| Message ID | 20200528183615.27212-3-doshir@vmware.com |
|---|---|
| State | Superseded |
| Delegated to: | David Miller |
| Headers | show |
| Series | vmxnet3: upgrade to version 4 | expand |
On Thu, May 28, 2020 at 11:36:13AM -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..83cec9946466 100644 > --- a/drivers/net/vmxnet3/vmxnet3_ethtool.c > +++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c > @@ -665,18 +665,237 @@ 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; > + /* fallthrough */ > + 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; This still suffers from the inconsistency between get and set handler I already pointed out in v1: - there is no way to change VMXNET3_RSS_FIELDS_TCPIP{4,6} bits - get_rxnfc() may return value that set_rxnfc() won't accept - get_rxnfc() may return different value than set_rxnfc() set Above, vmxnet3_get_rss_hash_opts() returns 0 or RXH_L4_B_0_1 | RXH_L4_B_2_3 | RXH_IP_SRC | RXH_IP_DST for any of {TCP,UDP}_V{4,6}_FLOW, depending on corresponding bit in rss_fields. But here you accept only all four bits for TCP (both v4 and v6) and either the two RXH_IP_* bits or all four for UDP. Michal > + 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; > +} [...]
On 5/28/20, 12:21 PM, "Michal Kubecek" <mkubecek@suse.cz> wrote: > On Thu, May 28, 2020 at 11:36:13AM -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> > > --- > > This still suffers from the inconsistency between get and set handler > I already pointed out in v1: > > - there is no way to change VMXNET3_RSS_FIELDS_TCPIP{4,6} bits > - get_rxnfc() may return value that set_rxnfc() won't accept > - get_rxnfc() may return different value than set_rxnfc() set > > Above, vmxnet3_get_rss_hash_opts() returns 0 or > RXH_L4_B_0_1 | RXH_L4_B_2_3 | RXH_IP_SRC | RXH_IP_DST for any of > {TCP,UDP}_V{4,6}_FLOW, depending on corresponding bit in rss_fields. But > here you accept only all four bits for TCP (both v4 and v6) and either > the two RXH_IP_* bits or all four for UDP. > > Michal Hi Michal, That is intentional as vmxnet3 device always expects TCP rss to be enabled if rss is supported. If RSS is enabled, by default rss_fields has TCP/IP RSS supported and cannot be disabled. Its only for UDP/ESP flows the config can change. Hence, get_rss always reports TCP/IP RSS enabled, and set_rss does not accept disabling TCP RSS. Hope this answers your concern. Thanks, Ronak
On Thu, May 28, 2020 at 07:29:34PM +0000, Ronak Doshi wrote: > > On 5/28/20, 12:21 PM, "Michal Kubecek" <mkubecek@suse.cz> wrote: > > > On Thu, May 28, 2020 at 11:36:13AM -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> > > > --- > > > > This still suffers from the inconsistency between get and set handler > > I already pointed out in v1: > > > > - there is no way to change VMXNET3_RSS_FIELDS_TCPIP{4,6} bits > > - get_rxnfc() may return value that set_rxnfc() won't accept > > - get_rxnfc() may return different value than set_rxnfc() set > > > > Above, vmxnet3_get_rss_hash_opts() returns 0 or > > RXH_L4_B_0_1 | RXH_L4_B_2_3 | RXH_IP_SRC | RXH_IP_DST for any of > > {TCP,UDP}_V{4,6}_FLOW, depending on corresponding bit in rss_fields. But > > here you accept only all four bits for TCP (both v4 and v6) and either > > the two RXH_IP_* bits or all four for UDP. > > > > Michal > > Hi Michal, > > That is intentional as vmxnet3 device always expects TCP rss to be enabled > if rss is supported. If RSS is enabled, by default rss_fields has TCP/IP RSS > supported and cannot be disabled. Its only for UDP/ESP flows the config > can change. Hence, get_rss always reports TCP/IP RSS enabled, and set_rss > does not accept disabling TCP RSS. Hope this answers your concern. Maybe it will be easier to understand what I'm talking about if I show it in a table. Let's use shortcuts L3 = RXH_IP_SRC | RXH_IP_DST L4 = RXH_L4_B_0_1 | RXH_L4_B_2_3 Then vmxnet3_get_rss_hash_opts() translates rss_fields bits to info->data like this: 0 1 --------------------------------------------- VMXNET3_RSS_FIELDS_TCPIP4 0 L3 | L4 VMXNET3_RSS_FIELDS_TCPIP6 0 L3 | L4 VMXNET3_RSS_FIELDS_UDPIP4 0 L3 | L4 VMXNET3_RSS_FIELDS_UDPIP6 0 L3 | L4 VMXNET3_RSS_FIELDS_ESPIP4 L3 L3 | L4 VMXNET3_RSS_FIELDS_ESPIP6 L3 L3 But the translation from info->data to bits of rss_fields which should be the inverse of above, actually works like ("err" means -EINVAL error and "noop" that nothing is done): 0 L3 L3 | L4 --------------------------------------------------- VMXNET3_RSS_FIELDS_TCPIP4 err err noop VMXNET3_RSS_FIELDS_TCPIP6 err err noop VMXNET3_RSS_FIELDS_UDPIP4 err 0 1 VMXNET3_RSS_FIELDS_UDPIP6 err 0 1 VMXNET3_RSS_FIELDS_ESPIP4 err 0 1 VMXNET3_RSS_FIELDS_ESPIP6 err noop err This means that for both TCP and UDP, you have cases where get handler will return value which will cause an error if it's fed back to set handler. And for UDP, accepted values for set are L3 and L3 | L4 but get handler returns 0 or L3 | L4. So UDP part is wrong and if TCP always hashes by all four fields, it would be cleaner to return that information unconditionally, like you do e.g. for ESPv6 (with a different value). Michal
On 5/28/20, 1:15 PM, "Michal Kubecek" <mkubecek@suse.cz> wrote: > This means that for both TCP and UDP, you have cases where get handler > will return value which will cause an error if it's fed back to set > handler. And for UDP, accepted values for set are L3 and L3 | L4 but get > handler returns 0 or L3 | L4. > > So UDP part is wrong and if TCP always hashes by all four fields, it > would be cleaner to return that information unconditionally, like you do > e.g. for ESPv6 (with a different value). > > Michal Okay, yes for UDP I should return L3 instead of 0 when rss_fields does not support UDP RSS. I made these changes to avoid fallthrough, but missed this part. Also, will remove the check for TCP and pass it unconditionally. Thanks
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..83cec9946466 100644 --- a/drivers/net/vmxnet3/vmxnet3_ethtool.c +++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c @@ -665,18 +665,237 @@ 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; + /* fallthrough */ + 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 +1106,7 @@ 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 | 224 +++++++++++++++++++++++++++++++++- drivers/net/vmxnet3/vmxnet3_int.h | 4 + 4 files changed, 277 insertions(+), 2 deletions(-)