summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/google/gve/gve_ethtool.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2025-03-26 21:48:21 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2025-03-26 21:48:21 -0700
commit1a9239bb4253f9076b5b4b2a1a4e8d7defd77a95 (patch)
tree286dda5e84757594218e684b94b01b3a3cac15a2 /drivers/net/ethernet/google/gve/gve_ethtool.c
parente61f33273ca755b3e2ebee4520a76097199dc7a8 (diff)
parent023b1e9d265ca0662111a9df23d22b4632717a8a (diff)
downloadlwn-master.tar.gz
lwn-master.zip
Merge tag 'net-next-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextHEADmaster
Pull networking updates from Jakub Kicinski: "Core & protocols: - Continue Netlink conversions to per-namespace RTNL lock (IPv4 routing, routing rules, routing next hops, ARP ioctls) - Continue extending the use of netdev instance locks. As a driver opt-in protect queue operations and (in due course) ethtool operations with the instance lock and not RTNL lock. - Support collecting TCP timestamps (data submitted, sent, acked) in BPF, allowing for transparent (to the application) and lower overhead tracking of TCP RPC performance. - Tweak existing networking Rx zero-copy infra to support zero-copy Rx via io_uring. - Optimize MPTCP performance in single subflow mode by 29%. - Enable GRO on packets which went thru XDP CPU redirect (were queued for processing on a different CPU). Improving TCP stream performance up to 2x. - Improve performance of contended connect() by 200% by searching for an available 4-tuple under RCU rather than a spin lock. Bring an additional 229% improvement by tweaking hash distribution. - Avoid unconditionally touching sk_tsflags on RX, improving performance under UDP flood by as much as 10%. - Avoid skb_clone() dance in ping_rcv() to improve performance under ping flood. - Avoid FIB lookup in netfilter if socket is available, 20% perf win. - Rework network device creation (in-kernel) API to more clearly identify network namespaces and their roles. There are up to 4 namespace roles but we used to have just 2 netns pointer arguments, interpreted differently based on context. - Use sysfs_break_active_protection() instead of trylock to avoid deadlocks between unregistering objects and sysfs access. - Add a new sysctl and sockopt for capping max retransmit timeout in TCP. - Support masking port and DSCP in routing rule matches. - Support dumping IPv4 multicast addresses with RTM_GETMULTICAST. - Support specifying at what time packet should be sent on AF_XDP sockets. - Expose TCP ULP diagnostic info (for TLS and MPTCP) to non-admin users. - Add Netlink YAML spec for WiFi (nl80211) and conntrack. - Introduce EXPORT_IPV6_MOD() and EXPORT_IPV6_MOD_GPL() for symbols which only need to be exported when IPv6 support is built as a module. - Age FDB entries based on Rx not Tx traffic in VxLAN, similar to normal bridging. - Allow users to specify source port range for GENEVE tunnels. - netconsole: allow attaching kernel release, CPU ID and task name to messages as metadata Driver API: - Continue rework / fixing of Energy Efficient Ethernet (EEE) across the SW layers. Delegate the responsibilities to phylink where possible. Improve its handling in phylib. - Support symmetric OR-XOR RSS hashing algorithm. - Support tracking and preserving IRQ affinity by NAPI itself. - Support loopback mode speed selection for interface selftests. Device drivers: - Remove the IBM LCS driver for s390 - Remove the sb1000 cable modem driver - Add support for SFP module access over SMBus - Add MCTP transport driver for MCTP-over-USB - Enable XDP metadata support in multiple drivers - Ethernet high-speed NICs: - Broadcom (bnxt): - add PCIe TLP Processing Hints (TPH) support for new AMD platforms - support dumping RoCE queue state for debug - opt into instance locking - Intel (100G, ice, idpf): - ice: rework MSI-X IRQ management and distribution - ice: support for E830 devices - iavf: add support for Rx timestamping - iavf: opt into instance locking - nVidia/Mellanox: - mlx4: use page pool memory allocator for Rx - mlx5: support for one PTP device per hardware clock - mlx5: support for 200Gbps per-lane link modes - mlx5: move IPSec policy check after decryption - AMD/Solarflare: - support FW flashing via devlink - Cisco (enic): - use page pool memory allocator for Rx - enable 32, 64 byte CQEs - get max rx/tx ring size from the device - Meta (fbnic): - support flow steering and RSS configuration - report queue stats - support TCP segmentation - support IRQ coalescing - support ring size configuration - Marvell/Cavium: - support AF_XDP - Wangxun: - support for PTP clock and timestamping - Huawei (hibmcge): - checksum offload - add more statistics - Ethernet virtual: - VirtIO net: - aggressively suppress Tx completions, improve perf by 96% with 1 CPU and 55% with 2 CPUs - expose NAPI to IRQ mapping and persist NAPI settings - Google (gve): - support XDP in DQO RDA Queue Format - opt into instance locking - Microsoft vNIC: - support BIG TCP - Ethernet NICs consumer, and embedded: - Synopsys (stmmac): - cleanup Tx and Tx clock setting and other link-focused cleanups - enable SGMII and 2500BASEX mode switching for Intel platforms - support Sophgo SG2044 - Broadcom switches (b53): - support for BCM53101 - TI: - iep: add perout configuration support - icssg: support XDP - Cadence (macb): - implement BQL - Xilinx (axinet): - support dynamic IRQ moderation and changing coalescing at runtime - implement BQL - report standard stats - MediaTek: - support phylink managed EEE - Intel: - igc: don't restart the interface on every XDP program change - RealTek (r8169): - support reading registers of internal PHYs directly - increase max jumbo packet size on RTL8125/RTL8126 - Airoha: - support for RISC-V NPU packet processing unit - enable scatter-gather and support MTU up to 9kB - Tehuti (tn40xx): - support cards with TN4010 MAC and an Aquantia AQR105 PHY - Ethernet PHYs: - support for TJA1102S, TJA1121 - dp83tg720: add randomized polling intervals for link detection - dp83822: support changing the transmit amplitude voltage - support for LEDs on 88q2xxx - CAN: - canxl: support Remote Request Substitution bit access - flexcan: add S32G2/S32G3 SoC - WiFi: - remove cooked monitor support - strict mode for better AP testing - basic EPCS support - OMI RX bandwidth reduction support - batman-adv: add support for jumbo frames - WiFi drivers: - RealTek (rtw88): - support RTL8814AE and RTL8814AU - RealTek (rtw89): - switch using wiphy_lock and wiphy_work - add BB context to manipulate two PHY as preparation of MLO - improve BT-coexistence mechanism to play A2DP smoothly - Intel (iwlwifi): - add new iwlmld sub-driver for latest HW/FW combinations - MediaTek (mt76): - preparation for mt7996 Multi-Link Operation (MLO) support - Qualcomm/Atheros (ath12k): - continued work on MLO - Silabs (wfx): - Wake-on-WLAN support - Bluetooth: - add support for skb TX SND/COMPLETION timestamping - hci_core: enable buffer flow control for SCO/eSCO - coredump: log devcd dumps into the monitor - Bluetooth drivers: - intel: add support to configure TX power - nxp: handle bootloader error during cmd5 and cmd7" * tag 'net-next-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1681 commits) unix: fix up for "apparmor: add fine grained af_unix mediation" mctp: Fix incorrect tx flow invalidation condition in mctp-i2c net: usb: asix: ax88772: Increase phy_name size net: phy: Introduce PHY_ID_SIZE — minimum size for PHY ID string net: libwx: fix Tx L4 checksum net: libwx: fix Tx descriptor content for some tunnel packets atm: Fix NULL pointer dereference net: tn40xx: add pci-id of the aqr105-based Tehuti TN4010 cards net: tn40xx: prepare tn40xx driver to find phy of the TN9510 card net: tn40xx: create swnode for mdio and aqr105 phy and add to mdiobus net: phy: aquantia: add essential functions to aqr105 driver net: phy: aquantia: search for firmware-name in fwnode net: phy: aquantia: add probe function to aqr105 for firmware loading net: phy: Add swnode support to mdiobus_scan gve: add XDP DROP and PASS support for DQ gve: update XDP allocation path support RX buffer posting gve: merge packet buffer size fields gve: update GQ RX to use buf_size gve: introduce config-based allocation for XDP gve: remove xdp_xsk_done and xdp_xsk_wakeup statistics ...
Diffstat (limited to 'drivers/net/ethernet/google/gve/gve_ethtool.c')
-rw-r--r--drivers/net/ethernet/google/gve/gve_ethtool.c90
1 files changed, 70 insertions, 20 deletions
diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
index bdfc6e77b2af..31a21ccf4863 100644
--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -63,8 +63,8 @@ static const char gve_gstrings_rx_stats[][ETH_GSTRING_LEN] = {
static const char gve_gstrings_tx_stats[][ETH_GSTRING_LEN] = {
"tx_posted_desc[%u]", "tx_completed_desc[%u]", "tx_consumed_desc[%u]", "tx_bytes[%u]",
"tx_wake[%u]", "tx_stop[%u]", "tx_event_counter[%u]",
- "tx_dma_mapping_error[%u]", "tx_xsk_wakeup[%u]",
- "tx_xsk_done[%u]", "tx_xsk_sent[%u]", "tx_xdp_xmit[%u]", "tx_xdp_xmit_errors[%u]"
+ "tx_dma_mapping_error[%u]",
+ "tx_xsk_sent[%u]", "tx_xdp_xmit[%u]", "tx_xdp_xmit_errors[%u]"
};
static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] = {
@@ -417,9 +417,7 @@ gve_get_ethtool_stats(struct net_device *netdev,
data[i++] = value;
}
}
- /* XDP xsk counters */
- data[i++] = tx->xdp_xsk_wakeup;
- data[i++] = tx->xdp_xsk_done;
+ /* XDP counters */
do {
start = u64_stats_fetch_begin(&priv->tx[ring].statss);
data[i] = tx->xdp_xsk_sent;
@@ -477,11 +475,12 @@ static int gve_set_channels(struct net_device *netdev,
struct ethtool_channels *cmd)
{
struct gve_priv *priv = netdev_priv(netdev);
- struct gve_queue_config new_tx_cfg = priv->tx_cfg;
- struct gve_queue_config new_rx_cfg = priv->rx_cfg;
+ struct gve_tx_queue_config new_tx_cfg = priv->tx_cfg;
+ struct gve_rx_queue_config new_rx_cfg = priv->rx_cfg;
struct ethtool_channels old_settings;
int new_tx = cmd->tx_count;
int new_rx = cmd->rx_count;
+ bool reset_rss = false;
gve_get_channels(netdev, &old_settings);
@@ -492,22 +491,27 @@ static int gve_set_channels(struct net_device *netdev,
if (!new_rx || !new_tx)
return -EINVAL;
- if (priv->num_xdp_queues &&
- (new_tx != new_rx || (2 * new_tx > priv->tx_cfg.max_queues))) {
- dev_err(&priv->pdev->dev, "XDP load failed: The number of configured RX queues should be equal to the number of configured TX queues and the number of configured RX/TX queues should be less than or equal to half the maximum number of RX/TX queues");
- return -EINVAL;
- }
+ if (priv->xdp_prog) {
+ if (new_tx != new_rx ||
+ (2 * new_tx > priv->tx_cfg.max_queues)) {
+ dev_err(&priv->pdev->dev, "The number of configured RX queues should be equal to the number of configured TX queues and the number of configured RX/TX queues should be less than or equal to half the maximum number of RX/TX queues when XDP program is installed");
+ return -EINVAL;
+ }
- if (!netif_running(netdev)) {
- priv->tx_cfg.num_queues = new_tx;
- priv->rx_cfg.num_queues = new_rx;
- return 0;
+ /* One XDP TX queue per RX queue. */
+ new_tx_cfg.num_xdp_queues = new_rx;
+ } else {
+ new_tx_cfg.num_xdp_queues = 0;
}
+ if (new_rx != priv->rx_cfg.num_queues &&
+ priv->cache_rss_config && !netif_is_rxfh_configured(netdev))
+ reset_rss = true;
+
new_tx_cfg.num_queues = new_tx;
new_rx_cfg.num_queues = new_rx;
- return gve_adjust_queues(priv, new_rx_cfg, new_tx_cfg);
+ return gve_adjust_queues(priv, new_rx_cfg, new_tx_cfg, reset_rss);
}
static void gve_get_ringparam(struct net_device *netdev,
@@ -643,8 +647,7 @@ static int gve_set_tunable(struct net_device *netdev,
switch (etuna->id) {
case ETHTOOL_RX_COPYBREAK:
{
- u32 max_copybreak = gve_is_gqi(priv) ?
- GVE_DEFAULT_RX_BUFFER_SIZE : priv->data_buffer_size_dqo;
+ u32 max_copybreak = priv->rx_cfg.packet_buffer_size;
len = *(u32 *)value;
if (len > max_copybreak)
@@ -855,6 +858,25 @@ static u32 gve_get_rxfh_indir_size(struct net_device *netdev)
return priv->rss_lut_size;
}
+static void gve_get_rss_config_cache(struct gve_priv *priv,
+ struct ethtool_rxfh_param *rxfh)
+{
+ struct gve_rss_config *rss_config = &priv->rss_config;
+
+ rxfh->hfunc = ETH_RSS_HASH_TOP;
+
+ if (rxfh->key) {
+ rxfh->key_size = priv->rss_key_size;
+ memcpy(rxfh->key, rss_config->hash_key, priv->rss_key_size);
+ }
+
+ if (rxfh->indir) {
+ rxfh->indir_size = priv->rss_lut_size;
+ memcpy(rxfh->indir, rss_config->hash_lut,
+ priv->rss_lut_size * sizeof(*rxfh->indir));
+ }
+}
+
static int gve_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
{
struct gve_priv *priv = netdev_priv(netdev);
@@ -862,18 +884,46 @@ static int gve_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rx
if (!priv->rss_key_size || !priv->rss_lut_size)
return -EOPNOTSUPP;
+ if (priv->cache_rss_config) {
+ gve_get_rss_config_cache(priv, rxfh);
+ return 0;
+ }
+
return gve_adminq_query_rss_config(priv, rxfh);
}
+static void gve_set_rss_config_cache(struct gve_priv *priv,
+ struct ethtool_rxfh_param *rxfh)
+{
+ struct gve_rss_config *rss_config = &priv->rss_config;
+
+ if (rxfh->key)
+ memcpy(rss_config->hash_key, rxfh->key, priv->rss_key_size);
+
+ if (rxfh->indir)
+ memcpy(rss_config->hash_lut, rxfh->indir,
+ priv->rss_lut_size * sizeof(*rxfh->indir));
+}
+
static int gve_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh,
struct netlink_ext_ack *extack)
{
struct gve_priv *priv = netdev_priv(netdev);
+ int err;
if (!priv->rss_key_size || !priv->rss_lut_size)
return -EOPNOTSUPP;
- return gve_adminq_configure_rss(priv, rxfh);
+ err = gve_adminq_configure_rss(priv, rxfh);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "Fail to configure RSS config");
+ return err;
+ }
+
+ if (priv->cache_rss_config)
+ gve_set_rss_config_cache(priv, rxfh);
+
+ return 0;
}
const struct ethtool_ops gve_ethtool_ops = {