diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-03-19 20:05:34 +0300 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-03-19 20:05:34 +0300 |
| commit | 1200b6809dfd9d73bc4c7db76d288c35fa4b2ebe (patch) | |
| tree | 552e03de245cdbd0780ca1215914edc4a26540f7 /drivers/net/ethernet/mellanox | |
| parent | 6b5f04b6cf8ebab9a65d9c0026c650bb2538fd0f (diff) | |
| parent | fe30937b65354c7fec244caebbdaae68e28ca797 (diff) | |
| download | linux-1200b6809dfd9d73bc4c7db76d288c35fa4b2ebe.tar.xz | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Highlights:
1) Support more Realtek wireless chips, from Jes Sorenson.
2) New BPF types for per-cpu hash and arrap maps, from Alexei
Starovoitov.
3) Make several TCP sysctls per-namespace, from Nikolay Borisov.
4) Allow the use of SO_REUSEPORT in order to do per-thread processing
of incoming TCP/UDP connections. The muxing can be done using a
BPF program which hashes the incoming packet. From Craig Gallek.
5) Add a multiplexer for TCP streams, to provide a messaged based
interface. BPF programs can be used to determine the message
boundaries. From Tom Herbert.
6) Add 802.1AE MACSEC support, from Sabrina Dubroca.
7) Avoid factorial complexity when taking down an inetdev interface
with lots of configured addresses. We were doing things like
traversing the entire address less for each address removed, and
flushing the entire netfilter conntrack table for every address as
well.
8) Add and use SKB bulk free infrastructure, from Jesper Brouer.
9) Allow offloading u32 classifiers to hardware, and implement for
ixgbe, from John Fastabend.
10) Allow configuring IRQ coalescing parameters on a per-queue basis,
from Kan Liang.
11) Extend ethtool so that larger link mode masks can be supported.
From David Decotigny.
12) Introduce devlink, which can be used to configure port link types
(ethernet vs Infiniband, etc.), port splitting, and switch device
level attributes as a whole. From Jiri Pirko.
13) Hardware offload support for flower classifiers, from Amir Vadai.
14) Add "Local Checksum Offload". Basically, for a tunneled packet
the checksum of the outer header is 'constant' (because with the
checksum field filled into the inner protocol header, the payload
of the outer frame checksums to 'zero'), and we can take advantage
of that in various ways. From Edward Cree"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1548 commits)
bonding: fix bond_get_stats()
net: bcmgenet: fix dma api length mismatch
net/mlx4_core: Fix backward compatibility on VFs
phy: mdio-thunder: Fix some Kconfig typos
lan78xx: add ndo_get_stats64
lan78xx: handle statistics counter rollover
RDS: TCP: Remove unused constant
RDS: TCP: Add sysctl tunables for sndbuf/rcvbuf on rds-tcp socket
net: smc911x: convert pxa dma to dmaengine
team: remove duplicate set of flag IFF_MULTICAST
bonding: remove duplicate set of flag IFF_MULTICAST
net: fix a comment typo
ethernet: micrel: fix some error codes
ip_tunnels, bpf: define IP_TUNNEL_OPTS_MAX and use it
bpf, dst: add and use dst_tclassid helper
bpf: make skb->tc_classid also readable
net: mvneta: bm: clarify dependencies
cls_bpf: reset class and reuse major in da
ldmvsw: Checkpatch sunvnet.c and sunvnet_common.c
ldmvsw: Add ldmvsw.c driver code
...
Diffstat (limited to 'drivers/net/ethernet/mellanox')
42 files changed, 2532 insertions, 403 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/Kconfig b/drivers/net/ethernet/mellanox/mlx4/Kconfig index 1486ce902a56..9ca3734ebb6b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx4/Kconfig @@ -4,6 +4,7 @@ config MLX4_EN tristate "Mellanox Technologies 1/10/40Gbit Ethernet support" + depends on MAY_USE_DEVLINK depends on PCI select MLX4_CORE select PTP_1588_CLOCK diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index dd84cabb2a51..f69584a9b47f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -501,34 +501,30 @@ static u32 mlx4_en_autoneg_get(struct net_device *dev) return autoneg; } -static u32 ptys_get_supported_port(struct mlx4_ptys_reg *ptys_reg) +static void ptys2ethtool_update_supported_port(unsigned long *mask, + struct mlx4_ptys_reg *ptys_reg) { u32 eth_proto = be32_to_cpu(ptys_reg->eth_proto_cap); if (eth_proto & (MLX4_PROT_MASK(MLX4_10GBASE_T) | MLX4_PROT_MASK(MLX4_1000BASE_T) | MLX4_PROT_MASK(MLX4_100BASE_TX))) { - return SUPPORTED_TP; - } - - if (eth_proto & (MLX4_PROT_MASK(MLX4_10GBASE_CR) + __set_bit(ETHTOOL_LINK_MODE_TP_BIT, mask); + } else if (eth_proto & (MLX4_PROT_MASK(MLX4_10GBASE_CR) | MLX4_PROT_MASK(MLX4_10GBASE_SR) | MLX4_PROT_MASK(MLX4_56GBASE_SR4) | MLX4_PROT_MASK(MLX4_40GBASE_CR4) | MLX4_PROT_MASK(MLX4_40GBASE_SR4) | MLX4_PROT_MASK(MLX4_1000BASE_CX_SGMII))) { - return SUPPORTED_FIBRE; - } - - if (eth_proto & (MLX4_PROT_MASK(MLX4_56GBASE_KR4) + __set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, mask); + } else if (eth_proto & (MLX4_PROT_MASK(MLX4_56GBASE_KR4) | MLX4_PROT_MASK(MLX4_40GBASE_KR4) | MLX4_PROT_MASK(MLX4_20GBASE_KR2) | MLX4_PROT_MASK(MLX4_10GBASE_KR) | MLX4_PROT_MASK(MLX4_10GBASE_KX4) | MLX4_PROT_MASK(MLX4_1000BASE_KX))) { - return SUPPORTED_Backplane; + __set_bit(ETHTOOL_LINK_MODE_Backplane_BIT, mask); } - return 0; } static u32 ptys_get_active_port(struct mlx4_ptys_reg *ptys_reg) @@ -574,122 +570,111 @@ static u32 ptys_get_active_port(struct mlx4_ptys_reg *ptys_reg) enum ethtool_report { SUPPORTED = 0, ADVERTISED = 1, - SPEED = 2 }; +struct ptys2ethtool_config { + __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertised); + u32 speed; +}; + +static unsigned long *ptys2ethtool_link_mode(struct ptys2ethtool_config *cfg, + enum ethtool_report report) +{ + switch (report) { + case SUPPORTED: + return cfg->supported; + case ADVERTISED: + return cfg->advertised; + } + return NULL; +} + +#define MLX4_BUILD_PTYS2ETHTOOL_CONFIG(reg_, speed_, ...) \ + ({ \ + struct ptys2ethtool_config *cfg; \ + const unsigned int modes[] = { __VA_ARGS__ }; \ + unsigned int i; \ + cfg = &ptys2ethtool_map[reg_]; \ + cfg->speed = speed_; \ + bitmap_zero(cfg->supported, \ + __ETHTOOL_LINK_MODE_MASK_NBITS); \ + bitmap_zero(cfg->advertised, \ + __ETHTOOL_LINK_MODE_MASK_NBITS); \ + for (i = 0 ; i < ARRAY_SIZE(modes) ; ++i) { \ + __set_bit(modes[i], cfg->supported); \ + __set_bit(modes[i], cfg->advertised); \ + } \ + }) + /* Translates mlx4 link mode to equivalent ethtool Link modes/speed */ -static u32 ptys2ethtool_map[MLX4_LINK_MODES_SZ][3] = { - [MLX4_100BASE_TX] = { - SUPPORTED_100baseT_Full, - ADVERTISED_100baseT_Full, - SPEED_100 - }, - - [MLX4_1000BASE_T] = { - SUPPORTED_1000baseT_Full, - ADVERTISED_1000baseT_Full, - SPEED_1000 - }, - [MLX4_1000BASE_CX_SGMII] = { - SUPPORTED_1000baseKX_Full, - ADVERTISED_1000baseKX_Full, - SPEED_1000 - }, - [MLX4_1000BASE_KX] = { - SUPPORTED_1000baseKX_Full, - ADVERTISED_1000baseKX_Full, - SPEED_1000 - }, - - [MLX4_10GBASE_T] = { - SUPPORTED_10000baseT_Full, - ADVERTISED_10000baseT_Full, - SPEED_10000 - }, - [MLX4_10GBASE_CX4] = { - SUPPORTED_10000baseKX4_Full, - ADVERTISED_10000baseKX4_Full, - SPEED_10000 - }, - [MLX4_10GBASE_KX4] = { - SUPPORTED_10000baseKX4_Full, - ADVERTISED_10000baseKX4_Full, - SPEED_10000 - }, - [MLX4_10GBASE_KR] = { - SUPPORTED_10000baseKR_Full, - ADVERTISED_10000baseKR_Full, - SPEED_10000 - }, - [MLX4_10GBASE_CR] = { - SUPPORTED_10000baseKR_Full, - ADVERTISED_10000baseKR_Full, - SPEED_10000 - }, - [MLX4_10GBASE_SR] = { - SUPPORTED_10000baseKR_Full, - ADVERTISED_10000baseKR_Full, - SPEED_10000 - }, - - [MLX4_20GBASE_KR2] = { - SUPPORTED_20000baseMLD2_Full | SUPPORTED_20000baseKR2_Full, - ADVERTISED_20000baseMLD2_Full | ADVERTISED_20000baseKR2_Full, - SPEED_20000 - }, - - [MLX4_40GBASE_CR4] = { - SUPPORTED_40000baseCR4_Full, - ADVERTISED_40000baseCR4_Full, - SPEED_40000 - }, - [MLX4_40GBASE_KR4] = { - SUPPORTED_40000baseKR4_Full, - ADVERTISED_40000baseKR4_Full, - SPEED_40000 - }, - [MLX4_40GBASE_SR4] = { - SUPPORTED_40000baseSR4_Full, - ADVERTISED_40000baseSR4_Full, - SPEED_40000 - }, - - [MLX4_56GBASE_KR4] = { - SUPPORTED_56000baseKR4_Full, - ADVERTISED_56000baseKR4_Full, - SPEED_56000 - }, - [MLX4_56GBASE_CR4] = { - SUPPORTED_56000baseCR4_Full, - ADVERTISED_56000baseCR4_Full, - SPEED_56000 - }, - [MLX4_56GBASE_SR4] = { - SUPPORTED_56000baseSR4_Full, - ADVERTISED_56000baseSR4_Full, - SPEED_56000 - }, +static struct ptys2ethtool_config ptys2ethtool_map[MLX4_LINK_MODES_SZ]; + +void __init mlx4_en_init_ptys2ethtool_map(void) +{ + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_100BASE_TX, SPEED_100, + ETHTOOL_LINK_MODE_100baseT_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_1000BASE_T, SPEED_1000, + ETHTOOL_LINK_MODE_1000baseT_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_1000BASE_CX_SGMII, SPEED_1000, + ETHTOOL_LINK_MODE_1000baseKX_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_1000BASE_KX, SPEED_1000, + ETHTOOL_LINK_MODE_1000baseKX_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_T, SPEED_10000, + ETHTOOL_LINK_MODE_10000baseT_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_CX4, SPEED_10000, + ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_KX4, SPEED_10000, + ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_KR, SPEED_10000, + ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_CR, SPEED_10000, + ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_10GBASE_SR, SPEED_10000, + ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_20GBASE_KR2, SPEED_20000, + ETHTOOL_LINK_MODE_20000baseMLD2_Full_BIT, + ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_40GBASE_CR4, SPEED_40000, + ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_40GBASE_KR4, SPEED_40000, + ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_40GBASE_SR4, SPEED_40000, + ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_56GBASE_KR4, SPEED_56000, + ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_56GBASE_CR4, SPEED_56000, + ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT); + MLX4_BUILD_PTYS2ETHTOOL_CONFIG(MLX4_56GBASE_SR4, SPEED_56000, + ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT); }; -static u32 ptys2ethtool_link_modes(u32 eth_proto, enum ethtool_report report) +static void ptys2ethtool_update_link_modes(unsigned long *link_modes, + u32 eth_proto, + enum ethtool_report report) { int i; - u32 link_modes = 0; - for (i = 0; i < MLX4_LINK_MODES_SZ; i++) { if (eth_proto & MLX4_PROT_MASK(i)) - link_modes |= ptys2ethtool_map[i][report]; + bitmap_or(link_modes, link_modes, + ptys2ethtool_link_mode(&ptys2ethtool_map[i], + report), + __ETHTOOL_LINK_MODE_MASK_NBITS); } - return link_modes; } -static u32 ethtool2ptys_link_modes(u32 link_modes, enum ethtool_report report) +static u32 ethtool2ptys_link_modes(const unsigned long *link_modes, + enum ethtool_report report) { int i; u32 ptys_modes = 0; for (i = 0; i < MLX4_LINK_MODES_SZ; i++) { - if (ptys2ethtool_map[i][report] & link_modes) + if (bitmap_intersects( + ptys2ethtool_link_mode(&ptys2ethtool_map[i], + report), + link_modes, + __ETHTOOL_LINK_MODE_MASK_NBITS)) ptys_modes |= 1 << i; } return ptys_modes; @@ -702,14 +687,15 @@ static u32 speed2ptys_link_modes(u32 speed) u32 ptys_modes = 0; for (i = 0; i < MLX4_LINK_MODES_SZ; i++) { - if (ptys2ethtool_map[i][SPEED] == speed) + if (ptys2ethtool_map[i].speed == speed) ptys_modes |= 1 << i; } return ptys_modes; } -static int ethtool_get_ptys_settings(struct net_device *dev, - struct ethtool_cmd *cmd) +static int +ethtool_get_ptys_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *link_ksettings) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_ptys_reg ptys_reg; @@ -737,79 +723,102 @@ static int ethtool_get_ptys_settings(struct net_device *dev, en_dbg(DRV, priv, "ptys_reg.eth_proto_lp_adv %x\n", be32_to_cpu(ptys_reg.eth_proto_lp_adv)); - cmd->supported = 0; - cmd->advertising = 0; + /* reset supported/advertising masks */ + ethtool_link_ksettings_zero_link_mode(link_ksettings, supported); + ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); - cmd->supported |= ptys_get_supported_port(&ptys_reg); + ptys2ethtool_update_supported_port(link_ksettings->link_modes.supported, + &ptys_reg); eth_proto = be32_to_cpu(ptys_reg.eth_proto_cap); - cmd->supported |= ptys2ethtool_link_modes(eth_proto, SUPPORTED); + ptys2ethtool_update_link_modes(link_ksettings->link_modes.supported, + eth_proto, SUPPORTED); eth_proto = be32_to_cpu(ptys_reg.eth_proto_admin); - cmd->advertising |= ptys2ethtool_link_modes(eth_proto, ADVERTISED); + ptys2ethtool_update_link_modes(link_ksettings->link_modes.advertising, + eth_proto, ADVERTISED); - cmd->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; - cmd->advertising |= (priv->prof->tx_pause) ? ADVERTISED_Pause : 0; + ethtool_link_ksettings_add_link_mode(link_ksettings, supported, + Pause); + ethtool_link_ksettings_add_link_mode(link_ksettings, supported, + Asym_Pause); - cmd->advertising |= (priv->prof->tx_pause ^ priv->prof->rx_pause) ? - ADVERTISED_Asym_Pause : 0; + if (priv->prof->tx_pause) + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, Pause); + if (priv->prof->tx_pause ^ priv->prof->rx_pause) + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, Asym_Pause); - cmd->port = ptys_get_active_port(&ptys_reg); - cmd->transceiver = (SUPPORTED_TP & cmd->supported) ? - XCVR_EXTERNAL : XCVR_INTERNAL; + link_ksettings->base.port = ptys_get_active_port(&ptys_reg); if (mlx4_en_autoneg_get(dev)) { - cmd->supported |= SUPPORTED_Autoneg; - cmd->advertising |= ADVERTISED_Autoneg; + ethtool_link_ksettings_add_link_mode(link_ksettings, + supported, Autoneg); + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, Autoneg); } - cmd->autoneg = (priv->port_state.flags & MLX4_EN_PORT_ANC) ? + link_ksettings->base.autoneg + = (priv->port_state.flags & MLX4_EN_PORT_ANC) ? AUTONEG_ENABLE : AUTONEG_DISABLE; eth_proto = be32_to_cpu(ptys_reg.eth_proto_lp_adv); - cmd->lp_advertising = ptys2ethtool_link_modes(eth_proto, ADVERTISED); - cmd->lp_advertising |= (priv->port_state.flags & MLX4_EN_PORT_ANC) ? - ADVERTISED_Autoneg : 0; + ethtool_link_ksettings_zero_link_mode(link_ksettings, lp_advertising); + ptys2ethtool_update_link_modes( + link_ksettings->link_modes.lp_advertising, + eth_proto, ADVERTISED); + if (priv->port_state.flags & MLX4_EN_PORT_ANC) + ethtool_link_ksettings_add_link_mode(link_ksettings, + lp_advertising, Autoneg); - cmd->phy_address = 0; - cmd->mdio_support = 0; - cmd->maxtxpkt = 0; - cmd->maxrxpkt = 0; - cmd->eth_tp_mdix = ETH_TP_MDI_INVALID; - cmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO; + link_ksettings->base.phy_address = 0; + link_ksettings->base.mdio_support = 0; + link_ksettings->base.eth_tp_mdix = ETH_TP_MDI_INVALID; + link_ksettings->base.eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO; return ret; } -static void ethtool_get_default_settings(struct net_device *dev, - struct ethtool_cmd *cmd) +static void +ethtool_get_default_link_ksettings( + struct net_device *dev, struct ethtool_link_ksettings *link_ksettings) { struct mlx4_en_priv *priv = netdev_priv(dev); int trans_type; - cmd->autoneg = AUTONEG_DISABLE; - cmd->supported = SUPPORTED_10000baseT_Full; - cmd->advertising = ADVERTISED_10000baseT_Full; - trans_type = priv->port_state.transceiver; + link_ksettings->base.autoneg = AUTONEG_DISABLE; + + ethtool_link_ksettings_zero_link_mode(link_ksettings, supported); + ethtool_link_ksettings_add_link_mode(link_ksettings, supported, + 10000baseT_Full); + ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); + ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, + 10000baseT_Full); + + trans_type = priv->port_state.transceiver; if (trans_type > 0 && trans_type <= 0xC) { - cmd->port = PORT_FIBRE; - cmd->transceiver = XCVR_EXTERNAL; - cmd->supported |= SUPPORTED_FIBRE; - cmd->advertising |= ADVERTISED_FIBRE; + link_ksettings->base.port = PORT_FIBRE; + ethtool_link_ksettings_add_link_mode(link_ksettings, + supported, FIBRE); + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, FIBRE); } else if (trans_type == 0x80 || trans_type == 0) { - cmd->port = PORT_TP; - cmd->transceiver = XCVR_INTERNAL; - cmd->supported |= SUPPORTED_TP; - cmd->advertising |= ADVERTISED_TP; + link_ksettings->base.port = PORT_TP; + ethtool_link_ksettings_add_link_mode(link_ksettings, + supported, TP); + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, TP); } else { - cmd->port = -1; - cmd->transceiver = -1; + link_ksettings->base.port = -1; } } -static int mlx4_en_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int +mlx4_en_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *link_ksettings) { struct mlx4_en_priv *priv = netdev_priv(dev); int ret = -EINVAL; @@ -822,16 +831,16 @@ static int mlx4_en_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) priv->port_state.flags & MLX4_EN_PORT_ANE); if (priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ETH_PROT_CTRL) - ret = ethtool_get_ptys_settings(dev, cmd); + ret = ethtool_get_ptys_link_ksettings(dev, link_ksettings); if (ret) /* ETH PROT CRTL is not supported or PTYS CMD failed */ - ethtool_get_default_settings(dev, cmd); + ethtool_get_default_link_ksettings(dev, link_ksettings); if (netif_carrier_ok(dev)) { - ethtool_cmd_speed_set(cmd, priv->port_state.link_speed); - cmd->duplex = DUPLEX_FULL; + link_ksettings->base.speed = priv->port_state.link_speed; + link_ksettings->base.duplex = DUPLEX_FULL; } else { - ethtool_cmd_speed_set(cmd, SPEED_UNKNOWN); - cmd->duplex = DUPLEX_UNKNOWN; + link_ksettings->base.speed = SPEED_UNKNOWN; + link_ksettings->base.duplex = DUPLEX_UNKNOWN; } return 0; } @@ -855,21 +864,29 @@ static __be32 speed_set_ptys_admin(struct mlx4_en_priv *priv, u32 speed, return proto_admin; } -static int mlx4_en_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int +mlx4_en_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *link_ksettings) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_ptys_reg ptys_reg; __be32 proto_admin; int ret; - u32 ptys_adv = ethtool2ptys_link_modes(cmd->advertising, ADVERTISED); - int speed = ethtool_cmd_speed(cmd); + u32 ptys_adv = ethtool2ptys_link_modes( + link_ksettings->link_modes.advertising, ADVERTISED); + const int speed = link_ksettings->base.speed; - en_dbg(DRV, priv, "Set Speed=%d adv=0x%x autoneg=%d duplex=%d\n", - speed, cmd->advertising, cmd->autoneg, cmd->duplex); + en_dbg(DRV, priv, + "Set Speed=%d adv={%*pbl} autoneg=%d duplex=%d\n", + speed, __ETHTOOL_LINK_MODE_MASK_NBITS, + link_ksettings->link_modes.advertising, + link_ksettings->base.autoneg, + link_ksettings->base.duplex); - if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ETH_PROT_CTRL) || - (cmd->duplex == DUPLEX_HALF)) + if (!(priv->mdev->dev->caps.flags2 & + MLX4_DEV_CAP_FLAG2_ETH_PROT_CTRL) || + (link_ksettings->base.duplex == DUPLEX_HALF)) return -EINVAL; memset(&ptys_reg, 0, sizeof(ptys_reg)); @@ -883,7 +900,7 @@ static int mlx4_en_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) return 0; } - proto_admin = cmd->autoneg == AUTONEG_ENABLE ? + proto_admin = link_ksettings->base.autoneg == AUTONEG_ENABLE ? cpu_to_be32(ptys_adv) : speed_set_ptys_admin(priv, speed, ptys_reg.eth_proto_cap); @@ -1982,8 +1999,8 @@ static int mlx4_en_set_phys_id(struct net_device *dev, const struct ethtool_ops mlx4_en_ethtool_ops = { .get_drvinfo = mlx4_en_get_drvinfo, - .get_settings = mlx4_en_get_settings, - .set_settings = mlx4_en_set_settings, + .get_link_ksettings = mlx4_en_get_link_ksettings, + .set_link_ksettings = mlx4_en_set_link_ksettings, .get_link = ethtool_op_get_link, .get_strings = mlx4_en_get_strings, .get_sset_count = mlx4_en_get_sset_count, diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c index e0ec280a7fa1..bf7628db098a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c @@ -382,6 +382,7 @@ static void mlx4_en_verify_params(void) static int __init mlx4_en_init(void) { mlx4_en_verify_params(); + mlx4_en_init_ptys2ethtool_map(); return mlx4_register_interface(&mlx4_en_interface); } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 21e2c0960271..b4b258c8ca47 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -40,6 +40,7 @@ #include <net/ip.h> #include <net/busy_poll.h> #include <net/vxlan.h> +#include <net/devlink.h> #include <linux/mlx4/driver.h> #include <linux/mlx4/device.h> @@ -69,6 +70,15 @@ int mlx4_en_setup_tc(struct net_device *dev, u8 up) return 0; } +static int __mlx4_en_setup_tc(struct net_device *dev, u32 handle, __be16 proto, + struct tc_to_netdev *tc) +{ + if (tc->type != TC_SETUP_MQPRIO) + return -EINVAL; + + return mlx4_en_setup_tc(dev, tc->tc); +} + #ifdef CONFIG_RFS_ACCEL struct mlx4_en_filter { @@ -2024,8 +2034,11 @@ void mlx4_en_destroy_netdev(struct net_device *dev) en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port); /* Unregister device - this will close the port if it was up */ - if (priv->registered) + if (priv->registered) { + devlink_port_type_clear(mlx4_get_devlink_port(mdev->dev, + priv->port)); unregister_netdev(dev); + } if (priv->allocated) mlx4_free_hwq_res(mdev->dev, &priv->res, MLX4_EN_PAGE_SIZE); @@ -2462,7 +2475,7 @@ static const struct net_device_ops mlx4_netdev_ops = { #endif .ndo_set_features = mlx4_en_set_features, .ndo_fix_features = mlx4_en_fix_features, - .ndo_setup_tc = mlx4_en_setup_tc, + .ndo_setup_tc = __mlx4_en_setup_tc, #ifdef CONFIG_RFS_ACCEL .ndo_rx_flow_steer = mlx4_en_filter_rfs, #endif @@ -2500,7 +2513,7 @@ static const struct net_device_ops mlx4_netdev_ops_master = { #endif .ndo_set_features = mlx4_en_set_features, .ndo_fix_features = mlx4_en_fix_features, - .ndo_setup_tc = mlx4_en_setup_tc, + .ndo_setup_tc = __mlx4_en_setup_tc, #ifdef CONFIG_RFS_ACCEL .ndo_rx_flow_steer = mlx4_en_filter_rfs, #endif @@ -3042,6 +3055,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, } priv->registered = 1; + devlink_port_type_eth_set(mlx4_get_devlink_port(mdev->dev, priv->port), + dev); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index e0946ab22010..c0d7b7296236 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -276,7 +276,8 @@ static void mlx4_en_stamp_wqe(struct mlx4_en_priv *priv, static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring *ring, - int index, u8 owner, u64 timestamp) + int index, u8 owner, u64 timestamp, + int napi_mode) { struct mlx4_en_tx_info *tx_info = &ring->tx_info[index]; struct mlx4_en_tx_desc *tx_desc = ring->buf + index * TXBB_SIZE; @@ -347,7 +348,8 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, } } } - dev_consume_skb_any(skb); + napi_consume_skb(skb, napi_mode); + return tx_info->nr_txbb; } @@ -371,7 +373,8 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring) while (ring->cons != ring->prod) { ring->last_nr_txbb = mlx4_en_free_tx_desc(priv, ring, ring->cons & ring->size_mask, - !!(ring->cons & ring->size), 0); + !!(ring->cons & ring->size), 0, + 0 /* Non-NAPI caller */); ring->cons += ring->last_nr_txbb; cnt++; } @@ -385,7 +388,7 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring) } static bool mlx4_en_process_tx_cq(struct net_device *dev, - struct mlx4_en_cq *cq) + struct mlx4_en_cq *cq, int napi_budget) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_cq *mcq = &cq->mcq; @@ -451,7 +454,7 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev, last_nr_txbb = mlx4_en_free_tx_desc( priv, ring, ring_index, !!((ring_cons + txbbs_skipped) & - ring->size), timestamp); + ring->size), timestamp, napi_budget); mlx4_en_stamp_wqe(priv, ring, stamp_index, !!((ring_cons + txbbs_stamp) & @@ -511,7 +514,7 @@ int mlx4_en_poll_tx_cq(struct napi_struct *napi, int budget) struct mlx4_en_priv *priv = netdev_priv(dev); int clean_complete; - clean_complete = mlx4_en_process_tx_cq(dev, cq); + clean_complete = mlx4_en_process_tx_cq(dev, cq, budget); if (!clean_complete) return budget; diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c index 0472941af820..dec77d6f0ac9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/intf.c +++ b/drivers/net/ethernet/mellanox/mlx4/intf.c @@ -34,6 +34,7 @@ #include <linux/slab.h> #include <linux/export.h> #include <linux/errno.h> +#include <net/devlink.h> #include "mlx4.h" @@ -249,3 +250,11 @@ void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int return result; } EXPORT_SYMBOL_GPL(mlx4_get_protocol_dev); + +struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port) +{ + struct mlx4_port_info *info = &mlx4_priv(dev)->port[port]; + + return &info->devlink_port; +} +EXPORT_SYMBOL_GPL(mlx4_get_devlink_port); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index f8674ae62752..358f7230da58 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -42,6 +42,7 @@ #include <linux/io-mapping.h> #include <linux/delay.h> #include <linux/kmod.h> +#include <net/devlink.h> #include <linux/mlx4/device.h> #include <linux/mlx4/doorbell.h> @@ -104,6 +105,11 @@ module_param(enable_64b_cqe_eqe, bool, 0444); MODULE_PARM_DESC(enable_64b_cqe_eqe, "Enable 64 byte CQEs/EQEs when the FW supports this (default: True)"); +static bool enable_4k_uar; +module_param(enable_4k_uar, bool, 0444); +MODULE_PARM_DESC(enable_4k_uar, + "Enable using 4K UAR. Should not be enabled if have VFs which do not support 4K UARs (default: false)"); + #define PF_CONTEXT_BEHAVIOUR_MASK (MLX4_FUNC_CAP_64B_EQE_CQE | \ MLX4_FUNC_CAP_EQE_CQE_STRIDE | \ MLX4_FUNC_CAP_DMFS_A0_STATIC) @@ -422,7 +428,11 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) /* Virtual PCI function needs to determine UAR page size from * firmware. Only master PCI function can set the uar page size */ - dev->uar_page_shift = DEFAULT_UAR_PAGE_SHIFT; + if (enable_4k_uar) + dev->uar_page_shift = DEFAULT_UAR_PAGE_SHIFT; + else + dev->uar_page_shift = PAGE_SHIFT; + mlx4_set_num_reserved_uars(dev, dev_cap); } @@ -1081,36 +1091,20 @@ static ssize_t show_port_type(struct device *dev, return strlen(buf); } -static ssize_t set_port_type(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static int __set_port_type(struct mlx4_port_info *info, + enum mlx4_port_type port_type) { - struct mlx4_port_info *info = container_of(attr, struct mlx4_port_info, - port_attr); struct mlx4_dev *mdev = info->dev; struct mlx4_priv *priv = mlx4_priv(mdev); enum mlx4_port_type types[MLX4_MAX_PORTS]; enum mlx4_port_type new_types[MLX4_MAX_PORTS]; - static DEFINE_MUTEX(set_port_type_mutex); int i; int err = 0; - mutex_lock(&set_port_type_mutex); - - if (!strcmp(buf, "ib\n")) - info->tmp_type = MLX4_PORT_TYPE_IB; - else if (!strcmp(buf, "eth\n")) - info->tmp_type = MLX4_PORT_TYPE_ETH; - else if (!strcmp(buf, "auto\n")) - info->tmp_type = MLX4_PORT_TYPE_AUTO; - else { - mlx4_err(mdev, "%s is not supported port type\n", buf); - err = -EINVAL; - goto err_out; - } - mlx4_stop_sense(mdev); mutex_lock(&priv->port_mutex); + info->tmp_type = port_type; + /* Possible type is always the one that was delivered */ mdev->caps.possible_type[info->port] = info->tmp_type; @@ -1152,6 +1146,37 @@ static ssize_t set_port_type(struct device *dev, out: mlx4_start_sense(mdev); mutex_unlock(&priv->port_mutex); + + return err; +} + +static ssize_t set_port_type(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct mlx4_port_info *info = container_of(attr, struct mlx4_port_info, + port_attr); + struct mlx4_dev *mdev = info->dev; + enum mlx4_port_type port_type; + static DEFINE_MUTEX(set_port_type_mutex); + int err; + + mutex_lock(&set_port_type_mutex); + + if (!strcmp(buf, "ib\n")) { + port_type = MLX4_PORT_TYPE_IB; + } else if (!strcmp(buf, "eth\n")) { + port_type = MLX4_PORT_TYPE_ETH; + } else if (!strcmp(buf, "auto\n")) { + port_type = MLX4_PORT_TYPE_AUTO; + } else { + mlx4_err(mdev, "%s is not supported port type\n", buf); + err = -EINVAL; + goto err_out; + } + + err = __set_port_type(info, port_type); + err_out: mutex_unlock(&set_port_type_mutex); @@ -2217,11 +2242,14 @@ static int mlx4_init_hca(struct mlx4_dev *dev) dev->caps.max_fmr_maps = (1 << (32 - ilog2(dev->caps.num_mpts))) - 1; - /* Always set UAR page size 4KB, set log_uar_sz accordingly */ - init_hca.log_uar_sz = ilog2(dev->caps.num_uars) + - PAGE_SHIFT - - DEFAULT_UAR_PAGE_SHIFT; - init_hca.uar_page_sz = DEFAULT_UAR_PAGE_SHIFT - 12; + if (enable_4k_uar) { + init_hca.log_uar_sz = ilog2(dev->caps.num_uars) + + PAGE_SHIFT - DEFAULT_UAR_PAGE_SHIFT; + init_hca.uar_page_sz = DEFAULT_UAR_PAGE_SHIFT - 12; + } else { + init_hca.log_uar_sz = ilog2(dev->caps.num_uars); + init_hca.uar_page_sz = PAGE_SHIFT - 12; + } init_hca.mw_enabled = 0; if (dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW || @@ -2889,8 +2917,13 @@ no_msi: static int mlx4_init_port_info(struct mlx4_dev *dev, int port) { + struct devlink *devlink = priv_to_devlink(mlx4_priv(dev)); struct mlx4_port_info *info = &mlx4_priv(dev)->port[port]; - int err = 0; + int err; + + err = devlink_port_register(devlink, &info->devlink_port, port); + if (err) + return err; info->dev = dev; info->port = port; @@ -2915,6 +2948,7 @@ static int mlx4_init_port_info(struct mlx4_dev *dev, int port) err = device_create_file(&dev->persist->pdev->dev, &info->port_attr); if (err) { mlx4_err(dev, "Failed to create file for port %d\n", port); + devlink_port_unregister(&info->devlink_port); info->port = -1; } @@ -3686,23 +3720,54 @@ err_disable_pdev: return err; } +static int mlx4_devlink_port_type_set(struct devlink_port *devlink_port, + enum devlink_port_type port_type) +{ + struct mlx4_port_info *info = container_of(devlink_port, + struct mlx4_port_info, + devlink_port); + enum mlx4_port_type mlx4_port_type; + + switch (port_type) { + case DEVLINK_PORT_TYPE_AUTO: + mlx4_port_type = MLX4_PORT_TYPE_AUTO; + break; + case DEVLINK_PORT_TYPE_ETH: + mlx4_port_type = MLX4_PORT_TYPE_ETH; + break; + case DEVLINK_PORT_TYPE_IB: + mlx4_port_type = MLX4_PORT_TYPE_IB; + break; + default: + return -EOPNOTSUPP; + } + + return __set_port_type(info, mlx4_port_type); +} + +static const struct devlink_ops mlx4_devlink_ops = { + .port_type_set = mlx4_devlink_port_type_set, +}; + static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) { + struct devlink *devlink; struct mlx4_priv *priv; struct mlx4_dev *dev; int ret; printk_once(KERN_INFO "%s", mlx4_version); - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) + devlink = devlink_alloc(&mlx4_devlink_ops, sizeof(*priv)); + if (!devlink) return -ENOMEM; + priv = devlink_priv(devlink); dev = &priv->dev; dev->persist = kzalloc(sizeof(*dev->persist), GFP_KERNEL); if (!dev->persist) { - kfree(priv); - return -ENOMEM; + ret = -ENOMEM; + goto err_devlink_free; } dev->persist->pdev = pdev; dev->persist->dev = dev; @@ -3711,14 +3776,23 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) mutex_init(&dev->persist->device_state_mutex); mutex_init(&dev->persist->interface_state_mutex); + ret = devlink_register(devlink, &pdev->dev); + if (ret) + goto err_persist_free; + ret = __mlx4_init_one(pdev, id->driver_data, priv); - if (ret) { - kfree(dev->persist); - kfree(priv); - } else { - pci_save_state(pdev); - } + if (ret) + goto err_devlink_unregister; + pci_save_state(pdev); + return 0; + +err_devlink_unregister: + devlink_unregister(devlink); +err_persist_free: + kfree(dev->persist); +err_devlink_free: + devlink_free(devlink); return ret; } @@ -3819,6 +3893,7 @@ static void mlx4_remove_one(struct pci_dev *pdev) struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev); struct mlx4_dev *dev = persist->dev; struct mlx4_priv *priv = mlx4_priv(dev); + struct devlink *devlink = priv_to_devlink(priv); int active_vfs = 0; mutex_lock(&persist->interface_state_mutex); @@ -3849,8 +3924,9 @@ static void mlx4_remove_one(struct pci_dev *pdev) pci_release_regions(pdev); pci_disable_device(pdev); + devlink_unregister(devlink); kfree(dev->persist); - kfree(priv); + devlink_free(devlink); pci_set_drvdata(pdev, NULL); } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 7baef52db6b7..ef9683101ead 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -45,6 +45,7 @@ #include <linux/workqueue.h> #include <linux/interrupt.h> #include <linux/spinlock.h> +#include <net/devlink.h> #include <linux/mlx4/device.h> #include <linux/mlx4/driver.h> @@ -828,6 +829,7 @@ struct mlx4_port_info { struct mlx4_roce_gid_table gid_table; int base_qpn; struct cpu_rmap *rmap; + struct devlink_port devlink_port; }; struct mlx4_sense { diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 35de7d2e6b34..d12ab6a73344 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -607,6 +607,7 @@ static inline struct mlx4_cqe *mlx4_en_get_cqe(void *buf, int idx, int cqe_sz) #define MLX4_EN_WOL_DO_MODIFY (1ULL << 63) +void mlx4_en_init_ptys2ethtool_map(void); void mlx4_en_update_loopback_state(struct net_device *dev, netdev_features_t features); diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 25ce1b030a00..cd9b2b28df88 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -3141,7 +3141,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev, case QP_TRANS_RTS2RTS: case QP_TRANS_SQD2SQD: case QP_TRANS_SQD2RTS: - if (slave != mlx4_master_func_num(dev)) + if (slave != mlx4_master_func_num(dev)) { if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH) { port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1; if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB) @@ -3160,6 +3160,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev, if (qp_ctx->alt_path.mgid_index >= num_gids) return -EINVAL; } + } break; default: break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index c503ea05e742..1cf722eba607 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -19,3 +19,15 @@ config MLX5_CORE_EN Ethernet support in Mellanox Technologies ConnectX-4 NIC. Ethernet and Infiniband support in ConnectX-4 are currently mutually exclusive. + +config MLX5_CORE_EN_DCB + bool "Data Center Bridging (DCB) Support" + default y + depends on MLX5_CORE_EN && DCB + ---help--- + Say Y here if you want to use Data Center Bridging (DCB) in the + driver. + If set to N, will not be able to configure QoS and ratelimit attributes. + This flag is depended on the kernel's DCB support. + + If unsure, set to Y diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 01c0256effb8..4fc45ee0c5d1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -3,6 +3,9 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \ mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o + mlx5_core-$(CONFIG_MLX5_CORE_EN) += wq.o eswitch.o \ en_main.o en_fs.o en_ethtool.o en_tx.o en_rx.o \ - en_txrx.o en_clock.o + en_txrx.o en_clock.o vxlan.o en_tc.o + +mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 037fc4cdf5af..97f5114fc113 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved. + * Copyright (c) 2013-2016, Mellanox Technologies. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -560,6 +560,18 @@ const char *mlx5_command_str(int command) case MLX5_CMD_OP_ACCESS_REG: return "MLX5_CMD_OP_ACCESS_REG"; + case MLX5_CMD_OP_SET_WOL_ROL: + return "SET_WOL_ROL"; + + case MLX5_CMD_OP_QUERY_WOL_ROL: + return "QUERY_WOL_ROL"; + + case MLX5_CMD_OP_ADD_VXLAN_UDP_DPORT: + return "ADD_VXLAN_UDP_DPORT"; + + case MLX5_CMD_OP_DELETE_VXLAN_UDP_DPORT: + return "DELETE_VXLAN_UDP_DPORT"; + default: return "unknown command opcode"; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 81b2013ef968..879e6276c473 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2015, Mellanox Technologies. All rights reserved. + * Copyright (c) 2015-2016, Mellanox Technologies. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -29,6 +29,8 @@ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ +#ifndef __MLX5_EN_H__ +#define __MLX5_EN_H__ #include <linux/if_vlan.h> #include <linux/etherdevice.h> @@ -38,8 +40,10 @@ #include <linux/mlx5/driver.h> #include <linux/mlx5/qp.h> #include <linux/mlx5/cq.h> +#include <linux/mlx5/port.h> #include <linux/mlx5/vport.h> #include <linux/mlx5/transobj.h> +#include <linux/rhashtable.h> #include "wq.h" #include "mlx5_core.h" @@ -69,6 +73,11 @@ #define MLX5E_NUM_MAIN_GROUPS 9 +#ifdef CONFIG_MLX5_CORE_EN_DCB +#define MLX5E_MAX_BW_ALLOC 100 /* Max percentage of BW allocation */ +#define MLX5E_MIN_BW_ALLOC 1 /* Min percentage of BW allocation */ +#endif + static const char vport_strings[][ETH_GSTRING_LEN] = { /* vport statistics */ "rx_packets", @@ -95,12 +104,15 @@ static const char vport_strings[][ETH_GSTRING_LEN] = { /* SW counters */ "tso_packets", "tso_bytes", + "tso_inner_packets", + "tso_inner_bytes", "lro_packets", "lro_bytes", "rx_csum_good", "rx_csum_none", "rx_csum_sw", "tx_csum_offload", + "tx_csum_inner", "tx_queue_stopped", "tx_queue_wake", "tx_queue_dropped", @@ -133,18 +145,21 @@ struct mlx5e_vport_stats { /* SW counters */ u64 tso_packets; u64 tso_bytes; + u64 tso_inner_packets; + u64 tso_inner_bytes; u64 lro_packets; u64 lro_bytes; u64 rx_csum_good; u64 rx_csum_none; u64 rx_csum_sw; u64 tx_csum_offload; + u64 tx_csum_inner; u64 tx_queue_stopped; u64 tx_queue_wake; u64 tx_queue_dropped; u64 rx_wqe_err; -#define NUM_VPORT_COUNTERS 32 +#define NUM_VPORT_COUNTERS 35 }; static const char pport_strings[][ETH_GSTRING_LEN] = { @@ -247,24 +262,32 @@ static const char sq_stats_strings[][ETH_GSTRING_LEN] = { "bytes", "tso_packets", "tso_bytes", + "tso_inner_packets", + "tso_inner_bytes", + "csum_offload_inner", + "nop", "csum_offload_none", "stopped", "wake", "dropped", - "nop" }; struct mlx5e_sq_stats { + /* commonly accessed in data path */ u64 packets; u64 bytes; u64 tso_packets; u64 tso_bytes; + u64 tso_inner_packets; + u64 tso_inner_bytes; + u64 csum_offload_inner; + u64 nop; + /* less likely accessed in data path */ u64 csum_offload_none; u64 stopped; u64 wake; u64 dropped; - u64 nop; -#define NUM_SQ_STATS 9 +#define NUM_SQ_STATS 12 }; struct mlx5e_stats { @@ -276,7 +299,6 @@ struct mlx5e_params { u8 log_sq_size; u8 log_rq_size; u16 num_channels; - u8 default_vlan_prio; u8 num_tc; u16 rx_cq_moderation_usec; u16 rx_cq_moderation_pkts; @@ -289,6 +311,9 @@ struct mlx5e_params { u8 rss_hfunc; u8 toeplitz_hash_key[40]; u32 indirection_rqt[MLX5E_INDIR_RQT_SIZE]; +#ifdef CONFIG_MLX5_CORE_EN_DCB + struct ieee_ets ets; +#endif }; struct mlx5e_tstamp { @@ -363,6 +388,7 @@ struct mlx5e_sq_dma { enum { MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, + MLX5E_SQ_STATE_BF_ENABLE, }; struct mlx5e_sq { @@ -391,7 +417,6 @@ struct mlx5e_sq { struct mlx5_wq_cyc wq; u32 dma_fifo_mask; void __iomem *uar_map; - void __iomem *uar_bf_map; struct netdev_queue *txq; u32 sqn; u16 bf_buf_size; @@ -492,21 +517,33 @@ struct mlx5e_vlan_db { bool filter_disabled; }; +struct mlx5e_vxlan_db { + spinlock_t lock; /* protect vxlan table */ + struct radix_tree_root tree; +}; + struct mlx5e_flow_table { int num_groups; struct mlx5_flow_table *t; struct mlx5_flow_group **g; }; +struct mlx5e_tc_flow_table { + struct mlx5_flow_table *t; + + struct rhashtable_params ht_params; + struct rhashtable ht; +}; + struct mlx5e_flow_tables { struct mlx5_flow_namespace *ns; + struct mlx5e_tc_flow_table tc; struct mlx5e_flow_table vlan; struct mlx5e_flow_table main; }; struct mlx5e_priv { /* priv data path fields - start */ - int default_vlan_prio; struct mlx5e_sq **txq_to_sq_map; int channeltc_to_txq_map[MLX5E_MAX_NUM_CHANNELS][MLX5E_MAX_NUM_TC]; /* priv data path fields - end */ @@ -527,9 +564,9 @@ struct mlx5e_priv { struct mlx5e_flow_tables fts; struct mlx5e_eth_addr_db eth_addr; struct mlx5e_vlan_db vlan; + struct mlx5e_vxlan_db vxlan; struct mlx5e_params params; - spinlock_t async_events_spinlock; /* sync hw events */ struct work_struct update_carrier_work; struct work_struct set_rx_mode_work; struct delayed_work update_stats_work; @@ -592,7 +629,7 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev); void mlx5e_completion_event(struct mlx5_core_cq *mcq); void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event); int mlx5e_napi_poll(struct napi_struct *napi, int budget); -bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq); +bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget); int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget); bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq); struct mlx5_cqe64 *mlx5e_get_cqe(struct mlx5e_cq *cq); @@ -640,16 +677,12 @@ static inline void mlx5e_tx_notify_hw(struct mlx5e_sq *sq, * doorbell */ wmb(); - - if (bf_sz) { - __iowrite64_copy(sq->uar_bf_map + ofst, &wqe->ctrl, bf_sz); - - /* flush the write-combining mapped buffer */ - wmb(); - - } else { + if (bf_sz) + __iowrite64_copy(sq->uar_map + ofst, &wqe->ctrl, bf_sz); + else mlx5_write64((__be32 *)&wqe->ctrl, sq->uar_map + ofst, NULL); - } + /* flush the write-combining mapped buffer */ + wmb(); sq->bf_offset ^= sq->bf_buf_size; } @@ -669,4 +702,11 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) } extern const struct ethtool_ops mlx5e_ethtool_ops; +#ifdef CONFIG_MLX5_CORE_EN_DCB +extern const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops; +int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets); +#endif + u16 mlx5e_get_max_inline_cap(struct mlx5_core_dev *mdev); + +#endif /* __MLX5_EN_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c new file mode 100644 index 000000000000..3036f279a8fd --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -0,0 +1,302 @@ +/* + * Copyright (c) 2016, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ +#include <linux/device.h> +#include <linux/netdevice.h> +#include "en.h" + +#define MLX5E_MAX_PRIORITY 8 + +#define MLX5E_100MB (100000) +#define MLX5E_1GB (1000000) + +static int mlx5e_dcbnl_ieee_getets(struct net_device *netdev, + struct ieee_ets *ets) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + + if (!MLX5_CAP_GEN(priv->mdev, ets)) + return -ENOTSUPP; + + memcpy(ets, &priv->params.ets, sizeof(*ets)); + return 0; +} + +enum { + MLX5E_VENDOR_TC_GROUP_NUM = 7, + MLX5E_ETS_TC_GROUP_NUM = 0, +}; + +static void mlx5e_build_tc_group(struct ieee_ets *ets, u8 *tc_group, int max_tc) +{ + bool any_tc_mapped_to_ets = false; + int strict_group; + int i; + + for (i = 0; i <= max_tc; i++) + if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) + any_tc_mapped_to_ets = true; + + strict_group = any_tc_mapped_to_ets ? 1 : 0; + + for (i = 0; i <= max_tc; i++) { + switch (ets->tc_tsa[i]) { + case IEEE_8021QAZ_TSA_VENDOR: + tc_group[i] = MLX5E_VENDOR_TC_GROUP_NUM; + break; + case IEEE_8021QAZ_TSA_STRICT: + tc_group[i] = strict_group++; + break; + case IEEE_8021QAZ_TSA_ETS: + tc_group[i] = MLX5E_ETS_TC_GROUP_NUM; + break; + } + } +} + +static void mlx5e_build_tc_tx_bw(struct ieee_ets *ets, u8 *tc_tx_bw, + u8 *tc_group, int max_tc) +{ + int i; + + for (i = 0; i <= max_tc; i++) { + switch (ets->tc_tsa[i]) { + case IEEE_8021QAZ_TSA_VENDOR: + tc_tx_bw[i] = MLX5E_MAX_BW_ALLOC; + break; + case IEEE_8021QAZ_TSA_STRICT: + tc_tx_bw[i] = MLX5E_MAX_BW_ALLOC; + break; + case IEEE_8021QAZ_TSA_ETS: + tc_tx_bw[i] = ets->tc_tx_bw[i] ?: MLX5E_MIN_BW_ALLOC; + break; + } + } +} + +int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets) +{ + struct mlx5_core_dev *mdev = priv->mdev; + u8 tc_tx_bw[IEEE_8021QAZ_MAX_TCS]; + u8 tc_group[IEEE_8021QAZ_MAX_TCS]; + int max_tc = mlx5_max_tc(mdev); + int err; + + if (!MLX5_CAP_GEN(mdev, ets)) + return -ENOTSUPP; + + mlx5e_build_tc_group(ets, tc_group, max_tc); + mlx5e_build_tc_tx_bw(ets, tc_tx_bw, tc_group, max_tc); + + err = mlx5_set_port_prio_tc(mdev, ets->prio_tc); + if (err) + return err; + + err = mlx5_set_port_tc_group(mdev, tc_group); + if (err) + return err; + + return mlx5_set_port_tc_bw_alloc(mdev, tc_tx_bw); +} + +static int mlx5e_dbcnl_validate_ets(struct ieee_ets *ets) +{ + int bw_sum = 0; + int i; + + /* Validate Priority */ + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + if (ets->prio_tc[i] >= MLX5E_MAX_PRIORITY) + return -EINVAL; + } + + /* Validate Bandwidth Sum */ + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) + bw_sum += ets->tc_tx_bw[i]; + } + + if (bw_sum != 0 && bw_sum != 100) + return -EINVAL; + return 0; +} + +static int mlx5e_dcbnl_ieee_setets(struct net_device *netdev, + struct ieee_ets *ets) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + int err; + + err = mlx5e_dbcnl_validate_ets(ets); + if (err) + return err; + + err = mlx5e_dcbnl_ieee_setets_core(priv, ets); + if (err) + return err; + + memcpy(&priv->params.ets, ets, sizeof(*ets)); + priv->params.ets.ets_cap = mlx5_max_tc(priv->mdev) + 1; + + return 0; +} + +static int mlx5e_dcbnl_ieee_getpfc(struct net_device *dev, + struct ieee_pfc *pfc) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5_core_dev *mdev = priv->mdev; + + pfc->pfc_cap = mlx5_max_tc(mdev) + 1; + + return mlx5_query_port_pfc(mdev, &pfc->pfc_en, NULL); +} + +static int mlx5e_dcbnl_ieee_setpfc(struct net_device *dev, + struct ieee_pfc *pfc) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5_core_dev *mdev = priv->mdev; + enum mlx5_port_status ps; + u8 curr_pfc_en; + int ret; + + mlx5_query_port_pfc(mdev, &curr_pfc_en, NULL); + + if (pfc->pfc_en == curr_pfc_en) + return 0; + + mlx5_query_port_admin_status(mdev, &ps); + if (ps == MLX5_PORT_UP) + mlx5_set_port_admin_status(mdev, MLX5_PORT_DOWN); + + ret = mlx5_set_port_pfc(mdev, pfc->pfc_en, pfc->pfc_en); + + if (ps == MLX5_PORT_UP) + mlx5_set_port_admin_status(mdev, MLX5_PORT_UP); + + return ret; +} + +static u8 mlx5e_dcbnl_getdcbx(struct net_device *dev) +{ + return DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_IEEE; +} + +static u8 mlx5e_dcbnl_setdcbx(struct net_device *dev, u8 mode) +{ + if ((mode & DCB_CAP_DCBX_LLD_MANAGED) || + (mode & DCB_CAP_DCBX_VER_CEE) || + !(mode & DCB_CAP_DCBX_VER_IEEE) || + !(mode & DCB_CAP_DCBX_HOST)) + return 1; + + return 0; +} + +static int mlx5e_dcbnl_ieee_getmaxrate(struct net_device *netdev, + struct ieee_maxrate *maxrate) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + u8 max_bw_value[IEEE_8021QAZ_MAX_TCS]; + u8 max_bw_unit[IEEE_8021QAZ_MAX_TCS]; + int err; + int i; + + err = mlx5_query_port_ets_rate_limit(mdev, max_bw_value, max_bw_unit); + if (err) + return err; + + memset(maxrate->tc_maxrate, 0, sizeof(maxrate->tc_maxrate)); + + for (i = 0; i <= mlx5_max_tc(mdev); i++) { + switch (max_bw_unit[i]) { + case MLX5_100_MBPS_UNIT: + maxrate->tc_maxrate[i] = max_bw_value[i] * MLX5E_100MB; + break; + case MLX5_GBPS_UNIT: + maxrate->tc_maxrate[i] = max_bw_value[i] * MLX5E_1GB; + break; + case MLX5_BW_NO_LIMIT: + break; + default: + WARN(true, "non-supported BW unit"); + break; + } + } + + return 0; +} + +static int mlx5e_dcbnl_ieee_setmaxrate(struct net_device *netdev, + struct ieee_maxrate *maxrate) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + u8 max_bw_value[IEEE_8021QAZ_MAX_TCS]; + u8 max_bw_unit[IEEE_8021QAZ_MAX_TCS]; + __u64 upper_limit_mbps = roundup(255 * MLX5E_100MB, MLX5E_1GB); + int i; + + memset(max_bw_value, 0, sizeof(max_bw_value)); + memset(max_bw_unit, 0, sizeof(max_bw_unit)); + + for (i = 0; i <= mlx5_max_tc(mdev); i++) { + if (!maxrate->tc_maxrate[i]) { + max_bw_unit[i] = MLX5_BW_NO_LIMIT; + continue; + } + if (maxrate->tc_maxrate[i] < upper_limit_mbps) { + max_bw_value[i] = div_u64(maxrate->tc_maxrate[i], + MLX5E_100MB); + max_bw_value[i] = max_bw_value[i] ? max_bw_value[i] : 1; + max_bw_unit[i] = MLX5_100_MBPS_UNIT; + } else { + max_bw_value[i] = div_u64(maxrate->tc_maxrate[i], + MLX5E_1GB); + max_bw_unit[i] = MLX5_GBPS_UNIT; + } + } + + return mlx5_modify_port_ets_rate_limit(mdev, max_bw_value, max_bw_unit); +} + +const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops = { + .ieee_getets = mlx5e_dcbnl_ieee_getets, + .ieee_setets = mlx5e_dcbnl_ieee_setets, + .ieee_getmaxrate = mlx5e_dcbnl_ieee_getmaxrate, + .ieee_setmaxrate = mlx5e_dcbnl_ieee_setmaxrate, + .ieee_getpfc = mlx5e_dcbnl_ieee_getpfc, + .ieee_setpfc = mlx5e_dcbnl_ieee_setpfc, + .getdcbx = mlx5e_dcbnl_getdcbx, + .setdcbx = mlx5e_dcbnl_setdcbx, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 5abeb00fceb8..68834b715f6c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -211,13 +211,14 @@ static void mlx5e_get_strings(struct net_device *dev, sprintf(data + (idx++) * ETH_GSTRING_LEN, "rx%d_%s", i, rq_stats_strings[j]); - for (i = 0; i < priv->params.num_channels; i++) - for (tc = 0; tc < priv->params.num_tc; tc++) + for (tc = 0; tc < priv->params.num_tc; tc++) + for (i = 0; i < priv->params.num_channels; i++) for (j = 0; j < NUM_SQ_STATS; j++) sprintf(data + - (idx++) * ETH_GSTRING_LEN, - "tx%d_%d_%s", i, tc, - sq_stats_strings[j]); + (idx++) * ETH_GSTRING_LEN, + "tx%d_%s", + priv->channeltc_to_txq_map[i][tc], + sq_stats_strings[j]); break; } } @@ -249,8 +250,8 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev, &priv->state) ? 0 : ((u64 *)&priv->channel[i]->rq.stats)[j]; - for (i = 0; i < priv->params.num_channels; i++) - for (tc = 0; tc < priv->params.num_tc; tc++) + for (tc = 0; tc < priv->params.num_tc; tc++) + for (i = 0; i < priv->params.num_channels; i++) for (j = 0; j < NUM_SQ_STATS; j++) data[idx++] = !test_bit(MLX5E_STATE_OPENED, &priv->state) ? 0 : @@ -401,6 +402,9 @@ static int mlx5e_get_coalesce(struct net_device *netdev, { struct mlx5e_priv *priv = netdev_priv(netdev); + if (!MLX5_CAP_GEN(priv->mdev, cq_moderation)) + return -ENOTSUPP; + coal->rx_coalesce_usecs = priv->params.rx_cq_moderation_usec; coal->rx_max_coalesced_frames = priv->params.rx_cq_moderation_pkts; coal->tx_coalesce_usecs = priv->params.tx_cq_moderation_usec; @@ -418,11 +422,18 @@ static int mlx5e_set_coalesce(struct net_device *netdev, int tc; int i; + if (!MLX5_CAP_GEN(mdev, cq_moderation)) + return -ENOTSUPP; + + mutex_lock(&priv->state_lock); priv->params.tx_cq_moderation_usec = coal->tx_coalesce_usecs; priv->params.tx_cq_moderation_pkts = coal->tx_max_coalesced_frames; priv->params.rx_cq_moderation_usec = coal->rx_coalesce_usecs; priv->params.rx_cq_moderation_pkts = coal->rx_max_coalesced_frames; + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + goto out; + for (i = 0; i < priv->params.num_channels; ++i) { c = priv->channel[i]; @@ -438,6 +449,8 @@ static int mlx5e_set_coalesce(struct net_device *netdev, coal->rx_max_coalesced_frames); } +out: + mutex_unlock(&priv->state_lock); return 0; } @@ -900,6 +913,129 @@ static int mlx5e_get_ts_info(struct net_device *dev, return 0; } +static __u32 mlx5e_get_wol_supported(struct mlx5_core_dev *mdev) +{ + __u32 ret = 0; + + if (MLX5_CAP_GEN(mdev, wol_g)) + ret |= WAKE_MAGIC; + + if (MLX5_CAP_GEN(mdev, wol_s)) + ret |= WAKE_MAGICSECURE; + + if (MLX5_CAP_GEN(mdev, wol_a)) + ret |= WAKE_ARP; + + if (MLX5_CAP_GEN(mdev, wol_b)) + ret |= WAKE_BCAST; + + if (MLX5_CAP_GEN(mdev, wol_m)) + ret |= WAKE_MCAST; + + if (MLX5_CAP_GEN(mdev, wol_u)) + ret |= WAKE_UCAST; + + if (MLX5_CAP_GEN(mdev, wol_p)) + ret |= WAKE_PHY; + + return ret; +} + +static __u32 mlx5e_refomrat_wol_mode_mlx5_to_linux(u8 mode) +{ + __u32 ret = 0; + + if (mode & MLX5_WOL_MAGIC) + ret |= WAKE_MAGIC; + + if (mode & MLX5_WOL_SECURED_MAGIC) + ret |= WAKE_MAGICSECURE; + + if (mode & MLX5_WOL_ARP) + ret |= WAKE_ARP; + + if (mode & MLX5_WOL_BROADCAST) + ret |= WAKE_BCAST; + + if (mode & MLX5_WOL_MULTICAST) + ret |= WAKE_MCAST; + + if (mode & MLX5_WOL_UNICAST) + ret |= WAKE_UCAST; + + if (mode & MLX5_WOL_PHY_ACTIVITY) + ret |= WAKE_PHY; + + return ret; +} + +static u8 mlx5e_refomrat_wol_mode_linux_to_mlx5(__u32 mode) +{ + u8 ret = 0; + + if (mode & WAKE_MAGIC) + ret |= MLX5_WOL_MAGIC; + + if (mode & WAKE_MAGICSECURE) + ret |= MLX5_WOL_SECURED_MAGIC; + + if (mode & WAKE_ARP) + ret |= MLX5_WOL_ARP; + + if (mode & WAKE_BCAST) + ret |= MLX5_WOL_BROADCAST; + + if (mode & WAKE_MCAST) + ret |= MLX5_WOL_MULTICAST; + + if (mode & WAKE_UCAST) + ret |= MLX5_WOL_UNICAST; + + if (mode & WAKE_PHY) + ret |= MLX5_WOL_PHY_ACTIVITY; + + return ret; +} + +static void mlx5e_get_wol(struct net_device *netdev, + struct ethtool_wolinfo *wol) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + u8 mlx5_wol_mode; + int err; + + memset(wol, 0, sizeof(*wol)); + + wol->supported = mlx5e_get_wol_supported(mdev); + if (!wol->supported) + return; + + err = mlx5_query_port_wol(mdev, &mlx5_wol_mode); + if (err) + return; + + wol->wolopts = mlx5e_refomrat_wol_mode_mlx5_to_linux(mlx5_wol_mode); +} + +static int mlx5e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + __u32 wol_supported = mlx5e_get_wol_supported(mdev); + u32 mlx5_wol_mode; + + if (!wol_supported) + return -ENOTSUPP; + + if (wol->wolopts & ~wol_supported) + return -EINVAL; + + mlx5_wol_mode = mlx5e_refomrat_wol_mode_linux_to_mlx5(wol->wolopts); + + return mlx5_set_port_wol(mdev, mlx5_wol_mode); +} + const struct ethtool_ops mlx5e_ethtool_ops = { .get_drvinfo = mlx5e_get_drvinfo, .get_link = ethtool_op_get_link, @@ -924,4 +1060,6 @@ const struct ethtool_ops mlx5e_ethtool_ops = { .get_pauseparam = mlx5e_get_pauseparam, .set_pauseparam = mlx5e_set_pauseparam, .get_ts_info = mlx5e_get_ts_info, + .get_wol = mlx5e_get_wol, + .set_wol = mlx5e_set_wol, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 80d81abc4820..d00a24203410 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -1041,7 +1041,7 @@ static int mlx5e_create_main_flow_table(struct mlx5e_priv *priv) int err; ft->num_groups = 0; - ft->t = mlx5_create_flow_table(priv->fts.ns, 0, MLX5E_MAIN_TABLE_SIZE); + ft->t = mlx5_create_flow_table(priv->fts.ns, 1, MLX5E_MAIN_TABLE_SIZE); if (IS_ERR(ft->t)) { err = PTR_ERR(ft->t); @@ -1150,7 +1150,7 @@ static int mlx5e_create_vlan_flow_table(struct mlx5e_priv *priv) int err; ft->num_groups = 0; - ft->t = mlx5_create_flow_table(priv->fts.ns, 0, MLX5E_VLAN_TABLE_SIZE); + ft->t = mlx5_create_flow_table(priv->fts.ns, 1, MLX5E_VLAN_TABLE_SIZE); if (IS_ERR(ft->t)) { err = PTR_ERR(ft->t); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 0c49951606b6..e0adb604f461 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2015, Mellanox Technologies. All rights reserved. + * Copyright (c) 2015-2016, Mellanox Technologies. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -30,9 +30,14 @@ * SOFTWARE. */ +#include <net/tc_act/tc_gact.h> +#include <net/pkt_cls.h> #include <linux/mlx5/fs.h> +#include <net/vxlan.h> #include "en.h" +#include "en_tc.h" #include "eswitch.h" +#include "vxlan.h" struct mlx5e_rq_param { u32 rqc[MLX5_ST_SZ_DW(rqc)]; @@ -147,9 +152,12 @@ void mlx5e_update_stats(struct mlx5e_priv *priv) s->tx_bytes = 0; s->tso_packets = 0; s->tso_bytes = 0; + s->tso_inner_packets = 0; + s->tso_inner_bytes = 0; s->tx_queue_stopped = 0; s->tx_queue_wake = 0; s->tx_queue_dropped = 0; + s->tx_csum_inner = 0; tx_offload_none = 0; s->lro_packets = 0; s->lro_bytes = 0; @@ -174,9 +182,12 @@ void mlx5e_update_stats(struct mlx5e_priv *priv) s->tx_bytes += sq_stats->bytes; s->tso_packets += sq_stats->tso_packets; s->tso_bytes += sq_stats->tso_bytes; + s->tso_inner_packets += sq_stats->tso_inner_packets; + s->tso_inner_bytes += sq_stats->tso_inner_bytes; s->tx_queue_stopped += sq_stats->stopped; s->tx_queue_wake += sq_stats->wake; s->tx_queue_dropped += sq_stats->dropped; + s->tx_csum_inner += sq_stats->csum_offload_inner; tx_offload_none += sq_stats->csum_offload_none; } } @@ -234,7 +245,7 @@ void mlx5e_update_stats(struct mlx5e_priv *priv) MLX5_GET_CTR(out, transmitted_eth_broadcast.octets); /* Update calculated offload counters */ - s->tx_csum_offload = s->tx_packets - tx_offload_none; + s->tx_csum_offload = s->tx_packets - tx_offload_none - s->tx_csum_inner; s->rx_csum_good = s->rx_packets - s->rx_csum_none - s->rx_csum_sw; @@ -258,9 +269,14 @@ static void mlx5e_update_stats_work(struct work_struct *work) mutex_unlock(&priv->state_lock); } -static void __mlx5e_async_event(struct mlx5e_priv *priv, - enum mlx5_dev_event event) +static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv, + enum mlx5_dev_event event, unsigned long param) { + struct mlx5e_priv *priv = vpriv; + + if (!test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state)) + return; + switch (event) { case MLX5_DEV_EVENT_PORT_UP: case MLX5_DEV_EVENT_PORT_DOWN: @@ -272,17 +288,6 @@ static void __mlx5e_async_event(struct mlx5e_priv *priv, } } -static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv, - enum mlx5_dev_event event, unsigned long param) -{ - struct mlx5e_priv *priv = vpriv; - - spin_lock(&priv->async_events_spinlock); - if (test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state)) - __mlx5e_async_event(priv, event); - spin_unlock(&priv->async_events_spinlock); -} - static void mlx5e_enable_async_events(struct mlx5e_priv *priv) { set_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state); @@ -290,9 +295,8 @@ static void mlx5e_enable_async_events(struct mlx5e_priv *priv) static void mlx5e_disable_async_events(struct mlx5e_priv *priv) { - spin_lock_irq(&priv->async_events_spinlock); clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLE, &priv->state); - spin_unlock_irq(&priv->async_events_spinlock); + synchronize_irq(mlx5_get_msix_vec(priv->mdev, MLX5_EQ_VEC_ASYNC)); } #define MLX5E_HW2SW_MTU(hwmtu) (hwmtu - (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN)) @@ -538,7 +542,7 @@ static int mlx5e_create_sq(struct mlx5e_channel *c, int txq_ix; int err; - err = mlx5_alloc_map_uar(mdev, &sq->uar); + err = mlx5_alloc_map_uar(mdev, &sq->uar, true); if (err) return err; @@ -550,8 +554,12 @@ static int mlx5e_create_sq(struct mlx5e_channel *c, goto err_unmap_free_uar; sq->wq.db = &sq->wq.db[MLX5_SND_DBR]; - sq->uar_map = sq->uar.map; - sq->uar_bf_map = sq->uar.bf_map; + if (sq->uar.bf_map) { + set_bit(MLX5E_SQ_STATE_BF_ENABLE, &sq->state); + sq->uar_map = sq->uar.bf_map; + } else { + sq->uar_map = sq->uar.map; + } sq->bf_buf_size = (1 << MLX5_CAP_GEN(mdev, log_bf_reg_size)) / 2; sq->max_inline = param->max_inline; @@ -860,12 +868,10 @@ static int mlx5e_open_cq(struct mlx5e_channel *c, if (err) goto err_destroy_cq; - err = mlx5_core_modify_cq_moderation(mdev, &cq->mcq, - moderation_usecs, - moderation_frames); - if (err) - goto err_destroy_cq; - + if (MLX5_CAP_GEN(mdev, cq_moderation)) + mlx5_core_modify_cq_moderation(mdev, &cq->mcq, + moderation_usecs, + moderation_frames); return 0; err_destroy_cq: @@ -1054,6 +1060,15 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv, param->wq.linear = 1; } +static void mlx5e_build_drop_rq_param(struct mlx5e_rq_param *param) +{ + void *rqc = param->rqc; + void *wq = MLX5_ADDR_OF(rqc, rqc, wq); + + MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST); + MLX5_SET(wq, wq, log_wq_stride, ilog2(sizeof(struct mlx5e_rx_wqe))); +} + static void mlx5e_build_sq_param(struct mlx5e_priv *priv, struct mlx5e_sq_param *param) { @@ -1410,6 +1425,24 @@ static int mlx5e_set_dev_port_mtu(struct net_device *netdev) return 0; } +static void mlx5e_netdev_set_tcs(struct net_device *netdev) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + int nch = priv->params.num_channels; + int ntc = priv->params.num_tc; + int tc; + + netdev_reset_tc(netdev); + + if (ntc == 1) + return; + + netdev_set_num_tc(netdev, ntc); + + for (tc = 0; tc < ntc; tc++) + netdev_set_tc_queue(netdev, tc, nch, tc * nch); +} + int mlx5e_open_locked(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -1418,6 +1451,8 @@ int mlx5e_open_locked(struct net_device *netdev) set_bit(MLX5E_STATE_OPENED, &priv->state); + mlx5e_netdev_set_tcs(netdev); + num_txqs = priv->params.num_channels * priv->params.num_tc; netif_set_real_num_tx_queues(netdev, num_txqs); netif_set_real_num_rx_queues(netdev, priv->params.num_channels); @@ -1440,8 +1475,8 @@ int mlx5e_open_locked(struct net_device *netdev) goto err_close_channels; } - mlx5e_update_carrier(priv); mlx5e_redirect_rqts(priv); + mlx5e_update_carrier(priv); mlx5e_timestamp_init(priv); schedule_delayed_work(&priv->update_stats_work, 0); @@ -1480,8 +1515,8 @@ int mlx5e_close_locked(struct net_device *netdev) clear_bit(MLX5E_STATE_OPENED, &priv->state); mlx5e_timestamp_cleanup(priv); - mlx5e_redirect_rqts(priv); netif_carrier_off(priv->netdev); + mlx5e_redirect_rqts(priv); mlx5e_close_channels(priv); return 0; @@ -1563,8 +1598,7 @@ static int mlx5e_open_drop_rq(struct mlx5e_priv *priv) memset(&cq_param, 0, sizeof(cq_param)); memset(&rq_param, 0, sizeof(rq_param)); - mlx5e_build_rx_cq_param(priv, &cq_param); - mlx5e_build_rq_param(priv, &rq_param); + mlx5e_build_drop_rq_param(&rq_param); err = mlx5e_create_drop_cq(priv, cq, &cq_param); if (err) @@ -1612,7 +1646,7 @@ static int mlx5e_create_tis(struct mlx5e_priv *priv, int tc) memset(in, 0, sizeof(in)); - MLX5_SET(tisc, tisc, prio, tc); + MLX5_SET(tisc, tisc, prio, tc << 1); MLX5_SET(tisc, tisc, transport_domain, priv->tdn); return mlx5_core_create_tis(mdev, in, sizeof(in), &priv->tisn[tc]); @@ -1628,7 +1662,7 @@ static int mlx5e_create_tises(struct mlx5e_priv *priv) int err; int tc; - for (tc = 0; tc < priv->params.num_tc; tc++) { + for (tc = 0; tc < MLX5E_MAX_NUM_TC; tc++) { err = mlx5e_create_tis(priv, tc); if (err) goto err_close_tises; @@ -1647,7 +1681,7 @@ static void mlx5e_destroy_tises(struct mlx5e_priv *priv) { int tc; - for (tc = 0; tc < priv->params.num_tc; tc++) + for (tc = 0; tc < MLX5E_MAX_NUM_TC; tc++) mlx5e_destroy_tis(priv, tc); } @@ -1824,6 +1858,58 @@ static void mlx5e_destroy_tirs(struct mlx5e_priv *priv) mlx5e_destroy_tir(priv, i); } +static int mlx5e_setup_tc(struct net_device *netdev, u8 tc) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + bool was_opened; + int err = 0; + + if (tc && tc != MLX5E_MAX_NUM_TC) + return -EINVAL; + + mutex_lock(&priv->state_lock); + + was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state); + if (was_opened) + mlx5e_close_locked(priv->netdev); + + priv->params.num_tc = tc ? tc : 1; + + if (was_opened) + err = mlx5e_open_locked(priv->netdev); + + mutex_unlock(&priv->state_lock); + + return err; +} + +static int mlx5e_ndo_setup_tc(struct net_device *dev, u32 handle, + __be16 proto, struct tc_to_netdev *tc) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + + if (TC_H_MAJ(handle) != TC_H_MAJ(TC_H_INGRESS)) + goto mqprio; + + switch (tc->type) { + case TC_SETUP_CLSFLOWER: + switch (tc->cls_flower->command) { + case TC_CLSFLOWER_REPLACE: + return mlx5e_configure_flower(priv, proto, tc->cls_flower); + case TC_CLSFLOWER_DESTROY: + return mlx5e_delete_flower(priv, tc->cls_flower); + } + default: + return -EOPNOTSUPP; + } + +mqprio: + if (tc->type != TC_SETUP_MQPRIO) + return -EINVAL; + + return mlx5e_setup_tc(dev, tc->tc); +} + static struct rtnl_link_stats64 * mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) { @@ -1903,6 +1989,13 @@ static int mlx5e_set_features(struct net_device *netdev, mlx5e_disable_vlan_filter(priv); } + if ((changes & NETIF_F_HW_TC) && !(features & NETIF_F_HW_TC) && + mlx5e_tc_num_filters(priv)) { + netdev_err(netdev, + "Active offloaded tc filters, can't turn hw_tc_offload off\n"); + return -EINVAL; + } + return err; } @@ -2026,10 +2119,84 @@ static int mlx5e_get_vf_stats(struct net_device *dev, vf_stats); } +static void mlx5e_add_vxlan_port(struct net_device *netdev, + sa_family_t sa_family, __be16 port) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + + if (!mlx5e_vxlan_allowed(priv->mdev)) + return; + + mlx5e_vxlan_add_port(priv, be16_to_cpu(port)); +} + +static void mlx5e_del_vxlan_port(struct net_device *netdev, + sa_family_t sa_family, __be16 port) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + + if (!mlx5e_vxlan_allowed(priv->mdev)) + return; + + mlx5e_vxlan_del_port(priv, be16_to_cpu(port)); +} + +static netdev_features_t mlx5e_vxlan_features_check(struct mlx5e_priv *priv, + struct sk_buff *skb, + netdev_features_t features) +{ + struct udphdr *udph; + u16 proto; + u16 port = 0; + + switch (vlan_get_protocol(skb)) { + case htons(ETH_P_IP): + proto = ip_hdr(skb)->protocol; + break; + case htons(ETH_P_IPV6): + proto = ipv6_hdr(skb)->nexthdr; + break; + default: + goto out; + } + + if (proto == IPPROTO_UDP) { + udph = udp_hdr(skb); + port = be16_to_cpu(udph->dest); + } + + /* Verify if UDP port is being offloaded by HW */ + if (port && mlx5e_vxlan_lookup_port(priv, port)) + return features; + +out: + /* Disable CSUM and GSO if the udp dport is not offloaded by HW */ + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); +} + +static netdev_features_t mlx5e_features_check(struct sk_buff *skb, + struct net_device *netdev, + netdev_features_t features) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + + features = vlan_features_check(skb, features); + features = vxlan_features_check(skb, features); + + /* Validate if the tunneled packet is being offloaded by HW */ + if (skb->encapsulation && + (features & NETIF_F_CSUM_MASK || features & NETIF_F_GSO_MASK)) + return mlx5e_vxlan_features_check(priv, skb, features); + + return features; +} + static const struct net_device_ops mlx5e_netdev_ops_basic = { .ndo_open = mlx5e_open, .ndo_stop = mlx5e_close, .ndo_start_xmit = mlx5e_xmit, + .ndo_setup_tc = mlx5e_ndo_setup_tc, + .ndo_select_queue = mlx5e_select_queue, .ndo_get_stats64 = mlx5e_get_stats, .ndo_set_rx_mode = mlx5e_set_rx_mode, .ndo_set_mac_address = mlx5e_set_mac, @@ -2044,6 +2211,8 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = { .ndo_open = mlx5e_open, .ndo_stop = mlx5e_close, .ndo_start_xmit = mlx5e_xmit, + .ndo_setup_tc = mlx5e_ndo_setup_tc, + .ndo_select_queue = mlx5e_select_queue, .ndo_get_stats64 = mlx5e_get_stats, .ndo_set_rx_mode = mlx5e_set_rx_mode, .ndo_set_mac_address = mlx5e_set_mac, @@ -2052,6 +2221,9 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = { .ndo_set_features = mlx5e_set_features, .ndo_change_mtu = mlx5e_change_mtu, .ndo_do_ioctl = mlx5e_ioctl, + .ndo_add_vxlan_port = mlx5e_add_vxlan_port, + .ndo_del_vxlan_port = mlx5e_del_vxlan_port, + .ndo_features_check = mlx5e_features_check, .ndo_set_vf_mac = mlx5e_set_vf_mac, .ndo_set_vf_vlan = mlx5e_set_vf_vlan, .ndo_get_vf_config = mlx5e_get_vf_config, @@ -2078,6 +2250,8 @@ static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev) } if (!MLX5_CAP_ETH(mdev, self_lb_en_modifiable)) mlx5_core_warn(mdev, "Self loop back prevention is not supported\n"); + if (!MLX5_CAP_GEN(mdev, cq_moderation)) + mlx5_core_warn(mdev, "CQ modiration is not supported\n"); return 0; } @@ -2091,6 +2265,24 @@ u16 mlx5e_get_max_inline_cap(struct mlx5_core_dev *mdev) 2 /*sizeof(mlx5e_tx_wqe.inline_hdr_start)*/; } +#ifdef CONFIG_MLX5_CORE_EN_DCB +static void mlx5e_ets_init(struct mlx5e_priv *priv) +{ + int i; + + priv->params.ets.ets_cap = mlx5_max_tc(priv->mdev) + 1; + for (i = 0; i < priv->params.ets.ets_cap; i++) { + priv->params.ets.tc_tx_bw[i] = MLX5E_MAX_BW_ALLOC; + priv->params.ets.tc_tsa[i] = IEEE_8021QAZ_TSA_VENDOR; + priv->params.ets.prio_tc[i] = i; + } + + /* tclass[prio=0]=1, tclass[prio=1]=0, tclass[prio=i]=i (for i>1) */ + priv->params.ets.prio_tc[0] = 1; + priv->params.ets.prio_tc[1] = 0; +} +#endif + void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len, int num_channels) { @@ -2122,7 +2314,6 @@ static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev, priv->params.min_rx_wqes = MLX5E_PARAMS_DEFAULT_MIN_RX_WQES; priv->params.num_tc = 1; - priv->params.default_vlan_prio = 0; priv->params.rss_hfunc = ETH_RSS_HASH_XOR; netdev_rss_key_fill(priv->params.toeplitz_hash_key, @@ -2137,9 +2328,11 @@ static void mlx5e_build_netdev_priv(struct mlx5_core_dev *mdev, priv->mdev = mdev; priv->netdev = netdev; priv->params.num_channels = num_channels; - priv->default_vlan_prio = priv->params.default_vlan_prio; - spin_lock_init(&priv->async_events_spinlock); +#ifdef CONFIG_MLX5_CORE_EN_DCB + mlx5e_ets_init(priv); +#endif + mutex_init(&priv->state_lock); INIT_WORK(&priv->update_carrier_work, mlx5e_update_carrier_work); @@ -2166,10 +2359,14 @@ static void mlx5e_build_netdev(struct net_device *netdev) SET_NETDEV_DEV(netdev, &mdev->pdev->dev); - if (MLX5_CAP_GEN(mdev, vport_group_manager)) + if (MLX5_CAP_GEN(mdev, vport_group_manager)) { netdev->netdev_ops = &mlx5e_netdev_ops_sriov; - else +#ifdef CONFIG_MLX5_CORE_EN_DCB + netdev->dcbnl_ops = &mlx5e_dcbnl_ops; +#endif + } else { netdev->netdev_ops = &mlx5e_netdev_ops_basic; + } netdev->watchdog_timeo = 15 * HZ; @@ -2192,10 +2389,27 @@ static void mlx5e_build_netdev(struct net_device *netdev) netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX; netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; + if (mlx5e_vxlan_allowed(mdev)) { + netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; + netdev->hw_enc_features |= NETIF_F_IP_CSUM; + netdev->hw_enc_features |= NETIF_F_RXCSUM; + netdev->hw_enc_features |= NETIF_F_TSO; + netdev->hw_enc_features |= NETIF_F_TSO6; + netdev->hw_enc_features |= NETIF_F_RXHASH; + netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL; + } + netdev->features = netdev->hw_features; if (!priv->params.lro_en) netdev->features &= ~NETIF_F_LRO; +#define FT_CAP(f) MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.f) + if (FT_CAP(flow_modify_en) && + FT_CAP(modify_root) && + FT_CAP(identified_miss_table_mode) && + FT_CAP(flow_table_modify)) + priv->netdev->hw_features |= NETIF_F_HW_TC; + netdev->features |= NETIF_F_HIGHDMA; netdev->priv_flags |= IFF_UNICAST_FLT; @@ -2238,7 +2452,9 @@ static void *mlx5e_create_netdev(struct mlx5_core_dev *mdev) if (mlx5e_check_required_hca_cap(mdev)) return NULL; - netdev = alloc_etherdev_mqs(sizeof(struct mlx5e_priv), nch, nch); + netdev = alloc_etherdev_mqs(sizeof(struct mlx5e_priv), + nch * MLX5E_MAX_NUM_TC, + nch); if (!netdev) { mlx5_core_err(mdev, "alloc_etherdev_mqs() failed\n"); return NULL; @@ -2251,7 +2467,7 @@ static void *mlx5e_create_netdev(struct mlx5_core_dev *mdev) priv = netdev_priv(netdev); - err = mlx5_alloc_map_uar(mdev, &priv->cq_uar); + err = mlx5_alloc_map_uar(mdev, &priv->cq_uar, false); if (err) { mlx5_core_err(mdev, "alloc_map uar failed, %d\n", err); goto err_free_netdev; @@ -2313,17 +2529,33 @@ static void *mlx5e_create_netdev(struct mlx5_core_dev *mdev) mlx5e_init_eth_addr(priv); + mlx5e_vxlan_init(priv); + + err = mlx5e_tc_init(priv); + if (err) + goto err_destroy_flow_tables; + +#ifdef CONFIG_MLX5_CORE_EN_DCB + mlx5e_dcbnl_ieee_setets_core(priv, &priv->params.ets); +#endif + err = register_netdev(netdev); if (err) { mlx5_core_err(mdev, "register_netdev failed, %d\n", err); - goto err_destroy_flow_tables; + goto err_tc_cleanup; } + if (mlx5e_vxlan_allowed(mdev)) + vxlan_get_rx_port(netdev); + mlx5e_enable_async_events(priv); schedule_work(&priv->set_rx_mode_work); return priv; +err_tc_cleanup: + mlx5e_tc_cleanup(priv); + err_destroy_flow_tables: mlx5e_destroy_flow_tables(priv); @@ -2371,6 +2603,8 @@ static void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, void *vpriv) mlx5e_disable_async_events(priv); flush_scheduled_work(); unregister_netdev(netdev); + mlx5e_tc_cleanup(priv); + mlx5e_vxlan_cleanup(priv); mlx5e_destroy_flow_tables(priv); mlx5e_destroy_tirs(priv); mlx5e_destroy_rqt(priv, MLX5E_SINGLE_RQ_RQT); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 59658b9d05d1..58d4e2f962c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -35,6 +35,7 @@ #include <linux/tcp.h> #include <net/busy_poll.h> #include "en.h" +#include "en_tc.h" static inline bool mlx5e_rx_hw_stamp(struct mlx5e_tstamp *tstamp) { @@ -167,14 +168,15 @@ static inline bool is_first_ethertype_ip(struct sk_buff *skb) static inline void mlx5e_handle_csum(struct net_device *netdev, struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq, - struct sk_buff *skb) + struct sk_buff *skb, + bool lro) { if (unlikely(!(netdev->features & NETIF_F_RXCSUM))) goto csum_none; - if (likely(cqe->hds_ip_ext & CQE_L4_OK)) { + if (lro) { skb->ip_summed = CHECKSUM_UNNECESSARY; - } else if (is_first_ethertype_ip(skb)) { + } else if (likely(is_first_ethertype_ip(skb))) { skb->ip_summed = CHECKSUM_COMPLETE; skb->csum = csum_unfold((__force __sum16)cqe->check_sum); rq->stats.csum_sw++; @@ -211,7 +213,7 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, if (unlikely(mlx5e_rx_hw_stamp(tstamp))) mlx5e_fill_hwstamp(tstamp, get_cqe_ts(cqe), skb_hwtstamps(skb)); - mlx5e_handle_csum(netdev, cqe, rq, skb); + mlx5e_handle_csum(netdev, cqe, rq, skb, !!lro_num_seg); skb->protocol = eth_type_trans(skb, netdev); @@ -223,6 +225,8 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, if (cqe_has_vlan(cqe)) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), be16_to_cpu(cqe->vlan_info)); + + skb->mark = be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK; } int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c new file mode 100644 index 000000000000..b3de09f13425 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -0,0 +1,429 @@ +/* + * Copyright (c) 2016, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <net/flow_dissector.h> +#include <net/pkt_cls.h> +#include <net/tc_act/tc_gact.h> +#include <net/tc_act/tc_skbedit.h> +#include <linux/mlx5/fs.h> +#include <linux/mlx5/device.h> +#include <linux/rhashtable.h> +#include "en.h" +#include "en_tc.h" + +struct mlx5e_tc_flow { + struct rhash_head node; + u64 cookie; + struct mlx5_flow_rule *rule; +}; + +#define MLX5E_TC_FLOW_TABLE_NUM_ENTRIES 1024 +#define MLX5E_TC_FLOW_TABLE_NUM_GROUPS 4 + +static struct mlx5_flow_rule *mlx5e_tc_add_flow(struct mlx5e_priv *priv, + u32 *match_c, u32 *match_v, + u32 action, u32 flow_tag) +{ + struct mlx5_flow_destination dest = { + .type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE, + {.ft = priv->fts.vlan.t}, + }; + struct mlx5_flow_rule *rule; + bool table_created = false; + + if (IS_ERR_OR_NULL(priv->fts.tc.t)) { + priv->fts.tc.t = + mlx5_create_auto_grouped_flow_table(priv->fts.ns, 0, + MLX5E_TC_FLOW_TABLE_NUM_ENTRIES, + MLX5E_TC_FLOW_TABLE_NUM_GROUPS); + if (IS_ERR(priv->fts.tc.t)) { + netdev_err(priv->netdev, + "Failed to create tc offload table\n"); + return ERR_CAST(priv->fts.tc.t); + } + + table_created = true; + } + + rule = mlx5_add_flow_rule(priv->fts.tc.t, MLX5_MATCH_OUTER_HEADERS, + match_c, match_v, + action, flow_tag, + action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST ? &dest : NULL); + + if (IS_ERR(rule) && table_created) { + mlx5_destroy_flow_table(priv->fts.tc.t); + priv->fts.tc.t = NULL; + } + + return rule; +} + +static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, + struct mlx5_flow_rule *rule) +{ + mlx5_del_flow_rule(rule); + + if (!mlx5e_tc_num_filters(priv)) { + mlx5_destroy_flow_table(priv->fts.tc.t); + priv->fts.tc.t = NULL; + } +} + +static int parse_cls_flower(struct mlx5e_priv *priv, + u32 *match_c, u32 *match_v, + struct tc_cls_flower_offload *f) +{ + void *headers_c = MLX5_ADDR_OF(fte_match_param, match_c, outer_headers); + void *headers_v = MLX5_ADDR_OF(fte_match_param, match_v, outer_headers); + u16 addr_type = 0; + u8 ip_proto = 0; + + if (f->dissector->used_keys & + ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | + BIT(FLOW_DISSECTOR_KEY_BASIC) | + BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_PORTS))) { + netdev_warn(priv->netdev, "Unsupported key used: 0x%x\n", + f->dissector->used_keys); + return -EOPNOTSUPP; + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_dissector_key_control *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->key); + addr_type = key->addr_type; + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_dissector_key_basic *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->key); + struct flow_dissector_key_basic *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->mask); + ip_proto = key->ip_proto; + + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype, + ntohs(mask->n_proto)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, + ntohs(key->n_proto)); + + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol, + mask->ip_proto); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, + key->ip_proto); + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_dissector_key_eth_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ETH_ADDRS, + f->key); + struct flow_dissector_key_eth_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ETH_ADDRS, + f->mask); + + ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, + dmac_47_16), + mask->dst); + ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, + dmac_47_16), + key->dst); + + ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, + smac_47_16), + mask->src); + ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, + smac_47_16), + key->src); + } + + if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + struct flow_dissector_key_ipv4_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, + f->key); + struct flow_dissector_key_ipv4_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, + f->mask); + + memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, + src_ipv4_src_ipv6.ipv4_layout.ipv4), + &mask->src, sizeof(mask->src)); + memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, + src_ipv4_src_ipv6.ipv4_layout.ipv4), + &key->src, sizeof(key->src)); + memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, + dst_ipv4_dst_ipv6.ipv4_layout.ipv4), + &mask->dst, sizeof(mask->dst)); + memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, + dst_ipv4_dst_ipv6.ipv4_layout.ipv4), + &key->dst, sizeof(key->dst)); + } + + if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + struct flow_dissector_key_ipv6_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, + f->key); + struct flow_dissector_key_ipv6_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, + f->mask); + + memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, + src_ipv4_src_ipv6.ipv6_layout.ipv6), + &mask->src, sizeof(mask->src)); + memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, + src_ipv4_src_ipv6.ipv6_layout.ipv6), + &key->src, sizeof(key->src)); + + memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, + dst_ipv4_dst_ipv6.ipv6_layout.ipv6), + &mask->dst, sizeof(mask->dst)); + memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, + dst_ipv4_dst_ipv6.ipv6_layout.ipv6), + &key->dst, sizeof(key->dst)); + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_dissector_key_ports *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_PORTS, + f->key); + struct flow_dissector_key_ports *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_PORTS, + f->mask); + switch (ip_proto) { + case IPPROTO_TCP: + MLX5_SET(fte_match_set_lyr_2_4, headers_c, + tcp_sport, ntohs(mask->src)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, + tcp_sport, ntohs(key->src)); + + MLX5_SET(fte_match_set_lyr_2_4, headers_c, + tcp_dport, ntohs(mask->dst)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, + tcp_dport, ntohs(key->dst)); + break; + + case IPPROTO_UDP: + MLX5_SET(fte_match_set_lyr_2_4, headers_c, + udp_sport, ntohs(mask->src)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, + udp_sport, ntohs(key->src)); + + MLX5_SET(fte_match_set_lyr_2_4, headers_c, + udp_dport, ntohs(mask->dst)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, + udp_dport, ntohs(key->dst)); + break; + default: + netdev_err(priv->netdev, + "Only UDP and TCP transport are supported\n"); + return -EINVAL; + } + } + + return 0; +} + +static int parse_tc_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, + u32 *action, u32 *flow_tag) +{ + const struct tc_action *a; + + if (tc_no_actions(exts)) + return -EINVAL; + + *flow_tag = MLX5_FS_DEFAULT_FLOW_TAG; + *action = 0; + + tc_for_each_action(a, exts) { + /* Only support a single action per rule */ + if (*action) + return -EINVAL; + + if (is_tcf_gact_shot(a)) { + *action |= MLX5_FLOW_CONTEXT_ACTION_DROP; + continue; + } + + if (is_tcf_skbedit_mark(a)) { + u32 mark = tcf_skbedit_mark(a); + + if (mark & ~MLX5E_TC_FLOW_ID_MASK) { + netdev_warn(priv->netdev, "Bad flow mark - only 16 bit is supported: 0x%x\n", + mark); + return -EINVAL; + } + + *flow_tag = mark; + *action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + continue; + } + + return -EINVAL; + } + + return 0; +} + +int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol, + struct tc_cls_flower_offload *f) +{ + struct mlx5e_tc_flow_table *tc = &priv->fts.tc; + u32 *match_c; + u32 *match_v; + int err = 0; + u32 flow_tag; + u32 action; + struct mlx5e_tc_flow *flow; + struct mlx5_flow_rule *old = NULL; + + flow = rhashtable_lookup_fast(&tc->ht, &f->cookie, + tc->ht_params); + if (flow) + old = flow->rule; + else + flow = kzalloc(sizeof(*flow), GFP_KERNEL); + + match_c = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL); + match_v = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL); + if (!match_c || !match_v || !flow) { + err = -ENOMEM; + goto err_free; + } + + flow->cookie = f->cookie; + + err = parse_cls_flower(priv, match_c, match_v, f); + if (err < 0) + goto err_free; + + err = parse_tc_actions(priv, f->exts, &action, &flow_tag); + if (err < 0) + goto err_free; + + err = rhashtable_insert_fast(&tc->ht, &flow->node, + tc->ht_params); + if (err) + goto err_free; + + flow->rule = mlx5e_tc_add_flow(priv, match_c, match_v, action, + flow_tag); + if (IS_ERR(flow->rule)) { + err = PTR_ERR(flow->rule); + goto err_hash_del; + } + + if (old) + mlx5e_tc_del_flow(priv, old); + + goto out; + +err_hash_del: + rhashtable_remove_fast(&tc->ht, &flow->node, tc->ht_params); + +err_free: + if (!old) + kfree(flow); +out: + kfree(match_c); + kfree(match_v); + return err; +} + +int mlx5e_delete_flower(struct mlx5e_priv *priv, + struct tc_cls_flower_offload *f) +{ + struct mlx5e_tc_flow *flow; + struct mlx5e_tc_flow_table *tc = &priv->fts.tc; + + flow = rhashtable_lookup_fast(&tc->ht, &f->cookie, + tc->ht_params); + if (!flow) + return -EINVAL; + + rhashtable_remove_fast(&tc->ht, &flow->node, tc->ht_params); + + mlx5e_tc_del_flow(priv, flow->rule); + + kfree(flow); + + return 0; +} + +static const struct rhashtable_params mlx5e_tc_flow_ht_params = { + .head_offset = offsetof(struct mlx5e_tc_flow, node), + .key_offset = offsetof(struct mlx5e_tc_flow, cookie), + .key_len = sizeof(((struct mlx5e_tc_flow *)0)->cookie), + .automatic_shrinking = true, +}; + +int mlx5e_tc_init(struct mlx5e_priv *priv) +{ + struct mlx5e_tc_flow_table *tc = &priv->fts.tc; + + tc->ht_params = mlx5e_tc_flow_ht_params; + return rhashtable_init(&tc->ht, &tc->ht_params); +} + +static void _mlx5e_tc_del_flow(void *ptr, void *arg) +{ + struct mlx5e_tc_flow *flow = ptr; + struct mlx5e_priv *priv = arg; + + mlx5e_tc_del_flow(priv, flow->rule); + kfree(flow); +} + +void mlx5e_tc_cleanup(struct mlx5e_priv *priv) +{ + struct mlx5e_tc_flow_table *tc = &priv->fts.tc; + + rhashtable_free_and_destroy(&tc->ht, _mlx5e_tc_del_flow, priv); + + if (!IS_ERR_OR_NULL(priv->fts.tc.t)) { + mlx5_destroy_flow_table(priv->fts.tc.t); + priv->fts.tc.t = NULL; + } +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h new file mode 100644 index 000000000000..d677428dc10f --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -0,0 +1,51 @@ +/* + * Copyright (c) 2016, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef __MLX5_EN_TC_H__ +#define __MLX5_EN_TC_H__ + +#define MLX5E_TC_FLOW_ID_MASK 0x0000ffff + +int mlx5e_tc_init(struct mlx5e_priv *priv); +void mlx5e_tc_cleanup(struct mlx5e_priv *priv); + +int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol, + struct tc_cls_flower_offload *f); +int mlx5e_delete_flower(struct mlx5e_priv *priv, + struct tc_cls_flower_offload *f); + +static inline int mlx5e_tc_num_filters(struct mlx5e_priv *priv) +{ + return atomic_read(&priv->fts.tc.ht.nelems); +} + +#endif /* __MLX5_EN_TC_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index bb4eeeb007de..1ffc7cb6f78c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2015, Mellanox Technologies. All rights reserved. + * Copyright (c) 2015-2016, Mellanox Technologies. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU @@ -109,12 +109,10 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, { struct mlx5e_priv *priv = netdev_priv(dev); int channel_ix = fallback(dev, skb); - int up = skb_vlan_tag_present(skb) ? - skb->vlan_tci >> VLAN_PRIO_SHIFT : - priv->default_vlan_prio; - int tc = netdev_get_prio_tc_map(dev, up); + int up = (netdev_get_num_tc(dev) && skb_vlan_tag_present(skb)) ? + skb->vlan_tci >> VLAN_PRIO_SHIFT : 0; - return priv->channeltc_to_txq_map[channel_ix][tc]; + return priv->channeltc_to_txq_map[channel_ix][up]; } static inline u16 mlx5e_get_inline_hdr_size(struct mlx5e_sq *sq, @@ -188,9 +186,16 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) memset(wqe, 0, sizeof(*wqe)); - if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) - eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM | MLX5_ETH_WQE_L4_CSUM; - else + if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { + eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM; + if (skb->encapsulation) { + eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM | + MLX5_ETH_WQE_L4_INNER_CSUM; + sq->stats.csum_offload_inner++; + } else { + eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM; + } + } else sq->stats.csum_offload_none++; if (sq->cc != sq->prev_cc) { @@ -199,15 +204,20 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) } if (skb_is_gso(skb)) { - u32 payload_len; - eseg->mss = cpu_to_be16(skb_shinfo(skb)->gso_size); opcode = MLX5_OPCODE_LSO; - ihs = skb_transport_offset(skb) + tcp_hdrlen(skb); - payload_len = skb->len - ihs; + + if (skb->encapsulation) { + ihs = skb_inner_transport_offset(skb) + inner_tcp_hdrlen(skb); + sq->stats.tso_inner_packets++; + sq->stats.tso_inner_bytes += skb->len - ihs; + } else { + ihs = skb_transport_offset(skb) + tcp_hdrlen(skb); + sq->stats.tso_packets++; + sq->stats.tso_bytes += skb->len - ihs; + } + num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs; - sq->stats.tso_packets++; - sq->stats.tso_bytes += payload_len; } else { bf = sq->bf_budget && !skb->xmit_more && @@ -295,7 +305,7 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_sq *sq, struct sk_buff *skb) if (!skb->xmit_more || netif_xmit_stopped(sq->txq)) { int bf_sz = 0; - if (bf && sq->uar_bf_map) + if (bf && test_bit(MLX5E_SQ_STATE_BF_ENABLE, &sq->state)) bf_sz = wi->num_wqebbs << 3; cseg->fm_ce_se = MLX5_WQE_CTRL_CQ_UPDATE; @@ -329,7 +339,7 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev) return mlx5e_sq_xmit(sq, skb); } -bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq) +bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) { struct mlx5e_sq *sq; u32 dma_fifo_cc; @@ -401,7 +411,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq) npkts++; nbytes += wi->num_bytes; sqcc += wi->num_wqebbs; - dev_kfree_skb(skb); + napi_consume_skb(skb, napi_budget); } while (!last_wqe); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index 66d51a77609e..9bb4395aceeb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -60,7 +60,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) clear_bit(MLX5E_CHANNEL_NAPI_SCHED, &c->flags); for (i = 0; i < c->num_tc; i++) - busy |= mlx5e_poll_tx_cq(&c->sq[i].cq); + busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget); work_done = mlx5e_poll_rx_cq(&c->rq.cq, budget); busy |= work_done == budget; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 647a3ca2c2a9..18fccec72c5d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -442,6 +442,11 @@ int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq) } EXPORT_SYMBOL_GPL(mlx5_destroy_unmap_eq); +u32 mlx5_get_msix_vec(struct mlx5_core_dev *dev, int vecidx) +{ + return dev->priv.msix_arr[MLX5_EQ_VEC_ASYNC].vector; +} + int mlx5_eq_init(struct mlx5_core_dev *dev) { int err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index a9894d2e8e26..f46f1db0fc00 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -218,19 +218,22 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, match_value); memcpy(in_match_value, &fte->val, MLX5_ST_SZ_BYTES(fte_match_param)); - in_dests = MLX5_ADDR_OF(flow_context, in_flow_context, destination); - list_for_each_entry(dst, &fte->node.children, node.list) { - unsigned int id; - - MLX5_SET(dest_format_struct, in_dests, destination_type, - dst->dest_attr.type); - if (dst->dest_attr.type == - MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE) - id = dst->dest_attr.ft->id; - else - id = dst->dest_attr.tir_num; - MLX5_SET(dest_format_struct, in_dests, destination_id, id); - in_dests += MLX5_ST_SZ_BYTES(dest_format_struct); + if (fte->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { + in_dests = MLX5_ADDR_OF(flow_context, in_flow_context, destination); + list_for_each_entry(dst, &fte->node.children, node.list) { + unsigned int id; + + MLX5_SET(dest_format_struct, in_dests, destination_type, + dst->dest_attr.type); + if (dst->dest_attr.type == + MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE) { + id = dst->dest_attr.ft->id; + } else { + id = dst->dest_attr.tir_num; + } + MLX5_SET(dest_format_struct, in_dests, destination_id, id); + in_dests += MLX5_ST_SZ_BYTES(dest_format_struct); + } } memset(out, 0, sizeof(out)); err = mlx5_cmd_exec_check_status(dev, in, inlen, out, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index bf3446794bd5..5121be4675d1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -73,8 +73,8 @@ #define BY_PASS_MIN_LEVEL (KENREL_MIN_LEVEL + MLX5_BY_PASS_NUM_PRIOS +\ LEFTOVERS_MAX_FT) -#define KERNEL_MAX_FT 2 -#define KERNEL_NUM_PRIOS 1 +#define KERNEL_MAX_FT 3 +#define KERNEL_NUM_PRIOS 2 #define KENREL_MIN_LEVEL 2 #define ANCHOR_MAX_FT 1 @@ -372,8 +372,8 @@ static void del_rule(struct fs_node *node) list_del(&rule->next_ft); mutex_unlock(&rule->dest_attr.ft->lock); } - fte->dests_size--; - if (fte->dests_size) { + if ((fte->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) && + --fte->dests_size) { err = mlx5_cmd_update_fte(dev, ft, fg->id, fte); if (err) @@ -837,7 +837,8 @@ static struct mlx5_flow_rule *alloc_rule(struct mlx5_flow_destination *dest) INIT_LIST_HEAD(&rule->next_ft); rule->node.type = FS_TYPE_FLOW_DEST; - memcpy(&rule->dest_attr, dest, sizeof(*dest)); + if (dest) + memcpy(&rule->dest_attr, dest, sizeof(*dest)); return rule; } @@ -864,8 +865,9 @@ static struct mlx5_flow_rule *add_rule_fte(struct fs_fte *fte, list_add(&rule->node.list, &fte->node.children); else list_add_tail(&rule->node.list, &fte->node.children); - fte->dests_size++; - if (fte->dests_size == 1) + if (dest) + fte->dests_size++; + if (fte->dests_size == 1 || !dest) err = mlx5_cmd_create_fte(get_dev(&ft->node), ft, fg->id, fte); else @@ -881,7 +883,8 @@ static struct mlx5_flow_rule *add_rule_fte(struct fs_fte *fte, free_rule: list_del(&rule->node.list); kfree(rule); - fte->dests_size--; + if (dest) + fte->dests_size--; return ERR_PTR(err); } @@ -1101,6 +1104,9 @@ _mlx5_add_flow_rule(struct mlx5_flow_table *ft, struct mlx5_flow_group *g; struct mlx5_flow_rule *rule; + if ((action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) && !dest) + return ERR_PTR(-EINVAL); + nested_lock_ref_node(&ft->node, FS_MUTEX_GRANDPARENT); fs_for_each_fg(g, ft) if (compare_match_criteria(g->mask.match_criteria_enable, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 0916bbc69269..72a94e72ee25 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -767,22 +767,6 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev) return -ENOTSUPP; } -static int map_bf_area(struct mlx5_core_dev *dev) -{ - resource_size_t bf_start = pci_resource_start(dev->pdev, 0); - resource_size_t bf_len = pci_resource_len(dev->pdev, 0); - - dev->priv.bf_mapping = io_mapping_create_wc(bf_start, bf_len); - - return dev->priv.bf_mapping ? 0 : -ENOMEM; -} - -static void unmap_bf_area(struct mlx5_core_dev *dev) -{ - if (dev->priv.bf_mapping) - io_mapping_free(dev->priv.bf_mapping); -} - static void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv) { struct mlx5_device_context *dev_ctx; @@ -1103,14 +1087,9 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) goto err_stop_eqs; } - if (map_bf_area(dev)) - dev_err(&pdev->dev, "Failed to map blue flame area\n"); - err = mlx5_irq_set_affinity_hints(dev); - if (err) { + if (err) dev_err(&pdev->dev, "Failed to alloc affinity hint cpumask\n"); - goto err_unmap_bf_area; - } MLX5_INIT_DOORBELL_LOCK(&priv->cq_uar_lock); @@ -1169,10 +1148,6 @@ err_fs: mlx5_cleanup_qp_table(dev); mlx5_cleanup_cq_table(dev); mlx5_irq_clear_affinity_hints(dev); - -err_unmap_bf_area: - unmap_bf_area(dev); - free_comp_eqs(dev); err_stop_eqs: @@ -1242,7 +1217,6 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) mlx5_cleanup_qp_table(dev); mlx5_cleanup_cq_table(dev); mlx5_irq_clear_affinity_hints(dev); - unmap_bf_area(dev); free_comp_eqs(dev); mlx5_stop_eqs(dev); mlx5_free_uuars(dev, &priv->uuari); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 0336847ec9a1..0b0b226c789e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -99,6 +99,7 @@ int mlx5_core_enable_hca(struct mlx5_core_dev *dev, u16 func_id); int mlx5_core_disable_hca(struct mlx5_core_dev *dev, u16 func_id); int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev); cycle_t mlx5_read_internal_timer(struct mlx5_core_dev *dev); +u32 mlx5_get_msix_vec(struct mlx5_core_dev *dev, int vecidx); void mlx5e_init(void); void mlx5e_cleanup(void); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 5635ce7ad693..ae378c575deb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -32,6 +32,7 @@ #include <linux/module.h> #include <linux/mlx5/driver.h> +#include <linux/mlx5/port.h> #include <linux/mlx5/cmd.h> #include "mlx5_core.h" @@ -386,3 +387,223 @@ int mlx5_query_port_pause(struct mlx5_core_dev *dev, return 0; } EXPORT_SYMBOL_GPL(mlx5_query_port_pause); + +int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx) +{ + u32 in[MLX5_ST_SZ_DW(pfcc_reg)]; + u32 out[MLX5_ST_SZ_DW(pfcc_reg)]; + + memset(in, 0, sizeof(in)); + MLX5_SET(pfcc_reg, in, local_port, 1); + MLX5_SET(pfcc_reg, in, pfctx, pfc_en_tx); + MLX5_SET(pfcc_reg, in, pfcrx, pfc_en_rx); + MLX5_SET_TO_ONES(pfcc_reg, in, prio_mask_tx); + MLX5_SET_TO_ONES(pfcc_reg, in, prio_mask_rx); + + return mlx5_core_access_reg(dev, in, sizeof(in), out, + sizeof(out), MLX5_REG_PFCC, 0, 1); +} +EXPORT_SYMBOL_GPL(mlx5_set_port_pfc); + +int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx) +{ + u32 in[MLX5_ST_SZ_DW(pfcc_reg)]; + u32 out[MLX5_ST_SZ_DW(pfcc_reg)]; + int err; + + memset(in, 0, sizeof(in)); + MLX5_SET(pfcc_reg, in, local_port, 1); + + err = mlx5_core_access_reg(dev, in, sizeof(in), out, + sizeof(out), MLX5_REG_PFCC, 0, 0); + if (err) + return err; + + if (pfc_en_tx) + *pfc_en_tx = MLX5_GET(pfcc_reg, out, pfctx); + + if (pfc_en_rx) + *pfc_en_rx = MLX5_GET(pfcc_reg, out, pfcrx); + + return 0; +} +EXPORT_SYMBOL_GPL(mlx5_query_port_pfc); + +int mlx5_max_tc(struct mlx5_core_dev *mdev) +{ + u8 num_tc = MLX5_CAP_GEN(mdev, max_tc) ? : 8; + + return num_tc - 1; +} + +int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc) +{ + u32 in[MLX5_ST_SZ_DW(qtct_reg)]; + u32 out[MLX5_ST_SZ_DW(qtct_reg)]; + int err; + int i; + + memset(in, 0, sizeof(in)); + for (i = 0; i < 8; i++) { + if (prio_tc[i] > mlx5_max_tc(mdev)) + return -EINVAL; + + MLX5_SET(qtct_reg, in, prio, i); + MLX5_SET(qtct_reg, in, tclass, prio_tc[i]); + + err = mlx5_core_access_reg(mdev, in, sizeof(in), out, + sizeof(out), MLX5_REG_QTCT, 0, 1); + if (err) + return err; + } + + return 0; +} +EXPORT_SYMBOL_GPL(mlx5_set_port_prio_tc); + +static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in, + int inlen) +{ + u32 out[MLX5_ST_SZ_DW(qtct_reg)]; + + if (!MLX5_CAP_GEN(mdev, ets)) + return -ENOTSUPP; + + return mlx5_core_access_reg(mdev, in, inlen, out, sizeof(out), + MLX5_REG_QETCR, 0, 1); +} + +static int mlx5_query_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *out, + int outlen) +{ + u32 in[MLX5_ST_SZ_DW(qtct_reg)]; + + if (!MLX5_CAP_GEN(mdev, ets)) + return -ENOTSUPP; + + memset(in, 0, sizeof(in)); + return mlx5_core_access_reg(mdev, in, sizeof(in), out, outlen, + MLX5_REG_QETCR, 0, 0); +} + +int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group) +{ + u32 in[MLX5_ST_SZ_DW(qetc_reg)]; + int i; + + memset(in, 0, sizeof(in)); + + for (i = 0; i <= mlx5_max_tc(mdev); i++) { + MLX5_SET(qetc_reg, in, tc_configuration[i].g, 1); + MLX5_SET(qetc_reg, in, tc_configuration[i].group, tc_group[i]); + } + + return mlx5_set_port_qetcr_reg(mdev, in, sizeof(in)); +} +EXPORT_SYMBOL_GPL(mlx5_set_port_tc_group); + +int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw) +{ + u32 in[MLX5_ST_SZ_DW(qetc_reg)]; + int i; + + memset(in, 0, sizeof(in)); + + for (i = 0; i <= mlx5_max_tc(mdev); i++) { + MLX5_SET(qetc_reg, in, tc_configuration[i].b, 1); + MLX5_SET(qetc_reg, in, tc_configuration[i].bw_allocation, tc_bw[i]); + } + + return mlx5_set_port_qetcr_reg(mdev, in, sizeof(in)); +} +EXPORT_SYMBOL_GPL(mlx5_set_port_tc_bw_alloc); + +int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev, + u8 *max_bw_value, + u8 *max_bw_units) +{ + u32 in[MLX5_ST_SZ_DW(qetc_reg)]; + void *ets_tcn_conf; + int i; + + memset(in, 0, sizeof(in)); + + MLX5_SET(qetc_reg, in, port_number, 1); + + for (i = 0; i <= mlx5_max_tc(mdev); i++) { + ets_tcn_conf = MLX5_ADDR_OF(qetc_reg, in, tc_configuration[i]); + + MLX5_SET(ets_tcn_config_reg, ets_tcn_conf, r, 1); + MLX5_SET(ets_tcn_config_reg, ets_tcn_conf, max_bw_units, + max_bw_units[i]); + MLX5_SET(ets_tcn_config_reg, ets_tcn_conf, max_bw_value, + max_bw_value[i]); + } + + return mlx5_set_port_qetcr_reg(mdev, in, sizeof(in)); +} +EXPORT_SYMBOL_GPL(mlx5_modify_port_ets_rate_limit); + +int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev, + u8 *max_bw_value, + u8 *max_bw_units) +{ + u32 out[MLX5_ST_SZ_DW(qetc_reg)]; + void *ets_tcn_conf; + int err; + int i; + + err = mlx5_query_port_qetcr_reg(mdev, out, sizeof(out)); + if (err) + return err; + + for (i = 0; i <= mlx5_max_tc(mdev); i++) { + ets_tcn_conf = MLX5_ADDR_OF(qetc_reg, out, tc_configuration[i]); + + max_bw_value[i] = MLX5_GET(ets_tcn_config_reg, ets_tcn_conf, + max_bw_value); + max_bw_units[i] = MLX5_GET(ets_tcn_config_reg, ets_tcn_conf, + max_bw_units); + } + + return 0; +} +EXPORT_SYMBOL_GPL(mlx5_query_port_ets_rate_limit); + +int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode) +{ + u32 in[MLX5_ST_SZ_DW(set_wol_rol_in)]; + u32 out[MLX5_ST_SZ_DW(set_wol_rol_out)]; + + memset(in, 0, sizeof(in)); + memset(out, 0, sizeof(out)); + + MLX5_SET(set_wol_rol_in, in, opcode, MLX5_CMD_OP_SET_WOL_ROL); + MLX5_SET(set_wol_rol_in, in, wol_mode_valid, 1); + MLX5_SET(set_wol_rol_in, in, wol_mode, wol_mode); + + return mlx5_cmd_exec_check_status(mdev, in, sizeof(in), + out, sizeof(out)); +} +EXPORT_SYMBOL_GPL(mlx5_set_port_wol); + +int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode) +{ + u32 in[MLX5_ST_SZ_DW(query_wol_rol_in)]; + u32 out[MLX5_ST_SZ_DW(query_wol_rol_out)]; + int err; + + memset(in, 0, sizeof(in)); + memset(out, 0, sizeof(out)); + + MLX5_SET(query_wol_rol_in, in, opcode, MLX5_CMD_OP_QUERY_WOL_ROL); + + err = mlx5_cmd_exec_check_status(mdev, in, sizeof(in), + out, sizeof(out)); + + if (!err) + *wol_mode = MLX5_GET(query_wol_rol_out, out, wol_mode); + + return err; +} +EXPORT_SYMBOL_GPL(mlx5_query_port_wol); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c index eb05c845ece9..8ba080e441a1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c @@ -226,7 +226,8 @@ int mlx5_free_uuars(struct mlx5_core_dev *dev, struct mlx5_uuar_info *uuari) return 0; } -int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar) +int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar, + bool map_wc) { phys_addr_t pfn; phys_addr_t uar_bar_start; @@ -240,20 +241,26 @@ int mlx5_alloc_map_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar) uar_bar_start = pci_resource_start(mdev->pdev, 0); pfn = (uar_bar_start >> PAGE_SHIFT) + uar->index; - uar->map = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE); - if (!uar->map) { - mlx5_core_warn(mdev, "ioremap() failed, %d\n", err); - err = -ENOMEM; - goto err_free_uar; - } - if (mdev->priv.bf_mapping) - uar->bf_map = io_mapping_map_wc(mdev->priv.bf_mapping, - uar->index << PAGE_SHIFT); + if (map_wc) { + uar->bf_map = ioremap_wc(pfn << PAGE_SHIFT, PAGE_SIZE); + if (!uar->bf_map) { + mlx5_core_warn(mdev, "ioremap_wc() failed\n"); + uar->map = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE); + if (!uar->map) + goto err_free_uar; + } + } else { + uar->map = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE); + if (!uar->map) + goto err_free_uar; + } return 0; err_free_uar: + mlx5_core_warn(mdev, "ioremap() failed\n"); + err = -ENOMEM; mlx5_cmd_free_uar(mdev, uar->index); return err; @@ -262,8 +269,8 @@ EXPORT_SYMBOL(mlx5_alloc_map_uar); void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar) { - io_mapping_unmap(uar->bf_map); iounmap(uar->map); + iounmap(uar->bf_map); mlx5_cmd_free_uar(mdev, uar->index); } EXPORT_SYMBOL(mlx5_unmap_free_uar); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c new file mode 100644 index 000000000000..9f10df25f3cd --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c @@ -0,0 +1,170 @@ +/* + * Copyright (c) 2016, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/mlx5/driver.h> +#include "mlx5_core.h" +#include "vxlan.h" + +void mlx5e_vxlan_init(struct mlx5e_priv *priv) +{ + struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan; + + spin_lock_init(&vxlan_db->lock); + INIT_RADIX_TREE(&vxlan_db->tree, GFP_ATOMIC); +} + +static int mlx5e_vxlan_core_add_port_cmd(struct mlx5_core_dev *mdev, u16 port) +{ + struct mlx5_outbox_hdr *hdr; + int err; + + u32 in[MLX5_ST_SZ_DW(add_vxlan_udp_dport_in)]; + u32 out[MLX5_ST_SZ_DW(add_vxlan_udp_dport_out)]; + + memset(in, 0, sizeof(in)); + memset(out, 0, sizeof(out)); + + MLX5_SET(add_vxlan_udp_dport_in, in, opcode, + MLX5_CMD_OP_ADD_VXLAN_UDP_DPORT); + MLX5_SET(add_vxlan_udp_dport_in, in, vxlan_udp_port, port); + + err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); + if (err) + return err; + + hdr = (struct mlx5_outbox_hdr *)out; + return hdr->status ? -ENOMEM : 0; +} + +static int mlx5e_vxlan_core_del_port_cmd(struct mlx5_core_dev *mdev, u16 port) +{ + u32 in[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_in)]; + u32 out[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_out)]; + + memset(&in, 0, sizeof(in)); + memset(&out, 0, sizeof(out)); + + MLX5_SET(delete_vxlan_udp_dport_in, in, opcode, + MLX5_CMD_OP_DELETE_VXLAN_UDP_DPORT); + MLX5_SET(delete_vxlan_udp_dport_in, in, vxlan_udp_port, port); + + return mlx5_cmd_exec_check_status(mdev, in, sizeof(in), out, + sizeof(out)); +} + +struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port) +{ + struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan; + struct mlx5e_vxlan *vxlan; + + spin_lock(&vxlan_db->lock); + vxlan = radix_tree_lookup(&vxlan_db->tree, port); + spin_unlock(&vxlan_db->lock); + + return vxlan; +} + +int mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port) +{ + struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan; + struct mlx5e_vxlan *vxlan; + int err; + + err = mlx5e_vxlan_core_add_port_cmd(priv->mdev, port); + if (err) + return err; + + vxlan = kzalloc(sizeof(*vxlan), GFP_KERNEL); + if (!vxlan) { + err = -ENOMEM; + goto err_delete_port; + } + + vxlan->udp_port = port; + + spin_lock_irq(&vxlan_db->lock); + err = radix_tree_insert(&vxlan_db->tree, vxlan->udp_port, vxlan); + spin_unlock_irq(&vxlan_db->lock); + if (err) + goto err_free; + + return 0; + +err_free: + kfree(vxlan); +err_delete_port: + mlx5e_vxlan_core_del_port_cmd(priv->mdev, port); + return err; +} + +static void __mlx5e_vxlan_core_del_port(struct mlx5e_priv *priv, u16 port) +{ + struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan; + struct mlx5e_vxlan *vxlan; + + spin_lock_irq(&vxlan_db->lock); + vxlan = radix_tree_delete(&vxlan_db->tree, port); + spin_unlock_irq(&vxlan_db->lock); + + if (!vxlan) + return; + + mlx5e_vxlan_core_del_port_cmd(priv->mdev, vxlan->udp_port); + + kfree(vxlan); +} + +void mlx5e_vxlan_del_port(struct mlx5e_priv *priv, u16 port) +{ + if (!mlx5e_vxlan_lookup_port(priv, port)) + return; + + __mlx5e_vxlan_core_del_port(priv, port); +} + +void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv) +{ + struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan; + struct mlx5e_vxlan *vxlan; + unsigned int port = 0; + + spin_lock_irq(&vxlan_db->lock); + while (radix_tree_gang_lookup(&vxlan_db->tree, (void **)&vxlan, port, 1)) { + port = vxlan->udp_port; + spin_unlock_irq(&vxlan_db->lock); + __mlx5e_vxlan_core_del_port(priv, (u16)port); + spin_lock_irq(&vxlan_db->lock); + } + spin_unlock_irq(&vxlan_db->lock); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h new file mode 100644 index 000000000000..a01685056ab1 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h @@ -0,0 +1,54 @@ +/* + * Copyright (c) 2016, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ +#ifndef __MLX5_VXLAN_H__ +#define __MLX5_VXLAN_H__ + +#include <linux/mlx5/driver.h> +#include "en.h" + +struct mlx5e_vxlan { + u16 udp_port; +}; + +static inline bool mlx5e_vxlan_allowed(struct mlx5_core_dev *mdev) +{ + return (MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) && + mlx5_core_is_pf(mdev)); +} + +void mlx5e_vxlan_init(struct mlx5e_priv *priv); +int mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port); +void mlx5e_vxlan_del_port(struct mlx5e_priv *priv, u16 port); +struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port); +void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv); + +#endif /* __MLX5_VXLAN_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig index ce26adcb4988..2ad7f67854d5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig @@ -4,6 +4,7 @@ config MLXSW_CORE tristate "Mellanox Technologies Switch ASICs support" + depends on MAY_USE_DEVLINK ---help--- This driver supports Mellanox Technologies Switch ASICs family. diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 22379eb8e924..f69f6280519f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -56,6 +56,7 @@ #include <linux/rcupdate.h> #include <linux/slab.h> #include <asm/byteorder.h> +#include <net/devlink.h> #include "core.h" #include "item.h" @@ -784,6 +785,38 @@ static void mlxsw_core_debugfs_fini(struct mlxsw_core *mlxsw_core) debugfs_remove_recursive(mlxsw_core->dbg_dir); } +static int mlxsw_devlink_port_split(struct devlink *devlink, + unsigned int port_index, + unsigned int count) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + + if (port_index >= MLXSW_PORT_MAX_PORTS) + return -EINVAL; + if (!mlxsw_core->driver->port_split) + return -EOPNOTSUPP; + return mlxsw_core->driver->port_split(mlxsw_core->driver_priv, + port_index, count); +} + +static int mlxsw_devlink_port_unsplit(struct devlink *devlink, + unsigned int port_index) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + + if (port_index >= MLXSW_PORT_MAX_PORTS) + return -EINVAL; + if (!mlxsw_core->driver->port_unsplit) + return -EOPNOTSUPP; + return mlxsw_core->driver->port_unsplit(mlxsw_core->driver_priv, + port_index); +} + +static const struct devlink_ops mlxsw_devlink_ops = { + .port_split = mlxsw_devlink_port_split, + .port_unsplit = mlxsw_devlink_port_unsplit, +}; + int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, const struct mlxsw_bus *mlxsw_bus, void *bus_priv) @@ -791,6 +824,7 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, const char *device_kind = mlxsw_bus_info->device_kind; struct mlxsw_core *mlxsw_core; struct mlxsw_driver *mlxsw_driver; + struct devlink *devlink; size_t alloc_size; int err; @@ -798,12 +832,13 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, if (!mlxsw_driver) return -EINVAL; alloc_size = sizeof(*mlxsw_core) + mlxsw_driver->priv_size; - mlxsw_core = kzalloc(alloc_size, GFP_KERNEL); - if (!mlxsw_core) { + devlink = devlink_alloc(&mlxsw_devlink_ops, alloc_size); + if (!devlink) { err = -ENOMEM; - goto err_core_alloc; + goto err_devlink_alloc; } + mlxsw_core = devlink_priv(devlink); INIT_LIST_HEAD(&mlxsw_core->rx_listener_list); INIT_LIST_HEAD(&mlxsw_core->event_listener_list); mlxsw_core->driver = mlxsw_driver; @@ -841,6 +876,10 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, if (err) goto err_hwmon_init; + err = devlink_register(devlink, mlxsw_bus_info->dev); + if (err) + goto err_devlink_register; + err = mlxsw_driver->init(mlxsw_core->driver_priv, mlxsw_core, mlxsw_bus_info); if (err) @@ -855,6 +894,8 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, err_debugfs_init: mlxsw_core->driver->fini(mlxsw_core->driver_priv); err_driver_init: + devlink_unregister(devlink); +err_devlink_register: err_hwmon_init: mlxsw_emad_fini(mlxsw_core); err_emad_init: @@ -864,8 +905,8 @@ err_bus_init: err_alloc_lag_mapping: free_percpu(mlxsw_core->pcpu_stats); err_alloc_stats: - kfree(mlxsw_core); -err_core_alloc: + devlink_free(devlink); +err_devlink_alloc: mlxsw_core_driver_put(device_kind); return err; } @@ -874,14 +915,16 @@ EXPORT_SYMBOL(mlxsw_core_bus_device_register); void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core) { const char *device_kind = mlxsw_core->bus_info->device_kind; + struct devlink *devlink = priv_to_devlink(mlxsw_core); mlxsw_core_debugfs_fini(mlxsw_core); mlxsw_core->driver->fini(mlxsw_core->driver_priv); + devlink_unregister(devlink); mlxsw_emad_fini(mlxsw_core); mlxsw_core->bus->fini(mlxsw_core->bus_priv); kfree(mlxsw_core->lag.mapping); free_percpu(mlxsw_core->pcpu_stats); - kfree(mlxsw_core); + devlink_free(devlink); mlxsw_core_driver_put(device_kind); } EXPORT_SYMBOL(mlxsw_core_bus_device_unregister); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index a01723600f0a..c73d1c0792a6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -186,6 +186,8 @@ struct mlxsw_driver { int (*init)(void *driver_priv, struct mlxsw_core *mlxsw_core, const struct mlxsw_bus_info *mlxsw_bus_info); void (*fini)(void *driver_priv); + int (*port_split)(void *driver_priv, u8 local_port, unsigned int count); + int (*port_unsplit)(void *driver_priv, u8 local_port); void (*txhdr_construct)(struct sk_buff *skb, const struct mlxsw_tx_info *tx_info); u8 txhdr_len; diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 7992c553c1f5..7f4173c8eda3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -1681,11 +1681,18 @@ static const struct mlxsw_bus mlxsw_pci_bus = { static int mlxsw_pci_sw_reset(struct mlxsw_pci *mlxsw_pci) { + unsigned long end; + mlxsw_pci_write32(mlxsw_pci, SW_RESET, MLXSW_PCI_SW_RESET_RST_BIT); - /* Current firware does not let us know when the reset is done. - * So we just wait here for constant time and hope for the best. - */ - msleep(MLXSW_PCI_SW_RESET_TIMEOUT_MSECS); + wmb(); /* reset needs to be written before we read control register */ + end = jiffies + msecs_to_jiffies(MLXSW_PCI_SW_RESET_TIMEOUT_MSECS); + do { + u32 val = mlxsw_pci_read32(mlxsw_pci, FW_READY); + + if ((val & MLXSW_PCI_FW_READY_MASK) == MLXSW_PCI_FW_READY_MAGIC) + break; + cond_resched(); + } while (time_before(jiffies, end)); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.h b/drivers/net/ethernet/mellanox/mlxsw/pci.h index 912106054ff2..d942a3e6fa41 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.h @@ -61,6 +61,9 @@ #define MLXSW_PCI_SW_RESET 0xF0010 #define MLXSW_PCI_SW_RESET_RST_BIT BIT(0) #define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 5000 +#define MLXSW_PCI_FW_READY 0xA1844 +#define MLXSW_PCI_FW_READY_MASK 0xFF +#define MLXSW_PCI_FW_READY_MAGIC 0x5E #define MLXSW_PCI_DOORBELL_SDQ_OFFSET 0x000 #define MLXSW_PCI_DOORBELL_RDQ_OFFSET 0x200 diff --git a/drivers/net/ethernet/mellanox/mlxsw/port.h b/drivers/net/ethernet/mellanox/mlxsw/port.h index ae65b9940aed..f33b997f2b61 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/port.h +++ b/drivers/net/ethernet/mellanox/mlxsw/port.h @@ -59,6 +59,8 @@ #define MLXSW_PORT_DONT_CARE (MLXSW_PORT_MAX_PORTS) +#define MLXSW_PORT_MODULE_MAX_WIDTH 4 + enum mlxsw_port_admin_status { MLXSW_PORT_ADMIN_STATUS_UP = 1, MLXSW_PORT_ADMIN_STATUS_DOWN = 2, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index a94daa8c346c..4afbc3e9e381 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -49,6 +49,7 @@ #include <linux/jiffies.h> #include <linux/bitops.h> #include <linux/list.h> +#include <net/devlink.h> #include <net/switchdev.h> #include <generated/utsrelease.h> @@ -304,21 +305,47 @@ mlxsw_sp_port_system_port_mapping_set(struct mlxsw_sp_port *mlxsw_sp_port) return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sspr), sspr_pl); } -static int mlxsw_sp_port_module_check(struct mlxsw_sp_port *mlxsw_sp_port, - bool *p_usable) +static int mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp, + u8 local_port, u8 *p_module, + u8 *p_width) { - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; char pmlp_pl[MLXSW_REG_PMLP_LEN]; int err; - mlxsw_reg_pmlp_pack(pmlp_pl, mlxsw_sp_port->local_port); + mlxsw_reg_pmlp_pack(pmlp_pl, local_port); err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(pmlp), pmlp_pl); if (err) return err; - *p_usable = mlxsw_reg_pmlp_width_get(pmlp_pl) ? true : false; + *p_module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0); + *p_width = mlxsw_reg_pmlp_width_get(pmlp_pl); return 0; } +static int mlxsw_sp_port_module_map(struct mlxsw_sp *mlxsw_sp, u8 local_port, + u8 module, u8 width, u8 lane) +{ + char pmlp_pl[MLXSW_REG_PMLP_LEN]; + int i; + + mlxsw_reg_pmlp_pack(pmlp_pl, local_port); + mlxsw_reg_pmlp_width_set(pmlp_pl, width); + for (i = 0; i < width; i++) { + mlxsw_reg_pmlp_module_set(pmlp_pl, i, module); + mlxsw_reg_pmlp_tx_lane_set(pmlp_pl, i, lane + i); /* Rx & Tx */ + } + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmlp), pmlp_pl); +} + +static int mlxsw_sp_port_module_unmap(struct mlxsw_sp *mlxsw_sp, u8 local_port) +{ + char pmlp_pl[MLXSW_REG_PMLP_LEN]; + + mlxsw_reg_pmlp_pack(pmlp_pl, local_port); + mlxsw_reg_pmlp_width_set(pmlp_pl, 0); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmlp), pmlp_pl); +} + static int mlxsw_sp_port_open(struct net_device *dev) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); @@ -1273,6 +1300,18 @@ static u32 mlxsw_sp_to_ptys_speed(u32 speed) return ptys_proto; } +static u32 mlxsw_sp_to_ptys_upper_speed(u32 upper_speed) +{ + u32 ptys_proto = 0; + int i; + + for (i = 0; i < MLXSW_SP_PORT_LINK_MODE_LEN; i++) { + if (mlxsw_sp_port_link_mode[i].speed <= upper_speed) + ptys_proto |= mlxsw_sp_port_link_mode[i].mask; + } + return ptys_proto; +} + static int mlxsw_sp_port_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) { @@ -1349,11 +1388,27 @@ static const struct ethtool_ops mlxsw_sp_port_ethtool_ops = { .set_settings = mlxsw_sp_port_set_settings, }; -static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port) +static int +mlxsw_sp_port_speed_by_width_set(struct mlxsw_sp_port *mlxsw_sp_port, u8 width) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + u32 upper_speed = MLXSW_SP_PORT_BASE_SPEED * width; + char ptys_pl[MLXSW_REG_PTYS_LEN]; + u32 eth_proto_admin; + + eth_proto_admin = mlxsw_sp_to_ptys_upper_speed(upper_speed); + mlxsw_reg_ptys_pack(ptys_pl, mlxsw_sp_port->local_port, + eth_proto_admin); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl); +} + +static int __mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, + bool split, u8 module, u8 width) { + struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); struct mlxsw_sp_port *mlxsw_sp_port; + struct devlink_port *devlink_port; struct net_device *dev; - bool usable; size_t bytes; int err; @@ -1364,6 +1419,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port) mlxsw_sp_port->dev = dev; mlxsw_sp_port->mlxsw_sp = mlxsw_sp; mlxsw_sp_port->local_port = local_port; + mlxsw_sp_port->split = split; bytes = DIV_ROUND_UP(VLAN_N_VID, BITS_PER_BYTE); mlxsw_sp_port->active_vlans = kzalloc(bytes, GFP_KERNEL); if (!mlxsw_sp_port->active_vlans) { @@ -1404,17 +1460,14 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port) */ dev->hard_header_len += MLXSW_TXHDR_LEN; - err = mlxsw_sp_port_module_check(mlxsw_sp_port, &usable); + devlink_port = &mlxsw_sp_port->devlink_port; + if (mlxsw_sp_port->split) + devlink_port_split_set(devlink_port, module); + err = devlink_port_register(devlink, devlink_port, local_port); if (err) { - dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to check module\n", + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to register devlink port\n", mlxsw_sp_port->local_port); - goto err_port_module_check; - } - - if (!usable) { - dev_dbg(mlxsw_sp->bus_info->dev, "Port %d: Not usable, skipping initialization\n", - mlxsw_sp_port->local_port); - goto port_not_usable; + goto err_devlink_port_register; } err = mlxsw_sp_port_system_port_mapping_set(mlxsw_sp_port); @@ -1431,6 +1484,13 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port) goto err_port_swid_set; } + err = mlxsw_sp_port_speed_by_width_set(mlxsw_sp_port, width); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to enable speeds\n", + mlxsw_sp_port->local_port); + goto err_port_speed_by_width_set; + } + err = mlxsw_sp_port_mtu_set(mlxsw_sp_port, ETH_DATA_LEN); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set MTU\n", @@ -1457,6 +1517,8 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port) goto err_register_netdev; } + devlink_port_type_eth_set(devlink_port, dev); + err = mlxsw_sp_port_vlan_init(mlxsw_sp_port); if (err) goto err_port_vlan_init; @@ -1470,10 +1532,11 @@ err_register_netdev: err_port_buffers_init: err_port_admin_status_set: err_port_mtu_set: +err_port_speed_by_width_set: err_port_swid_set: err_port_system_port_mapping_set: -port_not_usable: -err_port_module_check: + devlink_port_unregister(&mlxsw_sp_port->devlink_port); +err_devlink_port_register: err_dev_addr_init: free_percpu(mlxsw_sp_port->pcpu_stats); err_alloc_stats: @@ -1485,6 +1548,28 @@ err_port_active_vlans_alloc: return err; } +static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, + bool split, u8 module, u8 width, u8 lane) +{ + int err; + + err = mlxsw_sp_port_module_map(mlxsw_sp, local_port, module, width, + lane); + if (err) + return err; + + err = __mlxsw_sp_port_create(mlxsw_sp, local_port, split, module, + width); + if (err) + goto err_port_create; + + return 0; + +err_port_create: + mlxsw_sp_port_module_unmap(mlxsw_sp, local_port); + return err; +} + static void mlxsw_sp_port_vports_fini(struct mlxsw_sp_port *mlxsw_sp_port) { struct net_device *dev = mlxsw_sp_port->dev; @@ -1505,12 +1590,19 @@ static void mlxsw_sp_port_vports_fini(struct mlxsw_sp_port *mlxsw_sp_port) static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port) { struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp->ports[local_port]; + struct devlink_port *devlink_port; if (!mlxsw_sp_port) return; + mlxsw_sp->ports[local_port] = NULL; + devlink_port = &mlxsw_sp_port->devlink_port; + devlink_port_type_clear(devlink_port); unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */ + devlink_port_unregister(devlink_port); mlxsw_sp_port_vports_fini(mlxsw_sp_port); mlxsw_sp_port_switchdev_fini(mlxsw_sp_port); + mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT); + mlxsw_sp_port_module_unmap(mlxsw_sp, mlxsw_sp_port->local_port); free_percpu(mlxsw_sp_port->pcpu_stats); kfree(mlxsw_sp_port->untagged_vlans); kfree(mlxsw_sp_port->active_vlans); @@ -1529,6 +1621,7 @@ static void mlxsw_sp_ports_remove(struct mlxsw_sp *mlxsw_sp) static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp) { size_t alloc_size; + u8 module, width; int i; int err; @@ -1538,19 +1631,158 @@ static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp) return -ENOMEM; for (i = 1; i < MLXSW_PORT_MAX_PORTS; i++) { - err = mlxsw_sp_port_create(mlxsw_sp, i); + err = mlxsw_sp_port_module_info_get(mlxsw_sp, i, &module, + &width); + if (err) + goto err_port_module_info_get; + if (!width) + continue; + mlxsw_sp->port_to_module[i] = module; + err = __mlxsw_sp_port_create(mlxsw_sp, i, false, module, width); if (err) goto err_port_create; } return 0; err_port_create: +err_port_module_info_get: for (i--; i >= 1; i--) mlxsw_sp_port_remove(mlxsw_sp, i); kfree(mlxsw_sp->ports); return err; } +static u8 mlxsw_sp_cluster_base_port_get(u8 local_port) +{ + u8 offset = (local_port - 1) % MLXSW_SP_PORTS_PER_CLUSTER_MAX; + + return local_port - offset; +} + +static int mlxsw_sp_port_split(void *priv, u8 local_port, unsigned int count) +{ + struct mlxsw_sp *mlxsw_sp = priv; + struct mlxsw_sp_port *mlxsw_sp_port; + u8 width = MLXSW_PORT_MODULE_MAX_WIDTH / count; + u8 module, cur_width, base_port; + int i; + int err; + + mlxsw_sp_port = mlxsw_sp->ports[local_port]; + if (!mlxsw_sp_port) { + dev_err(mlxsw_sp->bus_info->dev, "Port number \"%d\" does not exist\n", + local_port); + return -EINVAL; + } + + if (count != 2 && count != 4) { + netdev_err(mlxsw_sp_port->dev, "Port can only be split into 2 or 4 ports\n"); + return -EINVAL; + } + + err = mlxsw_sp_port_module_info_get(mlxsw_sp, local_port, &module, + &cur_width); + if (err) { + netdev_err(mlxsw_sp_port->dev, "Failed to get port's width\n"); + return err; + } + + if (cur_width != MLXSW_PORT_MODULE_MAX_WIDTH) { + netdev_err(mlxsw_sp_port->dev, "Port cannot be split further\n"); + return -EINVAL; + } + + /* Make sure we have enough slave (even) ports for the split. */ + if (count == 2) { + base_port = local_port; + if (mlxsw_sp->ports[base_port + 1]) { + netdev_err(mlxsw_sp_port->dev, "Invalid split configuration\n"); + return -EINVAL; + } + } else { + base_port = mlxsw_sp_cluster_base_port_get(local_port); + if (mlxsw_sp->ports[base_port + 1] || + mlxsw_sp->ports[base_port + 3]) { + netdev_err(mlxsw_sp_port->dev, "Invalid split configuration\n"); + return -EINVAL; + } + } + + for (i = 0; i < count; i++) + mlxsw_sp_port_remove(mlxsw_sp, base_port + i); + + for (i = 0; i < count; i++) { + err = mlxsw_sp_port_create(mlxsw_sp, base_port + i, true, + module, width, i * width); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to create split port\n"); + goto err_port_create; + } + } + + return 0; + +err_port_create: + for (i--; i >= 0; i--) + mlxsw_sp_port_remove(mlxsw_sp, base_port + i); + for (i = 0; i < count / 2; i++) { + module = mlxsw_sp->port_to_module[base_port + i * 2]; + mlxsw_sp_port_create(mlxsw_sp, base_port + i * 2, false, + module, MLXSW_PORT_MODULE_MAX_WIDTH, 0); + } + return err; +} + +static int mlxsw_sp_port_unsplit(void *priv, u8 local_port) +{ + struct mlxsw_sp *mlxsw_sp = priv; + struct mlxsw_sp_port *mlxsw_sp_port; + u8 module, cur_width, base_port; + unsigned int count; + int i; + int err; + + mlxsw_sp_port = mlxsw_sp->ports[local_port]; + if (!mlxsw_sp_port) { + dev_err(mlxsw_sp->bus_info->dev, "Port number \"%d\" does not exist\n", + local_port); + return -EINVAL; + } + + if (!mlxsw_sp_port->split) { + netdev_err(mlxsw_sp_port->dev, "Port wasn't split\n"); + return -EINVAL; + } + + err = mlxsw_sp_port_module_info_get(mlxsw_sp, local_port, &module, + &cur_width); + if (err) { + netdev_err(mlxsw_sp_port->dev, "Failed to get port's width\n"); + return err; + } + count = cur_width == 1 ? 4 : 2; + + base_port = mlxsw_sp_cluster_base_port_get(local_port); + + /* Determine which ports to remove. */ + if (count == 2 && local_port >= base_port + 2) + base_port = base_port + 2; + + for (i = 0; i < count; i++) + mlxsw_sp_port_remove(mlxsw_sp, base_port + i); + + for (i = 0; i < count / 2; i++) { + module = mlxsw_sp->port_to_module[base_port + i * 2]; + err = mlxsw_sp_port_create(mlxsw_sp, base_port + i * 2, false, + module, MLXSW_PORT_MODULE_MAX_WIDTH, + 0); + if (err) + dev_err(mlxsw_sp->bus_info->dev, "Failed to reinstantiate port\n"); + } + + return 0; +} + static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg, char *pude_pl, void *priv) { @@ -1974,6 +2206,8 @@ static struct mlxsw_driver mlxsw_sp_driver = { .priv_size = sizeof(struct mlxsw_sp), .init = mlxsw_sp_init, .fini = mlxsw_sp_fini, + .port_split = mlxsw_sp_port_split, + .port_unsplit = mlxsw_sp_port_unsplit, .txhdr_construct = mlxsw_sp_txhdr_construct, .txhdr_len = MLXSW_TXHDR_LEN, .profile = &mlxsw_sp_config_profile, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 3b89ed2f3c76..4b8abaf06321 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -43,6 +43,7 @@ #include <linux/if_vlan.h> #include <linux/list.h> #include <net/switchdev.h> +#include <net/devlink.h> #include "port.h" #include "core.h" @@ -57,6 +58,10 @@ #define MLXSW_SP_MID_MAX 7000 +#define MLXSW_SP_PORTS_PER_CLUSTER_MAX 4 + +#define MLXSW_SP_PORT_BASE_SPEED 25000 /* Mb/s */ + struct mlxsw_sp_port; struct mlxsw_sp_upper { @@ -118,10 +123,13 @@ struct mlxsw_sp { #define MLXSW_SP_DEFAULT_LEARNING_INTERVAL 100 unsigned int interval; /* ms */ } fdb_notify; +#define MLXSW_SP_MIN_AGEING_TIME 10 +#define MLXSW_SP_MAX_AGEING_TIME 1000000 #define MLXSW_SP_DEFAULT_AGEING_TIME 300 u32 ageing_time; struct mlxsw_sp_upper master_bridge; struct mlxsw_sp_upper lags[MLXSW_SP_LAG_MAX]; + u8 port_to_module[MLXSW_PORT_MAX_PORTS]; }; static inline struct mlxsw_sp_upper * @@ -149,7 +157,8 @@ struct mlxsw_sp_port { learning_sync:1, uc_flood:1, bridged:1, - lagged:1; + lagged:1, + split:1; u16 pvid; u16 lag_id; struct { @@ -162,6 +171,7 @@ struct mlxsw_sp_port { unsigned long *untagged_vlans; /* VLAN interfaces */ struct list_head vports_list; + struct devlink_port devlink_port; }; static inline struct mlxsw_sp_port * diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 7b56098acc58..e1c74efff51a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -311,8 +311,13 @@ static int mlxsw_sp_port_attr_br_ageing_set(struct mlxsw_sp_port *mlxsw_sp_port, unsigned long ageing_jiffies = clock_t_to_jiffies(ageing_clock_t); u32 ageing_time = jiffies_to_msecs(ageing_jiffies) / 1000; - if (switchdev_trans_ph_prepare(trans)) - return 0; + if (switchdev_trans_ph_prepare(trans)) { + if (ageing_time < MLXSW_SP_MIN_AGEING_TIME || + ageing_time > MLXSW_SP_MAX_AGEING_TIME) + return -ERANGE; + else + return 0; + } return mlxsw_sp_ageing_set(mlxsw_sp, ageing_time); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index d85960cfb694..7a60a26759b6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -43,6 +43,7 @@ #include <linux/device.h> #include <linux/skbuff.h> #include <linux/if_vlan.h> +#include <net/devlink.h> #include <net/switchdev.h> #include <generated/utsrelease.h> @@ -78,6 +79,7 @@ struct mlxsw_sx_port { struct mlxsw_sx_port_pcpu_stats __percpu *pcpu_stats; struct mlxsw_sx *mlxsw_sx; u8 local_port; + struct devlink_port devlink_port; }; /* tx_hdr_version @@ -953,7 +955,9 @@ mlxsw_sx_port_mac_learning_mode_set(struct mlxsw_sx_port *mlxsw_sx_port, static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port) { + struct devlink *devlink = priv_to_devlink(mlxsw_sx->core); struct mlxsw_sx_port *mlxsw_sx_port; + struct devlink_port *devlink_port; struct net_device *dev; bool usable; int err; @@ -1007,6 +1011,14 @@ static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port) goto port_not_usable; } + devlink_port = &mlxsw_sx_port->devlink_port; + err = devlink_port_register(devlink, devlink_port, local_port); + if (err) { + dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to register devlink port\n", + mlxsw_sx_port->local_port); + goto err_devlink_port_register; + } + err = mlxsw_sx_port_system_port_mapping_set(mlxsw_sx_port); if (err) { dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set system port mapping\n", @@ -1064,6 +1076,8 @@ static int mlxsw_sx_port_create(struct mlxsw_sx *mlxsw_sx, u8 local_port) goto err_register_netdev; } + devlink_port_type_eth_set(devlink_port, dev); + mlxsw_sx->ports[local_port] = mlxsw_sx_port; return 0; @@ -1075,6 +1089,8 @@ err_port_mtu_set: err_port_speed_set: err_port_swid_set: err_port_system_port_mapping_set: + devlink_port_unregister(&mlxsw_sx_port->devlink_port); +err_devlink_port_register: port_not_usable: err_port_module_check: err_dev_addr_get: @@ -1087,11 +1103,15 @@ err_alloc_stats: static void mlxsw_sx_port_remove(struct mlxsw_sx *mlxsw_sx, u8 local_port) { struct mlxsw_sx_port *mlxsw_sx_port = mlxsw_sx->ports[local_port]; + struct devlink_port *devlink_port; if (!mlxsw_sx_port) return; + devlink_port = &mlxsw_sx_port->devlink_port; + devlink_port_type_clear(devlink_port); unregister_netdev(mlxsw_sx_port->dev); /* This calls ndo_stop */ mlxsw_sx_port_swid_set(mlxsw_sx_port, MLXSW_PORT_SWID_DISABLED_PORT); + devlink_port_unregister(devlink_port); free_percpu(mlxsw_sx_port->pcpu_stats); free_netdev(mlxsw_sx_port->dev); } |