet3/vmxnet3_ethtool.c:704:6: warning: this statement may fall through [-Wimplicit-fallthrough=]
704 | if (rss_fields & VMXNET3_RSS_FIELDS_ESPIP4)
| ^
drivers/net/vmxnet3/vmxnet3_ethtool.c:706:2: note: here
706 | case SCTP_V4_FLOW:
| ^~~~
vim +704 drivers/net/vmxnet3/vmxnet3_ethtool.c
667
668 static int
669 vmxnet3_get_rss_hash_opts(struct vmxnet3_adapter *adapter,
670 struct ethtool_rxnfc *info)
671 {
672 enum Vmxnet3_RSSField rss_fields;
673
674 if (netif_running(adapter->netdev)) {
675 unsigned long flags;
676
677 spin_lock_irqsave(&adapter->cmd_lock, flags);
678
679 VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
680 VMXNET3_CMD_GET_RSS_FIELDS);
681 rss_fields = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD);
682 spin_unlock_irqrestore(&adapter->cmd_lock, flags);
683 } else {
684 rss_fields = adapter->rss_fields;
685 }
686
687 info->data = 0;
688
689 /* Report default options for RSS on vmxnet3 */
690 switch (info->flow_type) {
691 case TCP_V4_FLOW:
692 if (rss_fields & VMXNET3_RSS_FIELDS_TCPIP4)
693 info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3 |
694 RXH_IP_SRC | RXH_IP_DST;
695 break;
696 case UDP_V4_FLOW:
697 if (rss_fields & VMXNET3_RSS_FIELDS_UDPIP4)
698 info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3 |
699 RXH_IP_SRC | RXH_IP_DST;
700 break;
701 case AH_ESP_V4_FLOW:
702 case AH_V4_FLOW:
703 case ESP_V4_FLOW:
> 704 if (rss_fields & VMXNET3_RSS_FIELDS_ESPIP4)
705 info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
706 case SCTP_V4_FLOW:
707 case IPV4_FLOW:
708 info->data |= RXH_IP_SRC | RXH_IP_DST;
709 break;
710 case TCP_V6_FLOW:
711 if (rss_fields & VMXNET3_RSS_FIELDS_TCPIP6)
712 info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3 |
713 RXH_IP_SRC | RXH_IP_DST;
714 break;
715 case UDP_V6_FLOW:
716 if (rss_fields & VMXNET3_RSS_FIELDS_UDPIP6)
717 info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3 |
718 RXH_IP_SRC | RXH_IP_DST;
719 break;
720 case AH_ESP_V6_FLOW:
721 case AH_V6_FLOW:
722 case ESP_V6_FLOW:
723 case SCTP_V6_FLOW:
724 case IPV6_FLOW:
725 info->data |= RXH_IP_SRC | RXH_IP_DST;
726 break;
727 default:
728 return -EINVAL;
729 }
730
731 return 0;
732 }
733
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
diff --git a/drivers/net/vmxnet3/vmxnet3_defs.h b/drivers/net/vmxnet3/vmxnet3_defs.h index c77274228a3e..aac97fac1186 100644 --- a/drivers/net/vmxnet3/vmxnet3_defs.h +++ b/drivers/net/vmxnet3/vmxnet3_defs.h @@ -82,6 +82,7 @@ enum { VMXNET3_CMD_RESERVED3, VMXNET3_CMD_SET_COALESCE, VMXNET3_CMD_REGISTER_MEMREGS, + VMXNET3_CMD_SET_RSS_FIELDS, VMXNET3_CMD_FIRST_GET = 0xF00D0000, VMXNET3_CMD_GET_QUEUE_STATUS = VMXNET3_CMD_FIRST_GET, @@ -96,6 +97,7 @@ enum { VMXNET3_CMD_GET_RESERVED1, VMXNET3_CMD_GET_TXDATA_DESC_SIZE, VMXNET3_CMD_GET_COALESCE, + VMXNET3_CMD_GET_RSS_FIELDS, }; /* @@ -685,12 +687,22 @@ struct Vmxnet3_MemRegs { struct Vmxnet3_MemoryRegion memRegs[1]; }; +enum Vmxnet3_RSSField { + VMXNET3_RSS_FIELDS_TCPIP4 = 0x0001, + VMXNET3_RSS_FIELDS_TCPIP6 = 0x0002, + VMXNET3_RSS_FIELDS_UDPIP4 = 0x0004, + VMXNET3_RSS_FIELDS_UDPIP6 = 0x0008, + VMXNET3_RSS_FIELDS_ESPIP4 = 0x0010, + VMXNET3_RSS_FIELDS_ESPIP6 = 0x0020, +}; + /* If the command data <= 16 bytes, use the shared memory directly. * otherwise, use variable length configuration descriptor. */ union Vmxnet3_CmdInfo { struct Vmxnet3_VariableLenConfDesc varConf; struct Vmxnet3_SetPolling setPolling; + enum Vmxnet3_RSSField setRssFields; __le64 data[2]; }; diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index ec2878f8c1f6..4ea7a40ada88 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -2554,6 +2554,39 @@ vmxnet3_init_coalesce(struct vmxnet3_adapter *adapter) spin_unlock_irqrestore(&adapter->cmd_lock, flags); } +static void +vmxnet3_init_rssfields(struct vmxnet3_adapter *adapter) +{ + struct Vmxnet3_DriverShared *shared = adapter->shared; + union Vmxnet3_CmdInfo *cmdInfo = &shared->cu.cmdInfo; + unsigned long flags; + + if (!VMXNET3_VERSION_GE_4(adapter)) + return; + + spin_lock_irqsave(&adapter->cmd_lock, flags); + + if (adapter->default_rss_fields) { + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_GET_RSS_FIELDS); + adapter->rss_fields = + VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + } else { + cmdInfo->setRssFields = adapter->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); +} + int vmxnet3_activate_dev(struct vmxnet3_adapter *adapter) { @@ -2603,6 +2636,7 @@ vmxnet3_activate_dev(struct vmxnet3_adapter *adapter) } vmxnet3_init_coalesce(adapter); + vmxnet3_init_rssfields(adapter); for (i = 0; i < adapter->num_rx_queues; i++) { VMXNET3_WRITE_BAR0_REG(adapter, @@ -3430,6 +3464,11 @@ vmxnet3_probe_device(struct pci_dev *pdev, adapter->default_coal_mode = true; } + if (VMXNET3_VERSION_GE_4(adapter)) { + adapter->default_rss_fields = true; + adapter->rss_fields = VMXNET3_RSS_FIELDS_DEFAULT; + } + SET_NETDEV_DEV(netdev, &pdev->dev); vmxnet3_declare_features(adapter, dma64); diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c index 1163eca7aba5..ceedf63020cb 100644 --- a/drivers/net/vmxnet3/vmxnet3_ethtool.c +++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c @@ -665,18 +665,236 @@ vmxnet3_set_ringparam(struct net_device *netdev, 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: + if (rss_fields & VMXNET3_RSS_FIELDS_TCPIP4) + 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 | + 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; + case SCTP_V4_FLOW: + case IPV4_FLOW: + info->data |= RXH_IP_SRC | RXH_IP_DST; + break; + case TCP_V6_FLOW: + if (rss_fields & VMXNET3_RSS_FIELDS_TCPIP6) + info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3 | + 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 | + RXH_IP_SRC | RXH_IP_DST; + break; + case AH_ESP_V6_FLOW: + case AH_V6_FLOW: + case ESP_V6_FLOW: + 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: + 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; + + 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; - return 0; + break; + case ETHTOOL_GRXFH: + if (!VMXNET3_VERSION_GE_4(adapter)) { + err = -EOPNOTSUPP; + break; + } + err = vmxnet3_get_rss_hash_opts(adapter, info); + break; + default: + err = -EOPNOTSUPP; + break; } - return -EOPNOTSUPP; + + 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; + } + + 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 @@ -887,6 +1105,7 @@ static const struct ethtool_ops vmxnet3_ethtool_ops = { .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, diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index e803ffad75d6..d52ccc3eeba2 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -377,6 +377,8 @@ struct vmxnet3_adapter { u16 rxdata_desc_size; bool rxdataring_enabled; + bool default_rss_fields; + enum Vmxnet3_RSSField rss_fields; struct work_struct work; @@ -438,6 +440,8 @@ struct vmxnet3_adapter { #define VMXNET3_COAL_RBC_RATE(usecs) (1000000 / usecs) #define VMXNET3_COAL_RBC_USECS(rbc_rate) (1000000 / rbc_rate) +#define VMXNET3_RSS_FIELDS_DEFAULT (VMXNET3_RSS_FIELDS_TCPIP4 | \ + VMXNET3_RSS_FIELDS_TCPIP6) int vmxnet3_quiesce_dev(struct vmxnet3_adapter *adapter);
With vmxnet3 version 4, the emulation supports multiqueue(RSS) for UDP and ESP traffic. A guest can enable/disable RSS for UDP/ESP over IPv4/IPv6 by issuing commands introduced in this patch. ESP ipv6 is not yet supported in this patch. This patch implements get_rss_hash_opts and set_rss_hash_opts methods to allow querying and configuring different Rx flow hash configurations. Signed-off-by: Ronak Doshi <doshir@vmware.com> --- drivers/net/vmxnet3/vmxnet3_defs.h | 12 ++ drivers/net/vmxnet3/vmxnet3_drv.c | 39 ++++++ drivers/net/vmxnet3/vmxnet3_ethtool.c | 223 +++++++++++++++++++++++++++++++++- drivers/net/vmxnet3/vmxnet3_int.h | 4 + 4 files changed, 276 insertions(+), 2 deletions(-)