diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-05-02 16:40:27 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-05-02 16:40:27 -0700 |
| commit | 8d65b08debc7e62b2c6032d7fe7389d895b92cbc (patch) | |
| tree | 0c3141b60c3a03cc32742b5750c5e763b9dae489 /drivers/net/ethernet/intel | |
| parent | Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert... (diff) | |
| parent | Merge branch 'tipc-refactor-socket-receive-functions' (diff) | |
| download | linux-8d65b08debc7e62b2c6032d7fe7389d895b92cbc.tar.gz linux-8d65b08debc7e62b2c6032d7fe7389d895b92cbc.zip | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Millar:
"Here are some highlights from the 2065 networking commits that
happened this development cycle:
1) XDP support for IXGBE (John Fastabend) and thunderx (Sunil Kowuri)
2) Add a generic XDP driver, so that anyone can test XDP even if they
lack a networking device whose driver has explicit XDP support
(me).
3) Sparc64 now has an eBPF JIT too (me)
4) Add a BPF program testing framework via BPF_PROG_TEST_RUN (Alexei
Starovoitov)
5) Make netfitler network namespace teardown less expensive (Florian
Westphal)
6) Add symmetric hashing support to nft_hash (Laura Garcia Liebana)
7) Implement NAPI and GRO in netvsc driver (Stephen Hemminger)
8) Support TC flower offload statistics in mlxsw (Arkadi Sharshevsky)
9) Multiqueue support in stmmac driver (Joao Pinto)
10) Remove TCP timewait recycling, it never really could possibly work
well in the real world and timestamp randomization really zaps any
hint of usability this feature had (Soheil Hassas Yeganeh)
11) Support level3 vs level4 ECMP route hashing in ipv4 (Nikolay
Aleksandrov)
12) Add socket busy poll support to epoll (Sridhar Samudrala)
13) Netlink extended ACK support (Johannes Berg, Pablo Neira Ayuso,
and several others)
14) IPSEC hw offload infrastructure (Steffen Klassert)"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2065 commits)
tipc: refactor function tipc_sk_recv_stream()
tipc: refactor function tipc_sk_recvmsg()
net: thunderx: Optimize page recycling for XDP
net: thunderx: Support for XDP header adjustment
net: thunderx: Add support for XDP_TX
net: thunderx: Add support for XDP_DROP
net: thunderx: Add basic XDP support
net: thunderx: Cleanup receive buffer allocation
net: thunderx: Optimize CQE_TX handling
net: thunderx: Optimize RBDR descriptor handling
net: thunderx: Support for page recycling
ipx: call ipxitf_put() in ioctl error path
net: sched: add helpers to handle extended actions
qed*: Fix issues in the ptp filter config implementation.
qede: Fix concurrency issue in PTP Tx path processing.
stmmac: Add support for SIMATIC IOT2000 platform
net: hns: fix ethtool_get_strings overflow in hns driver
tcp: fix wraparound issue in tcp_lp
bpf, arm64: fix jit branch offset related to ldimm64
bpf, arm64: implement jiting of BPF_XADD
...
Diffstat (limited to 'drivers/net/ethernet/intel')
81 files changed, 8575 insertions, 3601 deletions
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index 1349b45f014d..1542a2158e96 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -235,17 +235,6 @@ config I40E_DCB If unsure, say N. -config I40E_FCOE - bool "Fibre Channel over Ethernet (FCoE)" - default n - depends on I40E && DCB && FCOE - ---help--- - Say Y here if you want to use Fibre Channel over Ethernet (FCoE) - in the driver. This will create new netdev for exclusive FCoE - use with XL710 FCoE offloads enabled. - - If unsure, say N. - config I40EVF tristate "Intel(R) XL710 X710 Virtual Function Ethernet support" depends on PCI_MSI diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c index 975eeb885ca2..ec8aa4562cc9 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c +++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c @@ -103,104 +103,104 @@ static const char e1000_gstrings_test[][ETH_GSTRING_LEN] = { #define E1000_TEST_LEN ARRAY_SIZE(e1000_gstrings_test) -static int e1000_get_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int e1000_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; + u32 supported, advertising; if (hw->media_type == e1000_media_type_copper) { - ecmd->supported = (SUPPORTED_10baseT_Half | - SUPPORTED_10baseT_Full | - SUPPORTED_100baseT_Half | - SUPPORTED_100baseT_Full | - SUPPORTED_1000baseT_Full| - SUPPORTED_Autoneg | - SUPPORTED_TP); - ecmd->advertising = ADVERTISED_TP; + supported = (SUPPORTED_10baseT_Half | + SUPPORTED_10baseT_Full | + SUPPORTED_100baseT_Half | + SUPPORTED_100baseT_Full | + SUPPORTED_1000baseT_Full| + SUPPORTED_Autoneg | + SUPPORTED_TP); + advertising = ADVERTISED_TP; if (hw->autoneg == 1) { - ecmd->advertising |= ADVERTISED_Autoneg; + advertising |= ADVERTISED_Autoneg; /* the e1000 autoneg seems to match ethtool nicely */ - ecmd->advertising |= hw->autoneg_advertised; + advertising |= hw->autoneg_advertised; } - ecmd->port = PORT_TP; - ecmd->phy_address = hw->phy_addr; - - if (hw->mac_type == e1000_82543) - ecmd->transceiver = XCVR_EXTERNAL; - else - ecmd->transceiver = XCVR_INTERNAL; - + cmd->base.port = PORT_TP; + cmd->base.phy_address = hw->phy_addr; } else { - ecmd->supported = (SUPPORTED_1000baseT_Full | - SUPPORTED_FIBRE | - SUPPORTED_Autoneg); + supported = (SUPPORTED_1000baseT_Full | + SUPPORTED_FIBRE | + SUPPORTED_Autoneg); - ecmd->advertising = (ADVERTISED_1000baseT_Full | - ADVERTISED_FIBRE | - ADVERTISED_Autoneg); + advertising = (ADVERTISED_1000baseT_Full | + ADVERTISED_FIBRE | + ADVERTISED_Autoneg); - ecmd->port = PORT_FIBRE; - - if (hw->mac_type >= e1000_82545) - ecmd->transceiver = XCVR_INTERNAL; - else - ecmd->transceiver = XCVR_EXTERNAL; + cmd->base.port = PORT_FIBRE; } if (er32(STATUS) & E1000_STATUS_LU) { e1000_get_speed_and_duplex(hw, &adapter->link_speed, &adapter->link_duplex); - ethtool_cmd_speed_set(ecmd, adapter->link_speed); + cmd->base.speed = adapter->link_speed; /* unfortunately FULL_DUPLEX != DUPLEX_FULL * and HALF_DUPLEX != DUPLEX_HALF */ if (adapter->link_duplex == FULL_DUPLEX) - ecmd->duplex = DUPLEX_FULL; + cmd->base.duplex = DUPLEX_FULL; else - ecmd->duplex = DUPLEX_HALF; + cmd->base.duplex = DUPLEX_HALF; } else { - ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN); - ecmd->duplex = DUPLEX_UNKNOWN; + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; } - ecmd->autoneg = ((hw->media_type == e1000_media_type_fiber) || + cmd->base.autoneg = ((hw->media_type == e1000_media_type_fiber) || hw->autoneg) ? AUTONEG_ENABLE : AUTONEG_DISABLE; /* MDI-X => 1; MDI => 0 */ if ((hw->media_type == e1000_media_type_copper) && netif_carrier_ok(netdev)) - ecmd->eth_tp_mdix = (!!adapter->phy_info.mdix_mode ? + cmd->base.eth_tp_mdix = (!!adapter->phy_info.mdix_mode ? ETH_TP_MDI_X : ETH_TP_MDI); else - ecmd->eth_tp_mdix = ETH_TP_MDI_INVALID; + cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID; if (hw->mdix == AUTO_ALL_MODES) - ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO; + cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO; else - ecmd->eth_tp_mdix_ctrl = hw->mdix; + cmd->base.eth_tp_mdix_ctrl = hw->mdix; + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); + return 0; } -static int e1000_set_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int e1000_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *cmd) { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; + u32 advertising; + + ethtool_convert_link_mode_to_legacy_u32(&advertising, + cmd->link_modes.advertising); /* MDI setting is only allowed when autoneg enabled because * some hardware doesn't allow MDI setting when speed or * duplex is forced. */ - if (ecmd->eth_tp_mdix_ctrl) { + if (cmd->base.eth_tp_mdix_ctrl) { if (hw->media_type != e1000_media_type_copper) return -EOPNOTSUPP; - if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) && - (ecmd->autoneg != AUTONEG_ENABLE)) { + if ((cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) && + (cmd->base.autoneg != AUTONEG_ENABLE)) { e_err(drv, "forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n"); return -EINVAL; } @@ -209,32 +209,31 @@ static int e1000_set_settings(struct net_device *netdev, while (test_and_set_bit(__E1000_RESETTING, &adapter->flags)) msleep(1); - if (ecmd->autoneg == AUTONEG_ENABLE) { + if (cmd->base.autoneg == AUTONEG_ENABLE) { hw->autoneg = 1; if (hw->media_type == e1000_media_type_fiber) hw->autoneg_advertised = ADVERTISED_1000baseT_Full | - ADVERTISED_FIBRE | - ADVERTISED_Autoneg; + ADVERTISED_FIBRE | + ADVERTISED_Autoneg; else - hw->autoneg_advertised = ecmd->advertising | + hw->autoneg_advertised = advertising | ADVERTISED_TP | ADVERTISED_Autoneg; - ecmd->advertising = hw->autoneg_advertised; } else { - u32 speed = ethtool_cmd_speed(ecmd); + u32 speed = cmd->base.speed; /* calling this overrides forced MDI setting */ - if (e1000_set_spd_dplx(adapter, speed, ecmd->duplex)) { + if (e1000_set_spd_dplx(adapter, speed, cmd->base.duplex)) { clear_bit(__E1000_RESETTING, &adapter->flags); return -EINVAL; } } /* MDI-X => 2; MDI => 1; Auto => 3 */ - if (ecmd->eth_tp_mdix_ctrl) { - if (ecmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO) + if (cmd->base.eth_tp_mdix_ctrl) { + if (cmd->base.eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO) hw->mdix = AUTO_ALL_MODES; else - hw->mdix = ecmd->eth_tp_mdix_ctrl; + hw->mdix = cmd->base.eth_tp_mdix_ctrl; } /* reset the link */ @@ -1875,8 +1874,6 @@ static void e1000_get_strings(struct net_device *netdev, u32 stringset, } static const struct ethtool_ops e1000_ethtool_ops = { - .get_settings = e1000_get_settings, - .set_settings = e1000_set_settings, .get_drvinfo = e1000_get_drvinfo, .get_regs_len = e1000_get_regs_len, .get_regs = e1000_get_regs, @@ -1901,6 +1898,8 @@ static const struct ethtool_ops e1000_ethtool_ops = { .get_coalesce = e1000_get_coalesce, .set_coalesce = e1000_set_coalesce, .get_ts_info = ethtool_op_get_ts_info, + .get_link_ksettings = e1000_get_link_ksettings, + .set_link_ksettings = e1000_set_link_ksettings, }; void e1000_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 93fc6c67306b..bd8b05fe8258 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -131,7 +131,6 @@ static void e1000_watchdog(struct work_struct *work); static void e1000_82547_tx_fifo_stall_task(struct work_struct *work); static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, struct net_device *netdev); -static struct net_device_stats *e1000_get_stats(struct net_device *netdev); static int e1000_change_mtu(struct net_device *netdev, int new_mtu); static int e1000_set_mac(struct net_device *netdev, void *p); static irqreturn_t e1000_intr(int irq, void *data); @@ -846,7 +845,6 @@ static const struct net_device_ops e1000_netdev_ops = { .ndo_open = e1000_open, .ndo_stop = e1000_close, .ndo_start_xmit = e1000_xmit_frame, - .ndo_get_stats = e1000_get_stats, .ndo_set_rx_mode = e1000_set_rx_mode, .ndo_set_mac_address = e1000_set_mac, .ndo_tx_timeout = e1000_tx_timeout, @@ -3530,19 +3528,6 @@ static void e1000_reset_task(struct work_struct *work) } /** - * e1000_get_stats - Get System Network Statistics - * @netdev: network interface device structure - * - * Returns the address of the device statistics structure. - * The statistics are actually updated from the watchdog. - **/ -static struct net_device_stats *e1000_get_stats(struct net_device *netdev) -{ - /* only return the current stats */ - return &netdev->stats; -} - -/** * e1000_change_mtu - Change the Maximum Transfer Unit * @netdev: network interface device structure * @new_mtu: new value for maximum frame size diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index a29b12e80855..c7c994eb410e 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -135,7 +135,8 @@ enum e1000_boards { board_pchlan, board_pch2lan, board_pch_lpt, - board_pch_spt + board_pch_spt, + board_pch_cnp }; struct e1000_ps_page { @@ -378,18 +379,22 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca); * INCVALUE_n into the TIMINCA register allowing 32+8+(24-INCVALUE_SHIFT_n) * bits to count nanoseconds leaving the rest for fractional nonseconds. */ -#define INCVALUE_96MHz 125 -#define INCVALUE_SHIFT_96MHz 17 -#define INCPERIOD_SHIFT_96MHz 2 -#define INCPERIOD_96MHz (12 >> INCPERIOD_SHIFT_96MHz) +#define INCVALUE_96MHZ 125 +#define INCVALUE_SHIFT_96MHZ 17 +#define INCPERIOD_SHIFT_96MHZ 2 +#define INCPERIOD_96MHZ (12 >> INCPERIOD_SHIFT_96MHZ) -#define INCVALUE_25MHz 40 -#define INCVALUE_SHIFT_25MHz 18 -#define INCPERIOD_25MHz 1 +#define INCVALUE_25MHZ 40 +#define INCVALUE_SHIFT_25MHZ 18 +#define INCPERIOD_25MHZ 1 -#define INCVALUE_24MHz 125 -#define INCVALUE_SHIFT_24MHz 14 -#define INCPERIOD_24MHz 3 +#define INCVALUE_24MHZ 125 +#define INCVALUE_SHIFT_24MHZ 14 +#define INCPERIOD_24MHZ 3 + +#define INCVALUE_38400KHZ 26 +#define INCVALUE_SHIFT_38400KHZ 19 +#define INCPERIOD_38400KHZ 1 /* Another drawback of scaling the incvalue by a large factor is the * 64-bit SYSTIM register overflows more quickly. This is dealt with @@ -515,6 +520,7 @@ extern const struct e1000_info e1000_pch_info; extern const struct e1000_info e1000_pch2_info; extern const struct e1000_info e1000_pch_lpt_info; extern const struct e1000_info e1000_pch_spt_info; +extern const struct e1000_info e1000_pch_cnp_info; extern const struct e1000_info e1000_es2_info; void e1000e_ptp_init(struct e1000_adapter *adapter); diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 7aff68a4a4df..e23dbd9190d6 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -117,55 +117,52 @@ static const char e1000_gstrings_test[][ETH_GSTRING_LEN] = { #define E1000_TEST_LEN ARRAY_SIZE(e1000_gstrings_test) -static int e1000_get_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int e1000_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; - u32 speed; + u32 speed, supported, advertising; if (hw->phy.media_type == e1000_media_type_copper) { - ecmd->supported = (SUPPORTED_10baseT_Half | - SUPPORTED_10baseT_Full | - SUPPORTED_100baseT_Half | - SUPPORTED_100baseT_Full | - SUPPORTED_1000baseT_Full | - SUPPORTED_Autoneg | - SUPPORTED_TP); + supported = (SUPPORTED_10baseT_Half | + SUPPORTED_10baseT_Full | + SUPPORTED_100baseT_Half | + SUPPORTED_100baseT_Full | + SUPPORTED_1000baseT_Full | + SUPPORTED_Autoneg | + SUPPORTED_TP); if (hw->phy.type == e1000_phy_ife) - ecmd->supported &= ~SUPPORTED_1000baseT_Full; - ecmd->advertising = ADVERTISED_TP; + supported &= ~SUPPORTED_1000baseT_Full; + advertising = ADVERTISED_TP; if (hw->mac.autoneg == 1) { - ecmd->advertising |= ADVERTISED_Autoneg; + advertising |= ADVERTISED_Autoneg; /* the e1000 autoneg seems to match ethtool nicely */ - ecmd->advertising |= hw->phy.autoneg_advertised; + advertising |= hw->phy.autoneg_advertised; } - ecmd->port = PORT_TP; - ecmd->phy_address = hw->phy.addr; - ecmd->transceiver = XCVR_INTERNAL; - + cmd->base.port = PORT_TP; + cmd->base.phy_address = hw->phy.addr; } else { - ecmd->supported = (SUPPORTED_1000baseT_Full | - SUPPORTED_FIBRE | - SUPPORTED_Autoneg); + supported = (SUPPORTED_1000baseT_Full | + SUPPORTED_FIBRE | + SUPPORTED_Autoneg); - ecmd->advertising = (ADVERTISED_1000baseT_Full | - ADVERTISED_FIBRE | - ADVERTISED_Autoneg); + advertising = (ADVERTISED_1000baseT_Full | + ADVERTISED_FIBRE | + ADVERTISED_Autoneg); - ecmd->port = PORT_FIBRE; - ecmd->transceiver = XCVR_EXTERNAL; + cmd->base.port = PORT_FIBRE; } speed = SPEED_UNKNOWN; - ecmd->duplex = DUPLEX_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; if (netif_running(netdev)) { if (netif_carrier_ok(netdev)) { speed = adapter->link_speed; - ecmd->duplex = adapter->link_duplex - 1; + cmd->base.duplex = adapter->link_duplex - 1; } } else if (!pm_runtime_suspended(netdev->dev.parent)) { u32 status = er32(STATUS); @@ -179,30 +176,36 @@ static int e1000_get_settings(struct net_device *netdev, speed = SPEED_10; if (status & E1000_STATUS_FD) - ecmd->duplex = DUPLEX_FULL; + cmd->base.duplex = DUPLEX_FULL; else - ecmd->duplex = DUPLEX_HALF; + cmd->base.duplex = DUPLEX_HALF; } } - ethtool_cmd_speed_set(ecmd, speed); - ecmd->autoneg = ((hw->phy.media_type == e1000_media_type_fiber) || + cmd->base.speed = speed; + cmd->base.autoneg = ((hw->phy.media_type == e1000_media_type_fiber) || hw->mac.autoneg) ? AUTONEG_ENABLE : AUTONEG_DISABLE; /* MDI-X => 2; MDI =>1; Invalid =>0 */ if ((hw->phy.media_type == e1000_media_type_copper) && netif_carrier_ok(netdev)) - ecmd->eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X : ETH_TP_MDI; + cmd->base.eth_tp_mdix = hw->phy.is_mdix ? + ETH_TP_MDI_X : ETH_TP_MDI; else - ecmd->eth_tp_mdix = ETH_TP_MDI_INVALID; + cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID; if (hw->phy.mdix == AUTO_ALL_MODES) - ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO; + cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO; else - ecmd->eth_tp_mdix_ctrl = hw->phy.mdix; + cmd->base.eth_tp_mdix_ctrl = hw->phy.mdix; if (hw->phy.media_type != e1000_media_type_copper) - ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_INVALID; + cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_INVALID; + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); return 0; } @@ -262,12 +265,16 @@ err_inval: return -EINVAL; } -static int e1000_set_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int e1000_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *cmd) { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; int ret_val = 0; + u32 advertising; + + ethtool_convert_link_mode_to_legacy_u32(&advertising, + cmd->link_modes.advertising); pm_runtime_get_sync(netdev->dev.parent); @@ -285,14 +292,14 @@ static int e1000_set_settings(struct net_device *netdev, * some hardware doesn't allow MDI setting when speed or * duplex is forced. */ - if (ecmd->eth_tp_mdix_ctrl) { + if (cmd->base.eth_tp_mdix_ctrl) { if (hw->phy.media_type != e1000_media_type_copper) { ret_val = -EOPNOTSUPP; goto out; } - if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) && - (ecmd->autoneg != AUTONEG_ENABLE)) { + if ((cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) && + (cmd->base.autoneg != AUTONEG_ENABLE)) { e_err("forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n"); ret_val = -EINVAL; goto out; @@ -302,35 +309,35 @@ static int e1000_set_settings(struct net_device *netdev, while (test_and_set_bit(__E1000_RESETTING, &adapter->state)) usleep_range(1000, 2000); - if (ecmd->autoneg == AUTONEG_ENABLE) { + if (cmd->base.autoneg == AUTONEG_ENABLE) { hw->mac.autoneg = 1; if (hw->phy.media_type == e1000_media_type_fiber) hw->phy.autoneg_advertised = ADVERTISED_1000baseT_Full | ADVERTISED_FIBRE | ADVERTISED_Autoneg; else - hw->phy.autoneg_advertised = ecmd->advertising | + hw->phy.autoneg_advertised = advertising | ADVERTISED_TP | ADVERTISED_Autoneg; - ecmd->advertising = hw->phy.autoneg_advertised; + advertising = hw->phy.autoneg_advertised; if (adapter->fc_autoneg) hw->fc.requested_mode = e1000_fc_default; } else { - u32 speed = ethtool_cmd_speed(ecmd); + u32 speed = cmd->base.speed; /* calling this overrides forced MDI setting */ - if (e1000_set_spd_dplx(adapter, speed, ecmd->duplex)) { + if (e1000_set_spd_dplx(adapter, speed, cmd->base.duplex)) { ret_val = -EINVAL; goto out; } } /* MDI-X => 2; MDI => 1; Auto => 3 */ - if (ecmd->eth_tp_mdix_ctrl) { + if (cmd->base.eth_tp_mdix_ctrl) { /* fix up the value for auto (3 => 0) as zero is mapped * internally to auto */ - if (ecmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO) + if (cmd->base.eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO) hw->phy.mdix = AUTO_ALL_MODES; else - hw->phy.mdix = ecmd->eth_tp_mdix_ctrl; + hw->phy.mdix = cmd->base.eth_tp_mdix_ctrl; } /* reset the link */ @@ -904,19 +911,20 @@ static int e1000_reg_test(struct e1000_adapter *adapter, u64 *data) case e1000_pch2lan: case e1000_pch_lpt: case e1000_pch_spt: + /* fall through */ + case e1000_pch_cnp: mask |= BIT(18); break; default: break; } - if ((mac->type == e1000_pch_lpt) || (mac->type == e1000_pch_spt)) + if (mac->type >= e1000_pch_lpt) wlock_mac = (er32(FWSM) & E1000_FWSM_WLOCK_MAC_MASK) >> E1000_FWSM_WLOCK_MAC_SHIFT; for (i = 0; i < mac->rar_entry_count; i++) { - if ((mac->type == e1000_pch_lpt) || - (mac->type == e1000_pch_spt)) { + if (mac->type >= e1000_pch_lpt) { /* Cannot test write-protected SHRAL[n] registers */ if ((wlock_mac == 1) || (wlock_mac && (i > wlock_mac))) continue; @@ -1525,7 +1533,7 @@ static int e1000_setup_loopback_test(struct e1000_adapter *adapter) struct e1000_hw *hw = &adapter->hw; u32 rctl, fext_nvm11, tarc0; - if (hw->mac.type == e1000_pch_spt) { + if (hw->mac.type >= e1000_pch_spt) { fext_nvm11 = er32(FEXTNVM11); fext_nvm11 |= E1000_FEXTNVM11_DISABLE_MULR_FIX; ew32(FEXTNVM11, fext_nvm11); @@ -1569,6 +1577,7 @@ static void e1000_loopback_cleanup(struct e1000_adapter *adapter) switch (hw->mac.type) { case e1000_pch_spt: + case e1000_pch_cnp: fext_nvm11 = er32(FEXTNVM11); fext_nvm11 &= ~E1000_FEXTNVM11_DISABLE_MULR_FIX; ew32(FEXTNVM11, fext_nvm11); @@ -2313,8 +2322,6 @@ static int e1000e_get_ts_info(struct net_device *netdev, } static const struct ethtool_ops e1000_ethtool_ops = { - .get_settings = e1000_get_settings, - .set_settings = e1000_set_settings, .get_drvinfo = e1000_get_drvinfo, .get_regs_len = e1000_get_regs_len, .get_regs = e1000_get_regs, @@ -2342,6 +2349,8 @@ static const struct ethtool_ops e1000_ethtool_ops = { .get_ts_info = e1000e_get_ts_info, .get_eee = e1000e_get_eee, .set_eee = e1000e_set_eee, + .get_link_ksettings = e1000_get_link_ksettings, + .set_link_ksettings = e1000_set_link_ksettings, }; void e1000e_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index 4e733bf1a38e..66bd5060a65b 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -96,6 +96,10 @@ struct e1000_hw; #define E1000_DEV_ID_PCH_SPT_I219_V4 0x15D8 #define E1000_DEV_ID_PCH_SPT_I219_LM5 0x15E3 #define E1000_DEV_ID_PCH_SPT_I219_V5 0x15D6 +#define E1000_DEV_ID_PCH_CNP_I219_LM6 0x15BD +#define E1000_DEV_ID_PCH_CNP_I219_V6 0x15BE +#define E1000_DEV_ID_PCH_CNP_I219_LM7 0x15BB +#define E1000_DEV_ID_PCH_CNP_I219_V7 0x15BC #define E1000_REVISION_4 4 @@ -118,6 +122,7 @@ enum e1000_mac_type { e1000_pch2lan, e1000_pch_lpt, e1000_pch_spt, + e1000_pch_cnp, }; enum e1000_media_type { diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index f3aaca743ea3..68ea8b4555ab 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -237,7 +237,7 @@ static bool e1000_phy_is_accessible_pchlan(struct e1000_hw *hw) if (ret_val) return false; out: - if ((hw->mac.type == e1000_pch_lpt) || (hw->mac.type == e1000_pch_spt)) { + if (hw->mac.type >= e1000_pch_lpt) { /* Only unforce SMBus if ME is not active */ if (!(er32(FWSM) & E1000_ICH_FWSM_FW_VALID)) { /* Unforce SMBus mode in PHY */ @@ -333,6 +333,7 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) switch (hw->mac.type) { case e1000_pch_lpt: case e1000_pch_spt: + case e1000_pch_cnp: if (e1000_phy_is_accessible_pchlan(hw)) break; @@ -474,6 +475,7 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw) case e1000_pch2lan: case e1000_pch_lpt: case e1000_pch_spt: + case e1000_pch_cnp: /* In case the PHY needs to be in mdio slow mode, * set slow mode and try to get the PHY id again. */ @@ -607,7 +609,7 @@ static s32 e1000_init_nvm_params_ich8lan(struct e1000_hw *hw) nvm->type = e1000_nvm_flash_sw; - if (hw->mac.type == e1000_pch_spt) { + if (hw->mac.type >= e1000_pch_spt) { /* in SPT, gfpreg doesn't exist. NVM size is taken from the * STRAP register. This is because in SPT the GbE Flash region * is no longer accessed through the flash registers. Instead, @@ -715,6 +717,7 @@ static s32 e1000_init_mac_params_ich8lan(struct e1000_hw *hw) /* fall-through */ case e1000_pch_lpt: case e1000_pch_spt: + case e1000_pch_cnp: case e1000_pchlan: /* check management mode */ mac->ops.check_mng_mode = e1000_check_mng_mode_pchlan; @@ -732,7 +735,7 @@ static s32 e1000_init_mac_params_ich8lan(struct e1000_hw *hw) break; } - if ((mac->type == e1000_pch_lpt) || (mac->type == e1000_pch_spt)) { + if (mac->type >= e1000_pch_lpt) { mac->rar_entry_count = E1000_PCH_LPT_RAR_ENTRIES; mac->ops.rar_set = e1000_rar_set_pch_lpt; mac->ops.setup_physical_interface = @@ -1399,9 +1402,7 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) * aggressive resulting in many collisions. To avoid this, increase * the IPG and reduce Rx latency in the PHY. */ - if (((hw->mac.type == e1000_pch2lan) || - (hw->mac.type == e1000_pch_lpt) || - (hw->mac.type == e1000_pch_spt)) && link) { + if ((hw->mac.type >= e1000_pch2lan) && link) { u16 speed, duplex; e1000e_get_speed_and_duplex_copper(hw, &speed, &duplex); @@ -1412,7 +1413,7 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) tipg_reg |= 0xFF; /* Reduce Rx latency in analog PHY */ emi_val = 0; - } else if (hw->mac.type == e1000_pch_spt && + } else if (hw->mac.type >= e1000_pch_spt && duplex == FULL_DUPLEX && speed != SPEED_1000) { tipg_reg |= 0xC; emi_val = 1; @@ -1435,8 +1436,7 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) emi_addr = I217_RX_CONFIG; ret_val = e1000_write_emi_reg_locked(hw, emi_addr, emi_val); - if (hw->mac.type == e1000_pch_lpt || - hw->mac.type == e1000_pch_spt) { + if (hw->mac.type >= e1000_pch_lpt) { u16 phy_reg; e1e_rphy_locked(hw, I217_PLL_CLOCK_GATE_REG, &phy_reg); @@ -1452,7 +1452,7 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) if (ret_val) return ret_val; - if (hw->mac.type == e1000_pch_spt) { + if (hw->mac.type >= e1000_pch_spt) { u16 data; u16 ptr_gap; @@ -1502,7 +1502,7 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) * on power up. * Set the Beacon Duration for I217 to 8 usec */ - if ((hw->mac.type == e1000_pch_lpt) || (hw->mac.type == e1000_pch_spt)) { + if (hw->mac.type >= e1000_pch_lpt) { u32 mac_reg; mac_reg = er32(FEXTNVM4); @@ -1520,8 +1520,7 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) if (ret_val) return ret_val; } - if ((hw->mac.type == e1000_pch_lpt) || - (hw->mac.type == e1000_pch_spt)) { + if (hw->mac.type >= e1000_pch_lpt) { /* Set platform power management values for * Latency Tolerance Reporting (LTR) */ @@ -1533,15 +1532,18 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) /* Clear link partner's EEE ability */ hw->dev_spec.ich8lan.eee_lp_ability = 0; - /* FEXTNVM6 K1-off workaround */ - if (hw->mac.type == e1000_pch_spt) { - u32 pcieanacfg = er32(PCIEANACFG); + if (hw->mac.type >= e1000_pch_lpt) { u32 fextnvm6 = er32(FEXTNVM6); - if (pcieanacfg & E1000_FEXTNVM6_K1_OFF_ENABLE) - fextnvm6 |= E1000_FEXTNVM6_K1_OFF_ENABLE; - else - fextnvm6 &= ~E1000_FEXTNVM6_K1_OFF_ENABLE; + if (hw->mac.type == e1000_pch_spt) { + /* FEXTNVM6 K1-off workaround - for SPT only */ + u32 pcieanacfg = er32(PCIEANACFG); + + if (pcieanacfg & E1000_FEXTNVM6_K1_OFF_ENABLE) + fextnvm6 |= E1000_FEXTNVM6_K1_OFF_ENABLE; + else + fextnvm6 &= ~E1000_FEXTNVM6_K1_OFF_ENABLE; + } ew32(FEXTNVM6, fextnvm6); } @@ -1640,6 +1642,7 @@ static s32 e1000_get_variants_ich8lan(struct e1000_adapter *adapter) case e1000_pch2lan: case e1000_pch_lpt: case e1000_pch_spt: + case e1000_pch_cnp: rc = e1000_init_phy_params_pchlan(hw); break; default: @@ -2091,6 +2094,7 @@ static s32 e1000_sw_lcd_config_ich8lan(struct e1000_hw *hw) case e1000_pch2lan: case e1000_pch_lpt: case e1000_pch_spt: + case e1000_pch_cnp: sw_cfg_mask = E1000_FEXTNVM_SW_CONFIG_ICH8M; break; default: @@ -3125,6 +3129,7 @@ static s32 e1000_valid_nvm_bank_detect_ich8lan(struct e1000_hw *hw, u32 *bank) switch (hw->mac.type) { case e1000_pch_spt: + case e1000_pch_cnp: bank1_offset = nvm->flash_bank_size; act_offset = E1000_ICH_NVM_SIG_WORD; @@ -3380,7 +3385,7 @@ static s32 e1000_flash_cycle_init_ich8lan(struct e1000_hw *hw) /* Clear FCERR and DAEL in hw status by writing 1 */ hsfsts.hsf_status.flcerr = 1; hsfsts.hsf_status.dael = 1; - if (hw->mac.type == e1000_pch_spt) + if (hw->mac.type >= e1000_pch_spt) ew32flash(ICH_FLASH_HSFSTS, hsfsts.regval & 0xFFFF); else ew16flash(ICH_FLASH_HSFSTS, hsfsts.regval); @@ -3399,7 +3404,7 @@ static s32 e1000_flash_cycle_init_ich8lan(struct e1000_hw *hw) * Begin by setting Flash Cycle Done. */ hsfsts.hsf_status.flcdone = 1; - if (hw->mac.type == e1000_pch_spt) + if (hw->mac.type >= e1000_pch_spt) ew32flash(ICH_FLASH_HSFSTS, hsfsts.regval & 0xFFFF); else ew16flash(ICH_FLASH_HSFSTS, hsfsts.regval); @@ -3423,7 +3428,7 @@ static s32 e1000_flash_cycle_init_ich8lan(struct e1000_hw *hw) * now set the Flash Cycle Done. */ hsfsts.hsf_status.flcdone = 1; - if (hw->mac.type == e1000_pch_spt) + if (hw->mac.type >= e1000_pch_spt) ew32flash(ICH_FLASH_HSFSTS, hsfsts.regval & 0xFFFF); else @@ -3450,13 +3455,13 @@ static s32 e1000_flash_cycle_ich8lan(struct e1000_hw *hw, u32 timeout) u32 i = 0; /* Start a cycle by writing 1 in Flash Cycle Go in Hw Flash Control */ - if (hw->mac.type == e1000_pch_spt) + if (hw->mac.type >= e1000_pch_spt) hsflctl.regval = er32flash(ICH_FLASH_HSFSTS) >> 16; else hsflctl.regval = er16flash(ICH_FLASH_HSFCTL); hsflctl.hsf_ctrl.flcgo = 1; - if (hw->mac.type == e1000_pch_spt) + if (hw->mac.type >= e1000_pch_spt) ew32flash(ICH_FLASH_HSFSTS, hsflctl.regval << 16); else ew16flash(ICH_FLASH_HSFCTL, hsflctl.regval); @@ -3527,7 +3532,7 @@ static s32 e1000_read_flash_byte_ich8lan(struct e1000_hw *hw, u32 offset, /* In SPT, only 32 bits access is supported, * so this function should not be called. */ - if (hw->mac.type == e1000_pch_spt) + if (hw->mac.type >= e1000_pch_spt) return -E1000_ERR_NVM; else ret_val = e1000_read_flash_data_ich8lan(hw, offset, 1, &word); @@ -3634,8 +3639,7 @@ static s32 e1000_read_flash_data32_ich8lan(struct e1000_hw *hw, u32 offset, s32 ret_val = -E1000_ERR_NVM; u8 count = 0; - if (offset > ICH_FLASH_LINEAR_ADDR_MASK || - hw->mac.type != e1000_pch_spt) + if (offset > ICH_FLASH_LINEAR_ADDR_MASK || hw->mac.type < e1000_pch_spt) return -E1000_ERR_NVM; flash_linear_addr = ((ICH_FLASH_LINEAR_ADDR_MASK & offset) + hw->nvm.flash_base_addr); @@ -4068,6 +4072,7 @@ static s32 e1000_validate_nvm_checksum_ich8lan(struct e1000_hw *hw) switch (hw->mac.type) { case e1000_pch_lpt: case e1000_pch_spt: + case e1000_pch_cnp: word = NVM_COMPAT; valid_csum_mask = NVM_COMPAT_VALID_CSUM; break; @@ -4153,7 +4158,7 @@ static s32 e1000_write_flash_data_ich8lan(struct e1000_hw *hw, u32 offset, s32 ret_val; u8 count = 0; - if (hw->mac.type == e1000_pch_spt) { + if (hw->mac.type >= e1000_pch_spt) { if (size != 4 || offset > ICH_FLASH_LINEAR_ADDR_MASK) return -E1000_ERR_NVM; } else { @@ -4173,7 +4178,7 @@ static s32 e1000_write_flash_data_ich8lan(struct e1000_hw *hw, u32 offset, /* In SPT, This register is in Lan memory space, not * flash. Therefore, only 32 bit access is supported */ - if (hw->mac.type == e1000_pch_spt) + if (hw->mac.type >= e1000_pch_spt) hsflctl.regval = er32flash(ICH_FLASH_HSFSTS) >> 16; else hsflctl.regval = er16flash(ICH_FLASH_HSFCTL); @@ -4185,7 +4190,7 @@ static s32 e1000_write_flash_data_ich8lan(struct e1000_hw *hw, u32 offset, * not flash. Therefore, only 32 bit access is * supported */ - if (hw->mac.type == e1000_pch_spt) + if (hw->mac.type >= e1000_pch_spt) ew32flash(ICH_FLASH_HSFSTS, hsflctl.regval << 16); else ew16flash(ICH_FLASH_HSFCTL, hsflctl.regval); @@ -4243,7 +4248,7 @@ static s32 e1000_write_flash_data32_ich8lan(struct e1000_hw *hw, u32 offset, s32 ret_val; u8 count = 0; - if (hw->mac.type == e1000_pch_spt) { + if (hw->mac.type >= e1000_pch_spt) { if (offset > ICH_FLASH_LINEAR_ADDR_MASK) return -E1000_ERR_NVM; } @@ -4259,7 +4264,7 @@ static s32 e1000_write_flash_data32_ich8lan(struct e1000_hw *hw, u32 offset, /* In SPT, This register is in Lan memory space, not * flash. Therefore, only 32 bit access is supported */ - if (hw->mac.type == e1000_pch_spt) + if (hw->mac.type >= e1000_pch_spt) hsflctl.regval = er32flash(ICH_FLASH_HSFSTS) >> 16; else @@ -4272,7 +4277,7 @@ static s32 e1000_write_flash_data32_ich8lan(struct e1000_hw *hw, u32 offset, * not flash. Therefore, only 32 bit access is * supported */ - if (hw->mac.type == e1000_pch_spt) + if (hw->mac.type >= e1000_pch_spt) ew32flash(ICH_FLASH_HSFSTS, hsflctl.regval << 16); else ew16flash(ICH_FLASH_HSFCTL, hsflctl.regval); @@ -4464,14 +4469,14 @@ static s32 e1000_erase_flash_bank_ich8lan(struct e1000_hw *hw, u32 bank) /* Write a value 11 (block Erase) in Flash * Cycle field in hw flash control */ - if (hw->mac.type == e1000_pch_spt) + if (hw->mac.type >= e1000_pch_spt) hsflctl.regval = er32flash(ICH_FLASH_HSFSTS) >> 16; else hsflctl.regval = er16flash(ICH_FLASH_HSFCTL); hsflctl.hsf_ctrl.flcycle = ICH_CYCLE_ERASE; - if (hw->mac.type == e1000_pch_spt) + if (hw->mac.type >= e1000_pch_spt) ew32flash(ICH_FLASH_HSFSTS, hsflctl.regval << 16); else @@ -4894,8 +4899,7 @@ static void e1000_initialize_hw_bits_ich8lan(struct e1000_hw *hw) ew32(RFCTL, reg); /* Enable ECC on Lynxpoint */ - if ((hw->mac.type == e1000_pch_lpt) || - (hw->mac.type == e1000_pch_spt)) { + if (hw->mac.type >= e1000_pch_lpt) { reg = er32(PBECCSTS); reg |= E1000_PBECCSTS_ECC_ENABLE; ew32(PBECCSTS, reg); @@ -5299,7 +5303,7 @@ void e1000_suspend_workarounds_ich8lan(struct e1000_hw *hw) (device_id == E1000_DEV_ID_PCH_LPTLP_I218_V) || (device_id == E1000_DEV_ID_PCH_I218_LM3) || (device_id == E1000_DEV_ID_PCH_I218_V3) || - (hw->mac.type == e1000_pch_spt)) { + (hw->mac.type >= e1000_pch_spt)) { u32 fextnvm6 = er32(FEXTNVM6); ew32(FEXTNVM6, fextnvm6 & ~E1000_FEXTNVM6_REQ_PLL_CLK); @@ -5865,7 +5869,8 @@ const struct e1000_info e1000_pch2_info = { | FLAG_HAS_JUMBO_FRAMES | FLAG_APME_IN_WUC, .flags2 = FLAG2_HAS_PHY_STATS - | FLAG2_HAS_EEE, + | FLAG2_HAS_EEE + | FLAG2_CHECK_SYSTIM_OVERFLOW, .pba = 26, .max_hw_frame_size = 9022, .get_variants = e1000_get_variants_ich8lan, @@ -5914,3 +5919,23 @@ const struct e1000_info e1000_pch_spt_info = { .phy_ops = &ich8_phy_ops, .nvm_ops = &spt_nvm_ops, }; + +const struct e1000_info e1000_pch_cnp_info = { + .mac = e1000_pch_cnp, + .flags = FLAG_IS_ICH + | FLAG_HAS_WOL + | FLAG_HAS_HW_TIMESTAMP + | FLAG_HAS_CTRLEXT_ON_LOAD + | FLAG_HAS_AMT + | FLAG_HAS_FLASH + | FLAG_HAS_JUMBO_FRAMES + | FLAG_APME_IN_WUC, + .flags2 = FLAG2_HAS_PHY_STATS + | FLAG2_HAS_EEE, + .pba = 26, + .max_hw_frame_size = 9022, + .get_variants = e1000_get_variants_ich8lan, + .mac_ops = &ich8_mac_ops, + .phy_ops = &ich8_phy_ops, + .nvm_ops = &spt_nvm_ops, +}; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index e9af89ad039c..b3679728caac 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -71,6 +71,7 @@ static const struct e1000_info *e1000_info_tbl[] = { [board_pch2lan] = &e1000_pch2_info, [board_pch_lpt] = &e1000_pch_lpt_info, [board_pch_spt] = &e1000_pch_spt_info, + [board_pch_cnp] = &e1000_pch_cnp_info, }; struct e1000_reg_info { @@ -1791,8 +1792,7 @@ static irqreturn_t e1000_intr_msi(int __always_unused irq, void *data) } /* Reset on uncorrectable ECC error */ - if ((icr & E1000_ICR_ECCER) && ((hw->mac.type == e1000_pch_lpt) || - (hw->mac.type == e1000_pch_spt))) { + if ((icr & E1000_ICR_ECCER) && (hw->mac.type >= e1000_pch_lpt)) { u32 pbeccsts = er32(PBECCSTS); adapter->corr_errors += @@ -1872,8 +1872,7 @@ static irqreturn_t e1000_intr(int __always_unused irq, void *data) } /* Reset on uncorrectable ECC error */ - if ((icr & E1000_ICR_ECCER) && ((hw->mac.type == e1000_pch_lpt) || - (hw->mac.type == e1000_pch_spt))) { + if ((icr & E1000_ICR_ECCER) && (hw->mac.type >= e1000_pch_lpt)) { u32 pbeccsts = er32(PBECCSTS); adapter->corr_errors += @@ -2241,8 +2240,7 @@ static void e1000_irq_enable(struct e1000_adapter *adapter) if (adapter->msix_entries) { ew32(EIAC_82574, adapter->eiac_mask & E1000_EIAC_MASK_82574); ew32(IMS, adapter->eiac_mask | E1000_IMS_LSC); - } else if ((hw->mac.type == e1000_pch_lpt) || - (hw->mac.type == e1000_pch_spt)) { + } else if (hw->mac.type >= e1000_pch_lpt) { ew32(IMS, IMS_ENABLE_MASK | E1000_IMS_ECCER); } else { ew32(IMS, IMS_ENABLE_MASK); @@ -3000,8 +2998,8 @@ static void e1000_configure_tx(struct e1000_adapter *adapter) hw->mac.ops.config_collision_dist(hw); - /* SPT Si errata workaround to avoid data corruption */ - if (hw->mac.type == e1000_pch_spt) { + /* SPT and CNP Si errata workaround to avoid data corruption */ + if (hw->mac.type >= e1000_pch_spt) { u32 reg_val; reg_val = er32(IOSFPC); @@ -3497,8 +3495,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca) /* Make sure clock is enabled on I217/I218/I219 before checking * the frequency */ - if (((hw->mac.type == e1000_pch_lpt) || - (hw->mac.type == e1000_pch_spt)) && + if ((hw->mac.type >= e1000_pch_lpt) && !(er32(TSYNCTXCTL) & E1000_TSYNCTXCTL_ENABLED) && !(er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_ENABLED)) { u32 fextnvm7 = er32(FEXTNVM7); @@ -3511,37 +3508,58 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca) switch (hw->mac.type) { case e1000_pch2lan: + /* Stable 96MHz frequency */ + incperiod = INCPERIOD_96MHZ; + incvalue = INCVALUE_96MHZ; + shift = INCVALUE_SHIFT_96MHZ; + adapter->cc.shift = shift + INCPERIOD_SHIFT_96MHZ; + break; case e1000_pch_lpt: if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) { /* Stable 96MHz frequency */ - incperiod = INCPERIOD_96MHz; - incvalue = INCVALUE_96MHz; - shift = INCVALUE_SHIFT_96MHz; - adapter->cc.shift = shift + INCPERIOD_SHIFT_96MHz; + incperiod = INCPERIOD_96MHZ; + incvalue = INCVALUE_96MHZ; + shift = INCVALUE_SHIFT_96MHZ; + adapter->cc.shift = shift + INCPERIOD_SHIFT_96MHZ; } else { /* Stable 25MHz frequency */ - incperiod = INCPERIOD_25MHz; - incvalue = INCVALUE_25MHz; - shift = INCVALUE_SHIFT_25MHz; + incperiod = INCPERIOD_25MHZ; + incvalue = INCVALUE_25MHZ; + shift = INCVALUE_SHIFT_25MHZ; adapter->cc.shift = shift; } break; case e1000_pch_spt: if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) { /* Stable 24MHz frequency */ - incperiod = INCPERIOD_24MHz; - incvalue = INCVALUE_24MHz; - shift = INCVALUE_SHIFT_24MHz; + incperiod = INCPERIOD_24MHZ; + incvalue = INCVALUE_24MHZ; + shift = INCVALUE_SHIFT_24MHZ; adapter->cc.shift = shift; break; } return -EINVAL; + case e1000_pch_cnp: + if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) { + /* Stable 24MHz frequency */ + incperiod = INCPERIOD_24MHZ; + incvalue = INCVALUE_24MHZ; + shift = INCVALUE_SHIFT_24MHZ; + adapter->cc.shift = shift; + } else { + /* Stable 38400KHz frequency */ + incperiod = INCPERIOD_38400KHZ; + incvalue = INCVALUE_38400KHZ; + shift = INCVALUE_SHIFT_38400KHZ; + adapter->cc.shift = shift; + } + break; case e1000_82574: case e1000_82583: /* Stable 25MHz frequency */ - incperiod = INCPERIOD_25MHz; - incvalue = INCVALUE_25MHz; - shift = INCVALUE_SHIFT_25MHz; + incperiod = INCPERIOD_25MHZ; + incvalue = INCVALUE_25MHZ; + shift = INCVALUE_SHIFT_25MHZ; adapter->cc.shift = shift; break; default: @@ -4032,6 +4050,7 @@ void e1000e_reset(struct e1000_adapter *adapter) case e1000_pch2lan: case e1000_pch_lpt: case e1000_pch_spt: + case e1000_pch_cnp: fc->refresh_time = 0x0400; if (adapter->netdev->mtu <= ETH_DATA_LEN) { @@ -4076,7 +4095,7 @@ void e1000e_reset(struct e1000_adapter *adapter) } } - if (hw->mac.type == e1000_pch_spt) + if (hw->mac.type >= e1000_pch_spt) e1000_flush_desc_rings(adapter); /* Allow time for pending master requests to run */ mac->ops.reset_hw(hw); @@ -4151,7 +4170,7 @@ void e1000e_reset(struct e1000_adapter *adapter) phy_data &= ~IGP02E1000_PM_SPD; e1e_wphy(hw, IGP02E1000_PHY_POWER_MGMT, phy_data); } - if (hw->mac.type == e1000_pch_spt && adapter->int_mode == 0) { + if (hw->mac.type >= e1000_pch_spt && adapter->int_mode == 0) { u32 reg; /* Fextnvm7 @ 0xe4[2] = 1 */ @@ -4285,7 +4304,7 @@ void e1000e_down(struct e1000_adapter *adapter, bool reset) if (!pci_channel_offline(adapter->pdev)) { if (reset) e1000e_reset(adapter); - else if (hw->mac.type == e1000_pch_spt) + else if (hw->mac.type >= e1000_pch_spt) e1000_flush_desc_rings(adapter); } e1000_clean_tx_ring(adapter->tx_ring); @@ -4973,8 +4992,7 @@ static void e1000e_update_stats(struct e1000_adapter *adapter) adapter->stats.mgpdc += er32(MGTPDC); /* Correctable ECC Errors */ - if ((hw->mac.type == e1000_pch_lpt) || - (hw->mac.type == e1000_pch_spt)) { + if (hw->mac.type >= e1000_pch_lpt) { u32 pbeccsts = er32(PBECCSTS); adapter->corr_errors += @@ -6348,8 +6366,7 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) if (adapter->hw.phy.type == e1000_phy_igp_3) { e1000e_igp3_phy_powerdown_workaround_ich8lan(&adapter->hw); - } else if ((hw->mac.type == e1000_pch_lpt) || - (hw->mac.type == e1000_pch_spt)) { + } else if (hw->mac.type >= e1000_pch_lpt) { if (!(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC))) /* ULP does not support wake from unicast, multicast * or broadcast. @@ -7508,6 +7525,10 @@ static const struct pci_device_id e1000_pci_tbl[] = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_V4), board_pch_spt }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_LM5), board_pch_spt }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_SPT_I219_V5), board_pch_spt }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CNP_I219_LM6), board_pch_cnp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CNP_I219_V6), board_pch_cnp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CNP_I219_LM7), board_pch_cnp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CNP_I219_V7), board_pch_cnp }, { 0, 0, 0, 0, 0, 0, 0 } /* terminate list */ }; diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c index 34cc3be0df8e..b366885487a8 100644 --- a/drivers/net/ethernet/intel/e1000e/ptp.c +++ b/drivers/net/ethernet/intel/e1000e/ptp.c @@ -301,8 +301,8 @@ void e1000e_ptp_init(struct e1000_adapter *adapter) case e1000_pch2lan: case e1000_pch_lpt: case e1000_pch_spt: - if (((hw->mac.type != e1000_pch_lpt) && - (hw->mac.type != e1000_pch_spt)) || + case e1000_pch_cnp: + if ((hw->mac.type < e1000_pch_lpt) || (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)) { adapter->ptp_clock_info.max_adj = 24000000 - 1; break; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index 52b979443cde..689c413b7782 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * Copyright(c) 2013 - 2017 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -65,14 +65,16 @@ enum fm10k_ring_state_t { __FM10K_TX_DETECT_HANG, __FM10K_HANG_CHECK_ARMED, __FM10K_TX_XPS_INIT_DONE, + /* This must be last and is used to calculate BITMAP size */ + __FM10K_TX_STATE_SIZE__, }; #define check_for_tx_hang(ring) \ - test_bit(__FM10K_TX_DETECT_HANG, &(ring)->state) + test_bit(__FM10K_TX_DETECT_HANG, (ring)->state) #define set_check_for_tx_hang(ring) \ - set_bit(__FM10K_TX_DETECT_HANG, &(ring)->state) + set_bit(__FM10K_TX_DETECT_HANG, (ring)->state) #define clear_check_for_tx_hang(ring) \ - clear_bit(__FM10K_TX_DETECT_HANG, &(ring)->state) + clear_bit(__FM10K_TX_DETECT_HANG, (ring)->state) struct fm10k_tx_buffer { struct fm10k_tx_desc *next_to_watch; @@ -126,7 +128,7 @@ struct fm10k_ring { struct fm10k_rx_buffer *rx_buffer; }; u32 __iomem *tail; - unsigned long state; + DECLARE_BITMAP(state, __FM10K_TX_STATE_SIZE__); dma_addr_t dma; /* phys. address of descriptor ring */ unsigned int size; /* length in bytes */ @@ -249,18 +251,46 @@ struct fm10k_udp_port { /* one work queue for entire driver */ extern struct workqueue_struct *fm10k_workqueue; +/* The following enumeration contains flags which indicate or enable modified + * driver behaviors. To avoid race conditions, the flags are stored in + * a BITMAP in the fm10k_intfc structure. The BITMAP should be accessed using + * atomic *_bit() operations. + */ +enum fm10k_flags_t { + FM10K_FLAG_RESET_REQUESTED, + FM10K_FLAG_RSS_FIELD_IPV4_UDP, + FM10K_FLAG_RSS_FIELD_IPV6_UDP, + FM10K_FLAG_SWPRI_CONFIG, + /* __FM10K_FLAGS_SIZE__ is used to calculate the size of + * interface->flags and must be the last value in this + * enumeration. + */ + __FM10K_FLAGS_SIZE__ +}; + +enum fm10k_state_t { + __FM10K_RESETTING, + __FM10K_DOWN, + __FM10K_SERVICE_SCHED, + __FM10K_SERVICE_REQUEST, + __FM10K_SERVICE_DISABLE, + __FM10K_MBX_LOCK, + __FM10K_LINK_DOWN, + __FM10K_UPDATING_STATS, + /* This value must be last and determines the BITMAP size */ + __FM10K_STATE_SIZE__, +}; + struct fm10k_intfc { unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; struct net_device *netdev; struct fm10k_l2_accel *l2_accel; /* pointer to L2 acceleration list */ struct pci_dev *pdev; - unsigned long state; + DECLARE_BITMAP(state, __FM10K_STATE_SIZE__); + + /* Access flag values using atomic *_bit() operations */ + DECLARE_BITMAP(flags, __FM10K_FLAGS_SIZE__); - u32 flags; -#define FM10K_FLAG_RESET_REQUESTED (u32)(BIT(0)) -#define FM10K_FLAG_RSS_FIELD_IPV4_UDP (u32)(BIT(1)) -#define FM10K_FLAG_RSS_FIELD_IPV6_UDP (u32)(BIT(2)) -#define FM10K_FLAG_SWPRI_CONFIG (u32)(BIT(3)) int xcast_mode; /* Tx fast path data */ @@ -352,22 +382,12 @@ struct fm10k_intfc { u16 vid; }; -enum fm10k_state_t { - __FM10K_RESETTING, - __FM10K_DOWN, - __FM10K_SERVICE_SCHED, - __FM10K_SERVICE_DISABLE, - __FM10K_MBX_LOCK, - __FM10K_LINK_DOWN, - __FM10K_UPDATING_STATS, -}; - static inline void fm10k_mbx_lock(struct fm10k_intfc *interface) { /* busy loop if we cannot obtain the lock as some calls * such as ndo_set_rx_mode may be made in atomic context */ - while (test_and_set_bit(__FM10K_MBX_LOCK, &interface->state)) + while (test_and_set_bit(__FM10K_MBX_LOCK, interface->state)) udelay(20); } @@ -375,12 +395,12 @@ static inline void fm10k_mbx_unlock(struct fm10k_intfc *interface) { /* flush memory to make sure state is correct */ smp_mb__before_atomic(); - clear_bit(__FM10K_MBX_LOCK, &interface->state); + clear_bit(__FM10K_MBX_LOCK, interface->state); } static inline int fm10k_mbx_trylock(struct fm10k_intfc *interface) { - return !test_and_set_bit(__FM10K_MBX_LOCK, &interface->state); + return !test_and_set_bit(__FM10K_MBX_LOCK, interface->state); } /* fm10k_test_staterr - test bits in Rx descriptor status and error fields */ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index 0c84fef750f4..c7234f35f8ff 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * Copyright(c) 2013 - 2017 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -562,7 +562,7 @@ static int fm10k_set_ringparam(struct net_device *netdev, return 0; } - while (test_and_set_bit(__FM10K_RESETTING, &interface->state)) + while (test_and_set_bit(__FM10K_RESETTING, interface->state)) usleep_range(1000, 2000); if (!netif_running(interface->netdev)) { @@ -648,7 +648,7 @@ err_setup: fm10k_up(interface); vfree(temp_ring); clear_reset: - clear_bit(__FM10K_RESETTING, &interface->state); + clear_bit(__FM10K_RESETTING, interface->state); return err; } @@ -716,7 +716,8 @@ static int fm10k_get_rss_hash_opts(struct fm10k_intfc *interface, cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; /* fall through */ case UDP_V4_FLOW: - if (interface->flags & FM10K_FLAG_RSS_FIELD_IPV4_UDP) + if (test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP, + interface->flags)) cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; /* fall through */ case SCTP_V4_FLOW: @@ -732,7 +733,8 @@ static int fm10k_get_rss_hash_opts(struct fm10k_intfc *interface, cmd->data |= RXH_IP_SRC | RXH_IP_DST; break; case UDP_V6_FLOW: - if (interface->flags & FM10K_FLAG_RSS_FIELD_IPV6_UDP) + if (test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP, + interface->flags)) cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; cmd->data |= RXH_IP_SRC | RXH_IP_DST; break; @@ -764,12 +766,13 @@ static int fm10k_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, return ret; } -#define UDP_RSS_FLAGS (FM10K_FLAG_RSS_FIELD_IPV4_UDP | \ - FM10K_FLAG_RSS_FIELD_IPV6_UDP) static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface, struct ethtool_rxnfc *nfc) { - u32 flags = interface->flags; + int rss_ipv4_udp = test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP, + interface->flags); + int rss_ipv6_udp = test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP, + interface->flags); /* RSS does not support anything other than hashing * to queues on src and dst IPs and ports @@ -793,10 +796,12 @@ static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface, return -EINVAL; switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { case 0: - flags &= ~FM10K_FLAG_RSS_FIELD_IPV4_UDP; + clear_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP, + interface->flags); break; case (RXH_L4_B_0_1 | RXH_L4_B_2_3): - flags |= FM10K_FLAG_RSS_FIELD_IPV4_UDP; + set_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP, + interface->flags); break; default: return -EINVAL; @@ -808,10 +813,12 @@ static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface, return -EINVAL; switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { case 0: - flags &= ~FM10K_FLAG_RSS_FIELD_IPV6_UDP; + clear_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP, + interface->flags); break; case (RXH_L4_B_0_1 | RXH_L4_B_2_3): - flags |= FM10K_FLAG_RSS_FIELD_IPV6_UDP; + set_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP, + interface->flags); break; default: return -EINVAL; @@ -835,28 +842,41 @@ static int fm10k_set_rss_hash_opt(struct fm10k_intfc *interface, return -EINVAL; } - /* if we changed something we need to update flags */ - if (flags != interface->flags) { + /* If something changed we need to update the MRQC register. Note that + * test_bit() is guaranteed to return strictly 0 or 1, so testing for + * equality is safe. + */ + if ((rss_ipv4_udp != test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP, + interface->flags)) || + (rss_ipv6_udp != test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP, + interface->flags))) { struct fm10k_hw *hw = &interface->hw; + bool warn = false; u32 mrqc; - if ((flags & UDP_RSS_FLAGS) && - !(interface->flags & UDP_RSS_FLAGS)) - netif_warn(interface, drv, interface->netdev, - "enabling UDP RSS: fragmented packets may arrive out of order to the stack above\n"); - - interface->flags = flags; - /* Perform hash on these packet types */ mrqc = FM10K_MRQC_IPV4 | FM10K_MRQC_TCP_IPV4 | FM10K_MRQC_IPV6 | FM10K_MRQC_TCP_IPV6; - if (flags & FM10K_FLAG_RSS_FIELD_IPV4_UDP) + if (test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP, + interface->flags)) { mrqc |= FM10K_MRQC_UDP_IPV4; - if (flags & FM10K_FLAG_RSS_FIELD_IPV6_UDP) + warn = true; + } + if (test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP, + interface->flags)) { mrqc |= FM10K_MRQC_UDP_IPV6; + warn = true; + } + + /* If we enable UDP RSS display a warning that this may cause + * fragmented UDP packets to arrive out of order. + */ + if (warn) + netif_warn(interface, drv, interface->netdev, + "enabling UDP RSS: fragmented packets may arrive out of order to the stack above\n"); fm10k_write_reg(hw, FM10K_MRQC(0), mrqc); } @@ -939,7 +959,7 @@ static void fm10k_self_test(struct net_device *dev, memset(data, 0, sizeof(*data) * FM10K_TEST_LEN); - if (FM10K_REMOVED(hw)) { + if (FM10K_REMOVED(hw->hw_addr)) { netif_err(interface, drv, dev, "Interface removed - test blocked\n"); eth_test->flags |= ETH_TEST_FL_FAILED; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 5bb233a9614c..9dffaba85ae6 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * Copyright(c) 2013 - 2017 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -34,7 +34,7 @@ const char fm10k_driver_version[] = DRV_VERSION; char fm10k_driver_name[] = "fm10k"; static const char fm10k_driver_string[] = DRV_SUMMARY; static const char fm10k_copyright[] = - "Copyright (c) 2013 - 2016 Intel Corporation."; + "Copyright(c) 2013 - 2017 Intel Corporation."; MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION(DRV_SUMMARY); @@ -1175,13 +1175,13 @@ bool fm10k_check_tx_hang(struct fm10k_ring *tx_ring) /* update completed stats and continue */ tx_ring->tx_stats.tx_done_old = tx_done; /* reset the countdown */ - clear_bit(__FM10K_HANG_CHECK_ARMED, &tx_ring->state); + clear_bit(__FM10K_HANG_CHECK_ARMED, tx_ring->state); return false; } /* make sure it is true for two checks in a row */ - return test_and_set_bit(__FM10K_HANG_CHECK_ARMED, &tx_ring->state); + return test_and_set_bit(__FM10K_HANG_CHECK_ARMED, tx_ring->state); } /** @@ -1191,9 +1191,9 @@ bool fm10k_check_tx_hang(struct fm10k_ring *tx_ring) void fm10k_tx_timeout_reset(struct fm10k_intfc *interface) { /* Do the reset outside of interrupt context */ - if (!test_bit(__FM10K_DOWN, &interface->state)) { + if (!test_bit(__FM10K_DOWN, interface->state)) { interface->tx_timeout_count++; - interface->flags |= FM10K_FLAG_RESET_REQUESTED; + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); fm10k_service_event_schedule(interface); } } @@ -1214,7 +1214,7 @@ static bool fm10k_clean_tx_irq(struct fm10k_q_vector *q_vector, unsigned int budget = q_vector->tx.work_limit; unsigned int i = tx_ring->next_to_clean; - if (test_bit(__FM10K_DOWN, &interface->state)) + if (test_bit(__FM10K_DOWN, interface->state)) return true; tx_buffer = &tx_ring->tx_buffer[i]; @@ -1344,7 +1344,7 @@ static bool fm10k_clean_tx_irq(struct fm10k_q_vector *q_vector, smp_mb(); if (__netif_subqueue_stopped(tx_ring->netdev, tx_ring->queue_index) && - !test_bit(__FM10K_DOWN, &interface->state)) { + !test_bit(__FM10K_DOWN, interface->state)) { netif_wake_subqueue(tx_ring->netdev, tx_ring->queue_index); ++tx_ring->tx_stats.restart_queue; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 01db688cf539..24f2f6f86f5a 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * Copyright(c) 2013 - 2017 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -737,6 +737,23 @@ static void fm10k_tx_timeout(struct net_device *netdev) } } +/** + * fm10k_host_mbx_ready - Check PF interface's mailbox readiness + * @interface: board private structure + * + * This function checks if the PF interface's mailbox is ready before queueing + * mailbox messages for transmission. This will prevent filling the TX mailbox + * queue when the receiver is not ready. VF interfaces are exempt from this + * check since it will block all PF-VF mailbox messages from being sent from + * the VF to the PF at initialization. + **/ +static bool fm10k_host_mbx_ready(struct fm10k_intfc *interface) +{ + struct fm10k_hw *hw = &interface->hw; + + return (hw->mac.type == fm10k_mac_vf || interface->host_ready); +} + static int fm10k_uc_vlan_unsync(struct net_device *netdev, const unsigned char *uc_addr) { @@ -745,12 +762,15 @@ static int fm10k_uc_vlan_unsync(struct net_device *netdev, u16 glort = interface->glort; u16 vid = interface->vid; bool set = !!(vid / VLAN_N_VID); - int err; + int err = -EHOSTDOWN; /* drop any leading bits on the VLAN ID */ vid &= VLAN_N_VID - 1; - err = hw->mac.ops.update_uc_addr(hw, glort, uc_addr, vid, set, 0); + if (fm10k_host_mbx_ready(interface)) + err = hw->mac.ops.update_uc_addr(hw, glort, uc_addr, + vid, set, 0); + if (err) return err; @@ -766,12 +786,14 @@ static int fm10k_mc_vlan_unsync(struct net_device *netdev, u16 glort = interface->glort; u16 vid = interface->vid; bool set = !!(vid / VLAN_N_VID); - int err; + int err = -EHOSTDOWN; /* drop any leading bits on the VLAN ID */ vid &= VLAN_N_VID - 1; - err = hw->mac.ops.update_mc_addr(hw, glort, mc_addr, vid, set); + if (fm10k_host_mbx_ready(interface)) + err = hw->mac.ops.update_mc_addr(hw, glort, mc_addr, vid, set); + if (err) return err; @@ -822,7 +844,7 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set) /* Do not throw an error if the interface is down. We will sync once * we come up */ - if (test_bit(__FM10K_DOWN, &interface->state)) + if (test_bit(__FM10K_DOWN, interface->state)) return 0; fm10k_mbx_lock(interface); @@ -834,9 +856,13 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set) goto err_out; } - /* update our base MAC address */ - err = hw->mac.ops.update_uc_addr(hw, interface->glort, hw->mac.addr, - vid, set, 0); + /* update our base MAC address if host's mailbox is ready */ + if (fm10k_host_mbx_ready(interface)) + err = hw->mac.ops.update_uc_addr(hw, interface->glort, + hw->mac.addr, vid, set, 0); + else + err = -EHOSTDOWN; + if (err) goto err_out; @@ -907,12 +933,15 @@ static int __fm10k_uc_sync(struct net_device *dev, if (!is_valid_ether_addr(addr)) return -EADDRNOTAVAIL; - /* update table with current entries */ + /* update table with current entries if host's mailbox is ready */ + if (!fm10k_host_mbx_ready(interface)) + return -EHOSTDOWN; + for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1; vid < VLAN_N_VID; vid = fm10k_find_next_vlan(interface, vid)) { err = hw->mac.ops.update_uc_addr(hw, glort, addr, - vid, sync, 0); + vid, sync, 0); if (err) return err; } @@ -970,7 +999,10 @@ static int __fm10k_mc_sync(struct net_device *dev, struct fm10k_hw *hw = &interface->hw; u16 vid, glort = interface->glort; - /* update table with current entries */ + /* update table with current entries if host's mailbox is ready */ + if (!fm10k_host_mbx_ready(interface)) + return 0; + for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1; vid < VLAN_N_VID; vid = fm10k_find_next_vlan(interface, vid)) { @@ -1018,8 +1050,10 @@ static void fm10k_set_rx_mode(struct net_device *dev) if (interface->xcast_mode == FM10K_XCAST_MODE_PROMISC) fm10k_clear_unused_vlans(interface); - /* update xcast mode */ - hw->mac.ops.update_xcast_mode(hw, interface->glort, xcast_mode); + /* update xcast mode if host's mailbox is ready */ + if (fm10k_host_mbx_ready(interface)) + hw->mac.ops.update_xcast_mode(hw, interface->glort, + xcast_mode); /* record updated xcast mode state */ interface->xcast_mode = xcast_mode; @@ -1054,8 +1088,10 @@ void fm10k_restore_rx_state(struct fm10k_intfc *interface) fm10k_mbx_lock(interface); - /* Enable logical port */ - hw->mac.ops.update_lport_state(hw, glort, interface->glort_count, true); + /* Enable logical port if host's mailbox is ready */ + if (fm10k_host_mbx_ready(interface)) + hw->mac.ops.update_lport_state(hw, glort, + interface->glort_count, true); /* update VLAN table */ hw->mac.ops.update_vlan(hw, FM10K_VLAN_ALL, 0, @@ -1069,12 +1105,18 @@ void fm10k_restore_rx_state(struct fm10k_intfc *interface) vid < VLAN_N_VID; vid = fm10k_find_next_vlan(interface, vid)) { hw->mac.ops.update_vlan(hw, vid, 0, true); - hw->mac.ops.update_uc_addr(hw, glort, hw->mac.addr, - vid, true, 0); + + /* Update unicast entries if host's mailbox is ready */ + if (fm10k_host_mbx_ready(interface)) + hw->mac.ops.update_uc_addr(hw, glort, hw->mac.addr, + vid, true, 0); } - /* update xcast mode before synchronizing addresses */ - hw->mac.ops.update_xcast_mode(hw, glort, xcast_mode); + /* update xcast mode before synchronizing addresses if host's mailbox + * is ready + */ + if (fm10k_host_mbx_ready(interface)) + hw->mac.ops.update_xcast_mode(hw, glort, xcast_mode); /* synchronize all of the addresses */ __dev_uc_sync(netdev, fm10k_uc_sync, fm10k_uc_unsync); @@ -1096,9 +1138,12 @@ void fm10k_reset_rx_state(struct fm10k_intfc *interface) fm10k_mbx_lock(interface); - /* clear the logical port state on lower device */ - hw->mac.ops.update_lport_state(hw, interface->glort, - interface->glort_count, false); + /* clear the logical port state on lower device if host's mailbox is + * ready + */ + if (fm10k_host_mbx_ready(interface)) + hw->mac.ops.update_lport_state(hw, interface->glort, + interface->glort_count, false); fm10k_mbx_unlock(interface); @@ -1115,8 +1160,8 @@ void fm10k_reset_rx_state(struct fm10k_intfc *interface) * @netdev: network interface device structure * @stats: storage space for 64bit statistics * - * Returns 64bit statistics, for use in the ndo_get_stats64 callback. This - * function replaces fm10k_get_stats for kernels which support it. + * Obtain 64bit statistics in a way that is safe for both 32bit and 64bit + * architectures. */ static void fm10k_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) @@ -1207,7 +1252,7 @@ int fm10k_setup_tc(struct net_device *dev, u8 tc) goto err_open; /* flag to indicate SWPRI has yet to be updated */ - interface->flags |= FM10K_FLAG_SWPRI_CONFIG; + set_bit(FM10K_FLAG_SWPRI_CONFIG, interface->flags); return 0; err_open: @@ -1226,7 +1271,9 @@ static int __fm10k_setup_tc(struct net_device *dev, u32 handle, __be16 proto, if (tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return fm10k_setup_tc(dev, tc->tc); + tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return fm10k_setup_tc(dev, tc->mqprio->num_tc); } static void fm10k_assign_l2_accel(struct fm10k_intfc *interface, @@ -1317,8 +1364,13 @@ static void *fm10k_dfwd_add_station(struct net_device *dev, fm10k_mbx_lock(interface); glort = l2_accel->dglort + 1 + i; - hw->mac.ops.update_xcast_mode(hw, glort, FM10K_XCAST_MODE_MULTI); - hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr, 0, true, 0); + + if (fm10k_host_mbx_ready(interface)) { + hw->mac.ops.update_xcast_mode(hw, glort, + FM10K_XCAST_MODE_MULTI); + hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr, + 0, true, 0); + } fm10k_mbx_unlock(interface); @@ -1352,8 +1404,13 @@ static void fm10k_dfwd_del_station(struct net_device *dev, void *priv) fm10k_mbx_lock(interface); glort = l2_accel->dglort + 1 + i; - hw->mac.ops.update_xcast_mode(hw, glort, FM10K_XCAST_MODE_NONE); - hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr, 0, false, 0); + + if (fm10k_host_mbx_ready(interface)) { + hw->mac.ops.update_xcast_mode(hw, glort, + FM10K_XCAST_MODE_NONE); + hw->mac.ops.update_uc_addr(hw, glort, sdev->dev_addr, + 0, false, 0); + } fm10k_mbx_unlock(interface); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index e372a5823480..3e26d27ad213 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -1,5 +1,5 @@ /* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. + * Copyright(c) 2013 - 2017 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -19,6 +19,7 @@ */ #include <linux/module.h> +#include <linux/interrupt.h> #include <linux/aer.h> #include "fm10k.h" @@ -92,18 +93,29 @@ static int fm10k_hw_ready(struct fm10k_intfc *interface) void fm10k_service_event_schedule(struct fm10k_intfc *interface) { - if (!test_bit(__FM10K_SERVICE_DISABLE, &interface->state) && - !test_and_set_bit(__FM10K_SERVICE_SCHED, &interface->state)) + if (!test_bit(__FM10K_SERVICE_DISABLE, interface->state) && + !test_and_set_bit(__FM10K_SERVICE_SCHED, interface->state)) { + clear_bit(__FM10K_SERVICE_REQUEST, interface->state); queue_work(fm10k_workqueue, &interface->service_task); + } else { + set_bit(__FM10K_SERVICE_REQUEST, interface->state); + } } static void fm10k_service_event_complete(struct fm10k_intfc *interface) { - WARN_ON(!test_bit(__FM10K_SERVICE_SCHED, &interface->state)); + WARN_ON(!test_bit(__FM10K_SERVICE_SCHED, interface->state)); /* flush memory to make sure state is correct before next watchog */ smp_mb__before_atomic(); - clear_bit(__FM10K_SERVICE_SCHED, &interface->state); + clear_bit(__FM10K_SERVICE_SCHED, interface->state); + + /* If a service event was requested since we started, immediately + * re-schedule now. This ensures we don't drop a request until the + * next timer event. + */ + if (test_bit(__FM10K_SERVICE_REQUEST, interface->state)) + fm10k_service_event_schedule(interface); } /** @@ -136,7 +148,7 @@ static void fm10k_detach_subtask(struct fm10k_intfc *interface) if (~value) { interface->hw.hw_addr = interface->uc_addr; netif_device_attach(netdev); - interface->flags |= FM10K_FLAG_RESET_REQUESTED; + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); netdev_warn(netdev, "PCIe link restored, device now attached\n"); return; } @@ -158,7 +170,7 @@ static void fm10k_prepare_for_reset(struct fm10k_intfc *interface) /* put off any impending NetWatchDogTimeout */ netif_trans_update(netdev); - while (test_and_set_bit(__FM10K_RESETTING, &interface->state)) + while (test_and_set_bit(__FM10K_RESETTING, interface->state)) usleep_range(1000, 2000); rtnl_lock(); @@ -241,7 +253,7 @@ static int fm10k_handle_reset(struct fm10k_intfc *interface) rtnl_unlock(); - clear_bit(__FM10K_RESETTING, &interface->state); + clear_bit(__FM10K_RESETTING, interface->state); return err; err_open: @@ -253,7 +265,7 @@ reinit_err: rtnl_unlock(); - clear_bit(__FM10K_RESETTING, &interface->state); + clear_bit(__FM10K_RESETTING, interface->state); return err; } @@ -272,11 +284,10 @@ static void fm10k_reinit(struct fm10k_intfc *interface) static void fm10k_reset_subtask(struct fm10k_intfc *interface) { - if (!(interface->flags & FM10K_FLAG_RESET_REQUESTED)) + if (!test_and_clear_bit(FM10K_FLAG_RESET_REQUESTED, + interface->flags)) return; - interface->flags &= ~FM10K_FLAG_RESET_REQUESTED; - netdev_err(interface->netdev, "Reset interface\n"); fm10k_reinit(interface); @@ -295,7 +306,7 @@ static void fm10k_configure_swpri_map(struct fm10k_intfc *interface) int i; /* clear flag indicating update is needed */ - interface->flags &= ~FM10K_FLAG_SWPRI_CONFIG; + clear_bit(FM10K_FLAG_SWPRI_CONFIG, interface->flags); /* these registers are only available on the PF */ if (hw->mac.type != fm10k_mac_pf) @@ -316,14 +327,14 @@ static void fm10k_watchdog_update_host_state(struct fm10k_intfc *interface) struct fm10k_hw *hw = &interface->hw; s32 err; - if (test_bit(__FM10K_LINK_DOWN, &interface->state)) { + if (test_bit(__FM10K_LINK_DOWN, interface->state)) { interface->host_ready = false; if (time_is_after_jiffies(interface->link_down_event)) return; - clear_bit(__FM10K_LINK_DOWN, &interface->state); + clear_bit(__FM10K_LINK_DOWN, interface->state); } - if (interface->flags & FM10K_FLAG_SWPRI_CONFIG) { + if (test_bit(FM10K_FLAG_SWPRI_CONFIG, interface->flags)) { if (rtnl_trylock()) { fm10k_configure_swpri_map(interface); rtnl_unlock(); @@ -335,7 +346,7 @@ static void fm10k_watchdog_update_host_state(struct fm10k_intfc *interface) err = hw->mac.ops.get_host_state(hw, &interface->host_ready); if (err && time_is_before_jiffies(interface->last_reset)) - interface->flags |= FM10K_FLAG_RESET_REQUESTED; + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); /* free the lock */ fm10k_mbx_unlock(interface); @@ -411,7 +422,7 @@ void fm10k_update_stats(struct fm10k_intfc *interface) int i; /* ensure only one thread updates stats at a time */ - if (test_and_set_bit(__FM10K_UPDATING_STATS, &interface->state)) + if (test_and_set_bit(__FM10K_UPDATING_STATS, interface->state)) return; /* do not allow stats update via service task for next second */ @@ -492,7 +503,7 @@ void fm10k_update_stats(struct fm10k_intfc *interface) net_stats->rx_errors = rx_errors; net_stats->rx_dropped = interface->stats.nodesc_drop.count; - clear_bit(__FM10K_UPDATING_STATS, &interface->state); + clear_bit(__FM10K_UPDATING_STATS, interface->state); } /** @@ -522,7 +533,7 @@ static void fm10k_watchdog_flush_tx(struct fm10k_intfc *interface) * controller to flush Tx. */ if (some_tx_pending) - interface->flags |= FM10K_FLAG_RESET_REQUESTED; + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); } /** @@ -532,8 +543,8 @@ static void fm10k_watchdog_flush_tx(struct fm10k_intfc *interface) static void fm10k_watchdog_subtask(struct fm10k_intfc *interface) { /* if interface is down do nothing */ - if (test_bit(__FM10K_DOWN, &interface->state) || - test_bit(__FM10K_RESETTING, &interface->state)) + if (test_bit(__FM10K_DOWN, interface->state) || + test_bit(__FM10K_RESETTING, interface->state)) return; if (interface->host_ready) @@ -563,8 +574,8 @@ static void fm10k_check_hang_subtask(struct fm10k_intfc *interface) int i; /* If we're down or resetting, just bail */ - if (test_bit(__FM10K_DOWN, &interface->state) || - test_bit(__FM10K_RESETTING, &interface->state)) + if (test_bit(__FM10K_DOWN, interface->state) || + test_bit(__FM10K_RESETTING, interface->state)) return; /* rate limit tx hang checks to only once every 2 seconds */ @@ -663,7 +674,7 @@ static void fm10k_configure_tx_ring(struct fm10k_intfc *interface, FM10K_PFVTCTL_FTAG_DESC_ENABLE); /* Initialize XPS */ - if (!test_and_set_bit(__FM10K_TX_XPS_INIT_DONE, &ring->state) && + if (!test_and_set_bit(__FM10K_TX_XPS_INIT_DONE, ring->state) && ring->q_vector) netif_set_xps_queue(ring->netdev, &ring->q_vector->affinity_mask, @@ -743,6 +754,7 @@ static void fm10k_configure_rx_ring(struct fm10k_intfc *interface, /* disable queue to avoid issues while updating state */ rxqctl = fm10k_read_reg(hw, FM10K_RXQCTL(reg_idx)); rxqctl &= ~FM10K_RXQCTL_ENABLE; + fm10k_write_reg(hw, FM10K_RXQCTL(reg_idx), rxqctl); fm10k_write_flush(hw); /* possible poll here to verify ring resources have been cleaned */ @@ -863,9 +875,9 @@ static void fm10k_configure_dglort(struct fm10k_intfc *interface) FM10K_MRQC_IPV6 | FM10K_MRQC_TCP_IPV6; - if (interface->flags & FM10K_FLAG_RSS_FIELD_IPV4_UDP) + if (test_bit(FM10K_FLAG_RSS_FIELD_IPV4_UDP, interface->flags)) mrqc |= FM10K_MRQC_UDP_IPV4; - if (interface->flags & FM10K_FLAG_RSS_FIELD_IPV6_UDP) + if (test_bit(FM10K_FLAG_RSS_FIELD_IPV6_UDP, interface->flags)) mrqc |= FM10K_MRQC_UDP_IPV6; fm10k_write_reg(hw, FM10K_MRQC(0), mrqc); @@ -980,7 +992,7 @@ void fm10k_netpoll(struct net_device *netdev) int i; /* if interface is down do nothing */ - if (test_bit(__FM10K_DOWN, &interface->state)) + if (test_bit(__FM10K_DOWN, interface->state)) return; for (i = 0; i < interface->num_q_vectors; i++) @@ -1167,13 +1179,13 @@ static irqreturn_t fm10k_msix_mbx_pf(int __always_unused irq, void *data) } if (err == FM10K_ERR_RESET_REQUESTED) - interface->flags |= FM10K_FLAG_RESET_REQUESTED; + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); /* if switch toggled state we should reset GLORTs */ if (eicr & FM10K_EICR_SWITCHNOTREADY) { /* force link down for at least 4 seconds */ interface->link_down_event = jiffies + (4 * HZ); - set_bit(__FM10K_LINK_DOWN, &interface->state); + set_bit(__FM10K_LINK_DOWN, interface->state); /* reset dglort_map back to no config */ hw->mac.dglort_map = FM10K_DGLORTMAP_NONE; @@ -1246,12 +1258,12 @@ static s32 fm10k_mbx_mac_addr(struct fm10k_hw *hw, u32 **results, /* MAC was changed so we need reset */ if (is_valid_ether_addr(hw->mac.perm_addr) && !ether_addr_equal(hw->mac.perm_addr, hw->mac.addr)) - interface->flags |= FM10K_FLAG_RESET_REQUESTED; + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); /* VLAN override was changed, or default VLAN changed */ if ((vlan_override != hw->mac.vlan_override) || (default_vid != hw->mac.default_vid)) - interface->flags |= FM10K_FLAG_RESET_REQUESTED; + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); return 0; } @@ -1325,7 +1337,7 @@ static s32 fm10k_lport_map(struct fm10k_hw *hw, u32 **results, if (!err && hw->swapi.status) { /* force link down for a reasonable delay */ interface->link_down_event = jiffies + (2 * HZ); - set_bit(__FM10K_LINK_DOWN, &interface->state); + set_bit(__FM10K_LINK_DOWN, interface->state); /* reset dglort_map back to no config */ hw->mac.dglort_map = FM10K_DGLORTMAP_NONE; @@ -1356,7 +1368,7 @@ static s32 fm10k_lport_map(struct fm10k_hw *hw, u32 **results, /* we need to reset if port count was just updated */ if (dglort_map != hw->mac.dglort_map) - interface->flags |= FM10K_FLAG_RESET_REQUESTED; + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); return 0; } @@ -1395,7 +1407,7 @@ static s32 fm10k_update_pvid(struct fm10k_hw *hw, u32 **results, /* we need to reset if default VLAN was just updated */ if (pvid != hw->mac.default_vid) - interface->flags |= FM10K_FLAG_RESET_REQUESTED; + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); hw->mac.default_vid = pvid; @@ -1623,10 +1635,10 @@ void fm10k_up(struct fm10k_intfc *interface) hw->mac.ops.update_int_moderator(hw); /* enable statistics capture again */ - clear_bit(__FM10K_UPDATING_STATS, &interface->state); + clear_bit(__FM10K_UPDATING_STATS, interface->state); /* clear down bit to indicate we are ready to go */ - clear_bit(__FM10K_DOWN, &interface->state); + clear_bit(__FM10K_DOWN, interface->state); /* enable polling cleanups */ fm10k_napi_enable_all(interface); @@ -1660,7 +1672,7 @@ void fm10k_down(struct fm10k_intfc *interface) int err, i = 0, count = 0; /* signal that we are down to the interrupt handler and service task */ - if (test_and_set_bit(__FM10K_DOWN, &interface->state)) + if (test_and_set_bit(__FM10K_DOWN, interface->state)) return; /* call carrier off first to avoid false dev_watchdog timeouts */ @@ -1680,7 +1692,7 @@ void fm10k_down(struct fm10k_intfc *interface) fm10k_update_stats(interface); /* prevent updating statistics while we're down */ - while (test_and_set_bit(__FM10K_UPDATING_STATS, &interface->state)) + while (test_and_set_bit(__FM10K_UPDATING_STATS, interface->state)) usleep_range(1000, 2000); /* skip waiting for TX DMA if we lost PCIe link */ @@ -1849,8 +1861,8 @@ static int fm10k_sw_init(struct fm10k_intfc *interface, memcpy(interface->rssrk, rss_key, sizeof(rss_key)); /* Start off interface as being down */ - set_bit(__FM10K_DOWN, &interface->state); - set_bit(__FM10K_UPDATING_STATS, &interface->state); + set_bit(__FM10K_DOWN, interface->state); + set_bit(__FM10K_UPDATING_STATS, interface->state); return 0; } @@ -2027,7 +2039,7 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * must ensure it is disabled since we haven't yet requested the timer * or work item. */ - set_bit(__FM10K_SERVICE_DISABLE, &interface->state); + set_bit(__FM10K_SERVICE_DISABLE, interface->state); err = fm10k_mbx_request_irq(interface); if (err) @@ -2068,7 +2080,7 @@ static int fm10k_probe(struct pci_dev *pdev, const struct pci_device_id *ent) fm10k_iov_configure(pdev, 0); /* clear the service task disable bit to allow service task to start */ - clear_bit(__FM10K_SERVICE_DISABLE, &interface->state); + clear_bit(__FM10K_SERVICE_DISABLE, interface->state); return 0; @@ -2106,7 +2118,7 @@ static void fm10k_remove(struct pci_dev *pdev) del_timer_sync(&interface->service_timer); - set_bit(__FM10K_SERVICE_DISABLE, &interface->state); + set_bit(__FM10K_SERVICE_DISABLE, interface->state); cancel_work_sync(&interface->service_task); /* free netdev, this may bounce the interrupts due to setup_tc */ @@ -2145,7 +2157,7 @@ static void fm10k_prepare_suspend(struct fm10k_intfc *interface) * stopped. We stop the watchdog task until after we resume software * activity. */ - set_bit(__FM10K_SERVICE_DISABLE, &interface->state); + set_bit(__FM10K_SERVICE_DISABLE, interface->state); cancel_work_sync(&interface->service_task); fm10k_prepare_for_reset(interface); @@ -2171,10 +2183,10 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface) /* force link to stay down for a second to prevent link flutter */ interface->link_down_event = jiffies + (HZ); - set_bit(__FM10K_LINK_DOWN, &interface->state); + set_bit(__FM10K_LINK_DOWN, interface->state); /* clear the service task disable bit to allow service task to start */ - clear_bit(__FM10K_SERVICE_DISABLE, &interface->state); + clear_bit(__FM10K_SERVICE_DISABLE, interface->state); fm10k_service_event_schedule(interface); return err; diff --git a/drivers/net/ethernet/intel/i40e/Makefile b/drivers/net/ethernet/intel/i40e/Makefile index 3b3c63e54ed6..3da482c3d68d 100644 --- a/drivers/net/ethernet/intel/i40e/Makefile +++ b/drivers/net/ethernet/intel/i40e/Makefile @@ -28,6 +28,9 @@ # Makefile for the Intel(R) Ethernet Connection XL710 (i40e.ko) driver # +ccflags-y += -I$(src) +subdir-ccflags-y += -I$(src) + obj-$(CONFIG_I40E) += i40e.o i40e-objs := i40e_main.o \ @@ -45,4 +48,3 @@ i40e-objs := i40e_main.o \ i40e_virtchnl_pf.o i40e-$(CONFIG_I40E_DCB) += i40e_dcb.o i40e_dcb_nl.o -i40e-$(CONFIG_I40E_FCOE) += i40e_fcoe.o diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 82d8040fa418..cdde3cc28fb5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -56,9 +56,6 @@ #include <linux/ptp_clock_kernel.h> #include "i40e_type.h" #include "i40e_prototype.h" -#ifdef I40E_FCOE -#include "i40e_fcoe.h" -#endif #include "i40e_client.h" #include "i40e_virtchnl.h" #include "i40e_virtchnl_pf.h" @@ -85,10 +82,6 @@ (((pf)->flags & I40E_FLAG_128_QP_RSS_CAPABLE) ? 128 : 64) #define I40E_FDIR_RING 0 #define I40E_FDIR_RING_COUNT 32 -#ifdef I40E_FCOE -#define I40E_DEFAULT_FCOE 8 /* default number of QPs for FCoE */ -#define I40E_MINIMUM_FCOE 1 /* minimum number of QPs for FCoE */ -#endif /* I40E_FCOE */ #define I40E_MAX_AQ_BUF_SIZE 4096 #define I40E_AQ_LEN 256 #define I40E_AQ_WORK_LIMIT 66 /* max number of VFs + a little */ @@ -98,14 +91,6 @@ #define I40E_QUEUE_WAIT_RETRY_LIMIT 10 #define I40E_INT_NAME_STR_LEN (IFNAMSIZ + 16) -/* Ethtool Private Flags */ -#define I40E_PRIV_FLAGS_MFP_FLAG BIT(0) -#define I40E_PRIV_FLAGS_LINKPOLL_FLAG BIT(1) -#define I40E_PRIV_FLAGS_FD_ATR BIT(2) -#define I40E_PRIV_FLAGS_VEB_STATS BIT(3) -#define I40E_PRIV_FLAGS_HW_ATR_EVICT BIT(4) -#define I40E_PRIV_FLAGS_TRUE_PROMISC_SUPPORT BIT(5) - #define I40E_NVM_VERSION_LO_SHIFT 0 #define I40E_NVM_VERSION_LO_MASK (0xff << I40E_NVM_VERSION_LO_SHIFT) #define I40E_NVM_VERSION_HI_SHIFT 12 @@ -140,7 +125,6 @@ enum i40e_state_t { __I40E_CONFIG_BUSY, __I40E_CONFIG_DONE, __I40E_DOWN, - __I40E_NEEDS_RESTART, __I40E_SERVICE_SCHED, __I40E_ADMINQ_EVENT_PENDING, __I40E_MDD_EVENT_PENDING, @@ -153,15 +137,28 @@ enum i40e_state_t { __I40E_GLOBAL_RESET_REQUESTED, __I40E_EMP_RESET_REQUESTED, __I40E_EMP_RESET_INTR_RECEIVED, - __I40E_FILTER_OVERFLOW_PROMISC, __I40E_SUSPENDED, __I40E_PTP_TX_IN_PROGRESS, __I40E_BAD_EEPROM, __I40E_DOWN_REQUESTED, __I40E_FD_FLUSH_REQUESTED, __I40E_RESET_FAILED, - __I40E_PORT_TX_SUSPENDED, + __I40E_PORT_SUSPENDED, __I40E_VF_DISABLE, + /* This must be last as it determines the size of the BITMAP */ + __I40E_STATE_SIZE__, +}; + +/* VSI state flags */ +enum i40e_vsi_state_t { + __I40E_VSI_DOWN, + __I40E_VSI_NEEDS_RESTART, + __I40E_VSI_SYNCING_FILTERS, + __I40E_VSI_OVERFLOW_PROMISC, + __I40E_VSI_REINIT_REQUESTED, + __I40E_VSI_DOWN_REQUESTED, + /* This must be last as it determines the size of the BITMAP */ + __I40E_VSI_STATE_SIZE__, }; enum i40e_interrupt_policy { @@ -202,17 +199,32 @@ enum i40e_fd_stat_idx { #define I40E_FD_ATR_TUNNEL_STAT_IDX(pf_id) \ (I40E_FD_STAT_PF_IDX(pf_id) + I40E_FD_STAT_ATR_TUNNEL) +/* The following structure contains the data parsed from the user-defined + * field of the ethtool_rx_flow_spec structure. + */ +struct i40e_rx_flow_userdef { + bool flex_filter; + u16 flex_word; + u16 flex_offset; +}; + struct i40e_fdir_filter { struct hlist_node fdir_node; /* filter ipnut set */ u8 flow_type; u8 ip4_proto; /* TX packet view of src and dst */ - __be32 dst_ip[4]; - __be32 src_ip[4]; + __be32 dst_ip; + __be32 src_ip; __be16 src_port; __be16 dst_port; __be32 sctp_v_tag; + + /* Flexible data to match within the packet payload */ + __be16 flex_word; + u16 flex_offset; + bool flex_filter; + /* filter control */ u16 q_index; u8 flex_off; @@ -244,15 +256,85 @@ struct i40e_tc_configuration { }; struct i40e_udp_port_config { - __be16 index; + /* AdminQ command interface expects port number in Host byte order */ + u16 port; u8 type; }; +/* macros related to FLX_PIT */ +#define I40E_FLEX_SET_FSIZE(fsize) (((fsize) << \ + I40E_PRTQF_FLX_PIT_FSIZE_SHIFT) & \ + I40E_PRTQF_FLX_PIT_FSIZE_MASK) +#define I40E_FLEX_SET_DST_WORD(dst) (((dst) << \ + I40E_PRTQF_FLX_PIT_DEST_OFF_SHIFT) & \ + I40E_PRTQF_FLX_PIT_DEST_OFF_MASK) +#define I40E_FLEX_SET_SRC_WORD(src) (((src) << \ + I40E_PRTQF_FLX_PIT_SOURCE_OFF_SHIFT) & \ + I40E_PRTQF_FLX_PIT_SOURCE_OFF_MASK) +#define I40E_FLEX_PREP_VAL(dst, fsize, src) (I40E_FLEX_SET_DST_WORD(dst) | \ + I40E_FLEX_SET_FSIZE(fsize) | \ + I40E_FLEX_SET_SRC_WORD(src)) + +#define I40E_FLEX_PIT_GET_SRC(flex) (((flex) & \ + I40E_PRTQF_FLX_PIT_SOURCE_OFF_MASK) >> \ + I40E_PRTQF_FLX_PIT_SOURCE_OFF_SHIFT) +#define I40E_FLEX_PIT_GET_DST(flex) (((flex) & \ + I40E_PRTQF_FLX_PIT_DEST_OFF_MASK) >> \ + I40E_PRTQF_FLX_PIT_DEST_OFF_SHIFT) +#define I40E_FLEX_PIT_GET_FSIZE(flex) (((flex) & \ + I40E_PRTQF_FLX_PIT_FSIZE_MASK) >> \ + I40E_PRTQF_FLX_PIT_FSIZE_SHIFT) + +#define I40E_MAX_FLEX_SRC_OFFSET 0x1F + +/* macros related to GLQF_ORT */ +#define I40E_ORT_SET_IDX(idx) (((idx) << \ + I40E_GLQF_ORT_PIT_INDX_SHIFT) & \ + I40E_GLQF_ORT_PIT_INDX_MASK) + +#define I40E_ORT_SET_COUNT(count) (((count) << \ + I40E_GLQF_ORT_FIELD_CNT_SHIFT) & \ + I40E_GLQF_ORT_FIELD_CNT_MASK) + +#define I40E_ORT_SET_PAYLOAD(payload) (((payload) << \ + I40E_GLQF_ORT_FLX_PAYLOAD_SHIFT) & \ + I40E_GLQF_ORT_FLX_PAYLOAD_MASK) + +#define I40E_ORT_PREP_VAL(idx, count, payload) (I40E_ORT_SET_IDX(idx) | \ + I40E_ORT_SET_COUNT(count) | \ + I40E_ORT_SET_PAYLOAD(payload)) + +#define I40E_L3_GLQF_ORT_IDX 34 +#define I40E_L4_GLQF_ORT_IDX 35 + +/* Flex PIT register index */ +#define I40E_FLEX_PIT_IDX_START_L2 0 +#define I40E_FLEX_PIT_IDX_START_L3 3 +#define I40E_FLEX_PIT_IDX_START_L4 6 + +#define I40E_FLEX_PIT_TABLE_SIZE 3 + +#define I40E_FLEX_DEST_UNUSED 63 + +#define I40E_FLEX_INDEX_ENTRIES 8 + +/* Flex MASK to disable all flexible entries */ +#define I40E_FLEX_INPUT_MASK (I40E_FLEX_50_MASK | I40E_FLEX_51_MASK | \ + I40E_FLEX_52_MASK | I40E_FLEX_53_MASK | \ + I40E_FLEX_54_MASK | I40E_FLEX_55_MASK | \ + I40E_FLEX_56_MASK | I40E_FLEX_57_MASK) + +struct i40e_flex_pit { + struct list_head list; + u16 src_offset; + u8 pit_index; +}; + /* struct that defines the Ethernet device */ struct i40e_pf { struct pci_dev *pdev; struct i40e_hw hw; - unsigned long state; + DECLARE_BITMAP(state, __I40E_STATE_SIZE__); struct msix_entry *msix_entries; bool fc_autoneg_status; @@ -262,10 +344,6 @@ struct i40e_pf { u16 num_vmdq_msix; /* num queue vectors per vmdq pool */ u16 num_req_vfs; /* num VFs requested for this VF */ u16 num_vf_qps; /* num queue pairs per VF */ -#ifdef I40E_FCOE - u16 num_fcoe_qps; /* num fcoe queues this PF has set up */ - u16 num_fcoe_msix; /* num queue vectors per fcoe pool */ -#endif /* I40E_FCOE */ u16 num_lan_qps; /* num lan queues this PF has set up */ u16 num_lan_msix; /* num queue vectors for the base PF vsi */ u16 num_fdsb_msix; /* num queue vectors for sideband Fdir */ @@ -285,7 +363,23 @@ struct i40e_pf { u32 fd_flush_cnt; u32 fd_add_err; u32 fd_atr_cnt; - u32 fd_tcp_rule; + + /* Book-keeping of side-band filter count per flow-type. + * This is used to detect and handle input set changes for + * respective flow-type. + */ + u16 fd_tcp4_filter_cnt; + u16 fd_udp4_filter_cnt; + u16 fd_sctp4_filter_cnt; + u16 fd_ip4_filter_cnt; + + /* Flexible filter table values that need to be programmed into + * hardware, which expects L3 and L4 to be programmed separately. We + * need to ensure that the values are in ascended order and don't have + * duplicates, so we track each L3 and L4 values in separate lists. + */ + struct list_head l3_flex_pit_list; + struct list_head l4_flex_pit_list; struct i40e_udp_port_config udp_ports[I40E_MAX_PF_UDP_OFFLOAD_PORTS]; u16 pending_udp_bitmap; @@ -307,21 +401,15 @@ struct i40e_pf { #define I40E_FLAG_MSIX_ENABLED BIT_ULL(3) #define I40E_FLAG_RSS_ENABLED BIT_ULL(6) #define I40E_FLAG_VMDQ_ENABLED BIT_ULL(7) -#define I40E_FLAG_FDIR_REQUIRES_REINIT BIT_ULL(8) -#define I40E_FLAG_NEED_LINK_UPDATE BIT_ULL(9) #define I40E_FLAG_IWARP_ENABLED BIT_ULL(10) -#ifdef I40E_FCOE -#define I40E_FLAG_FCOE_ENABLED BIT_ULL(11) -#endif /* I40E_FCOE */ -#define I40E_FLAG_CLEAN_ADMINQ BIT_ULL(14) #define I40E_FLAG_FILTER_SYNC BIT_ULL(15) #define I40E_FLAG_SERVICE_CLIENT_REQUESTED BIT_ULL(16) -#define I40E_FLAG_PROCESS_MDD_EVENT BIT_ULL(17) -#define I40E_FLAG_PROCESS_VFLR_EVENT BIT_ULL(18) #define I40E_FLAG_SRIOV_ENABLED BIT_ULL(19) #define I40E_FLAG_DCB_ENABLED BIT_ULL(20) #define I40E_FLAG_FD_SB_ENABLED BIT_ULL(21) #define I40E_FLAG_FD_ATR_ENABLED BIT_ULL(22) +#define I40E_FLAG_FD_SB_AUTO_DISABLED BIT_ULL(23) +#define I40E_FLAG_FD_ATR_AUTO_DISABLED BIT_ULL(24) #define I40E_FLAG_PTP BIT_ULL(25) #define I40E_FLAG_MFP_ENABLED BIT_ULL(26) #define I40E_FLAG_UDP_FILTER_SYNC BIT_ULL(27) @@ -348,16 +436,13 @@ struct i40e_pf { #define I40E_FLAG_TRUE_PROMISC_SUPPORT BIT_ULL(51) #define I40E_FLAG_HAVE_CRT_RETIMER BIT_ULL(52) #define I40E_FLAG_PTP_L4_CAPABLE BIT_ULL(53) -#define I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE BIT_ULL(54) +#define I40E_FLAG_CLIENT_RESET BIT_ULL(54) #define I40E_FLAG_TEMP_LINK_POLLING BIT_ULL(55) +#define I40E_FLAG_CLIENT_L2_CHANGE BIT_ULL(56) +#define I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE BIT_ULL(57) +#define I40E_FLAG_LEGACY_RX BIT_ULL(58) - /* tracks features that get auto disabled by errors */ - u64 auto_disable_flags; - -#ifdef I40E_FCOE - struct i40e_fcoe fcoe; - -#endif /* I40E_FCOE */ + struct i40e_client_instance *cinst; bool stat_offsets_loaded; struct i40e_hw_port_stats stats; struct i40e_hw_port_stats stats_offsets; @@ -412,8 +497,6 @@ struct i40e_pf { */ u16 dcbx_cap; - u32 fcoe_hmc_filt_num; - u32 fcoe_hmc_cntx_num; struct i40e_filter_control_settings filter_settings; struct ptp_clock *ptp_clock; @@ -517,7 +600,7 @@ struct i40e_vsi { bool stat_offsets_loaded; u32 current_netdev_flags; - unsigned long state; + DECLARE_BITMAP(state, __I40E_VSI_STATE_SIZE__); #define I40E_VSI_FLAG_FILTER_CHANGED BIT(0) #define I40E_VSI_FLAG_VEB_OWNER BIT(1) unsigned long flags; @@ -533,16 +616,10 @@ struct i40e_vsi { struct rtnl_link_stats64 net_stats_offsets; struct i40e_eth_stats eth_stats; struct i40e_eth_stats eth_stats_offsets; -#ifdef I40E_FCOE - struct i40e_fcoe_stats fcoe_stats; - struct i40e_fcoe_stats fcoe_stats_offsets; - bool fcoe_stat_offsets_loaded; -#endif u32 tx_restart; u32 tx_busy; u64 tx_linearize; u64 tx_force_wb; - u64 tx_lost_interrupt; u32 rx_buf_failed; u32 rx_page_failed; @@ -628,9 +705,6 @@ struct i40e_q_vector { u8 num_ringpairs; /* total number of ring pairs in vector */ -#define I40E_Q_VECTOR_HUNG_DETECT 0 /* Bit Index for hung detection logic */ - unsigned long hung_detected; /* Set/Reset for hung_detection logic */ - cpumask_t affinity_mask; struct irq_affinity_notify affinity_notify; @@ -696,27 +770,49 @@ static inline void i40e_vsi_setup_irqhandler(struct i40e_vsi *vsi, } /** - * i40e_rx_is_programming_status - check for programming status descriptor - * @qw: the first quad word of the program status descriptor + * i40e_get_fd_cnt_all - get the total FD filter space available + * @pf: pointer to the PF struct + **/ +static inline int i40e_get_fd_cnt_all(struct i40e_pf *pf) +{ + return pf->hw.fdir_shared_filter_count + pf->fdir_pf_filter_count; +} + +/** + * i40e_read_fd_input_set - reads value of flow director input set register + * @pf: pointer to the PF struct + * @addr: register addr * - * The value of in the descriptor length field indicate if this - * is a programming status descriptor for flow director or FCoE - * by the value of I40E_RX_PROG_STATUS_DESC_LENGTH, otherwise - * it is a packet descriptor. + * This function reads value of flow director input set register + * specified by 'addr' (which is specific to flow-type) **/ -static inline bool i40e_rx_is_programming_status(u64 qw) +static inline u64 i40e_read_fd_input_set(struct i40e_pf *pf, u16 addr) { - return I40E_RX_PROG_STATUS_DESC_LENGTH == - (qw >> I40E_RX_PROG_STATUS_DESC_LENGTH_SHIFT); + u64 val; + + val = i40e_read_rx_ctl(&pf->hw, I40E_PRTQF_FD_INSET(addr, 1)); + val <<= 32; + val += i40e_read_rx_ctl(&pf->hw, I40E_PRTQF_FD_INSET(addr, 0)); + + return val; } /** - * i40e_get_fd_cnt_all - get the total FD filter space available + * i40e_write_fd_input_set - writes value into flow director input set register * @pf: pointer to the PF struct + * @addr: register addr + * @val: value to be written + * + * This function writes specified value to the register specified by 'addr'. + * This register is input set register based on flow-type. **/ -static inline int i40e_get_fd_cnt_all(struct i40e_pf *pf) +static inline void i40e_write_fd_input_set(struct i40e_pf *pf, + u16 addr, u64 val) { - return pf->hw.fdir_shared_filter_count + pf->fdir_pf_filter_count; + i40e_write_rx_ctl(&pf->hw, I40E_PRTQF_FD_INSET(addr, 1), + (u32)(val >> 32)); + i40e_write_rx_ctl(&pf->hw, I40E_PRTQF_FD_INSET(addr, 0), + (u32)(val & 0xFFFFFFFFULL)); } /* needed by i40e_ethtool.c */ @@ -725,7 +821,7 @@ void i40e_down(struct i40e_vsi *vsi); extern const char i40e_driver_name[]; extern const char i40e_driver_version_str[]; void i40e_do_reset_safe(struct i40e_pf *pf, u32 reset_flags); -void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags); +void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired); int i40e_config_rss(struct i40e_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size); int i40e_get_rss(struct i40e_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size); void i40e_fill_rss_lut(struct i40e_pf *pf, u8 *lut, @@ -773,17 +869,14 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi); struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type, u16 uplink, u32 param1); int i40e_vsi_release(struct i40e_vsi *vsi); -#ifdef I40E_FCOE -void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, - struct i40e_vsi_context *ctxt, - u8 enabled_tc, bool is_add); -#endif void i40e_service_event_schedule(struct i40e_pf *pf); void i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id, u8 *msg, u16 len); int i40e_vsi_start_rings(struct i40e_vsi *vsi); void i40e_vsi_stop_rings(struct i40e_vsi *vsi); +void i40e_vsi_stop_rings_no_wait(struct i40e_vsi *vsi); +int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi); int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count); struct i40e_veb *i40e_veb_setup(struct i40e_pf *pf, u16 flags, u16 uplink_seid, u16 downlink_seid, u8 enabled_tc); @@ -813,8 +906,7 @@ void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi); void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset); void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs); void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id); -int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id, - enum i40e_client_type type); +int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id); /** * i40e_irq_dynamic_enable - Enable default interrupt generation settings * @vsi: pointer to a vsi @@ -838,20 +930,7 @@ static inline void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector) void i40e_irq_dynamic_disable_icr0(struct i40e_pf *pf); void i40e_irq_dynamic_enable_icr0(struct i40e_pf *pf, bool clearpba); -#ifdef I40E_FCOE -void i40e_get_netdev_stats_struct(struct net_device *netdev, - struct rtnl_link_stats64 *storage); -int i40e_set_mac(struct net_device *netdev, void *p); -void i40e_set_rx_mode(struct net_device *netdev); -#endif int i40e_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd); -#ifdef I40E_FCOE -void i40e_tx_timeout(struct net_device *netdev); -int i40e_vlan_rx_add_vid(struct net_device *netdev, - __always_unused __be16 proto, u16 vid); -int i40e_vlan_rx_kill_vid(struct net_device *netdev, - __always_unused __be16 proto, u16 vid); -#endif int i40e_open(struct net_device *netdev); int i40e_close(struct net_device *netdev); int i40e_vsi_open(struct i40e_vsi *vsi); @@ -865,25 +944,6 @@ struct i40e_mac_filter *i40e_add_mac_filter(struct i40e_vsi *vsi, int i40e_del_mac_filter(struct i40e_vsi *vsi, const u8 *macaddr); bool i40e_is_vsi_in_vlan(struct i40e_vsi *vsi); struct i40e_mac_filter *i40e_find_mac(struct i40e_vsi *vsi, const u8 *macaddr); -#ifdef I40E_FCOE -int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto, - struct tc_to_netdev *tc); -void i40e_netpoll(struct net_device *netdev); -int i40e_fcoe_enable(struct net_device *netdev); -int i40e_fcoe_disable(struct net_device *netdev); -int i40e_fcoe_vsi_init(struct i40e_vsi *vsi, struct i40e_vsi_context *ctxt); -u8 i40e_get_fcoe_tc_map(struct i40e_pf *pf); -void i40e_fcoe_config_netdev(struct net_device *netdev, struct i40e_vsi *vsi); -void i40e_fcoe_vsi_setup(struct i40e_pf *pf); -void i40e_init_pf_fcoe(struct i40e_pf *pf); -int i40e_fcoe_setup_ddp_resources(struct i40e_vsi *vsi); -void i40e_fcoe_free_ddp_resources(struct i40e_vsi *vsi); -int i40e_fcoe_handle_offload(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc, - struct sk_buff *skb); -void i40e_fcoe_handle_status(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc, u8 prog_id); -#endif /* I40E_FCOE */ void i40e_vlan_stripping_enable(struct i40e_vsi *vsi); #ifdef CONFIG_I40E_DCB void i40e_dcbnl_flush_apps(struct i40e_pf *pf, diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index 56fb27298936..ba04988e0598 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -850,8 +850,8 @@ i40e_status i40e_asq_send_command(struct i40e_hw *hw, */ if (i40e_asq_done(hw)) break; - usleep_range(1000, 2000); - total_delay++; + udelay(50); + total_delay += 50; } while (total_delay < hw->aq.asq_cmd_timeout); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.h b/drivers/net/ethernet/intel/i40e/i40e_adminq.h index d92aad38afdc..2349fbe04bd2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.h @@ -151,7 +151,7 @@ static inline int i40e_aq_rc_to_posix(int aq_ret, int aq_rc) /* general information */ #define I40E_AQ_LARGE_BUF 512 -#define I40E_ASQ_CMD_TIMEOUT 250 /* msecs */ +#define I40E_ASQ_CMD_TIMEOUT 250000 /* usecs */ void i40e_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, u16 opcode); diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 451f48b7540a..5eb04114e13f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -132,6 +132,10 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_list_func_capabilities = 0x000A, i40e_aqc_opc_list_dev_capabilities = 0x000B, + /* Proxy commands */ + i40e_aqc_opc_set_proxy_config = 0x0104, + i40e_aqc_opc_set_ns_proxy_table_entry = 0x0105, + /* LAA */ i40e_aqc_opc_mac_address_read = 0x0107, i40e_aqc_opc_mac_address_write = 0x0108, @@ -139,6 +143,10 @@ enum i40e_admin_queue_opc { /* PXE */ i40e_aqc_opc_clear_pxe_mode = 0x0110, + /* WoL commands */ + i40e_aqc_opc_set_wol_filter = 0x0120, + i40e_aqc_opc_get_wake_reason = 0x0121, + /* internal switch commands */ i40e_aqc_opc_get_switch_config = 0x0200, i40e_aqc_opc_add_statistics = 0x0201, @@ -177,10 +185,15 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_remove_control_packet_filter = 0x025B, i40e_aqc_opc_add_cloud_filters = 0x025C, i40e_aqc_opc_remove_cloud_filters = 0x025D, + i40e_aqc_opc_clear_wol_switch_filters = 0x025E, i40e_aqc_opc_add_mirror_rule = 0x0260, i40e_aqc_opc_delete_mirror_rule = 0x0261, + /* Pipeline Personalization Profile */ + i40e_aqc_opc_write_personalization_profile = 0x0270, + i40e_aqc_opc_get_personalization_profile_list = 0x0271, + /* DCB commands */ i40e_aqc_opc_dcb_ignore_pfc = 0x0301, i40e_aqc_opc_dcb_updated = 0x0302, @@ -563,6 +576,56 @@ struct i40e_aqc_clear_pxe { I40E_CHECK_CMD_LENGTH(i40e_aqc_clear_pxe); +/* Set WoL Filter (0x0120) */ + +struct i40e_aqc_set_wol_filter { + __le16 filter_index; +#define I40E_AQC_MAX_NUM_WOL_FILTERS 8 +#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT 15 +#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_MASK (0x1 << \ + I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT) + +#define I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT 0 +#define I40E_AQC_SET_WOL_FILTER_INDEX_MASK (0x7 << \ + I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT) + __le16 cmd_flags; +#define I40E_AQC_SET_WOL_FILTER 0x8000 +#define I40E_AQC_SET_WOL_FILTER_NO_TCO_WOL 0x4000 +#define I40E_AQC_SET_WOL_FILTER_ACTION_CLEAR 0 +#define I40E_AQC_SET_WOL_FILTER_ACTION_SET 1 + __le16 valid_flags; +#define I40E_AQC_SET_WOL_FILTER_ACTION_VALID 0x8000 +#define I40E_AQC_SET_WOL_FILTER_NO_TCO_ACTION_VALID 0x4000 + u8 reserved[2]; + __le32 address_high; + __le32 address_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_set_wol_filter); + +struct i40e_aqc_set_wol_filter_data { + u8 filter[128]; + u8 mask[16]; +}; + +I40E_CHECK_STRUCT_LEN(0x90, i40e_aqc_set_wol_filter_data); + +/* Get Wake Reason (0x0121) */ + +struct i40e_aqc_get_wake_reason_completion { + u8 reserved_1[2]; + __le16 wake_reason; +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT 0 +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_MASK (0xFF << \ + I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT) +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT 8 +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_MASK (0xFF << \ + I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT) + u8 reserved_2[12]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_wake_reason_completion); + /* Switch configuration commands (0x02xx) */ /* Used by many indirect commands that only pass an seid and a buffer in the @@ -645,6 +708,8 @@ struct i40e_aqc_set_port_parameters { #define I40E_AQ_SET_P_PARAMS_PAD_SHORT_PACKETS 2 /* must set! */ #define I40E_AQ_SET_P_PARAMS_DOUBLE_VLAN_ENA 4 __le16 bad_frame_vsi; +#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_SHIFT 0x0 +#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_MASK 0x3FF __le16 default_seid; /* reserved for command */ u8 reserved[10]; }; @@ -696,6 +761,7 @@ I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp); /* Set Switch Configuration (direct 0x0205) */ struct i40e_aqc_set_switch_config { __le16 flags; +/* flags used for both fields below */ #define I40E_AQ_SET_SWITCH_CFG_PROMISC 0x0001 #define I40E_AQ_SET_SWITCH_CFG_L2_FILTER 0x0002 __le16 valid_flags; @@ -1369,6 +1435,36 @@ struct i40e_aqc_add_delete_mirror_rule_completion { I40E_CHECK_CMD_LENGTH(i40e_aqc_add_delete_mirror_rule_completion); +/* Pipeline Personalization Profile */ +struct i40e_aqc_write_personalization_profile { + u8 flags; + u8 reserved[3]; + __le32 profile_track_id; + __le32 addr_high; + __le32 addr_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_write_personalization_profile); + +struct i40e_aqc_write_ppp_resp { + __le32 error_offset; + __le32 error_info; + __le32 addr_high; + __le32 addr_low; +}; + +struct i40e_aqc_get_applied_profiles { + u8 flags; +#define I40E_AQC_GET_PPP_GET_CONF 0x1 +#define I40E_AQC_GET_PPP_GET_RDPU_CONF 0x2 + u8 rsv[3]; + __le32 reserved; + __le32 addr_high; + __le32 addr_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_applied_profiles); + /* DCB 0x03xx*/ /* PFC Ignore (direct 0x0301) @@ -1844,11 +1940,12 @@ struct i40e_aqc_get_link_status { #define I40E_AQ_CONFIG_FEC_RS_ENA 0x02 #define I40E_AQ_CONFIG_CRC_ENA 0x04 #define I40E_AQ_CONFIG_PACING_MASK 0x78 - u8 external_power_ability; + u8 power_desc; #define I40E_AQ_LINK_POWER_CLASS_1 0x00 #define I40E_AQ_LINK_POWER_CLASS_2 0x01 #define I40E_AQ_LINK_POWER_CLASS_3 0x02 #define I40E_AQ_LINK_POWER_CLASS_4 0x03 +#define I40E_AQ_PWR_CLASS_MASK 0x03 u8 reserved[4]; }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c index d570219efd9f..c3b81a97558e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.c +++ b/drivers/net/ethernet/intel/i40e/i40e_client.c @@ -32,16 +32,10 @@ #include "i40e_client.h" static const char i40e_client_interface_version_str[] = I40E_CLIENT_VERSION_STR; - +static struct i40e_client *registered_client; static LIST_HEAD(i40e_devices); static DEFINE_MUTEX(i40e_device_mutex); -static LIST_HEAD(i40e_clients); -static DEFINE_MUTEX(i40e_client_mutex); - -static LIST_HEAD(i40e_client_instances); -static DEFINE_MUTEX(i40e_client_instance_mutex); - static int i40e_client_virtchnl_send(struct i40e_info *ldev, struct i40e_client *client, u32 vf_id, u8 *msg, u16 len); @@ -67,28 +61,6 @@ static struct i40e_ops i40e_lan_ops = { }; /** - * i40e_client_type_to_vsi_type - convert client type to vsi type - * @client_type: the i40e_client type - * - * returns the related vsi type value - **/ -static -enum i40e_vsi_type i40e_client_type_to_vsi_type(enum i40e_client_type type) -{ - switch (type) { - case I40E_CLIENT_IWARP: - return I40E_VSI_IWARP; - - case I40E_CLIENT_VMDQ2: - return I40E_VSI_VMDQ2; - - default: - pr_err("i40e: Client type unknown\n"); - return I40E_VSI_TYPE_UNKNOWN; - } -} - -/** * i40e_client_get_params - Get the params that can change at runtime * @vsi: the VSI with the message * @param: clinet param struct @@ -134,31 +106,22 @@ int i40e_client_get_params(struct i40e_vsi *vsi, struct i40e_params *params) void i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id, u8 *msg, u16 len) { - struct i40e_client_instance *cdev; + struct i40e_pf *pf = vsi->back; + struct i40e_client_instance *cdev = pf->cinst; - if (!vsi) + if (!cdev || !cdev->client) + return; + if (!cdev->client->ops || !cdev->client->ops->virtchnl_receive) { + dev_dbg(&pf->pdev->dev, + "Cannot locate client instance virtual channel receive routine\n"); return; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if (cdev->lan_info.pf == vsi->back) { - if (!cdev->client || - !cdev->client->ops || - !cdev->client->ops->virtchnl_receive) { - dev_dbg(&vsi->back->pdev->dev, - "Cannot locate client instance virtual channel receive routine\n"); - continue; - } - if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state)) { - dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort virtchnl_receive\n"); - continue; - } - cdev->client->ops->virtchnl_receive(&cdev->lan_info, - cdev->client, - vf_id, msg, len); - } } - mutex_unlock(&i40e_client_instance_mutex); + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { + dev_dbg(&pf->pdev->dev, "Client is not open, abort virtchnl_receive\n"); + return; + } + cdev->client->ops->virtchnl_receive(&cdev->lan_info, cdev->client, + vf_id, msg, len); } /** @@ -169,39 +132,30 @@ i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id, u8 *msg, u16 len) **/ void i40e_notify_client_of_l2_param_changes(struct i40e_vsi *vsi) { - struct i40e_client_instance *cdev; + struct i40e_pf *pf = vsi->back; + struct i40e_client_instance *cdev = pf->cinst; struct i40e_params params; - if (!vsi) + if (!cdev || !cdev->client) return; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if (cdev->lan_info.pf == vsi->back) { - if (!cdev->client || - !cdev->client->ops || - !cdev->client->ops->l2_param_change) { - dev_dbg(&vsi->back->pdev->dev, - "Cannot locate client instance l2_param_change routine\n"); - continue; - } + if (!cdev->client->ops || !cdev->client->ops->l2_param_change) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance l2_param_change routine\n"); + return; + } + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { + dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort l2 param change\n"); + return; + } memset(¶ms, 0, sizeof(params)); i40e_client_get_params(vsi, ¶ms); - if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state)) { - dev_dbg(&vsi->back->pdev->dev, "Client is not open, abort l2 param change\n"); - continue; - } - cdev->lan_info.params = params; - cdev->client->ops->l2_param_change(&cdev->lan_info, - cdev->client, - ¶ms); - } - } - mutex_unlock(&i40e_client_instance_mutex); + memcpy(&cdev->lan_info.params, ¶ms, sizeof(struct i40e_params)); + cdev->client->ops->l2_param_change(&cdev->lan_info, cdev->client, + ¶ms); } /** - * i40e_client_release_qvlist + * i40e_client_release_qvlist - release MSI-X vector mapping for client * @ldev: pointer to L2 context. * **/ @@ -237,26 +191,19 @@ static void i40e_client_release_qvlist(struct i40e_info *ldev) **/ void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset) { - struct i40e_client_instance *cdev; + struct i40e_pf *pf = vsi->back; + struct i40e_client_instance *cdev = pf->cinst; - if (!vsi) + if (!cdev || !cdev->client) + return; + if (!cdev->client->ops || !cdev->client->ops->close) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance close routine\n"); return; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if (cdev->lan_info.netdev == vsi->netdev) { - if (!cdev->client || - !cdev->client->ops || !cdev->client->ops->close) { - dev_dbg(&vsi->back->pdev->dev, - "Cannot locate client instance close routine\n"); - continue; - } - cdev->client->ops->close(&cdev->lan_info, cdev->client, - reset); - clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); - i40e_client_release_qvlist(&cdev->lan_info); - } } - mutex_unlock(&i40e_client_instance_mutex); + cdev->client->ops->close(&cdev->lan_info, cdev->client, reset); + clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); + i40e_client_release_qvlist(&cdev->lan_info); } /** @@ -268,30 +215,20 @@ void i40e_notify_client_of_netdev_close(struct i40e_vsi *vsi, bool reset) **/ void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id) { - struct i40e_client_instance *cdev; + struct i40e_client_instance *cdev = pf->cinst; - if (!pf) + if (!cdev || !cdev->client) + return; + if (!cdev->client->ops || !cdev->client->ops->vf_reset) { + dev_dbg(&pf->pdev->dev, + "Cannot locate client instance VF reset routine\n"); + return; + } + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { + dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-reset\n"); return; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if (cdev->lan_info.pf == pf) { - if (!cdev->client || - !cdev->client->ops || - !cdev->client->ops->vf_reset) { - dev_dbg(&pf->pdev->dev, - "Cannot locate client instance VF reset routine\n"); - continue; - } - if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state)) { - dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-reset\n"); - continue; - } - cdev->client->ops->vf_reset(&cdev->lan_info, - cdev->client, vf_id); - } } - mutex_unlock(&i40e_client_instance_mutex); + cdev->client->ops->vf_reset(&cdev->lan_info, cdev->client, vf_id); } /** @@ -303,30 +240,21 @@ void i40e_notify_client_of_vf_reset(struct i40e_pf *pf, u32 vf_id) **/ void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs) { - struct i40e_client_instance *cdev; + struct i40e_client_instance *cdev = pf->cinst; - if (!pf) + if (!cdev || !cdev->client) + return; + if (!cdev->client->ops || !cdev->client->ops->vf_enable) { + dev_dbg(&pf->pdev->dev, + "Cannot locate client instance VF enable routine\n"); + return; + } + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, + &cdev->state)) { + dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-enable\n"); return; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if (cdev->lan_info.pf == pf) { - if (!cdev->client || - !cdev->client->ops || - !cdev->client->ops->vf_enable) { - dev_dbg(&pf->pdev->dev, - "Cannot locate client instance VF enable routine\n"); - continue; - } - if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state)) { - dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-enable\n"); - continue; - } - cdev->client->ops->vf_enable(&cdev->lan_info, - cdev->client, num_vfs); - } } - mutex_unlock(&i40e_client_instance_mutex); + cdev->client->ops->vf_enable(&cdev->lan_info, cdev->client, num_vfs); } /** @@ -337,37 +265,25 @@ void i40e_notify_client_of_vf_enable(struct i40e_pf *pf, u32 num_vfs) * If there is a client of the specified type attached to this PF, call * its vf_capable routine **/ -int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id, - enum i40e_client_type type) +int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id) { - struct i40e_client_instance *cdev; + struct i40e_client_instance *cdev = pf->cinst; int capable = false; - if (!pf) - return false; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if (cdev->lan_info.pf == pf) { - if (!cdev->client || - !cdev->client->ops || - !cdev->client->ops->vf_capable || - !(cdev->client->type == type)) { - dev_dbg(&pf->pdev->dev, - "Cannot locate client instance VF capability routine\n"); - continue; - } - if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state)) { - dev_dbg(&pf->pdev->dev, "Client is not open, abort vf-capable\n"); - continue; - } - capable = cdev->client->ops->vf_capable(&cdev->lan_info, - cdev->client, - vf_id); - break; - } + if (!cdev || !cdev->client) + goto out; + if (!cdev->client->ops || !cdev->client->ops->vf_capable) { + dev_info(&pf->pdev->dev, + "Cannot locate client instance VF capability routine\n"); + goto out; } - mutex_unlock(&i40e_client_instance_mutex); + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) + goto out; + + capable = cdev->client->ops->vf_capable(&cdev->lan_info, + cdev->client, + vf_id); +out: return capable; } @@ -377,27 +293,19 @@ int i40e_vf_client_capable(struct i40e_pf *pf, u32 vf_id, * @client: pointer to a client struct in the client list. * @existing: if there was already an existing instance * - * Returns cdev ptr on success or if already exists, NULL on failure **/ -static -struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf, - struct i40e_client *client, - bool *existing) +static void i40e_client_add_instance(struct i40e_pf *pf) { - struct i40e_client_instance *cdev; + struct i40e_client_instance *cdev = NULL; struct netdev_hw_addr *mac = NULL; struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry(cdev, &i40e_client_instances, list) { - if ((cdev->lan_info.pf == pf) && (cdev->client == client)) { - *existing = true; - goto out; - } - } + if (!registered_client || pf->cinst) + return; + cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); if (!cdev) - goto out; + return; cdev->lan_info.pf = (void *)pf; cdev->lan_info.netdev = vsi->netdev; @@ -417,7 +325,7 @@ struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf, if (i40e_client_get_params(vsi, &cdev->lan_info.params)) { kfree(cdev); cdev = NULL; - goto out; + return; } cdev->lan_info.msix_count = pf->num_iwarp_msix; @@ -430,41 +338,20 @@ struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf, else dev_err(&pf->pdev->dev, "MAC address list is empty!\n"); - cdev->client = client; - INIT_LIST_HEAD(&cdev->list); - list_add(&cdev->list, &i40e_client_instances); -out: - mutex_unlock(&i40e_client_instance_mutex); - return cdev; + cdev->client = registered_client; + pf->cinst = cdev; } /** * i40e_client_del_instance - removes a client instance from the list * @pf: pointer to the board struct * - * Returns 0 on success or non-0 on error **/ static -int i40e_client_del_instance(struct i40e_pf *pf, struct i40e_client *client) +void i40e_client_del_instance(struct i40e_pf *pf) { - struct i40e_client_instance *cdev, *tmp; - int ret = -ENODEV; - - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry_safe(cdev, tmp, &i40e_client_instances, list) { - if ((cdev->lan_info.pf != pf) || (cdev->client != client)) - continue; - - dev_info(&pf->pdev->dev, "Deleted instance of Client %s, of dev %d bus=0x%02x func=0x%02x)\n", - client->name, pf->hw.pf_id, - pf->hw.bus.device, pf->hw.bus.func); - list_del(&cdev->list); - kfree(cdev); - ret = 0; - break; - } - mutex_unlock(&i40e_client_instance_mutex); - return ret; + kfree(pf->cinst); + pf->cinst = NULL; } /** @@ -473,67 +360,50 @@ int i40e_client_del_instance(struct i40e_pf *pf, struct i40e_client *client) **/ void i40e_client_subtask(struct i40e_pf *pf) { + struct i40e_client *client = registered_client; struct i40e_client_instance *cdev; - struct i40e_client *client; - bool existing = false; + struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; int ret = 0; if (!(pf->flags & I40E_FLAG_SERVICE_CLIENT_REQUESTED)) return; pf->flags &= ~I40E_FLAG_SERVICE_CLIENT_REQUESTED; + cdev = pf->cinst; /* If we're down or resetting, just bail */ - if (test_bit(__I40E_DOWN, &pf->state) || - test_bit(__I40E_CONFIG_BUSY, &pf->state)) + if (test_bit(__I40E_DOWN, pf->state) || + test_bit(__I40E_CONFIG_BUSY, pf->state)) return; - /* Check client state and instantiate client if client registered */ - mutex_lock(&i40e_client_mutex); - list_for_each_entry(client, &i40e_clients, list) { - /* first check client is registered */ - if (!test_bit(__I40E_CLIENT_REGISTERED, &client->state)) - continue; - - /* Do we also need the LAN VSI to be up, to create instance */ - if (!(client->flags & I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE)) { - /* check if L2 VSI is up, if not we are not ready */ - if (test_bit(__I40E_DOWN, &pf->vsi[pf->lan_vsi]->state)) - continue; - } else { - dev_warn(&pf->pdev->dev, "This client %s is being instantiated at probe\n", - client->name); - } - - /* Add the client instance to the instance list */ - cdev = i40e_client_add_instance(pf, client, &existing); - if (!cdev) - continue; - - if (!existing) { - dev_info(&pf->pdev->dev, "Added instance of Client %s to PF%d bus=0x%02x dev=0x%02x func=0x%02x\n", - client->name, pf->hw.pf_id, - pf->hw.bus.bus_id, pf->hw.bus.device, - pf->hw.bus.func); - } + if (!client || !cdev) + return; - mutex_lock(&i40e_client_instance_mutex); - if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state)) { - /* Send an Open request to the client */ - if (client->ops && client->ops->open) - ret = client->ops->open(&cdev->lan_info, - client); - if (!ret) { - set_bit(__I40E_CLIENT_INSTANCE_OPENED, - &cdev->state); - } else { - /* remove client instance */ - i40e_client_del_instance(pf, client); + /* Here we handle client opens. If the client is down, but + * the netdev is up, then open the client. + */ + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { + if (!test_bit(__I40E_VSI_DOWN, vsi->state) && + client->ops && client->ops->open) { + set_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); + ret = client->ops->open(&cdev->lan_info, client); + if (ret) { + /* Remove failed client instance */ + clear_bit(__I40E_CLIENT_INSTANCE_OPENED, + &cdev->state); + i40e_client_del_instance(pf); } } - mutex_unlock(&i40e_client_instance_mutex); + } else { + /* Likewise for client close. If the client is up, but the netdev + * is down, then close the client. + */ + if (test_bit(__I40E_VSI_DOWN, vsi->state) && + client->ops && client->ops->close) { + clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); + client->ops->close(&cdev->lan_info, client, false); + i40e_client_release_qvlist(&cdev->lan_info); + } } - mutex_unlock(&i40e_client_mutex); } /** @@ -566,6 +436,12 @@ int i40e_lan_add_device(struct i40e_pf *pf) pf->hw.pf_id, pf->hw.bus.bus_id, pf->hw.bus.device, pf->hw.bus.func); + /* If a client has already been registered, we need to add an instance + * of it to our new LAN device. + */ + if (registered_client) + i40e_client_add_instance(pf); + /* Since in some cases register may have happened before a device gets * added, we can schedule a subtask to go initiate the clients if * they can be launched at probe time. @@ -589,6 +465,9 @@ int i40e_lan_del_device(struct i40e_pf *pf) struct i40e_device *ldev, *tmp; int ret = -ENODEV; + /* First, remove any client instance. */ + i40e_client_del_instance(pf); + mutex_lock(&i40e_device_mutex); list_for_each_entry_safe(ldev, tmp, &i40e_devices, list) { if (ldev->pf == pf) { @@ -601,7 +480,6 @@ int i40e_lan_del_device(struct i40e_pf *pf) break; } } - mutex_unlock(&i40e_device_mutex); return ret; } @@ -610,22 +488,24 @@ int i40e_lan_del_device(struct i40e_pf *pf) * i40e_client_release - release client specific resources * @client: pointer to the registered client * - * Return 0 on success or < 0 on error **/ -static int i40e_client_release(struct i40e_client *client) +static void i40e_client_release(struct i40e_client *client) { - struct i40e_client_instance *cdev, *tmp; + struct i40e_client_instance *cdev; + struct i40e_device *ldev; struct i40e_pf *pf; - int ret = 0; - LIST_HEAD(cdevs_tmp); - - mutex_lock(&i40e_client_instance_mutex); - list_for_each_entry_safe(cdev, tmp, &i40e_client_instances, list) { - if (strncmp(cdev->client->name, client->name, - I40E_CLIENT_STR_LENGTH)) + mutex_lock(&i40e_device_mutex); + list_for_each_entry(ldev, &i40e_devices, list) { + pf = ldev->pf; + cdev = pf->cinst; + if (!cdev) continue; - pf = (struct i40e_pf *)cdev->lan_info.pf; + + while (test_and_set_bit(__I40E_SERVICE_SCHED, + pf->state)) + usleep_range(500, 1000); + if (test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { if (client->ops && client->ops->close) client->ops->close(&cdev->lan_info, client, @@ -637,18 +517,13 @@ static int i40e_client_release(struct i40e_client *client) "Client %s instance for PF id %d closed\n", client->name, pf->hw.pf_id); } - /* delete the client instance from the list */ - list_move(&cdev->list, &cdevs_tmp); + /* delete the client instance */ + i40e_client_del_instance(pf); dev_info(&pf->pdev->dev, "Deleted client instance of Client %s\n", client->name); + clear_bit(__I40E_SERVICE_SCHED, pf->state); } - mutex_unlock(&i40e_client_instance_mutex); - - /* free the client device and release its vsi */ - list_for_each_entry_safe(cdev, tmp, &cdevs_tmp, list) { - kfree(cdev); - } - return ret; + mutex_unlock(&i40e_device_mutex); } /** @@ -664,6 +539,7 @@ static void i40e_client_prepare(struct i40e_client *client) mutex_lock(&i40e_device_mutex); list_for_each_entry(ldev, &i40e_devices, list) { pf = ldev->pf; + i40e_client_add_instance(pf); /* Start the client subtask */ pf->flags |= I40E_FLAG_SERVICE_CLIENT_REQUESTED; i40e_service_event_schedule(pf); @@ -785,15 +661,15 @@ static void i40e_client_request_reset(struct i40e_info *ldev, switch (reset_level) { case I40E_CLIENT_RESET_LEVEL_PF: - set_bit(__I40E_PF_RESET_REQUESTED, &pf->state); + set_bit(__I40E_PF_RESET_REQUESTED, pf->state); break; case I40E_CLIENT_RESET_LEVEL_CORE: - set_bit(__I40E_PF_RESET_REQUESTED, &pf->state); + set_bit(__I40E_PF_RESET_REQUESTED, pf->state); break; default: dev_warn(&pf->pdev->dev, - "Client %s instance for PF id %d request an unsupported reset: %d.\n", - client->name, pf->hw.pf_id, reset_level); + "Client for PF id %d requested an unsupported reset: %d.\n", + pf->hw.pf_id, reset_level); break; } @@ -852,8 +728,8 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev, } else { update = false; dev_warn(&pf->pdev->dev, - "Client %s instance for PF id %d request an unsupported Config: %x.\n", - client->name, pf->hw.pf_id, flag); + "Client for PF id %d request an unsupported Config: %x.\n", + pf->hw.pf_id, flag); } if (update) { @@ -878,7 +754,6 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev, int i40e_register_client(struct i40e_client *client) { int ret = 0; - enum i40e_vsi_type vsi_type; if (!client) { ret = -EIO; @@ -891,11 +766,9 @@ int i40e_register_client(struct i40e_client *client) goto out; } - mutex_lock(&i40e_client_mutex); - if (i40e_client_is_registered(client)) { + if (registered_client) { pr_info("i40e: Client %s has already been registered!\n", client->name); - mutex_unlock(&i40e_client_mutex); ret = -EEXIST; goto out; } @@ -908,22 +781,11 @@ int i40e_register_client(struct i40e_client *client) client->version.major, client->version.minor, client->version.build, i40e_client_interface_version_str); - mutex_unlock(&i40e_client_mutex); ret = -EIO; goto out; } - vsi_type = i40e_client_type_to_vsi_type(client->type); - if (vsi_type == I40E_VSI_TYPE_UNKNOWN) { - pr_info("i40e: Failed to register client %s due to unknown client type %d\n", - client->name, client->type); - mutex_unlock(&i40e_client_mutex); - ret = -EIO; - goto out; - } - list_add(&client->list, &i40e_clients); - set_bit(__I40E_CLIENT_REGISTERED, &client->state); - mutex_unlock(&i40e_client_mutex); + registered_client = client; i40e_client_prepare(client); @@ -943,29 +805,21 @@ int i40e_unregister_client(struct i40e_client *client) { int ret = 0; - /* When a unregister request comes through we would have to send - * a close for each of the client instances that were opened. - * client_release function is called to handle this. - */ - mutex_lock(&i40e_client_mutex); - if (!client || i40e_client_release(client)) { - ret = -EIO; - goto out; - } - - /* TODO: check if device is in reset, or if that matters? */ - if (!i40e_client_is_registered(client)) { + if (registered_client != client) { pr_info("i40e: Client %s has not been registered\n", client->name); ret = -ENODEV; goto out; } - clear_bit(__I40E_CLIENT_REGISTERED, &client->state); - list_del(&client->list); - pr_info("i40e: Unregistered client %s with return code %d\n", - client->name, ret); + registered_client = NULL; + /* When a unregister request comes through we would have to send + * a close for each of the client instances that were opened. + * client_release function is called to handle this. + */ + i40e_client_release(client); + + pr_info("i40e: Unregistered client %s\n", client->name); out: - mutex_unlock(&i40e_client_mutex); return ret; } EXPORT_SYMBOL(i40e_unregister_client); diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.h b/drivers/net/ethernet/intel/i40e/i40e_client.h index 528bd79b05fe..15b21a5315b5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.h +++ b/drivers/net/ethernet/intel/i40e/i40e_client.h @@ -57,11 +57,6 @@ enum i40e_client_instance_state { __I40E_CLIENT_INSTANCE_OPENED, }; -enum i40e_client_type { - I40E_CLIENT_IWARP, - I40E_CLIENT_VMDQ2 -}; - struct i40e_ops; struct i40e_client; @@ -214,7 +209,8 @@ struct i40e_client { u32 flags; #define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE BIT(0) #define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS BIT(2) - enum i40e_client_type type; + u8 type; +#define I40E_CLIENT_IWARP 0 const struct i40e_client_ops *ops; /* client ops provided by the client */ }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index ece57d6a6e23..24f020655291 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1088,33 +1088,6 @@ void i40e_pre_tx_queue_cfg(struct i40e_hw *hw, u32 queue, bool enable) wr32(hw, I40E_GLLAN_TXPRE_QDIS(reg_block), reg_val); } -#ifdef I40E_FCOE - -/** - * i40e_get_san_mac_addr - get SAN MAC address - * @hw: pointer to the HW structure - * @mac_addr: pointer to SAN MAC address - * - * Reads the adapter's SAN MAC address from NVM - **/ -i40e_status i40e_get_san_mac_addr(struct i40e_hw *hw, u8 *mac_addr) -{ - struct i40e_aqc_mac_address_read_data addrs; - i40e_status status; - u16 flags = 0; - - status = i40e_aq_mac_address_read(hw, &flags, &addrs, NULL); - if (status) - return status; - - if (flags & I40E_AQC_SAN_ADDR_VALID) - ether_addr_copy(mac_addr, addrs.pf_san_mac); - else - status = I40E_ERR_INVALID_MAC_ADDR; - - return status; -} -#endif /** * i40e_read_pba_string - Reads part number string from EEPROM @@ -4990,7 +4963,9 @@ u32 i40e_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr) int retry = 5; u32 val = 0; - use_register = (hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver < 5); + use_register = (((hw->aq.api_maj_ver == 1) && + (hw->aq.api_min_ver < 5)) || + (hw->mac.type == I40E_MAC_X722)); if (!use_register) { do_retry: status = i40e_aq_rx_ctl_read_register(hw, reg_addr, &val, NULL); @@ -5049,7 +5024,9 @@ void i40e_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val) bool use_register; int retry = 5; - use_register = (hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver < 5); + use_register = (((hw->aq.api_maj_ver == 1) && + (hw->aq.api_min_ver < 5)) || + (hw->mac.type == I40E_MAC_X722)); if (!use_register) { do_retry: status = i40e_aq_rx_ctl_write_register(hw, reg_addr, @@ -5065,3 +5042,215 @@ do_retry: if (status || use_register) wr32(hw, reg_addr, reg_val); } + +/** + * i40e_aq_write_ppp - Write pipeline personalization profile (ppp) + * @hw: pointer to the hw struct + * @buff: command buffer (size in bytes = buff_size) + * @buff_size: buffer size in bytes + * @track_id: package tracking id + * @error_offset: returns error offset + * @error_info: returns error information + * @cmd_details: pointer to command details structure or NULL + **/ +enum +i40e_status_code i40e_aq_write_ppp(struct i40e_hw *hw, void *buff, + u16 buff_size, u32 track_id, + u32 *error_offset, u32 *error_info, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_write_personalization_profile *cmd = + (struct i40e_aqc_write_personalization_profile *) + &desc.params.raw; + struct i40e_aqc_write_ppp_resp *resp; + i40e_status status; + + i40e_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_write_personalization_profile); + + desc.flags |= cpu_to_le16(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD); + if (buff_size > I40E_AQ_LARGE_BUF) + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); + + desc.datalen = cpu_to_le16(buff_size); + + cmd->profile_track_id = cpu_to_le32(track_id); + + status = i40e_asq_send_command(hw, &desc, buff, buff_size, cmd_details); + if (!status) { + resp = (struct i40e_aqc_write_ppp_resp *)&desc.params.raw; + if (error_offset) + *error_offset = le32_to_cpu(resp->error_offset); + if (error_info) + *error_info = le32_to_cpu(resp->error_info); + } + + return status; +} + +/** + * i40e_aq_get_ppp_list - Read pipeline personalization profile (ppp) + * @hw: pointer to the hw struct + * @buff: command buffer (size in bytes = buff_size) + * @buff_size: buffer size in bytes + * @cmd_details: pointer to command details structure or NULL + **/ +enum +i40e_status_code i40e_aq_get_ppp_list(struct i40e_hw *hw, void *buff, + u16 buff_size, u8 flags, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_get_applied_profiles *cmd = + (struct i40e_aqc_get_applied_profiles *)&desc.params.raw; + i40e_status status; + + i40e_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_get_personalization_profile_list); + + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); + if (buff_size > I40E_AQ_LARGE_BUF) + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); + desc.datalen = cpu_to_le16(buff_size); + + cmd->flags = flags; + + status = i40e_asq_send_command(hw, &desc, buff, buff_size, cmd_details); + + return status; +} + +/** + * i40e_find_segment_in_package + * @segment_type: the segment type to search for (i.e., SEGMENT_TYPE_I40E) + * @pkg_hdr: pointer to the package header to be searched + * + * This function searches a package file for a particular segment type. On + * success it returns a pointer to the segment header, otherwise it will + * return NULL. + **/ +struct i40e_generic_seg_header * +i40e_find_segment_in_package(u32 segment_type, + struct i40e_package_header *pkg_hdr) +{ + struct i40e_generic_seg_header *segment; + u32 i; + + /* Search all package segments for the requested segment type */ + for (i = 0; i < pkg_hdr->segment_count; i++) { + segment = + (struct i40e_generic_seg_header *)((u8 *)pkg_hdr + + pkg_hdr->segment_offset[i]); + + if (segment->type == segment_type) + return segment; + } + + return NULL; +} + +/** + * i40e_write_profile + * @hw: pointer to the hardware structure + * @profile: pointer to the profile segment of the package to be downloaded + * @track_id: package tracking id + * + * Handles the download of a complete package. + */ +enum i40e_status_code +i40e_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile, + u32 track_id) +{ + i40e_status status = 0; + struct i40e_section_table *sec_tbl; + struct i40e_profile_section_header *sec = NULL; + u32 dev_cnt; + u32 vendor_dev_id; + u32 *nvm; + u32 section_size = 0; + u32 offset = 0, info = 0; + u32 i; + + if (!track_id) { + i40e_debug(hw, I40E_DEBUG_PACKAGE, "Track_id can't be 0."); + return I40E_NOT_SUPPORTED; + } + + dev_cnt = profile->device_table_count; + + for (i = 0; i < dev_cnt; i++) { + vendor_dev_id = profile->device_table[i].vendor_dev_id; + if ((vendor_dev_id >> 16) == PCI_VENDOR_ID_INTEL) + if (hw->device_id == (vendor_dev_id & 0xFFFF)) + break; + } + if (i == dev_cnt) { + i40e_debug(hw, I40E_DEBUG_PACKAGE, "Device doesn't support PPP"); + return I40E_ERR_DEVICE_NOT_SUPPORTED; + } + + nvm = (u32 *)&profile->device_table[dev_cnt]; + sec_tbl = (struct i40e_section_table *)&nvm[nvm[0] + 1]; + + for (i = 0; i < sec_tbl->section_count; i++) { + sec = (struct i40e_profile_section_header *)((u8 *)profile + + sec_tbl->section_offset[i]); + + /* Skip 'AQ', 'note' and 'name' sections */ + if (sec->section.type != SECTION_TYPE_MMIO) + continue; + + section_size = sec->section.size + + sizeof(struct i40e_profile_section_header); + + /* Write profile */ + status = i40e_aq_write_ppp(hw, (void *)sec, (u16)section_size, + track_id, &offset, &info, NULL); + if (status) { + i40e_debug(hw, I40E_DEBUG_PACKAGE, + "Failed to write profile: offset %d, info %d", + offset, info); + break; + } + } + return status; +} + +/** + * i40e_add_pinfo_to_list + * @hw: pointer to the hardware structure + * @profile: pointer to the profile segment of the package + * @profile_info_sec: buffer for information section + * @track_id: package tracking id + * + * Register a profile to the list of loaded profiles. + */ +enum i40e_status_code +i40e_add_pinfo_to_list(struct i40e_hw *hw, + struct i40e_profile_segment *profile, + u8 *profile_info_sec, u32 track_id) +{ + i40e_status status = 0; + struct i40e_profile_section_header *sec = NULL; + struct i40e_profile_info *pinfo; + u32 offset = 0, info = 0; + + sec = (struct i40e_profile_section_header *)profile_info_sec; + sec->tbl_size = 1; + sec->data_end = sizeof(struct i40e_profile_section_header) + + sizeof(struct i40e_profile_info); + sec->section.type = SECTION_TYPE_INFO; + sec->section.offset = sizeof(struct i40e_profile_section_header); + sec->section.size = sizeof(struct i40e_profile_info); + pinfo = (struct i40e_profile_info *)(profile_info_sec + + sec->section.offset); + pinfo->track_id = track_id; + pinfo->version = profile->version; + pinfo->op = I40E_PPP_ADD_TRACKID; + memcpy(pinfo->name, profile->name, I40E_PPP_NAME_SIZE); + + status = i40e_aq_write_ppp(hw, (void *)sec, sec->data_end, + track_id, &offset, &info, NULL); + return status; +} diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 267ad2588255..8f326f87a815 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -158,9 +158,12 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) dev_info(&pf->pdev->dev, " vlgrp: & = %p\n", vsi->active_vlans); dev_info(&pf->pdev->dev, - " state = %li flags = 0x%08lx, netdev_registered = %i, current_netdev_flags = 0x%04x\n", - vsi->state, vsi->flags, - vsi->netdev_registered, vsi->current_netdev_flags); + " flags = 0x%08lx, netdev_registered = %i, current_netdev_flags = 0x%04x\n", + vsi->flags, vsi->netdev_registered, vsi->current_netdev_flags); + for (i = 0; i < BITS_TO_LONGS(__I40E_VSI_STATE_SIZE__); i++) + dev_info(&pf->pdev->dev, + " state[%d] = %08lx\n", + i, vsi->state[i]); if (vsi == pf->vsi[pf->lan_vsi]) dev_info(&pf->pdev->dev, " MAC address: %pM SAN MAC: %pM Port MAC: %pM\n", pf->hw.mac.addr, @@ -174,7 +177,7 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) } dev_info(&pf->pdev->dev, " active_filters %u, promisc_threshold %u, overflow promisc %s\n", vsi->active_filters, vsi->promisc_threshold, - (test_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state) ? + (test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state) ? "ON" : "OFF")); nstat = i40e_get_vsi_stats_struct(vsi); dev_info(&pf->pdev->dev, @@ -384,6 +387,8 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) " base_queue = %d, num_queue_pairs = %d, num_desc = %d\n", vsi->base_queue, vsi->num_queue_pairs, vsi->num_desc); dev_info(&pf->pdev->dev, " type = %i\n", vsi->type); + if (vsi->type == I40E_VSI_SRIOV) + dev_info(&pf->pdev->dev, " VF ID = %i\n", vsi->vf_id); dev_info(&pf->pdev->dev, " info: valid_sections = 0x%04x, switch_id = 0x%04x\n", vsi->info.valid_sections, vsi->info.switch_id); @@ -484,25 +489,6 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) vsi->bw_ets_limit_credits[i], vsi->bw_ets_max_quanta[i]); } -#ifdef I40E_FCOE - if (vsi->type == I40E_VSI_FCOE) { - dev_info(&pf->pdev->dev, - " fcoe_stats: rx_packets = %llu, rx_dwords = %llu, rx_dropped = %llu\n", - vsi->fcoe_stats.rx_fcoe_packets, - vsi->fcoe_stats.rx_fcoe_dwords, - vsi->fcoe_stats.rx_fcoe_dropped); - dev_info(&pf->pdev->dev, - " fcoe_stats: tx_packets = %llu, tx_dwords = %llu\n", - vsi->fcoe_stats.tx_fcoe_packets, - vsi->fcoe_stats.tx_fcoe_dwords); - dev_info(&pf->pdev->dev, - " fcoe_stats: bad_crc = %llu, last_error = %llu\n", - vsi->fcoe_stats.fcoe_bad_fccrc, - vsi->fcoe_stats.fcoe_last_error); - dev_info(&pf->pdev->dev, " fcoe_stats: ddp_count = %llu\n", - vsi->fcoe_stats.fcoe_ddp_count); - } -#endif } /** @@ -713,6 +699,47 @@ static void i40e_dbg_dump_veb_all(struct i40e_pf *pf) } } +/** + * i40e_dbg_dump_vf - dump VF info + * @pf: the i40e_pf created in command write + * @vf_id: the vf_id from the user + **/ +static void i40e_dbg_dump_vf(struct i40e_pf *pf, int vf_id) +{ + struct i40e_vf *vf; + struct i40e_vsi *vsi; + + if (!pf->num_alloc_vfs) { + dev_info(&pf->pdev->dev, "no VFs allocated\n"); + } else if ((vf_id >= 0) && (vf_id < pf->num_alloc_vfs)) { + vf = &pf->vf[vf_id]; + vsi = pf->vsi[vf->lan_vsi_idx]; + dev_info(&pf->pdev->dev, "vf %2d: VSI id=%d, seid=%d, qps=%d\n", + vf_id, vf->lan_vsi_id, vsi->seid, vf->num_queue_pairs); + dev_info(&pf->pdev->dev, " num MDD=%lld, invalid msg=%lld, valid msg=%lld\n", + vf->num_mdd_events, + vf->num_invalid_msgs, + vf->num_valid_msgs); + } else { + dev_info(&pf->pdev->dev, "invalid VF id %d\n", vf_id); + } +} + +/** + * i40e_dbg_dump_vf_all - dump VF info for all VFs + * @pf: the i40e_pf created in command write + **/ +static void i40e_dbg_dump_vf_all(struct i40e_pf *pf) +{ + int i; + + if (!pf->num_alloc_vfs) + dev_info(&pf->pdev->dev, "no VFs enabled!\n"); + else + for (i = 0; i < pf->num_alloc_vfs; i++) + i40e_dbg_dump_vf(pf, i); +} + #define I40E_MAX_DEBUG_OUT_BUFFER (4096*4) /** * i40e_dbg_command_write - write into command datum @@ -731,6 +758,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp, struct i40e_vsi *vsi; int vsi_seid; int veb_seid; + int vf_id; int cnt; /* don't allow partial writes */ @@ -933,6 +961,12 @@ static ssize_t i40e_dbg_command_write(struct file *filp, i40e_dbg_dump_veb_seid(pf, vsi_seid); else i40e_dbg_dump_veb_all(pf); + } else if (strncmp(&cmd_buf[5], "vf", 2) == 0) { + cnt = sscanf(&cmd_buf[7], "%i", &vf_id); + if (cnt > 0) + i40e_dbg_dump_vf(pf, vf_id); + else + i40e_dbg_dump_vf_all(pf); } else if (strncmp(&cmd_buf[5], "desc", 4) == 0) { int ring_id, desc_n; if (strncmp(&cmd_buf[10], "rx", 2) == 0) { @@ -1128,6 +1162,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp, dev_info(&pf->pdev->dev, "dump vsi [seid]\n"); dev_info(&pf->pdev->dev, "dump reset stats\n"); dev_info(&pf->pdev->dev, "dump port\n"); + dev_info(&pf->pdev->dev, "dump vf [vf_id]\n"); dev_info(&pf->pdev->dev, "dump debug fwdata <cluster_id> <table_id> <index>\n"); } @@ -1674,7 +1709,7 @@ static ssize_t i40e_dbg_netdev_ops_write(struct file *filp, } else if (!vsi->netdev) { dev_info(&pf->pdev->dev, "tx_timeout: no netdev for VSI %d\n", vsi_seid); - } else if (test_bit(__I40E_DOWN, &vsi->state)) { + } else if (test_bit(__I40E_VSI_DOWN, vsi->state)) { dev_info(&pf->pdev->dev, "tx_timeout: VSI %d not UP\n", vsi_seid); } else if (rtnl_trylock()) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index a22e26200bcc..7a8eb486b9ea 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -89,7 +89,6 @@ static const struct i40e_stats i40e_gstrings_misc_stats[] = { I40E_VSI_STAT("rx_unknown_protocol", eth_stats.rx_unknown_protocol), I40E_VSI_STAT("tx_linearize", tx_linearize), I40E_VSI_STAT("tx_force_wb", tx_force_wb), - I40E_VSI_STAT("tx_lost_interrupt", tx_lost_interrupt), I40E_VSI_STAT("rx_alloc_fail", rx_buf_failed), I40E_VSI_STAT("rx_pg_alloc_fail", rx_page_failed), }; @@ -162,19 +161,6 @@ static const struct i40e_stats i40e_gstrings_stats[] = { I40E_PF_STAT("rx_lpi_count", stats.rx_lpi_count), }; -#ifdef I40E_FCOE -static const struct i40e_stats i40e_gstrings_fcoe_stats[] = { - I40E_VSI_STAT("fcoe_bad_fccrc", fcoe_stats.fcoe_bad_fccrc), - I40E_VSI_STAT("rx_fcoe_dropped", fcoe_stats.rx_fcoe_dropped), - I40E_VSI_STAT("rx_fcoe_packets", fcoe_stats.rx_fcoe_packets), - I40E_VSI_STAT("rx_fcoe_dwords", fcoe_stats.rx_fcoe_dwords), - I40E_VSI_STAT("fcoe_ddp_count", fcoe_stats.fcoe_ddp_count), - I40E_VSI_STAT("fcoe_last_error", fcoe_stats.fcoe_last_error), - I40E_VSI_STAT("tx_fcoe_packets", fcoe_stats.tx_fcoe_packets), - I40E_VSI_STAT("tx_fcoe_dwords", fcoe_stats.tx_fcoe_dwords), -}; - -#endif /* I40E_FCOE */ #define I40E_QUEUE_STATS_LEN(n) \ (((struct i40e_netdev_priv *)netdev_priv((n)))->vsi->num_queue_pairs \ * 2 /* Tx and Rx together */ \ @@ -182,17 +168,9 @@ static const struct i40e_stats i40e_gstrings_fcoe_stats[] = { #define I40E_GLOBAL_STATS_LEN ARRAY_SIZE(i40e_gstrings_stats) #define I40E_NETDEV_STATS_LEN ARRAY_SIZE(i40e_gstrings_net_stats) #define I40E_MISC_STATS_LEN ARRAY_SIZE(i40e_gstrings_misc_stats) -#ifdef I40E_FCOE -#define I40E_FCOE_STATS_LEN ARRAY_SIZE(i40e_gstrings_fcoe_stats) -#define I40E_VSI_STATS_LEN(n) (I40E_NETDEV_STATS_LEN + \ - I40E_FCOE_STATS_LEN + \ - I40E_MISC_STATS_LEN + \ - I40E_QUEUE_STATS_LEN((n))) -#else #define I40E_VSI_STATS_LEN(n) (I40E_NETDEV_STATS_LEN + \ I40E_MISC_STATS_LEN + \ I40E_QUEUE_STATS_LEN((n))) -#endif /* I40E_FCOE */ #define I40E_PFC_STATS_LEN ( \ (FIELD_SIZEOF(struct i40e_pf, stats.priority_xoff_rx) + \ FIELD_SIZEOF(struct i40e_pf, stats.priority_xon_rx) + \ @@ -228,22 +206,37 @@ static const char i40e_gstrings_test[][ETH_GSTRING_LEN] = { #define I40E_TEST_LEN (sizeof(i40e_gstrings_test) / ETH_GSTRING_LEN) -static const char i40e_priv_flags_strings[][ETH_GSTRING_LEN] = { - "MFP", - "LinkPolling", - "flow-director-atr", - "veb-stats", - "hw-atr-eviction", +struct i40e_priv_flags { + char flag_string[ETH_GSTRING_LEN]; + u64 flag; + bool read_only; }; -#define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_priv_flags_strings) +#define I40E_PRIV_FLAG(_name, _flag, _read_only) { \ + .flag_string = _name, \ + .flag = _flag, \ + .read_only = _read_only, \ +} + +static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = { + /* NOTE: MFP setting cannot be changed */ + I40E_PRIV_FLAG("MFP", I40E_FLAG_MFP_ENABLED, 1), + I40E_PRIV_FLAG("LinkPolling", I40E_FLAG_LINK_POLLING_ENABLED, 0), + I40E_PRIV_FLAG("flow-director-atr", I40E_FLAG_FD_ATR_ENABLED, 0), + I40E_PRIV_FLAG("veb-stats", I40E_FLAG_VEB_STATS_ENABLED, 0), + I40E_PRIV_FLAG("hw-atr-eviction", I40E_FLAG_HW_ATR_EVICT_CAPABLE, 0), + I40E_PRIV_FLAG("legacy-rx", I40E_FLAG_LEGACY_RX, 0), +}; + +#define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags) /* Private flags with a global effect, restricted to PF 0 */ -static const char i40e_gl_priv_flags_strings[][ETH_GSTRING_LEN] = { - "vf-true-promisc-support", +static const struct i40e_priv_flags i40e_gl_gstrings_priv_flags[] = { + I40E_PRIV_FLAG("vf-true-promisc-support", + I40E_FLAG_TRUE_PROMISC_SUPPORT, 0), }; -#define I40E_GL_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gl_priv_flags_strings) +#define I40E_GL_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gl_gstrings_priv_flags) /** * i40e_partition_setting_complaint - generic complaint for MFP restriction @@ -387,7 +380,7 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported, * **/ static void i40e_get_settings_link_up(struct i40e_hw *hw, - struct ethtool_cmd *ecmd, + struct ethtool_link_ksettings *cmd, struct net_device *netdev, struct i40e_pf *pf) { @@ -395,90 +388,96 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, u32 link_speed = hw_link_info->link_speed; u32 e_advertising = 0x0; u32 e_supported = 0x0; + u32 supported, advertising; + + ethtool_convert_link_mode_to_legacy_u32(&supported, + cmd->link_modes.supported); + ethtool_convert_link_mode_to_legacy_u32(&advertising, + cmd->link_modes.advertising); /* Initialize supported and advertised settings based on phy settings */ switch (hw_link_info->phy_type) { case I40E_PHY_TYPE_40GBASE_CR4: case I40E_PHY_TYPE_40GBASE_CR4_CU: - ecmd->supported = SUPPORTED_Autoneg | - SUPPORTED_40000baseCR4_Full; - ecmd->advertising = ADVERTISED_Autoneg | - ADVERTISED_40000baseCR4_Full; + supported = SUPPORTED_Autoneg | + SUPPORTED_40000baseCR4_Full; + advertising = ADVERTISED_Autoneg | + ADVERTISED_40000baseCR4_Full; break; case I40E_PHY_TYPE_XLAUI: case I40E_PHY_TYPE_XLPPI: case I40E_PHY_TYPE_40GBASE_AOC: - ecmd->supported = SUPPORTED_40000baseCR4_Full; + supported = SUPPORTED_40000baseCR4_Full; break; case I40E_PHY_TYPE_40GBASE_SR4: - ecmd->supported = SUPPORTED_40000baseSR4_Full; + supported = SUPPORTED_40000baseSR4_Full; break; case I40E_PHY_TYPE_40GBASE_LR4: - ecmd->supported = SUPPORTED_40000baseLR4_Full; + supported = SUPPORTED_40000baseLR4_Full; break; case I40E_PHY_TYPE_10GBASE_SR: case I40E_PHY_TYPE_10GBASE_LR: case I40E_PHY_TYPE_1000BASE_SX: case I40E_PHY_TYPE_1000BASE_LX: - ecmd->supported = SUPPORTED_10000baseT_Full; + supported = SUPPORTED_10000baseT_Full; if (hw_link_info->module_type[2] & I40E_MODULE_TYPE_1000BASE_SX || hw_link_info->module_type[2] & I40E_MODULE_TYPE_1000BASE_LX) { - ecmd->supported |= SUPPORTED_1000baseT_Full; + supported |= SUPPORTED_1000baseT_Full; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - ecmd->advertising |= ADVERTISED_1000baseT_Full; + advertising |= ADVERTISED_1000baseT_Full; } if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) - ecmd->advertising |= ADVERTISED_10000baseT_Full; + advertising |= ADVERTISED_10000baseT_Full; break; case I40E_PHY_TYPE_10GBASE_T: case I40E_PHY_TYPE_1000BASE_T: case I40E_PHY_TYPE_100BASE_TX: - ecmd->supported = SUPPORTED_Autoneg | - SUPPORTED_10000baseT_Full | - SUPPORTED_1000baseT_Full | - SUPPORTED_100baseT_Full; - ecmd->advertising = ADVERTISED_Autoneg; + supported = SUPPORTED_Autoneg | + SUPPORTED_10000baseT_Full | + SUPPORTED_1000baseT_Full | + SUPPORTED_100baseT_Full; + advertising = ADVERTISED_Autoneg; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) - ecmd->advertising |= ADVERTISED_10000baseT_Full; + advertising |= ADVERTISED_10000baseT_Full; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - ecmd->advertising |= ADVERTISED_1000baseT_Full; + advertising |= ADVERTISED_1000baseT_Full; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB) - ecmd->advertising |= ADVERTISED_100baseT_Full; + advertising |= ADVERTISED_100baseT_Full; break; case I40E_PHY_TYPE_1000BASE_T_OPTICAL: - ecmd->supported = SUPPORTED_Autoneg | - SUPPORTED_1000baseT_Full; - ecmd->advertising = ADVERTISED_Autoneg | - ADVERTISED_1000baseT_Full; + supported = SUPPORTED_Autoneg | + SUPPORTED_1000baseT_Full; + advertising = ADVERTISED_Autoneg | + ADVERTISED_1000baseT_Full; break; case I40E_PHY_TYPE_10GBASE_CR1_CU: case I40E_PHY_TYPE_10GBASE_CR1: - ecmd->supported = SUPPORTED_Autoneg | - SUPPORTED_10000baseT_Full; - ecmd->advertising = ADVERTISED_Autoneg | - ADVERTISED_10000baseT_Full; + supported = SUPPORTED_Autoneg | + SUPPORTED_10000baseT_Full; + advertising = ADVERTISED_Autoneg | + ADVERTISED_10000baseT_Full; break; case I40E_PHY_TYPE_XAUI: case I40E_PHY_TYPE_XFI: case I40E_PHY_TYPE_SFI: case I40E_PHY_TYPE_10GBASE_SFPP_CU: case I40E_PHY_TYPE_10GBASE_AOC: - ecmd->supported = SUPPORTED_10000baseT_Full; - ecmd->advertising = SUPPORTED_10000baseT_Full; + supported = SUPPORTED_10000baseT_Full; + advertising = SUPPORTED_10000baseT_Full; break; case I40E_PHY_TYPE_SGMII: - ecmd->supported = SUPPORTED_Autoneg | - SUPPORTED_1000baseT_Full; + supported = SUPPORTED_Autoneg | + SUPPORTED_1000baseT_Full; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - ecmd->advertising |= ADVERTISED_1000baseT_Full; + advertising |= ADVERTISED_1000baseT_Full; if (pf->flags & I40E_FLAG_100M_SGMII_CAPABLE) { - ecmd->supported |= SUPPORTED_100baseT_Full; + supported |= SUPPORTED_100baseT_Full; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB) - ecmd->advertising |= ADVERTISED_100baseT_Full; + advertising |= ADVERTISED_100baseT_Full; } break; case I40E_PHY_TYPE_40GBASE_KR4: @@ -486,25 +485,25 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, case I40E_PHY_TYPE_10GBASE_KR: case I40E_PHY_TYPE_10GBASE_KX4: case I40E_PHY_TYPE_1000BASE_KX: - ecmd->supported |= SUPPORTED_40000baseKR4_Full | - SUPPORTED_20000baseKR2_Full | - SUPPORTED_10000baseKR_Full | - SUPPORTED_10000baseKX4_Full | - SUPPORTED_1000baseKX_Full | - SUPPORTED_Autoneg; - ecmd->advertising |= ADVERTISED_40000baseKR4_Full | - ADVERTISED_20000baseKR2_Full | - ADVERTISED_10000baseKR_Full | - ADVERTISED_10000baseKX4_Full | - ADVERTISED_1000baseKX_Full | - ADVERTISED_Autoneg; + supported |= SUPPORTED_40000baseKR4_Full | + SUPPORTED_20000baseKR2_Full | + SUPPORTED_10000baseKR_Full | + SUPPORTED_10000baseKX4_Full | + SUPPORTED_1000baseKX_Full | + SUPPORTED_Autoneg; + advertising |= ADVERTISED_40000baseKR4_Full | + ADVERTISED_20000baseKR2_Full | + ADVERTISED_10000baseKR_Full | + ADVERTISED_10000baseKX4_Full | + ADVERTISED_1000baseKX_Full | + ADVERTISED_Autoneg; break; case I40E_PHY_TYPE_25GBASE_KR: case I40E_PHY_TYPE_25GBASE_CR: case I40E_PHY_TYPE_25GBASE_SR: case I40E_PHY_TYPE_25GBASE_LR: - ecmd->supported = SUPPORTED_Autoneg; - ecmd->advertising = ADVERTISED_Autoneg; + supported = SUPPORTED_Autoneg; + advertising = ADVERTISED_Autoneg; /* TODO: add speeds when ethtool is ready to support*/ break; default: @@ -520,38 +519,43 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, i40e_phy_type_to_ethtool(pf, &e_supported, &e_advertising); - ecmd->supported = ecmd->supported & e_supported; - ecmd->advertising = ecmd->advertising & e_advertising; + supported = supported & e_supported; + advertising = advertising & e_advertising; /* Set speed and duplex */ switch (link_speed) { case I40E_LINK_SPEED_40GB: - ethtool_cmd_speed_set(ecmd, SPEED_40000); + cmd->base.speed = SPEED_40000; break; case I40E_LINK_SPEED_25GB: #ifdef SPEED_25000 - ethtool_cmd_speed_set(ecmd, SPEED_25000); + cmd->base.speed = SPEED_25000; #else netdev_info(netdev, "Speed is 25G, display not supported by this version of ethtool.\n"); #endif break; case I40E_LINK_SPEED_20GB: - ethtool_cmd_speed_set(ecmd, SPEED_20000); + cmd->base.speed = SPEED_20000; break; case I40E_LINK_SPEED_10GB: - ethtool_cmd_speed_set(ecmd, SPEED_10000); + cmd->base.speed = SPEED_10000; break; case I40E_LINK_SPEED_1GB: - ethtool_cmd_speed_set(ecmd, SPEED_1000); + cmd->base.speed = SPEED_1000; break; case I40E_LINK_SPEED_100MB: - ethtool_cmd_speed_set(ecmd, SPEED_100); + cmd->base.speed = SPEED_100; break; default: break; } - ecmd->duplex = DUPLEX_FULL; + cmd->base.duplex = DUPLEX_FULL; + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); } /** @@ -562,18 +566,24 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, * Reports link settings that can be determined when link is down **/ static void i40e_get_settings_link_down(struct i40e_hw *hw, - struct ethtool_cmd *ecmd, + struct ethtool_link_ksettings *cmd, struct i40e_pf *pf) { + u32 supported, advertising; + /* link is down and the driver needs to fall back on * supported phy types to figure out what info to display */ - i40e_phy_type_to_ethtool(pf, &ecmd->supported, - &ecmd->advertising); + i40e_phy_type_to_ethtool(pf, &supported, &advertising); + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); /* With no link speed and duplex are unknown */ - ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN); - ecmd->duplex = DUPLEX_UNKNOWN; + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; } /** @@ -583,74 +593,85 @@ static void i40e_get_settings_link_down(struct i40e_hw *hw, * * Reports speed/duplex settings based on media_type **/ -static int i40e_get_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int i40e_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_pf *pf = np->vsi->back; struct i40e_hw *hw = &pf->hw; struct i40e_link_status *hw_link_info = &hw->phy.link_info; bool link_up = hw_link_info->link_info & I40E_AQ_LINK_UP; + u32 advertising; if (link_up) - i40e_get_settings_link_up(hw, ecmd, netdev, pf); + i40e_get_settings_link_up(hw, cmd, netdev, pf); else - i40e_get_settings_link_down(hw, ecmd, pf); + i40e_get_settings_link_down(hw, cmd, pf); /* Now set the settings that don't rely on link being up/down */ /* Set autoneg settings */ - ecmd->autoneg = ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ? + cmd->base.autoneg = ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ? AUTONEG_ENABLE : AUTONEG_DISABLE); switch (hw->phy.media_type) { case I40E_MEDIA_TYPE_BACKPLANE: - ecmd->supported |= SUPPORTED_Autoneg | - SUPPORTED_Backplane; - ecmd->advertising |= ADVERTISED_Autoneg | - ADVERTISED_Backplane; - ecmd->port = PORT_NONE; + ethtool_link_ksettings_add_link_mode(cmd, supported, + Autoneg); + ethtool_link_ksettings_add_link_mode(cmd, supported, + Backplane); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + Autoneg); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + Backplane); + cmd->base.port = PORT_NONE; break; case I40E_MEDIA_TYPE_BASET: - ecmd->supported |= SUPPORTED_TP; - ecmd->advertising |= ADVERTISED_TP; - ecmd->port = PORT_TP; + ethtool_link_ksettings_add_link_mode(cmd, supported, TP); + ethtool_link_ksettings_add_link_mode(cmd, advertising, TP); + cmd->base.port = PORT_TP; break; case I40E_MEDIA_TYPE_DA: case I40E_MEDIA_TYPE_CX4: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_DA; + ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE); + ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE); + cmd->base.port = PORT_DA; break; case I40E_MEDIA_TYPE_FIBER: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->port = PORT_FIBRE; + ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE); + cmd->base.port = PORT_FIBRE; break; case I40E_MEDIA_TYPE_UNKNOWN: default: - ecmd->port = PORT_OTHER; + cmd->base.port = PORT_OTHER; break; } - /* Set transceiver */ - ecmd->transceiver = XCVR_EXTERNAL; - /* Set flow control settings */ - ecmd->supported |= SUPPORTED_Pause; + ethtool_link_ksettings_add_link_mode(cmd, supported, Pause); switch (hw->fc.requested_mode) { case I40E_FC_FULL: - ecmd->advertising |= ADVERTISED_Pause; + ethtool_link_ksettings_add_link_mode(cmd, advertising, + Pause); break; case I40E_FC_TX_PAUSE: - ecmd->advertising |= ADVERTISED_Asym_Pause; + ethtool_link_ksettings_add_link_mode(cmd, advertising, + Asym_Pause); break; case I40E_FC_RX_PAUSE: - ecmd->advertising |= (ADVERTISED_Pause | - ADVERTISED_Asym_Pause); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + Pause); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + Asym_Pause); break; default: - ecmd->advertising &= ~(ADVERTISED_Pause | - ADVERTISED_Asym_Pause); + ethtool_convert_link_mode_to_legacy_u32( + &advertising, cmd->link_modes.advertising); + + advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); + + ethtool_convert_legacy_u32_to_link_mode( + cmd->link_modes.advertising, advertising); break; } @@ -664,8 +685,8 @@ static int i40e_get_settings(struct net_device *netdev, * * Set speed/duplex per media_types advertised/forced **/ -static int i40e_set_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int i40e_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *cmd) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_aq_get_phy_abilities_resp abilities; @@ -673,12 +694,15 @@ static int i40e_set_settings(struct net_device *netdev, struct i40e_pf *pf = np->vsi->back; struct i40e_vsi *vsi = np->vsi; struct i40e_hw *hw = &pf->hw; - struct ethtool_cmd safe_ecmd; + struct ethtool_link_ksettings safe_cmd; + struct ethtool_link_ksettings copy_cmd; i40e_status status = 0; bool change = false; + int timeout = 50; int err = 0; - u8 autoneg; + u32 autoneg; u32 advertise; + u32 tmp; /* Changing port settings is not supported if this isn't the * port's controlling PF @@ -706,33 +730,47 @@ static int i40e_set_settings(struct net_device *netdev, return -EOPNOTSUPP; } + /* copy the cmd to copy_cmd to avoid modifying the origin */ + memcpy(©_cmd, cmd, sizeof(struct ethtool_link_ksettings)); + /* get our own copy of the bits to check against */ - memset(&safe_ecmd, 0, sizeof(struct ethtool_cmd)); - i40e_get_settings(netdev, &safe_ecmd); + memset(&safe_cmd, 0, sizeof(struct ethtool_link_ksettings)); + i40e_get_link_ksettings(netdev, &safe_cmd); - /* save autoneg and speed out of ecmd */ - autoneg = ecmd->autoneg; - advertise = ecmd->advertising; + /* save autoneg and speed out of cmd */ + autoneg = cmd->base.autoneg; + ethtool_convert_link_mode_to_legacy_u32(&advertise, + cmd->link_modes.advertising); /* set autoneg and speed back to what they currently are */ - ecmd->autoneg = safe_ecmd.autoneg; - ecmd->advertising = safe_ecmd.advertising; + copy_cmd.base.autoneg = safe_cmd.base.autoneg; + ethtool_convert_link_mode_to_legacy_u32( + &tmp, safe_cmd.link_modes.advertising); + ethtool_convert_legacy_u32_to_link_mode( + copy_cmd.link_modes.advertising, tmp); + + copy_cmd.base.cmd = safe_cmd.base.cmd; - ecmd->cmd = safe_ecmd.cmd; - /* If ecmd and safe_ecmd are not the same now, then they are + /* If copy_cmd and safe_cmd are not the same now, then they are * trying to set something that we do not support */ - if (memcmp(ecmd, &safe_ecmd, sizeof(struct ethtool_cmd))) + if (memcmp(©_cmd, &safe_cmd, sizeof(struct ethtool_link_ksettings))) return -EOPNOTSUPP; - while (test_bit(__I40E_CONFIG_BUSY, &vsi->state)) + while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state)) { + timeout--; + if (!timeout) + return -EBUSY; usleep_range(1000, 2000); + } /* Get the current phy config */ status = i40e_aq_get_phy_capabilities(hw, false, false, &abilities, NULL); - if (status) - return -EAGAIN; + if (status) { + err = -EAGAIN; + goto done; + } /* Copy abilities to config in case autoneg is not * set below @@ -745,9 +783,11 @@ static int i40e_set_settings(struct net_device *netdev, /* If autoneg was not already enabled */ if (!(hw->phy.link_info.an_info & I40E_AQ_AN_COMPLETED)) { /* If autoneg is not supported, return error */ - if (!(safe_ecmd.supported & SUPPORTED_Autoneg)) { + if (!ethtool_link_ksettings_test_link_mode( + &safe_cmd, supported, Autoneg)) { netdev_info(netdev, "Autoneg not supported on this phy\n"); - return -EINVAL; + err = -EINVAL; + goto done; } /* Autoneg is allowed to change */ config.abilities = abilities.abilities | @@ -760,11 +800,13 @@ static int i40e_set_settings(struct net_device *netdev, /* If autoneg is supported 10GBASE_T is the only PHY * that can disable it, so otherwise return error */ - if (safe_ecmd.supported & SUPPORTED_Autoneg && + if (ethtool_link_ksettings_test_link_mode( + &safe_cmd, supported, Autoneg) && hw->phy.link_info.phy_type != I40E_PHY_TYPE_10GBASE_T) { netdev_info(netdev, "Autoneg cannot be disabled on this phy\n"); - return -EINVAL; + err = -EINVAL; + goto done; } /* Autoneg is allowed to change */ config.abilities = abilities.abilities & @@ -773,8 +815,12 @@ static int i40e_set_settings(struct net_device *netdev, } } - if (advertise & ~safe_ecmd.supported) - return -EINVAL; + ethtool_convert_link_mode_to_legacy_u32(&tmp, + safe_cmd.link_modes.supported); + if (advertise & ~tmp) { + err = -EINVAL; + goto done; + } if (advertise & ADVERTISED_100baseT_Full) config.link_speed |= I40E_LINK_SPEED_100MB; @@ -830,7 +876,8 @@ static int i40e_set_settings(struct net_device *netdev, netdev_info(netdev, "Set phy config failed, err %s aq_err %s\n", i40e_stat_str(hw, status), i40e_aq_str(hw, hw->aq.asq_last_status)); - return -EAGAIN; + err = -EAGAIN; + goto done; } status = i40e_update_link_info(hw); @@ -843,6 +890,9 @@ static int i40e_set_settings(struct net_device *netdev, netdev_info(netdev, "Nothing changed, exiting without setting anything.\n"); } +done: + clear_bit(__I40E_CONFIG_BUSY, pf->state); + return err; } @@ -937,7 +987,7 @@ static int i40e_set_pauseparam(struct net_device *netdev, } /* If we have link and don't have autoneg */ - if (!test_bit(__I40E_DOWN, &pf->state) && + if (!test_bit(__I40E_DOWN, pf->state) && !(hw_link_info->an_info & I40E_AQ_AN_COMPLETED)) { /* Send message that it might not necessarily work*/ netdev_info(netdev, "Autoneg did not complete so changing settings may not result in an actual change.\n"); @@ -989,10 +1039,10 @@ static int i40e_set_pauseparam(struct net_device *netdev, err = -EAGAIN; } - if (!test_bit(__I40E_DOWN, &pf->state)) { + if (!test_bit(__I40E_DOWN, pf->state)) { /* Give it a little more time to try to come back */ msleep(75); - if (!test_bit(__I40E_DOWN, &pf->state)) + if (!test_bit(__I40E_DOWN, pf->state)) return i40e_nway_reset(netdev); } @@ -1089,8 +1139,8 @@ static int i40e_get_eeprom(struct net_device *netdev, /* make sure it is the right magic for NVMUpdate */ if ((eeprom->magic >> 16) != hw->device_id) errno = -EINVAL; - else if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) || - test_bit(__I40E_RESET_INTR_RECEIVED, &pf->state)) + else if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state) || + test_bit(__I40E_RESET_INTR_RECEIVED, pf->state)) errno = -EBUSY; else ret_val = i40e_nvmupd_command(hw, cmd, bytes, &errno); @@ -1165,6 +1215,11 @@ static int i40e_get_eeprom_len(struct net_device *netdev) struct i40e_hw *hw = &np->vsi->back->hw; u32 val; +#define X722_EEPROM_SCOPE_LIMIT 0x5B9FFF + if (hw->mac.type == I40E_MAC_X722) { + val = X722_EEPROM_SCOPE_LIMIT + 1; + return val; + } val = (rd32(hw, I40E_GLPCI_LBARCTRL) & I40E_GLPCI_LBARCTRL_FL_SIZE_MASK) >> I40E_GLPCI_LBARCTRL_FL_SIZE_SHIFT; @@ -1191,8 +1246,8 @@ static int i40e_set_eeprom(struct net_device *netdev, /* check for NVMUpdate access method */ else if (!eeprom->magic || (eeprom->magic >> 16) != hw->device_id) errno = -EINVAL; - else if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) || - test_bit(__I40E_RESET_INTR_RECEIVED, &pf->state)) + else if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state) || + test_bit(__I40E_RESET_INTR_RECEIVED, pf->state)) errno = -EBUSY; else ret_val = i40e_nvmupd_command(hw, cmd, bytes, &errno); @@ -1252,6 +1307,7 @@ static int i40e_set_ringparam(struct net_device *netdev, struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; u32 new_rx_count, new_tx_count; + int timeout = 50; int i, err = 0; if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) @@ -1276,8 +1332,12 @@ static int i40e_set_ringparam(struct net_device *netdev, (new_rx_count == vsi->rx_rings[0]->count)) return 0; - while (test_and_set_bit(__I40E_CONFIG_BUSY, &pf->state)) + while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state)) { + timeout--; + if (!timeout) + return -EBUSY; usleep_range(1000, 2000); + } if (!netif_running(vsi->netdev)) { /* simple case - set for the next time the netdev is started */ @@ -1425,7 +1485,7 @@ free_tx: } done: - clear_bit(__I40E_CONFIG_BUSY, &pf->state); + clear_bit(__I40E_CONFIG_BUSY, pf->state); return err; } @@ -1483,13 +1543,6 @@ static void i40e_get_ethtool_stats(struct net_device *netdev, data[i++] = (i40e_gstrings_misc_stats[j].sizeof_stat == sizeof(u64)) ? *(u64 *)p : *(u32 *)p; } -#ifdef I40E_FCOE - for (j = 0; j < I40E_FCOE_STATS_LEN; j++) { - p = (char *)vsi + i40e_gstrings_fcoe_stats[j].stat_offset; - data[i++] = (i40e_gstrings_fcoe_stats[j].sizeof_stat == - sizeof(u64)) ? *(u64 *)p : *(u32 *)p; - } -#endif rcu_read_lock(); for (j = 0; j < vsi->num_queue_pairs; j++) { tx_ring = ACCESS_ONCE(vsi->tx_rings[j]); @@ -1577,13 +1630,6 @@ static void i40e_get_strings(struct net_device *netdev, u32 stringset, i40e_gstrings_misc_stats[i].stat_string); p += ETH_GSTRING_LEN; } -#ifdef I40E_FCOE - for (i = 0; i < I40E_FCOE_STATS_LEN; i++) { - snprintf(p, ETH_GSTRING_LEN, "%s", - i40e_gstrings_fcoe_stats[i].stat_string); - p += ETH_GSTRING_LEN; - } -#endif for (i = 0; i < vsi->num_queue_pairs; i++) { snprintf(p, ETH_GSTRING_LEN, "tx-%d.tx_packets", i); p += ETH_GSTRING_LEN; @@ -1648,12 +1694,18 @@ static void i40e_get_strings(struct net_device *netdev, u32 stringset, /* BUG_ON(p - data != I40E_STATS_LEN * ETH_GSTRING_LEN); */ break; case ETH_SS_PRIV_FLAGS: - memcpy(data, i40e_priv_flags_strings, - I40E_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN); - data += I40E_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN; - if (pf->hw.pf_id == 0) - memcpy(data, i40e_gl_priv_flags_strings, - I40E_GL_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN); + for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++) { + snprintf(p, ETH_GSTRING_LEN, "%s", + i40e_gstrings_priv_flags[i].flag_string); + p += ETH_GSTRING_LEN; + } + if (pf->hw.pf_id != 0) + break; + for (i = 0; i < I40E_GL_PRIV_FLAGS_STR_LEN; i++) { + snprintf(p, ETH_GSTRING_LEN, "%s", + i40e_gl_gstrings_priv_flags[i].flag_string); + p += ETH_GSTRING_LEN; + } break; default: break; @@ -1774,7 +1826,7 @@ static inline bool i40e_active_vfs(struct i40e_pf *pf) int i; for (i = 0; i < pf->num_alloc_vfs; i++) - if (test_bit(I40E_VF_STAT_ACTIVE, &vfs[i].vf_states)) + if (test_bit(I40E_VF_STATE_ACTIVE, &vfs[i].vf_states)) return true; return false; } @@ -1795,7 +1847,7 @@ static void i40e_diag_test(struct net_device *netdev, /* Offline tests */ netif_info(pf, drv, netdev, "offline testing starting\n"); - set_bit(__I40E_TESTING, &pf->state); + set_bit(__I40E_TESTING, pf->state); if (i40e_active_vfs(pf) || i40e_active_vmdqs(pf)) { dev_warn(&pf->pdev->dev, @@ -1805,7 +1857,7 @@ static void i40e_diag_test(struct net_device *netdev, data[I40E_ETH_TEST_INTR] = 1; data[I40E_ETH_TEST_LINK] = 1; eth_test->flags |= ETH_TEST_FL_FAILED; - clear_bit(__I40E_TESTING, &pf->state); + clear_bit(__I40E_TESTING, pf->state); goto skip_ol_tests; } @@ -1819,7 +1871,7 @@ static void i40e_diag_test(struct net_device *netdev, * link then the following link test would have * to be moved to before the reset */ - i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED)); + i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true); if (i40e_link_test(netdev, &data[I40E_ETH_TEST_LINK])) eth_test->flags |= ETH_TEST_FL_FAILED; @@ -1834,8 +1886,8 @@ static void i40e_diag_test(struct net_device *netdev, if (i40e_reg_test(netdev, &data[I40E_ETH_TEST_REG])) eth_test->flags |= ETH_TEST_FL_FAILED; - clear_bit(__I40E_TESTING, &pf->state); - i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED)); + clear_bit(__I40E_TESTING, pf->state); + i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true); if (if_running) i40e_open(netdev); @@ -2285,6 +2337,102 @@ static int i40e_get_rss_hash_opts(struct i40e_pf *pf, struct ethtool_rxnfc *cmd) } /** + * i40e_check_mask - Check whether a mask field is set + * @mask: the full mask value + * @field; mask of the field to check + * + * If the given mask is fully set, return positive value. If the mask for the + * field is fully unset, return zero. Otherwise return a negative error code. + **/ +static int i40e_check_mask(u64 mask, u64 field) +{ + u64 value = mask & field; + + if (value == field) + return 1; + else if (!value) + return 0; + else + return -1; +} + +/** + * i40e_parse_rx_flow_user_data - Deconstruct user-defined data + * @fsp: pointer to rx flow specification + * @data: pointer to userdef data structure for storage + * + * Read the user-defined data and deconstruct the value into a structure. No + * other code should read the user-defined data, so as to ensure that every + * place consistently reads the value correctly. + * + * The user-defined field is a 64bit Big Endian format value, which we + * deconstruct by reading bits or bit fields from it. Single bit flags shall + * be defined starting from the highest bits, while small bit field values + * shall be defined starting from the lowest bits. + * + * Returns 0 if the data is valid, and non-zero if the userdef data is invalid + * and the filter should be rejected. The data structure will always be + * modified even if FLOW_EXT is not set. + * + **/ +static int i40e_parse_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp, + struct i40e_rx_flow_userdef *data) +{ + u64 value, mask; + int valid; + + /* Zero memory first so it's always consistent. */ + memset(data, 0, sizeof(*data)); + + if (!(fsp->flow_type & FLOW_EXT)) + return 0; + + value = be64_to_cpu(*((__be64 *)fsp->h_ext.data)); + mask = be64_to_cpu(*((__be64 *)fsp->m_ext.data)); + +#define I40E_USERDEF_FLEX_WORD GENMASK_ULL(15, 0) +#define I40E_USERDEF_FLEX_OFFSET GENMASK_ULL(31, 16) +#define I40E_USERDEF_FLEX_FILTER GENMASK_ULL(31, 0) + + valid = i40e_check_mask(mask, I40E_USERDEF_FLEX_FILTER); + if (valid < 0) { + return -EINVAL; + } else if (valid) { + data->flex_word = value & I40E_USERDEF_FLEX_WORD; + data->flex_offset = + (value & I40E_USERDEF_FLEX_OFFSET) >> 16; + data->flex_filter = true; + } + + return 0; +} + +/** + * i40e_fill_rx_flow_user_data - Fill in user-defined data field + * @fsp: pointer to rx_flow specification + * + * Reads the userdef data structure and properly fills in the user defined + * fields of the rx_flow_spec. + **/ +static void i40e_fill_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp, + struct i40e_rx_flow_userdef *data) +{ + u64 value = 0, mask = 0; + + if (data->flex_filter) { + value |= data->flex_word; + value |= (u64)data->flex_offset << 16; + mask |= I40E_USERDEF_FLEX_FILTER; + } + + if (value || mask) + fsp->flow_type |= FLOW_EXT; + + *((__be64 *)fsp->h_ext.data) = cpu_to_be64(value); + *((__be64 *)fsp->m_ext.data) = cpu_to_be64(mask); +} + +/** * i40e_get_ethtool_fdir_all - Populates the rule count of a command * @pf: Pointer to the physical function struct * @cmd: The command to get or set Rx flow classification rules @@ -2335,8 +2483,11 @@ static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf, { struct ethtool_rx_flow_spec *fsp = (struct ethtool_rx_flow_spec *)&cmd->fs; + struct i40e_rx_flow_userdef userdef = {0}; struct i40e_fdir_filter *rule = NULL; struct hlist_node *node2; + u64 input_set; + u16 index; hlist_for_each_entry_safe(rule, node2, &pf->fdir_filter_list, fdir_node) { @@ -2359,8 +2510,48 @@ static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf, */ fsp->h_u.tcp_ip4_spec.psrc = rule->dst_port; fsp->h_u.tcp_ip4_spec.pdst = rule->src_port; - fsp->h_u.tcp_ip4_spec.ip4src = rule->dst_ip[0]; - fsp->h_u.tcp_ip4_spec.ip4dst = rule->src_ip[0]; + fsp->h_u.tcp_ip4_spec.ip4src = rule->dst_ip; + fsp->h_u.tcp_ip4_spec.ip4dst = rule->src_ip; + + switch (rule->flow_type) { + case SCTP_V4_FLOW: + index = I40E_FILTER_PCTYPE_NONF_IPV4_SCTP; + break; + case TCP_V4_FLOW: + index = I40E_FILTER_PCTYPE_NONF_IPV4_TCP; + break; + case UDP_V4_FLOW: + index = I40E_FILTER_PCTYPE_NONF_IPV4_UDP; + break; + case IP_USER_FLOW: + index = I40E_FILTER_PCTYPE_NONF_IPV4_OTHER; + break; + default: + /* If we have stored a filter with a flow type not listed here + * it is almost certainly a driver bug. WARN(), and then + * assign the input_set as if all fields are enabled to avoid + * reading unassigned memory. + */ + WARN(1, "Missing input set index for flow_type %d\n", + rule->flow_type); + input_set = 0xFFFFFFFFFFFFFFFFULL; + goto no_input_set; + } + + input_set = i40e_read_fd_input_set(pf, index); + +no_input_set: + if (input_set & I40E_L3_SRC_MASK) + fsp->m_u.tcp_ip4_spec.ip4src = htonl(0xFFFF); + + if (input_set & I40E_L3_DST_MASK) + fsp->m_u.tcp_ip4_spec.ip4dst = htonl(0xFFFF); + + if (input_set & I40E_L4_SRC_MASK) + fsp->m_u.tcp_ip4_spec.psrc = htons(0xFFFFFFFF); + + if (input_set & I40E_L4_DST_MASK) + fsp->m_u.tcp_ip4_spec.pdst = htons(0xFFFFFFFF); if (rule->dest_ctl == I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET) fsp->ring_cookie = RX_CLS_FLOW_DISC; @@ -2372,11 +2563,24 @@ static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf, vsi = i40e_find_vsi_from_id(pf, rule->dest_vsi); if (vsi && vsi->type == I40E_VSI_SRIOV) { - fsp->h_ext.data[1] = htonl(vsi->vf_id); - fsp->m_ext.data[1] = htonl(0x1); + /* VFs are zero-indexed by the driver, but ethtool + * expects them to be one-indexed, so add one here + */ + u64 ring_vf = vsi->vf_id + 1; + + ring_vf <<= ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF; + fsp->ring_cookie |= ring_vf; } } + if (rule->flex_filter) { + userdef.flex_filter = true; + userdef.flex_word = be16_to_cpu(rule->flex_word); + userdef.flex_offset = rule->flex_offset; + } + + i40e_fill_rx_flow_user_data(fsp, &userdef); + return 0; } @@ -2574,24 +2778,6 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc) } /** - * i40e_match_fdir_input_set - Match a new filter against an existing one - * @rule: The filter already added - * @input: The new filter to comapre against - * - * Returns true if the two input set match - **/ -static bool i40e_match_fdir_input_set(struct i40e_fdir_filter *rule, - struct i40e_fdir_filter *input) -{ - if ((rule->dst_ip[0] != input->dst_ip[0]) || - (rule->src_ip[0] != input->src_ip[0]) || - (rule->dst_port != input->dst_port) || - (rule->src_port != input->src_port)) - return false; - return true; -} - -/** * i40e_update_ethtool_fdir_entry - Updates the fdir filter entry * @vsi: Pointer to the targeted VSI * @input: The filter to update or NULL to indicate deletion @@ -2626,22 +2812,22 @@ static int i40e_update_ethtool_fdir_entry(struct i40e_vsi *vsi, /* if there is an old rule occupying our place remove it */ if (rule && (rule->fd_id == sw_idx)) { - if (input && !i40e_match_fdir_input_set(rule, input)) - err = i40e_add_del_fdir(vsi, rule, false); - else if (!input) - err = i40e_add_del_fdir(vsi, rule, false); + /* Remove this rule, since we're either deleting it, or + * replacing it. + */ + err = i40e_add_del_fdir(vsi, rule, false); hlist_del(&rule->fdir_node); kfree(rule); pf->fdir_pf_active_filters--; } - /* If no input this was a delete, err should be 0 if a rule was - * successfully found and removed from the list else -EINVAL + /* If we weren't given an input, this is a delete, so just return the + * error code indicating if there was an entry at the requested slot */ if (!input) return err; - /* initialize node and set software index */ + /* Otherwise, install the new rule as requested */ INIT_HLIST_NODE(&input->fdir_node); /* add filter to the list */ @@ -2658,6 +2844,69 @@ static int i40e_update_ethtool_fdir_entry(struct i40e_vsi *vsi, } /** + * i40e_prune_flex_pit_list - Cleanup unused entries in FLX_PIT table + * @pf: pointer to PF structure + * + * This function searches the list of filters and determines which FLX_PIT + * entries are still required. It will prune any entries which are no longer + * in use after the deletion. + **/ +static void i40e_prune_flex_pit_list(struct i40e_pf *pf) +{ + struct i40e_flex_pit *entry, *tmp; + struct i40e_fdir_filter *rule; + + /* First, we'll check the l3 table */ + list_for_each_entry_safe(entry, tmp, &pf->l3_flex_pit_list, list) { + bool found = false; + + hlist_for_each_entry(rule, &pf->fdir_filter_list, fdir_node) { + if (rule->flow_type != IP_USER_FLOW) + continue; + if (rule->flex_filter && + rule->flex_offset == entry->src_offset) { + found = true; + break; + } + } + + /* If we didn't find the filter, then we can prune this entry + * from the list. + */ + if (!found) { + list_del(&entry->list); + kfree(entry); + } + } + + /* Followed by the L4 table */ + list_for_each_entry_safe(entry, tmp, &pf->l4_flex_pit_list, list) { + bool found = false; + + hlist_for_each_entry(rule, &pf->fdir_filter_list, fdir_node) { + /* Skip this filter if it's L3, since we already + * checked those in the above loop + */ + if (rule->flow_type == IP_USER_FLOW) + continue; + if (rule->flex_filter && + rule->flex_offset == entry->src_offset) { + found = true; + break; + } + } + + /* If we didn't find the filter, then we can prune this entry + * from the list. + */ + if (!found) { + list_del(&entry->list); + kfree(entry); + } + } +} + +/** * i40e_del_fdir_entry - Deletes a Flow Director filter entry * @vsi: Pointer to the targeted VSI * @cmd: The command to get or set Rx flow classification rules @@ -2675,20 +2924,700 @@ static int i40e_del_fdir_entry(struct i40e_vsi *vsi, struct i40e_pf *pf = vsi->back; int ret = 0; - if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) || - test_bit(__I40E_RESET_INTR_RECEIVED, &pf->state)) + if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state) || + test_bit(__I40E_RESET_INTR_RECEIVED, pf->state)) return -EBUSY; - if (test_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state)) + if (test_bit(__I40E_FD_FLUSH_REQUESTED, pf->state)) return -EBUSY; ret = i40e_update_ethtool_fdir_entry(vsi, NULL, fsp->location, cmd); + i40e_prune_flex_pit_list(pf); + i40e_fdir_check_and_reenable(pf); return ret; } /** + * i40e_unused_pit_index - Find an unused PIT index for given list + * @pf: the PF data structure + * + * Find the first unused flexible PIT index entry. We search both the L3 and + * L4 flexible PIT lists so that the returned index is unique and unused by + * either currently programmed L3 or L4 filters. We use a bit field as storage + * to track which indexes are already used. + **/ +static u8 i40e_unused_pit_index(struct i40e_pf *pf) +{ + unsigned long available_index = 0xFF; + struct i40e_flex_pit *entry; + + /* We need to make sure that the new index isn't in use by either L3 + * or L4 filters so that IP_USER_FLOW filters can program both L3 and + * L4 to use the same index. + */ + + list_for_each_entry(entry, &pf->l4_flex_pit_list, list) + clear_bit(entry->pit_index, &available_index); + + list_for_each_entry(entry, &pf->l3_flex_pit_list, list) + clear_bit(entry->pit_index, &available_index); + + return find_first_bit(&available_index, 8); +} + +/** + * i40e_find_flex_offset - Find an existing flex src_offset + * @flex_pit_list: L3 or L4 flex PIT list + * @src_offset: new src_offset to find + * + * Searches the flex_pit_list for an existing offset. If no offset is + * currently programmed, then this will return an ERR_PTR if there is no space + * to add a new offset, otherwise it returns NULL. + **/ +static +struct i40e_flex_pit *i40e_find_flex_offset(struct list_head *flex_pit_list, + u16 src_offset) +{ + struct i40e_flex_pit *entry; + int size = 0; + + /* Search for the src_offset first. If we find a matching entry + * already programmed, we can simply re-use it. + */ + list_for_each_entry(entry, flex_pit_list, list) { + size++; + if (entry->src_offset == src_offset) + return entry; + } + + /* If we haven't found an entry yet, then the provided src offset has + * not yet been programmed. We will program the src offset later on, + * but we need to indicate whether there is enough space to do so + * here. We'll make use of ERR_PTR for this purpose. + */ + if (size >= I40E_FLEX_PIT_TABLE_SIZE) + return ERR_PTR(-ENOSPC); + + return NULL; +} + +/** + * i40e_add_flex_offset - Add src_offset to flex PIT table list + * @flex_pit_list: L3 or L4 flex PIT list + * @src_offset: new src_offset to add + * @pit_index: the PIT index to program + * + * This function programs the new src_offset to the list. It is expected that + * i40e_find_flex_offset has already been tried and returned NULL, indicating + * that this offset is not programmed, and that the list has enough space to + * store another offset. + * + * Returns 0 on success, and negative value on error. + **/ +static int i40e_add_flex_offset(struct list_head *flex_pit_list, + u16 src_offset, + u8 pit_index) +{ + struct i40e_flex_pit *new_pit, *entry; + + new_pit = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!new_pit) + return -ENOMEM; + + new_pit->src_offset = src_offset; + new_pit->pit_index = pit_index; + + /* We need to insert this item such that the list is sorted by + * src_offset in ascending order. + */ + list_for_each_entry(entry, flex_pit_list, list) { + if (new_pit->src_offset < entry->src_offset) { + list_add_tail(&new_pit->list, &entry->list); + return 0; + } + + /* If we found an entry with our offset already programmed we + * can simply return here, after freeing the memory. However, + * if the pit_index does not match we need to report an error. + */ + if (new_pit->src_offset == entry->src_offset) { + int err = 0; + + /* If the PIT index is not the same we can't re-use + * the entry, so we must report an error. + */ + if (new_pit->pit_index != entry->pit_index) + err = -EINVAL; + + kfree(new_pit); + return err; + } + } + + /* If we reached here, then we haven't yet added the item. This means + * that we should add the item at the end of the list. + */ + list_add_tail(&new_pit->list, flex_pit_list); + return 0; +} + +/** + * __i40e_reprogram_flex_pit - Re-program specific FLX_PIT table + * @pf: Pointer to the PF structure + * @flex_pit_list: list of flexible src offsets in use + * #flex_pit_start: index to first entry for this section of the table + * + * In order to handle flexible data, the hardware uses a table of values + * called the FLX_PIT table. This table is used to indicate which sections of + * the input correspond to what PIT index values. Unfortunately, hardware is + * very restrictive about programming this table. Entries must be ordered by + * src_offset in ascending order, without duplicates. Additionally, unused + * entries must be set to the unused index value, and must have valid size and + * length according to the src_offset ordering. + * + * This function will reprogram the FLX_PIT register from a book-keeping + * structure that we guarantee is already ordered correctly, and has no more + * than 3 entries. + * + * To make things easier, we only support flexible values of one word length, + * rather than allowing variable length flexible values. + **/ +static void __i40e_reprogram_flex_pit(struct i40e_pf *pf, + struct list_head *flex_pit_list, + int flex_pit_start) +{ + struct i40e_flex_pit *entry = NULL; + u16 last_offset = 0; + int i = 0, j = 0; + + /* First, loop over the list of flex PIT entries, and reprogram the + * registers. + */ + list_for_each_entry(entry, flex_pit_list, list) { + /* We have to be careful when programming values for the + * largest SRC_OFFSET value. It is possible that adding + * additional empty values at the end would overflow the space + * for the SRC_OFFSET in the FLX_PIT register. To avoid this, + * we check here and add the empty values prior to adding the + * largest value. + * + * To determine this, we will use a loop from i+1 to 3, which + * will determine whether the unused entries would have valid + * SRC_OFFSET. Note that there cannot be extra entries past + * this value, because the only valid values would have been + * larger than I40E_MAX_FLEX_SRC_OFFSET, and thus would not + * have been added to the list in the first place. + */ + for (j = i + 1; j < 3; j++) { + u16 offset = entry->src_offset + j; + int index = flex_pit_start + i; + u32 value = I40E_FLEX_PREP_VAL(I40E_FLEX_DEST_UNUSED, + 1, + offset - 3); + + if (offset > I40E_MAX_FLEX_SRC_OFFSET) { + i40e_write_rx_ctl(&pf->hw, + I40E_PRTQF_FLX_PIT(index), + value); + i++; + } + } + + /* Now, we can program the actual value into the table */ + i40e_write_rx_ctl(&pf->hw, + I40E_PRTQF_FLX_PIT(flex_pit_start + i), + I40E_FLEX_PREP_VAL(entry->pit_index + 50, + 1, + entry->src_offset)); + i++; + } + + /* In order to program the last entries in the table, we need to + * determine the valid offset. If the list is empty, we'll just start + * with 0. Otherwise, we'll start with the last item offset and add 1. + * This ensures that all entries have valid sizes. If we don't do this + * correctly, the hardware will disable flexible field parsing. + */ + if (!list_empty(flex_pit_list)) + last_offset = list_prev_entry(entry, list)->src_offset + 1; + + for (; i < 3; i++, last_offset++) { + i40e_write_rx_ctl(&pf->hw, + I40E_PRTQF_FLX_PIT(flex_pit_start + i), + I40E_FLEX_PREP_VAL(I40E_FLEX_DEST_UNUSED, + 1, + last_offset)); + } +} + +/** + * i40e_reprogram_flex_pit - Reprogram all FLX_PIT tables after input set change + * @pf: pointer to the PF structure + * + * This function reprograms both the L3 and L4 FLX_PIT tables. See the + * internal helper function for implementation details. + **/ +static void i40e_reprogram_flex_pit(struct i40e_pf *pf) +{ + __i40e_reprogram_flex_pit(pf, &pf->l3_flex_pit_list, + I40E_FLEX_PIT_IDX_START_L3); + + __i40e_reprogram_flex_pit(pf, &pf->l4_flex_pit_list, + I40E_FLEX_PIT_IDX_START_L4); + + /* We also need to program the L3 and L4 GLQF ORT register */ + i40e_write_rx_ctl(&pf->hw, + I40E_GLQF_ORT(I40E_L3_GLQF_ORT_IDX), + I40E_ORT_PREP_VAL(I40E_FLEX_PIT_IDX_START_L3, + 3, 1)); + + i40e_write_rx_ctl(&pf->hw, + I40E_GLQF_ORT(I40E_L4_GLQF_ORT_IDX), + I40E_ORT_PREP_VAL(I40E_FLEX_PIT_IDX_START_L4, + 3, 1)); +} + +/** + * i40e_flow_str - Converts a flow_type into a human readable string + * @flow_type: the flow type from a flow specification + * + * Currently only flow types we support are included here, and the string + * value attempts to match what ethtool would use to configure this flow type. + **/ +static const char *i40e_flow_str(struct ethtool_rx_flow_spec *fsp) +{ + switch (fsp->flow_type & ~FLOW_EXT) { + case TCP_V4_FLOW: + return "tcp4"; + case UDP_V4_FLOW: + return "udp4"; + case SCTP_V4_FLOW: + return "sctp4"; + case IP_USER_FLOW: + return "ip4"; + default: + return "unknown"; + } +} + +/** + * i40e_pit_index_to_mask - Return the FLEX mask for a given PIT index + * @pit_index: PIT index to convert + * + * Returns the mask for a given PIT index. Will return 0 if the pit_index is + * of range. + **/ +static u64 i40e_pit_index_to_mask(int pit_index) +{ + switch (pit_index) { + case 0: + return I40E_FLEX_50_MASK; + case 1: + return I40E_FLEX_51_MASK; + case 2: + return I40E_FLEX_52_MASK; + case 3: + return I40E_FLEX_53_MASK; + case 4: + return I40E_FLEX_54_MASK; + case 5: + return I40E_FLEX_55_MASK; + case 6: + return I40E_FLEX_56_MASK; + case 7: + return I40E_FLEX_57_MASK; + default: + return 0; + } +} + +/** + * i40e_print_input_set - Show changes between two input sets + * @vsi: the vsi being configured + * @old: the old input set + * @new: the new input set + * + * Print the difference between old and new input sets by showing which series + * of words are toggled on or off. Only displays the bits we actually support + * changing. + **/ +static void i40e_print_input_set(struct i40e_vsi *vsi, u64 old, u64 new) +{ + struct i40e_pf *pf = vsi->back; + bool old_value, new_value; + int i; + + old_value = !!(old & I40E_L3_SRC_MASK); + new_value = !!(new & I40E_L3_SRC_MASK); + if (old_value != new_value) + netif_info(pf, drv, vsi->netdev, "L3 source address: %s -> %s\n", + old_value ? "ON" : "OFF", + new_value ? "ON" : "OFF"); + + old_value = !!(old & I40E_L3_DST_MASK); + new_value = !!(new & I40E_L3_DST_MASK); + if (old_value != new_value) + netif_info(pf, drv, vsi->netdev, "L3 destination address: %s -> %s\n", + old_value ? "ON" : "OFF", + new_value ? "ON" : "OFF"); + + old_value = !!(old & I40E_L4_SRC_MASK); + new_value = !!(new & I40E_L4_SRC_MASK); + if (old_value != new_value) + netif_info(pf, drv, vsi->netdev, "L4 source port: %s -> %s\n", + old_value ? "ON" : "OFF", + new_value ? "ON" : "OFF"); + + old_value = !!(old & I40E_L4_DST_MASK); + new_value = !!(new & I40E_L4_DST_MASK); + if (old_value != new_value) + netif_info(pf, drv, vsi->netdev, "L4 destination port: %s -> %s\n", + old_value ? "ON" : "OFF", + new_value ? "ON" : "OFF"); + + old_value = !!(old & I40E_VERIFY_TAG_MASK); + new_value = !!(new & I40E_VERIFY_TAG_MASK); + if (old_value != new_value) + netif_info(pf, drv, vsi->netdev, "SCTP verification tag: %s -> %s\n", + old_value ? "ON" : "OFF", + new_value ? "ON" : "OFF"); + + /* Show change of flexible filter entries */ + for (i = 0; i < I40E_FLEX_INDEX_ENTRIES; i++) { + u64 flex_mask = i40e_pit_index_to_mask(i); + + old_value = !!(old & flex_mask); + new_value = !!(new & flex_mask); + if (old_value != new_value) + netif_info(pf, drv, vsi->netdev, "FLEX index %d: %s -> %s\n", + i, + old_value ? "ON" : "OFF", + new_value ? "ON" : "OFF"); + } + + netif_info(pf, drv, vsi->netdev, " Current input set: %0llx\n", + old); + netif_info(pf, drv, vsi->netdev, "Requested input set: %0llx\n", + new); +} + +/** + * i40e_check_fdir_input_set - Check that a given rx_flow_spec mask is valid + * @vsi: pointer to the targeted VSI + * @fsp: pointer to Rx flow specification + * @userdef: userdefined data from flow specification + * + * Ensures that a given ethtool_rx_flow_spec has a valid mask. Some support + * for partial matches exists with a few limitations. First, hardware only + * supports masking by word boundary (2 bytes) and not per individual bit. + * Second, hardware is limited to using one mask for a flow type and cannot + * use a separate mask for each filter. + * + * To support these limitations, if we already have a configured filter for + * the specified type, this function enforces that new filters of the type + * match the configured input set. Otherwise, if we do not have a filter of + * the specified type, we allow the input set to be updated to match the + * desired filter. + * + * To help ensure that administrators understand why filters weren't displayed + * as supported, we print a diagnostic message displaying how the input set + * would change and warning to delete the preexisting filters if required. + * + * Returns 0 on successful input set match, and a negative return code on + * failure. + **/ +static int i40e_check_fdir_input_set(struct i40e_vsi *vsi, + struct ethtool_rx_flow_spec *fsp, + struct i40e_rx_flow_userdef *userdef) +{ + struct i40e_pf *pf = vsi->back; + struct ethtool_tcpip4_spec *tcp_ip4_spec; + struct ethtool_usrip4_spec *usr_ip4_spec; + u64 current_mask, new_mask; + bool new_flex_offset = false; + bool flex_l3 = false; + u16 *fdir_filter_count; + u16 index, src_offset = 0; + u8 pit_index = 0; + int err; + + switch (fsp->flow_type & ~FLOW_EXT) { + case SCTP_V4_FLOW: + index = I40E_FILTER_PCTYPE_NONF_IPV4_SCTP; + fdir_filter_count = &pf->fd_sctp4_filter_cnt; + break; + case TCP_V4_FLOW: + index = I40E_FILTER_PCTYPE_NONF_IPV4_TCP; + fdir_filter_count = &pf->fd_tcp4_filter_cnt; + break; + case UDP_V4_FLOW: + index = I40E_FILTER_PCTYPE_NONF_IPV4_UDP; + fdir_filter_count = &pf->fd_udp4_filter_cnt; + break; + case IP_USER_FLOW: + index = I40E_FILTER_PCTYPE_NONF_IPV4_OTHER; + fdir_filter_count = &pf->fd_ip4_filter_cnt; + flex_l3 = true; + break; + default: + return -EOPNOTSUPP; + } + + /* Read the current input set from register memory. */ + current_mask = i40e_read_fd_input_set(pf, index); + new_mask = current_mask; + + /* Determine, if any, the required changes to the input set in order + * to support the provided mask. + * + * Hardware only supports masking at word (2 byte) granularity and does + * not support full bitwise masking. This implementation simplifies + * even further and only supports fully enabled or fully disabled + * masks for each field, even though we could split the ip4src and + * ip4dst fields. + */ + switch (fsp->flow_type & ~FLOW_EXT) { + case SCTP_V4_FLOW: + new_mask &= ~I40E_VERIFY_TAG_MASK; + /* Fall through */ + case TCP_V4_FLOW: + case UDP_V4_FLOW: + tcp_ip4_spec = &fsp->m_u.tcp_ip4_spec; + + /* IPv4 source address */ + if (tcp_ip4_spec->ip4src == htonl(0xFFFFFFFF)) + new_mask |= I40E_L3_SRC_MASK; + else if (!tcp_ip4_spec->ip4src) + new_mask &= ~I40E_L3_SRC_MASK; + else + return -EOPNOTSUPP; + + /* IPv4 destination address */ + if (tcp_ip4_spec->ip4dst == htonl(0xFFFFFFFF)) + new_mask |= I40E_L3_DST_MASK; + else if (!tcp_ip4_spec->ip4dst) + new_mask &= ~I40E_L3_DST_MASK; + else + return -EOPNOTSUPP; + + /* L4 source port */ + if (tcp_ip4_spec->psrc == htons(0xFFFF)) + new_mask |= I40E_L4_SRC_MASK; + else if (!tcp_ip4_spec->psrc) + new_mask &= ~I40E_L4_SRC_MASK; + else + return -EOPNOTSUPP; + + /* L4 destination port */ + if (tcp_ip4_spec->pdst == htons(0xFFFF)) + new_mask |= I40E_L4_DST_MASK; + else if (!tcp_ip4_spec->pdst) + new_mask &= ~I40E_L4_DST_MASK; + else + return -EOPNOTSUPP; + + /* Filtering on Type of Service is not supported. */ + if (tcp_ip4_spec->tos) + return -EOPNOTSUPP; + + break; + case IP_USER_FLOW: + usr_ip4_spec = &fsp->m_u.usr_ip4_spec; + + /* IPv4 source address */ + if (usr_ip4_spec->ip4src == htonl(0xFFFFFFFF)) + new_mask |= I40E_L3_SRC_MASK; + else if (!usr_ip4_spec->ip4src) + new_mask &= ~I40E_L3_SRC_MASK; + else + return -EOPNOTSUPP; + + /* IPv4 destination address */ + if (usr_ip4_spec->ip4dst == htonl(0xFFFFFFFF)) + new_mask |= I40E_L3_DST_MASK; + else if (!usr_ip4_spec->ip4dst) + new_mask &= ~I40E_L3_DST_MASK; + else + return -EOPNOTSUPP; + + /* First 4 bytes of L4 header */ + if (usr_ip4_spec->l4_4_bytes == htonl(0xFFFFFFFF)) + new_mask |= I40E_L4_SRC_MASK | I40E_L4_DST_MASK; + else if (!usr_ip4_spec->l4_4_bytes) + new_mask &= ~(I40E_L4_SRC_MASK | I40E_L4_DST_MASK); + else + return -EOPNOTSUPP; + + /* Filtering on Type of Service is not supported. */ + if (usr_ip4_spec->tos) + return -EOPNOTSUPP; + + /* Filtering on IP version is not supported */ + if (usr_ip4_spec->ip_ver) + return -EINVAL; + + /* Filtering on L4 protocol is not supported */ + if (usr_ip4_spec->proto) + return -EINVAL; + + break; + default: + return -EOPNOTSUPP; + } + + /* First, clear all flexible filter entries */ + new_mask &= ~I40E_FLEX_INPUT_MASK; + + /* If we have a flexible filter, try to add this offset to the correct + * flexible filter PIT list. Once finished, we can update the mask. + * If the src_offset changed, we will get a new mask value which will + * trigger an input set change. + */ + if (userdef->flex_filter) { + struct i40e_flex_pit *l3_flex_pit = NULL, *flex_pit = NULL; + + /* Flexible offset must be even, since the flexible payload + * must be aligned on 2-byte boundary. + */ + if (userdef->flex_offset & 0x1) { + dev_warn(&pf->pdev->dev, + "Flexible data offset must be 2-byte aligned\n"); + return -EINVAL; + } + + src_offset = userdef->flex_offset >> 1; + + /* FLX_PIT source offset value is only so large */ + if (src_offset > I40E_MAX_FLEX_SRC_OFFSET) { + dev_warn(&pf->pdev->dev, + "Flexible data must reside within first 64 bytes of the packet payload\n"); + return -EINVAL; + } + + /* See if this offset has already been programmed. If we get + * an ERR_PTR, then the filter is not safe to add. Otherwise, + * if we get a NULL pointer, this means we will need to add + * the offset. + */ + flex_pit = i40e_find_flex_offset(&pf->l4_flex_pit_list, + src_offset); + if (IS_ERR(flex_pit)) + return PTR_ERR(flex_pit); + + /* IP_USER_FLOW filters match both L4 (ICMP) and L3 (unknown) + * packet types, and thus we need to program both L3 and L4 + * flexible values. These must have identical flexible index, + * as otherwise we can't correctly program the input set. So + * we'll find both an L3 and L4 index and make sure they are + * the same. + */ + if (flex_l3) { + l3_flex_pit = + i40e_find_flex_offset(&pf->l3_flex_pit_list, + src_offset); + if (IS_ERR(l3_flex_pit)) + return PTR_ERR(l3_flex_pit); + + if (flex_pit) { + /* If we already had a matching L4 entry, we + * need to make sure that the L3 entry we + * obtained uses the same index. + */ + if (l3_flex_pit) { + if (l3_flex_pit->pit_index != + flex_pit->pit_index) { + return -EINVAL; + } + } else { + new_flex_offset = true; + } + } else { + flex_pit = l3_flex_pit; + } + } + + /* If we didn't find an existing flex offset, we need to + * program a new one. However, we don't immediately program it + * here because we will wait to program until after we check + * that it is safe to change the input set. + */ + if (!flex_pit) { + new_flex_offset = true; + pit_index = i40e_unused_pit_index(pf); + } else { + pit_index = flex_pit->pit_index; + } + + /* Update the mask with the new offset */ + new_mask |= i40e_pit_index_to_mask(pit_index); + } + + /* If the mask and flexible filter offsets for this filter match the + * currently programmed values we don't need any input set change, so + * this filter is safe to install. + */ + if (new_mask == current_mask && !new_flex_offset) + return 0; + + netif_info(pf, drv, vsi->netdev, "Input set change requested for %s flows:\n", + i40e_flow_str(fsp)); + i40e_print_input_set(vsi, current_mask, new_mask); + if (new_flex_offset) { + netif_info(pf, drv, vsi->netdev, "FLEX index %d: Offset -> %d", + pit_index, src_offset); + } + + /* Hardware input sets are global across multiple ports, so even the + * main port cannot change them when in MFP mode as this would impact + * any filters on the other ports. + */ + if (pf->flags & I40E_FLAG_MFP_ENABLED) { + netif_err(pf, drv, vsi->netdev, "Cannot change Flow Director input sets while MFP is enabled\n"); + return -EOPNOTSUPP; + } + + /* This filter requires us to update the input set. However, hardware + * only supports one input set per flow type, and does not support + * separate masks for each filter. This means that we can only support + * a single mask for all filters of a specific type. + * + * If we have preexisting filters, they obviously depend on the + * current programmed input set. Display a diagnostic message in this + * case explaining why the filter could not be accepted. + */ + if (*fdir_filter_count) { + netif_err(pf, drv, vsi->netdev, "Cannot change input set for %s flows until %d preexisting filters are removed\n", + i40e_flow_str(fsp), + *fdir_filter_count); + return -EOPNOTSUPP; + } + + i40e_write_fd_input_set(pf, index, new_mask); + + /* Add the new offset and update table, if necessary */ + if (new_flex_offset) { + err = i40e_add_flex_offset(&pf->l4_flex_pit_list, src_offset, + pit_index); + if (err) + return err; + + if (flex_l3) { + err = i40e_add_flex_offset(&pf->l3_flex_pit_list, + src_offset, + pit_index); + if (err) + return err; + } + + i40e_reprogram_flex_pit(pf); + } + + return 0; +} + +/** * i40e_add_fdir_ethtool - Add/Remove Flow Director filters * @vsi: pointer to the targeted VSI * @cmd: command to get or set RX flow classification rules @@ -2699,11 +3628,13 @@ static int i40e_del_fdir_entry(struct i40e_vsi *vsi, static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi, struct ethtool_rxnfc *cmd) { + struct i40e_rx_flow_userdef userdef; struct ethtool_rx_flow_spec *fsp; struct i40e_fdir_filter *input; + u16 dest_vsi = 0, q_index = 0; struct i40e_pf *pf; int ret = -EINVAL; - u16 vf_id; + u8 dest_ctl; if (!vsi) return -EINVAL; @@ -2712,26 +3643,61 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi, if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED)) return -EOPNOTSUPP; - if (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED) + if (pf->flags & I40E_FLAG_FD_SB_AUTO_DISABLED) return -ENOSPC; - if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) || - test_bit(__I40E_RESET_INTR_RECEIVED, &pf->state)) + if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state) || + test_bit(__I40E_RESET_INTR_RECEIVED, pf->state)) return -EBUSY; - if (test_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state)) + if (test_bit(__I40E_FD_FLUSH_REQUESTED, pf->state)) return -EBUSY; fsp = (struct ethtool_rx_flow_spec *)&cmd->fs; + /* Parse the user-defined field */ + if (i40e_parse_rx_flow_user_data(fsp, &userdef)) + return -EINVAL; + + /* Extended MAC field is not supported */ + if (fsp->flow_type & FLOW_MAC_EXT) + return -EINVAL; + + ret = i40e_check_fdir_input_set(vsi, fsp, &userdef); + if (ret) + return ret; + if (fsp->location >= (pf->hw.func_caps.fd_filters_best_effort + pf->hw.func_caps.fd_filters_guaranteed)) { return -EINVAL; } - if ((fsp->ring_cookie != RX_CLS_FLOW_DISC) && - (fsp->ring_cookie >= vsi->num_queue_pairs)) - return -EINVAL; + /* ring_cookie is either the drop index, or is a mask of the queue + * index and VF id we wish to target. + */ + if (fsp->ring_cookie == RX_CLS_FLOW_DISC) { + dest_ctl = I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET; + } else { + u32 ring = ethtool_get_flow_spec_ring(fsp->ring_cookie); + u8 vf = ethtool_get_flow_spec_ring_vf(fsp->ring_cookie); + + if (!vf) { + if (ring >= vsi->num_queue_pairs) + return -EINVAL; + dest_vsi = vsi->id; + } else { + /* VFs are zero-indexed, so we subtract one here */ + vf--; + + if (vf >= pf->num_alloc_vfs) + return -EINVAL; + if (ring >= pf->vf[vf].num_queue_pairs) + return -EINVAL; + dest_vsi = pf->vf[vf].lan_vsi_id; + } + dest_ctl = I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_QINDEX; + q_index = ring; + } input = kzalloc(sizeof(*input), GFP_KERNEL); @@ -2739,20 +3705,14 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi, return -ENOMEM; input->fd_id = fsp->location; - - if (fsp->ring_cookie == RX_CLS_FLOW_DISC) - input->dest_ctl = I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET; - else - input->dest_ctl = - I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_QINDEX; - - input->q_index = fsp->ring_cookie; - input->flex_off = 0; - input->pctype = 0; - input->dest_vsi = vsi->id; + input->q_index = q_index; + input->dest_vsi = dest_vsi; + input->dest_ctl = dest_ctl; input->fd_status = I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID; input->cnt_index = I40E_FD_SB_STAT_IDX(pf->hw.pf_id); - input->flow_type = fsp->flow_type; + input->dst_ip = fsp->h_u.tcp_ip4_spec.ip4src; + input->src_ip = fsp->h_u.tcp_ip4_spec.ip4dst; + input->flow_type = fsp->flow_type & ~FLOW_EXT; input->ip4_proto = fsp->h_u.usr_ip4_spec.proto; /* Reverse the src and dest notion, since the HW expects them to be from @@ -2760,33 +3720,29 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi, */ input->dst_port = fsp->h_u.tcp_ip4_spec.psrc; input->src_port = fsp->h_u.tcp_ip4_spec.pdst; - input->dst_ip[0] = fsp->h_u.tcp_ip4_spec.ip4src; - input->src_ip[0] = fsp->h_u.tcp_ip4_spec.ip4dst; - - if (ntohl(fsp->m_ext.data[1])) { - vf_id = ntohl(fsp->h_ext.data[1]); - if (vf_id >= pf->num_alloc_vfs) { - netif_info(pf, drv, vsi->netdev, - "Invalid VF id %d\n", vf_id); - goto free_input; - } - /* Find vsi id from vf id and override dest vsi */ - input->dest_vsi = pf->vf[vf_id].lan_vsi_id; - if (input->q_index >= pf->vf[vf_id].num_queue_pairs) { - netif_info(pf, drv, vsi->netdev, - "Invalid queue id %d for VF %d\n", - input->q_index, vf_id); - goto free_input; - } + input->dst_ip = fsp->h_u.tcp_ip4_spec.ip4src; + input->src_ip = fsp->h_u.tcp_ip4_spec.ip4dst; + + if (userdef.flex_filter) { + input->flex_filter = true; + input->flex_word = cpu_to_be16(userdef.flex_word); + input->flex_offset = userdef.flex_offset; } ret = i40e_add_del_fdir(vsi, input, true); -free_input: if (ret) - kfree(input); - else - i40e_update_ethtool_fdir_entry(vsi, input, fsp->location, NULL); + goto free_input; + + /* Add the input filter to the fdir_input_list, possibly replacing + * a previous filter. Do not free the input structure after adding it + * to the list as this would cause a use-after-free bug. + */ + i40e_update_ethtool_fdir_entry(vsi, input, fsp->location, NULL); + return 0; + +free_input: + kfree(input); return ret; } @@ -3036,7 +3992,7 @@ static int i40e_set_rxfh(struct net_device *netdev, const u32 *indir, * @dev: network interface device structure * * The get string set count and the string set should be matched for each - * flag returned. Add new strings for each flag to the i40e_priv_flags_strings + * flag returned. Add new strings for each flag to the i40e_gstrings_priv_flags * array. * * Returns a u32 bitmap of flags. @@ -3046,19 +4002,27 @@ static u32 i40e_get_priv_flags(struct net_device *dev) struct i40e_netdev_priv *np = netdev_priv(dev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - u32 ret_flags = 0; + u32 i, j, ret_flags = 0; + + for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++) { + const struct i40e_priv_flags *priv_flags; + + priv_flags = &i40e_gstrings_priv_flags[i]; + + if (priv_flags->flag & pf->flags) + ret_flags |= BIT(i); + } + + if (pf->hw.pf_id != 0) + return ret_flags; + + for (j = 0; j < I40E_GL_PRIV_FLAGS_STR_LEN; j++) { + const struct i40e_priv_flags *priv_flags; - ret_flags |= pf->flags & I40E_FLAG_LINK_POLLING_ENABLED ? - I40E_PRIV_FLAGS_LINKPOLL_FLAG : 0; - ret_flags |= pf->flags & I40E_FLAG_FD_ATR_ENABLED ? - I40E_PRIV_FLAGS_FD_ATR : 0; - ret_flags |= pf->flags & I40E_FLAG_VEB_STATS_ENABLED ? - I40E_PRIV_FLAGS_VEB_STATS : 0; - ret_flags |= pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE ? - 0 : I40E_PRIV_FLAGS_HW_ATR_EVICT; - if (pf->hw.pf_id == 0) { - ret_flags |= pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT ? - I40E_PRIV_FLAGS_TRUE_PROMISC_SUPPORT : 0; + priv_flags = &i40e_gl_gstrings_priv_flags[j]; + + if (priv_flags->flag & pf->flags) + ret_flags |= BIT(i + j); } return ret_flags; @@ -3074,54 +4038,66 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) struct i40e_netdev_priv *np = netdev_priv(dev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - u16 sw_flags = 0, valid_flags = 0; - bool reset_required = false; - bool promisc_change = false; - int ret; + u64 changed_flags; + u32 i, j; - /* NOTE: MFP is not settable */ + changed_flags = pf->flags; - if (flags & I40E_PRIV_FLAGS_LINKPOLL_FLAG) - pf->flags |= I40E_FLAG_LINK_POLLING_ENABLED; - else - pf->flags &= ~I40E_FLAG_LINK_POLLING_ENABLED; + for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++) { + const struct i40e_priv_flags *priv_flags; - /* allow the user to control the state of the Flow - * Director ATR (Application Targeted Routing) feature - * of the driver + priv_flags = &i40e_gstrings_priv_flags[i]; + + if (priv_flags->read_only) + continue; + + if (flags & BIT(i)) + pf->flags |= priv_flags->flag; + else + pf->flags &= ~(priv_flags->flag); + } + + if (pf->hw.pf_id != 0) + goto flags_complete; + + for (j = 0; j < I40E_GL_PRIV_FLAGS_STR_LEN; j++) { + const struct i40e_priv_flags *priv_flags; + + priv_flags = &i40e_gl_gstrings_priv_flags[j]; + + if (priv_flags->read_only) + continue; + + if (flags & BIT(i + j)) + pf->flags |= priv_flags->flag; + else + pf->flags &= ~(priv_flags->flag); + } + +flags_complete: + /* check for flags that changed */ + changed_flags ^= pf->flags; + + /* Process any additional changes needed as a result of flag changes. + * The changed_flags value reflects the list of bits that were + * changed in the code above. */ - if (flags & I40E_PRIV_FLAGS_FD_ATR) { - pf->flags |= I40E_FLAG_FD_ATR_ENABLED; - } else { - pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED; - pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED; - - /* flush current ATR settings */ - set_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state); - } - - if ((flags & I40E_PRIV_FLAGS_VEB_STATS) && - !(pf->flags & I40E_FLAG_VEB_STATS_ENABLED)) { - pf->flags |= I40E_FLAG_VEB_STATS_ENABLED; - reset_required = true; - } else if (!(flags & I40E_PRIV_FLAGS_VEB_STATS) && - (pf->flags & I40E_FLAG_VEB_STATS_ENABLED)) { - pf->flags &= ~I40E_FLAG_VEB_STATS_ENABLED; - reset_required = true; - } - - if (pf->hw.pf_id == 0) { - if ((flags & I40E_PRIV_FLAGS_TRUE_PROMISC_SUPPORT) && - !(pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT)) { - pf->flags |= I40E_FLAG_TRUE_PROMISC_SUPPORT; - promisc_change = true; - } else if (!(flags & I40E_PRIV_FLAGS_TRUE_PROMISC_SUPPORT) && - (pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT)) { - pf->flags &= ~I40E_FLAG_TRUE_PROMISC_SUPPORT; - promisc_change = true; - } + + /* Flush current ATR settings if ATR was disabled */ + if ((changed_flags & I40E_FLAG_FD_ATR_ENABLED) && + !(pf->flags & I40E_FLAG_FD_ATR_ENABLED)) { + pf->flags |= I40E_FLAG_FD_ATR_AUTO_DISABLED; + set_bit(__I40E_FD_FLUSH_REQUESTED, pf->state); } - if (promisc_change) { + + /* Only allow ATR evict on hardware that is capable of handling it */ + if (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) + pf->flags &= ~I40E_FLAG_HW_ATR_EVICT_CAPABLE; + + if (changed_flags & I40E_FLAG_TRUE_PROMISC_SUPPORT) { + u16 sw_flags = 0, valid_flags = 0; + int ret; + if (!(pf->flags & I40E_FLAG_TRUE_PROMISC_SUPPORT)) sw_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC; valid_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC; @@ -3137,22 +4113,17 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) } } - if ((flags & I40E_PRIV_FLAGS_HW_ATR_EVICT) && - (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE)) - pf->auto_disable_flags &= ~I40E_FLAG_HW_ATR_EVICT_CAPABLE; - else - pf->auto_disable_flags |= I40E_FLAG_HW_ATR_EVICT_CAPABLE; - - /* if needed, issue reset to cause things to take effect */ - if (reset_required) - i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED)); + /* Issue reset to cause things to take effect, as additional bits + * are added we will need to create a mask of bits requiring reset + */ + if ((changed_flags & I40E_FLAG_VEB_STATS_ENABLED) || + ((changed_flags & I40E_FLAG_LEGACY_RX) && netif_running(dev))) + i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true); return 0; } static const struct ethtool_ops i40e_ethtool_ops = { - .get_settings = i40e_get_settings, - .set_settings = i40e_set_settings, .get_drvinfo = i40e_get_drvinfo, .get_regs_len = i40e_get_regs_len, .get_regs = i40e_get_regs, @@ -3189,6 +4160,8 @@ static const struct ethtool_ops i40e_ethtool_ops = { .set_priv_flags = i40e_set_priv_flags, .get_per_queue_coalesce = i40e_get_per_queue_coalesce, .set_per_queue_coalesce = i40e_set_per_queue_coalesce, + .get_link_ksettings = i40e_get_link_ksettings, + .set_link_ksettings = i40e_set_link_ksettings, }; void i40e_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 82a95cc2c8ee..d5c9c9e06ff5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -32,6 +32,12 @@ #include "i40e.h" #include "i40e_diag.h" #include <net/udp_tunnel.h> +/* All i40e tracepoints are defined by the include below, which + * must be included exactly once across the whole kernel with + * CREATE_TRACE_POINTS defined + */ +#define CREATE_TRACE_POINTS +#include "i40e_trace.h" const char i40e_driver_name[] = "i40e"; static const char i40e_driver_string[] = @@ -39,9 +45,9 @@ static const char i40e_driver_string[] = #define DRV_KERN "-k" -#define DRV_VERSION_MAJOR 1 -#define DRV_VERSION_MINOR 6 -#define DRV_VERSION_BUILD 27 +#define DRV_VERSION_MAJOR 2 +#define DRV_VERSION_MINOR 1 +#define DRV_VERSION_BUILD 14 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) DRV_KERN @@ -50,13 +56,16 @@ static const char i40e_copyright[] = "Copyright (c) 2013 - 2014 Intel Corporatio /* a bit of forward declarations */ static void i40e_vsi_reinit_locked(struct i40e_vsi *vsi); -static void i40e_handle_reset_warning(struct i40e_pf *pf); +static void i40e_handle_reset_warning(struct i40e_pf *pf, bool lock_acquired); static int i40e_add_vsi(struct i40e_vsi *vsi); static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi); static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit); static int i40e_setup_misc_vector(struct i40e_pf *pf); static void i40e_determine_queue_usage(struct i40e_pf *pf); static int i40e_setup_pf_filter_control(struct i40e_pf *pf); +static void i40e_prep_for_reset(struct i40e_pf *pf, bool lock_acquired); +static int i40e_reset(struct i40e_pf *pf); +static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired); static void i40e_fdir_sb_setup(struct i40e_pf *pf); static int i40e_veb_get_bw_info(struct i40e_veb *veb); @@ -286,8 +295,8 @@ struct i40e_vsi *i40e_find_vsi_from_id(struct i40e_pf *pf, u16 id) **/ void i40e_service_event_schedule(struct i40e_pf *pf) { - if (!test_bit(__I40E_DOWN, &pf->state) && - !test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state)) + if (!test_bit(__I40E_VSI_DOWN, pf->state) && + !test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) queue_work(i40e_wq, &pf->service_task); } @@ -299,11 +308,7 @@ void i40e_service_event_schedule(struct i40e_pf *pf) * device is munged, not just the one netdev port, so go for the full * reset. **/ -#ifdef I40E_FCOE -void i40e_tx_timeout(struct net_device *netdev) -#else static void i40e_tx_timeout(struct net_device *netdev) -#endif { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; @@ -372,13 +377,13 @@ static void i40e_tx_timeout(struct net_device *netdev) switch (pf->tx_timeout_recovery_level) { case 1: - set_bit(__I40E_PF_RESET_REQUESTED, &pf->state); + set_bit(__I40E_PF_RESET_REQUESTED, pf->state); break; case 2: - set_bit(__I40E_CORE_RESET_REQUESTED, &pf->state); + set_bit(__I40E_CORE_RESET_REQUESTED, pf->state); break; case 3: - set_bit(__I40E_GLOBAL_RESET_REQUESTED, &pf->state); + set_bit(__I40E_GLOBAL_RESET_REQUESTED, pf->state); break; default: netdev_err(netdev, "tx_timeout recovery unsuccessful\n"); @@ -408,10 +413,7 @@ struct rtnl_link_stats64 *i40e_get_vsi_stats_struct(struct i40e_vsi *vsi) * Returns the address of the device statistics structure. * The statistics are actually updated from the service task. **/ -#ifndef I40E_FCOE -static -#endif -void i40e_get_netdev_stats_struct(struct net_device *netdev, +static void i40e_get_netdev_stats_struct(struct net_device *netdev, struct rtnl_link_stats64 *stats) { struct i40e_netdev_priv *np = netdev_priv(netdev); @@ -420,7 +422,7 @@ void i40e_get_netdev_stats_struct(struct net_device *netdev, struct rtnl_link_stats64 *vsi_stats = i40e_get_vsi_stats_struct(vsi); int i; - if (test_bit(__I40E_DOWN, &vsi->state)) + if (test_bit(__I40E_VSI_DOWN, vsi->state)) return; if (!vsi->tx_rings) @@ -723,55 +725,6 @@ static void i40e_update_veb_stats(struct i40e_veb *veb) veb->stat_offsets_loaded = true; } -#ifdef I40E_FCOE -/** - * i40e_update_fcoe_stats - Update FCoE-specific ethernet statistics counters. - * @vsi: the VSI that is capable of doing FCoE - **/ -static void i40e_update_fcoe_stats(struct i40e_vsi *vsi) -{ - struct i40e_pf *pf = vsi->back; - struct i40e_hw *hw = &pf->hw; - struct i40e_fcoe_stats *ofs; - struct i40e_fcoe_stats *fs; /* device's eth stats */ - int idx; - - if (vsi->type != I40E_VSI_FCOE) - return; - - idx = hw->pf_id + I40E_FCOE_PF_STAT_OFFSET; - fs = &vsi->fcoe_stats; - ofs = &vsi->fcoe_stats_offsets; - - i40e_stat_update32(hw, I40E_GL_FCOEPRC(idx), - vsi->fcoe_stat_offsets_loaded, - &ofs->rx_fcoe_packets, &fs->rx_fcoe_packets); - i40e_stat_update48(hw, I40E_GL_FCOEDWRCH(idx), I40E_GL_FCOEDWRCL(idx), - vsi->fcoe_stat_offsets_loaded, - &ofs->rx_fcoe_dwords, &fs->rx_fcoe_dwords); - i40e_stat_update32(hw, I40E_GL_FCOERPDC(idx), - vsi->fcoe_stat_offsets_loaded, - &ofs->rx_fcoe_dropped, &fs->rx_fcoe_dropped); - i40e_stat_update32(hw, I40E_GL_FCOEPTC(idx), - vsi->fcoe_stat_offsets_loaded, - &ofs->tx_fcoe_packets, &fs->tx_fcoe_packets); - i40e_stat_update48(hw, I40E_GL_FCOEDWTCH(idx), I40E_GL_FCOEDWTCL(idx), - vsi->fcoe_stat_offsets_loaded, - &ofs->tx_fcoe_dwords, &fs->tx_fcoe_dwords); - i40e_stat_update32(hw, I40E_GL_FCOECRC(idx), - vsi->fcoe_stat_offsets_loaded, - &ofs->fcoe_bad_fccrc, &fs->fcoe_bad_fccrc); - i40e_stat_update32(hw, I40E_GL_FCOELAST(idx), - vsi->fcoe_stat_offsets_loaded, - &ofs->fcoe_last_error, &fs->fcoe_last_error); - i40e_stat_update32(hw, I40E_GL_FCOEDDPC(idx), - vsi->fcoe_stat_offsets_loaded, - &ofs->fcoe_ddp_count, &fs->fcoe_ddp_count); - - vsi->fcoe_stat_offsets_loaded = true; -} - -#endif /** * i40e_update_vsi_stats - Update the vsi statistics counters. * @vsi: the VSI to be updated @@ -790,7 +743,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) struct i40e_eth_stats *oes; struct i40e_eth_stats *es; /* device's eth stats */ u32 tx_restart, tx_busy; - u64 tx_lost_interrupt; struct i40e_ring *p; u32 rx_page, rx_buf; u64 bytes, packets; @@ -801,8 +753,8 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) u64 tx_p, tx_b; u16 q; - if (test_bit(__I40E_DOWN, &vsi->state) || - test_bit(__I40E_CONFIG_BUSY, &pf->state)) + if (test_bit(__I40E_VSI_DOWN, vsi->state) || + test_bit(__I40E_CONFIG_BUSY, pf->state)) return; ns = i40e_get_vsi_stats_struct(vsi); @@ -816,7 +768,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) rx_b = rx_p = 0; tx_b = tx_p = 0; tx_restart = tx_busy = tx_linearize = tx_force_wb = 0; - tx_lost_interrupt = 0; rx_page = 0; rx_buf = 0; rcu_read_lock(); @@ -835,7 +786,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) tx_busy += p->tx_stats.tx_busy; tx_linearize += p->tx_stats.tx_linearize; tx_force_wb += p->tx_stats.tx_force_wb; - tx_lost_interrupt += p->tx_stats.tx_lost_interrupt; /* Rx queue is part of the same block as Tx queue */ p = &p[1]; @@ -854,7 +804,6 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) vsi->tx_busy = tx_busy; vsi->tx_linearize = tx_linearize; vsi->tx_force_wb = tx_force_wb; - vsi->tx_lost_interrupt = tx_lost_interrupt; vsi->rx_page_failed = rx_page; vsi->rx_buf_failed = rx_buf; @@ -1101,13 +1050,13 @@ static void i40e_update_pf_stats(struct i40e_pf *pf) &osd->rx_lpi_count, &nsd->rx_lpi_count); if (pf->flags & I40E_FLAG_FD_SB_ENABLED && - !(pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) + !(pf->flags & I40E_FLAG_FD_SB_AUTO_DISABLED)) nsd->fd_sb_status = true; else nsd->fd_sb_status = false; if (pf->flags & I40E_FLAG_FD_ATR_ENABLED && - !(pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) + !(pf->flags & I40E_FLAG_FD_ATR_AUTO_DISABLED)) nsd->fd_atr_status = true; else nsd->fd_atr_status = false; @@ -1129,9 +1078,6 @@ void i40e_update_stats(struct i40e_vsi *vsi) i40e_update_pf_stats(pf); i40e_update_vsi_stats(vsi); -#ifdef I40E_FCOE - i40e_update_fcoe_stats(vsi); -#endif } /** @@ -1400,7 +1346,7 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi, * to failed, so we don't bother to try sending the filter * to the hardware. */ - if (test_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state)) + if (test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state)) f->state = I40E_FILTER_FAILED; else f->state = I40E_FILTER_NEW; @@ -1562,11 +1508,7 @@ int i40e_del_mac_filter(struct i40e_vsi *vsi, const u8 *macaddr) * * Returns 0 on success, negative on failure **/ -#ifdef I40E_FCOE -int i40e_set_mac(struct net_device *netdev, void *p) -#else static int i40e_set_mac(struct net_device *netdev, void *p) -#endif { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; @@ -1583,8 +1525,8 @@ static int i40e_set_mac(struct net_device *netdev, void *p) return 0; } - if (test_bit(__I40E_DOWN, &vsi->back->state) || - test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state)) + if (test_bit(__I40E_VSI_DOWN, vsi->back->state) || + test_bit(__I40E_RESET_RECOVERY_PENDING, vsi->back->state)) return -EADDRNOTAVAIL; if (ether_addr_equal(hw->mac.addr, addr->sa_data)) @@ -1626,17 +1568,10 @@ static int i40e_set_mac(struct net_device *netdev, void *p) * * Setup VSI queue mapping for enabled traffic classes. **/ -#ifdef I40E_FCOE -void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, - struct i40e_vsi_context *ctxt, - u8 enabled_tc, - bool is_add) -#else static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, struct i40e_vsi_context *ctxt, u8 enabled_tc, bool is_add) -#endif { struct i40e_pf *pf = vsi->back; u16 sections = 0; @@ -1686,11 +1621,6 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, qcount = min_t(int, pf->alloc_rss_size, num_tc_qps); break; -#ifdef I40E_FCOE - case I40E_VSI_FCOE: - qcount = num_tc_qps; - break; -#endif case I40E_VSI_FDIR: case I40E_VSI_SRIOV: case I40E_VSI_VMDQ2: @@ -1800,11 +1730,7 @@ static int i40e_addr_unsync(struct net_device *netdev, const u8 *addr) * i40e_set_rx_mode - NDO callback to set the netdev filters * @netdev: network interface device structure **/ -#ifdef I40E_FCOE -void i40e_set_rx_mode(struct net_device *netdev) -#else static void i40e_set_rx_mode(struct net_device *netdev) -#endif { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; @@ -1883,19 +1809,12 @@ static void i40e_undo_add_filter_entries(struct i40e_vsi *vsi, static struct i40e_new_mac_filter *i40e_next_filter(struct i40e_new_mac_filter *next) { - while (next) { - next = hlist_entry(next->hlist.next, - typeof(struct i40e_new_mac_filter), - hlist); - - /* keep going if we found a broadcast filter */ - if (next && is_broadcast_ether_addr(next->f->macaddr)) - continue; - - break; + hlist_for_each_entry_continue(next, hlist) { + if (!is_broadcast_ether_addr(next->f->macaddr)) + return next; } - return next; + return NULL; } /** @@ -2001,7 +1920,7 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name, if (fcnt != num_add) { *promisc_changed = true; - set_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state); + set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); dev_warn(&vsi->back->pdev->dev, "Error %s adding RX filters on %s, promiscuous mode forced on\n", i40e_aq_str(hw, aq_err), @@ -2084,7 +2003,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) struct i40e_aqc_add_macvlan_element_data *add_list; struct i40e_aqc_remove_macvlan_element_data *del_list; - while (test_and_set_bit(__I40E_CONFIG_BUSY, &vsi->state)) + while (test_and_set_bit(__I40E_VSI_SYNCING_FILTERS, vsi->state)) usleep_range(1000, 2000); pf = vsi->back; @@ -2220,8 +2139,8 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) num_add = 0; hlist_for_each_entry_safe(new, h, &tmp_add_list, hlist) { - if (test_bit(__I40E_FILTER_OVERFLOW_PROMISC, - &vsi->state)) { + if (test_bit(__I40E_VSI_OVERFLOW_PROMISC, + vsi->state)) { new->state = I40E_FILTER_FAILED; continue; } @@ -2308,20 +2227,20 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) * safely exit if we didn't just enter, we no longer have any failed * filters, and we have reduced filters below the threshold value. */ - if (test_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state) && + if (test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state) && !promisc_changed && !failed_filters && (vsi->active_filters < vsi->promisc_threshold)) { dev_info(&pf->pdev->dev, "filter logjam cleared on %s, leaving overflow promiscuous mode\n", vsi_name); - clear_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state); + clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); promisc_changed = true; vsi->promisc_threshold = 0; } /* if the VF is not trusted do not do promisc */ if ((vsi->type == I40E_VSI_SRIOV) && !pf->vf[vsi->vf_id].trusted) { - clear_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state); + clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); goto out; } @@ -2346,12 +2265,12 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) } if ((changed_flags & IFF_PROMISC) || (promisc_changed && - test_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state))) { + test_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state))) { bool cur_promisc; cur_promisc = (!!(vsi->current_netdev_flags & IFF_PROMISC) || - test_bit(__I40E_FILTER_OVERFLOW_PROMISC, - &vsi->state)); + test_bit(__I40E_VSI_OVERFLOW_PROMISC, + vsi->state)); if ((vsi->type == I40E_VSI_MAIN) && (pf->lan_veb != I40E_NO_VEB) && !(pf->flags & I40E_FLAG_MFP_ENABLED)) { @@ -2434,7 +2353,7 @@ out: if (retval) vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; - clear_bit(__I40E_CONFIG_BUSY, &vsi->state); + clear_bit(__I40E_VSI_SYNCING_FILTERS, vsi->state); return retval; err_no_memory: @@ -2446,7 +2365,7 @@ err_no_memory_locked: spin_unlock_bh(&vsi->mac_filter_hash_lock); vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; - clear_bit(__I40E_CONFIG_BUSY, &vsi->state); + clear_bit(__I40E_VSI_SYNCING_FILTERS, vsi->state); return -ENOMEM; } @@ -2487,13 +2406,15 @@ static int i40e_change_mtu(struct net_device *netdev, int new_mtu) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; + struct i40e_pf *pf = vsi->back; netdev_info(netdev, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); netdev->mtu = new_mtu; if (netif_running(netdev)) i40e_vsi_reinit_locked(vsi); - i40e_notify_client_of_l2_param_changes(vsi); + pf->flags |= (I40E_FLAG_SERVICE_CLIENT_REQUESTED | + I40E_FLAG_CLIENT_L2_CHANGE); return 0; } @@ -2707,13 +2628,8 @@ void i40e_vsi_kill_vlan(struct i40e_vsi *vsi, u16 vid) * * net_device_ops implementation for adding vlan ids **/ -#ifdef I40E_FCOE -int i40e_vlan_rx_add_vid(struct net_device *netdev, - __always_unused __be16 proto, u16 vid) -#else static int i40e_vlan_rx_add_vid(struct net_device *netdev, __always_unused __be16 proto, u16 vid) -#endif { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; @@ -2744,13 +2660,8 @@ static int i40e_vlan_rx_add_vid(struct net_device *netdev, * * net_device_ops implementation for removing vlan ids **/ -#ifdef I40E_FCOE -int i40e_vlan_rx_kill_vid(struct net_device *netdev, - __always_unused __be16 proto, u16 vid) -#else static int i40e_vlan_rx_kill_vid(struct net_device *netdev, __always_unused __be16 proto, u16 vid) -#endif { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; @@ -2920,9 +2831,6 @@ static int i40e_vsi_setup_rx_resources(struct i40e_vsi *vsi) for (i = 0; i < vsi->num_queue_pairs && !err; i++) err = i40e_setup_rx_descriptors(vsi->rx_rings[i]); -#ifdef I40E_FCOE - i40e_fcoe_setup_ddp_resources(vsi); -#endif return err; } @@ -2942,9 +2850,6 @@ static void i40e_vsi_free_rx_resources(struct i40e_vsi *vsi) for (i = 0; i < vsi->num_queue_pairs; i++) if (vsi->rx_rings[i] && vsi->rx_rings[i]->desc) i40e_free_rx_resources(vsi->rx_rings[i]); -#ifdef I40E_FCOE - i40e_fcoe_free_ddp_resources(vsi); -#endif } /** @@ -3015,9 +2920,6 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring) tx_ctx.qlen = ring->count; tx_ctx.fd_ena = !!(vsi->back->flags & (I40E_FLAG_FD_SB_ENABLED | I40E_FLAG_FD_ATR_ENABLED)); -#ifdef I40E_FCOE - tx_ctx.fc_ena = (vsi->type == I40E_VSI_FCOE); -#endif tx_ctx.timesync_ena = !!(vsi->back->flags & I40E_FLAG_PTP); /* FDIR VSI tx ring can still use RS bit and writebacks */ if (vsi->type != I40E_VSI_FDIR) @@ -3098,7 +3000,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) ring->rx_buf_len = vsi->rx_buf_len; - rx_ctx.dbuff = ring->rx_buf_len >> I40E_RXQ_CTX_DBUFF_SHIFT; + rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len, + BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT)); rx_ctx.base = (ring->dma / 128); rx_ctx.qlen = ring->count; @@ -3120,9 +3023,6 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) rx_ctx.l2tsel = 1; /* this controls whether VLAN is stripped from inner headers */ rx_ctx.showiv = 0; -#ifdef I40E_FCOE - rx_ctx.fc_ena = (vsi->type == I40E_VSI_FCOE); -#endif /* set the prefena field to 1 because the manual says to */ rx_ctx.prefena = 1; @@ -3144,6 +3044,12 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) return -ENOMEM; } + /* configure Rx buffer alignment */ + if (!vsi->netdev || (vsi->back->flags & I40E_FLAG_LEGACY_RX)) + clear_ring_build_skb_enabled(ring); + else + set_ring_build_skb_enabled(ring); + /* cache tail for quicker writes, and clear the reg before use */ ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q); writel(0, ring->tail); @@ -3181,27 +3087,21 @@ static int i40e_vsi_configure_rx(struct i40e_vsi *vsi) int err = 0; u16 i; - if (vsi->netdev && (vsi->netdev->mtu > ETH_DATA_LEN)) - vsi->max_frame = vsi->netdev->mtu + ETH_HLEN - + ETH_FCS_LEN + VLAN_HLEN; - else - vsi->max_frame = I40E_RXBUFFER_2048; - - vsi->rx_buf_len = I40E_RXBUFFER_2048; - -#ifdef I40E_FCOE - /* setup rx buffer for FCoE */ - if ((vsi->type == I40E_VSI_FCOE) && - (vsi->back->flags & I40E_FLAG_FCOE_ENABLED)) { - vsi->rx_buf_len = I40E_RXBUFFER_3072; - vsi->max_frame = I40E_RXBUFFER_3072; + if (!vsi->netdev || (vsi->back->flags & I40E_FLAG_LEGACY_RX)) { + vsi->max_frame = I40E_MAX_RXBUFFER; + vsi->rx_buf_len = I40E_RXBUFFER_2048; +#if (PAGE_SIZE < 8192) + } else if (!I40E_2K_TOO_SMALL_WITH_PADDING && + (vsi->netdev->mtu <= ETH_DATA_LEN)) { + vsi->max_frame = I40E_RXBUFFER_1536 - NET_IP_ALIGN; + vsi->rx_buf_len = I40E_RXBUFFER_1536 - NET_IP_ALIGN; +#endif + } else { + vsi->max_frame = I40E_MAX_RXBUFFER; + vsi->rx_buf_len = (PAGE_SIZE < 8192) ? I40E_RXBUFFER_3072 : + I40E_RXBUFFER_2048; } -#endif /* I40E_FCOE */ - /* round up for the chip's needs */ - vsi->rx_buf_len = ALIGN(vsi->rx_buf_len, - BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT)); - /* set up individual rings */ for (i = 0; i < vsi->num_queue_pairs && !err; i++) err = i40e_configure_rx_ring(vsi->rx_rings[i]); @@ -3281,6 +3181,12 @@ static void i40e_fdir_filter_restore(struct i40e_vsi *vsi) if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED)) return; + /* Reset FDir counters as we're replaying all existing filters */ + pf->fd_tcp4_filter_cnt = 0; + pf->fd_udp4_filter_cnt = 0; + pf->fd_sctp4_filter_cnt = 0; + pf->fd_ip4_filter_cnt = 0; + hlist_for_each_entry_safe(filter, node, &pf->fdir_filter_list, fdir_node) { i40e_add_del_fdir(vsi, filter, true); @@ -3705,29 +3611,29 @@ static irqreturn_t i40e_intr(int irq, void *data) * this is not a performance path and napi_schedule() * can deal with rescheduling. */ - if (!test_bit(__I40E_DOWN, &pf->state)) + if (!test_bit(__I40E_VSI_DOWN, pf->state)) napi_schedule_irqoff(&q_vector->napi); } if (icr0 & I40E_PFINT_ICR0_ADMINQ_MASK) { ena_mask &= ~I40E_PFINT_ICR0_ENA_ADMINQ_MASK; - set_bit(__I40E_ADMINQ_EVENT_PENDING, &pf->state); + set_bit(__I40E_ADMINQ_EVENT_PENDING, pf->state); i40e_debug(&pf->hw, I40E_DEBUG_NVM, "AdminQ event\n"); } if (icr0 & I40E_PFINT_ICR0_MAL_DETECT_MASK) { ena_mask &= ~I40E_PFINT_ICR0_ENA_MAL_DETECT_MASK; - set_bit(__I40E_MDD_EVENT_PENDING, &pf->state); + set_bit(__I40E_MDD_EVENT_PENDING, pf->state); } if (icr0 & I40E_PFINT_ICR0_VFLR_MASK) { ena_mask &= ~I40E_PFINT_ICR0_ENA_VFLR_MASK; - set_bit(__I40E_VFLR_EVENT_PENDING, &pf->state); + set_bit(__I40E_VFLR_EVENT_PENDING, pf->state); } if (icr0 & I40E_PFINT_ICR0_GRST_MASK) { - if (!test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state)) - set_bit(__I40E_RESET_INTR_RECEIVED, &pf->state); + if (!test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) + set_bit(__I40E_RESET_INTR_RECEIVED, pf->state); ena_mask &= ~I40E_PFINT_ICR0_ENA_GRST_MASK; val = rd32(hw, I40E_GLGEN_RSTAT); val = (val & I40E_GLGEN_RSTAT_RESET_TYPE_MASK) @@ -3738,7 +3644,7 @@ static irqreturn_t i40e_intr(int irq, void *data) pf->globr_count++; } else if (val == I40E_RESET_EMPR) { pf->empr_count++; - set_bit(__I40E_EMP_RESET_INTR_RECEIVED, &pf->state); + set_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state); } } @@ -3771,7 +3677,7 @@ static irqreturn_t i40e_intr(int irq, void *data) (icr0_remaining & I40E_PFINT_ICR0_PCI_EXCEPTION_MASK) || (icr0_remaining & I40E_PFINT_ICR0_ECC_ERR_MASK)) { dev_info(&pf->pdev->dev, "device will be reset\n"); - set_bit(__I40E_PF_RESET_REQUESTED, &pf->state); + set_bit(__I40E_PF_RESET_REQUESTED, pf->state); i40e_service_event_schedule(pf); } ena_mask &= ~icr0_remaining; @@ -3781,7 +3687,7 @@ static irqreturn_t i40e_intr(int irq, void *data) enable_intr: /* re-enable interrupt causes */ wr32(hw, I40E_PFINT_ICR0_ENA, ena_mask); - if (!test_bit(__I40E_DOWN, &pf->state)) { + if (!test_bit(__I40E_VSI_DOWN, pf->state)) { i40e_service_event_schedule(pf); i40e_irq_dynamic_enable_icr0(pf, false); } @@ -3993,11 +3899,7 @@ static int i40e_vsi_request_irq(struct i40e_vsi *vsi, char *basename) * This is used by netconsole to send skbs without having to re-enable * interrupts. It's not called while the normal interrupt routine is executing. **/ -#ifdef I40E_FCOE -void i40e_netpoll(struct net_device *netdev) -#else static void i40e_netpoll(struct net_device *netdev) -#endif { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; @@ -4005,7 +3907,7 @@ static void i40e_netpoll(struct net_device *netdev) int i; /* if interface is down do nothing */ - if (test_bit(__I40E_DOWN, &vsi->state)) + if (test_bit(__I40E_VSI_DOWN, vsi->state)) return; if (pf->flags & I40E_FLAG_MSIX_ENABLED) { @@ -4017,6 +3919,8 @@ static void i40e_netpoll(struct net_device *netdev) } #endif +#define I40E_QTX_ENA_WAIT_COUNT 50 + /** * i40e_pf_txq_wait - Wait for a PF's Tx queue to be enabled or disabled * @pf: the PF being configured @@ -4047,6 +3951,50 @@ static int i40e_pf_txq_wait(struct i40e_pf *pf, int pf_q, bool enable) } /** + * i40e_control_tx_q - Start or stop a particular Tx queue + * @pf: the PF structure + * @pf_q: the PF queue to configure + * @enable: start or stop the queue + * + * This function enables or disables a single queue. Note that any delay + * required after the operation is expected to be handled by the caller of + * this function. + **/ +static void i40e_control_tx_q(struct i40e_pf *pf, int pf_q, bool enable) +{ + struct i40e_hw *hw = &pf->hw; + u32 tx_reg; + int i; + + /* warn the TX unit of coming changes */ + i40e_pre_tx_queue_cfg(&pf->hw, pf_q, enable); + if (!enable) + usleep_range(10, 20); + + for (i = 0; i < I40E_QTX_ENA_WAIT_COUNT; i++) { + tx_reg = rd32(hw, I40E_QTX_ENA(pf_q)); + if (((tx_reg >> I40E_QTX_ENA_QENA_REQ_SHIFT) & 1) == + ((tx_reg >> I40E_QTX_ENA_QENA_STAT_SHIFT) & 1)) + break; + usleep_range(1000, 2000); + } + + /* Skip if the queue is already in the requested state */ + if (enable == !!(tx_reg & I40E_QTX_ENA_QENA_STAT_MASK)) + return; + + /* turn on/off the queue */ + if (enable) { + wr32(hw, I40E_QTX_HEAD(pf_q), 0); + tx_reg |= I40E_QTX_ENA_QENA_REQ_MASK; + } else { + tx_reg &= ~I40E_QTX_ENA_QENA_REQ_MASK; + } + + wr32(hw, I40E_QTX_ENA(pf_q), tx_reg); +} + +/** * i40e_vsi_control_tx - Start or stop a VSI's rings * @vsi: the VSI being configured * @enable: start or stop the rings @@ -4054,41 +4002,11 @@ static int i40e_pf_txq_wait(struct i40e_pf *pf, int pf_q, bool enable) static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable) { struct i40e_pf *pf = vsi->back; - struct i40e_hw *hw = &pf->hw; - int i, j, pf_q, ret = 0; - u32 tx_reg; + int i, pf_q, ret = 0; pf_q = vsi->base_queue; for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) { - - /* warn the TX unit of coming changes */ - i40e_pre_tx_queue_cfg(&pf->hw, pf_q, enable); - if (!enable) - usleep_range(10, 20); - - for (j = 0; j < 50; j++) { - tx_reg = rd32(hw, I40E_QTX_ENA(pf_q)); - if (((tx_reg >> I40E_QTX_ENA_QENA_REQ_SHIFT) & 1) == - ((tx_reg >> I40E_QTX_ENA_QENA_STAT_SHIFT) & 1)) - break; - usleep_range(1000, 2000); - } - /* Skip if the queue is already in the requested state */ - if (enable == !!(tx_reg & I40E_QTX_ENA_QENA_STAT_MASK)) - continue; - - /* turn on/off the queue */ - if (enable) { - wr32(hw, I40E_QTX_HEAD(pf_q), 0); - tx_reg |= I40E_QTX_ENA_QENA_REQ_MASK; - } else { - tx_reg &= ~I40E_QTX_ENA_QENA_REQ_MASK; - } - - wr32(hw, I40E_QTX_ENA(pf_q), tx_reg); - /* No waiting for the Tx queue to disable */ - if (!enable && test_bit(__I40E_PORT_TX_SUSPENDED, &pf->state)) - continue; + i40e_control_tx_q(pf, pf_q, enable); /* wait for the change to finish */ ret = i40e_pf_txq_wait(pf, pf_q, enable); @@ -4100,8 +4018,6 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable) } } - if (hw->revision_id == 0) - mdelay(50); return ret; } @@ -4135,6 +4051,43 @@ static int i40e_pf_rxq_wait(struct i40e_pf *pf, int pf_q, bool enable) } /** + * i40e_control_rx_q - Start or stop a particular Rx queue + * @pf: the PF structure + * @pf_q: the PF queue to configure + * @enable: start or stop the queue + * + * This function enables or disables a single queue. Note that any delay + * required after the operation is expected to be handled by the caller of + * this function. + **/ +static void i40e_control_rx_q(struct i40e_pf *pf, int pf_q, bool enable) +{ + struct i40e_hw *hw = &pf->hw; + u32 rx_reg; + int i; + + for (i = 0; i < I40E_QTX_ENA_WAIT_COUNT; i++) { + rx_reg = rd32(hw, I40E_QRX_ENA(pf_q)); + if (((rx_reg >> I40E_QRX_ENA_QENA_REQ_SHIFT) & 1) == + ((rx_reg >> I40E_QRX_ENA_QENA_STAT_SHIFT) & 1)) + break; + usleep_range(1000, 2000); + } + + /* Skip if the queue is already in the requested state */ + if (enable == !!(rx_reg & I40E_QRX_ENA_QENA_STAT_MASK)) + return; + + /* turn on/off the queue */ + if (enable) + rx_reg |= I40E_QRX_ENA_QENA_REQ_MASK; + else + rx_reg &= ~I40E_QRX_ENA_QENA_REQ_MASK; + + wr32(hw, I40E_QRX_ENA(pf_q), rx_reg); +} + +/** * i40e_vsi_control_rx - Start or stop a VSI's rings * @vsi: the VSI being configured * @enable: start or stop the rings @@ -4142,33 +4095,11 @@ static int i40e_pf_rxq_wait(struct i40e_pf *pf, int pf_q, bool enable) static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable) { struct i40e_pf *pf = vsi->back; - struct i40e_hw *hw = &pf->hw; - int i, j, pf_q, ret = 0; - u32 rx_reg; + int i, pf_q, ret = 0; pf_q = vsi->base_queue; for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) { - for (j = 0; j < 50; j++) { - rx_reg = rd32(hw, I40E_QRX_ENA(pf_q)); - if (((rx_reg >> I40E_QRX_ENA_QENA_REQ_SHIFT) & 1) == - ((rx_reg >> I40E_QRX_ENA_QENA_STAT_SHIFT) & 1)) - break; - usleep_range(1000, 2000); - } - - /* Skip if the queue is already in the requested state */ - if (enable == !!(rx_reg & I40E_QRX_ENA_QENA_STAT_MASK)) - continue; - - /* turn on/off the queue */ - if (enable) - rx_reg |= I40E_QRX_ENA_QENA_REQ_MASK; - else - rx_reg &= ~I40E_QRX_ENA_QENA_REQ_MASK; - wr32(hw, I40E_QRX_ENA(pf_q), rx_reg); - /* No waiting for the Tx queue to disable */ - if (!enable && test_bit(__I40E_PORT_TX_SUSPENDED, &pf->state)) - continue; + i40e_control_rx_q(pf, pf_q, enable); /* wait for the change to finish */ ret = i40e_pf_rxq_wait(pf, pf_q, enable); @@ -4180,6 +4111,12 @@ static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable) } } + /* Due to HW errata, on Rx disable only, the register can indicate done + * before it really is. Needs 50ms to be sure + */ + if (!enable) + mdelay(50); + return ret; } @@ -4206,6 +4143,10 @@ int i40e_vsi_start_rings(struct i40e_vsi *vsi) **/ void i40e_vsi_stop_rings(struct i40e_vsi *vsi) { + /* When port TX is suspended, don't wait */ + if (test_bit(__I40E_PORT_SUSPENDED, vsi->back->state)) + return i40e_vsi_stop_rings_no_wait(vsi); + /* do rx first for enable and last for disable * Ignore return value, we need to shutdown whatever we can */ @@ -4214,6 +4155,29 @@ void i40e_vsi_stop_rings(struct i40e_vsi *vsi) } /** + * i40e_vsi_stop_rings_no_wait - Stop a VSI's rings and do not delay + * @vsi: the VSI being shutdown + * + * This function stops all the rings for a VSI but does not delay to verify + * that rings have been disabled. It is expected that the caller is shutting + * down multiple VSIs at once and will delay together for all the VSIs after + * initiating the shutdown. This is particularly useful for shutting down lots + * of VFs together. Otherwise, a large delay can be incurred while configuring + * each VSI in serial. + **/ +void i40e_vsi_stop_rings_no_wait(struct i40e_vsi *vsi) +{ + struct i40e_pf *pf = vsi->back; + int i, pf_q; + + pf_q = vsi->base_queue; + for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) { + i40e_control_tx_q(pf, pf_q, false); + i40e_control_rx_q(pf, pf_q, false); + } +} + +/** * i40e_vsi_free_irq - Free the irq association with the OS * @vsi: the VSI being configured **/ @@ -4471,17 +4435,16 @@ static void i40e_napi_disable_all(struct i40e_vsi *vsi) **/ static void i40e_vsi_close(struct i40e_vsi *vsi) { - bool reset = false; - - if (!test_and_set_bit(__I40E_DOWN, &vsi->state)) + struct i40e_pf *pf = vsi->back; + if (!test_and_set_bit(__I40E_VSI_DOWN, vsi->state)) i40e_down(vsi); i40e_vsi_free_irq(vsi); i40e_vsi_free_tx_resources(vsi); i40e_vsi_free_rx_resources(vsi); vsi->current_netdev_flags = 0; - if (test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state)) - reset = true; - i40e_notify_client_of_netdev_close(vsi, reset); + pf->flags |= I40E_FLAG_SERVICE_CLIENT_REQUESTED; + if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) + pf->flags |= I40E_FLAG_CLIENT_RESET; } /** @@ -4490,18 +4453,10 @@ static void i40e_vsi_close(struct i40e_vsi *vsi) **/ static void i40e_quiesce_vsi(struct i40e_vsi *vsi) { - if (test_bit(__I40E_DOWN, &vsi->state)) - return; - - /* No need to disable FCoE VSI when Tx suspended */ - if ((test_bit(__I40E_PORT_TX_SUSPENDED, &vsi->back->state)) && - vsi->type == I40E_VSI_FCOE) { - dev_dbg(&vsi->back->pdev->dev, - "VSI seid %d skipping FCoE VSI disable\n", vsi->seid); + if (test_bit(__I40E_VSI_DOWN, vsi->state)) return; - } - set_bit(__I40E_NEEDS_RESTART, &vsi->state); + set_bit(__I40E_VSI_NEEDS_RESTART, vsi->state); if (vsi->netdev && netif_running(vsi->netdev)) vsi->netdev->netdev_ops->ndo_stop(vsi->netdev); else @@ -4514,10 +4469,9 @@ static void i40e_quiesce_vsi(struct i40e_vsi *vsi) **/ static void i40e_unquiesce_vsi(struct i40e_vsi *vsi) { - if (!test_bit(__I40E_NEEDS_RESTART, &vsi->state)) + if (!test_and_clear_bit(__I40E_VSI_NEEDS_RESTART, vsi->state)) return; - clear_bit(__I40E_NEEDS_RESTART, &vsi->state); if (vsi->netdev && netif_running(vsi->netdev)) vsi->netdev->netdev_ops->ndo_open(vsi->netdev); else @@ -4552,21 +4506,20 @@ static void i40e_pf_unquiesce_all_vsi(struct i40e_pf *pf) } } -#ifdef CONFIG_I40E_DCB /** * i40e_vsi_wait_queues_disabled - Wait for VSI's queues to be disabled * @vsi: the VSI being configured * - * This function waits for the given VSI's queues to be disabled. + * Wait until all queues on a given VSI have been disabled. **/ -static int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi) +int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; int i, pf_q, ret; pf_q = vsi->base_queue; for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) { - /* Check and wait for the disable status of the queue */ + /* Check and wait for the Tx queue */ ret = i40e_pf_txq_wait(pf, pf_q, false); if (ret) { dev_info(&pf->pdev->dev, @@ -4574,11 +4527,7 @@ static int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi) vsi->seid, pf_q); return ret; } - } - - pf_q = vsi->base_queue; - for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) { - /* Check and wait for the disable status of the queue */ + /* Check and wait for the Tx queue */ ret = i40e_pf_rxq_wait(pf, pf_q, false); if (ret) { dev_info(&pf->pdev->dev, @@ -4591,6 +4540,7 @@ static int i40e_vsi_wait_queues_disabled(struct i40e_vsi *vsi) return 0; } +#ifdef CONFIG_I40E_DCB /** * i40e_pf_wait_queues_disabled - Wait for all queues of PF VSIs to be disabled * @pf: the PF @@ -4603,8 +4553,7 @@ static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf) int v, ret = 0; for (v = 0; v < pf->hw.func_caps.num_vsis; v++) { - /* No need to wait for FCoE VSI queues */ - if (pf->vsi[v] && pf->vsi[v]->type != I40E_VSI_FCOE) { + if (pf->vsi[v]) { ret = i40e_vsi_wait_queues_disabled(pf->vsi[v]); if (ret) break; @@ -4622,16 +4571,15 @@ static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf) * @vsi: Pointer to VSI struct * * This function checks specified queue for given VSI. Detects hung condition. - * Sets hung bit since it is two step process. Before next run of service task - * if napi_poll runs, it reset 'hung' bit for respective q_vector. If not, - * hung condition remain unchanged and during subsequent run, this function - * issues SW interrupt to recover from hung condition. + * We proactively detect hung TX queues by checking if interrupts are disabled + * but there are pending descriptors. If it appears hung, attempt to recover + * by triggering a SW interrupt. **/ static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi) { struct i40e_ring *tx_ring = NULL; struct i40e_pf *pf; - u32 head, val, tx_pending_hw; + u32 val, tx_pending; int i; pf = vsi->back; @@ -4657,47 +4605,15 @@ static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi) else val = rd32(&pf->hw, I40E_PFINT_DYN_CTL0); - head = i40e_get_head(tx_ring); - - tx_pending_hw = i40e_get_tx_pending(tx_ring, false); - - /* HW is done executing descriptors, updated HEAD write back, - * but SW hasn't processed those descriptors. If interrupt is - * not generated from this point ON, it could result into - * dev_watchdog detecting timeout on those netdev_queue, - * hence proactively trigger SW interrupt. - */ - if (tx_pending_hw && (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) { - /* NAPI Poll didn't run and clear since it was set */ - if (test_and_clear_bit(I40E_Q_VECTOR_HUNG_DETECT, - &tx_ring->q_vector->hung_detected)) { - netdev_info(vsi->netdev, "VSI_seid %d, Hung TX queue %d, tx_pending_hw: %d, NTC:0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x\n", - vsi->seid, q_idx, tx_pending_hw, - tx_ring->next_to_clean, head, - tx_ring->next_to_use, - readl(tx_ring->tail)); - netdev_info(vsi->netdev, "VSI_seid %d, Issuing force_wb for TX queue %d, Interrupt Reg: 0x%x\n", - vsi->seid, q_idx, val); - i40e_force_wb(vsi, tx_ring->q_vector); - } else { - /* First Chance - detected possible hung */ - set_bit(I40E_Q_VECTOR_HUNG_DETECT, - &tx_ring->q_vector->hung_detected); - } - } + tx_pending = i40e_get_tx_pending(tx_ring); - /* This is the case where we have interrupts missing, - * so the tx_pending in HW will most likely be 0, but we - * will have tx_pending in SW since the WB happened but the - * interrupt got lost. + /* Interrupts are disabled and TX pending is non-zero, + * trigger the SW interrupt (don't wait). Worst case + * there will be one extra interrupt which may result + * into not cleaning any queues because queues are cleaned. */ - if ((!tx_pending_hw) && i40e_get_tx_pending(tx_ring, true) && - (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) { - local_bh_disable(); - if (napi_reschedule(&tx_ring->q_vector->napi)) - tx_ring->tx_stats.tx_lost_interrupt++; - local_bh_enable(); - } + if (tx_pending && (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) + i40e_force_wb(vsi, tx_ring->q_vector); } /** @@ -4721,8 +4637,8 @@ static void i40e_detect_recover_hung(struct i40e_pf *pf) return; /* Make sure, VSI state is not DOWN/RECOVERY_PENDING */ - if (test_bit(__I40E_DOWN, &vsi->back->state) || - test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state)) + if (test_bit(__I40E_VSI_DOWN, vsi->back->state) || + test_bit(__I40E_RESET_RECOVERY_PENDING, vsi->back->state)) return; /* Make sure type is MAIN VSI */ @@ -5228,20 +5144,12 @@ static void i40e_dcb_reconfigure(struct i40e_pf *pf) continue; /* - Enable all TCs for the LAN VSI -#ifdef I40E_FCOE - * - For FCoE VSI only enable the TC configured - * as per the APP TLV -#endif * - For all others keep them at TC0 for now */ if (v == pf->lan_vsi) tc_map = i40e_pf_get_tc_map(pf); else tc_map = I40E_DEFAULT_TRAFFIC_CLASS; -#ifdef I40E_FCOE - if (pf->vsi[v]->type == I40E_VSI_FCOE) - tc_map = i40e_get_fcoe_tc_map(pf); -#endif /* #ifdef I40E_FCOE */ ret = i40e_vsi_config_tc(pf->vsi[v], tc_map); if (ret) { @@ -5277,7 +5185,7 @@ static int i40e_resume_port_tx(struct i40e_pf *pf) i40e_stat_str(&pf->hw, ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); /* Schedule PF reset to recover */ - set_bit(__I40E_PF_RESET_REQUESTED, &pf->state); + set_bit(__I40E_PF_RESET_REQUESTED, pf->state); i40e_service_event_schedule(pf); } @@ -5308,10 +5216,6 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf) (hw->dcbx_status == I40E_DCBX_STATUS_DISABLED)) { dev_info(&pf->pdev->dev, "DCBX offload is not supported or is disabled for this PF.\n"); - - if (pf->flags & I40E_FLAG_MFP_ENABLED) - goto out; - } else { /* When status is not DISABLED then DCBX in FW */ pf->dcbx_cap = DCB_CAP_DCBX_LLD_MANAGED | @@ -5449,7 +5353,7 @@ static int i40e_up_complete(struct i40e_vsi *vsi) if (err) return err; - clear_bit(__I40E_DOWN, &vsi->state); + clear_bit(__I40E_VSI_DOWN, vsi->state); i40e_napi_enable_all(vsi); i40e_vsi_enable_irq(vsi); @@ -5472,13 +5376,8 @@ static int i40e_up_complete(struct i40e_vsi *vsi) /* replay FDIR SB filters */ if (vsi->type == I40E_VSI_FDIR) { /* reset fd counters */ - pf->fd_add_err = pf->fd_atr_cnt = 0; - if (pf->fd_tcp_rule > 0) { - pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED; - if (I40E_DEBUG_FD & pf->hw.debug_mask) - dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 exist\n"); - pf->fd_tcp_rule = 0; - } + pf->fd_add_err = 0; + pf->fd_atr_cnt = 0; i40e_fdir_filter_restore(vsi); } @@ -5503,12 +5402,12 @@ static void i40e_vsi_reinit_locked(struct i40e_vsi *vsi) struct i40e_pf *pf = vsi->back; WARN_ON(in_interrupt()); - while (test_and_set_bit(__I40E_CONFIG_BUSY, &pf->state)) + while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state)) usleep_range(1000, 2000); i40e_down(vsi); i40e_up(vsi); - clear_bit(__I40E_CONFIG_BUSY, &pf->state); + clear_bit(__I40E_CONFIG_BUSY, pf->state); } /** @@ -5535,7 +5434,7 @@ void i40e_down(struct i40e_vsi *vsi) int i; /* It is assumed that the caller of this function - * sets the vsi->state __I40E_DOWN bit. + * sets the vsi->state __I40E_VSI_DOWN bit. */ if (vsi->netdev) { netif_carrier_off(vsi->netdev); @@ -5550,8 +5449,6 @@ void i40e_down(struct i40e_vsi *vsi) i40e_clean_rx_ring(vsi->rx_rings[i]); } - i40e_notify_client_of_netdev_close(vsi, false); - } /** @@ -5612,17 +5509,15 @@ exit: return ret; } -#ifdef I40E_FCOE -int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto, - struct tc_to_netdev *tc) -#else static int __i40e_setup_tc(struct net_device *netdev, u32 handle, __be16 proto, struct tc_to_netdev *tc) -#endif { - if (handle != TC_H_ROOT || tc->type != TC_SETUP_MQPRIO) + if (tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return i40e_setup_tc(netdev, tc->tc); + + tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return i40e_setup_tc(netdev, tc->mqprio->num_tc); } /** @@ -5645,8 +5540,8 @@ int i40e_open(struct net_device *netdev) int err; /* disallow open during test or if eeprom is broken */ - if (test_bit(__I40E_TESTING, &pf->state) || - test_bit(__I40E_BAD_EEPROM, &pf->state)) + if (test_bit(__I40E_TESTING, pf->state) || + test_bit(__I40E_BAD_EEPROM, pf->state)) return -EBUSY; netif_carrier_off(netdev); @@ -5675,6 +5570,8 @@ int i40e_open(struct net_device *netdev) * Finish initialization of the VSI. * * Returns 0 on success, negative value on failure + * + * Note: expects to be called while under rtnl_lock() **/ int i40e_vsi_open(struct i40e_vsi *vsi) { @@ -5738,7 +5635,7 @@ err_setup_rx: err_setup_tx: i40e_vsi_free_tx_resources(vsi); if (vsi == pf->vsi[pf->lan_vsi]) - i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED)); + i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), true); return err; } @@ -5753,6 +5650,7 @@ err_setup_tx: static void i40e_fdir_filter_exit(struct i40e_pf *pf) { struct i40e_fdir_filter *filter; + struct i40e_flex_pit *pit_entry, *tmp; struct hlist_node *node2; hlist_for_each_entry_safe(filter, node2, @@ -5760,7 +5658,43 @@ static void i40e_fdir_filter_exit(struct i40e_pf *pf) hlist_del(&filter->fdir_node); kfree(filter); } + + list_for_each_entry_safe(pit_entry, tmp, &pf->l3_flex_pit_list, list) { + list_del(&pit_entry->list); + kfree(pit_entry); + } + INIT_LIST_HEAD(&pf->l3_flex_pit_list); + + list_for_each_entry_safe(pit_entry, tmp, &pf->l4_flex_pit_list, list) { + list_del(&pit_entry->list); + kfree(pit_entry); + } + INIT_LIST_HEAD(&pf->l4_flex_pit_list); + pf->fdir_pf_active_filters = 0; + pf->fd_tcp4_filter_cnt = 0; + pf->fd_udp4_filter_cnt = 0; + pf->fd_sctp4_filter_cnt = 0; + pf->fd_ip4_filter_cnt = 0; + + /* Reprogram the default input set for TCP/IPv4 */ + i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_TCP, + I40E_L3_SRC_MASK | I40E_L3_DST_MASK | + I40E_L4_SRC_MASK | I40E_L4_DST_MASK); + + /* Reprogram the default input set for UDP/IPv4 */ + i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_UDP, + I40E_L3_SRC_MASK | I40E_L3_DST_MASK | + I40E_L4_SRC_MASK | I40E_L4_DST_MASK); + + /* Reprogram the default input set for SCTP/IPv4 */ + i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_SCTP, + I40E_L3_SRC_MASK | I40E_L3_DST_MASK | + I40E_L4_SRC_MASK | I40E_L4_DST_MASK); + + /* Reprogram the default input set for Other/IPv4 */ + i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_OTHER, + I40E_L3_SRC_MASK | I40E_L3_DST_MASK); } /** @@ -5787,12 +5721,14 @@ int i40e_close(struct net_device *netdev) * i40e_do_reset - Start a PF or Core Reset sequence * @pf: board private structure * @reset_flags: which reset is requested + * @lock_acquired: indicates whether or not the lock has been acquired + * before this function was called. * * The essential difference in resets is that the PF Reset * doesn't clear the packet buffers, doesn't reset the PE * firmware, and doesn't bother the other PFs on the chip. **/ -void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags) +void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired) { u32 val; @@ -5838,7 +5774,7 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags) * for the Core Reset. */ dev_dbg(&pf->pdev->dev, "PFR requested\n"); - i40e_handle_reset_warning(pf); + i40e_handle_reset_warning(pf, lock_acquired); } else if (reset_flags & BIT_ULL(__I40E_REINIT_REQUESTED)) { int v; @@ -5850,10 +5786,9 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags) struct i40e_vsi *vsi = pf->vsi[v]; if (vsi != NULL && - test_bit(__I40E_REINIT_REQUESTED, &vsi->state)) { + test_and_clear_bit(__I40E_VSI_REINIT_REQUESTED, + vsi->state)) i40e_vsi_reinit_locked(pf->vsi[v]); - clear_bit(__I40E_REINIT_REQUESTED, &vsi->state); - } } } else if (reset_flags & BIT_ULL(__I40E_DOWN_REQUESTED)) { int v; @@ -5864,10 +5799,10 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags) struct i40e_vsi *vsi = pf->vsi[v]; if (vsi != NULL && - test_bit(__I40E_DOWN_REQUESTED, &vsi->state)) { - set_bit(__I40E_DOWN, &vsi->state); + test_and_clear_bit(__I40E_VSI_DOWN_REQUESTED, + vsi->state)) { + set_bit(__I40E_VSI_DOWN, vsi->state); i40e_down(vsi); - clear_bit(__I40E_DOWN_REQUESTED, &vsi->state); } } } else { @@ -6007,7 +5942,7 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf, else pf->flags &= ~I40E_FLAG_DCB_ENABLED; - set_bit(__I40E_PORT_TX_SUSPENDED, &pf->state); + set_bit(__I40E_PORT_SUSPENDED, pf->state); /* Reconfiguration needed quiesce all VSIs */ i40e_pf_quiesce_all_vsi(pf); @@ -6016,7 +5951,7 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf, ret = i40e_resume_port_tx(pf); - clear_bit(__I40E_PORT_TX_SUSPENDED, &pf->state); + clear_bit(__I40E_PORT_SUSPENDED, pf->state); /* In case of error no point in resuming VSIs */ if (ret) goto exit; @@ -6025,12 +5960,12 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf, ret = i40e_pf_wait_queues_disabled(pf); if (ret) { /* Schedule PF reset to recover */ - set_bit(__I40E_PF_RESET_REQUESTED, &pf->state); + set_bit(__I40E_PF_RESET_REQUESTED, pf->state); i40e_service_event_schedule(pf); } else { i40e_pf_unquiesce_all_vsi(pf); - /* Notify the client for the DCB changes */ - i40e_notify_client_of_l2_param_changes(pf->vsi[pf->lan_vsi]); + pf->flags |= (I40E_FLAG_SERVICE_CLIENT_REQUESTED | + I40E_FLAG_CLIENT_L2_CHANGE); } exit: @@ -6047,7 +5982,7 @@ exit: void i40e_do_reset_safe(struct i40e_pf *pf, u32 reset_flags) { rtnl_lock(); - i40e_do_reset(pf, reset_flags); + i40e_do_reset(pf, reset_flags, true); rtnl_unlock(); } @@ -6140,34 +6075,33 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf) u32 fcnt_prog, fcnt_avail; struct hlist_node *node; - if (test_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state)) + if (test_bit(__I40E_FD_FLUSH_REQUESTED, pf->state)) return; - /* Check if, FD SB or ATR was auto disabled and if there is enough room - * to re-enable - */ + /* Check if we have enough room to re-enable FDir SB capability. */ fcnt_prog = i40e_get_global_fd_count(pf); fcnt_avail = pf->fdir_pf_filter_count; if ((fcnt_prog < (fcnt_avail - I40E_FDIR_BUFFER_HEAD_ROOM)) || (pf->fd_add_err == 0) || (i40e_get_current_atr_cnt(pf) < pf->fd_atr_cnt)) { - if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) && - (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) { - pf->auto_disable_flags &= ~I40E_FLAG_FD_SB_ENABLED; - if (I40E_DEBUG_FD & pf->hw.debug_mask) + if (pf->flags & I40E_FLAG_FD_SB_AUTO_DISABLED) { + pf->flags &= ~I40E_FLAG_FD_SB_AUTO_DISABLED; + if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) && + (I40E_DEBUG_FD & pf->hw.debug_mask)) dev_info(&pf->pdev->dev, "FD Sideband/ntuple is being enabled since we have space in the table now\n"); } } - /* Wait for some more space to be available to turn on ATR. We also - * must check that no existing ntuple rules for TCP are in effect + /* We should wait for even more space before re-enabling ATR. + * Additionally, we cannot enable ATR as long as we still have TCP SB + * rules active. */ - if (fcnt_prog < (fcnt_avail - I40E_FDIR_BUFFER_HEAD_ROOM * 2)) { - if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && - (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED) && - (pf->fd_tcp_rule == 0)) { - pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED; - if (I40E_DEBUG_FD & pf->hw.debug_mask) + if ((fcnt_prog < (fcnt_avail - I40E_FDIR_BUFFER_HEAD_ROOM_FOR_ATR)) && + (pf->fd_tcp4_filter_cnt == 0)) { + if (pf->flags & I40E_FLAG_FD_ATR_AUTO_DISABLED) { + pf->flags &= ~I40E_FLAG_FD_ATR_AUTO_DISABLED; + if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && + (I40E_DEBUG_FD & pf->hw.debug_mask)) dev_info(&pf->pdev->dev, "ATR is being enabled since we have space in the table and there are no conflicting ntuple rules\n"); } } @@ -6218,7 +6152,7 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf) } pf->fd_flush_timestamp = jiffies; - pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED; + pf->flags |= I40E_FLAG_FD_ATR_AUTO_DISABLED; /* flush all filters */ wr32(&pf->hw, I40E_PFQF_CTL_1, I40E_PFQF_CTL_1_CLEARFDTABLE_MASK); @@ -6237,9 +6171,9 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf) } else { /* replay sideband filters */ i40e_fdir_filter_restore(pf->vsi[pf->lan_vsi]); - if (!disable_atr) - pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED; - clear_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state); + if (!disable_atr && !pf->fd_tcp4_filter_cnt) + pf->flags &= ~I40E_FLAG_FD_ATR_AUTO_DISABLED; + clear_bit(__I40E_FD_FLUSH_REQUESTED, pf->state); if (I40E_DEBUG_FD & pf->hw.debug_mask) dev_info(&pf->pdev->dev, "FD Filter table flushed and FD-SB replayed.\n"); } @@ -6269,10 +6203,10 @@ static void i40e_fdir_reinit_subtask(struct i40e_pf *pf) { /* if interface is down do nothing */ - if (test_bit(__I40E_DOWN, &pf->state)) + if (test_bit(__I40E_VSI_DOWN, pf->state)) return; - if (test_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state)) + if (test_bit(__I40E_FD_FLUSH_REQUESTED, pf->state)) i40e_fdir_flush_and_replay(pf); i40e_fdir_check_and_reenable(pf); @@ -6286,14 +6220,11 @@ static void i40e_fdir_reinit_subtask(struct i40e_pf *pf) **/ static void i40e_vsi_link_event(struct i40e_vsi *vsi, bool link_up) { - if (!vsi || test_bit(__I40E_DOWN, &vsi->state)) + if (!vsi || test_bit(__I40E_VSI_DOWN, vsi->state)) return; switch (vsi->type) { case I40E_VSI_MAIN: -#ifdef I40E_FCOE - case I40E_VSI_FCOE: -#endif if (!vsi->netdev || !vsi->netdev_registered) break; @@ -6382,11 +6313,11 @@ static void i40e_link_event(struct i40e_pf *pf) if (new_link == old_link && new_link_speed == old_link_speed && - (test_bit(__I40E_DOWN, &vsi->state) || + (test_bit(__I40E_VSI_DOWN, vsi->state) || new_link == netif_carrier_ok(vsi->netdev))) return; - if (!test_bit(__I40E_DOWN, &vsi->state)) + if (!test_bit(__I40E_VSI_DOWN, vsi->state)) i40e_print_link_message(vsi, new_link); /* Notify the base of the switch tree connected to @@ -6413,8 +6344,8 @@ static void i40e_watchdog_subtask(struct i40e_pf *pf) int i; /* if interface is down do nothing */ - if (test_bit(__I40E_DOWN, &pf->state) || - test_bit(__I40E_CONFIG_BUSY, &pf->state)) + if (test_bit(__I40E_VSI_DOWN, pf->state) || + test_bit(__I40E_CONFIG_BUSY, pf->state)) return; /* make sure we don't do these things too often */ @@ -6452,44 +6383,44 @@ static void i40e_reset_subtask(struct i40e_pf *pf) { u32 reset_flags = 0; - rtnl_lock(); - if (test_bit(__I40E_REINIT_REQUESTED, &pf->state)) { + if (test_bit(__I40E_REINIT_REQUESTED, pf->state)) { reset_flags |= BIT(__I40E_REINIT_REQUESTED); - clear_bit(__I40E_REINIT_REQUESTED, &pf->state); + clear_bit(__I40E_REINIT_REQUESTED, pf->state); } - if (test_bit(__I40E_PF_RESET_REQUESTED, &pf->state)) { + if (test_bit(__I40E_PF_RESET_REQUESTED, pf->state)) { reset_flags |= BIT(__I40E_PF_RESET_REQUESTED); - clear_bit(__I40E_PF_RESET_REQUESTED, &pf->state); + clear_bit(__I40E_PF_RESET_REQUESTED, pf->state); } - if (test_bit(__I40E_CORE_RESET_REQUESTED, &pf->state)) { + if (test_bit(__I40E_CORE_RESET_REQUESTED, pf->state)) { reset_flags |= BIT(__I40E_CORE_RESET_REQUESTED); - clear_bit(__I40E_CORE_RESET_REQUESTED, &pf->state); + clear_bit(__I40E_CORE_RESET_REQUESTED, pf->state); } - if (test_bit(__I40E_GLOBAL_RESET_REQUESTED, &pf->state)) { + if (test_bit(__I40E_GLOBAL_RESET_REQUESTED, pf->state)) { reset_flags |= BIT(__I40E_GLOBAL_RESET_REQUESTED); - clear_bit(__I40E_GLOBAL_RESET_REQUESTED, &pf->state); + clear_bit(__I40E_GLOBAL_RESET_REQUESTED, pf->state); } - if (test_bit(__I40E_DOWN_REQUESTED, &pf->state)) { - reset_flags |= BIT(__I40E_DOWN_REQUESTED); - clear_bit(__I40E_DOWN_REQUESTED, &pf->state); + if (test_bit(__I40E_VSI_DOWN_REQUESTED, pf->state)) { + reset_flags |= BIT(__I40E_VSI_DOWN_REQUESTED); + clear_bit(__I40E_VSI_DOWN_REQUESTED, pf->state); } /* If there's a recovery already waiting, it takes * precedence before starting a new reset sequence. */ - if (test_bit(__I40E_RESET_INTR_RECEIVED, &pf->state)) { - i40e_handle_reset_warning(pf); - goto unlock; + if (test_bit(__I40E_RESET_INTR_RECEIVED, pf->state)) { + i40e_prep_for_reset(pf, false); + i40e_reset(pf); + i40e_rebuild(pf, false, false); } /* If we're already down or resetting, just bail */ if (reset_flags && - !test_bit(__I40E_DOWN, &pf->state) && - !test_bit(__I40E_CONFIG_BUSY, &pf->state)) - i40e_do_reset(pf, reset_flags); - -unlock: - rtnl_unlock(); + !test_bit(__I40E_VSI_DOWN, pf->state) && + !test_bit(__I40E_CONFIG_BUSY, pf->state)) { + rtnl_lock(); + i40e_do_reset(pf, reset_flags, true); + rtnl_unlock(); + } } /** @@ -6534,7 +6465,7 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf) u32 val; /* Do not run clean AQ when PF reset fails */ - if (test_bit(__I40E_RESET_FAILED, &pf->state)) + if (test_bit(__I40E_RESET_FAILED, pf->state)) return; /* check for error indications */ @@ -6635,9 +6566,11 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf) opcode); break; } - } while (pending && (i++ < pf->adminq_work_limit)); + } while (i++ < pf->adminq_work_limit); + + if (i < pf->adminq_work_limit) + clear_bit(__I40E_ADMINQ_EVENT_PENDING, pf->state); - clear_bit(__I40E_ADMINQ_EVENT_PENDING, &pf->state); /* re-enable Admin queue interrupt cause */ val = rd32(hw, I40E_PFINT_ICR0_ENA); val |= I40E_PFINT_ICR0_ENA_ADMINQ_MASK; @@ -6662,13 +6595,13 @@ static void i40e_verify_eeprom(struct i40e_pf *pf) if (err) { dev_info(&pf->pdev->dev, "eeprom check failed (%d), Tx/Rx traffic disabled\n", err); - set_bit(__I40E_BAD_EEPROM, &pf->state); + set_bit(__I40E_BAD_EEPROM, pf->state); } } - if (!err && test_bit(__I40E_BAD_EEPROM, &pf->state)) { + if (!err && test_bit(__I40E_BAD_EEPROM, pf->state)) { dev_info(&pf->pdev->dev, "eeprom check passed, Tx/Rx traffic enabled\n"); - clear_bit(__I40E_BAD_EEPROM, &pf->state); + clear_bit(__I40E_BAD_EEPROM, pf->state); } } @@ -6975,17 +6908,19 @@ static void i40e_fdir_teardown(struct i40e_pf *pf) /** * i40e_prep_for_reset - prep for the core to reset * @pf: board private structure + * @lock_acquired: indicates whether or not the lock has been acquired + * before this function was called. * * Close up the VFs and other things in prep for PF Reset. **/ -static void i40e_prep_for_reset(struct i40e_pf *pf) +static void i40e_prep_for_reset(struct i40e_pf *pf, bool lock_acquired) { struct i40e_hw *hw = &pf->hw; i40e_status ret = 0; u32 v; - clear_bit(__I40E_RESET_INTR_RECEIVED, &pf->state); - if (test_and_set_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state)) + clear_bit(__I40E_RESET_INTR_RECEIVED, pf->state); + if (test_and_set_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) return; if (i40e_check_asq_alive(&pf->hw)) i40e_vc_notify_reset(pf); @@ -6993,7 +6928,12 @@ static void i40e_prep_for_reset(struct i40e_pf *pf) dev_dbg(&pf->pdev->dev, "Tearing down internal switch for reset\n"); /* quiesce the VSIs and their queues that are not already DOWN */ + /* pf_quiesce_all_vsi modifies netdev structures -rtnl_lock needed */ + if (!lock_acquired) + rtnl_lock(); i40e_pf_quiesce_all_vsi(pf); + if (!lock_acquired) + rtnl_unlock(); for (v = 0; v < pf->num_alloc_vsi; v++) { if (pf->vsi[v]) @@ -7028,31 +6968,41 @@ static void i40e_send_version(struct i40e_pf *pf) } /** - * i40e_reset_and_rebuild - reset and rebuild using a saved config + * i40e_reset - wait for core reset to finish reset, reset pf if corer not seen * @pf: board private structure - * @reinit: if the Main VSI needs to re-initialized. **/ -static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit) +static int i40e_reset(struct i40e_pf *pf) { struct i40e_hw *hw = &pf->hw; - u8 set_fc_aq_fail = 0; i40e_status ret; - u32 val; - u32 v; - /* Now we wait for GRST to settle out. - * We don't have to delete the VEBs or VSIs from the hw switch - * because the reset will make them disappear. - */ ret = i40e_pf_reset(hw); if (ret) { dev_info(&pf->pdev->dev, "PF reset failed, %d\n", ret); - set_bit(__I40E_RESET_FAILED, &pf->state); - goto clear_recovery; + set_bit(__I40E_RESET_FAILED, pf->state); + clear_bit(__I40E_RESET_RECOVERY_PENDING, pf->state); + } else { + pf->pfr_count++; } - pf->pfr_count++; + return ret; +} + +/** + * i40e_rebuild - rebuild using a saved config + * @pf: board private structure + * @reinit: if the Main VSI needs to re-initialized. + * @lock_acquired: indicates whether or not the lock has been acquired + * before this function was called. + **/ +static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) +{ + struct i40e_hw *hw = &pf->hw; + u8 set_fc_aq_fail = 0; + i40e_status ret; + u32 val; + int v; - if (test_bit(__I40E_DOWN, &pf->state)) + if (test_bit(__I40E_VSI_DOWN, pf->state)) goto clear_recovery; dev_dbg(&pf->pdev->dev, "Rebuilding internal switch\n"); @@ -7066,7 +7016,7 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit) } /* re-verify the eeprom if we just had an EMP reset */ - if (test_and_clear_bit(__I40E_EMP_RESET_INTR_RECEIVED, &pf->state)) + if (test_and_clear_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state)) i40e_verify_eeprom(pf); i40e_clear_pxe_mode(hw); @@ -7075,8 +7025,7 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit) goto end_core_reset; ret = i40e_init_lan_hmc(hw, hw->func_caps.num_tx_qp, - hw->func_caps.num_rx_qp, - pf->fcoe_hmc_cntx_num, pf->fcoe_hmc_filt_num); + hw->func_caps.num_rx_qp, 0, 0); if (ret) { dev_info(&pf->pdev->dev, "init_lan_hmc failed: %d\n", ret); goto end_core_reset; @@ -7095,14 +7044,12 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit) /* Continue without DCB enabled */ } #endif /* CONFIG_I40E_DCB */ -#ifdef I40E_FCOE - i40e_init_pf_fcoe(pf); - -#endif /* do basic switch setup */ + if (!lock_acquired) + rtnl_lock(); ret = i40e_setup_pf_switch(pf, reinit); if (ret) - goto end_core_reset; + goto end_unlock; /* The driver only wants link up/down and module qualification * reports from firmware. Note the negative logic. @@ -7173,7 +7120,7 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit) if (ret) { dev_info(&pf->pdev->dev, "rebuild of Main VSI failed: %d\n", ret); - goto end_core_reset; + goto end_unlock; } } @@ -7216,18 +7163,45 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit) /* restart the VSIs that were rebuilt and running before the reset */ i40e_pf_unquiesce_all_vsi(pf); - if (pf->num_alloc_vfs) { - for (v = 0; v < pf->num_alloc_vfs; v++) - i40e_reset_vf(&pf->vf[v], true); - } + /* Release the RTNL lock before we start resetting VFs */ + if (!lock_acquired) + rtnl_unlock(); + + i40e_reset_all_vfs(pf, true); /* tell the firmware that we're starting */ i40e_send_version(pf); + /* We've already released the lock, so don't do it again */ + goto end_core_reset; + +end_unlock: + if (!lock_acquired) + rtnl_unlock(); end_core_reset: - clear_bit(__I40E_RESET_FAILED, &pf->state); + clear_bit(__I40E_RESET_FAILED, pf->state); clear_recovery: - clear_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state); + clear_bit(__I40E_RESET_RECOVERY_PENDING, pf->state); +} + +/** + * i40e_reset_and_rebuild - reset and rebuild using a saved config + * @pf: board private structure + * @reinit: if the Main VSI needs to re-initialized. + * @lock_acquired: indicates whether or not the lock has been acquired + * before this function was called. + **/ +static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit, + bool lock_acquired) +{ + int ret; + /* Now we wait for GRST to settle out. + * We don't have to delete the VEBs or VSIs from the hw switch + * because the reset will make them disappear. + */ + ret = i40e_reset(pf); + if (!ret) + i40e_rebuild(pf, reinit, lock_acquired); } /** @@ -7236,11 +7210,13 @@ clear_recovery: * * Close up the VFs and other things in prep for a Core Reset, * then get ready to rebuild the world. + * @lock_acquired: indicates whether or not the lock has been acquired + * before this function was called. **/ -static void i40e_handle_reset_warning(struct i40e_pf *pf) +static void i40e_handle_reset_warning(struct i40e_pf *pf, bool lock_acquired) { - i40e_prep_for_reset(pf); - i40e_reset_and_rebuild(pf, false); + i40e_prep_for_reset(pf, lock_acquired); + i40e_reset_and_rebuild(pf, false, lock_acquired); } /** @@ -7258,7 +7234,7 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf) u32 reg; int i; - if (!test_bit(__I40E_MDD_EVENT_PENDING, &pf->state)) + if (!test_bit(__I40E_MDD_EVENT_PENDING, pf->state)) return; /* find what triggered the MDD event */ @@ -7310,7 +7286,7 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf) } /* Queue belongs to the PF, initiate a reset */ if (pf_mdd_detected) { - set_bit(__I40E_PF_RESET_REQUESTED, &pf->state); + set_bit(__I40E_PF_RESET_REQUESTED, pf->state); i40e_service_event_schedule(pf); } } @@ -7339,12 +7315,12 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf) "Too many MDD events on VF %d, disabled\n", i); dev_info(&pf->pdev->dev, "Use PF Control I/F to re-enable the VF\n"); - set_bit(I40E_VF_STAT_DISABLED, &vf->vf_states); + set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states); } } /* re-enable mdd interrupt cause */ - clear_bit(__I40E_MDD_EVENT_PENDING, &pf->state); + clear_bit(__I40E_MDD_EVENT_PENDING, pf->state); reg = rd32(hw, I40E_PFINT_ICR0_ENA); reg |= I40E_PFINT_ICR0_ENA_MAL_DETECT_MASK; wr32(hw, I40E_PFINT_ICR0_ENA, reg); @@ -7352,6 +7328,23 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf) } /** + * i40e_sync_udp_filters - Trigger a sync event for existing UDP filters + * @pf: board private structure + **/ +static void i40e_sync_udp_filters(struct i40e_pf *pf) +{ + int i; + + /* loop through and set pending bit for all active UDP filters */ + for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) { + if (pf->udp_ports[i].port) + pf->pending_udp_bitmap |= BIT_ULL(i); + } + + pf->flags |= I40E_FLAG_UDP_FILTER_SYNC; +} + +/** * i40e_sync_udp_filters_subtask - Sync the VSI filter list with HW * @pf: board private structure **/ @@ -7359,7 +7352,7 @@ static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf) { struct i40e_hw *hw = &pf->hw; i40e_status ret; - __be16 port; + u16 port; int i; if (!(pf->flags & I40E_FLAG_UDP_FILTER_SYNC)) @@ -7370,7 +7363,7 @@ static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf) for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) { if (pf->pending_udp_bitmap & BIT_ULL(i)) { pf->pending_udp_bitmap &= ~BIT_ULL(i); - port = pf->udp_ports[i].index; + port = pf->udp_ports[i].port; if (port) ret = i40e_aq_add_udp_tunnel(hw, port, pf->udp_ports[i].type, @@ -7383,11 +7376,11 @@ static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf) "%s %s port %d, index %d failed, err %s aq_err %s\n", pf->udp_ports[i].type ? "vxlan" : "geneve", port ? "add" : "delete", - ntohs(port), i, + port, i, i40e_stat_str(&pf->hw, ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); - pf->udp_ports[i].index = 0; + pf->udp_ports[i].port = 0; } } } @@ -7405,11 +7398,10 @@ static void i40e_service_task(struct work_struct *work) unsigned long start_time = jiffies; /* don't bother with service tasks if a reset is in progress */ - if (test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state)) { + if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) return; - } - if (test_and_set_bit(__I40E_SERVICE_SCHED, &pf->state)) + if (test_and_set_bit(__I40E_SERVICE_SCHED, pf->state)) return; i40e_detect_recover_hung(pf); @@ -7419,23 +7411,34 @@ static void i40e_service_task(struct work_struct *work) i40e_vc_process_vflr_event(pf); i40e_watchdog_subtask(pf); i40e_fdir_reinit_subtask(pf); - i40e_client_subtask(pf); + if (pf->flags & I40E_FLAG_CLIENT_RESET) { + /* Client subtask will reopen next time through. */ + i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], true); + pf->flags &= ~I40E_FLAG_CLIENT_RESET; + } else { + i40e_client_subtask(pf); + if (pf->flags & I40E_FLAG_CLIENT_L2_CHANGE) { + i40e_notify_client_of_l2_param_changes( + pf->vsi[pf->lan_vsi]); + pf->flags &= ~I40E_FLAG_CLIENT_L2_CHANGE; + } + } i40e_sync_filters_subtask(pf); i40e_sync_udp_filters_subtask(pf); i40e_clean_adminq_subtask(pf); /* flush memory to make sure state is correct before next watchdog */ smp_mb__before_atomic(); - clear_bit(__I40E_SERVICE_SCHED, &pf->state); + clear_bit(__I40E_SERVICE_SCHED, pf->state); /* If the tasks have taken longer than one timer cycle or there * is more work to be done, reschedule the service task now * rather than wait for the timer to tick again. */ if (time_after(jiffies, (start_time + pf->service_timer_period)) || - test_bit(__I40E_ADMINQ_EVENT_PENDING, &pf->state) || - test_bit(__I40E_MDD_EVENT_PENDING, &pf->state) || - test_bit(__I40E_VFLR_EVENT_PENDING, &pf->state)) + test_bit(__I40E_ADMINQ_EVENT_PENDING, pf->state) || + test_bit(__I40E_MDD_EVENT_PENDING, pf->state) || + test_bit(__I40E_VFLR_EVENT_PENDING, pf->state)) i40e_service_event_schedule(pf); } @@ -7492,15 +7495,6 @@ static int i40e_set_num_rings_in_vsi(struct i40e_vsi *vsi) I40E_REQ_DESCRIPTOR_MULTIPLE); break; -#ifdef I40E_FCOE - case I40E_VSI_FCOE: - vsi->alloc_queue_pairs = pf->num_fcoe_qps; - vsi->num_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS, - I40E_REQ_DESCRIPTOR_MULTIPLE); - vsi->num_q_vectors = pf->num_fcoe_msix; - break; - -#endif /* I40E_FCOE */ default: WARN_ON(1); return -ENODATA; @@ -7593,7 +7587,7 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type) } vsi->type = type; vsi->back = pf; - set_bit(__I40E_DOWN, &vsi->state); + set_bit(__I40E_VSI_DOWN, vsi->state); vsi->flags = 0; vsi->idx = vsi_idx; vsi->int_rate_limit = 0; @@ -7817,6 +7811,7 @@ static int i40e_reserve_msix_vectors(struct i40e_pf *pf, int vectors) static int i40e_init_msix(struct i40e_pf *pf) { struct i40e_hw *hw = &pf->hw; + int cpus, extra_vectors; int vectors_left; int v_budget, i; int v_actual; @@ -7835,9 +7830,6 @@ static int i40e_init_msix(struct i40e_pf *pf) * - assumes symmetric Tx/Rx pairing * - The number of VMDq pairs * - The CPU count within the NUMA node if iWARP is enabled -#ifdef I40E_FCOE - * - The number of FCOE qps. -#endif * Once we count this up, try the request. * * If we can't get what we want, we'll simplify to nearly nothing @@ -7852,10 +7844,16 @@ static int i40e_init_msix(struct i40e_pf *pf) vectors_left--; } - /* reserve vectors for the main PF traffic queues */ - pf->num_lan_msix = min_t(int, num_online_cpus(), vectors_left); + /* reserve some vectors for the main PF traffic queues. Initially we + * only reserve at most 50% of the available vectors, in the case that + * the number of online CPUs is large. This ensures that we can enable + * extra features as well. Once we've enabled the other features, we + * will use any remaining vectors to reach as close as we can to the + * number of online CPUs. + */ + cpus = num_online_cpus(); + pf->num_lan_msix = min_t(int, cpus, vectors_left / 2); vectors_left -= pf->num_lan_msix; - v_budget += pf->num_lan_msix; /* reserve one vector for sideband flow director */ if (pf->flags & I40E_FLAG_FD_SB_ENABLED) { @@ -7868,20 +7866,6 @@ static int i40e_init_msix(struct i40e_pf *pf) } } -#ifdef I40E_FCOE - /* can we reserve enough for FCoE? */ - if (pf->flags & I40E_FLAG_FCOE_ENABLED) { - if (!vectors_left) - pf->num_fcoe_msix = 0; - else if (vectors_left >= pf->num_fcoe_qps) - pf->num_fcoe_msix = pf->num_fcoe_qps; - else - pf->num_fcoe_msix = 1; - v_budget += pf->num_fcoe_msix; - vectors_left -= pf->num_fcoe_msix; - } - -#endif /* can we reserve enough for iWARP? */ if (pf->flags & I40E_FLAG_IWARP_ENABLED) { iwarp_requested = pf->num_iwarp_msix; @@ -7918,6 +7902,23 @@ static int i40e_init_msix(struct i40e_pf *pf) } } + /* On systems with a large number of SMP cores, we previously limited + * the number of vectors for num_lan_msix to be at most 50% of the + * available vectors, to allow for other features. Now, we add back + * the remaining vectors. However, we ensure that the total + * num_lan_msix will not exceed num_online_cpus(). To do this, we + * calculate the number of vectors we can add without going over the + * cap of CPUs. For systems with a small number of CPUs this will be + * zero. + */ + extra_vectors = min_t(int, cpus - pf->num_lan_msix, vectors_left); + pf->num_lan_msix += extra_vectors; + vectors_left -= extra_vectors; + + WARN(vectors_left < 0, + "Calculation of remaining vectors underflowed. This is an accounting bug when determining total MSI-X vectors.\n"); + + v_budget += pf->num_lan_msix; pf->msix_entries = kcalloc(v_budget, sizeof(struct msix_entry), GFP_KERNEL); if (!pf->msix_entries) @@ -7958,10 +7959,6 @@ static int i40e_init_msix(struct i40e_pf *pf) pf->num_vmdq_msix = 1; /* force VMDqs to only one vector */ pf->num_vmdq_vsis = 1; pf->num_vmdq_qps = 1; -#ifdef I40E_FCOE - pf->num_fcoe_qps = 0; - pf->num_fcoe_msix = 0; -#endif /* partition out the remaining vectors */ switch (vec) { @@ -7975,13 +7972,6 @@ static int i40e_init_msix(struct i40e_pf *pf) } else { pf->num_lan_msix = 2; } -#ifdef I40E_FCOE - /* give one vector to FCoE */ - if (pf->flags & I40E_FLAG_FCOE_ENABLED) { - pf->num_lan_msix = 1; - pf->num_fcoe_msix = 1; - } -#endif break; default: if (pf->flags & I40E_FLAG_IWARP_ENABLED) { @@ -8001,13 +7991,6 @@ static int i40e_init_msix(struct i40e_pf *pf) (vec - (pf->num_iwarp_msix + pf->num_vmdq_vsis)), pf->num_lan_msix); pf->num_lan_qps = pf->num_lan_msix; -#ifdef I40E_FCOE - /* give one vector to FCoE */ - if (pf->flags & I40E_FLAG_FCOE_ENABLED) { - pf->num_fcoe_msix = 1; - vec--; - } -#endif break; } } @@ -8028,13 +8011,6 @@ static int i40e_init_msix(struct i40e_pf *pf) dev_info(&pf->pdev->dev, "IWARP disabled, not enough MSI-X vectors\n"); pf->flags &= ~I40E_FLAG_IWARP_ENABLED; } -#ifdef I40E_FCOE - - if ((pf->flags & I40E_FLAG_FCOE_ENABLED) && (pf->num_fcoe_msix == 0)) { - dev_info(&pf->pdev->dev, "FCOE disabled, not enough MSI-X vectors\n"); - pf->flags &= ~I40E_FLAG_FCOE_ENABLED; - } -#endif i40e_debug(&pf->hw, I40E_DEBUG_INIT, "MSI-X vector distribution: PF %d, VMDq %d, FDSB %d, iWARP %d\n", pf->num_lan_msix, @@ -8133,9 +8109,6 @@ static int i40e_init_interrupt_scheme(struct i40e_pf *pf) if (vectors < 0) { pf->flags &= ~(I40E_FLAG_MSIX_ENABLED | I40E_FLAG_IWARP_ENABLED | -#ifdef I40E_FCOE - I40E_FLAG_FCOE_ENABLED | -#endif I40E_FLAG_RSS_ENABLED | I40E_FLAG_DCB_CAPABLE | I40E_FLAG_DCB_ENABLED | @@ -8196,7 +8169,7 @@ static int i40e_setup_misc_vector(struct i40e_pf *pf) /* Only request the irq if this is the first time through, and * not when we're rebuilding after a Reset */ - if (!test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state)) { + if (!test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) { err = request_irq(pf->msix_entries[0].vector, i40e_intr, 0, pf->int_name, pf); if (err) { @@ -8368,13 +8341,10 @@ static int i40e_config_rss_reg(struct i40e_vsi *vsi, const u8 *seed, if (vsi->type == I40E_VSI_MAIN) { for (i = 0; i <= I40E_PFQF_HKEY_MAX_INDEX; i++) - i40e_write_rx_ctl(hw, I40E_PFQF_HKEY(i), - seed_dw[i]); + wr32(hw, I40E_PFQF_HKEY(i), seed_dw[i]); } else if (vsi->type == I40E_VSI_SRIOV) { for (i = 0; i <= I40E_VFQF_HKEY1_MAX_INDEX; i++) - i40e_write_rx_ctl(hw, - I40E_VFQF_HKEY1(i, vf_id), - seed_dw[i]); + wr32(hw, I40E_VFQF_HKEY1(i, vf_id), seed_dw[i]); } else { dev_err(&pf->pdev->dev, "Cannot set RSS seed - invalid VSI type\n"); } @@ -8392,9 +8362,7 @@ static int i40e_config_rss_reg(struct i40e_vsi *vsi, const u8 *seed, if (lut_size != I40E_VF_HLUT_ARRAY_SIZE) return -EINVAL; for (i = 0; i <= I40E_VFQF_HLUT_MAX_INDEX; i++) - i40e_write_rx_ctl(hw, - I40E_VFQF_HLUT1(i, vf_id), - lut_dw[i]); + wr32(hw, I40E_VFQF_HLUT1(i, vf_id), lut_dw[i]); } else { dev_err(&pf->pdev->dev, "Cannot set RSS LUT - invalid VSI type\n"); } @@ -8522,9 +8490,12 @@ static int i40e_pf_config_rss(struct i40e_pf *pf) i40e_write_rx_ctl(hw, I40E_PFQF_CTL_0, reg_val); /* Determine the RSS size of the VSI */ - if (!vsi->rss_size) - vsi->rss_size = min_t(int, pf->alloc_rss_size, - vsi->num_queue_pairs); + if (!vsi->rss_size) { + u16 qcount; + + qcount = vsi->num_queue_pairs / vsi->tc_config.numtc; + vsi->rss_size = min_t(int, pf->alloc_rss_size, qcount); + } if (!vsi->rss_size) return -EINVAL; @@ -8558,6 +8529,7 @@ static int i40e_pf_config_rss(struct i40e_pf *pf) * * returns 0 if rss is not enabled, if enabled returns the final rss queue * count which may be different from the requested queue count. + * Note: expects to be called while under rtnl_lock() **/ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count) { @@ -8570,12 +8542,14 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count) new_rss_size = min_t(int, queue_count, pf->rss_size_max); if (queue_count != vsi->num_queue_pairs) { + u16 qcount; + vsi->req_queue_pairs = queue_count; - i40e_prep_for_reset(pf); + i40e_prep_for_reset(pf, true); pf->alloc_rss_size = new_rss_size; - i40e_reset_and_rebuild(pf, true); + i40e_reset_and_rebuild(pf, true, true); /* Discard the user configured hash keys and lut, if less * queues are enabled. @@ -8587,8 +8561,8 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count) } /* Reset vsi->rss_size, as number of enabled queues changed */ - vsi->rss_size = min_t(int, pf->alloc_rss_size, - vsi->num_queue_pairs); + qcount = vsi->num_queue_pairs / vsi->tc_config.numtc; + vsi->rss_size = min_t(int, pf->alloc_rss_size, qcount); i40e_pf_config_rss(pf); } @@ -8821,10 +8795,6 @@ static int i40e_sw_init(struct i40e_pf *pf) pf->num_iwarp_msix = (int)num_online_cpus() + 1; } -#ifdef I40E_FCOE - i40e_init_pf_fcoe(pf); - -#endif /* I40E_FCOE */ #ifdef CONFIG_PCI_IOV if (pf->hw.func_caps.num_vfs && pf->hw.partition_id == 1) { pf->num_vf_qps = I40E_DEFAULT_QUEUES_PER_VF; @@ -8851,9 +8821,9 @@ static int i40e_sw_init(struct i40e_pf *pf) (pf->hw.aq.api_min_ver > 4))) { /* Supported in FW API version higher than 1.4 */ pf->flags |= I40E_FLAG_GENEVE_OFFLOAD_CAPABLE; - pf->auto_disable_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE; + pf->flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE; } else { - pf->auto_disable_flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE; + pf->flags = I40E_FLAG_HW_ATR_EVICT_CAPABLE; } pf->eeprom_version = 0xDEAD; @@ -8913,16 +8883,16 @@ bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features) need_reset = true; i40e_fdir_filter_exit(pf); } - pf->flags &= ~I40E_FLAG_FD_SB_ENABLED; - pf->auto_disable_flags &= ~I40E_FLAG_FD_SB_ENABLED; + pf->flags &= ~(I40E_FLAG_FD_SB_ENABLED | + I40E_FLAG_FD_SB_AUTO_DISABLED); /* reset fd counters */ - pf->fd_add_err = pf->fd_atr_cnt = pf->fd_tcp_rule = 0; - pf->fdir_pf_active_filters = 0; + pf->fd_add_err = 0; + pf->fd_atr_cnt = 0; /* if ATR was auto disabled it can be re-enabled. */ - if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && - (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) { - pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED; - if (I40E_DEBUG_FD & pf->hw.debug_mask) + if (pf->flags & I40E_FLAG_FD_ATR_AUTO_DISABLED) { + pf->flags &= ~I40E_FLAG_FD_ATR_AUTO_DISABLED; + if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && + (I40E_DEBUG_FD & pf->hw.debug_mask)) dev_info(&pf->pdev->dev, "ATR re-enabled.\n"); } } @@ -8955,6 +8925,7 @@ static void i40e_clear_rss_lut(struct i40e_vsi *vsi) * i40e_set_features - set the netdev feature flags * @netdev: ptr to the netdev being adjusted * @features: the feature set that the stack is suggesting + * Note: expects to be called while under rtnl_lock() **/ static int i40e_set_features(struct net_device *netdev, netdev_features_t features) @@ -8978,7 +8949,7 @@ static int i40e_set_features(struct net_device *netdev, need_reset = i40e_set_ntuple(pf, features); if (need_reset) - i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED)); + i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), true); return 0; } @@ -8990,12 +8961,12 @@ static int i40e_set_features(struct net_device *netdev, * * Returns the index number or I40E_MAX_PF_UDP_OFFLOAD_PORTS if port not found **/ -static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, __be16 port) +static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, u16 port) { u8 i; for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) { - if (pf->udp_ports[i].index == port) + if (pf->udp_ports[i].port == port) return i; } @@ -9013,7 +8984,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev, struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - __be16 port = ti->port; + u16 port = ntohs(ti->port); u8 next_idx; u8 idx; @@ -9021,8 +8992,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev, /* Check if port already exists */ if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) { - netdev_info(netdev, "port %d already offloaded\n", - ntohs(port)); + netdev_info(netdev, "port %d already offloaded\n", port); return; } @@ -9031,7 +9001,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev, if (next_idx == I40E_MAX_PF_UDP_OFFLOAD_PORTS) { netdev_info(netdev, "maximum number of offloaded UDP ports reached, not adding port %d\n", - ntohs(port)); + port); return; } @@ -9049,7 +9019,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev, } /* New port: add it and mark its index in the bitmap */ - pf->udp_ports[next_idx].index = port; + pf->udp_ports[next_idx].port = port; pf->pending_udp_bitmap |= BIT_ULL(next_idx); pf->flags |= I40E_FLAG_UDP_FILTER_SYNC; } @@ -9065,7 +9035,7 @@ static void i40e_udp_tunnel_del(struct net_device *netdev, struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - __be16 port = ti->port; + u16 port = ntohs(ti->port); u8 idx; idx = i40e_get_udp_port_idx(pf, port); @@ -9090,14 +9060,14 @@ static void i40e_udp_tunnel_del(struct net_device *netdev, /* if port exists, set it to 0 (mark for deletion) * and make it pending */ - pf->udp_ports[idx].index = 0; + pf->udp_ports[idx].port = 0; pf->pending_udp_bitmap |= BIT_ULL(idx); pf->flags |= I40E_FLAG_UDP_FILTER_SYNC; return; not_found: netdev_warn(netdev, "UDP port %d was not found, not deleting\n", - ntohs(port)); + port); } static int i40e_get_phys_port_id(struct net_device *netdev, @@ -9174,6 +9144,8 @@ static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], * is to change the mode then that requires a PF reset to * allow rebuild of the components with required hardware * bridge mode enabled. + * + * Note: expects to be called while under rtnl_lock() **/ static int i40e_ndo_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, @@ -9229,7 +9201,8 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev, pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; else pf->flags &= ~I40E_FLAG_VEB_MODE_ENABLED; - i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED)); + i40e_do_reset(pf, BIT_ULL(__I40E_PF_RESET_REQUESTED), + true); break; } } @@ -9352,10 +9325,6 @@ static const struct net_device_ops i40e_netdev_ops = { .ndo_poll_controller = i40e_netpoll, #endif .ndo_setup_tc = __i40e_setup_tc, -#ifdef I40E_FCOE - .ndo_fcoe_enable = i40e_fcoe_enable, - .ndo_fcoe_disable = i40e_fcoe_disable, -#endif .ndo_set_features = i40e_set_features, .ndo_set_vf_mac = i40e_ndo_set_vf_mac, .ndo_set_vf_vlan = i40e_ndo_set_vf_port_vlan, @@ -9388,6 +9357,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) u8 broadcast[ETH_ALEN]; u8 mac_addr[ETH_ALEN]; int etherdev_size; + netdev_features_t hw_enc_features; + netdev_features_t hw_features; etherdev_size = sizeof(struct i40e_netdev_priv); netdev = alloc_etherdev_mq(etherdev_size, vsi->alloc_queue_pairs); @@ -9398,52 +9369,57 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) np = netdev_priv(netdev); np->vsi = vsi; - netdev->hw_enc_features |= NETIF_F_SG | - NETIF_F_IP_CSUM | - NETIF_F_IPV6_CSUM | - NETIF_F_HIGHDMA | - NETIF_F_SOFT_FEATURES | - NETIF_F_TSO | - NETIF_F_TSO_ECN | - NETIF_F_TSO6 | - NETIF_F_GSO_GRE | - NETIF_F_GSO_GRE_CSUM | - NETIF_F_GSO_IPXIP4 | - NETIF_F_GSO_IPXIP6 | - NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM | - NETIF_F_GSO_PARTIAL | - NETIF_F_SCTP_CRC | - NETIF_F_RXHASH | - NETIF_F_RXCSUM | - 0; + hw_enc_features = NETIF_F_SG | + NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM | + NETIF_F_HIGHDMA | + NETIF_F_SOFT_FEATURES | + NETIF_F_TSO | + NETIF_F_TSO_ECN | + NETIF_F_TSO6 | + NETIF_F_GSO_GRE | + NETIF_F_GSO_GRE_CSUM | + NETIF_F_GSO_PARTIAL | + NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM | + NETIF_F_SCTP_CRC | + NETIF_F_RXHASH | + NETIF_F_RXCSUM | + 0; if (!(pf->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE)) netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM; netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM; + netdev->hw_enc_features |= hw_enc_features; + /* record features VLANs can make use of */ - netdev->vlan_features |= netdev->hw_enc_features | - NETIF_F_TSO_MANGLEID; + netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID; if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) netdev->hw_features |= NETIF_F_NTUPLE; + hw_features = hw_enc_features | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX; - netdev->hw_features |= netdev->hw_enc_features | - NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_CTAG_RX; + netdev->hw_features |= hw_features; - netdev->features |= netdev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; + netdev->features |= hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID; if (vsi->type == I40E_VSI_MAIN) { SET_NETDEV_DEV(netdev, &pf->pdev->dev); ether_addr_copy(mac_addr, hw->mac.perm_addr); - /* The following steps are necessary to prevent reception - * of tagged packets - some older NVM configurations load a - * default a MAC-VLAN filter that accepts any tagged packet - * which must be replaced by a normal filter. + /* The following steps are necessary for two reasons. First, + * some older NVM configurations load a default MAC-VLAN + * filter that will accept any tagged packet, and we want to + * replace this with a normal filter. Additionally, it is + * possible our MAC address was provided by the platform using + * Open Firmware or similar. + * + * Thus, we need to remove the default filter and install one + * specific to the MAC address. */ i40e_rm_default_mac_filter(vsi, mac_addr); spin_lock_bh(&vsi->mac_filter_hash_lock); @@ -9489,9 +9465,6 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) netdev->netdev_ops = &i40e_netdev_ops; netdev->watchdog_timeo = 5 * HZ; i40e_set_ethtool_ops(netdev); -#ifdef I40E_FCOE - i40e_fcoe_config_netdev(netdev, vsi); -#endif /* MTU range: 68 - 9706 */ netdev->min_mtu = ETH_MIN_MTU; @@ -9715,16 +9688,6 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, true); break; -#ifdef I40E_FCOE - case I40E_VSI_FCOE: - ret = i40e_fcoe_vsi_init(vsi, &ctxt); - if (ret) { - dev_info(&pf->pdev->dev, "failed to initialize FCoE VSI\n"); - return ret; - } - break; - -#endif /* I40E_FCOE */ case I40E_VSI_IWARP: /* send down message to iWARP */ break; @@ -9751,7 +9714,7 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) } vsi->active_filters = 0; - clear_bit(__I40E_FILTER_OVERFLOW_PROMISC, &vsi->state); + clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); spin_lock_bh(&vsi->mac_filter_hash_lock); /* If macvlan filters already exist, force them to get loaded */ hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { @@ -9804,7 +9767,7 @@ int i40e_vsi_release(struct i40e_vsi *vsi) return -ENODEV; } if (vsi == pf->vsi[pf->lan_vsi] && - !test_bit(__I40E_DOWN, &pf->state)) { + !test_bit(__I40E_VSI_DOWN, pf->state)) { dev_info(&pf->pdev->dev, "Can't remove PF VSI\n"); return -ENODEV; } @@ -10141,7 +10104,6 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type, } } case I40E_VSI_VMDQ2: - case I40E_VSI_FCOE: ret = i40e_config_netdev(vsi); if (ret) goto err_netdev; @@ -10789,6 +10751,9 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit) i40e_ptp_init(pf); + /* repopulate tunnel port filters */ + i40e_sync_udp_filters(pf); + return ret; } @@ -10801,9 +10766,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf) int queues_left; pf->num_lan_qps = 0; -#ifdef I40E_FCOE - pf->num_fcoe_qps = 0; -#endif /* Find the max queues to be put into basic use. We'll always be * using TC0, whether or not DCB is running, and TC0 will get the @@ -10820,9 +10782,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf) /* make sure all the fancies are disabled */ pf->flags &= ~(I40E_FLAG_RSS_ENABLED | I40E_FLAG_IWARP_ENABLED | -#ifdef I40E_FCOE - I40E_FLAG_FCOE_ENABLED | -#endif I40E_FLAG_FD_SB_ENABLED | I40E_FLAG_FD_ATR_ENABLED | I40E_FLAG_DCB_CAPABLE | @@ -10839,9 +10798,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf) pf->flags &= ~(I40E_FLAG_RSS_ENABLED | I40E_FLAG_IWARP_ENABLED | -#ifdef I40E_FCOE - I40E_FLAG_FCOE_ENABLED | -#endif I40E_FLAG_FD_SB_ENABLED | I40E_FLAG_FD_ATR_ENABLED | I40E_FLAG_DCB_ENABLED | @@ -10862,22 +10818,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf) queues_left -= pf->num_lan_qps; } -#ifdef I40E_FCOE - if (pf->flags & I40E_FLAG_FCOE_ENABLED) { - if (I40E_DEFAULT_FCOE <= queues_left) { - pf->num_fcoe_qps = I40E_DEFAULT_FCOE; - } else if (I40E_MINIMUM_FCOE <= queues_left) { - pf->num_fcoe_qps = I40E_MINIMUM_FCOE; - } else { - pf->num_fcoe_qps = 0; - pf->flags &= ~I40E_FLAG_FCOE_ENABLED; - dev_info(&pf->pdev->dev, "not enough queues for FCoE. FCoE feature will be disabled\n"); - } - - queues_left -= pf->num_fcoe_qps; - } - -#endif if (pf->flags & I40E_FLAG_FD_SB_ENABLED) { if (queues_left > 1) { queues_left -= 1; /* save 1 queue for FD */ @@ -10909,9 +10849,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf) pf->num_lan_qps, pf->alloc_rss_size, pf->num_req_vfs, pf->num_vf_qps, pf->num_vmdq_vsis, pf->num_vmdq_qps, queues_left); -#ifdef I40E_FCOE - dev_dbg(&pf->pdev->dev, "fcoe queues = %d\n", pf->num_fcoe_qps); -#endif } /** @@ -10978,10 +10915,6 @@ static void i40e_print_features(struct i40e_pf *pf) i += snprintf(&buf[i], REMAIN(i), " Geneve"); if (pf->flags & I40E_FLAG_PTP) i += snprintf(&buf[i], REMAIN(i), " PTP"); -#ifdef I40E_FCOE - if (pf->flags & I40E_FLAG_FCOE_ENABLED) - i += snprintf(&buf[i], REMAIN(i), " FCOE"); -#endif if (pf->flags & I40E_FLAG_VEB_MODE_ENABLED) i += snprintf(&buf[i], REMAIN(i), " VEB"); else @@ -10994,20 +10927,18 @@ static void i40e_print_features(struct i40e_pf *pf) /** * i40e_get_platform_mac_addr - get platform-specific MAC address - * * @pdev: PCI device information struct * @pf: board private structure * - * Look up the MAC address in Open Firmware on systems that support it, - * and use IDPROM on SPARC if no OF address is found. On return, the - * I40E_FLAG_PF_MAC will be wset in pf->flags if a platform-specific value - * has been selected. + * Look up the MAC address for the device. First we'll try + * eth_platform_get_mac_address, which will check Open Firmware, or arch + * specific fallback. Otherwise, we'll default to the stored value in + * firmware. **/ static void i40e_get_platform_mac_addr(struct pci_dev *pdev, struct i40e_pf *pf) { - pf->flags &= ~I40E_FLAG_PF_MAC; - if (!eth_platform_get_mac_address(&pdev->dev, pf->hw.mac.addr)) - pf->flags |= I40E_FLAG_PF_MAC; + if (eth_platform_get_mac_address(&pdev->dev, pf->hw.mac.addr)) + i40e_get_mac_addr(&pf->hw, pf->hw.mac.addr); } /** @@ -11072,7 +11003,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } pf->next_vsi = 0; pf->pdev = pdev; - set_bit(__I40E_DOWN, &pf->state); + set_bit(__I40E_VSI_DOWN, pf->state); hw = &pf->hw; hw->back = pf; @@ -11098,6 +11029,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->bus.bus_id = pdev->bus->number; pf->instance = pfs_found; + INIT_LIST_HEAD(&pf->l3_flex_pit_list); + INIT_LIST_HEAD(&pf->l4_flex_pit_list); + /* set up the locks for the AQ, do this only once in probe * and destroy them only once in remove */ @@ -11196,8 +11130,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } err = i40e_init_lan_hmc(hw, hw->func_caps.num_tx_qp, - hw->func_caps.num_rx_qp, - pf->fcoe_hmc_cntx_num, pf->fcoe_hmc_filt_num); + hw->func_caps.num_rx_qp, 0, 0); if (err) { dev_info(&pdev->dev, "init_lan_hmc failed: %d\n", err); goto err_init_lan_hmc; @@ -11219,9 +11152,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) i40e_aq_stop_lldp(hw, true, NULL); } - i40e_get_mac_addr(hw, hw->mac.addr); /* allow a platform config to override the HW addr */ i40e_get_platform_mac_addr(pdev, pf); + if (!is_valid_ether_addr(hw->mac.addr)) { dev_info(&pdev->dev, "invalid MAC address %pM\n", hw->mac.addr); err = -EIO; @@ -11232,18 +11165,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) i40e_get_port_mac_addr(hw, hw->mac.port_addr); if (is_valid_ether_addr(hw->mac.port_addr)) pf->flags |= I40E_FLAG_PORT_ID_VALID; -#ifdef I40E_FCOE - err = i40e_get_san_mac_addr(hw, hw->mac.san_addr); - if (err) - dev_info(&pdev->dev, - "(non-fatal) SAN MAC retrieval failed: %d\n", err); - if (!is_valid_ether_addr(hw->mac.san_addr)) { - dev_warn(&pdev->dev, "invalid SAN MAC address %pM, falling back to LAN MAC\n", - hw->mac.san_addr); - ether_addr_copy(hw->mac.san_addr, hw->mac.addr); - } - dev_info(&pf->pdev->dev, "SAN MAC: %pM\n", hw->mac.san_addr); -#endif /* I40E_FCOE */ pci_set_drvdata(pdev, pf); pci_save_state(pdev); @@ -11261,8 +11182,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pf->service_timer_period = HZ; INIT_WORK(&pf->service_task, i40e_service_task); - clear_bit(__I40E_SERVICE_SCHED, &pf->state); - pf->flags |= I40E_FLAG_NEED_LINK_UPDATE; + clear_bit(__I40E_SERVICE_SCHED, pf->state); /* NVM bit on means WoL disabled for the port */ i40e_read_nvm_word(hw, I40E_SR_NVM_WAKE_ON_LAN, &wol_nvm_bits); @@ -11300,7 +11220,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* prep for VF support */ if ((pf->flags & I40E_FLAG_SRIOV_ENABLED) && (pf->flags & I40E_FLAG_MSIX_ENABLED) && - !test_bit(__I40E_BAD_EEPROM, &pf->state)) { + !test_bit(__I40E_BAD_EEPROM, pf->state)) { if (pci_num_vf(pdev)) pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; } @@ -11373,7 +11293,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * before setting up the misc vector or we get a race and the vector * ends up disabled forever. */ - clear_bit(__I40E_DOWN, &pf->state); + clear_bit(__I40E_VSI_DOWN, pf->state); /* In case of MSIX we are going to setup the misc vector right here * to handle admin queue events etc. In case of legacy and MSI @@ -11393,7 +11313,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* prep for VF support */ if ((pf->flags & I40E_FLAG_SRIOV_ENABLED) && (pf->flags & I40E_FLAG_MSIX_ENABLED) && - !test_bit(__I40E_BAD_EEPROM, &pf->state)) { + !test_bit(__I40E_BAD_EEPROM, pf->state)) { /* disable link interrupts for VFs */ val = rd32(hw, I40E_PFGEN_PORTMDIO_NUM); val &= ~I40E_PFGEN_PORTMDIO_NUM_VFLINK_STAT_ENA_MASK; @@ -11434,16 +11354,13 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) round_jiffies(jiffies + pf->service_timer_period)); /* add this PF to client device list and launch a client service task */ - err = i40e_lan_add_device(pf); - if (err) - dev_info(&pdev->dev, "Failed to add PF to client API service list: %d\n", - err); - -#ifdef I40E_FCOE - /* create FCoE interface */ - i40e_fcoe_vsi_setup(pf); + if (pf->flags & I40E_FLAG_IWARP_ENABLED) { + err = i40e_lan_add_device(pf); + if (err) + dev_info(&pdev->dev, "Failed to add PF to client API service list: %d\n", + err); + } -#endif #define PCI_SPEED_SIZE 8 #define PCI_WIDTH_SIZE 8 /* Devices on the IOSF bus do not have this information @@ -11531,7 +11448,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Unwind what we've done if something failed in the setup */ err_vsis: - set_bit(__I40E_DOWN, &pf->state); + set_bit(__I40E_VSI_DOWN, pf->state); i40e_clear_interrupt_scheme(pf); kfree(pf->vsi); err_switch_setup: @@ -11582,13 +11499,18 @@ static void i40e_remove(struct pci_dev *pdev) i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0); /* no more scheduling of any task */ - set_bit(__I40E_SUSPENDED, &pf->state); - set_bit(__I40E_DOWN, &pf->state); + set_bit(__I40E_SUSPENDED, pf->state); + set_bit(__I40E_VSI_DOWN, pf->state); if (pf->service_timer.data) del_timer_sync(&pf->service_timer); if (pf->service_task.func) cancel_work_sync(&pf->service_task); + /* Client close must be called explicitly here because the timer + * has been stopped. + */ + i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false); + if (pf->flags & I40E_FLAG_SRIOV_ENABLED) { i40e_free_vfs(pf); pf->flags &= ~I40E_FLAG_SRIOV_ENABLED; @@ -11615,10 +11537,11 @@ static void i40e_remove(struct pci_dev *pdev) i40e_vsi_release(pf->vsi[pf->lan_vsi]); /* remove attached clients */ - ret_code = i40e_lan_del_device(pf); - if (ret_code) { - dev_warn(&pdev->dev, "Failed to delete client device: %d\n", - ret_code); + if (pf->flags & I40E_FLAG_IWARP_ENABLED) { + ret_code = i40e_lan_del_device(pf); + if (ret_code) + dev_warn(&pdev->dev, "Failed to delete client device: %d\n", + ret_code); } /* shutdown and destroy the HMC */ @@ -11685,9 +11608,9 @@ static pci_ers_result_t i40e_pci_error_detected(struct pci_dev *pdev, } /* shutdown all operations */ - if (!test_bit(__I40E_SUSPENDED, &pf->state)) { + if (!test_bit(__I40E_SUSPENDED, pf->state)) { rtnl_lock(); - i40e_prep_for_reset(pf); + i40e_prep_for_reset(pf, true); rtnl_unlock(); } @@ -11752,11 +11675,11 @@ static void i40e_pci_error_resume(struct pci_dev *pdev) struct i40e_pf *pf = pci_get_drvdata(pdev); dev_dbg(&pdev->dev, "%s\n", __func__); - if (test_bit(__I40E_SUSPENDED, &pf->state)) + if (test_bit(__I40E_SUSPENDED, pf->state)) return; rtnl_lock(); - i40e_handle_reset_warning(pf); + i40e_handle_reset_warning(pf, true); rtnl_unlock(); } @@ -11816,10 +11739,10 @@ static void i40e_shutdown(struct pci_dev *pdev) struct i40e_pf *pf = pci_get_drvdata(pdev); struct i40e_hw *hw = &pf->hw; - set_bit(__I40E_SUSPENDED, &pf->state); - set_bit(__I40E_DOWN, &pf->state); + set_bit(__I40E_SUSPENDED, pf->state); + set_bit(__I40E_VSI_DOWN, pf->state); rtnl_lock(); - i40e_prep_for_reset(pf); + i40e_prep_for_reset(pf, true); rtnl_unlock(); wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0)); @@ -11829,11 +11752,16 @@ static void i40e_shutdown(struct pci_dev *pdev) cancel_work_sync(&pf->service_task); i40e_fdir_teardown(pf); + /* Client close must be called explicitly here because the timer + * has been stopped. + */ + i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false); + if (pf->wol_en && (pf->flags & I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE)) i40e_enable_mc_magic_wake(pf); rtnl_lock(); - i40e_prep_for_reset(pf); + i40e_prep_for_reset(pf, true); rtnl_unlock(); wr32(hw, I40E_PFPM_APM, @@ -11860,14 +11788,14 @@ static int i40e_suspend(struct pci_dev *pdev, pm_message_t state) struct i40e_hw *hw = &pf->hw; int retval = 0; - set_bit(__I40E_SUSPENDED, &pf->state); - set_bit(__I40E_DOWN, &pf->state); + set_bit(__I40E_SUSPENDED, pf->state); + set_bit(__I40E_VSI_DOWN, pf->state); if (pf->wol_en && (pf->flags & I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE)) i40e_enable_mc_magic_wake(pf); rtnl_lock(); - i40e_prep_for_reset(pf); + i40e_prep_for_reset(pf, true); rtnl_unlock(); wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0)); @@ -11912,10 +11840,10 @@ static int i40e_resume(struct pci_dev *pdev) pci_wake_from_d3(pdev, false); /* handling the reset will rebuild the device state */ - if (test_and_clear_bit(__I40E_SUSPENDED, &pf->state)) { - clear_bit(__I40E_DOWN, &pf->state); + if (test_and_clear_bit(__I40E_SUSPENDED, pf->state)) { + clear_bit(__I40E_VSI_DOWN, pf->state); rtnl_lock(); - i40e_reset_and_rebuild(pf, false); + i40e_reset_and_rebuild(pf, false, true); rtnl_unlock(); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index 38ee18f11124..800bd55d0159 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -292,14 +292,14 @@ i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, { enum i40e_status_code ret_code = 0; - if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) { - ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); - if (!ret_code) { + ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); + if (!ret_code) { + if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) { ret_code = i40e_read_nvm_word_aq(hw, offset, data); - i40e_release_nvm(hw); + } else { + ret_code = i40e_read_nvm_word_srctl(hw, offset, data); } - } else { - ret_code = i40e_read_nvm_word_srctl(hw, offset, data); + i40e_release_nvm(hw); } return ret_code; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_osdep.h b/drivers/net/ethernet/intel/i40e/i40e_osdep.h index fea81ed065db..80e66da6b145 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_osdep.h +++ b/drivers/net/ethernet/intel/i40e/i40e_osdep.h @@ -78,7 +78,4 @@ do { \ } while (0) typedef enum i40e_status_code i40e_status; -#ifdef CONFIG_I40E_FCOE -#define I40E_FCOE -#endif #endif /* _I40E_OSDEP_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index 2551fc827444..c56d976cf85a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -304,9 +304,6 @@ i40e_status i40e_read_pba_string(struct i40e_hw *hw, u8 *pba_num, u32 pba_num_size); i40e_status i40e_validate_mac_addr(u8 *mac_addr); void i40e_pre_tx_queue_cfg(struct i40e_hw *hw, u32 queue, bool enable); -#ifdef I40E_FCOE -i40e_status i40e_get_san_mac_addr(struct i40e_hw *hw, u8 *mac_addr); -#endif /* prototype for functions used for NVM access */ i40e_status i40e_init_nvm(struct i40e_hw *hw); i40e_status i40e_acquire_nvm(struct i40e_hw *hw, @@ -380,4 +377,21 @@ i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, u16 reg, u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num); i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw, u32 time, u32 interval); +i40e_status i40e_aq_write_ppp(struct i40e_hw *hw, void *buff, + u16 buff_size, u32 track_id, + u32 *error_offset, u32 *error_info, + struct i40e_asq_cmd_details *cmd_details); +i40e_status i40e_aq_get_ppp_list(struct i40e_hw *hw, void *buff, + u16 buff_size, u8 flags, + struct i40e_asq_cmd_details *cmd_details); +struct i40e_generic_seg_header * +i40e_find_segment_in_package(u32 segment_type, + struct i40e_package_header *pkg_header); +enum i40e_status_code +i40e_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg, + u32 track_id); +enum i40e_status_code +i40e_add_pinfo_to_list(struct i40e_hw *hw, + struct i40e_profile_segment *profile, + u8 *profile_info_sec, u32 track_id); #endif /* _I40E_PROTOTYPE_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index 2caee35528fa..18c1cc08da97 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -358,7 +358,7 @@ void i40e_ptp_tx_hwtstamp(struct i40e_pf *pf) skb_tstamp_tx(pf->ptp_tx_skb, &shhwtstamps); dev_kfree_skb_any(pf->ptp_tx_skb); pf->ptp_tx_skb = NULL; - clear_bit_unlock(__I40E_PTP_TX_IN_PROGRESS, &pf->state); + clear_bit_unlock(__I40E_PTP_TX_IN_PROGRESS, pf->state); } /** @@ -768,7 +768,7 @@ void i40e_ptp_stop(struct i40e_pf *pf) if (pf->ptp_tx_skb) { dev_kfree_skb_any(pf->ptp_tx_skb); pf->ptp_tx_skb = NULL; - clear_bit_unlock(__I40E_PTP_TX_IN_PROGRESS, &pf->state); + clear_bit_unlock(__I40E_PTP_TX_IN_PROGRESS, pf->state); } if (pf->ptp_clock) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_trace.h b/drivers/net/ethernet/intel/i40e/i40e_trace.h new file mode 100644 index 000000000000..d3e55f54a05e --- /dev/null +++ b/drivers/net/ethernet/intel/i40e/i40e_trace.h @@ -0,0 +1,229 @@ +/******************************************************************************* + * + * Intel(R) 40-10 Gigabit Ethernet Connection Network Driver + * Copyright(c) 2013 - 2017 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + * + ******************************************************************************/ + +/* Modeled on trace-events-sample.h */ + +/* The trace subsystem name for i40e will be "i40e". + * + * This file is named i40e_trace.h. + * + * Since this include file's name is different from the trace + * subsystem name, we'll have to define TRACE_INCLUDE_FILE at the end + * of this file. + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM i40e + +/* See trace-events-sample.h for a detailed description of why this + * guard clause is different from most normal include files. + */ +#if !defined(_I40E_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) +#define _I40E_TRACE_H_ + +#include <linux/tracepoint.h> + +/** + * i40e_trace() macro enables shared code to refer to trace points + * like: + * + * trace_i40e{,vf}_example(args...) + * + * ... as: + * + * i40e_trace(example, args...) + * + * ... to resolve to the PF or VF version of the tracepoint without + * ifdefs, and to allow tracepoints to be disabled entirely at build + * time. + * + * Trace point should always be referred to in the driver via this + * macro. + * + * Similarly, i40e_trace_enabled(trace_name) wraps references to + * trace_i40e{,vf}_<trace_name>_enabled() functions. + */ +#define _I40E_TRACE_NAME(trace_name) (trace_ ## i40e ## _ ## trace_name) +#define I40E_TRACE_NAME(trace_name) _I40E_TRACE_NAME(trace_name) + +#define i40e_trace(trace_name, args...) I40E_TRACE_NAME(trace_name)(args) + +#define i40e_trace_enabled(trace_name) I40E_TRACE_NAME(trace_name##_enabled)() + +/* Events common to PF and VF. Corresponding versions will be defined + * for both, named trace_i40e_* and trace_i40evf_*. The i40e_trace() + * macro above will select the right trace point name for the driver + * being built from shared code. + */ + +/* Events related to a vsi & ring */ +DECLARE_EVENT_CLASS( + i40e_tx_template, + + TP_PROTO(struct i40e_ring *ring, + struct i40e_tx_desc *desc, + struct i40e_tx_buffer *buf), + + TP_ARGS(ring, desc, buf), + + /* The convention here is to make the first fields in the + * TP_STRUCT match the TP_PROTO exactly. This enables the use + * of the args struct generated by the tplist tool (from the + * bcc-tools package) to be used for those fields. To access + * fields other than the tracepoint args will require the + * tplist output to be adjusted. + */ + TP_STRUCT__entry( + __field(void*, ring) + __field(void*, desc) + __field(void*, buf) + __string(devname, ring->netdev->name) + ), + + TP_fast_assign( + __entry->ring = ring; + __entry->desc = desc; + __entry->buf = buf; + __assign_str(devname, ring->netdev->name); + ), + + TP_printk( + "netdev: %s ring: %p desc: %p buf %p", + __get_str(devname), __entry->ring, + __entry->desc, __entry->buf) +); + +DEFINE_EVENT( + i40e_tx_template, i40e_clean_tx_irq, + TP_PROTO(struct i40e_ring *ring, + struct i40e_tx_desc *desc, + struct i40e_tx_buffer *buf), + + TP_ARGS(ring, desc, buf)); + +DEFINE_EVENT( + i40e_tx_template, i40e_clean_tx_irq_unmap, + TP_PROTO(struct i40e_ring *ring, + struct i40e_tx_desc *desc, + struct i40e_tx_buffer *buf), + + TP_ARGS(ring, desc, buf)); + +DECLARE_EVENT_CLASS( + i40e_rx_template, + + TP_PROTO(struct i40e_ring *ring, + union i40e_32byte_rx_desc *desc, + struct sk_buff *skb), + + TP_ARGS(ring, desc, skb), + + TP_STRUCT__entry( + __field(void*, ring) + __field(void*, desc) + __field(void*, skb) + __string(devname, ring->netdev->name) + ), + + TP_fast_assign( + __entry->ring = ring; + __entry->desc = desc; + __entry->skb = skb; + __assign_str(devname, ring->netdev->name); + ), + + TP_printk( + "netdev: %s ring: %p desc: %p skb %p", + __get_str(devname), __entry->ring, + __entry->desc, __entry->skb) +); + +DEFINE_EVENT( + i40e_rx_template, i40e_clean_rx_irq, + TP_PROTO(struct i40e_ring *ring, + union i40e_32byte_rx_desc *desc, + struct sk_buff *skb), + + TP_ARGS(ring, desc, skb)); + +DEFINE_EVENT( + i40e_rx_template, i40e_clean_rx_irq_rx, + TP_PROTO(struct i40e_ring *ring, + union i40e_32byte_rx_desc *desc, + struct sk_buff *skb), + + TP_ARGS(ring, desc, skb)); + +DECLARE_EVENT_CLASS( + i40e_xmit_template, + + TP_PROTO(struct sk_buff *skb, + struct i40e_ring *ring), + + TP_ARGS(skb, ring), + + TP_STRUCT__entry( + __field(void*, skb) + __field(void*, ring) + __string(devname, ring->netdev->name) + ), + + TP_fast_assign( + __entry->skb = skb; + __entry->ring = ring; + __assign_str(devname, ring->netdev->name); + ), + + TP_printk( + "netdev: %s skb: %p ring: %p", + __get_str(devname), __entry->skb, + __entry->ring) +); + +DEFINE_EVENT( + i40e_xmit_template, i40e_xmit_frame_ring, + TP_PROTO(struct sk_buff *skb, + struct i40e_ring *ring), + + TP_ARGS(skb, ring)); + +DEFINE_EVENT( + i40e_xmit_template, i40e_xmit_frame_ring_drop, + TP_PROTO(struct sk_buff *skb, + struct i40e_ring *ring), + + TP_ARGS(skb, ring)); + +/* Events unique to the PF. */ + +#endif /* _I40E_TRACE_H_ */ +/* This must be outside ifdef _I40E_TRACE_H */ + +/* This trace include file is not located in the .../include/trace + * with the kernel tracepoint definitions, because we're a loadable + * module. + */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE i40e_trace +#include <trace/define_trace.h> diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 97d46058d71d..29321a6167a6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -27,6 +27,7 @@ #include <linux/prefetch.h> #include <net/busy_poll.h> #include "i40e.h" +#include "i40e_trace.h" #include "i40e_prototype.h" static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, @@ -71,6 +72,9 @@ static void i40e_fdir(struct i40e_ring *tx_ring, flex_ptype |= I40E_TXD_FLTR_QW0_PCTYPE_MASK & (fdata->pctype << I40E_TXD_FLTR_QW0_PCTYPE_SHIFT); + flex_ptype |= I40E_TXD_FLTR_QW0_PCTYPE_MASK & + (fdata->flex_offset << I40E_TXD_FLTR_QW0_FLEXOFF_SHIFT); + /* Use LAN VSI Id if not programmed by user */ flex_ptype |= I40E_TXD_FLTR_QW0_DEST_VSI_MASK & ((u32)(fdata->dest_vsi ? : pf->vsi[pf->lan_vsi]->id) << @@ -203,7 +207,6 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi, struct i40e_pf *pf = vsi->back; struct udphdr *udp; struct iphdr *ip; - bool err = false; u8 *raw_packet; int ret; static char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0, @@ -219,18 +222,28 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi, udp = (struct udphdr *)(raw_packet + IP_HEADER_OFFSET + sizeof(struct iphdr)); - ip->daddr = fd_data->dst_ip[0]; + ip->daddr = fd_data->dst_ip; udp->dest = fd_data->dst_port; - ip->saddr = fd_data->src_ip[0]; + ip->saddr = fd_data->src_ip; udp->source = fd_data->src_port; + if (fd_data->flex_filter) { + u8 *payload = raw_packet + I40E_UDPIP_DUMMY_PACKET_LEN; + __be16 pattern = fd_data->flex_word; + u16 off = fd_data->flex_offset; + + *((__force __be16 *)(payload + off)) = pattern; + } + fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_UDP; ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add); if (ret) { dev_info(&pf->pdev->dev, "PCTYPE:%d, Filter command send failed for fd_id:%d (ret = %d)\n", fd_data->pctype, fd_data->fd_id, ret); - err = true; + /* Free the packet buffer since it wasn't added to the ring */ + kfree(raw_packet); + return -EOPNOTSUPP; } else if (I40E_DEBUG_FD & pf->hw.debug_mask) { if (add) dev_info(&pf->pdev->dev, @@ -241,10 +254,13 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi, "Filter deleted for PCTYPE %d loc = %d\n", fd_data->pctype, fd_data->fd_id); } - if (err) - kfree(raw_packet); - return err ? -EOPNOTSUPP : 0; + if (add) + pf->fd_udp4_filter_cnt++; + else + pf->fd_udp4_filter_cnt--; + + return 0; } #define I40E_TCPIP_DUMMY_PACKET_LEN 54 @@ -263,7 +279,6 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi, struct i40e_pf *pf = vsi->back; struct tcphdr *tcp; struct iphdr *ip; - bool err = false; u8 *raw_packet; int ret; /* Dummy packet */ @@ -281,39 +296,110 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi, tcp = (struct tcphdr *)(raw_packet + IP_HEADER_OFFSET + sizeof(struct iphdr)); - ip->daddr = fd_data->dst_ip[0]; + ip->daddr = fd_data->dst_ip; tcp->dest = fd_data->dst_port; - ip->saddr = fd_data->src_ip[0]; + ip->saddr = fd_data->src_ip; tcp->source = fd_data->src_port; + if (fd_data->flex_filter) { + u8 *payload = raw_packet + I40E_TCPIP_DUMMY_PACKET_LEN; + __be16 pattern = fd_data->flex_word; + u16 off = fd_data->flex_offset; + + *((__force __be16 *)(payload + off)) = pattern; + } + + fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP; + ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add); + if (ret) { + dev_info(&pf->pdev->dev, + "PCTYPE:%d, Filter command send failed for fd_id:%d (ret = %d)\n", + fd_data->pctype, fd_data->fd_id, ret); + /* Free the packet buffer since it wasn't added to the ring */ + kfree(raw_packet); + return -EOPNOTSUPP; + } else if (I40E_DEBUG_FD & pf->hw.debug_mask) { + if (add) + dev_info(&pf->pdev->dev, "Filter OK for PCTYPE %d loc = %d)\n", + fd_data->pctype, fd_data->fd_id); + else + dev_info(&pf->pdev->dev, + "Filter deleted for PCTYPE %d loc = %d\n", + fd_data->pctype, fd_data->fd_id); + } + if (add) { - pf->fd_tcp_rule++; + pf->fd_tcp4_filter_cnt++; if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && I40E_DEBUG_FD & pf->hw.debug_mask) dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n"); - pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED; + pf->flags |= I40E_FLAG_FD_ATR_AUTO_DISABLED; } else { - pf->fd_tcp_rule = (pf->fd_tcp_rule > 0) ? - (pf->fd_tcp_rule - 1) : 0; - if (pf->fd_tcp_rule == 0) { - if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) && - I40E_DEBUG_FD & pf->hw.debug_mask) - dev_info(&pf->pdev->dev, "ATR re-enabled due to no sideband TCP/IPv4 rules\n"); - pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED; - } + pf->fd_tcp4_filter_cnt--; } - fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP; - ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add); + return 0; +} + +#define I40E_SCTPIP_DUMMY_PACKET_LEN 46 +/** + * i40e_add_del_fdir_sctpv4 - Add/Remove SCTPv4 Flow Director filters for + * a specific flow spec + * @vsi: pointer to the targeted VSI + * @fd_data: the flow director data required for the FDir descriptor + * @add: true adds a filter, false removes it + * + * Returns 0 if the filters were successfully added or removed + **/ +static int i40e_add_del_fdir_sctpv4(struct i40e_vsi *vsi, + struct i40e_fdir_filter *fd_data, + bool add) +{ + struct i40e_pf *pf = vsi->back; + struct sctphdr *sctp; + struct iphdr *ip; + u8 *raw_packet; + int ret; + /* Dummy packet */ + static char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0, + 0x45, 0, 0, 0x20, 0, 0, 0x40, 0, 0x40, 0x84, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0}; + + raw_packet = kzalloc(I40E_FDIR_MAX_RAW_PACKET_SIZE, GFP_KERNEL); + if (!raw_packet) + return -ENOMEM; + memcpy(raw_packet, packet, I40E_SCTPIP_DUMMY_PACKET_LEN); + + ip = (struct iphdr *)(raw_packet + IP_HEADER_OFFSET); + sctp = (struct sctphdr *)(raw_packet + IP_HEADER_OFFSET + + sizeof(struct iphdr)); + ip->daddr = fd_data->dst_ip; + sctp->dest = fd_data->dst_port; + ip->saddr = fd_data->src_ip; + sctp->source = fd_data->src_port; + + if (fd_data->flex_filter) { + u8 *payload = raw_packet + I40E_SCTPIP_DUMMY_PACKET_LEN; + __be16 pattern = fd_data->flex_word; + u16 off = fd_data->flex_offset; + + *((__force __be16 *)(payload + off)) = pattern; + } + + fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_SCTP; + ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add); if (ret) { dev_info(&pf->pdev->dev, "PCTYPE:%d, Filter command send failed for fd_id:%d (ret = %d)\n", fd_data->pctype, fd_data->fd_id, ret); - err = true; + /* Free the packet buffer since it wasn't added to the ring */ + kfree(raw_packet); + return -EOPNOTSUPP; } else if (I40E_DEBUG_FD & pf->hw.debug_mask) { if (add) - dev_info(&pf->pdev->dev, "Filter OK for PCTYPE %d loc = %d)\n", + dev_info(&pf->pdev->dev, + "Filter OK for PCTYPE %d loc = %d\n", fd_data->pctype, fd_data->fd_id); else dev_info(&pf->pdev->dev, @@ -321,10 +407,12 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi, fd_data->pctype, fd_data->fd_id); } - if (err) - kfree(raw_packet); + if (add) + pf->fd_sctp4_filter_cnt++; + else + pf->fd_sctp4_filter_cnt--; - return err ? -EOPNOTSUPP : 0; + return 0; } #define I40E_IP_DUMMY_PACKET_LEN 34 @@ -343,7 +431,6 @@ static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi, { struct i40e_pf *pf = vsi->back; struct iphdr *ip; - bool err = false; u8 *raw_packet; int ret; int i; @@ -359,18 +446,29 @@ static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi, memcpy(raw_packet, packet, I40E_IP_DUMMY_PACKET_LEN); ip = (struct iphdr *)(raw_packet + IP_HEADER_OFFSET); - ip->saddr = fd_data->src_ip[0]; - ip->daddr = fd_data->dst_ip[0]; + ip->saddr = fd_data->src_ip; + ip->daddr = fd_data->dst_ip; ip->protocol = 0; + if (fd_data->flex_filter) { + u8 *payload = raw_packet + I40E_IP_DUMMY_PACKET_LEN; + __be16 pattern = fd_data->flex_word; + u16 off = fd_data->flex_offset; + + *((__force __be16 *)(payload + off)) = pattern; + } + fd_data->pctype = i; ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add); - if (ret) { dev_info(&pf->pdev->dev, "PCTYPE:%d, Filter command send failed for fd_id:%d (ret = %d)\n", fd_data->pctype, fd_data->fd_id, ret); - err = true; + /* The packet buffer wasn't added to the ring so we + * need to free it now. + */ + kfree(raw_packet); + return -EOPNOTSUPP; } else if (I40E_DEBUG_FD & pf->hw.debug_mask) { if (add) dev_info(&pf->pdev->dev, @@ -383,10 +481,12 @@ static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi, } } - if (err) - kfree(raw_packet); + if (add) + pf->fd_ip4_filter_cnt++; + else + pf->fd_ip4_filter_cnt--; - return err ? -EOPNOTSUPP : 0; + return 0; } /** @@ -409,6 +509,9 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi, case UDP_V4_FLOW: ret = i40e_add_del_fdir_udpv4(vsi, input, add); break; + case SCTP_V4_FLOW: + ret = i40e_add_del_fdir_sctpv4(vsi, input, add); + break; case IP_USER_FLOW: switch (input->ip4_proto) { case IPPROTO_TCP: @@ -417,19 +520,23 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi, case IPPROTO_UDP: ret = i40e_add_del_fdir_udpv4(vsi, input, add); break; + case IPPROTO_SCTP: + ret = i40e_add_del_fdir_sctpv4(vsi, input, add); + break; case IPPROTO_IP: ret = i40e_add_del_fdir_ipv4(vsi, input, add); break; default: /* We cannot support masking based on protocol */ - goto unsupported_flow; + dev_info(&pf->pdev->dev, "Unsupported IPv4 protocol 0x%02x\n", + input->ip4_proto); + return -EINVAL; } break; default: -unsupported_flow: - dev_info(&pf->pdev->dev, "Could not specify spec type %d\n", + dev_info(&pf->pdev->dev, "Unsupported flow type 0x%02x\n", input->flow_type); - ret = -EINVAL; + return -EINVAL; } /* The buffer allocated here will be normally be freed by @@ -476,7 +583,7 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring, * progress do nothing, once flush is complete the state will * be cleared. */ - if (test_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state)) + if (test_bit(__I40E_FD_FLUSH_REQUESTED, pf->state)) return; pf->fd_add_err++; @@ -484,9 +591,9 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring, pf->fd_atr_cnt = i40e_get_current_atr_cnt(pf); if ((rx_desc->wb.qword0.hi_dword.fd_id == 0) && - (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) { - pf->auto_disable_flags |= I40E_FLAG_FD_ATR_ENABLED; - set_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state); + pf->flags & I40E_FLAG_FD_SB_AUTO_DISABLED) { + pf->flags |= I40E_FLAG_FD_ATR_AUTO_DISABLED; + set_bit(__I40E_FD_FLUSH_REQUESTED, pf->state); } /* filter programming failed most likely due to table full */ @@ -498,12 +605,10 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring, */ if (fcnt_prog >= (fcnt_avail - I40E_FDIR_BUFFER_FULL_MARGIN)) { if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) && - !(pf->auto_disable_flags & - I40E_FLAG_FD_SB_ENABLED)) { + !(pf->flags & I40E_FLAG_FD_SB_AUTO_DISABLED)) { + pf->flags |= I40E_FLAG_FD_SB_AUTO_DISABLED; if (I40E_DEBUG_FD & pf->hw.debug_mask) dev_warn(&pdev->dev, "FD filter space full, new ntuple rules will not be added\n"); - pf->auto_disable_flags |= - I40E_FLAG_FD_SB_ENABLED; } } } else if (error == BIT(I40E_RX_PROG_STATUS_DESC_NO_FD_ENTRY_SHIFT)) { @@ -599,19 +704,15 @@ void i40e_free_tx_resources(struct i40e_ring *tx_ring) /** * i40e_get_tx_pending - how many tx descriptors not processed * @tx_ring: the ring of descriptors - * @in_sw: is tx_pending being checked in SW or HW * * Since there is no access to the ring head register * in XL710, we need to use our local copies **/ -u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw) +u32 i40e_get_tx_pending(struct i40e_ring *ring) { u32 head, tail; - if (!in_sw) - head = i40e_get_head(ring); - else - head = ring->next_to_clean; + head = i40e_get_head(ring); tail = readl(ring->tail); if (head != tail) @@ -657,6 +758,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, /* prevent any other reads prior to eop_desc */ read_barrier_depends(); + i40e_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf); /* we have caught up to head, no work left to do */ if (tx_head == tx_desc) break; @@ -683,6 +785,8 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, /* unmap remaining buffers */ while (tx_desc != eop_desc) { + i40e_trace(clean_tx_irq_unmap, + tx_ring, tx_desc, tx_buf); tx_buf++; tx_desc++; @@ -734,11 +838,11 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, * them to be written back in case we stay in NAPI. * In this mode on X722 we do not enable Interrupt. */ - unsigned int j = i40e_get_tx_pending(tx_ring, false); + unsigned int j = i40e_get_tx_pending(tx_ring); if (budget && ((j / WB_STRIDE) == 0) && (j > 0) && - !test_bit(__I40E_DOWN, &vsi->state) && + !test_bit(__I40E_VSI_DOWN, vsi->state) && (I40E_DESC_UNUSED(tx_ring) != tx_ring->count)) tx_ring->arm_wb = true; } @@ -756,7 +860,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, smp_mb(); if (__netif_subqueue_stopped(tx_ring->netdev, tx_ring->queue_index) && - !test_bit(__I40E_DOWN, &vsi->state)) { + !test_bit(__I40E_VSI_DOWN, vsi->state)) { netif_wake_subqueue(tx_ring->netdev, tx_ring->queue_index); ++tx_ring->tx_stats.restart_queue; @@ -930,9 +1034,29 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) } /** + * i40e_rx_is_programming_status - check for programming status descriptor + * @qw: qword representing status_error_len in CPU ordering + * + * The value of in the descriptor length field indicate if this + * is a programming status descriptor for flow director or FCoE + * by the value of I40E_RX_PROG_STATUS_DESC_LENGTH, otherwise + * it is a packet descriptor. + **/ +static inline bool i40e_rx_is_programming_status(u64 qw) +{ + /* The Rx filter programming status and SPH bit occupy the same + * spot in the descriptor. Since we don't support packet split we + * can just reuse the bit as an indication that this is a + * programming status descriptor. + */ + return qw & I40E_RXD_QW1_LENGTH_SPH_MASK; +} + +/** * i40e_clean_programming_status - clean the programming status descriptor * @rx_ring: the rx ring that has this descriptor * @rx_desc: the rx descriptor written back by HW + * @qw: qword representing status_error_len in CPU ordering * * Flow director should handle FD_FILTER_STATUS to check its filter programming * status being successful or not and take actions accordingly. FCoE should @@ -940,22 +1064,23 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) * **/ static void i40e_clean_programming_status(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc) + union i40e_rx_desc *rx_desc, + u64 qw) { - u64 qw; + u32 ntc = rx_ring->next_to_clean + 1; u8 id; - qw = le64_to_cpu(rx_desc->wb.qword1.status_error_len); + /* fetch, update, and store next to clean */ + ntc = (ntc < rx_ring->count) ? ntc : 0; + rx_ring->next_to_clean = ntc; + + prefetch(I40E_RX_DESC(rx_ring, ntc)); + id = (qw & I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK) >> I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT; if (id == I40E_RX_PROG_STATUS_DESC_FD_FILTER_STATUS) i40e_fd_handle_status(rx_ring, rx_desc, id); -#ifdef I40E_FCOE - else if ((id == I40E_RX_PROG_STATUS_DESC_FCOE_CTXT_PROG_STATUS) || - (id == I40E_RX_PROG_STATUS_DESC_FCOE_CTXT_INVL_STATUS)) - i40e_fcoe_handle_status(rx_ring, rx_desc, id); -#endif } /** @@ -1010,7 +1135,6 @@ err: **/ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) { - struct device *dev = rx_ring->dev; unsigned long bi_size; u16 i; @@ -1030,8 +1154,22 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) if (!rx_bi->page) continue; - dma_unmap_page(dev, rx_bi->dma, PAGE_SIZE, DMA_FROM_DEVICE); - __free_pages(rx_bi->page, 0); + /* Invalidate cache lines that may have been written to by + * device so that we avoid corrupting memory. + */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_bi->dma, + rx_bi->page_offset, + rx_ring->rx_buf_len, + DMA_FROM_DEVICE); + + /* free resources associated with mapping */ + dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma, + i40e_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + I40E_RX_DMA_ATTR); + + __page_frag_cache_drain(rx_bi->page, rx_bi->pagecnt_bias); rx_bi->page = NULL; rx_bi->page_offset = 0; @@ -1132,6 +1270,17 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) } /** + * i40e_rx_offset - Return expected offset into page to access data + * @rx_ring: Ring we are requesting offset of + * + * Returns the offset value for ring into the data buffer. + */ +static inline unsigned int i40e_rx_offset(struct i40e_ring *rx_ring) +{ + return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0; +} + +/** * i40e_alloc_mapped_page - recycle or make a new page * @rx_ring: ring to use * @bi: rx_buffer struct to modify @@ -1152,27 +1301,33 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, } /* alloc new page for storage */ - page = dev_alloc_page(); + page = dev_alloc_pages(i40e_rx_pg_order(rx_ring)); if (unlikely(!page)) { rx_ring->rx_stats.alloc_page_failed++; return false; } /* map page for use */ - dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE); + dma = dma_map_page_attrs(rx_ring->dev, page, 0, + i40e_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + I40E_RX_DMA_ATTR); /* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use */ if (dma_mapping_error(rx_ring->dev, dma)) { - __free_pages(page, 0); + __free_pages(page, i40e_rx_pg_order(rx_ring)); rx_ring->rx_stats.alloc_page_failed++; return false; } bi->dma = dma; bi->page = page; - bi->page_offset = 0; + bi->page_offset = i40e_rx_offset(rx_ring); + + /* initialize pagecnt_bias to 1 representing we fully own page */ + bi->pagecnt_bias = 1; return true; } @@ -1219,6 +1374,12 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) if (!i40e_alloc_mapped_page(rx_ring, bi)) goto no_buffers; + /* sync the buffer for use by the device */ + dma_sync_single_range_for_device(rx_ring->dev, bi->dma, + bi->page_offset, + rx_ring->rx_buf_len, + DMA_FROM_DEVICE); + /* Refresh the desc even if buffer_addrs didn't change * because each write-back erases this info. */ @@ -1259,8 +1420,6 @@ no_buffers: * @vsi: the VSI we care about * @skb: skb currently being received and modified * @rx_desc: the receive descriptor - * - * skb->protocol must be set before this function is called **/ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, struct sk_buff *skb, @@ -1422,12 +1581,12 @@ void i40e_process_skb_fields(struct i40e_ring *rx_ring, i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype); - /* modifies the skb - consumes the enet header */ - skb->protocol = eth_type_trans(skb, rx_ring->netdev); - i40e_rx_checksum(rx_ring->vsi, skb, rx_desc); skb_record_rx_queue(skb, rx_ring->queue_index); + + /* modifies the skb - consumes the enet header */ + skb->protocol = eth_type_trans(skb, rx_ring->netdev); } /** @@ -1472,7 +1631,10 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring, rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; /* transfer page from old buffer to new buffer */ - *new_buff = *old_buff; + new_buff->dma = old_buff->dma; + new_buff->page = old_buff->page; + new_buff->page_offset = old_buff->page_offset; + new_buff->pagecnt_bias = old_buff->pagecnt_bias; } /** @@ -1493,8 +1655,6 @@ static inline bool i40e_page_is_reusable(struct page *page) * the adapter for another receive * * @rx_buffer: buffer containing the page - * @page: page address from rx_buffer - * @truesize: actual size of the buffer in this page * * If page is reusable, rx_buffer->page_offset is adjusted to point to * an unused region in the page. @@ -1517,13 +1677,10 @@ static inline bool i40e_page_is_reusable(struct page *page) * * In either case, if the page is reusable its refcount is increased. **/ -static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer, - struct page *page, - const unsigned int truesize) +static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) { -#if (PAGE_SIZE >= 8192) - unsigned int last_offset = PAGE_SIZE - I40E_RXBUFFER_2048; -#endif + unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; + struct page *page = rx_buffer->page; /* Is any reuse possible? */ if (unlikely(!i40e_page_is_reusable(page))) @@ -1531,21 +1688,23 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer, #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely(page_count(page) != 1)) + if (unlikely((page_count(page) - pagecnt_bias) > 1)) return false; - - /* flip page offset to other buffer */ - rx_buffer->page_offset ^= truesize; #else - /* move offset up to the next cache line */ - rx_buffer->page_offset += truesize; - - if (rx_buffer->page_offset > last_offset) +#define I40E_LAST_OFFSET \ + (SKB_WITH_OVERHEAD(PAGE_SIZE) - I40E_RXBUFFER_2048) + if (rx_buffer->page_offset > I40E_LAST_OFFSET) return false; #endif - /* Inc ref count on page before passing it up to the stack */ - get_page(page); + /* If we have drained the page fragment pool we need to update + * the pagecnt_bias and page count so that we fully restock the + * number of references the driver holds. + */ + if (unlikely(!pagecnt_bias)) { + page_ref_add(page, USHRT_MAX); + rx_buffer->pagecnt_bias = USHRT_MAX; + } return true; } @@ -1554,145 +1713,201 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer, * i40e_add_rx_frag - Add contents of Rx buffer to sk_buff * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: buffer containing page to add - * @size: packet length from rx_desc * @skb: sk_buff to place the data into + * @size: packet length from rx_desc * * This function will add the data contained in rx_buffer->page to the skb. - * This is done either through a direct copy if the data in the buffer is - * less than the skb header size, otherwise it will just attach the page as - * a frag to the skb. + * It will just attach the page as a frag to the skb. * - * The function will then update the page offset if necessary and return - * true if the buffer can be reused by the adapter. + * The function will then update the page offset. **/ -static bool i40e_add_rx_frag(struct i40e_ring *rx_ring, +static void i40e_add_rx_frag(struct i40e_ring *rx_ring, struct i40e_rx_buffer *rx_buffer, - unsigned int size, - struct sk_buff *skb) + struct sk_buff *skb, + unsigned int size) { - struct page *page = rx_buffer->page; - unsigned char *va = page_address(page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) - unsigned int truesize = I40E_RXBUFFER_2048; + unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; #else - unsigned int truesize = ALIGN(size, L1_CACHE_BYTES); + unsigned int truesize = SKB_DATA_ALIGN(size + i40e_rx_offset(rx_ring)); #endif - unsigned int pull_len; - - if (unlikely(skb_is_nonlinear(skb))) - goto add_tail_frag; - - /* will the data fit in the skb we allocated? if so, just - * copy it as it is pretty small anyway - */ - if (size <= I40E_RX_HDR_SIZE) { - memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); - /* page is reusable, we can reuse buffer as-is */ - if (likely(i40e_page_is_reusable(page))) - return true; + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, + rx_buffer->page_offset, size, truesize); - /* this page cannot be reused so discard it */ - __free_pages(page, 0); - return false; - } + /* page is being used so we must update the page offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif +} - /* we need the header to contain the greater of either - * ETH_HLEN or 60 bytes if the skb->len is less than - * 60 for skb_pad. - */ - pull_len = eth_get_headlen(va, I40E_RX_HDR_SIZE); +/** + * i40e_get_rx_buffer - Fetch Rx buffer and synchronize data for use + * @rx_ring: rx descriptor ring to transact packets on + * @size: size of buffer to add to skb + * + * This function will pull an Rx buffer from the ring and synchronize it + * for use by the CPU. + */ +static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring, + const unsigned int size) +{ + struct i40e_rx_buffer *rx_buffer; - /* align pull length to size of long to optimize - * memcpy performance - */ - memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long))); + rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean]; + prefetchw(rx_buffer->page); - /* update all of the pointers */ - va += pull_len; - size -= pull_len; + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + size, + DMA_FROM_DEVICE); -add_tail_frag: - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, - (unsigned long)va & ~PAGE_MASK, size, truesize); + /* We have pulled a buffer for use, so decrement pagecnt_bias */ + rx_buffer->pagecnt_bias--; - return i40e_can_reuse_rx_page(rx_buffer, page, truesize); + return rx_buffer; } /** - * i40e_fetch_rx_buffer - Allocate skb and populate it + * i40e_construct_skb - Allocate skb and populate it * @rx_ring: rx descriptor ring to transact packets on - * @rx_desc: descriptor containing info written by hardware + * @rx_buffer: rx buffer to pull data from + * @size: size of buffer to add to skb * - * This function allocates an skb on the fly, and populates it with the page - * data from the current receive descriptor, taking care to set up the skb - * correctly, as well as handling calling the page recycle function if - * necessary. + * This function allocates an skb. It then populates it with the page + * data from the current receive descriptor, taking care to set up the + * skb correctly. */ -static inline -struct sk_buff *i40e_fetch_rx_buffer(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc, - struct sk_buff *skb) +static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, + struct i40e_rx_buffer *rx_buffer, + unsigned int size) { - u64 local_status_error_len = - le64_to_cpu(rx_desc->wb.qword1.status_error_len); - unsigned int size = - (local_status_error_len & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> - I40E_RXD_QW1_LENGTH_PBUF_SHIFT; - struct i40e_rx_buffer *rx_buffer; - struct page *page; + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(size); +#endif + unsigned int headlen; + struct sk_buff *skb; - rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean]; - page = rx_buffer->page; - prefetchw(page); + /* prefetch first cache line of first page */ + prefetch(va); +#if L1_CACHE_BYTES < 128 + prefetch(va + L1_CACHE_BYTES); +#endif + + /* allocate a skb to store the frags */ + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, + I40E_RX_HDR_SIZE, + GFP_ATOMIC | __GFP_NOWARN); + if (unlikely(!skb)) + return NULL; + + /* Determine available headroom for copy */ + headlen = size; + if (headlen > I40E_RX_HDR_SIZE) + headlen = eth_get_headlen(va, I40E_RX_HDR_SIZE); + + /* align pull length to size of long to optimize memcpy performance */ + memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); + + /* update all of the pointers */ + size -= headlen; + if (size) { + skb_add_rx_frag(skb, 0, rx_buffer->page, + rx_buffer->page_offset + headlen, + size, truesize); - if (likely(!skb)) { - void *page_addr = page_address(page) + rx_buffer->page_offset; + /* buffer is used by skb, update page_offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif + } else { + /* buffer is unused, reset bias back to rx_buffer */ + rx_buffer->pagecnt_bias++; + } - /* prefetch first cache line of first page */ - prefetch(page_addr); + return skb; +} + +/** + * i40e_build_skb - Build skb around an existing buffer + * @rx_ring: Rx descriptor ring to transact packets on + * @rx_buffer: Rx buffer to pull data from + * @size: size of buffer to add to skb + * + * This function builds an skb around an existing Rx buffer, taking care + * to set up the skb correctly and avoid any memcpy overhead. + */ +static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, + struct i40e_rx_buffer *rx_buffer, + unsigned int size) +{ + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(size); +#endif + struct sk_buff *skb; + + /* prefetch first cache line of first page */ + prefetch(va); #if L1_CACHE_BYTES < 128 - prefetch(page_addr + L1_CACHE_BYTES); + prefetch(va + L1_CACHE_BYTES); #endif + /* build an skb around the page buffer */ + skb = build_skb(va - I40E_SKB_PAD, truesize); + if (unlikely(!skb)) + return NULL; - /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, - I40E_RX_HDR_SIZE, - GFP_ATOMIC | __GFP_NOWARN); - if (unlikely(!skb)) { - rx_ring->rx_stats.alloc_buff_failed++; - return NULL; - } + /* update pointers within the skb to store the data */ + skb_reserve(skb, I40E_SKB_PAD); + __skb_put(skb, size); - /* we will be copying header into skb->data in - * pskb_may_pull so it is in our interest to prefetch - * it now to avoid a possible cache miss - */ - prefetchw(skb->data); - } + /* buffer is used by skb, update page_offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, - rx_buffer->dma, - rx_buffer->page_offset, - size, - DMA_FROM_DEVICE); + return skb; +} - /* pull page into skb */ - if (i40e_add_rx_frag(rx_ring, rx_buffer, size, skb)) { +/** + * i40e_put_rx_buffer - Clean up used buffer and either recycle or free + * @rx_ring: rx descriptor ring to transact packets on + * @rx_buffer: rx buffer to pull data from + * + * This function will clean up the contents of the rx_buffer. It will + * either recycle the bufer or unmap it and free the associated resources. + */ +static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, + struct i40e_rx_buffer *rx_buffer) +{ + if (i40e_can_reuse_rx_page(rx_buffer)) { /* hand second half of page back to the ring */ i40e_reuse_rx_page(rx_ring, rx_buffer); rx_ring->rx_stats.page_reuse_count++; } else { /* we are not reusing the buffer so unmap it */ - dma_unmap_page(rx_ring->dev, rx_buffer->dma, PAGE_SIZE, - DMA_FROM_DEVICE); + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + i40e_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); } /* clear contents of buffer_info */ rx_buffer->page = NULL; - - return skb; } /** @@ -1718,11 +1933,6 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring, prefetch(I40E_RX_DESC(rx_ring, ntc)); -#define staterrlen rx_desc->wb.qword1.status_error_len - if (unlikely(i40e_rx_is_programming_status(le64_to_cpu(staterrlen)))) { - i40e_clean_programming_status(rx_ring, rx_desc); - return true; - } /* if we are the last buffer then there is nothing else to do */ #define I40E_RXD_EOF BIT(I40E_RX_DESC_STATUS_EOF_SHIFT) if (likely(i40e_test_staterr(rx_desc, I40E_RXD_EOF))) @@ -1753,7 +1963,9 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) bool failure = false; while (likely(total_rx_packets < budget)) { + struct i40e_rx_buffer *rx_buffer; union i40e_rx_desc *rx_desc; + unsigned int size; u16 vlan_tag; u8 rx_ptype; u64 qword; @@ -1770,22 +1982,44 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) /* status_error_len will always be zero for unused descriptors * because it's cleared in cleanup, and overlaps with hdr_addr * which is always zero because packet split isn't used, if the - * hardware wrote DD then it will be non-zero + * hardware wrote DD then the length will be non-zero */ - if (!i40e_test_staterr(rx_desc, - BIT(I40E_RX_DESC_STATUS_DD_SHIFT))) - break; + qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); /* This memory barrier is needed to keep us from reading - * any other fields out of the rx_desc until we know the - * DD bit is set. + * any other fields out of the rx_desc until we have + * verified the descriptor has been written back. */ dma_rmb(); - skb = i40e_fetch_rx_buffer(rx_ring, rx_desc, skb); - if (!skb) + if (unlikely(i40e_rx_is_programming_status(qword))) { + i40e_clean_programming_status(rx_ring, rx_desc, qword); + continue; + } + size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> + I40E_RXD_QW1_LENGTH_PBUF_SHIFT; + if (!size) break; + i40e_trace(clean_rx_irq, rx_ring, rx_desc, skb); + rx_buffer = i40e_get_rx_buffer(rx_ring, size); + + /* retrieve a buffer from the ring */ + if (skb) + i40e_add_rx_frag(rx_ring, rx_buffer, skb, size); + else if (ring_uses_build_skb(rx_ring)) + skb = i40e_build_skb(rx_ring, rx_buffer, size); + else + skb = i40e_construct_skb(rx_ring, rx_buffer, size); + + /* exit if we failed to retrieve a buffer */ + if (!skb) { + rx_ring->rx_stats.alloc_buff_failed++; + rx_buffer->pagecnt_bias++; + break; + } + + i40e_put_rx_buffer(rx_ring, rx_buffer); cleaned_count++; if (i40e_is_non_eop(rx_ring, rx_desc, skb)) @@ -1798,6 +2032,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) */ if (unlikely(i40e_test_staterr(rx_desc, BIT(I40E_RXD_QW1_ERROR_SHIFT)))) { dev_kfree_skb_any(skb); + skb = NULL; continue; } @@ -1816,18 +2051,10 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) /* populate checksum, VLAN, and protocol */ i40e_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); -#ifdef I40E_FCOE - if (unlikely( - i40e_rx_is_fcoe(rx_ptype) && - !i40e_fcoe_handle_offload(rx_ring, rx_desc, skb))) { - dev_kfree_skb_any(skb); - continue; - } -#endif - vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ? le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0; + i40e_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb); i40e_receive_skb(rx_ring, skb, vlan_tag); skb = NULL; @@ -1944,7 +2171,7 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, } enable_int: - if (!test_bit(__I40E_DOWN, &vsi->state)) + if (!test_bit(__I40E_VSI_DOWN, vsi->state)) wr32(hw, INTREG(vector - 1), txval); if (q_vector->itr_countdown) @@ -1973,13 +2200,11 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) int budget_per_ring; int work_done = 0; - if (test_bit(__I40E_DOWN, &vsi->state)) { + if (test_bit(__I40E_VSI_DOWN, vsi->state)) { napi_complete(napi); return 0; } - /* Clear hung_detected bit */ - clear_bit(I40E_Q_VECTOR_HUNG_DETECT, &q_vector->hung_detected); /* Since the actual Tx work is minimal, we can give the Tx a larger * budget and be more aggressive about cleaning up the Tx descriptors. */ @@ -2079,7 +2304,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, if (!(pf->flags & I40E_FLAG_FD_ATR_ENABLED)) return; - if ((pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) + if (pf->flags & I40E_FLAG_FD_ATR_AUTO_DISABLED) return; /* if sampling is disabled do nothing */ @@ -2113,10 +2338,9 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, th = (struct tcphdr *)(hdr.network + hlen); /* Due to lack of space, no more new filters can be programmed */ - if (th->syn && (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) + if (th->syn && (pf->flags & I40E_FLAG_FD_ATR_AUTO_DISABLED)) return; - if ((pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) && - (!(pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))) { + if (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) { /* HW ATR eviction will take care of removing filters on FIN * and RST packets. */ @@ -2178,8 +2402,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) & I40E_TXD_FLTR_QW1_CNTINDEX_MASK; - if ((pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) && - (!(pf->auto_disable_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))) + if (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) dtype_cmd |= I40E_TXD_FLTR_QW1_ATR_MASK; fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32(flex_ptype); @@ -2200,15 +2423,9 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, * Returns error code indicate the frame should be dropped upon error and the * otherwise returns 0 to indicate the flags has been set properly. **/ -#ifdef I40E_FCOE -inline int i40e_tx_prepare_vlan_flags(struct sk_buff *skb, - struct i40e_ring *tx_ring, - u32 *flags) -#else static inline int i40e_tx_prepare_vlan_flags(struct sk_buff *skb, struct i40e_ring *tx_ring, u32 *flags) -#endif { __be16 protocol = skb->protocol; u32 tx_flags = 0; @@ -2409,7 +2626,7 @@ static int i40e_tsyn(struct i40e_ring *tx_ring, struct sk_buff *skb, return 0; if (pf->ptp_tx && - !test_and_set_bit_lock(__I40E_PTP_TX_IN_PROGRESS, &pf->state)) { + !test_and_set_bit_lock(__I40E_PTP_TX_IN_PROGRESS, pf->state)) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; pf->ptp_tx_skb = skb_get(skb); } else { @@ -2716,15 +2933,9 @@ bool __i40e_chk_linearize(struct sk_buff *skb) * @td_cmd: the command field in the descriptor * @td_offset: offset for checksum or crc **/ -#ifdef I40E_FCOE -inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, - struct i40e_tx_buffer *first, u32 tx_flags, - const u8 hdr_len, u32 td_cmd, u32 td_offset) -#else static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, struct i40e_tx_buffer *first, u32 tx_flags, const u8 hdr_len, u32 td_cmd, u32 td_offset) -#endif { unsigned int data_len = skb->data_len; unsigned int size = skb_headlen(skb); @@ -2925,6 +3136,8 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, /* prefetch the data, we'll need it later */ prefetch(skb->data); + i40e_trace(xmit_frame_ring, skb, tx_ring); + count = i40e_xmit_descriptor_count(skb); if (i40e_chk_linearize(skb, count)) { if (__skb_linearize(skb)) { @@ -3003,6 +3216,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, return NETDEV_TX_OK; out_drop: + i40e_trace(xmit_frame_ring_drop, first->skb, tx_ring); dev_kfree_skb_any(first->skb); first->skb = NULL; return NETDEV_TX_OK; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index f80979025c01..f5de51124cae 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -117,10 +117,9 @@ enum i40e_dyn_idx_t { /* Supported Rx Buffer Sizes (a multiple of 128) */ #define I40E_RXBUFFER_256 256 +#define I40E_RXBUFFER_1536 1536 /* 128B aligned standard Ethernet frame */ #define I40E_RXBUFFER_2048 2048 -#define I40E_RXBUFFER_3072 3072 /* For FCoE MTU of 2158 */ -#define I40E_RXBUFFER_4096 4096 -#define I40E_RXBUFFER_8192 8192 +#define I40E_RXBUFFER_3072 3072 /* Used for large frames w/ padding */ #define I40E_MAX_RXBUFFER 9728 /* largest size for single descriptor */ /* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we @@ -133,6 +132,61 @@ enum i40e_dyn_idx_t { #define I40E_RX_HDR_SIZE I40E_RXBUFFER_256 #define i40e_rx_desc i40e_32byte_rx_desc +#define I40E_RX_DMA_ATTR \ + (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) + +/* Attempt to maximize the headroom available for incoming frames. We + * use a 2K buffer for receives and need 1536/1534 to store the data for + * the frame. This leaves us with 512 bytes of room. From that we need + * to deduct the space needed for the shared info and the padding needed + * to IP align the frame. + * + * Note: For cache line sizes 256 or larger this value is going to end + * up negative. In these cases we should fall back to the legacy + * receive path. + */ +#if (PAGE_SIZE < 8192) +#define I40E_2K_TOO_SMALL_WITH_PADDING \ +((NET_SKB_PAD + I40E_RXBUFFER_1536) > SKB_WITH_OVERHEAD(I40E_RXBUFFER_2048)) + +static inline int i40e_compute_pad(int rx_buf_len) +{ + int page_size, pad_size; + + page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2); + pad_size = SKB_WITH_OVERHEAD(page_size) - rx_buf_len; + + return pad_size; +} + +static inline int i40e_skb_pad(void) +{ + int rx_buf_len; + + /* If a 2K buffer cannot handle a standard Ethernet frame then + * optimize padding for a 3K buffer instead of a 1.5K buffer. + * + * For a 3K buffer we need to add enough padding to allow for + * tailroom due to NET_IP_ALIGN possibly shifting us out of + * cache-line alignment. + */ + if (I40E_2K_TOO_SMALL_WITH_PADDING) + rx_buf_len = I40E_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN); + else + rx_buf_len = I40E_RXBUFFER_1536; + + /* if needed make room for NET_IP_ALIGN */ + rx_buf_len -= NET_IP_ALIGN; + + return i40e_compute_pad(rx_buf_len); +} + +#define I40E_SKB_PAD i40e_skb_pad() +#else +#define I40E_2K_TOO_SMALL_WITH_PADDING false +#define I40E_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +#endif + /** * i40e_test_staterr - tests bits in Rx descriptor status and error fields * @rx_desc: pointer to receive descriptor (in le64 format) @@ -255,7 +309,12 @@ struct i40e_tx_buffer { struct i40e_rx_buffer { dma_addr_t dma; struct page *page; - unsigned int page_offset; +#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) + __u32 page_offset; +#else + __u16 page_offset; +#endif + __u16 pagecnt_bias; }; struct i40e_queue_stats { @@ -269,7 +328,6 @@ struct i40e_tx_queue_stats { u64 tx_done_old; u64 tx_linearize; u64 tx_force_wb; - u64 tx_lost_interrupt; }; struct i40e_rx_queue_stats { @@ -335,7 +393,8 @@ struct i40e_ring { u8 packet_stride; u16 flags; -#define I40E_TXR_FLAGS_WB_ON_ITR BIT(0) +#define I40E_TXR_FLAGS_WB_ON_ITR BIT(0) +#define I40E_RXR_FLAGS_BUILD_SKB_ENABLED BIT(1) /* stats structs */ struct i40e_queue_stats stats; @@ -363,6 +422,21 @@ struct i40e_ring { */ } ____cacheline_internodealigned_in_smp; +static inline bool ring_uses_build_skb(struct i40e_ring *ring) +{ + return !!(ring->flags & I40E_RXR_FLAGS_BUILD_SKB_ENABLED); +} + +static inline void set_ring_build_skb_enabled(struct i40e_ring *ring) +{ + ring->flags |= I40E_RXR_FLAGS_BUILD_SKB_ENABLED; +} + +static inline void clear_ring_build_skb_enabled(struct i40e_ring *ring) +{ + ring->flags &= ~I40E_RXR_FLAGS_BUILD_SKB_ENABLED; +} + enum i40e_latency_range { I40E_LOWEST_LATENCY = 0, I40E_LOW_LATENCY = 1, @@ -384,6 +458,17 @@ struct i40e_ring_container { #define i40e_for_each_ring(pos, head) \ for (pos = (head).ring; pos != NULL; pos = pos->next) +static inline unsigned int i40e_rx_pg_order(struct i40e_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring->rx_buf_len > (PAGE_SIZE / 2)) + return 1; +#endif + return 0; +} + +#define i40e_rx_pg_size(_ring) (PAGE_SIZE << i40e_rx_pg_order(_ring)) + bool i40e_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count); netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev); void i40e_clean_tx_ring(struct i40e_ring *tx_ring); @@ -393,15 +478,8 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring); void i40e_free_tx_resources(struct i40e_ring *tx_ring); void i40e_free_rx_resources(struct i40e_ring *rx_ring); int i40e_napi_poll(struct napi_struct *napi, int budget); -#ifdef I40E_FCOE -void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, - struct i40e_tx_buffer *first, u32 tx_flags, - const u8 hdr_len, u32 td_cmd, u32 td_offset); -int i40e_tx_prepare_vlan_flags(struct sk_buff *skb, - struct i40e_ring *tx_ring, u32 *flags); -#endif void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector); -u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw); +u32 i40e_get_tx_pending(struct i40e_ring *ring); int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size); bool __i40e_chk_linearize(struct sk_buff *skb); @@ -483,16 +561,6 @@ static inline bool i40e_chk_linearize(struct sk_buff *skb, int count) } /** - * i40e_rx_is_fcoe - returns true if the Rx packet type is FCoE - * @ptype: the packet type field from Rx descriptor write-back - **/ -static inline bool i40e_rx_is_fcoe(u16 ptype) -{ - return (ptype >= I40E_RX_PTYPE_L2_FCOE_PAY3) && - (ptype <= I40E_RX_PTYPE_L2_FCOE_VFT_FCOTHER); -} - -/** * txring_txq - Find the netdev Tx ring based on the i40e Tx ring * @ring: Tx ring to find the netdev equivalent of **/ diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index 939f9fdc8f85..3a18ed13edc4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -78,6 +78,7 @@ enum i40e_debug_mask { I40E_DEBUG_DCB = 0x00000400, I40E_DEBUG_DIAG = 0x00000800, I40E_DEBUG_FD = 0x00001000, + I40E_DEBUG_PACKAGE = 0x00002000, I40E_DEBUG_IWARP = 0x00F00000, I40E_DEBUG_AQ_MESSAGE = 0x01000000, I40E_DEBUG_AQ_DESCRIPTOR = 0x02000000, @@ -1213,25 +1214,6 @@ struct i40e_veb_tc_stats { u64 tc_tx_bytes[I40E_MAX_TRAFFIC_CLASS]; }; -#ifdef I40E_FCOE -/* Statistics collected per function for FCoE */ -struct i40e_fcoe_stats { - u64 rx_fcoe_packets; /* fcoeprc */ - u64 rx_fcoe_dwords; /* focedwrc */ - u64 rx_fcoe_dropped; /* fcoerpdc */ - u64 tx_fcoe_packets; /* fcoeptc */ - u64 tx_fcoe_dwords; /* focedwtc */ - u64 fcoe_bad_fccrc; /* fcoecrc */ - u64 fcoe_last_error; /* fcoelast */ - u64 fcoe_ddp_count; /* fcoeddpc */ -}; - -/* offset to per function FCoE statistics block */ -#define I40E_FCOE_VF_STAT_OFFSET 0 -#define I40E_FCOE_PF_STAT_OFFSET 128 -#define I40E_FCOE_STAT_MAX (I40E_FCOE_PF_STAT_OFFSET + I40E_MAX_PF) - -#endif /* Statistics collected by the MAC */ struct i40e_hw_port_stats { /* eth stats collected by the port */ @@ -1319,125 +1301,6 @@ struct i40e_hw_port_stats { #define I40E_SRRD_SRCTL_ATTEMPTS 100000 -#ifdef I40E_FCOE -/* FCoE Tx context descriptor - Use the i40e_tx_context_desc struct */ - -enum i40E_fcoe_tx_ctx_desc_cmd_bits { - I40E_FCOE_TX_CTX_DESC_OPCODE_SINGLE_SEND = 0x00, /* 4 BITS */ - I40E_FCOE_TX_CTX_DESC_OPCODE_TSO_FC_CLASS2 = 0x01, /* 4 BITS */ - I40E_FCOE_TX_CTX_DESC_OPCODE_TSO_FC_CLASS3 = 0x05, /* 4 BITS */ - I40E_FCOE_TX_CTX_DESC_OPCODE_ETSO_FC_CLASS2 = 0x02, /* 4 BITS */ - I40E_FCOE_TX_CTX_DESC_OPCODE_ETSO_FC_CLASS3 = 0x06, /* 4 BITS */ - I40E_FCOE_TX_CTX_DESC_OPCODE_DWO_FC_CLASS2 = 0x03, /* 4 BITS */ - I40E_FCOE_TX_CTX_DESC_OPCODE_DWO_FC_CLASS3 = 0x07, /* 4 BITS */ - I40E_FCOE_TX_CTX_DESC_OPCODE_DDP_CTX_INVL = 0x08, /* 4 BITS */ - I40E_FCOE_TX_CTX_DESC_OPCODE_DWO_CTX_INVL = 0x09, /* 4 BITS */ - I40E_FCOE_TX_CTX_DESC_RELOFF = 0x10, - I40E_FCOE_TX_CTX_DESC_CLRSEQ = 0x20, - I40E_FCOE_TX_CTX_DESC_DIFENA = 0x40, - I40E_FCOE_TX_CTX_DESC_IL2TAG2 = 0x80 -}; - -/* FCoE DDP Context descriptor */ -struct i40e_fcoe_ddp_context_desc { - __le64 rsvd; - __le64 type_cmd_foff_lsize; -}; - -#define I40E_FCOE_DDP_CTX_QW1_DTYPE_SHIFT 0 -#define I40E_FCOE_DDP_CTX_QW1_DTYPE_MASK (0xFULL << \ - I40E_FCOE_DDP_CTX_QW1_DTYPE_SHIFT) - -#define I40E_FCOE_DDP_CTX_QW1_CMD_SHIFT 4 -#define I40E_FCOE_DDP_CTX_QW1_CMD_MASK (0xFULL << \ - I40E_FCOE_DDP_CTX_QW1_CMD_SHIFT) - -enum i40e_fcoe_ddp_ctx_desc_cmd_bits { - I40E_FCOE_DDP_CTX_DESC_BSIZE_512B = 0x00, /* 2 BITS */ - I40E_FCOE_DDP_CTX_DESC_BSIZE_4K = 0x01, /* 2 BITS */ - I40E_FCOE_DDP_CTX_DESC_BSIZE_8K = 0x02, /* 2 BITS */ - I40E_FCOE_DDP_CTX_DESC_BSIZE_16K = 0x03, /* 2 BITS */ - I40E_FCOE_DDP_CTX_DESC_DIFENA = 0x04, /* 1 BIT */ - I40E_FCOE_DDP_CTX_DESC_LASTSEQH = 0x08, /* 1 BIT */ -}; - -#define I40E_FCOE_DDP_CTX_QW1_FOFF_SHIFT 16 -#define I40E_FCOE_DDP_CTX_QW1_FOFF_MASK (0x3FFFULL << \ - I40E_FCOE_DDP_CTX_QW1_FOFF_SHIFT) - -#define I40E_FCOE_DDP_CTX_QW1_LSIZE_SHIFT 32 -#define I40E_FCOE_DDP_CTX_QW1_LSIZE_MASK (0x3FFFULL << \ - I40E_FCOE_DDP_CTX_QW1_LSIZE_SHIFT) - -/* FCoE DDP/DWO Queue Context descriptor */ -struct i40e_fcoe_queue_context_desc { - __le64 dmaindx_fbase; /* 0:11 DMAINDX, 12:63 FBASE */ - __le64 flen_tph; /* 0:12 FLEN, 13:15 TPH */ -}; - -#define I40E_FCOE_QUEUE_CTX_QW0_DMAINDX_SHIFT 0 -#define I40E_FCOE_QUEUE_CTX_QW0_DMAINDX_MASK (0xFFFULL << \ - I40E_FCOE_QUEUE_CTX_QW0_DMAINDX_SHIFT) - -#define I40E_FCOE_QUEUE_CTX_QW0_FBASE_SHIFT 12 -#define I40E_FCOE_QUEUE_CTX_QW0_FBASE_MASK (0xFFFFFFFFFFFFFULL << \ - I40E_FCOE_QUEUE_CTX_QW0_FBASE_SHIFT) - -#define I40E_FCOE_QUEUE_CTX_QW1_FLEN_SHIFT 0 -#define I40E_FCOE_QUEUE_CTX_QW1_FLEN_MASK (0x1FFFULL << \ - I40E_FCOE_QUEUE_CTX_QW1_FLEN_SHIFT) - -#define I40E_FCOE_QUEUE_CTX_QW1_TPH_SHIFT 13 -#define I40E_FCOE_QUEUE_CTX_QW1_TPH_MASK (0x7ULL << \ - I40E_FCOE_QUEUE_CTX_QW1_FLEN_SHIFT) - -enum i40e_fcoe_queue_ctx_desc_tph_bits { - I40E_FCOE_QUEUE_CTX_DESC_TPHRDESC = 0x1, - I40E_FCOE_QUEUE_CTX_DESC_TPHDATA = 0x2 -}; - -#define I40E_FCOE_QUEUE_CTX_QW1_RECIPE_SHIFT 30 -#define I40E_FCOE_QUEUE_CTX_QW1_RECIPE_MASK (0x3ULL << \ - I40E_FCOE_QUEUE_CTX_QW1_RECIPE_SHIFT) - -/* FCoE DDP/DWO Filter Context descriptor */ -struct i40e_fcoe_filter_context_desc { - __le32 param; - __le16 seqn; - - /* 48:51(0:3) RSVD, 52:63(4:15) DMAINDX */ - __le16 rsvd_dmaindx; - - /* 0:7 FLAGS, 8:52 RSVD, 53:63 LANQ */ - __le64 flags_rsvd_lanq; -}; - -#define I40E_FCOE_FILTER_CTX_QW0_DMAINDX_SHIFT 4 -#define I40E_FCOE_FILTER_CTX_QW0_DMAINDX_MASK (0xFFF << \ - I40E_FCOE_FILTER_CTX_QW0_DMAINDX_SHIFT) - -enum i40e_fcoe_filter_ctx_desc_flags_bits { - I40E_FCOE_FILTER_CTX_DESC_CTYP_DDP = 0x00, - I40E_FCOE_FILTER_CTX_DESC_CTYP_DWO = 0x01, - I40E_FCOE_FILTER_CTX_DESC_ENODE_INIT = 0x00, - I40E_FCOE_FILTER_CTX_DESC_ENODE_RSP = 0x02, - I40E_FCOE_FILTER_CTX_DESC_FC_CLASS2 = 0x00, - I40E_FCOE_FILTER_CTX_DESC_FC_CLASS3 = 0x04 -}; - -#define I40E_FCOE_FILTER_CTX_QW1_FLAGS_SHIFT 0 -#define I40E_FCOE_FILTER_CTX_QW1_FLAGS_MASK (0xFFULL << \ - I40E_FCOE_FILTER_CTX_QW1_FLAGS_SHIFT) - -#define I40E_FCOE_FILTER_CTX_QW1_PCTYPE_SHIFT 8 -#define I40E_FCOE_FILTER_CTX_QW1_PCTYPE_MASK (0x3FULL << \ - I40E_FCOE_FILTER_CTX_QW1_PCTYPE_SHIFT) - -#define I40E_FCOE_FILTER_CTX_QW1_LANQINDX_SHIFT 53 -#define I40E_FCOE_FILTER_CTX_QW1_LANQINDX_MASK (0x7FFULL << \ - I40E_FCOE_FILTER_CTX_QW1_LANQINDX_SHIFT) - -#endif /* I40E_FCOE */ enum i40e_switch_element_types { I40E_SWITCH_ELEMENT_TYPE_MAC = 1, I40E_SWITCH_ELEMENT_TYPE_PF = 2, @@ -1600,4 +1463,83 @@ struct i40e_lldp_variables { #define I40E_FLEX_56_MASK (0x1ULL << I40E_FLEX_56_SHIFT) #define I40E_FLEX_57_SHIFT 6 #define I40E_FLEX_57_MASK (0x1ULL << I40E_FLEX_57_SHIFT) + +/* Version format for PPP */ +struct i40e_ppp_version { + u8 major; + u8 minor; + u8 update; + u8 draft; +}; + +#define I40E_PPP_NAME_SIZE 32 + +/* Package header */ +struct i40e_package_header { + struct i40e_ppp_version version; + u32 segment_count; + u32 segment_offset[1]; +}; + +/* Generic segment header */ +struct i40e_generic_seg_header { +#define SEGMENT_TYPE_METADATA 0x00000001 +#define SEGMENT_TYPE_NOTES 0x00000002 +#define SEGMENT_TYPE_I40E 0x00000011 +#define SEGMENT_TYPE_X722 0x00000012 + u32 type; + struct i40e_ppp_version version; + u32 size; + char name[I40E_PPP_NAME_SIZE]; +}; + +struct i40e_metadata_segment { + struct i40e_generic_seg_header header; + struct i40e_ppp_version version; + u32 track_id; + char name[I40E_PPP_NAME_SIZE]; +}; + +struct i40e_device_id_entry { + u32 vendor_dev_id; + u32 sub_vendor_dev_id; +}; + +struct i40e_profile_segment { + struct i40e_generic_seg_header header; + struct i40e_ppp_version version; + char name[I40E_PPP_NAME_SIZE]; + u32 device_table_count; + struct i40e_device_id_entry device_table[1]; +}; + +struct i40e_section_table { + u32 section_count; + u32 section_offset[1]; +}; + +struct i40e_profile_section_header { + u16 tbl_size; + u16 data_end; + struct { +#define SECTION_TYPE_INFO 0x00000010 +#define SECTION_TYPE_MMIO 0x00000800 +#define SECTION_TYPE_AQ 0x00000801 +#define SECTION_TYPE_NOTE 0x80000000 +#define SECTION_TYPE_NAME 0x80000001 + u32 type; + u32 offset; + u32 size; + } section; +}; + +struct i40e_profile_info { + u32 track_id; + struct i40e_ppp_version version; + u8 op; +#define I40E_PPP_ADD_TRACKID 0x01 +#define I40E_PPP_REMOVE_TRACKID 0x02 + u8 reserved[7]; + u8 name[I40E_PPP_NAME_SIZE]; +}; #endif /* _I40E_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h index 974ba2baf6ea..8552192a5bde 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h @@ -163,7 +163,8 @@ struct i40e_virtchnl_vsi_resource { #define I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING 0x00020000 #define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 0x00040000 #define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF 0X00080000 -#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00100000 +#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP 0X00100000 +#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00200000 #define I40E_VF_BASE_MODE_OFFLOADS (I40E_VIRTCHNL_VF_OFFLOAD_L2 | \ I40E_VIRTCHNL_VF_OFFLOAD_VLAN | \ diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 78460c52b7c4..95c23fbaa211 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -50,8 +50,8 @@ static void i40e_vc_vf_broadcast(struct i40e_pf *pf, for (i = 0; i < pf->num_alloc_vfs; i++, vf++) { int abs_vf_id = vf->vf_id + (int)hw->func_caps.vf_base_id; /* Not all vfs are enabled so skip the ones that are not */ - if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states) && - !test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) + if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states) && + !test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) continue; /* Ignore return value on purpose - a given VF may fail, but @@ -137,8 +137,8 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf) return; /* verify if the VF is in either init or active before proceeding */ - if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states) && - !test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) + if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states) && + !test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) return; abs_vf_id = vf->vf_id + (int)vf->pf->hw.func_caps.vf_base_id; @@ -702,10 +702,8 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) dev_info(&pf->pdev->dev, "Could not allocate VF broadcast filter\n"); spin_unlock_bh(&vsi->mac_filter_hash_lock); - i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id), - (u32)hena); - i40e_write_rx_ctl(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id), - (u32)(hena >> 32)); + wr32(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id), (u32)hena); + wr32(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id), (u32)(hena >> 32)); } /* program mac filter */ @@ -811,6 +809,11 @@ static void i40e_free_vf_res(struct i40e_vf *vf) u32 reg_idx, reg; int i, msix_vf; + /* Start by disabling VF's configuration API to prevent the OS from + * accessing the VF's VSI after it's freed / invalidated. + */ + clear_bit(I40E_VF_STATE_INIT, &vf->vf_states); + /* free vsi & disconnect it from the parent uplink */ if (vf->lan_vsi_idx) { i40e_vsi_release(pf->vsi[vf->lan_vsi_idx]); @@ -850,7 +853,6 @@ static void i40e_free_vf_res(struct i40e_vf *vf) /* reset some of the state variables keeping track of the resources */ vf->num_queue_pairs = 0; vf->vf_states = 0; - clear_bit(I40E_VF_STAT_INIT, &vf->vf_states); } /** @@ -882,7 +884,7 @@ static int i40e_alloc_vf_res(struct i40e_vf *vf) vf->num_queue_pairs = total_queue_pairs; /* VF is now completely initialized */ - set_bit(I40E_VF_STAT_INIT, &vf->vf_states); + set_bit(I40E_VF_STATE_INIT, &vf->vf_states); error_alloc: if (ret) @@ -921,25 +923,30 @@ static int i40e_quiesce_vf_pci(struct i40e_vf *vf) } /** - * i40e_reset_vf + * i40e_trigger_vf_reset * @vf: pointer to the VF structure * @flr: VFLR was issued or not * - * reset the VF + * Trigger hardware to start a reset for a particular VF. Expects the caller + * to wait the proper amount of time to allow hardware to reset the VF before + * it cleans up and restores VF functionality. **/ -void i40e_reset_vf(struct i40e_vf *vf, bool flr) +static void i40e_trigger_vf_reset(struct i40e_vf *vf, bool flr) { struct i40e_pf *pf = vf->pf; struct i40e_hw *hw = &pf->hw; u32 reg, reg_idx, bit_idx; - bool rsd = false; - int i; - - if (test_and_set_bit(__I40E_VF_DISABLE, &pf->state)) - return; /* warn the VF */ - clear_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states); + clear_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states); + + /* Disable VF's configuration API during reset. The flag is re-enabled + * in i40e_alloc_vf_res(), when it's safe again to access VF's VSI. + * It's normally disabled in i40e_free_vf_res(), but it's safer + * to do it earlier to give some time to finish to any VF config + * functions that may still be running at this point. + */ + clear_bit(I40E_VF_STATE_INIT, &vf->vf_states); /* In the case of a VFLR, the HW has already reset the VF and we * just need to clean up, so don't hit the VFRTRIG register. @@ -960,6 +967,79 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr) if (i40e_quiesce_vf_pci(vf)) dev_err(&pf->pdev->dev, "VF %d PCI transactions stuck\n", vf->vf_id); +} + +/** + * i40e_cleanup_reset_vf + * @vf: pointer to the VF structure + * + * Cleanup a VF after the hardware reset is finished. Expects the caller to + * have verified whether the reset is finished properly, and ensure the + * minimum amount of wait time has passed. + **/ +static void i40e_cleanup_reset_vf(struct i40e_vf *vf) +{ + struct i40e_pf *pf = vf->pf; + struct i40e_hw *hw = &pf->hw; + u32 reg; + + /* free VF resources to begin resetting the VSI state */ + i40e_free_vf_res(vf); + + /* Enable hardware by clearing the reset bit in the VPGEN_VFRTRIG reg. + * By doing this we allow HW to access VF memory at any point. If we + * did it any sooner, HW could access memory while it was being freed + * in i40e_free_vf_res(), causing an IOMMU fault. + * + * On the other hand, this needs to be done ASAP, because the VF driver + * is waiting for this to happen and may report a timeout. It's + * harmless, but it gets logged into Guest OS kernel log, so best avoid + * it. + */ + reg = rd32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id)); + reg &= ~I40E_VPGEN_VFRTRIG_VFSWR_MASK; + wr32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id), reg); + + /* reallocate VF resources to finish resetting the VSI state */ + if (!i40e_alloc_vf_res(vf)) { + int abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id; + i40e_enable_vf_mappings(vf); + set_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states); + clear_bit(I40E_VF_STATE_DISABLED, &vf->vf_states); + /* Do not notify the client during VF init */ + if (test_and_clear_bit(I40E_VF_STATE_PRE_ENABLE, + &vf->vf_states)) + i40e_notify_client_of_vf_reset(pf, abs_vf_id); + vf->num_vlan = 0; + } + + /* Tell the VF driver the reset is done. This needs to be done only + * after VF has been fully initialized, because the VF driver may + * request resources immediately after setting this flag. + */ + wr32(hw, I40E_VFGEN_RSTAT1(vf->vf_id), I40E_VFR_VFACTIVE); +} + +/** + * i40e_reset_vf + * @vf: pointer to the VF structure + * @flr: VFLR was issued or not + * + * reset the VF + **/ +void i40e_reset_vf(struct i40e_vf *vf, bool flr) +{ + struct i40e_pf *pf = vf->pf; + struct i40e_hw *hw = &pf->hw; + bool rsd = false; + u32 reg; + int i; + + /* If VFs have been disabled, there is no need to reset */ + if (test_and_set_bit(__I40E_VF_DISABLE, pf->state)) + return; + + i40e_trigger_vf_reset(vf, flr); /* poll VPGEN_VFRSTAT reg to make sure * that reset is complete @@ -984,35 +1064,116 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr) if (!rsd) dev_err(&pf->pdev->dev, "VF reset check timeout on VF %d\n", vf->vf_id); - wr32(hw, I40E_VFGEN_RSTAT1(vf->vf_id), I40E_VFR_COMPLETED); - /* clear the reset bit in the VPGEN_VFRTRIG reg */ - reg = rd32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id)); - reg &= ~I40E_VPGEN_VFRTRIG_VFSWR_MASK; - wr32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id), reg); + usleep_range(10000, 20000); - /* On initial reset, we won't have any queues */ - if (vf->lan_vsi_idx == 0) - goto complete_reset; + /* On initial reset, we don't have any queues to disable */ + if (vf->lan_vsi_idx != 0) + i40e_vsi_stop_rings(pf->vsi[vf->lan_vsi_idx]); - i40e_vsi_stop_rings(pf->vsi[vf->lan_vsi_idx]); -complete_reset: - /* reallocate VF resources to reset the VSI state */ - i40e_free_vf_res(vf); - if (!i40e_alloc_vf_res(vf)) { - int abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id; - i40e_enable_vf_mappings(vf); - set_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states); - clear_bit(I40E_VF_STAT_DISABLED, &vf->vf_states); - /* Do not notify the client during VF init */ - if (vf->pf->num_alloc_vfs) - i40e_notify_client_of_vf_reset(pf, abs_vf_id); - vf->num_vlan = 0; + i40e_cleanup_reset_vf(vf); + + i40e_flush(hw); + clear_bit(__I40E_VF_DISABLE, pf->state); +} + +/** + * i40e_reset_all_vfs + * @pf: pointer to the PF structure + * @flr: VFLR was issued or not + * + * Reset all allocated VFs in one go. First, tell the hardware to reset each + * VF, then do all the waiting in one chunk, and finally finish restoring each + * VF after the wait. This is useful during PF routines which need to reset + * all VFs, as otherwise it must perform these resets in a serialized fashion. + **/ +void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) +{ + struct i40e_hw *hw = &pf->hw; + struct i40e_vf *vf; + int i, v; + u32 reg; + + /* If we don't have any VFs, then there is nothing to reset */ + if (!pf->num_alloc_vfs) + return; + + /* If VFs have been disabled, there is no need to reset */ + if (test_and_set_bit(__I40E_VF_DISABLE, pf->state)) + return; + + /* Begin reset on all VFs at once */ + for (v = 0; v < pf->num_alloc_vfs; v++) + i40e_trigger_vf_reset(&pf->vf[v], flr); + + /* HW requires some time to make sure it can flush the FIFO for a VF + * when it resets it. Poll the VPGEN_VFRSTAT register for each VF in + * sequence to make sure that it has completed. We'll keep track of + * the VFs using a simple iterator that increments once that VF has + * finished resetting. + */ + for (i = 0, v = 0; i < 10 && v < pf->num_alloc_vfs; i++) { + usleep_range(10000, 20000); + + /* Check each VF in sequence, beginning with the VF to fail + * the previous check. + */ + while (v < pf->num_alloc_vfs) { + vf = &pf->vf[v]; + reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id)); + if (!(reg & I40E_VPGEN_VFRSTAT_VFRD_MASK)) + break; + + /* If the current VF has finished resetting, move on + * to the next VF in sequence. + */ + v++; + } } - /* tell the VF the reset is done */ - wr32(hw, I40E_VFGEN_RSTAT1(vf->vf_id), I40E_VFR_VFACTIVE); + + if (flr) + usleep_range(10000, 20000); + + /* Display a warning if at least one VF didn't manage to reset in + * time, but continue on with the operation. + */ + if (v < pf->num_alloc_vfs) + dev_err(&pf->pdev->dev, "VF reset check timeout on VF %d\n", + pf->vf[v].vf_id); + usleep_range(10000, 20000); + + /* Begin disabling all the rings associated with VFs, but do not wait + * between each VF. + */ + for (v = 0; v < pf->num_alloc_vfs; v++) { + /* On initial reset, we don't have any queues to disable */ + if (pf->vf[v].lan_vsi_idx == 0) + continue; + + i40e_vsi_stop_rings_no_wait(pf->vsi[pf->vf[v].lan_vsi_idx]); + } + + /* Now that we've notified HW to disable all of the VF rings, wait + * until they finish. + */ + for (v = 0; v < pf->num_alloc_vfs; v++) { + /* On initial reset, we don't have any queues to disable */ + if (pf->vf[v].lan_vsi_idx == 0) + continue; + + i40e_vsi_wait_queues_disabled(pf->vsi[pf->vf[v].lan_vsi_idx]); + } + + /* Hw may need up to 50ms to finish disabling the RX queues. We + * minimize the wait by delaying only once for all VFs. + */ + mdelay(50); + + /* Finish the reset on each VF */ + for (v = 0; v < pf->num_alloc_vfs; v++) + i40e_cleanup_reset_vf(&pf->vf[v]); i40e_flush(hw); - clear_bit(__I40E_VF_DISABLE, &pf->state); + clear_bit(__I40E_VF_DISABLE, pf->state); } /** @@ -1029,13 +1190,25 @@ void i40e_free_vfs(struct i40e_pf *pf) if (!pf->vf) return; - while (test_and_set_bit(__I40E_VF_DISABLE, &pf->state)) + while (test_and_set_bit(__I40E_VF_DISABLE, pf->state)) usleep_range(1000, 2000); i40e_notify_client_of_vf_enable(pf, 0); - for (i = 0; i < pf->num_alloc_vfs; i++) - if (test_bit(I40E_VF_STAT_INIT, &pf->vf[i].vf_states)) - i40e_vsi_stop_rings(pf->vsi[pf->vf[i].lan_vsi_idx]); + + /* Amortize wait time by stopping all VFs at the same time */ + for (i = 0; i < pf->num_alloc_vfs; i++) { + if (test_bit(I40E_VF_STATE_INIT, &pf->vf[i].vf_states)) + continue; + + i40e_vsi_stop_rings_no_wait(pf->vsi[pf->vf[i].lan_vsi_idx]); + } + + for (i = 0; i < pf->num_alloc_vfs; i++) { + if (test_bit(I40E_VF_STATE_INIT, &pf->vf[i].vf_states)) + continue; + + i40e_vsi_wait_queues_disabled(pf->vsi[pf->vf[i].lan_vsi_idx]); + } /* Disable IOV before freeing resources. This lets any VF drivers * running in the host get themselves cleaned up before we yank @@ -1046,13 +1219,11 @@ void i40e_free_vfs(struct i40e_pf *pf) else dev_warn(&pf->pdev->dev, "VFs are assigned - not disabling SR-IOV\n"); - msleep(20); /* let any messages in transit get finished up */ - /* free up VF resources */ tmp = pf->num_alloc_vfs; pf->num_alloc_vfs = 0; for (i = 0; i < tmp; i++) { - if (test_bit(I40E_VF_STAT_INIT, &pf->vf[i].vf_states)) + if (test_bit(I40E_VF_STATE_INIT, &pf->vf[i].vf_states)) i40e_free_vf_res(&pf->vf[i]); /* disable qp mappings */ i40e_disable_vf_mappings(&pf->vf[i]); @@ -1075,7 +1246,7 @@ void i40e_free_vfs(struct i40e_pf *pf) wr32(hw, I40E_GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx)); } } - clear_bit(__I40E_VF_DISABLE, &pf->state); + clear_bit(__I40E_VF_DISABLE, pf->state); } #ifdef CONFIG_PCI_IOV @@ -1120,12 +1291,15 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs) /* assign default capabilities */ set_bit(I40E_VIRTCHNL_VF_CAP_L2, &vfs[i].vf_caps); vfs[i].spoofchk = true; - /* VF resources get allocated during reset */ - i40e_reset_vf(&vfs[i], false); + + set_bit(I40E_VF_STATE_PRE_ENABLE, &vfs[i].vf_states); } pf->num_alloc_vfs = num_alloc_vfs; + /* VF resources get allocated during reset */ + i40e_reset_all_vfs(pf, false); + i40e_notify_client_of_vf_enable(pf, num_alloc_vfs); err_alloc: @@ -1152,7 +1326,7 @@ static int i40e_pci_sriov_enable(struct pci_dev *pdev, int num_vfs) int pre_existing_vfs = pci_num_vf(pdev); int err = 0; - if (test_bit(__I40E_TESTING, &pf->state)) { + if (test_bit(__I40E_TESTING, pf->state)) { dev_warn(&pdev->dev, "Cannot enable SR-IOV virtual functions while the device is undergoing diagnostic testing\n"); err = -EPERM; @@ -1258,7 +1432,7 @@ static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode, "Number of invalid messages exceeded for VF %d\n", vf->vf_id); dev_err(&pf->pdev->dev, "Use PF Control I/F to enable the VF\n"); - set_bit(I40E_VF_STAT_DISABLED, &vf->vf_states); + set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states); } } else { vf->num_valid_msgs++; @@ -1333,7 +1507,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) int len = 0; int ret; - if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states)) { + if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -1359,10 +1533,10 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) if (!vsi->info.pvid) vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_VLAN; - if (i40e_vf_client_capable(pf, vf->vf_id, I40E_CLIENT_IWARP) && + if (i40e_vf_client_capable(pf, vf->vf_id) && (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_IWARP)) { vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_IWARP; - set_bit(I40E_VF_STAT_IWARPENA, &vf->vf_states); + set_bit(I40E_VF_STATE_IWARPENA, &vf->vf_states); } if (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF) { @@ -1383,6 +1557,13 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2; } + if (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_ENCAP) + vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_ENCAP; + + if ((pf->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE) && + (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM)) + vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM; + if (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING) { if (pf->flags & I40E_FLAG_MFP_ENABLED) { dev_err(&pf->pdev->dev, @@ -1416,7 +1597,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) ether_addr_copy(vfres->vsi_res[0].default_mac_addr, vf->default_lan_addr.addr); } - set_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states); + set_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states); err: /* send the response back to the VF */ @@ -1439,7 +1620,7 @@ err: **/ static void i40e_vc_reset_vf_msg(struct i40e_vf *vf) { - if (test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) + if (test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) i40e_reset_vf(vf, false); } @@ -1487,7 +1668,7 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, int bkt; vsi = i40e_find_vsi_from_id(pf, info->vsi_id); - if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) || + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || !i40e_vc_isvalid_vsi_id(vf, info->vsi_id) || !vsi) { aq_ret = I40E_ERR_PARAM; @@ -1548,9 +1729,9 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, "VF %d successfully set multicast promiscuous mode\n", vf->vf_id); if (allmulti) - set_bit(I40E_VF_STAT_MC_PROMISC, &vf->vf_states); + set_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states); else - clear_bit(I40E_VF_STAT_MC_PROMISC, &vf->vf_states); + clear_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states); } if (info->flags & I40E_FLAG_VF_UNICAST_PROMISC) @@ -1599,9 +1780,9 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, "VF %d successfully set unicast promiscuous mode\n", vf->vf_id); if (alluni) - set_bit(I40E_VF_STAT_UC_PROMISC, &vf->vf_states); + set_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states); else - clear_bit(I40E_VF_STAT_UC_PROMISC, &vf->vf_states); + clear_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states); } error_param: @@ -1630,7 +1811,7 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) i40e_status aq_ret = 0; int i; - if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) { + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; goto error_param; } @@ -1687,7 +1868,7 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) unsigned long tempmap; int i; - if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) { + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; goto error_param; } @@ -1747,7 +1928,7 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) u16 vsi_id = vqs->vsi_id; i40e_status aq_ret = 0; - if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) { + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; goto error_param; } @@ -1786,7 +1967,7 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) struct i40e_pf *pf = vf->pf; i40e_status aq_ret = 0; - if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) { + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; goto error_param; } @@ -1828,7 +2009,7 @@ static int i40e_vc_get_stats_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) memset(&stats, 0, sizeof(struct i40e_eth_stats)); - if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) { + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; goto error_param; } @@ -1853,7 +2034,7 @@ error_param: } /* If the VF is not trusted restrict the number of MAC/VLAN it can program */ -#define I40E_VC_MAX_MAC_ADDR_PER_VF 8 +#define I40E_VC_MAX_MAC_ADDR_PER_VF 12 #define I40E_VC_MAX_VLAN_PER_VF 8 /** @@ -1915,7 +2096,7 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) i40e_status ret = 0; int i; - if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) || + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || !i40e_vc_isvalid_vsi_id(vf, vsi_id)) { ret = I40E_ERR_PARAM; goto error_param; @@ -1984,7 +2165,7 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) i40e_status ret = 0; int i; - if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) || + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || !i40e_vc_isvalid_vsi_id(vf, vsi_id)) { ret = I40E_ERR_PARAM; goto error_param; @@ -2050,7 +2231,7 @@ static int i40e_vc_add_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) "VF is not trusted, switch the VF to trusted to add more VLAN addresses\n"); goto error_param; } - if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) || + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || !i40e_vc_isvalid_vsi_id(vf, vsi_id)) { aq_ret = I40E_ERR_PARAM; goto error_param; @@ -2077,12 +2258,12 @@ static int i40e_vc_add_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) if (!ret) vf->num_vlan++; - if (test_bit(I40E_VF_STAT_UC_PROMISC, &vf->vf_states)) + if (test_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states)) i40e_aq_set_vsi_uc_promisc_on_vlan(&pf->hw, vsi->seid, true, vfl->vlan_id[i], NULL); - if (test_bit(I40E_VF_STAT_MC_PROMISC, &vf->vf_states)) + if (test_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states)) i40e_aq_set_vsi_mc_promisc_on_vlan(&pf->hw, vsi->seid, true, vfl->vlan_id[i], @@ -2117,7 +2298,7 @@ static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) i40e_status aq_ret = 0; int i; - if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) || + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || !i40e_vc_isvalid_vsi_id(vf, vsi_id)) { aq_ret = I40E_ERR_PARAM; goto error_param; @@ -2140,12 +2321,12 @@ static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) i40e_vsi_kill_vlan(vsi, vfl->vlan_id[i]); vf->num_vlan--; - if (test_bit(I40E_VF_STAT_UC_PROMISC, &vf->vf_states)) + if (test_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states)) i40e_aq_set_vsi_uc_promisc_on_vlan(&pf->hw, vsi->seid, false, vfl->vlan_id[i], NULL); - if (test_bit(I40E_VF_STAT_MC_PROMISC, &vf->vf_states)) + if (test_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states)) i40e_aq_set_vsi_mc_promisc_on_vlan(&pf->hw, vsi->seid, false, vfl->vlan_id[i], @@ -2171,8 +2352,8 @@ static int i40e_vc_iwarp_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) int abs_vf_id = vf->vf_id + pf->hw.func_caps.vf_base_id; i40e_status aq_ret = 0; - if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) || - !test_bit(I40E_VF_STAT_IWARPENA, &vf->vf_states)) { + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || + !test_bit(I40E_VF_STATE_IWARPENA, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; goto error_param; } @@ -2202,8 +2383,8 @@ static int i40e_vc_iwarp_qvmap_msg(struct i40e_vf *vf, u8 *msg, u16 msglen, (struct i40e_virtchnl_iwarp_qvlist_info *)msg; i40e_status aq_ret = 0; - if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) || - !test_bit(I40E_VF_STAT_IWARPENA, &vf->vf_states)) { + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || + !test_bit(I40E_VF_STATE_IWARPENA, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; goto error_param; } @@ -2240,7 +2421,7 @@ static int i40e_vc_config_rss_key(struct i40e_vf *vf, u8 *msg, u16 msglen) u16 vsi_id = vrk->vsi_id; i40e_status aq_ret = 0; - if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) || + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || !i40e_vc_isvalid_vsi_id(vf, vsi_id) || (vrk->key_len != I40E_HKEY_ARRAY_SIZE)) { aq_ret = I40E_ERR_PARAM; @@ -2272,7 +2453,7 @@ static int i40e_vc_config_rss_lut(struct i40e_vf *vf, u8 *msg, u16 msglen) u16 vsi_id = vrl->vsi_id; i40e_status aq_ret = 0; - if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states) || + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || !i40e_vc_isvalid_vsi_id(vf, vsi_id) || (vrl->lut_entries != I40E_VF_HLUT_ARRAY_SIZE)) { aq_ret = I40E_ERR_PARAM; @@ -2302,7 +2483,7 @@ static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg, u16 msglen) i40e_status aq_ret = 0; int len = 0; - if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) { + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -2339,7 +2520,7 @@ static int i40e_vc_set_rss_hena(struct i40e_vf *vf, u8 *msg, u16 msglen) struct i40e_hw *hw = &pf->hw; i40e_status aq_ret = 0; - if (!test_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states)) { + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -2369,7 +2550,7 @@ static int i40e_vc_validate_vf_msg(struct i40e_vf *vf, u32 v_opcode, int valid_len = 0; /* Check if VF is disabled. */ - if (test_bit(I40E_VF_STAT_DISABLED, &vf->vf_states)) + if (test_bit(I40E_VF_STATE_DISABLED, &vf->vf_states)) return I40E_ERR_PARAM; /* Validate message length. */ @@ -2637,7 +2818,7 @@ int i40e_vc_process_vflr_event(struct i40e_pf *pf) struct i40e_vf *vf; int vf_id; - if (!test_bit(__I40E_VFLR_EVENT_PENDING, &pf->state)) + if (!test_bit(__I40E_VFLR_EVENT_PENDING, pf->state)) return 0; /* Re-enable the VFLR interrupt cause here, before looking for which @@ -2650,7 +2831,7 @@ int i40e_vc_process_vflr_event(struct i40e_pf *pf) wr32(hw, I40E_PFINT_ICR0_ENA, reg); i40e_flush(hw); - clear_bit(__I40E_VFLR_EVENT_PENDING, &pf->state); + clear_bit(__I40E_VFLR_EVENT_PENDING, pf->state); for (vf_id = 0; vf_id < pf->num_alloc_vfs; vf_id++) { reg_idx = (hw->func_caps.vf_base_id + vf_id) / 32; bit_idx = (hw->func_caps.vf_base_id + vf_id) % 32; @@ -2693,7 +2874,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) vf = &(pf->vf[vf_id]); vsi = pf->vsi[vf->lan_vsi_idx]; - if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states)) { + if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n", vf_id); ret = -EAGAIN; @@ -2782,7 +2963,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, vf = &(pf->vf[vf_id]); vsi = pf->vsi[vf->lan_vsi_idx]; - if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states)) { + if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n", vf_id); ret = -EAGAIN; @@ -2914,7 +3095,7 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, vf = &(pf->vf[vf_id]); vsi = pf->vsi[vf->lan_vsi_idx]; - if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states)) { + if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n", vf_id); ret = -EAGAIN; @@ -2995,7 +3176,7 @@ int i40e_ndo_get_vf_config(struct net_device *netdev, vf = &(pf->vf[vf_id]); /* first vsi is always the LAN vsi */ vsi = pf->vsi[vf->lan_vsi_idx]; - if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states)) { + if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n", vf_id); ret = -EAGAIN; @@ -3114,7 +3295,7 @@ int i40e_ndo_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool enable) } vf = &(pf->vf[vf_id]); - if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states)) { + if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n", vf_id); ret = -EAGAIN; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 4012d069939a..20d7c8160e9e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -56,13 +56,14 @@ enum i40e_queue_ctrl { /* VF states */ enum i40e_vf_states { - I40E_VF_STAT_INIT = 0, - I40E_VF_STAT_ACTIVE, - I40E_VF_STAT_IWARPENA, - I40E_VF_STAT_FCOEENA, - I40E_VF_STAT_DISABLED, - I40E_VF_STAT_MC_PROMISC, - I40E_VF_STAT_UC_PROMISC, + I40E_VF_STATE_INIT = 0, + I40E_VF_STATE_ACTIVE, + I40E_VF_STATE_IWARPENA, + I40E_VF_STATE_FCOEENA, + I40E_VF_STATE_DISABLED, + I40E_VF_STATE_MC_PROMISC, + I40E_VF_STATE_UC_PROMISC, + I40E_VF_STATE_PRE_ENABLE, }; /* VF capabilities */ @@ -87,7 +88,6 @@ struct i40e_vf { u16 stag; struct i40e_virtchnl_ether_addr default_lan_addr; - struct i40e_virtchnl_ether_addr default_fcoe_addr; u16 port_vlan_id; bool pf_set_mac; /* The VMM admin set the VF MAC address */ bool trusted; @@ -125,6 +125,7 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen); int i40e_vc_process_vflr_event(struct i40e_pf *pf); void i40e_reset_vf(struct i40e_vf *vf, bool flr); +void i40e_reset_all_vfs(struct i40e_pf *pf, bool flr); void i40e_vc_notify_vf_reset(struct i40e_vf *vf); /* VF configuration related iplink handlers */ diff --git a/drivers/net/ethernet/intel/i40evf/Makefile b/drivers/net/ethernet/intel/i40evf/Makefile index 3a423836a565..a393f4a07f06 100644 --- a/drivers/net/ethernet/intel/i40evf/Makefile +++ b/drivers/net/ethernet/intel/i40evf/Makefile @@ -29,8 +29,11 @@ # # +ccflags-y += -I$(src) +subdir-ccflags-y += -I$(src) + obj-$(CONFIG_I40EVF) += i40evf.o i40evf-objs := i40evf_main.o i40evf_ethtool.o i40evf_virtchnl.o \ - i40e_txrx.o i40e_common.o i40e_adminq.o + i40e_txrx.o i40e_common.o i40e_adminq.o i40evf_client.o diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c index 96385156b824..8b0d4b255dea 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c @@ -797,8 +797,8 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, */ if (i40evf_asq_done(hw)) break; - usleep_range(1000, 2000); - total_delay++; + udelay(50); + total_delay += 50; } while (total_delay < hw->aq.asq_cmd_timeout); } diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq.h index 1f9b3b5d946d..e0bfaa3d4a21 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.h @@ -151,7 +151,7 @@ static inline int i40e_aq_rc_to_posix(int aq_ret, int aq_rc) /* general information */ #define I40E_AQ_LARGE_BUF 512 -#define I40E_ASQ_CMD_TIMEOUT 250 /* msecs */ +#define I40E_ASQ_CMD_TIMEOUT 250000 /* usecs */ void i40evf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, u16 opcode); diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index eeb9864bc5b1..91d8786d386d 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -132,6 +132,10 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_list_func_capabilities = 0x000A, i40e_aqc_opc_list_dev_capabilities = 0x000B, + /* Proxy commands */ + i40e_aqc_opc_set_proxy_config = 0x0104, + i40e_aqc_opc_set_ns_proxy_table_entry = 0x0105, + /* LAA */ i40e_aqc_opc_mac_address_read = 0x0107, i40e_aqc_opc_mac_address_write = 0x0108, @@ -139,6 +143,10 @@ enum i40e_admin_queue_opc { /* PXE */ i40e_aqc_opc_clear_pxe_mode = 0x0110, + /* WoL commands */ + i40e_aqc_opc_set_wol_filter = 0x0120, + i40e_aqc_opc_get_wake_reason = 0x0121, + /* internal switch commands */ i40e_aqc_opc_get_switch_config = 0x0200, i40e_aqc_opc_add_statistics = 0x0201, @@ -177,10 +185,15 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_remove_control_packet_filter = 0x025B, i40e_aqc_opc_add_cloud_filters = 0x025C, i40e_aqc_opc_remove_cloud_filters = 0x025D, + i40e_aqc_opc_clear_wol_switch_filters = 0x025E, i40e_aqc_opc_add_mirror_rule = 0x0260, i40e_aqc_opc_delete_mirror_rule = 0x0261, + /* Pipeline Personalization Profile */ + i40e_aqc_opc_write_personalization_profile = 0x0270, + i40e_aqc_opc_get_personalization_profile_list = 0x0271, + /* DCB commands */ i40e_aqc_opc_dcb_ignore_pfc = 0x0301, i40e_aqc_opc_dcb_updated = 0x0302, @@ -558,6 +571,56 @@ struct i40e_aqc_clear_pxe { I40E_CHECK_CMD_LENGTH(i40e_aqc_clear_pxe); +/* Set WoL Filter (0x0120) */ + +struct i40e_aqc_set_wol_filter { + __le16 filter_index; +#define I40E_AQC_MAX_NUM_WOL_FILTERS 8 +#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT 15 +#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_MASK (0x1 << \ + I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT) + +#define I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT 0 +#define I40E_AQC_SET_WOL_FILTER_INDEX_MASK (0x7 << \ + I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT) + __le16 cmd_flags; +#define I40E_AQC_SET_WOL_FILTER 0x8000 +#define I40E_AQC_SET_WOL_FILTER_NO_TCO_WOL 0x4000 +#define I40E_AQC_SET_WOL_FILTER_ACTION_CLEAR 0 +#define I40E_AQC_SET_WOL_FILTER_ACTION_SET 1 + __le16 valid_flags; +#define I40E_AQC_SET_WOL_FILTER_ACTION_VALID 0x8000 +#define I40E_AQC_SET_WOL_FILTER_NO_TCO_ACTION_VALID 0x4000 + u8 reserved[2]; + __le32 address_high; + __le32 address_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_set_wol_filter); + +struct i40e_aqc_set_wol_filter_data { + u8 filter[128]; + u8 mask[16]; +}; + +I40E_CHECK_STRUCT_LEN(0x90, i40e_aqc_set_wol_filter_data); + +/* Get Wake Reason (0x0121) */ + +struct i40e_aqc_get_wake_reason_completion { + u8 reserved_1[2]; + __le16 wake_reason; +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT 0 +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_MASK (0xFF << \ + I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT) +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT 8 +#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_MASK (0xFF << \ + I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT) + u8 reserved_2[12]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_wake_reason_completion); + /* Switch configuration commands (0x02xx) */ /* Used by many indirect commands that only pass an seid and a buffer in the @@ -640,6 +703,8 @@ struct i40e_aqc_set_port_parameters { #define I40E_AQ_SET_P_PARAMS_PAD_SHORT_PACKETS 2 /* must set! */ #define I40E_AQ_SET_P_PARAMS_DOUBLE_VLAN_ENA 4 __le16 bad_frame_vsi; +#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_SHIFT 0x0 +#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_MASK 0x3FF __le16 default_seid; /* reserved for command */ u8 reserved[10]; }; @@ -691,6 +756,7 @@ I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp); /* Set Switch Configuration (direct 0x0205) */ struct i40e_aqc_set_switch_config { __le16 flags; +/* flags used for both fields below */ #define I40E_AQ_SET_SWITCH_CFG_PROMISC 0x0001 #define I40E_AQ_SET_SWITCH_CFG_L2_FILTER 0x0002 __le16 valid_flags; @@ -1364,6 +1430,36 @@ struct i40e_aqc_add_delete_mirror_rule_completion { I40E_CHECK_CMD_LENGTH(i40e_aqc_add_delete_mirror_rule_completion); +/* Pipeline Personalization Profile */ +struct i40e_aqc_write_personalization_profile { + u8 flags; + u8 reserved[3]; + __le32 profile_track_id; + __le32 addr_high; + __le32 addr_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_write_personalization_profile); + +struct i40e_aqc_write_ppp_resp { + __le32 error_offset; + __le32 error_info; + __le32 addr_high; + __le32 addr_low; +}; + +struct i40e_aqc_get_applied_profiles { + u8 flags; +#define I40E_AQC_GET_PPP_GET_CONF 0x1 +#define I40E_AQC_GET_PPP_GET_RDPU_CONF 0x2 + u8 rsv[3]; + __le32 reserved; + __le32 addr_high; + __le32 addr_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_applied_profiles); + /* DCB 0x03xx*/ /* PFC Ignore (direct 0x0301) @@ -1839,11 +1935,12 @@ struct i40e_aqc_get_link_status { #define I40E_AQ_CONFIG_FEC_RS_ENA 0x02 #define I40E_AQ_CONFIG_CRC_ENA 0x04 #define I40E_AQ_CONFIG_PACING_MASK 0x78 - u8 external_power_ability; + u8 power_desc; #define I40E_AQ_LINK_POWER_CLASS_1 0x00 #define I40E_AQ_LINK_POWER_CLASS_2 0x01 #define I40E_AQ_LINK_POWER_CLASS_3 0x02 #define I40E_AQ_LINK_POWER_CLASS_4 0x03 +#define I40E_AQ_PWR_CLASS_MASK 0x03 u8 reserved[4]; }; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c index 89dfdbca13db..43f10761f4ba 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_common.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c @@ -958,7 +958,9 @@ u32 i40evf_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr) int retry = 5; u32 val = 0; - use_register = (hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver < 5); + use_register = (((hw->aq.api_maj_ver == 1) && + (hw->aq.api_min_ver < 5)) || + (hw->mac.type == I40E_MAC_X722)); if (!use_register) { do_retry: status = i40evf_aq_rx_ctl_read_register(hw, reg_addr, @@ -1019,7 +1021,9 @@ void i40evf_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val) bool use_register; int retry = 5; - use_register = (hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver < 5); + use_register = (((hw->aq.api_maj_ver == 1) && + (hw->aq.api_min_ver < 5)) || + (hw->mac.type == I40E_MAC_X722)); if (!use_register) { do_retry: status = i40evf_aq_rx_ctl_write_register(hw, reg_addr, @@ -1127,3 +1131,215 @@ i40e_status i40e_vf_reset(struct i40e_hw *hw) return i40e_aq_send_msg_to_pf(hw, I40E_VIRTCHNL_OP_RESET_VF, 0, NULL, 0, NULL); } + +/** + * i40evf_aq_write_ppp - Write pipeline personalization profile (ppp) + * @hw: pointer to the hw struct + * @buff: command buffer (size in bytes = buff_size) + * @buff_size: buffer size in bytes + * @track_id: package tracking id + * @error_offset: returns error offset + * @error_info: returns error information + * @cmd_details: pointer to command details structure or NULL + **/ +enum +i40e_status_code i40evf_aq_write_ppp(struct i40e_hw *hw, void *buff, + u16 buff_size, u32 track_id, + u32 *error_offset, u32 *error_info, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_write_personalization_profile *cmd = + (struct i40e_aqc_write_personalization_profile *) + &desc.params.raw; + struct i40e_aqc_write_ppp_resp *resp; + i40e_status status; + + i40evf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_write_personalization_profile); + + desc.flags |= cpu_to_le16(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD); + if (buff_size > I40E_AQ_LARGE_BUF) + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); + + desc.datalen = cpu_to_le16(buff_size); + + cmd->profile_track_id = cpu_to_le32(track_id); + + status = i40evf_asq_send_command(hw, &desc, buff, buff_size, cmd_details); + if (!status) { + resp = (struct i40e_aqc_write_ppp_resp *)&desc.params.raw; + if (error_offset) + *error_offset = le32_to_cpu(resp->error_offset); + if (error_info) + *error_info = le32_to_cpu(resp->error_info); + } + + return status; +} + +/** + * i40evf_aq_get_ppp_list - Read pipeline personalization profile (ppp) + * @hw: pointer to the hw struct + * @buff: command buffer (size in bytes = buff_size) + * @buff_size: buffer size in bytes + * @cmd_details: pointer to command details structure or NULL + **/ +enum +i40e_status_code i40evf_aq_get_ppp_list(struct i40e_hw *hw, void *buff, + u16 buff_size, u8 flags, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_get_applied_profiles *cmd = + (struct i40e_aqc_get_applied_profiles *)&desc.params.raw; + i40e_status status; + + i40evf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_get_personalization_profile_list); + + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); + if (buff_size > I40E_AQ_LARGE_BUF) + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); + desc.datalen = cpu_to_le16(buff_size); + + cmd->flags = flags; + + status = i40evf_asq_send_command(hw, &desc, buff, buff_size, cmd_details); + + return status; +} + +/** + * i40evf_find_segment_in_package + * @segment_type: the segment type to search for (i.e., SEGMENT_TYPE_I40E) + * @pkg_hdr: pointer to the package header to be searched + * + * This function searches a package file for a particular segment type. On + * success it returns a pointer to the segment header, otherwise it will + * return NULL. + **/ +struct i40e_generic_seg_header * +i40evf_find_segment_in_package(u32 segment_type, + struct i40e_package_header *pkg_hdr) +{ + struct i40e_generic_seg_header *segment; + u32 i; + + /* Search all package segments for the requested segment type */ + for (i = 0; i < pkg_hdr->segment_count; i++) { + segment = + (struct i40e_generic_seg_header *)((u8 *)pkg_hdr + + pkg_hdr->segment_offset[i]); + + if (segment->type == segment_type) + return segment; + } + + return NULL; +} + +/** + * i40evf_write_profile + * @hw: pointer to the hardware structure + * @profile: pointer to the profile segment of the package to be downloaded + * @track_id: package tracking id + * + * Handles the download of a complete package. + */ +enum i40e_status_code +i40evf_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile, + u32 track_id) +{ + i40e_status status = 0; + struct i40e_section_table *sec_tbl; + struct i40e_profile_section_header *sec = NULL; + u32 dev_cnt; + u32 vendor_dev_id; + u32 *nvm; + u32 section_size = 0; + u32 offset = 0, info = 0; + u32 i; + + if (!track_id) { + i40e_debug(hw, I40E_DEBUG_PACKAGE, "Track_id can't be 0."); + return I40E_NOT_SUPPORTED; + } + + dev_cnt = profile->device_table_count; + + for (i = 0; i < dev_cnt; i++) { + vendor_dev_id = profile->device_table[i].vendor_dev_id; + if ((vendor_dev_id >> 16) == PCI_VENDOR_ID_INTEL) + if (hw->device_id == (vendor_dev_id & 0xFFFF)) + break; + } + if (i == dev_cnt) { + i40e_debug(hw, I40E_DEBUG_PACKAGE, "Device doesn't support PPP"); + return I40E_ERR_DEVICE_NOT_SUPPORTED; + } + + nvm = (u32 *)&profile->device_table[dev_cnt]; + sec_tbl = (struct i40e_section_table *)&nvm[nvm[0] + 1]; + + for (i = 0; i < sec_tbl->section_count; i++) { + sec = (struct i40e_profile_section_header *)((u8 *)profile + + sec_tbl->section_offset[i]); + + /* Skip 'AQ', 'note' and 'name' sections */ + if (sec->section.type != SECTION_TYPE_MMIO) + continue; + + section_size = sec->section.size + + sizeof(struct i40e_profile_section_header); + + /* Write profile */ + status = i40evf_aq_write_ppp(hw, (void *)sec, (u16)section_size, + track_id, &offset, &info, NULL); + if (status) { + i40e_debug(hw, I40E_DEBUG_PACKAGE, + "Failed to write profile: offset %d, info %d", + offset, info); + break; + } + } + return status; +} + +/** + * i40evf_add_pinfo_to_list + * @hw: pointer to the hardware structure + * @profile: pointer to the profile segment of the package + * @profile_info_sec: buffer for information section + * @track_id: package tracking id + * + * Register a profile to the list of loaded profiles. + */ +enum i40e_status_code +i40evf_add_pinfo_to_list(struct i40e_hw *hw, + struct i40e_profile_segment *profile, + u8 *profile_info_sec, u32 track_id) +{ + i40e_status status = 0; + struct i40e_profile_section_header *sec = NULL; + struct i40e_profile_info *pinfo; + u32 offset = 0, info = 0; + + sec = (struct i40e_profile_section_header *)profile_info_sec; + sec->tbl_size = 1; + sec->data_end = sizeof(struct i40e_profile_section_header) + + sizeof(struct i40e_profile_info); + sec->section.type = SECTION_TYPE_INFO; + sec->section.offset = sizeof(struct i40e_profile_section_header); + sec->section.size = sizeof(struct i40e_profile_info); + pinfo = (struct i40e_profile_info *)(profile_info_sec + + sec->section.offset); + pinfo->track_id = track_id; + pinfo->version = profile->version; + pinfo->op = I40E_PPP_ADD_TRACKID; + memcpy(pinfo->name, profile->name, I40E_PPP_NAME_SIZE); + + status = i40evf_aq_write_ppp(hw, (void *)sec, sec->data_end, + track_id, &offset, &info, NULL); + return status; +} diff --git a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h index ba6c6bda0e22..741223d5d809 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h @@ -122,4 +122,21 @@ i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, u16 reg, u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num); i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw, u32 time, u32 interval); +i40e_status i40evf_aq_write_ppp(struct i40e_hw *hw, void *buff, + u16 buff_size, u32 track_id, + u32 *error_offset, u32 *error_info, + struct i40e_asq_cmd_details *cmd_details); +i40e_status i40evf_aq_get_ppp_list(struct i40e_hw *hw, void *buff, + u16 buff_size, u8 flags, + struct i40e_asq_cmd_details *cmd_details); +struct i40e_generic_seg_header * +i40evf_find_segment_in_package(u32 segment_type, + struct i40e_package_header *pkg_header); +enum i40e_status_code +i40evf_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg, + u32 track_id); +enum i40e_status_code +i40evf_add_pinfo_to_list(struct i40e_hw *hw, + struct i40e_profile_segment *profile, + u8 *profile_info_sec, u32 track_id); #endif /* _I40E_PROTOTYPE_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_trace.h b/drivers/net/ethernet/intel/i40evf/i40e_trace.h new file mode 100644 index 000000000000..9a5100b2b7c7 --- /dev/null +++ b/drivers/net/ethernet/intel/i40evf/i40e_trace.h @@ -0,0 +1,229 @@ +/******************************************************************************* + * + * Intel(R) 40-10 Gigabit Ethernet Virtual Function Driver + * Copyright(c) 2013 - 2017 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + * + ******************************************************************************/ + +/* Modeled on trace-events-sample.h */ + +/* The trace subsystem name for i40evf will be "i40evf". + * + * This file is named i40e_trace.h. + * + * Since this include file's name is different from the trace + * subsystem name, we'll have to define TRACE_INCLUDE_FILE at the end + * of this file. + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM i40evf + +/* See trace-events-sample.h for a detailed description of why this + * guard clause is different from most normal include files. + */ +#if !defined(_I40E_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) +#define _I40E_TRACE_H_ + +#include <linux/tracepoint.h> + +/** + * i40e_trace() macro enables shared code to refer to trace points + * like: + * + * trace_i40e{,vf}_example(args...) + * + * ... as: + * + * i40e_trace(example, args...) + * + * ... to resolve to the PF or VF version of the tracepoint without + * ifdefs, and to allow tracepoints to be disabled entirely at build + * time. + * + * Trace point should always be referred to in the driver via this + * macro. + * + * Similarly, i40e_trace_enabled(trace_name) wraps references to + * trace_i40e{,vf}_<trace_name>_enabled() functions. + */ +#define _I40E_TRACE_NAME(trace_name) (trace_ ## i40evf ## _ ## trace_name) +#define I40E_TRACE_NAME(trace_name) _I40E_TRACE_NAME(trace_name) + +#define i40e_trace(trace_name, args...) I40E_TRACE_NAME(trace_name)(args) + +#define i40e_trace_enabled(trace_name) I40E_TRACE_NAME(trace_name##_enabled)() + +/* Events common to PF and VF. Corresponding versions will be defined + * for both, named trace_i40e_* and trace_i40evf_*. The i40e_trace() + * macro above will select the right trace point name for the driver + * being built from shared code. + */ + +/* Events related to a vsi & ring */ +DECLARE_EVENT_CLASS( + i40evf_tx_template, + + TP_PROTO(struct i40e_ring *ring, + struct i40e_tx_desc *desc, + struct i40e_tx_buffer *buf), + + TP_ARGS(ring, desc, buf), + + /* The convention here is to make the first fields in the + * TP_STRUCT match the TP_PROTO exactly. This enables the use + * of the args struct generated by the tplist tool (from the + * bcc-tools package) to be used for those fields. To access + * fields other than the tracepoint args will require the + * tplist output to be adjusted. + */ + TP_STRUCT__entry( + __field(void*, ring) + __field(void*, desc) + __field(void*, buf) + __string(devname, ring->netdev->name) + ), + + TP_fast_assign( + __entry->ring = ring; + __entry->desc = desc; + __entry->buf = buf; + __assign_str(devname, ring->netdev->name); + ), + + TP_printk( + "netdev: %s ring: %p desc: %p buf %p", + __get_str(devname), __entry->ring, + __entry->desc, __entry->buf) +); + +DEFINE_EVENT( + i40evf_tx_template, i40evf_clean_tx_irq, + TP_PROTO(struct i40e_ring *ring, + struct i40e_tx_desc *desc, + struct i40e_tx_buffer *buf), + + TP_ARGS(ring, desc, buf)); + +DEFINE_EVENT( + i40evf_tx_template, i40evf_clean_tx_irq_unmap, + TP_PROTO(struct i40e_ring *ring, + struct i40e_tx_desc *desc, + struct i40e_tx_buffer *buf), + + TP_ARGS(ring, desc, buf)); + +DECLARE_EVENT_CLASS( + i40evf_rx_template, + + TP_PROTO(struct i40e_ring *ring, + union i40e_32byte_rx_desc *desc, + struct sk_buff *skb), + + TP_ARGS(ring, desc, skb), + + TP_STRUCT__entry( + __field(void*, ring) + __field(void*, desc) + __field(void*, skb) + __string(devname, ring->netdev->name) + ), + + TP_fast_assign( + __entry->ring = ring; + __entry->desc = desc; + __entry->skb = skb; + __assign_str(devname, ring->netdev->name); + ), + + TP_printk( + "netdev: %s ring: %p desc: %p skb %p", + __get_str(devname), __entry->ring, + __entry->desc, __entry->skb) +); + +DEFINE_EVENT( + i40evf_rx_template, i40evf_clean_rx_irq, + TP_PROTO(struct i40e_ring *ring, + union i40e_32byte_rx_desc *desc, + struct sk_buff *skb), + + TP_ARGS(ring, desc, skb)); + +DEFINE_EVENT( + i40evf_rx_template, i40evf_clean_rx_irq_rx, + TP_PROTO(struct i40e_ring *ring, + union i40e_32byte_rx_desc *desc, + struct sk_buff *skb), + + TP_ARGS(ring, desc, skb)); + +DECLARE_EVENT_CLASS( + i40evf_xmit_template, + + TP_PROTO(struct sk_buff *skb, + struct i40e_ring *ring), + + TP_ARGS(skb, ring), + + TP_STRUCT__entry( + __field(void*, skb) + __field(void*, ring) + __string(devname, ring->netdev->name) + ), + + TP_fast_assign( + __entry->skb = skb; + __entry->ring = ring; + __assign_str(devname, ring->netdev->name); + ), + + TP_printk( + "netdev: %s skb: %p ring: %p", + __get_str(devname), __entry->skb, + __entry->ring) +); + +DEFINE_EVENT( + i40evf_xmit_template, i40evf_xmit_frame_ring, + TP_PROTO(struct sk_buff *skb, + struct i40e_ring *ring), + + TP_ARGS(skb, ring)); + +DEFINE_EVENT( + i40evf_xmit_template, i40evf_xmit_frame_ring_drop, + TP_PROTO(struct sk_buff *skb, + struct i40e_ring *ring), + + TP_ARGS(skb, ring)); + +/* Events unique to the VF. */ + +#endif /* _I40E_TRACE_H_ */ +/* This must be outside ifdef _I40E_TRACE_H */ + +/* This trace include file is not located in the .../include/trace + * with the kernel tracepoint definitions, because we're a loadable + * module. + */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE i40e_trace +#include <trace/define_trace.h> diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index c91fcf43ccbc..dfe241a12ad0 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -28,6 +28,7 @@ #include <net/busy_poll.h> #include "i40evf.h" +#include "i40e_trace.h" #include "i40e_prototype.h" static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, @@ -137,10 +138,7 @@ u32 i40evf_get_tx_pending(struct i40e_ring *ring, bool in_sw) { u32 head, tail; - if (!in_sw) - head = i40e_get_head(ring); - else - head = ring->next_to_clean; + head = ring->next_to_clean; tail = readl(ring->tail); if (head != tail) @@ -165,7 +163,6 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, { u16 i = tx_ring->next_to_clean; struct i40e_tx_buffer *tx_buf; - struct i40e_tx_desc *tx_head; struct i40e_tx_desc *tx_desc; unsigned int total_bytes = 0, total_packets = 0; unsigned int budget = vsi->work_limit; @@ -174,8 +171,6 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, tx_desc = I40E_TX_DESC(tx_ring, i); i -= tx_ring->count; - tx_head = I40E_TX_DESC(tx_ring, i40e_get_head(tx_ring)); - do { struct i40e_tx_desc *eop_desc = tx_buf->next_to_watch; @@ -186,8 +181,10 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, /* prevent any other reads prior to eop_desc */ read_barrier_depends(); - /* we have caught up to head, no work left to do */ - if (tx_head == tx_desc) + i40e_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf); + /* if the descriptor isn't done, no work yet to do */ + if (!(eop_desc->cmd_type_offset_bsz & + cpu_to_le64(I40E_TX_DESC_DTYPE_DESC_DONE))) break; /* clear next_to_watch to prevent false hangs */ @@ -212,6 +209,8 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, /* unmap remaining buffers */ while (tx_desc != eop_desc) { + i40e_trace(clean_tx_irq_unmap, + tx_ring, tx_desc, tx_buf); tx_buf++; tx_desc++; @@ -267,7 +266,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, if (budget && ((j / WB_STRIDE) == 0) && (j > 0) && - !test_bit(__I40E_DOWN, &vsi->state) && + !test_bit(__I40E_VSI_DOWN, vsi->state) && (I40E_DESC_UNUSED(tx_ring) != tx_ring->count)) tx_ring->arm_wb = true; } @@ -285,7 +284,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, smp_mb(); if (__netif_subqueue_stopped(tx_ring->netdev, tx_ring->queue_index) && - !test_bit(__I40E_DOWN, &vsi->state)) { + !test_bit(__I40E_VSI_DOWN, vsi->state)) { netif_wake_subqueue(tx_ring->netdev, tx_ring->queue_index); ++tx_ring->tx_stats.restart_queue; @@ -464,10 +463,6 @@ int i40evf_setup_tx_descriptors(struct i40e_ring *tx_ring) /* round up to nearest 4K */ tx_ring->size = tx_ring->count * sizeof(struct i40e_tx_desc); - /* add u32 for head writeback, align after this takes care of - * guaranteeing this is at least one cache line in size - */ - tx_ring->size += sizeof(u32); tx_ring->size = ALIGN(tx_ring->size, 4096); tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size, &tx_ring->dma, GFP_KERNEL); @@ -493,7 +488,6 @@ err: **/ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring) { - struct device *dev = rx_ring->dev; unsigned long bi_size; u16 i; @@ -513,8 +507,22 @@ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring) if (!rx_bi->page) continue; - dma_unmap_page(dev, rx_bi->dma, PAGE_SIZE, DMA_FROM_DEVICE); - __free_pages(rx_bi->page, 0); + /* Invalidate cache lines that may have been written to by + * device so that we avoid corrupting memory. + */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_bi->dma, + rx_bi->page_offset, + rx_ring->rx_buf_len, + DMA_FROM_DEVICE); + + /* free resources associated with mapping */ + dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma, + i40e_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + I40E_RX_DMA_ATTR); + + __page_frag_cache_drain(rx_bi->page, rx_bi->pagecnt_bias); rx_bi->page = NULL; rx_bi->page_offset = 0; @@ -615,6 +623,17 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) } /** + * i40e_rx_offset - Return expected offset into page to access data + * @rx_ring: Ring we are requesting offset of + * + * Returns the offset value for ring into the data buffer. + */ +static inline unsigned int i40e_rx_offset(struct i40e_ring *rx_ring) +{ + return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0; +} + +/** * i40e_alloc_mapped_page - recycle or make a new page * @rx_ring: ring to use * @bi: rx_buffer struct to modify @@ -635,27 +654,33 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, } /* alloc new page for storage */ - page = dev_alloc_page(); + page = dev_alloc_pages(i40e_rx_pg_order(rx_ring)); if (unlikely(!page)) { rx_ring->rx_stats.alloc_page_failed++; return false; } /* map page for use */ - dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE); + dma = dma_map_page_attrs(rx_ring->dev, page, 0, + i40e_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + I40E_RX_DMA_ATTR); /* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use */ if (dma_mapping_error(rx_ring->dev, dma)) { - __free_pages(page, 0); + __free_pages(page, i40e_rx_pg_order(rx_ring)); rx_ring->rx_stats.alloc_page_failed++; return false; } bi->dma = dma; bi->page = page; - bi->page_offset = 0; + bi->page_offset = i40e_rx_offset(rx_ring); + + /* initialize pagecnt_bias to 1 representing we fully own page */ + bi->pagecnt_bias = 1; return true; } @@ -702,6 +727,12 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) if (!i40e_alloc_mapped_page(rx_ring, bi)) goto no_buffers; + /* sync the buffer for use by the device */ + dma_sync_single_range_for_device(rx_ring->dev, bi->dma, + bi->page_offset, + rx_ring->rx_buf_len, + DMA_FROM_DEVICE); + /* Refresh the desc even if buffer_addrs didn't change * because each write-back erases this info. */ @@ -742,8 +773,6 @@ no_buffers: * @vsi: the VSI we care about * @skb: skb currently being received and modified * @rx_desc: the receive descriptor - * - * skb->protocol must be set before this function is called **/ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, struct sk_buff *skb, @@ -806,13 +835,6 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT)) return; - /* If there is an outer header present that might contain a checksum - * we need to bump the checksum level by 1 to reflect the fact that - * we are indicating we validated the inner checksum. - */ - if (decoded.tunnel_type >= I40E_RX_PTYPE_TUNNEL_IP_GRENAT) - skb->csum_level = 1; - /* Only report checksum unnecessary for TCP, UDP, or SCTP */ switch (decoded.inner_prot) { case I40E_RX_PTYPE_INNER_PROT_TCP: @@ -895,12 +917,12 @@ void i40evf_process_skb_fields(struct i40e_ring *rx_ring, { i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype); - /* modifies the skb - consumes the enet header */ - skb->protocol = eth_type_trans(skb, rx_ring->netdev); - i40e_rx_checksum(rx_ring->vsi, skb, rx_desc); skb_record_rx_queue(skb, rx_ring->queue_index); + + /* modifies the skb - consumes the enet header */ + skb->protocol = eth_type_trans(skb, rx_ring->netdev); } /** @@ -945,7 +967,10 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring, rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; /* transfer page from old buffer to new buffer */ - *new_buff = *old_buff; + new_buff->dma = old_buff->dma; + new_buff->page = old_buff->page; + new_buff->page_offset = old_buff->page_offset; + new_buff->pagecnt_bias = old_buff->pagecnt_bias; } /** @@ -966,8 +991,6 @@ static inline bool i40e_page_is_reusable(struct page *page) * the adapter for another receive * * @rx_buffer: buffer containing the page - * @page: page address from rx_buffer - * @truesize: actual size of the buffer in this page * * If page is reusable, rx_buffer->page_offset is adjusted to point to * an unused region in the page. @@ -990,13 +1013,10 @@ static inline bool i40e_page_is_reusable(struct page *page) * * In either case, if the page is reusable its refcount is increased. **/ -static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer, - struct page *page, - const unsigned int truesize) +static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) { -#if (PAGE_SIZE >= 8192) - unsigned int last_offset = PAGE_SIZE - I40E_RXBUFFER_2048; -#endif + unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; + struct page *page = rx_buffer->page; /* Is any reuse possible? */ if (unlikely(!i40e_page_is_reusable(page))) @@ -1004,21 +1024,23 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer, #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely(page_count(page) != 1)) + if (unlikely((page_count(page) - pagecnt_bias) > 1)) return false; - - /* flip page offset to other buffer */ - rx_buffer->page_offset ^= truesize; #else - /* move offset up to the next cache line */ - rx_buffer->page_offset += truesize; - - if (rx_buffer->page_offset > last_offset) +#define I40E_LAST_OFFSET \ + (SKB_WITH_OVERHEAD(PAGE_SIZE) - I40E_RXBUFFER_2048) + if (rx_buffer->page_offset > I40E_LAST_OFFSET) return false; #endif - /* Inc ref count on page before passing it up to the stack */ - get_page(page); + /* If we have drained the page fragment pool we need to update + * the pagecnt_bias and page count so that we fully restock the + * number of references the driver holds. + */ + if (unlikely(!pagecnt_bias)) { + page_ref_add(page, USHRT_MAX); + rx_buffer->pagecnt_bias = USHRT_MAX; + } return true; } @@ -1027,145 +1049,201 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer, * i40e_add_rx_frag - Add contents of Rx buffer to sk_buff * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: buffer containing page to add - * @size: packet length from rx_desc * @skb: sk_buff to place the data into + * @size: packet length from rx_desc * * This function will add the data contained in rx_buffer->page to the skb. - * This is done either through a direct copy if the data in the buffer is - * less than the skb header size, otherwise it will just attach the page as - * a frag to the skb. + * It will just attach the page as a frag to the skb. * - * The function will then update the page offset if necessary and return - * true if the buffer can be reused by the adapter. + * The function will then update the page offset. **/ -static bool i40e_add_rx_frag(struct i40e_ring *rx_ring, +static void i40e_add_rx_frag(struct i40e_ring *rx_ring, struct i40e_rx_buffer *rx_buffer, - unsigned int size, - struct sk_buff *skb) + struct sk_buff *skb, + unsigned int size) { - struct page *page = rx_buffer->page; - unsigned char *va = page_address(page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) - unsigned int truesize = I40E_RXBUFFER_2048; + unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; #else - unsigned int truesize = ALIGN(size, L1_CACHE_BYTES); + unsigned int truesize = SKB_DATA_ALIGN(size + i40e_rx_offset(rx_ring)); #endif - unsigned int pull_len; - - if (unlikely(skb_is_nonlinear(skb))) - goto add_tail_frag; - /* will the data fit in the skb we allocated? if so, just - * copy it as it is pretty small anyway - */ - if (size <= I40E_RX_HDR_SIZE) { - memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); - - /* page is reusable, we can reuse buffer as-is */ - if (likely(i40e_page_is_reusable(page))) - return true; + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, + rx_buffer->page_offset, size, truesize); - /* this page cannot be reused so discard it */ - __free_pages(page, 0); - return false; - } + /* page is being used so we must update the page offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif +} - /* we need the header to contain the greater of either - * ETH_HLEN or 60 bytes if the skb->len is less than - * 60 for skb_pad. - */ - pull_len = eth_get_headlen(va, I40E_RX_HDR_SIZE); +/** + * i40e_get_rx_buffer - Fetch Rx buffer and synchronize data for use + * @rx_ring: rx descriptor ring to transact packets on + * @size: size of buffer to add to skb + * + * This function will pull an Rx buffer from the ring and synchronize it + * for use by the CPU. + */ +static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring, + const unsigned int size) +{ + struct i40e_rx_buffer *rx_buffer; - /* align pull length to size of long to optimize - * memcpy performance - */ - memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long))); + rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean]; + prefetchw(rx_buffer->page); - /* update all of the pointers */ - va += pull_len; - size -= pull_len; + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + size, + DMA_FROM_DEVICE); -add_tail_frag: - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, - (unsigned long)va & ~PAGE_MASK, size, truesize); + /* We have pulled a buffer for use, so decrement pagecnt_bias */ + rx_buffer->pagecnt_bias--; - return i40e_can_reuse_rx_page(rx_buffer, page, truesize); + return rx_buffer; } /** - * i40evf_fetch_rx_buffer - Allocate skb and populate it + * i40e_construct_skb - Allocate skb and populate it * @rx_ring: rx descriptor ring to transact packets on - * @rx_desc: descriptor containing info written by hardware + * @rx_buffer: rx buffer to pull data from + * @size: size of buffer to add to skb * - * This function allocates an skb on the fly, and populates it with the page - * data from the current receive descriptor, taking care to set up the skb - * correctly, as well as handling calling the page recycle function if - * necessary. + * This function allocates an skb. It then populates it with the page + * data from the current receive descriptor, taking care to set up the + * skb correctly. */ -static inline -struct sk_buff *i40evf_fetch_rx_buffer(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc, - struct sk_buff *skb) +static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, + struct i40e_rx_buffer *rx_buffer, + unsigned int size) { - u64 local_status_error_len = - le64_to_cpu(rx_desc->wb.qword1.status_error_len); - unsigned int size = - (local_status_error_len & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> - I40E_RXD_QW1_LENGTH_PBUF_SHIFT; - struct i40e_rx_buffer *rx_buffer; - struct page *page; + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(size); +#endif + unsigned int headlen; + struct sk_buff *skb; - rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean]; - page = rx_buffer->page; - prefetchw(page); + /* prefetch first cache line of first page */ + prefetch(va); +#if L1_CACHE_BYTES < 128 + prefetch(va + L1_CACHE_BYTES); +#endif + + /* allocate a skb to store the frags */ + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, + I40E_RX_HDR_SIZE, + GFP_ATOMIC | __GFP_NOWARN); + if (unlikely(!skb)) + return NULL; + + /* Determine available headroom for copy */ + headlen = size; + if (headlen > I40E_RX_HDR_SIZE) + headlen = eth_get_headlen(va, I40E_RX_HDR_SIZE); + + /* align pull length to size of long to optimize memcpy performance */ + memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); + + /* update all of the pointers */ + size -= headlen; + if (size) { + skb_add_rx_frag(skb, 0, rx_buffer->page, + rx_buffer->page_offset + headlen, + size, truesize); + + /* buffer is used by skb, update page_offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif + } else { + /* buffer is unused, reset bias back to rx_buffer */ + rx_buffer->pagecnt_bias++; + } + + return skb; +} - if (likely(!skb)) { - void *page_addr = page_address(page) + rx_buffer->page_offset; +/** + * i40e_build_skb - Build skb around an existing buffer + * @rx_ring: Rx descriptor ring to transact packets on + * @rx_buffer: Rx buffer to pull data from + * @size: size of buffer to add to skb + * + * This function builds an skb around an existing Rx buffer, taking care + * to set up the skb correctly and avoid any memcpy overhead. + */ +static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, + struct i40e_rx_buffer *rx_buffer, + unsigned int size) +{ + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(size); +#endif + struct sk_buff *skb; - /* prefetch first cache line of first page */ - prefetch(page_addr); + /* prefetch first cache line of first page */ + prefetch(va); #if L1_CACHE_BYTES < 128 - prefetch(page_addr + L1_CACHE_BYTES); + prefetch(va + L1_CACHE_BYTES); #endif + /* build an skb around the page buffer */ + skb = build_skb(va - I40E_SKB_PAD, truesize); + if (unlikely(!skb)) + return NULL; - /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, - I40E_RX_HDR_SIZE, - GFP_ATOMIC | __GFP_NOWARN); - if (unlikely(!skb)) { - rx_ring->rx_stats.alloc_buff_failed++; - return NULL; - } + /* update pointers within the skb to store the data */ + skb_reserve(skb, I40E_SKB_PAD); + __skb_put(skb, size); - /* we will be copying header into skb->data in - * pskb_may_pull so it is in our interest to prefetch - * it now to avoid a possible cache miss - */ - prefetchw(skb->data); - } + /* buffer is used by skb, update page_offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, - rx_buffer->dma, - rx_buffer->page_offset, - size, - DMA_FROM_DEVICE); + return skb; +} - /* pull page into skb */ - if (i40e_add_rx_frag(rx_ring, rx_buffer, size, skb)) { +/** + * i40e_put_rx_buffer - Clean up used buffer and either recycle or free + * @rx_ring: rx descriptor ring to transact packets on + * @rx_buffer: rx buffer to pull data from + * + * This function will clean up the contents of the rx_buffer. It will + * either recycle the bufer or unmap it and free the associated resources. + */ +static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, + struct i40e_rx_buffer *rx_buffer) +{ + if (i40e_can_reuse_rx_page(rx_buffer)) { /* hand second half of page back to the ring */ i40e_reuse_rx_page(rx_ring, rx_buffer); rx_ring->rx_stats.page_reuse_count++; } else { /* we are not reusing the buffer so unmap it */ - dma_unmap_page(rx_ring->dev, rx_buffer->dma, PAGE_SIZE, - DMA_FROM_DEVICE); + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + i40e_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); } /* clear contents of buffer_info */ rx_buffer->page = NULL; - - return skb; } /** @@ -1221,7 +1299,9 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) bool failure = false; while (likely(total_rx_packets < budget)) { + struct i40e_rx_buffer *rx_buffer; union i40e_rx_desc *rx_desc; + unsigned int size; u16 vlan_tag; u8 rx_ptype; u64 qword; @@ -1238,22 +1318,40 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) /* status_error_len will always be zero for unused descriptors * because it's cleared in cleanup, and overlaps with hdr_addr * which is always zero because packet split isn't used, if the - * hardware wrote DD then it will be non-zero + * hardware wrote DD then the length will be non-zero */ - if (!i40e_test_staterr(rx_desc, - BIT(I40E_RX_DESC_STATUS_DD_SHIFT))) - break; + qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); /* This memory barrier is needed to keep us from reading - * any other fields out of the rx_desc until we know the - * DD bit is set. + * any other fields out of the rx_desc until we have + * verified the descriptor has been written back. */ dma_rmb(); - skb = i40evf_fetch_rx_buffer(rx_ring, rx_desc, skb); - if (!skb) + size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> + I40E_RXD_QW1_LENGTH_PBUF_SHIFT; + if (!size) break; + i40e_trace(clean_rx_irq, rx_ring, rx_desc, skb); + rx_buffer = i40e_get_rx_buffer(rx_ring, size); + + /* retrieve a buffer from the ring */ + if (skb) + i40e_add_rx_frag(rx_ring, rx_buffer, skb, size); + else if (ring_uses_build_skb(rx_ring)) + skb = i40e_build_skb(rx_ring, rx_buffer, size); + else + skb = i40e_construct_skb(rx_ring, rx_buffer, size); + + /* exit if we failed to retrieve a buffer */ + if (!skb) { + rx_ring->rx_stats.alloc_buff_failed++; + rx_buffer->pagecnt_bias++; + break; + } + + i40e_put_rx_buffer(rx_ring, rx_buffer); cleaned_count++; if (i40e_is_non_eop(rx_ring, rx_desc, skb)) @@ -1266,6 +1364,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) */ if (unlikely(i40e_test_staterr(rx_desc, BIT(I40E_RXD_QW1_ERROR_SHIFT)))) { dev_kfree_skb_any(skb); + skb = NULL; continue; } @@ -1288,6 +1387,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ? le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0; + i40e_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb); i40e_receive_skb(rx_ring, skb, vlan_tag); skb = NULL; @@ -1408,7 +1508,7 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, } enable_int: - if (!test_bit(__I40E_DOWN, &vsi->state)) + if (!test_bit(__I40E_VSI_DOWN, vsi->state)) wr32(hw, INTREG(vector - 1), txval); if (q_vector->itr_countdown) @@ -1437,7 +1537,7 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) int budget_per_ring; int work_done = 0; - if (test_bit(__I40E_DOWN, &vsi->state)) { + if (test_bit(__I40E_VSI_DOWN, vsi->state)) { napi_complete(napi); return 0; } @@ -1980,7 +2080,6 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, u16 i = tx_ring->next_to_use; u32 td_tag = 0; dma_addr_t dma; - u16 desc_count = 1; if (tx_flags & I40E_TX_FLAGS_HW_VLAN) { td_cmd |= I40E_TX_DESC_CMD_IL2TAG1; @@ -2016,7 +2115,6 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_desc++; i++; - desc_count++; if (i == tx_ring->count) { tx_desc = I40E_TX_DESC(tx_ring, 0); @@ -2038,7 +2136,6 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_desc++; i++; - desc_count++; if (i == tx_ring->count) { tx_desc = I40E_TX_DESC(tx_ring, 0); @@ -2064,46 +2161,8 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, i40e_maybe_stop_tx(tx_ring, DESC_NEEDED); - /* write last descriptor with EOP bit */ - td_cmd |= I40E_TX_DESC_CMD_EOP; - - /* We can OR these values together as they both are checked against - * 4 below and at this point desc_count will be used as a boolean value - * after this if/else block. - */ - desc_count |= ++tx_ring->packet_stride; - - /* Algorithm to optimize tail and RS bit setting: - * if queue is stopped - * mark RS bit - * reset packet counter - * else if xmit_more is supported and is true - * advance packet counter to 4 - * reset desc_count to 0 - * - * if desc_count >= 4 - * mark RS bit - * reset packet counter - * if desc_count > 0 - * update tail - * - * Note: If there are less than 4 descriptors - * pending and interrupts were disabled the service task will - * trigger a force WB. - */ - if (netif_xmit_stopped(txring_txq(tx_ring))) { - goto do_rs; - } else if (skb->xmit_more) { - /* set stride to arm on next packet and reset desc_count */ - tx_ring->packet_stride = WB_STRIDE; - desc_count = 0; - } else if (desc_count >= WB_STRIDE) { -do_rs: - /* write last descriptor with RS bit set */ - td_cmd |= I40E_TX_DESC_CMD_RS; - tx_ring->packet_stride = 0; - } - + /* write last descriptor with RS and EOP bits */ + td_cmd |= I40E_TXD_CMD; tx_desc->cmd_type_offset_bsz = build_ctob(td_cmd, td_offset, size, td_tag); @@ -2119,7 +2178,7 @@ do_rs: first->next_to_watch = tx_desc; /* notify HW of packet */ - if (desc_count) { + if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { writel(i, tx_ring->tail); /* we need this if more than one processor can write to our tail @@ -2170,6 +2229,8 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, /* prefetch the data, we'll need it later */ prefetch(skb->data); + i40e_trace(xmit_frame_ring, skb, tx_ring); + count = i40e_xmit_descriptor_count(skb); if (i40e_chk_linearize(skb, count)) { if (__skb_linearize(skb)) { @@ -2237,6 +2298,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, return NETDEV_TX_OK; out_drop: + i40e_trace(xmit_frame_ring_drop, first->skb, tx_ring); dev_kfree_skb_any(first->skb); first->skb = NULL; return NETDEV_TX_OK; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index 8274ba68bd32..901282c87cf6 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -104,10 +104,9 @@ enum i40e_dyn_idx_t { /* Supported Rx Buffer Sizes (a multiple of 128) */ #define I40E_RXBUFFER_256 256 +#define I40E_RXBUFFER_1536 1536 /* 128B aligned standard Ethernet frame */ #define I40E_RXBUFFER_2048 2048 -#define I40E_RXBUFFER_3072 3072 /* For FCoE MTU of 2158 */ -#define I40E_RXBUFFER_4096 4096 -#define I40E_RXBUFFER_8192 8192 +#define I40E_RXBUFFER_3072 3072 /* Used for large frames w/ padding */ #define I40E_MAX_RXBUFFER 9728 /* largest size for single descriptor */ /* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we @@ -120,6 +119,61 @@ enum i40e_dyn_idx_t { #define I40E_RX_HDR_SIZE I40E_RXBUFFER_256 #define i40e_rx_desc i40e_32byte_rx_desc +#define I40E_RX_DMA_ATTR \ + (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) + +/* Attempt to maximize the headroom available for incoming frames. We + * use a 2K buffer for receives and need 1536/1534 to store the data for + * the frame. This leaves us with 512 bytes of room. From that we need + * to deduct the space needed for the shared info and the padding needed + * to IP align the frame. + * + * Note: For cache line sizes 256 or larger this value is going to end + * up negative. In these cases we should fall back to the legacy + * receive path. + */ +#if (PAGE_SIZE < 8192) +#define I40E_2K_TOO_SMALL_WITH_PADDING \ +((NET_SKB_PAD + I40E_RXBUFFER_1536) > SKB_WITH_OVERHEAD(I40E_RXBUFFER_2048)) + +static inline int i40e_compute_pad(int rx_buf_len) +{ + int page_size, pad_size; + + page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2); + pad_size = SKB_WITH_OVERHEAD(page_size) - rx_buf_len; + + return pad_size; +} + +static inline int i40e_skb_pad(void) +{ + int rx_buf_len; + + /* If a 2K buffer cannot handle a standard Ethernet frame then + * optimize padding for a 3K buffer instead of a 1.5K buffer. + * + * For a 3K buffer we need to add enough padding to allow for + * tailroom due to NET_IP_ALIGN possibly shifting us out of + * cache-line alignment. + */ + if (I40E_2K_TOO_SMALL_WITH_PADDING) + rx_buf_len = I40E_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN); + else + rx_buf_len = I40E_RXBUFFER_1536; + + /* if needed make room for NET_IP_ALIGN */ + rx_buf_len -= NET_IP_ALIGN; + + return i40e_compute_pad(rx_buf_len); +} + +#define I40E_SKB_PAD i40e_skb_pad() +#else +#define I40E_2K_TOO_SMALL_WITH_PADDING false +#define I40E_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +#endif + /** * i40e_test_staterr - tests bits in Rx descriptor status and error fields * @rx_desc: pointer to receive descriptor (in le64 format) @@ -241,7 +295,12 @@ struct i40e_tx_buffer { struct i40e_rx_buffer { dma_addr_t dma; struct page *page; - unsigned int page_offset; +#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) + __u32 page_offset; +#else + __u16 page_offset; +#endif + __u16 pagecnt_bias; }; struct i40e_queue_stats { @@ -321,7 +380,8 @@ struct i40e_ring { u8 packet_stride; u16 flags; -#define I40E_TXR_FLAGS_WB_ON_ITR BIT(0) +#define I40E_TXR_FLAGS_WB_ON_ITR BIT(0) +#define I40E_RXR_FLAGS_BUILD_SKB_ENABLED BIT(1) /* stats structs */ struct i40e_queue_stats stats; @@ -349,6 +409,21 @@ struct i40e_ring { */ } ____cacheline_internodealigned_in_smp; +static inline bool ring_uses_build_skb(struct i40e_ring *ring) +{ + return !!(ring->flags & I40E_RXR_FLAGS_BUILD_SKB_ENABLED); +} + +static inline void set_ring_build_skb_enabled(struct i40e_ring *ring) +{ + ring->flags |= I40E_RXR_FLAGS_BUILD_SKB_ENABLED; +} + +static inline void clear_ring_build_skb_enabled(struct i40e_ring *ring) +{ + ring->flags &= ~I40E_RXR_FLAGS_BUILD_SKB_ENABLED; +} + enum i40e_latency_range { I40E_LOWEST_LATENCY = 0, I40E_LOW_LATENCY = 1, @@ -370,6 +445,17 @@ struct i40e_ring_container { #define i40e_for_each_ring(pos, head) \ for (pos = (head).ring; pos != NULL; pos = pos->next) +static inline unsigned int i40e_rx_pg_order(struct i40e_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring->rx_buf_len > (PAGE_SIZE / 2)) + return 1; +#endif + return 0; +} + +#define i40e_rx_pg_size(_ring) (PAGE_SIZE << i40e_rx_pg_order(_ring)) + bool i40evf_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count); netdev_tx_t i40evf_xmit_frame(struct sk_buff *skb, struct net_device *netdev); void i40evf_clean_tx_ring(struct i40e_ring *tx_ring); @@ -385,20 +471,6 @@ int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size); bool __i40evf_chk_linearize(struct sk_buff *skb); /** - * i40e_get_head - Retrieve head from head writeback - * @tx_ring: Tx ring to fetch head of - * - * Returns value of Tx ring head based on value stored - * in head write-back location - **/ -static inline u32 i40e_get_head(struct i40e_ring *tx_ring) -{ - void *head = (struct i40e_tx_desc *)tx_ring->desc + tx_ring->count; - - return le32_to_cpu(*(volatile __le32 *)head); -} - -/** * i40e_xmit_descriptor_count - calculate number of Tx descriptors needed * @skb: send buffer * @tx_ring: ring to send buffer on @@ -460,19 +532,7 @@ static inline bool i40e_chk_linearize(struct sk_buff *skb, int count) /* we can support up to 8 data buffers for a single send */ return count != I40E_MAX_BUFFER_TXD; } - -/** - * i40e_rx_is_fcoe - returns true if the Rx packet type is FCoE - * @ptype: the packet type field from Rx descriptor write-back - **/ -static inline bool i40e_rx_is_fcoe(u16 ptype) -{ - return (ptype >= I40E_RX_PTYPE_L2_FCOE_PAY3) && - (ptype <= I40E_RX_PTYPE_L2_FCOE_VFT_FCOTHER); -} - /** - * txring_txq - Find the netdev Tx ring based on the i40e Tx ring * @ring: Tx ring to find the netdev equivalent of **/ static inline struct netdev_queue *txring_txq(const struct i40e_ring *ring) diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h index 16bb88084bb9..bde7f24af1c6 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h @@ -78,6 +78,7 @@ enum i40e_debug_mask { I40E_DEBUG_DCB = 0x00000400, I40E_DEBUG_DIAG = 0x00000800, I40E_DEBUG_FD = 0x00001000, + I40E_DEBUG_PACKAGE = 0x00002000, I40E_DEBUG_AQ_MESSAGE = 0x01000000, I40E_DEBUG_AQ_DESCRIPTOR = 0x02000000, @@ -1396,4 +1397,83 @@ enum i40e_reset_type { #define I40E_FD_INSET_FLEX_WORD57_SHIFT 10 #define I40E_FD_INSET_FLEX_WORD57_MASK (0x1ULL << \ I40E_FD_INSET_FLEX_WORD57_SHIFT) + +/* Version format for PPP */ +struct i40e_ppp_version { + u8 major; + u8 minor; + u8 update; + u8 draft; +}; + +#define I40E_PPP_NAME_SIZE 32 + +/* Package header */ +struct i40e_package_header { + struct i40e_ppp_version version; + u32 segment_count; + u32 segment_offset[1]; +}; + +/* Generic segment header */ +struct i40e_generic_seg_header { +#define SEGMENT_TYPE_METADATA 0x00000001 +#define SEGMENT_TYPE_NOTES 0x00000002 +#define SEGMENT_TYPE_I40E 0x00000011 +#define SEGMENT_TYPE_X722 0x00000012 + u32 type; + struct i40e_ppp_version version; + u32 size; + char name[I40E_PPP_NAME_SIZE]; +}; + +struct i40e_metadata_segment { + struct i40e_generic_seg_header header; + struct i40e_ppp_version version; + u32 track_id; + char name[I40E_PPP_NAME_SIZE]; +}; + +struct i40e_device_id_entry { + u32 vendor_dev_id; + u32 sub_vendor_dev_id; +}; + +struct i40e_profile_segment { + struct i40e_generic_seg_header header; + struct i40e_ppp_version version; + char name[I40E_PPP_NAME_SIZE]; + u32 device_table_count; + struct i40e_device_id_entry device_table[1]; +}; + +struct i40e_section_table { + u32 section_count; + u32 section_offset[1]; +}; + +struct i40e_profile_section_header { + u16 tbl_size; + u16 data_end; + struct { +#define SECTION_TYPE_INFO 0x00000010 +#define SECTION_TYPE_MMIO 0x00000800 +#define SECTION_TYPE_AQ 0x00000801 +#define SECTION_TYPE_NOTE 0x80000000 +#define SECTION_TYPE_NAME 0x80000001 + u32 type; + u32 offset; + u32 size; + } section; +}; + +struct i40e_profile_info { + u32 track_id; + struct i40e_ppp_version version; + u8 op; +#define I40E_PPP_ADD_TRACKID 0x01 +#define I40E_PPP_REMOVE_TRACKID 0x02 + u8 reserved[7]; + u8 name[I40E_PPP_NAME_SIZE]; +}; #endif /* _I40E_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h index d38a2b2aea2b..c5ad0388c3d5 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h @@ -81,7 +81,9 @@ enum i40e_virtchnl_ops { I40E_VIRTCHNL_OP_GET_STATS = 15, I40E_VIRTCHNL_OP_FCOE = 16, I40E_VIRTCHNL_OP_EVENT = 17, /* must ALWAYS be 17 */ + I40E_VIRTCHNL_OP_IWARP = 20, I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP = 21, + I40E_VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP = 22, I40E_VIRTCHNL_OP_CONFIG_RSS_KEY = 23, I40E_VIRTCHNL_OP_CONFIG_RSS_LUT = 24, I40E_VIRTCHNL_OP_GET_RSS_HENA_CAPS = 25, @@ -161,7 +163,8 @@ struct i40e_virtchnl_vsi_resource { #define I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING 0x00020000 #define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 0x00040000 #define I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF 0X00080000 -#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00100000 +#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP 0X00100000 +#define I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00200000 #define I40E_VF_BASE_MODE_OFFLOADS (I40E_VIRTCHNL_VF_OFFLOAD_L2 | \ I40E_VIRTCHNL_VF_OFFLOAD_VLAN | \ @@ -393,6 +396,37 @@ struct i40e_virtchnl_pf_event { int severity; }; +/* I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP + * VF uses this message to request PF to map IWARP vectors to IWARP queues. + * The request for this originates from the VF IWARP driver through + * a client interface between VF LAN and VF IWARP driver. + * A vector could have an AEQ and CEQ attached to it although + * there is a single AEQ per VF IWARP instance in which case + * most vectors will have an INVALID_IDX for aeq and valid idx for ceq. + * There will never be a case where there will be multiple CEQs attached + * to a single vector. + * PF configures interrupt mapping and returns status. + */ + +/* HW does not define a type value for AEQ; only for RX/TX and CEQ. + * In order for us to keep the interface simple, SW will define a + * unique type value for AEQ. + */ +#define I40E_QUEUE_TYPE_PE_AEQ 0x80 +#define I40E_QUEUE_INVALID_IDX 0xFFFF + +struct i40e_virtchnl_iwarp_qv_info { + u32 v_idx; /* msix_vector */ + u16 ceq_idx; + u16 aeq_idx; + u8 itr_idx; +}; + +struct i40e_virtchnl_iwarp_qvlist_info { + u32 num_vectors; + struct i40e_virtchnl_iwarp_qv_info qv_info[1]; +}; + /* VF reset states - these are written into the RSTAT register: * I40E_VFGEN_RSTAT1 on the PF * I40E_VFGEN_RSTAT on the VF diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index 00c42d803276..b8ada6d8d890 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -49,6 +49,13 @@ #define DEFAULT_DEBUG_LEVEL_SHIFT 3 #define PFX "i40evf: " +/* VSI state flags shared with common code */ +enum i40evf_vsi_state_t { + __I40E_VSI_DOWN, + /* This must be last as it determines the size of the BITMAP */ + __I40E_VSI_STATE_SIZE__, +}; + /* dummy struct to make common code less painful */ struct i40e_vsi { struct i40evf_adapter *back; @@ -56,10 +63,11 @@ struct i40e_vsi { unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; u16 seid; u16 id; - unsigned long state; + DECLARE_BITMAP(state, __I40E_VSI_STATE_SIZE__); int base_vector; u16 work_limit; u16 qs_handle; + void *priv; /* client driver data reference. */ }; /* How many Rx Buffers do we bundle into one write to the hardware ? */ @@ -71,10 +79,6 @@ struct i40e_vsi { #define I40EVF_MAX_RXD 4096 #define I40EVF_MIN_RXD 64 #define I40EVF_REQ_DESCRIPTOR_MULTIPLE 32 - -/* Supported Rx Buffer Sizes */ -#define I40EVF_RXBUFFER_2048 2048 -#define I40EVF_MAX_RXBUFFER 16384 /* largest size for single descriptor */ #define I40EVF_MAX_AQ_BUF_SIZE 4096 #define I40EVF_AQ_LEN 32 #define I40EVF_AQ_MAX_ERR 20 /* times to try before resetting AQ */ @@ -169,15 +173,15 @@ enum i40evf_state_t { enum i40evf_critical_section_t { __I40EVF_IN_CRITICAL_TASK, /* cannot be interrupted */ + __I40EVF_IN_CLIENT_TASK, }; -/* make common code happy */ -#define __I40E_DOWN __I40EVF_DOWN /* board specific private data structure */ struct i40evf_adapter { struct timer_list watchdog_timer; struct work_struct reset_task; struct work_struct adminq_task; + struct delayed_work client_task; struct delayed_work init_task; struct i40e_q_vector *q_vectors; struct list_head vlan_filter_list; @@ -195,15 +199,16 @@ struct i40evf_adapter { u64 hw_csum_rx_error; u32 rx_desc_count; int num_msix_vectors; + int num_iwarp_msix; + int iwarp_base_vector; u32 client_pending; + struct i40e_client_instance *cinst; struct msix_entry *msix_entries; u32 flags; #define I40EVF_FLAG_RX_CSUM_ENABLED BIT(0) -#define I40EVF_FLAG_IN_NETPOLL BIT(4) #define I40EVF_FLAG_IMIR_ENABLED BIT(5) #define I40EVF_FLAG_MQ_CAPABLE BIT(6) -#define I40EVF_FLAG_NEED_LINK_UPDATE BIT(7) #define I40EVF_FLAG_PF_COMMS_FAILED BIT(8) #define I40EVF_FLAG_RESET_PENDING BIT(9) #define I40EVF_FLAG_RESET_NEEDED BIT(10) @@ -211,15 +216,18 @@ struct i40evf_adapter { #define I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE BIT(12) #define I40EVF_FLAG_ADDR_SET_BY_PF BIT(13) #define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(14) -#define I40EVF_FLAG_PROMISC_ON BIT(15) -#define I40EVF_FLAG_ALLMULTI_ON BIT(16) +#define I40EVF_FLAG_CLIENT_NEEDS_OPEN BIT(15) +#define I40EVF_FLAG_CLIENT_NEEDS_CLOSE BIT(16) +#define I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS BIT(17) +#define I40EVF_FLAG_PROMISC_ON BIT(18) +#define I40EVF_FLAG_ALLMULTI_ON BIT(19) +#define I40EVF_FLAG_LEGACY_RX BIT(20) /* duplicates for common code */ -#define I40E_FLAG_FDIR_ATR_ENABLED 0 #define I40E_FLAG_DCB_ENABLED 0 -#define I40E_FLAG_IN_NETPOLL I40EVF_FLAG_IN_NETPOLL #define I40E_FLAG_RX_CSUM_ENABLED I40EVF_FLAG_RX_CSUM_ENABLED #define I40E_FLAG_WB_ON_ITR_CAPABLE I40EVF_FLAG_WB_ON_ITR_CAPABLE #define I40E_FLAG_OUTER_UDP_CSUM_CAPABLE I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE +#define I40E_FLAG_LEGACY_RX I40EVF_FLAG_LEGACY_RX /* flags for admin queue service task */ u32 aq_required; #define I40EVF_FLAG_AQ_ENABLE_QUEUES BIT(0) @@ -246,7 +254,6 @@ struct i40evf_adapter { /* OS defined structs */ struct net_device *netdev; struct pci_dev *pdev; - struct net_device_stats net_stats; struct i40e_hw hw; /* defined in i40e_type.h */ @@ -258,10 +265,11 @@ struct i40evf_adapter { bool link_up; enum i40e_aq_link_speed link_speed; enum i40e_virtchnl_ops current_op; -#define CLIENT_ENABLED(_a) ((_a)->vf_res ? \ +#define CLIENT_ALLOWED(_a) ((_a)->vf_res ? \ (_a)->vf_res->vf_offload_flags & \ I40E_VIRTCHNL_VF_OFFLOAD_IWARP : \ 0) +#define CLIENT_ENABLED(_a) ((_a)->cinst) /* RSS by the PF should be preferred over RSS via other methods. */ #define RSS_PF(_a) ((_a)->vf_res->vf_offload_flags & \ I40E_VIRTCHNL_VF_OFFLOAD_RSS_PF) @@ -292,6 +300,12 @@ struct i40evf_adapter { /* Ethtool Private Flags */ +/* lan device */ +struct i40e_device { + struct list_head list; + struct i40evf_adapter *vf; +}; + /* needed by i40evf_ethtool.c */ extern char i40evf_driver_name[]; extern const char i40evf_driver_version[]; @@ -337,4 +351,11 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, enum i40e_virtchnl_ops v_opcode, i40e_status v_retval, u8 *msg, u16 msglen); int i40evf_config_rss(struct i40evf_adapter *adapter); +int i40evf_lan_add_device(struct i40evf_adapter *adapter); +int i40evf_lan_del_device(struct i40evf_adapter *adapter); +void i40evf_client_subtask(struct i40evf_adapter *adapter); +void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len); +void i40evf_notify_client_l2_params(struct i40e_vsi *vsi); +void i40evf_notify_client_open(struct i40e_vsi *vsi); +void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset); #endif /* _I40EVF_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_client.c b/drivers/net/ethernet/intel/i40evf/i40evf_client.c new file mode 100644 index 000000000000..ee737680a0e9 --- /dev/null +++ b/drivers/net/ethernet/intel/i40evf/i40evf_client.c @@ -0,0 +1,564 @@ +#include <linux/list.h> +#include <linux/errno.h> + +#include "i40evf.h" +#include "i40e_prototype.h" +#include "i40evf_client.h" + +static +const char i40evf_client_interface_version_str[] = I40EVF_CLIENT_VERSION_STR; +static struct i40e_client *vf_registered_client; +static LIST_HEAD(i40evf_devices); +static DEFINE_MUTEX(i40evf_device_mutex); + +static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev, + struct i40e_client *client, + u8 *msg, u16 len); + +static int i40evf_client_setup_qvlist(struct i40e_info *ldev, + struct i40e_client *client, + struct i40e_qvlist_info *qvlist_info); + +static struct i40e_ops i40evf_lan_ops = { + .virtchnl_send = i40evf_client_virtchnl_send, + .setup_qvlist = i40evf_client_setup_qvlist, +}; + +/** + * i40evf_notify_client_message - call the client message receive callback + * @vsi: the VSI associated with this client + * @msg: message buffer + * @len: length of message + * + * If there is a client to this VSI, call the client + **/ +void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len) +{ + struct i40e_client_instance *cinst; + + if (!vsi) + return; + + cinst = vsi->back->cinst; + if (!cinst || !cinst->client || !cinst->client->ops || + !cinst->client->ops->virtchnl_receive) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance virtchnl_receive function\n"); + return; + } + cinst->client->ops->virtchnl_receive(&cinst->lan_info, cinst->client, + msg, len); +} + +/** + * i40evf_notify_client_l2_params - call the client notify callback + * @vsi: the VSI with l2 param changes + * + * If there is a client to this VSI, call the client + **/ +void i40evf_notify_client_l2_params(struct i40e_vsi *vsi) +{ + struct i40e_client_instance *cinst; + struct i40e_params params; + + if (!vsi) + return; + + cinst = vsi->back->cinst; + memset(¶ms, 0, sizeof(params)); + params.mtu = vsi->netdev->mtu; + params.link_up = vsi->back->link_up; + params.qos.prio_qos[0].qs_handle = vsi->qs_handle; + + if (!cinst || !cinst->client || !cinst->client->ops || + !cinst->client->ops->l2_param_change) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance l2_param_change function\n"); + return; + } + cinst->client->ops->l2_param_change(&cinst->lan_info, cinst->client, + ¶ms); +} + +/** + * i40evf_notify_client_open - call the client open callback + * @vsi: the VSI with netdev opened + * + * If there is a client to this netdev, call the client with open + **/ +void i40evf_notify_client_open(struct i40e_vsi *vsi) +{ + struct i40evf_adapter *adapter = vsi->back; + struct i40e_client_instance *cinst = adapter->cinst; + int ret; + + if (!cinst || !cinst->client || !cinst->client->ops || + !cinst->client->ops->open) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance open function\n"); + return; + } + if (!(test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state))) { + ret = cinst->client->ops->open(&cinst->lan_info, cinst->client); + if (!ret) + set_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state); + } +} + +/** + * i40evf_client_release_qvlist - send a message to the PF to release iwarp qv map + * @ldev: pointer to L2 context. + * + * Return 0 on success or < 0 on error + **/ +static int i40evf_client_release_qvlist(struct i40e_info *ldev) +{ + struct i40evf_adapter *adapter = ldev->vf; + i40e_status err; + + if (adapter->aq_required) + return -EAGAIN; + + err = i40e_aq_send_msg_to_pf(&adapter->hw, + I40E_VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP, + I40E_SUCCESS, NULL, 0, NULL); + + if (err) + dev_err(&adapter->pdev->dev, + "Unable to send iWarp vector release message to PF, error %d, aq status %d\n", + err, adapter->hw.aq.asq_last_status); + + return err; +} + +/** + * i40evf_notify_client_close - call the client close callback + * @vsi: the VSI with netdev closed + * @reset: true when close called due to reset pending + * + * If there is a client to this netdev, call the client with close + **/ +void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset) +{ + struct i40evf_adapter *adapter = vsi->back; + struct i40e_client_instance *cinst = adapter->cinst; + + if (!cinst || !cinst->client || !cinst->client->ops || + !cinst->client->ops->close) { + dev_dbg(&vsi->back->pdev->dev, + "Cannot locate client instance close function\n"); + return; + } + cinst->client->ops->close(&cinst->lan_info, cinst->client, reset); + i40evf_client_release_qvlist(&cinst->lan_info); + clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state); +} + +/** + * i40evf_client_add_instance - add a client instance to the instance list + * @adapter: pointer to the board struct + * @client: pointer to a client struct in the client list. + * + * Returns cinst ptr on success, NULL on failure + **/ +static struct i40e_client_instance * +i40evf_client_add_instance(struct i40evf_adapter *adapter) +{ + struct i40e_client_instance *cinst = NULL; + struct netdev_hw_addr *mac = NULL; + struct i40e_vsi *vsi = &adapter->vsi; + int i; + + if (!vf_registered_client) + goto out; + + if (adapter->cinst) { + cinst = adapter->cinst; + goto out; + } + + cinst = kzalloc(sizeof(*cinst), GFP_KERNEL); + if (!cinst) + goto out; + + cinst->lan_info.vf = (void *)adapter; + cinst->lan_info.netdev = vsi->netdev; + cinst->lan_info.pcidev = adapter->pdev; + cinst->lan_info.fid = 0; + cinst->lan_info.ftype = I40E_CLIENT_FTYPE_VF; + cinst->lan_info.hw_addr = adapter->hw.hw_addr; + cinst->lan_info.ops = &i40evf_lan_ops; + cinst->lan_info.version.major = I40EVF_CLIENT_VERSION_MAJOR; + cinst->lan_info.version.minor = I40EVF_CLIENT_VERSION_MINOR; + cinst->lan_info.version.build = I40EVF_CLIENT_VERSION_BUILD; + set_bit(__I40E_CLIENT_INSTANCE_NONE, &cinst->state); + + cinst->lan_info.msix_count = adapter->num_iwarp_msix; + cinst->lan_info.msix_entries = + &adapter->msix_entries[adapter->iwarp_base_vector]; + + for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) { + cinst->lan_info.params.qos.prio_qos[i].tc = 0; + cinst->lan_info.params.qos.prio_qos[i].qs_handle = + vsi->qs_handle; + } + + mac = list_first_entry(&cinst->lan_info.netdev->dev_addrs.list, + struct netdev_hw_addr, list); + if (mac) + ether_addr_copy(cinst->lan_info.lanmac, mac->addr); + else + dev_err(&adapter->pdev->dev, "MAC address list is empty!\n"); + + cinst->client = vf_registered_client; + adapter->cinst = cinst; +out: + return cinst; +} + +/** + * i40evf_client_del_instance - removes a client instance from the list + * @adapter: pointer to the board struct + * @client: pointer to the client struct + * + **/ +static +void i40evf_client_del_instance(struct i40evf_adapter *adapter) +{ + kfree(adapter->cinst); + adapter->cinst = NULL; +} + +/** + * i40evf_client_subtask - client maintenance work + * @adapter: board private structure + **/ +void i40evf_client_subtask(struct i40evf_adapter *adapter) +{ + struct i40e_client *client = vf_registered_client; + struct i40e_client_instance *cinst; + int ret = 0; + + if (adapter->state < __I40EVF_DOWN) + return; + + /* first check client is registered */ + if (!client) + return; + + /* Add the client instance to the instance list */ + cinst = i40evf_client_add_instance(adapter); + if (!cinst) + return; + + dev_info(&adapter->pdev->dev, "Added instance of Client %s\n", + client->name); + + if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state)) { + /* Send an Open request to the client */ + + if (client->ops && client->ops->open) + ret = client->ops->open(&cinst->lan_info, client); + if (!ret) + set_bit(__I40E_CLIENT_INSTANCE_OPENED, + &cinst->state); + else + /* remove client instance */ + i40evf_client_del_instance(adapter); + } +} + +/** + * i40evf_lan_add_device - add a lan device struct to the list of lan devices + * @adapter: pointer to the board struct + * + * Returns 0 on success or none 0 on error + **/ +int i40evf_lan_add_device(struct i40evf_adapter *adapter) +{ + struct i40e_device *ldev; + int ret = 0; + + mutex_lock(&i40evf_device_mutex); + list_for_each_entry(ldev, &i40evf_devices, list) { + if (ldev->vf == adapter) { + ret = -EEXIST; + goto out; + } + } + ldev = kzalloc(sizeof(*ldev), GFP_KERNEL); + if (!ldev) { + ret = -ENOMEM; + goto out; + } + ldev->vf = adapter; + INIT_LIST_HEAD(&ldev->list); + list_add(&ldev->list, &i40evf_devices); + dev_info(&adapter->pdev->dev, "Added LAN device bus=0x%02x dev=0x%02x func=0x%02x\n", + adapter->hw.bus.bus_id, adapter->hw.bus.device, + adapter->hw.bus.func); + + /* Since in some cases register may have happened before a device gets + * added, we can schedule a subtask to go initiate the clients. + */ + adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; + +out: + mutex_unlock(&i40evf_device_mutex); + return ret; +} + +/** + * i40evf_lan_del_device - removes a lan device from the device list + * @adapter: pointer to the board struct + * + * Returns 0 on success or non-0 on error + **/ +int i40evf_lan_del_device(struct i40evf_adapter *adapter) +{ + struct i40e_device *ldev, *tmp; + int ret = -ENODEV; + + mutex_lock(&i40evf_device_mutex); + list_for_each_entry_safe(ldev, tmp, &i40evf_devices, list) { + if (ldev->vf == adapter) { + dev_info(&adapter->pdev->dev, + "Deleted LAN device bus=0x%02x dev=0x%02x func=0x%02x\n", + adapter->hw.bus.bus_id, adapter->hw.bus.device, + adapter->hw.bus.func); + list_del(&ldev->list); + kfree(ldev); + ret = 0; + break; + } + } + + mutex_unlock(&i40evf_device_mutex); + return ret; +} + +/** + * i40evf_client_release - release client specific resources + * @client: pointer to the registered client + * + **/ +static void i40evf_client_release(struct i40e_client *client) +{ + struct i40e_client_instance *cinst; + struct i40e_device *ldev; + struct i40evf_adapter *adapter; + + mutex_lock(&i40evf_device_mutex); + list_for_each_entry(ldev, &i40evf_devices, list) { + adapter = ldev->vf; + cinst = adapter->cinst; + if (!cinst) + continue; + if (test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state)) { + if (client->ops && client->ops->close) + client->ops->close(&cinst->lan_info, client, + false); + i40evf_client_release_qvlist(&cinst->lan_info); + clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state); + + dev_warn(&adapter->pdev->dev, + "Client %s instance closed\n", client->name); + } + /* delete the client instance */ + i40evf_client_del_instance(adapter); + dev_info(&adapter->pdev->dev, "Deleted client instance of Client %s\n", + client->name); + } + mutex_unlock(&i40evf_device_mutex); +} + +/** + * i40evf_client_prepare - prepare client specific resources + * @client: pointer to the registered client + * + **/ +static void i40evf_client_prepare(struct i40e_client *client) +{ + struct i40e_device *ldev; + struct i40evf_adapter *adapter; + + mutex_lock(&i40evf_device_mutex); + list_for_each_entry(ldev, &i40evf_devices, list) { + adapter = ldev->vf; + /* Signal the watchdog to service the client */ + adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; + } + mutex_unlock(&i40evf_device_mutex); +} + +/** + * i40evf_client_virtchnl_send - send a message to the PF instance + * @ldev: pointer to L2 context. + * @client: Client pointer. + * @msg: pointer to message buffer + * @len: message length + * + * Return 0 on success or < 0 on error + **/ +static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev, + struct i40e_client *client, + u8 *msg, u16 len) +{ + struct i40evf_adapter *adapter = ldev->vf; + i40e_status err; + + if (adapter->aq_required) + return -EAGAIN; + + err = i40e_aq_send_msg_to_pf(&adapter->hw, I40E_VIRTCHNL_OP_IWARP, + I40E_SUCCESS, msg, len, NULL); + if (err) + dev_err(&adapter->pdev->dev, "Unable to send iWarp message to PF, error %d, aq status %d\n", + err, adapter->hw.aq.asq_last_status); + + return err; +} + +/** + * i40evf_client_setup_qvlist - send a message to the PF to setup iwarp qv map + * @ldev: pointer to L2 context. + * @client: Client pointer. + * @qv_info: queue and vector list + * + * Return 0 on success or < 0 on error + **/ +static int i40evf_client_setup_qvlist(struct i40e_info *ldev, + struct i40e_client *client, + struct i40e_qvlist_info *qvlist_info) +{ + struct i40e_virtchnl_iwarp_qvlist_info *v_qvlist_info; + struct i40evf_adapter *adapter = ldev->vf; + struct i40e_qv_info *qv_info; + i40e_status err; + u32 v_idx, i; + u32 msg_size; + + if (adapter->aq_required) + return -EAGAIN; + + /* A quick check on whether the vectors belong to the client */ + for (i = 0; i < qvlist_info->num_vectors; i++) { + qv_info = &qvlist_info->qv_info[i]; + if (!qv_info) + continue; + v_idx = qv_info->v_idx; + if ((v_idx >= + (adapter->iwarp_base_vector + adapter->num_iwarp_msix)) || + (v_idx < adapter->iwarp_base_vector)) + return -EINVAL; + } + + v_qvlist_info = (struct i40e_virtchnl_iwarp_qvlist_info *)qvlist_info; + msg_size = sizeof(struct i40e_virtchnl_iwarp_qvlist_info) + + (sizeof(struct i40e_virtchnl_iwarp_qv_info) * + (v_qvlist_info->num_vectors - 1)); + + adapter->client_pending |= BIT(I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP); + err = i40e_aq_send_msg_to_pf(&adapter->hw, + I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP, + I40E_SUCCESS, (u8 *)v_qvlist_info, msg_size, NULL); + + if (err) { + dev_err(&adapter->pdev->dev, + "Unable to send iWarp vector config message to PF, error %d, aq status %d\n", + err, adapter->hw.aq.asq_last_status); + goto out; + } + + err = -EBUSY; + for (i = 0; i < 5; i++) { + msleep(100); + if (!(adapter->client_pending & + BIT(I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP))) { + err = 0; + break; + } + } +out: + return err; +} + +/** + * i40evf_register_client - Register a i40e client driver with the L2 driver + * @client: pointer to the i40e_client struct + * + * Returns 0 on success or non-0 on error + **/ +int i40evf_register_client(struct i40e_client *client) +{ + int ret = 0; + + if (!client) { + ret = -EIO; + goto out; + } + + if (strlen(client->name) == 0) { + pr_info("i40evf: Failed to register client with no name\n"); + ret = -EIO; + goto out; + } + + if (vf_registered_client) { + pr_info("i40evf: Client %s has already been registered!\n", + client->name); + ret = -EEXIST; + goto out; + } + + if ((client->version.major != I40EVF_CLIENT_VERSION_MAJOR) || + (client->version.minor != I40EVF_CLIENT_VERSION_MINOR)) { + pr_info("i40evf: Failed to register client %s due to mismatched client interface version\n", + client->name); + pr_info("Client is using version: %02d.%02d.%02d while LAN driver supports %s\n", + client->version.major, client->version.minor, + client->version.build, + i40evf_client_interface_version_str); + ret = -EIO; + goto out; + } + + vf_registered_client = client; + + i40evf_client_prepare(client); + + pr_info("i40evf: Registered client %s with return code %d\n", + client->name, ret); +out: + return ret; +} +EXPORT_SYMBOL(i40evf_register_client); + +/** + * i40evf_unregister_client - Unregister a i40e client driver with the L2 driver + * @client: pointer to the i40e_client struct + * + * Returns 0 on success or non-0 on error + **/ +int i40evf_unregister_client(struct i40e_client *client) +{ + int ret = 0; + + /* When a unregister request comes through we would have to send + * a close for each of the client instances that were opened. + * client_release function is called to handle this. + */ + i40evf_client_release(client); + + if (vf_registered_client != client) { + pr_info("i40evf: Client %s has not been registered\n", + client->name); + ret = -ENODEV; + goto out; + } + vf_registered_client = NULL; + pr_info("i40evf: Unregistered client %s\n", client->name); +out: + return ret; +} +EXPORT_SYMBOL(i40evf_unregister_client); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_client.h b/drivers/net/ethernet/intel/i40evf/i40evf_client.h new file mode 100644 index 000000000000..7d283c7506a5 --- /dev/null +++ b/drivers/net/ethernet/intel/i40evf/i40evf_client.h @@ -0,0 +1,166 @@ +#ifndef _I40E_CLIENT_H_ +#define _I40E_CLIENT_H_ + +#define I40EVF_CLIENT_STR_LENGTH 10 + +/* Client interface version should be updated anytime there is a change in the + * existing APIs or data structures. + */ +#define I40EVF_CLIENT_VERSION_MAJOR 0 +#define I40EVF_CLIENT_VERSION_MINOR 01 +#define I40EVF_CLIENT_VERSION_BUILD 00 +#define I40EVF_CLIENT_VERSION_STR \ + __stringify(I40EVF_CLIENT_VERSION_MAJOR) "." \ + __stringify(I40EVF_CLIENT_VERSION_MINOR) "." \ + __stringify(I40EVF_CLIENT_VERSION_BUILD) + +struct i40e_client_version { + u8 major; + u8 minor; + u8 build; + u8 rsvd; +}; + +enum i40e_client_state { + __I40E_CLIENT_NULL, + __I40E_CLIENT_REGISTERED +}; + +enum i40e_client_instance_state { + __I40E_CLIENT_INSTANCE_NONE, + __I40E_CLIENT_INSTANCE_OPENED, +}; + +struct i40e_ops; +struct i40e_client; + +/* HW does not define a type value for AEQ; only for RX/TX and CEQ. + * In order for us to keep the interface simple, SW will define a + * unique type value for AEQ. + */ +#define I40E_QUEUE_TYPE_PE_AEQ 0x80 +#define I40E_QUEUE_INVALID_IDX 0xFFFF + +struct i40e_qv_info { + u32 v_idx; /* msix_vector */ + u16 ceq_idx; + u16 aeq_idx; + u8 itr_idx; +}; + +struct i40e_qvlist_info { + u32 num_vectors; + struct i40e_qv_info qv_info[1]; +}; + +#define I40E_CLIENT_MSIX_ALL 0xFFFFFFFF + +/* set of LAN parameters useful for clients managed by LAN */ + +/* Struct to hold per priority info */ +struct i40e_prio_qos_params { + u16 qs_handle; /* qs handle for prio */ + u8 tc; /* TC mapped to prio */ + u8 reserved; +}; + +#define I40E_CLIENT_MAX_USER_PRIORITY 8 +/* Struct to hold Client QoS */ +struct i40e_qos_params { + struct i40e_prio_qos_params prio_qos[I40E_CLIENT_MAX_USER_PRIORITY]; +}; + +struct i40e_params { + struct i40e_qos_params qos; + u16 mtu; + u16 link_up; /* boolean */ +}; + +/* Structure to hold LAN device info for a client device */ +struct i40e_info { + struct i40e_client_version version; + u8 lanmac[6]; + struct net_device *netdev; + struct pci_dev *pcidev; + u8 __iomem *hw_addr; + u8 fid; /* function id, PF id or VF id */ +#define I40E_CLIENT_FTYPE_PF 0 +#define I40E_CLIENT_FTYPE_VF 1 + u8 ftype; /* function type, PF or VF */ + void *vf; /* cast to i40evf_adapter */ + + /* All L2 params that could change during the life span of the device + * and needs to be communicated to the client when they change + */ + struct i40e_params params; + struct i40e_ops *ops; + + u16 msix_count; /* number of msix vectors*/ + /* Array down below will be dynamically allocated based on msix_count */ + struct msix_entry *msix_entries; + u16 itr_index; /* Which ITR index the PE driver is suppose to use */ +}; + +struct i40e_ops { + /* setup_q_vector_list enables queues with a particular vector */ + int (*setup_qvlist)(struct i40e_info *ldev, struct i40e_client *client, + struct i40e_qvlist_info *qv_info); + + u32 (*virtchnl_send)(struct i40e_info *ldev, struct i40e_client *client, + u8 *msg, u16 len); + + /* If the PE Engine is unresponsive, RDMA driver can request a reset.*/ + void (*request_reset)(struct i40e_info *ldev, + struct i40e_client *client); +}; + +struct i40e_client_ops { + /* Should be called from register_client() or whenever the driver is + * ready to create a specific client instance. + */ + int (*open)(struct i40e_info *ldev, struct i40e_client *client); + + /* Should be closed when netdev is unavailable or when unregister + * call comes in. If the close happens due to a reset, set the reset + * bit to true. + */ + void (*close)(struct i40e_info *ldev, struct i40e_client *client, + bool reset); + + /* called when some l2 managed parameters changes - mss */ + void (*l2_param_change)(struct i40e_info *ldev, + struct i40e_client *client, + struct i40e_params *params); + + /* called when a message is received from the PF */ + int (*virtchnl_receive)(struct i40e_info *ldev, + struct i40e_client *client, + u8 *msg, u16 len); +}; + +/* Client device */ +struct i40e_client_instance { + struct list_head list; + struct i40e_info lan_info; + struct i40e_client *client; + unsigned long state; +}; + +struct i40e_client { + struct list_head list; /* list of registered clients */ + char name[I40EVF_CLIENT_STR_LENGTH]; + struct i40e_client_version version; + unsigned long state; /* client state */ + atomic_t ref_cnt; /* Count of all the client devices of this kind */ + u32 flags; +#define I40E_CLIENT_FLAGS_LAUNCH_ON_PROBE BIT(0) +#define I40E_TX_FLAGS_NOTIFY_OTHER_EVENTS BIT(2) + u8 type; +#define I40E_CLIENT_IWARP 0 + struct i40e_client_ops *ops; /* client ops provided by the client */ +}; + +/* used by clients */ +int i40evf_register_client(struct i40e_client *client); +int i40evf_unregister_client(struct i40e_client *client); +#endif /* _I40E_CLIENT_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c index 272d600c1ed0..9bb2cc7dd4e4 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c @@ -63,52 +63,74 @@ static const struct i40evf_stats i40evf_gstrings_stats[] = { #define I40EVF_STATS_LEN(_dev) \ (I40EVF_GLOBAL_STATS_LEN + I40EVF_QUEUE_STATS_LEN(_dev)) +/* For now we have one and only one private flag and it is only defined + * when we have support for the SKIP_CPU_SYNC DMA attribute. Instead + * of leaving all this code sitting around empty we will strip it unless + * our one private flag is actually available. + */ +struct i40evf_priv_flags { + char flag_string[ETH_GSTRING_LEN]; + u32 flag; + bool read_only; +}; + +#define I40EVF_PRIV_FLAG(_name, _flag, _read_only) { \ + .flag_string = _name, \ + .flag = _flag, \ + .read_only = _read_only, \ +} + +static const struct i40evf_priv_flags i40evf_gstrings_priv_flags[] = { + I40EVF_PRIV_FLAG("legacy-rx", I40EVF_FLAG_LEGACY_RX, 0), +}; + +#define I40EVF_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40evf_gstrings_priv_flags) + /** - * i40evf_get_settings - Get Link Speed and Duplex settings + * i40evf_get_link_ksettings - Get Link Speed and Duplex settings * @netdev: network interface device structure - * @ecmd: ethtool command + * @cmd: ethtool command * * Reports speed/duplex settings. Because this is a VF, we don't know what * kind of link we really have, so we fake it. **/ -static int i40evf_get_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int i40evf_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct i40evf_adapter *adapter = netdev_priv(netdev); - ecmd->supported = 0; - ecmd->autoneg = AUTONEG_DISABLE; - ecmd->transceiver = XCVR_DUMMY1; - ecmd->port = PORT_NONE; + ethtool_link_ksettings_zero_link_mode(cmd, supported); + cmd->base.autoneg = AUTONEG_DISABLE; + cmd->base.port = PORT_NONE; /* Set speed and duplex */ switch (adapter->link_speed) { case I40E_LINK_SPEED_40GB: - ethtool_cmd_speed_set(ecmd, SPEED_40000); + cmd->base.speed = SPEED_40000; break; case I40E_LINK_SPEED_25GB: #ifdef SPEED_25000 - ethtool_cmd_speed_set(ecmd, SPEED_25000); + cmd->base.speed = SPEED_25000; #else netdev_info(netdev, "Speed is 25G, display not supported by this version of ethtool.\n"); #endif break; case I40E_LINK_SPEED_20GB: - ethtool_cmd_speed_set(ecmd, SPEED_20000); + cmd->base.speed = SPEED_20000; break; case I40E_LINK_SPEED_10GB: - ethtool_cmd_speed_set(ecmd, SPEED_10000); + cmd->base.speed = SPEED_10000; break; case I40E_LINK_SPEED_1GB: - ethtool_cmd_speed_set(ecmd, SPEED_1000); + cmd->base.speed = SPEED_1000; break; case I40E_LINK_SPEED_100MB: - ethtool_cmd_speed_set(ecmd, SPEED_100); + cmd->base.speed = SPEED_100; break; default: break; } - ecmd->duplex = DUPLEX_FULL; + cmd->base.duplex = DUPLEX_FULL; return 0; } @@ -125,6 +147,8 @@ static int i40evf_get_sset_count(struct net_device *netdev, int sset) { if (sset == ETH_SS_STATS) return I40EVF_STATS_LEN(netdev); + else if (sset == ETH_SS_PRIV_FLAGS) + return I40EVF_PRIV_FLAGS_STR_LEN; else return -EINVAL; } @@ -190,7 +214,83 @@ static void i40evf_get_strings(struct net_device *netdev, u32 sset, u8 *data) snprintf(p, ETH_GSTRING_LEN, "rx-%u.bytes", i); p += ETH_GSTRING_LEN; } + } else if (sset == ETH_SS_PRIV_FLAGS) { + for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) { + snprintf(p, ETH_GSTRING_LEN, "%s", + i40evf_gstrings_priv_flags[i].flag_string); + p += ETH_GSTRING_LEN; + } + } +} + +/** + * i40evf_get_priv_flags - report device private flags + * @dev: network interface device structure + * + * The get string set count and the string set should be matched for each + * flag returned. Add new strings for each flag to the i40e_gstrings_priv_flags + * array. + * + * Returns a u32 bitmap of flags. + **/ +static u32 i40evf_get_priv_flags(struct net_device *netdev) +{ + struct i40evf_adapter *adapter = netdev_priv(netdev); + u32 i, ret_flags = 0; + + for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) { + const struct i40evf_priv_flags *priv_flags; + + priv_flags = &i40evf_gstrings_priv_flags[i]; + + if (priv_flags->flag & adapter->flags) + ret_flags |= BIT(i); + } + + return ret_flags; +} + +/** + * i40evf_set_priv_flags - set private flags + * @dev: network interface device structure + * @flags: bit flags to be set + **/ +static int i40evf_set_priv_flags(struct net_device *netdev, u32 flags) +{ + struct i40evf_adapter *adapter = netdev_priv(netdev); + u64 changed_flags; + u32 i; + + changed_flags = adapter->flags; + + for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) { + const struct i40evf_priv_flags *priv_flags; + + priv_flags = &i40evf_gstrings_priv_flags[i]; + + if (priv_flags->read_only) + continue; + + if (flags & BIT(i)) + adapter->flags |= priv_flags->flag; + else + adapter->flags &= ~(priv_flags->flag); + } + + /* check for flags that changed */ + changed_flags ^= adapter->flags; + + /* Process any additional changes needed as a result of flag changes. */ + + /* issue a reset to force legacy-rx change to take effect */ + if (changed_flags & I40EVF_FLAG_LEGACY_RX) { + if (netif_running(netdev)) { + adapter->flags |= I40EVF_FLAG_RESET_NEEDED; + schedule_work(&adapter->reset_task); + } } + + return 0; } /** @@ -239,6 +339,7 @@ static void i40evf_get_drvinfo(struct net_device *netdev, strlcpy(drvinfo->version, i40evf_driver_version, 32); strlcpy(drvinfo->fw_version, "N/A", 4); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), 32); + drvinfo->n_priv_flags = I40EVF_PRIV_FLAGS_STR_LEN; } /** @@ -643,7 +744,6 @@ static int i40evf_set_rxfh(struct net_device *netdev, const u32 *indir, } static const struct ethtool_ops i40evf_ethtool_ops = { - .get_settings = i40evf_get_settings, .get_drvinfo = i40evf_get_drvinfo, .get_link = ethtool_op_get_link, .get_ringparam = i40evf_get_ringparam, @@ -651,6 +751,8 @@ static const struct ethtool_ops i40evf_ethtool_ops = { .get_strings = i40evf_get_strings, .get_ethtool_stats = i40evf_get_ethtool_stats, .get_sset_count = i40evf_get_sset_count, + .get_priv_flags = i40evf_get_priv_flags, + .set_priv_flags = i40evf_set_priv_flags, .get_msglevel = i40evf_get_msglevel, .set_msglevel = i40evf_set_msglevel, .get_coalesce = i40evf_get_coalesce, @@ -663,6 +765,7 @@ static const struct ethtool_ops i40evf_ethtool_ops = { .set_rxfh = i40evf_set_rxfh, .get_channels = i40evf_get_channels, .get_rxfh_key_size = i40evf_get_rxfh_key_size, + .get_link_ksettings = i40evf_get_link_ksettings, }; /** diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index f35dcaac5bb7..ea110a730e16 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -26,6 +26,14 @@ #include "i40evf.h" #include "i40e_prototype.h" +#include "i40evf_client.h" +/* All i40evf tracepoints are defined by the include below, which must + * be included exactly once across the whole kernel with + * CREATE_TRACE_POINTS defined + */ +#define CREATE_TRACE_POINTS +#include "i40e_trace.h" + static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter); static int i40evf_setup_all_rx_resources(struct i40evf_adapter *adapter); static int i40evf_close(struct net_device *netdev); @@ -36,9 +44,9 @@ static const char i40evf_driver_string[] = #define DRV_KERN "-k" -#define DRV_VERSION_MAJOR 1 -#define DRV_VERSION_MINOR 6 -#define DRV_VERSION_BUILD 27 +#define DRV_VERSION_MAJOR 2 +#define DRV_VERSION_MINOR 1 +#define DRV_VERSION_BUILD 14 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) \ @@ -489,7 +497,7 @@ static void i40evf_netpoll(struct net_device *netdev) int i; /* if interface is down do nothing */ - if (test_bit(__I40E_DOWN, &adapter->vsi.state)) + if (test_bit(__I40E_VSI_DOWN, adapter->vsi.state)) return; for (i = 0; i < q_vectors; i++) @@ -685,12 +693,39 @@ static void i40evf_configure_tx(struct i40evf_adapter *adapter) **/ static void i40evf_configure_rx(struct i40evf_adapter *adapter) { + unsigned int rx_buf_len = I40E_RXBUFFER_2048; struct i40e_hw *hw = &adapter->hw; int i; + /* Legacy Rx will always default to a 2048 buffer size. */ +#if (PAGE_SIZE < 8192) + if (!(adapter->flags & I40EVF_FLAG_LEGACY_RX)) { + struct net_device *netdev = adapter->netdev; + + /* For jumbo frames on systems with 4K pages we have to use + * an order 1 page, so we might as well increase the size + * of our Rx buffer to make better use of the available space + */ + rx_buf_len = I40E_RXBUFFER_3072; + + /* We use a 1536 buffer size for configurations with + * standard Ethernet mtu. On x86 this gives us enough room + * for shared info and 192 bytes of padding. + */ + if (!I40E_2K_TOO_SMALL_WITH_PADDING && + (netdev->mtu <= ETH_DATA_LEN)) + rx_buf_len = I40E_RXBUFFER_1536 - NET_IP_ALIGN; + } +#endif + for (i = 0; i < adapter->num_active_queues; i++) { adapter->rx_rings[i].tail = hw->hw_addr + I40E_QRX_TAIL1(i); - adapter->rx_rings[i].rx_buf_len = I40EVF_RXBUFFER_2048; + adapter->rx_rings[i].rx_buf_len = rx_buf_len; + + if (adapter->flags & I40EVF_FLAG_LEGACY_RX) + clear_ring_build_skb_enabled(&adapter->rx_rings[i]); + else + set_ring_build_skb_enabled(&adapter->rx_rings[i]); } } @@ -1053,11 +1088,13 @@ static void i40evf_configure(struct i40evf_adapter *adapter) static void i40evf_up_complete(struct i40evf_adapter *adapter) { adapter->state = __I40EVF_RUNNING; - clear_bit(__I40E_DOWN, &adapter->vsi.state); + clear_bit(__I40E_VSI_DOWN, adapter->vsi.state); i40evf_napi_enable_all(adapter); adapter->aq_required |= I40EVF_FLAG_AQ_ENABLE_QUEUES; + if (CLIENT_ENABLED(adapter)) + adapter->flags |= I40EVF_FLAG_CLIENT_NEEDS_OPEN; mod_timer_pending(&adapter->watchdog_timer, jiffies + 1); } @@ -1235,13 +1272,13 @@ static int i40evf_set_interrupt_capability(struct i40evf_adapter *adapter) } pairs = adapter->num_active_queues; - /* It's easy to be greedy for MSI-X vectors, but it really - * doesn't do us much good if we have a lot more vectors - * than CPU's. So let's be conservative and only ask for - * (roughly) twice the number of vectors as there are CPU's. + /* It's easy to be greedy for MSI-X vectors, but it really doesn't do + * us much good if we have more vectors than CPUs. However, we already + * limit the total number of queues by the number of CPUs so we do not + * need any further limiting here. */ - v_budget = min_t(int, pairs, (int)(num_online_cpus() * 2)) + NONQ_VECS; - v_budget = min_t(int, v_budget, (int)adapter->vf_res->max_vectors); + v_budget = min_t(int, pairs + NONQ_VECS, + (int)adapter->vf_res->max_vectors); adapter->msix_entries = kcalloc(v_budget, sizeof(struct msix_entry), GFP_KERNEL); @@ -1472,6 +1509,13 @@ int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter) { int err; + err = i40evf_alloc_queues(adapter); + if (err) { + dev_err(&adapter->pdev->dev, + "Unable to allocate memory for queues\n"); + goto err_alloc_queues; + } + rtnl_lock(); err = i40evf_set_interrupt_capability(adapter); rtnl_unlock(); @@ -1488,23 +1532,16 @@ int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter) goto err_alloc_q_vectors; } - err = i40evf_alloc_queues(adapter); - if (err) { - dev_err(&adapter->pdev->dev, - "Unable to allocate memory for queues\n"); - goto err_alloc_queues; - } - dev_info(&adapter->pdev->dev, "Multiqueue %s: Queue pair count = %u", (adapter->num_active_queues > 1) ? "Enabled" : "Disabled", adapter->num_active_queues); return 0; -err_alloc_queues: - i40evf_free_q_vectors(adapter); err_alloc_q_vectors: i40evf_reset_interrupt_capability(adapter); err_set_interrupt: + i40evf_free_queues(adapter); +err_alloc_queues: return err; } @@ -1685,6 +1722,7 @@ static void i40evf_watchdog_task(struct work_struct *work) i40evf_set_promiscuous(adapter, 0); goto watchdog_done; } + schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5)); if (adapter->state == __I40EVF_RUNNING) i40evf_request_stats(adapter); @@ -1716,7 +1754,7 @@ static void i40evf_disable_vf(struct i40evf_adapter *adapter) adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED; if (netif_running(adapter->netdev)) { - set_bit(__I40E_DOWN, &adapter->vsi.state); + set_bit(__I40E_VSI_DOWN, adapter->vsi.state); netif_carrier_off(adapter->netdev); netif_tx_disable(adapter->netdev); adapter->link_up = false; @@ -1773,10 +1811,17 @@ static void i40evf_reset_task(struct work_struct *work) u32 reg_val; int i = 0, err; - while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, + while (test_and_set_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section)) usleep_range(500, 1000); - + if (CLIENT_ENABLED(adapter)) { + adapter->flags &= ~(I40EVF_FLAG_CLIENT_NEEDS_OPEN | + I40EVF_FLAG_CLIENT_NEEDS_CLOSE | + I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS | + I40EVF_FLAG_SERVICE_CLIENT_REQUESTED); + cancel_delayed_work_sync(&adapter->client_task); + i40evf_notify_client_close(&adapter->vsi, true); + } i40evf_misc_irq_disable(adapter); if (adapter->flags & I40EVF_FLAG_RESET_NEEDED) { adapter->flags &= ~I40EVF_FLAG_RESET_NEEDED; @@ -1819,6 +1864,7 @@ static void i40evf_reset_task(struct work_struct *work) dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n", reg_val); i40evf_disable_vf(adapter); + clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section); return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -1861,9 +1907,8 @@ continue_reset: } adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER; adapter->aq_required |= I40EVF_FLAG_AQ_ADD_VLAN_FILTER; - /* Open RDMA Client again */ - adapter->aq_required |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section); i40evf_misc_irq_enable(adapter); mod_timer(&adapter->watchdog_timer, jiffies + 2); @@ -1980,6 +2025,48 @@ out: } /** + * i40evf_client_task - worker thread to perform client work + * @work: pointer to work_struct containing our data + * + * This task handles client interactions. Because client calls can be + * reentrant, we can't handle them in the watchdog. + **/ +static void i40evf_client_task(struct work_struct *work) +{ + struct i40evf_adapter *adapter = + container_of(work, struct i40evf_adapter, client_task.work); + + /* If we can't get the client bit, just give up. We'll be rescheduled + * later. + */ + + if (test_and_set_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section)) + return; + + if (adapter->flags & I40EVF_FLAG_SERVICE_CLIENT_REQUESTED) { + i40evf_client_subtask(adapter); + adapter->flags &= ~I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; + goto out; + } + if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_CLOSE) { + i40evf_notify_client_close(&adapter->vsi, false); + adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_CLOSE; + goto out; + } + if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_OPEN) { + i40evf_notify_client_open(&adapter->vsi); + adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_OPEN; + goto out; + } + if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS) { + i40evf_notify_client_l2_params(&adapter->vsi); + adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS; + } +out: + clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section); +} + +/** * i40evf_free_all_tx_resources - Free Tx Resources for All Queues * @adapter: board private structure * @@ -2147,7 +2234,9 @@ static int i40evf_close(struct net_device *netdev) return 0; - set_bit(__I40E_DOWN, &adapter->vsi.state); + set_bit(__I40E_VSI_DOWN, adapter->vsi.state); + if (CLIENT_ENABLED(adapter)) + adapter->flags |= I40EVF_FLAG_CLIENT_NEEDS_CLOSE; i40evf_down(adapter); adapter->state = __I40EVF_DOWN_PENDING; @@ -2162,21 +2251,6 @@ static int i40evf_close(struct net_device *netdev) } /** - * i40evf_get_stats - Get System Network Statistics - * @netdev: network interface device structure - * - * Returns the address of the device statistics structure. - * The statistics are actually updated from the timer callback. - **/ -static struct net_device_stats *i40evf_get_stats(struct net_device *netdev) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - - /* only return the current stats */ - return &adapter->net_stats; -} - -/** * i40evf_change_mtu - Change the Maximum Transfer Unit * @netdev: network interface device structure * @new_mtu: new value for maximum frame size @@ -2188,6 +2262,10 @@ static int i40evf_change_mtu(struct net_device *netdev, int new_mtu) struct i40evf_adapter *adapter = netdev_priv(netdev); netdev->mtu = new_mtu; + if (CLIENT_ENABLED(adapter)) { + i40evf_notify_client_l2_params(&adapter->vsi); + adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; + } adapter->flags |= I40EVF_FLAG_RESET_NEEDED; schedule_work(&adapter->reset_task); @@ -2278,7 +2356,6 @@ static const struct net_device_ops i40evf_netdev_ops = { .ndo_open = i40evf_open, .ndo_stop = i40evf_close, .ndo_start_xmit = i40evf_xmit_frame, - .ndo_get_stats = i40evf_get_stats, .ndo_set_rx_mode = i40evf_set_rx_mode, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = i40evf_set_mac, @@ -2328,6 +2405,8 @@ int i40evf_process_config(struct i40evf_adapter *adapter) struct net_device *netdev = adapter->netdev; struct i40e_vsi *vsi = &adapter->vsi; int i; + netdev_features_t hw_enc_features; + netdev_features_t hw_features; /* got VF config message back from PF, now we can parse it */ for (i = 0; i < vfres->num_vsis; i++) { @@ -2339,46 +2418,52 @@ int i40evf_process_config(struct i40evf_adapter *adapter) return -ENODEV; } - netdev->hw_enc_features |= NETIF_F_SG | - NETIF_F_IP_CSUM | - NETIF_F_IPV6_CSUM | - NETIF_F_HIGHDMA | - NETIF_F_SOFT_FEATURES | - NETIF_F_TSO | - NETIF_F_TSO_ECN | - NETIF_F_TSO6 | + hw_enc_features = NETIF_F_SG | + NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM | + NETIF_F_HIGHDMA | + NETIF_F_SOFT_FEATURES | + NETIF_F_TSO | + NETIF_F_TSO_ECN | + NETIF_F_TSO6 | + NETIF_F_SCTP_CRC | + NETIF_F_RXHASH | + NETIF_F_RXCSUM | + 0; + + /* advertise to stack only if offloads for encapsulated packets is + * supported + */ + if (vfres->vf_offload_flags & I40E_VIRTCHNL_VF_OFFLOAD_ENCAP) { + hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE | NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_IPXIP4 | NETIF_F_GSO_IPXIP6 | - NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_GSO_PARTIAL | - NETIF_F_SCTP_CRC | - NETIF_F_RXHASH | - NETIF_F_RXCSUM | 0; - if (!(adapter->flags & I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE)) - netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM; - - netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM; + if (!(vfres->vf_offload_flags & + I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM)) + netdev->gso_partial_features |= + NETIF_F_GSO_UDP_TUNNEL_CSUM; + netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM; + netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID; + netdev->hw_enc_features |= hw_enc_features; + } /* record features VLANs can make use of */ - netdev->vlan_features |= netdev->hw_enc_features | - NETIF_F_TSO_MANGLEID; + netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID; /* Write features and hw_features separately to avoid polluting - * with, or dropping, features that are set when we registgered. + * with, or dropping, features that are set when we registered. */ - netdev->hw_features |= netdev->hw_enc_features; + hw_features = hw_enc_features; - netdev->features |= netdev->hw_enc_features | I40EVF_VLAN_FEATURES; - netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID; + netdev->hw_features |= hw_features; - /* disable VLAN features if not supported */ - if (!(vfres->vf_offload_flags & I40E_VIRTCHNL_VF_OFFLOAD_VLAN)) - netdev->features ^= I40EVF_VLAN_FEATURES; + netdev->features |= hw_features | I40EVF_VLAN_FEATURES; adapter->vsi.id = adapter->vsi_res->vsi_id; @@ -2519,9 +2604,6 @@ static void i40evf_init_task(struct work_struct *work) goto err_alloc; } - if (hw->mac.type == I40E_MAC_X722_VF) - adapter->flags |= I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE; - if (i40evf_process_config(adapter)) goto err_alloc; adapter->current_op = I40E_VIRTCHNL_OP_UNKNOWN; @@ -2581,13 +2663,19 @@ static void i40evf_init_task(struct work_struct *work) adapter->netdev_registered = true; netif_tx_stop_all_queues(netdev); + if (CLIENT_ALLOWED(adapter)) { + err = i40evf_lan_add_device(adapter); + if (err) + dev_info(&pdev->dev, "Failed to add VF to client API service list: %d\n", + err); + } dev_info(&pdev->dev, "MAC address: %pM\n", adapter->hw.mac.addr); if (netdev->features & NETIF_F_GRO) dev_info(&pdev->dev, "GRO is enabled\n"); adapter->state = __I40EVF_DOWN; - set_bit(__I40E_DOWN, &adapter->vsi.state); + set_bit(__I40E_VSI_DOWN, adapter->vsi.state); i40evf_misc_irq_enable(adapter); adapter->rss_key = kzalloc(adapter->rss_key_size, GFP_KERNEL); @@ -2745,6 +2833,7 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&adapter->reset_task, i40evf_reset_task); INIT_WORK(&adapter->adminq_task, i40evf_adminq_task); INIT_WORK(&adapter->watchdog_task, i40evf_watchdog_task); + INIT_DELAYED_WORK(&adapter->client_task, i40evf_client_task); INIT_DELAYED_WORK(&adapter->init_task, i40evf_init_task); schedule_delayed_work(&adapter->init_task, msecs_to_jiffies(5 * (pdev->devfn & 0x07))); @@ -2857,14 +2946,21 @@ static void i40evf_remove(struct pci_dev *pdev) struct i40evf_adapter *adapter = netdev_priv(netdev); struct i40evf_mac_filter *f, *ftmp; struct i40e_hw *hw = &adapter->hw; + int err; cancel_delayed_work_sync(&adapter->init_task); cancel_work_sync(&adapter->reset_task); - + cancel_delayed_work_sync(&adapter->client_task); if (adapter->netdev_registered) { unregister_netdev(netdev); adapter->netdev_registered = false; } + if (CLIENT_ALLOWED(adapter)) { + err = i40evf_lan_del_device(adapter); + if (err) + dev_warn(&pdev->dev, "Failed to delete client device: %d\n", + err); + } /* Shut down all the garbage mashers on the detention level */ adapter->state = __I40EVF_REMOVE; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index bee58af390e1..deb2cb8dac6b 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -26,6 +26,7 @@ #include "i40evf.h" #include "i40e_prototype.h" +#include "i40evf_client.h" /* busy wait delay in msec */ #define I40EVF_BUSY_WAIT_DELAY 10 @@ -158,7 +159,9 @@ int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter) I40E_VIRTCHNL_VF_OFFLOAD_RSS_REG | I40E_VIRTCHNL_VF_OFFLOAD_VLAN | I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR | - I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2; + I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 | + I40E_VIRTCHNL_VF_OFFLOAD_ENCAP | + I40E_VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM; adapter->current_op = I40E_VIRTCHNL_OP_GET_VF_RESOURCES; adapter->aq_required &= ~I40EVF_FLAG_AQ_GET_CONFIG; @@ -233,7 +236,7 @@ void i40evf_configure_queues(struct i40evf_adapter *adapter) struct i40e_virtchnl_vsi_queue_config_info *vqci; struct i40e_virtchnl_queue_pair_info *vqpi; int pairs = adapter->num_active_queues; - int i, len; + int i, len, max_frame = I40E_MAX_RXBUFFER; if (adapter->current_op != I40E_VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ @@ -248,6 +251,11 @@ void i40evf_configure_queues(struct i40evf_adapter *adapter) if (!vqci) return; + /* Limit maximum frame size when jumbo frames is not enabled */ + if (!(adapter->flags & I40EVF_FLAG_LEGACY_RX) && + (adapter->netdev->mtu <= ETH_DATA_LEN)) + max_frame = I40E_RXBUFFER_1536 - NET_IP_ALIGN; + vqci->vsi_id = adapter->vsi_res->vsi_id; vqci->num_queue_pairs = pairs; vqpi = vqci->qpair; @@ -259,17 +267,14 @@ void i40evf_configure_queues(struct i40evf_adapter *adapter) vqpi->txq.queue_id = i; vqpi->txq.ring_len = adapter->tx_rings[i].count; vqpi->txq.dma_ring_addr = adapter->tx_rings[i].dma; - vqpi->txq.headwb_enabled = 1; - vqpi->txq.dma_headwb_addr = vqpi->txq.dma_ring_addr + - (vqpi->txq.ring_len * sizeof(struct i40e_tx_desc)); - vqpi->rxq.vsi_id = vqci->vsi_id; vqpi->rxq.queue_id = i; vqpi->rxq.ring_len = adapter->rx_rings[i].count; vqpi->rxq.dma_ring_addr = adapter->rx_rings[i].dma; - vqpi->rxq.max_pkt_size = adapter->netdev->mtu - + ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN; - vqpi->rxq.databuffer_size = adapter->rx_rings[i].rx_buf_len; + vqpi->rxq.max_pkt_size = max_frame; + vqpi->rxq.databuffer_size = + ALIGN(adapter->rx_rings[i].rx_buf_len, + BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT)); vqpi++; } @@ -955,17 +960,17 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, case I40E_VIRTCHNL_OP_GET_STATS: { struct i40e_eth_stats *stats = (struct i40e_eth_stats *)msg; - adapter->net_stats.rx_packets = stats->rx_unicast + - stats->rx_multicast + - stats->rx_broadcast; - adapter->net_stats.tx_packets = stats->tx_unicast + - stats->tx_multicast + - stats->tx_broadcast; - adapter->net_stats.rx_bytes = stats->rx_bytes; - adapter->net_stats.tx_bytes = stats->tx_bytes; - adapter->net_stats.tx_errors = stats->tx_errors; - adapter->net_stats.rx_dropped = stats->rx_discards; - adapter->net_stats.tx_dropped = stats->tx_discards; + netdev->stats.rx_packets = stats->rx_unicast + + stats->rx_multicast + + stats->rx_broadcast; + netdev->stats.tx_packets = stats->tx_unicast + + stats->tx_multicast + + stats->tx_broadcast; + netdev->stats.rx_bytes = stats->rx_bytes; + netdev->stats.tx_bytes = stats->tx_bytes; + netdev->stats.tx_errors = stats->tx_errors; + netdev->stats.rx_dropped = stats->rx_discards; + netdev->stats.tx_dropped = stats->tx_discards; adapter->current_stats = *stats; } break; @@ -999,6 +1004,16 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, if (v_opcode != adapter->current_op) return; break; + case I40E_VIRTCHNL_OP_IWARP: + /* Gobble zero-length replies from the PF. They indicate that + * a previous message was received OK, and the client doesn't + * care about that. + */ + if (msglen && CLIENT_ENABLED(adapter)) + i40evf_notify_client_message(&adapter->vsi, + msg, msglen); + break; + case I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP: adapter->client_pending &= ~(BIT(I40E_VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP)); @@ -1014,7 +1029,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, } break; default: - if (v_opcode != adapter->current_op) + if (adapter->current_op && (v_opcode != adapter->current_op)) dev_warn(&adapter->pdev->dev, "Expected response %d from PF, received %d\n", adapter->current_op, v_opcode); break; diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h index 8aee314332a8..d8517779439b 100644 --- a/drivers/net/ethernet/intel/igb/e1000_defines.h +++ b/drivers/net/ethernet/intel/igb/e1000_defines.h @@ -39,6 +39,27 @@ #define E1000_WUFC_MC 0x00000008 /* Directed Multicast Wakeup Enable */ #define E1000_WUFC_BC 0x00000010 /* Broadcast Wakeup Enable */ +/* Wake Up Status */ +#define E1000_WUS_EX 0x00000004 /* Directed Exact */ +#define E1000_WUS_ARPD 0x00000020 /* Directed ARP Request */ +#define E1000_WUS_IPV4 0x00000040 /* Directed IPv4 */ +#define E1000_WUS_IPV6 0x00000080 /* Directed IPv6 */ +#define E1000_WUS_NSD 0x00000400 /* Directed IPv6 Neighbor Solicitation */ + +/* Packet types that are enabled for wake packet delivery */ +#define WAKE_PKT_WUS ( \ + E1000_WUS_EX | \ + E1000_WUS_ARPD | \ + E1000_WUS_IPV4 | \ + E1000_WUS_IPV6 | \ + E1000_WUS_NSD) + +/* Wake Up Packet Length */ +#define E1000_WUPL_MASK 0x00000FFF + +/* Wake Up Packet Memory stores the first 128 bytes of the wake up packet */ +#define E1000_WUPM_BYTES 128 + /* Extended Device Control */ #define E1000_CTRL_EXT_SDP2_DATA 0x00000040 /* Value of SW Defineable Pin 2 */ #define E1000_CTRL_EXT_SDP3_DATA 0x00000080 /* Value of SW Defineable Pin 3 */ diff --git a/drivers/net/ethernet/intel/igb/e1000_mbx.h b/drivers/net/ethernet/intel/igb/e1000_mbx.h index d20af6b2f581..3e7fed73df15 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mbx.h +++ b/drivers/net/ethernet/intel/igb/e1000_mbx.h @@ -55,6 +55,10 @@ #define E1000_VF_RESET 0x01 /* VF requests reset */ #define E1000_VF_SET_MAC_ADDR 0x02 /* VF requests to set MAC addr */ +/* VF requests to clear all unicast MAC filters */ +#define E1000_VF_MAC_FILTER_CLR (0x01 << E1000_VT_MSGINFO_SHIFT) +/* VF requests to add unicast MAC filter */ +#define E1000_VF_MAC_FILTER_ADD (0x02 << E1000_VT_MSGINFO_SHIFT) #define E1000_VF_SET_MULTICAST 0x03 /* VF requests to set MC addr */ #define E1000_VF_SET_VLAN 0x04 /* VF requests to set VLAN */ #define E1000_VF_SET_LPE 0x05 /* VF requests to set VMOLR.LPE */ diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index acbc3abe2ddd..bf9bf9056d0c 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -111,6 +111,16 @@ struct vf_data_storage { bool spoofchk_enabled; }; +/* Number of unicast MAC filters reserved for the PF in the RAR registers */ +#define IGB_PF_MAC_FILTERS_RESERVED 3 + +struct vf_mac_filter { + struct list_head l; + int vf; + bool free; + u8 vf_mac[ETH_ALEN]; +}; + #define IGB_VF_FLAG_CTS 0x00000001 /* VF is clear to send data */ #define IGB_VF_FLAG_UNI_PROMISC 0x00000002 /* VF has unicast promisc */ #define IGB_VF_FLAG_MULTI_PROMISC 0x00000004 /* VF has multicast promisc */ @@ -142,12 +152,24 @@ struct vf_data_storage { /* Supported Rx Buffer Sizes */ #define IGB_RXBUFFER_256 256 #define IGB_RXBUFFER_2048 2048 +#define IGB_RXBUFFER_3072 3072 #define IGB_RX_HDR_LEN IGB_RXBUFFER_256 -#define IGB_RX_BUFSZ IGB_RXBUFFER_2048 +#define IGB_TS_HDR_LEN 16 + +#define IGB_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +#if (PAGE_SIZE < 8192) +#define IGB_MAX_FRAME_BUILD_SKB \ + (SKB_WITH_OVERHEAD(IGB_RXBUFFER_2048) - IGB_SKB_PAD - IGB_TS_HDR_LEN) +#else +#define IGB_MAX_FRAME_BUILD_SKB (IGB_RXBUFFER_2048 - IGB_TS_HDR_LEN) +#endif /* How many Rx Buffers do we bundle into one write to the hardware ? */ #define IGB_RX_BUFFER_WRITE 16 /* Must be power of 2 */ +#define IGB_RX_DMA_ATTR \ + (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) + #define AUTO_ALL_MODES 0 #define IGB_EEPROM_APME 0x0400 @@ -301,12 +323,51 @@ struct igb_q_vector { }; enum e1000_ring_flags_t { + IGB_RING_FLAG_RX_3K_BUFFER, + IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, IGB_RING_FLAG_RX_SCTP_CSUM, IGB_RING_FLAG_RX_LB_VLAN_BSWAP, IGB_RING_FLAG_TX_CTX_IDX, IGB_RING_FLAG_TX_DETECT_HANG }; +#define ring_uses_large_buffer(ring) \ + test_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) +#define set_ring_uses_large_buffer(ring) \ + set_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) +#define clear_ring_uses_large_buffer(ring) \ + clear_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) + +#define ring_uses_build_skb(ring) \ + test_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) +#define set_ring_build_skb_enabled(ring) \ + set_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) +#define clear_ring_build_skb_enabled(ring) \ + clear_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) + +static inline unsigned int igb_rx_bufsz(struct igb_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring_uses_large_buffer(ring)) + return IGB_RXBUFFER_3072; + + if (ring_uses_build_skb(ring)) + return IGB_MAX_FRAME_BUILD_SKB + IGB_TS_HDR_LEN; +#endif + return IGB_RXBUFFER_2048; +} + +static inline unsigned int igb_rx_pg_order(struct igb_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring_uses_large_buffer(ring)) + return 1; +#endif + return 0; +} + +#define igb_rx_pg_size(_ring) (PAGE_SIZE << igb_rx_pg_order(_ring)) + #define IGB_TXD_DCMD (E1000_ADVTXD_DCMD_EOP | E1000_ADVTXD_DCMD_RS) #define IGB_RX_DESC(R, i) \ @@ -398,6 +459,15 @@ struct igb_nfc_filter { u16 action; }; +struct igb_mac_addr { + u8 addr[ETH_ALEN]; + u8 queue; + u8 state; /* bitmask */ +}; + +#define IGB_MAC_STATE_DEFAULT 0x1 +#define IGB_MAC_STATE_IN_USE 0x2 + /* board specific private data structure */ struct igb_adapter { unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; @@ -524,6 +594,10 @@ struct igb_adapter { /* lock for RX network flow classification filter */ spinlock_t nfc_lock; bool etype_bitmap[MAX_ETYPE_FILTER]; + + struct igb_mac_addr *mac_table; + struct vf_mac_filter vf_macs; + struct vf_mac_filter *vf_mac_list; }; /* flags controlling PTP/1588 function */ @@ -545,6 +619,7 @@ struct igb_adapter { #define IGB_FLAG_HAS_MSIX BIT(13) #define IGB_FLAG_EEE BIT(14) #define IGB_FLAG_VLAN_PROMISC BIT(15) +#define IGB_FLAG_RX_LEGACY BIT(16) /* Media Auto Sense */ #define IGB_MAS_ENABLE_0 0X0001 @@ -558,7 +633,6 @@ struct igb_adapter { #define IGB_DMCTLX_DCFLUSH_DIS 0x80000000 /* Disable DMA Coal Flush */ #define IGB_82576_TSYNC_SHIFT 19 -#define IGB_TS_HDR_LEN 16 enum e1000_state_t { __IGB_TESTING, __IGB_RESETTING, @@ -591,7 +665,6 @@ void igb_configure_rx_ring(struct igb_adapter *, struct igb_ring *); void igb_setup_tctl(struct igb_adapter *); void igb_setup_rctl(struct igb_adapter *); netdev_tx_t igb_xmit_frame_ring(struct sk_buff *, struct igb_ring *); -void igb_unmap_and_free_tx_resource(struct igb_ring *, struct igb_tx_buffer *); void igb_alloc_rx_buffers(struct igb_ring *, u16); void igb_update_stats(struct igb_adapter *, struct rtnl_link_stats64 *); bool igb_has_link(struct igb_adapter *adapter); @@ -604,7 +677,7 @@ void igb_ptp_reset(struct igb_adapter *adapter); void igb_ptp_suspend(struct igb_adapter *adapter); void igb_ptp_rx_hang(struct igb_adapter *adapter); void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb); -void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, unsigned char *va, +void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, struct sk_buff *skb); int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr); int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr); diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 737b664d004c..0efb62db6efd 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -144,7 +144,15 @@ static const char igb_gstrings_test[][ETH_GSTRING_LEN] = { }; #define IGB_TEST_LEN (sizeof(igb_gstrings_test) / ETH_GSTRING_LEN) -static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) +static const char igb_priv_flags_strings[][ETH_GSTRING_LEN] = { +#define IGB_PRIV_FLAGS_LEGACY_RX BIT(0) + "legacy-rx", +}; + +#define IGB_PRIV_FLAGS_STR_LEN ARRAY_SIZE(igb_priv_flags_strings) + +static int igb_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; @@ -152,76 +160,73 @@ static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) struct e1000_sfp_flags *eth_flags = &dev_spec->eth_flags; u32 status; u32 speed; + u32 supported, advertising; status = rd32(E1000_STATUS); if (hw->phy.media_type == e1000_media_type_copper) { - ecmd->supported = (SUPPORTED_10baseT_Half | - SUPPORTED_10baseT_Full | - SUPPORTED_100baseT_Half | - SUPPORTED_100baseT_Full | - SUPPORTED_1000baseT_Full| - SUPPORTED_Autoneg | - SUPPORTED_TP | - SUPPORTED_Pause); - ecmd->advertising = ADVERTISED_TP; + supported = (SUPPORTED_10baseT_Half | + SUPPORTED_10baseT_Full | + SUPPORTED_100baseT_Half | + SUPPORTED_100baseT_Full | + SUPPORTED_1000baseT_Full| + SUPPORTED_Autoneg | + SUPPORTED_TP | + SUPPORTED_Pause); + advertising = ADVERTISED_TP; if (hw->mac.autoneg == 1) { - ecmd->advertising |= ADVERTISED_Autoneg; + advertising |= ADVERTISED_Autoneg; /* the e1000 autoneg seems to match ethtool nicely */ - ecmd->advertising |= hw->phy.autoneg_advertised; + advertising |= hw->phy.autoneg_advertised; } - ecmd->port = PORT_TP; - ecmd->phy_address = hw->phy.addr; - ecmd->transceiver = XCVR_INTERNAL; + cmd->base.port = PORT_TP; + cmd->base.phy_address = hw->phy.addr; } else { - ecmd->supported = (SUPPORTED_FIBRE | - SUPPORTED_1000baseKX_Full | - SUPPORTED_Autoneg | - SUPPORTED_Pause); - ecmd->advertising = (ADVERTISED_FIBRE | - ADVERTISED_1000baseKX_Full); + supported = (SUPPORTED_FIBRE | + SUPPORTED_1000baseKX_Full | + SUPPORTED_Autoneg | + SUPPORTED_Pause); + advertising = (ADVERTISED_FIBRE | + ADVERTISED_1000baseKX_Full); if (hw->mac.type == e1000_i354) { if ((hw->device_id == E1000_DEV_ID_I354_BACKPLANE_2_5GBPS) && !(status & E1000_STATUS_2P5_SKU_OVER)) { - ecmd->supported |= SUPPORTED_2500baseX_Full; - ecmd->supported &= - ~SUPPORTED_1000baseKX_Full; - ecmd->advertising |= ADVERTISED_2500baseX_Full; - ecmd->advertising &= - ~ADVERTISED_1000baseKX_Full; + supported |= SUPPORTED_2500baseX_Full; + supported &= ~SUPPORTED_1000baseKX_Full; + advertising |= ADVERTISED_2500baseX_Full; + advertising &= ~ADVERTISED_1000baseKX_Full; } } if (eth_flags->e100_base_fx) { - ecmd->supported |= SUPPORTED_100baseT_Full; - ecmd->advertising |= ADVERTISED_100baseT_Full; + supported |= SUPPORTED_100baseT_Full; + advertising |= ADVERTISED_100baseT_Full; } if (hw->mac.autoneg == 1) - ecmd->advertising |= ADVERTISED_Autoneg; + advertising |= ADVERTISED_Autoneg; - ecmd->port = PORT_FIBRE; - ecmd->transceiver = XCVR_EXTERNAL; + cmd->base.port = PORT_FIBRE; } if (hw->mac.autoneg != 1) - ecmd->advertising &= ~(ADVERTISED_Pause | - ADVERTISED_Asym_Pause); + advertising &= ~(ADVERTISED_Pause | + ADVERTISED_Asym_Pause); switch (hw->fc.requested_mode) { case e1000_fc_full: - ecmd->advertising |= ADVERTISED_Pause; + advertising |= ADVERTISED_Pause; break; case e1000_fc_rx_pause: - ecmd->advertising |= (ADVERTISED_Pause | - ADVERTISED_Asym_Pause); + advertising |= (ADVERTISED_Pause | + ADVERTISED_Asym_Pause); break; case e1000_fc_tx_pause: - ecmd->advertising |= ADVERTISED_Asym_Pause; + advertising |= ADVERTISED_Asym_Pause; break; default: - ecmd->advertising &= ~(ADVERTISED_Pause | - ADVERTISED_Asym_Pause); + advertising &= ~(ADVERTISED_Pause | + ADVERTISED_Asym_Pause); } if (status & E1000_STATUS_LU) { if ((status & E1000_STATUS_2P5_SKU) && @@ -236,39 +241,46 @@ static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) } if ((status & E1000_STATUS_FD) || hw->phy.media_type != e1000_media_type_copper) - ecmd->duplex = DUPLEX_FULL; + cmd->base.duplex = DUPLEX_FULL; else - ecmd->duplex = DUPLEX_HALF; + cmd->base.duplex = DUPLEX_HALF; } else { speed = SPEED_UNKNOWN; - ecmd->duplex = DUPLEX_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; } - ethtool_cmd_speed_set(ecmd, speed); + cmd->base.speed = speed; if ((hw->phy.media_type == e1000_media_type_fiber) || hw->mac.autoneg) - ecmd->autoneg = AUTONEG_ENABLE; + cmd->base.autoneg = AUTONEG_ENABLE; else - ecmd->autoneg = AUTONEG_DISABLE; + cmd->base.autoneg = AUTONEG_DISABLE; /* MDI-X => 2; MDI =>1; Invalid =>0 */ if (hw->phy.media_type == e1000_media_type_copper) - ecmd->eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X : + cmd->base.eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X : ETH_TP_MDI; else - ecmd->eth_tp_mdix = ETH_TP_MDI_INVALID; + cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID; if (hw->phy.mdix == AUTO_ALL_MODES) - ecmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO; + cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO; else - ecmd->eth_tp_mdix_ctrl = hw->phy.mdix; + cmd->base.eth_tp_mdix_ctrl = hw->phy.mdix; + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); return 0; } -static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) +static int igb_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *cmd) { struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; + u32 advertising; /* When SoL/IDER sessions are active, autoneg/speed/duplex * cannot be changed @@ -283,12 +295,12 @@ static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) * some hardware doesn't allow MDI setting when speed or * duplex is forced. */ - if (ecmd->eth_tp_mdix_ctrl) { + if (cmd->base.eth_tp_mdix_ctrl) { if (hw->phy.media_type != e1000_media_type_copper) return -EOPNOTSUPP; - if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) && - (ecmd->autoneg != AUTONEG_ENABLE)) { + if ((cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) && + (cmd->base.autoneg != AUTONEG_ENABLE)) { dev_err(&adapter->pdev->dev, "forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n"); return -EINVAL; } @@ -297,10 +309,13 @@ static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) while (test_and_set_bit(__IGB_RESETTING, &adapter->state)) usleep_range(1000, 2000); - if (ecmd->autoneg == AUTONEG_ENABLE) { + ethtool_convert_link_mode_to_legacy_u32(&advertising, + cmd->link_modes.advertising); + + if (cmd->base.autoneg == AUTONEG_ENABLE) { hw->mac.autoneg = 1; if (hw->phy.media_type == e1000_media_type_fiber) { - hw->phy.autoneg_advertised = ecmd->advertising | + hw->phy.autoneg_advertised = advertising | ADVERTISED_FIBRE | ADVERTISED_Autoneg; switch (adapter->link_speed) { @@ -320,31 +335,31 @@ static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) break; } } else { - hw->phy.autoneg_advertised = ecmd->advertising | + hw->phy.autoneg_advertised = advertising | ADVERTISED_TP | ADVERTISED_Autoneg; } - ecmd->advertising = hw->phy.autoneg_advertised; + advertising = hw->phy.autoneg_advertised; if (adapter->fc_autoneg) hw->fc.requested_mode = e1000_fc_default; } else { - u32 speed = ethtool_cmd_speed(ecmd); + u32 speed = cmd->base.speed; /* calling this overrides forced MDI setting */ - if (igb_set_spd_dplx(adapter, speed, ecmd->duplex)) { + if (igb_set_spd_dplx(adapter, speed, cmd->base.duplex)) { clear_bit(__IGB_RESETTING, &adapter->state); return -EINVAL; } } /* MDI-X => 2; MDI => 1; Auto => 3 */ - if (ecmd->eth_tp_mdix_ctrl) { + if (cmd->base.eth_tp_mdix_ctrl) { /* fix up the value for auto (3 => 0) as zero is mapped * internally to auto */ - if (ecmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO) + if (cmd->base.eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO) hw->phy.mdix = AUTO_ALL_MODES; else - hw->phy.mdix = ecmd->eth_tp_mdix_ctrl; + hw->phy.mdix = cmd->base.eth_tp_mdix_ctrl; } /* reset the link */ @@ -852,6 +867,8 @@ static void igb_get_drvinfo(struct net_device *netdev, sizeof(drvinfo->fw_version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); + + drvinfo->n_priv_flags = IGB_PRIV_FLAGS_STR_LEN; } static void igb_get_ringparam(struct net_device *netdev, @@ -1811,14 +1828,14 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring, tx_ntc = tx_ring->next_to_clean; rx_desc = IGB_RX_DESC(rx_ring, rx_ntc); - while (igb_test_staterr(rx_desc, E1000_RXD_STAT_DD)) { + while (rx_desc->wb.upper.length) { /* check Rx buffer */ rx_buffer_info = &rx_ring->rx_buffer_info[rx_ntc]; /* sync Rx buffer for CPU read */ dma_sync_single_for_cpu(rx_ring->dev, rx_buffer_info->dma, - IGB_RX_BUFSZ, + size, DMA_FROM_DEVICE); /* verify contents of skb */ @@ -1828,12 +1845,21 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring, /* sync Rx buffer for device write */ dma_sync_single_for_device(rx_ring->dev, rx_buffer_info->dma, - IGB_RX_BUFSZ, + size, DMA_FROM_DEVICE); /* unmap buffer on Tx side */ tx_buffer_info = &tx_ring->tx_buffer_info[tx_ntc]; - igb_unmap_and_free_tx_resource(tx_ring, tx_buffer_info); + + /* Free all the Tx ring sk_buffs */ + dev_kfree_skb_any(tx_buffer_info->skb); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer_info, dma), + dma_unmap_len(tx_buffer_info, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer_info, len, 0); /* increment Rx/Tx next to clean counters */ rx_ntc++; @@ -2271,6 +2297,8 @@ static int igb_get_sset_count(struct net_device *netdev, int sset) return IGB_STATS_LEN; case ETH_SS_TEST: return IGB_TEST_LEN; + case ETH_SS_PRIV_FLAGS: + return IGB_PRIV_FLAGS_STR_LEN; default: return -ENOTSUPP; } @@ -2376,6 +2404,10 @@ static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data) } /* BUG_ON(p - data != IGB_STATS_LEN * ETH_GSTRING_LEN); */ break; + case ETH_SS_PRIV_FLAGS: + memcpy(data, igb_priv_flags_strings, + IGB_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN); + break; } } @@ -3388,9 +3420,38 @@ static int igb_set_channels(struct net_device *netdev, return 0; } +static u32 igb_get_priv_flags(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + u32 priv_flags = 0; + + if (adapter->flags & IGB_FLAG_RX_LEGACY) + priv_flags |= IGB_PRIV_FLAGS_LEGACY_RX; + + return priv_flags; +} + +static int igb_set_priv_flags(struct net_device *netdev, u32 priv_flags) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + unsigned int flags = adapter->flags; + + flags &= ~IGB_FLAG_RX_LEGACY; + if (priv_flags & IGB_PRIV_FLAGS_LEGACY_RX) + flags |= IGB_FLAG_RX_LEGACY; + + if (flags != adapter->flags) { + adapter->flags = flags; + + /* reset interface to repopulate queues */ + if (netif_running(netdev)) + igb_reinit_locked(adapter); + } + + return 0; +} + static const struct ethtool_ops igb_ethtool_ops = { - .get_settings = igb_get_settings, - .set_settings = igb_set_settings, .get_drvinfo = igb_get_drvinfo, .get_regs_len = igb_get_regs_len, .get_regs = igb_get_regs, @@ -3426,8 +3487,12 @@ static const struct ethtool_ops igb_ethtool_ops = { .set_rxfh = igb_set_rxfh, .get_channels = igb_get_channels, .set_channels = igb_set_channels, + .get_priv_flags = igb_get_priv_flags, + .set_priv_flags = igb_set_priv_flags, .begin = igb_ethtool_begin, .complete = igb_ethtool_complete, + .get_link_ksettings = igb_get_link_ksettings, + .set_link_ksettings = igb_set_link_ksettings, }; void igb_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index be456bae8169..1cf74aa4ebd9 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -161,11 +161,16 @@ static void igb_vlan_mode(struct net_device *netdev, static int igb_vlan_rx_add_vid(struct net_device *, __be16, u16); static int igb_vlan_rx_kill_vid(struct net_device *, __be16, u16); static void igb_restore_vlan(struct igb_adapter *); -static void igb_rar_set_qsel(struct igb_adapter *, u8 *, u32 , u8); +static void igb_rar_set_index(struct igb_adapter *, u32); static void igb_ping_all_vfs(struct igb_adapter *); static void igb_msg_task(struct igb_adapter *); static void igb_vmm_control(struct igb_adapter *); static int igb_set_vf_mac(struct igb_adapter *, int, unsigned char *); +static void igb_flush_mac_table(struct igb_adapter *); +static int igb_available_rars(struct igb_adapter *, u8); +static void igb_set_default_mac_filter(struct igb_adapter *); +static int igb_uc_sync(struct net_device *, const unsigned char *); +static int igb_uc_unsync(struct net_device *, const unsigned char *); static void igb_restore_vf_multicasts(struct igb_adapter *adapter); static int igb_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac); static int igb_ndo_set_vf_vlan(struct net_device *netdev, @@ -554,7 +559,7 @@ rx_ring_summary: 16, 1, page_address(buffer_info->page) + buffer_info->page_offset, - IGB_RX_BUFSZ, true); + igb_rx_bufsz(rx_ring), true); } } } @@ -1153,6 +1158,8 @@ msi_only: pci_disable_sriov(adapter->pdev); msleep(500); + kfree(adapter->vf_mac_list); + adapter->vf_mac_list = NULL; kfree(adapter->vf_data); adapter->vf_data = NULL; wr32(E1000_IOVCTL, E1000_IOVCTL_REUSE_VFQ); @@ -1987,6 +1994,13 @@ void igb_reset(struct igb_adapter *adapter) if (hw->mac.ops.init_hw(hw)) dev_err(&pdev->dev, "Hardware Error\n"); + /* RAR registers were cleared during init_hw, clear mac table */ + igb_flush_mac_table(adapter); + __dev_uc_unsync(adapter->netdev, NULL); + + /* Recover default RAR entry */ + igb_set_default_mac_filter(adapter); + /* Flow control settings reset on hardware reset, so guarantee flow * control is off when forcing speed. */ @@ -2095,11 +2109,9 @@ static int igb_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], /* guarantee we can provide a unique filter for the unicast address */ if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) { struct igb_adapter *adapter = netdev_priv(dev); - struct e1000_hw *hw = &adapter->hw; int vfn = adapter->vfs_allocated_count; - int rar_entries = hw->mac.rar_entry_count - (vfn + 1); - if (netdev_uc_count(dev) >= rar_entries) + if (netdev_uc_count(dev) >= igb_available_rars(adapter, vfn)) return -ENOMEM; } @@ -2517,6 +2529,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_eeprom; } + igb_set_default_mac_filter(adapter); + /* get firmware version for ethtool -i */ igb_set_fw_version(adapter); @@ -2761,6 +2775,7 @@ err_eeprom: if (hw->flash_address) iounmap(hw->flash_address); err_sw_init: + kfree(adapter->mac_table); kfree(adapter->shadow_vfta); igb_clear_interrupt_scheme(adapter); #ifdef CONFIG_PCI_IOV @@ -2796,6 +2811,8 @@ static int igb_disable_sriov(struct pci_dev *pdev) msleep(500); } + kfree(adapter->vf_mac_list); + adapter->vf_mac_list = NULL; kfree(adapter->vf_data); adapter->vf_data = NULL; adapter->vfs_allocated_count = 0; @@ -2816,8 +2833,9 @@ static int igb_enable_sriov(struct pci_dev *pdev, int num_vfs) struct net_device *netdev = pci_get_drvdata(pdev); struct igb_adapter *adapter = netdev_priv(netdev); int old_vfs = pci_num_vf(pdev); + struct vf_mac_filter *mac_list; int err = 0; - int i; + int num_vf_mac_filters, i; if (!(adapter->flags & IGB_FLAG_HAS_MSIX) || num_vfs > 7) { err = -EPERM; @@ -2845,6 +2863,38 @@ static int igb_enable_sriov(struct pci_dev *pdev, int num_vfs) goto out; } + /* Due to the limited number of RAR entries calculate potential + * number of MAC filters available for the VFs. Reserve entries + * for PF default MAC, PF MAC filters and at least one RAR entry + * for each VF for VF MAC. + */ + num_vf_mac_filters = adapter->hw.mac.rar_entry_count - + (1 + IGB_PF_MAC_FILTERS_RESERVED + + adapter->vfs_allocated_count); + + adapter->vf_mac_list = kcalloc(num_vf_mac_filters, + sizeof(struct vf_mac_filter), + GFP_KERNEL); + + mac_list = adapter->vf_mac_list; + INIT_LIST_HEAD(&adapter->vf_macs.l); + + if (adapter->vf_mac_list) { + /* Initialize list of VF MAC filters */ + for (i = 0; i < num_vf_mac_filters; i++) { + mac_list->vf = -1; + mac_list->free = true; + list_add(&mac_list->l, &adapter->vf_macs.l); + mac_list++; + } + } else { + /* If we could not allocate memory for the VF MAC filters + * we can continue without this feature but warn user. + */ + dev_err(&pdev->dev, + "Unable to allocate memory for VF MAC filter list\n"); + } + /* only call pci_enable_sriov() if no VFs are allocated already */ if (!old_vfs) { err = pci_enable_sriov(pdev, adapter->vfs_allocated_count); @@ -2861,6 +2911,8 @@ static int igb_enable_sriov(struct pci_dev *pdev, int num_vfs) goto out; err_out: + kfree(adapter->vf_mac_list); + adapter->vf_mac_list = NULL; kfree(adapter->vf_data); adapter->vf_data = NULL; adapter->vfs_allocated_count = 0; @@ -2937,6 +2989,7 @@ static void igb_remove(struct pci_dev *pdev) iounmap(hw->flash_address); pci_release_mem_regions(pdev); + kfree(adapter->mac_table); kfree(adapter->shadow_vfta); free_netdev(netdev); @@ -3099,6 +3152,11 @@ static int igb_sw_init(struct igb_adapter *adapter) /* Assume MSI-X interrupts, will be checked during IRQ allocation */ adapter->flags |= IGB_FLAG_HAS_MSIX; + adapter->mac_table = kzalloc(sizeof(struct igb_mac_addr) * + hw->mac.rar_entry_count, GFP_ATOMIC); + if (!adapter->mac_table) + return -ENOMEM; + igb_probe_vfs(adapter); igb_init_queue_configuration(adapter); @@ -3293,7 +3351,7 @@ int igb_setup_tx_resources(struct igb_ring *tx_ring) size = sizeof(struct igb_tx_buffer) * tx_ring->count; - tx_ring->tx_buffer_info = vzalloc(size); + tx_ring->tx_buffer_info = vmalloc(size); if (!tx_ring->tx_buffer_info) goto err; @@ -3404,6 +3462,10 @@ void igb_configure_tx_ring(struct igb_adapter *adapter, txdctl |= IGB_TX_HTHRESH << 8; txdctl |= IGB_TX_WTHRESH << 16; + /* reinitialize tx_buffer_info */ + memset(ring->tx_buffer_info, 0, + sizeof(struct igb_tx_buffer) * ring->count); + txdctl |= E1000_TXDCTL_QUEUE_ENABLE; wr32(E1000_TXDCTL(reg_idx), txdctl); } @@ -3435,7 +3497,7 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring) size = sizeof(struct igb_rx_buffer) * rx_ring->count; - rx_ring->rx_buffer_info = vzalloc(size); + rx_ring->rx_buffer_info = vmalloc(size); if (!rx_ring->rx_buffer_info) goto err; @@ -3720,6 +3782,7 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, struct igb_ring *ring) { struct e1000_hw *hw = &adapter->hw; + union e1000_adv_rx_desc *rx_desc; u64 rdba = ring->dma; int reg_idx = ring->reg_idx; u32 srrctl = 0, rxdctl = 0; @@ -3741,7 +3804,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, /* set descriptor configuration */ srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT; - srrctl |= IGB_RX_BUFSZ >> E1000_SRRCTL_BSIZEPKT_SHIFT; + if (ring_uses_large_buffer(ring)) + srrctl |= IGB_RXBUFFER_3072 >> E1000_SRRCTL_BSIZEPKT_SHIFT; + else + srrctl |= IGB_RXBUFFER_2048 >> E1000_SRRCTL_BSIZEPKT_SHIFT; srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF; if (hw->mac.type >= e1000_82580) srrctl |= E1000_SRRCTL_TIMESTAMP; @@ -3758,11 +3824,39 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, rxdctl |= IGB_RX_HTHRESH << 8; rxdctl |= IGB_RX_WTHRESH << 16; + /* initialize rx_buffer_info */ + memset(ring->rx_buffer_info, 0, + sizeof(struct igb_rx_buffer) * ring->count); + + /* initialize Rx descriptor 0 */ + rx_desc = IGB_RX_DESC(ring, 0); + rx_desc->wb.upper.length = 0; + /* enable receive descriptor fetching */ rxdctl |= E1000_RXDCTL_QUEUE_ENABLE; wr32(E1000_RXDCTL(reg_idx), rxdctl); } +static void igb_set_rx_buffer_len(struct igb_adapter *adapter, + struct igb_ring *rx_ring) +{ + /* set build_skb and buffer size flags */ + clear_ring_build_skb_enabled(rx_ring); + clear_ring_uses_large_buffer(rx_ring); + + if (adapter->flags & IGB_FLAG_RX_LEGACY) + return; + + set_ring_build_skb_enabled(rx_ring); + +#if (PAGE_SIZE < 8192) + if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB) + return; + + set_ring_uses_large_buffer(rx_ring); +#endif +} + /** * igb_configure_rx - Configure receive Unit after Reset * @adapter: board private structure @@ -3774,14 +3868,17 @@ static void igb_configure_rx(struct igb_adapter *adapter) int i; /* set the correct pool for the PF default MAC address in entry 0 */ - igb_rar_set_qsel(adapter, adapter->hw.mac.addr, 0, - adapter->vfs_allocated_count); + igb_set_default_mac_filter(adapter); /* Setup the HW Rx Head and Tail Descriptor Pointers and * the Base and Length of the Rx Descriptor Ring */ - for (i = 0; i < adapter->num_rx_queues; i++) - igb_configure_rx_ring(adapter, adapter->rx_ring[i]); + for (i = 0; i < adapter->num_rx_queues; i++) { + struct igb_ring *rx_ring = adapter->rx_ring[i]; + + igb_set_rx_buffer_len(adapter, rx_ring); + igb_configure_rx_ring(adapter, rx_ring); + } } /** @@ -3822,55 +3919,63 @@ static void igb_free_all_tx_resources(struct igb_adapter *adapter) igb_free_tx_resources(adapter->tx_ring[i]); } -void igb_unmap_and_free_tx_resource(struct igb_ring *ring, - struct igb_tx_buffer *tx_buffer) -{ - if (tx_buffer->skb) { - dev_kfree_skb_any(tx_buffer->skb); - if (dma_unmap_len(tx_buffer, len)) - dma_unmap_single(ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - } else if (dma_unmap_len(tx_buffer, len)) { - dma_unmap_page(ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - } - tx_buffer->next_to_watch = NULL; - tx_buffer->skb = NULL; - dma_unmap_len_set(tx_buffer, len, 0); - /* buffer_info must be completely set up in the transmit path */ -} - /** * igb_clean_tx_ring - Free Tx Buffers * @tx_ring: ring to be cleaned **/ static void igb_clean_tx_ring(struct igb_ring *tx_ring) { - struct igb_tx_buffer *buffer_info; - unsigned long size; - u16 i; + u16 i = tx_ring->next_to_clean; + struct igb_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; - if (!tx_ring->tx_buffer_info) - return; - /* Free all the Tx ring sk_buffs */ + while (i != tx_ring->next_to_use) { + union e1000_adv_tx_desc *eop_desc, *tx_desc; - for (i = 0; i < tx_ring->count; i++) { - buffer_info = &tx_ring->tx_buffer_info[i]; - igb_unmap_and_free_tx_resource(tx_ring, buffer_info); - } + /* Free all the Tx ring sk_buffs */ + dev_kfree_skb_any(tx_buffer->skb); - netdev_tx_reset_queue(txring_txq(tx_ring)); + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); - size = sizeof(struct igb_tx_buffer) * tx_ring->count; - memset(tx_ring->tx_buffer_info, 0, size); + /* check for eop_desc to determine the end of the packet */ + eop_desc = tx_buffer->next_to_watch; + tx_desc = IGB_TX_DESC(tx_ring, i); + + /* unmap remaining buffers */ + while (tx_desc != eop_desc) { + tx_buffer++; + tx_desc++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IGB_TX_DESC(tx_ring, 0); + } - /* Zero out the descriptor ring */ - memset(tx_ring->desc, 0, tx_ring->size); + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + } + /* move us one more past the eop_desc for start of next pkt */ + tx_buffer++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + } + } + + /* reset BQL for queue */ + netdev_tx_reset_queue(txring_txq(tx_ring)); + + /* reset next_to_use and next_to_clean */ tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; } @@ -3932,50 +4037,39 @@ static void igb_free_all_rx_resources(struct igb_adapter *adapter) **/ static void igb_clean_rx_ring(struct igb_ring *rx_ring) { - unsigned long size; - u16 i; + u16 i = rx_ring->next_to_clean; if (rx_ring->skb) dev_kfree_skb(rx_ring->skb); rx_ring->skb = NULL; - if (!rx_ring->rx_buffer_info) - return; - /* Free all the Rx ring sk_buffs */ - for (i = 0; i < rx_ring->count; i++) { + while (i != rx_ring->next_to_alloc) { struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i]; - if (!buffer_info->page) - continue; - /* Invalidate cache lines that may have been written to by * device so that we avoid corrupting memory. */ dma_sync_single_range_for_cpu(rx_ring->dev, buffer_info->dma, buffer_info->page_offset, - IGB_RX_BUFSZ, + igb_rx_bufsz(rx_ring), DMA_FROM_DEVICE); /* free resources associated with mapping */ dma_unmap_page_attrs(rx_ring->dev, buffer_info->dma, - PAGE_SIZE, + igb_rx_pg_size(rx_ring), DMA_FROM_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); + IGB_RX_DMA_ATTR); __page_frag_cache_drain(buffer_info->page, buffer_info->pagecnt_bias); - buffer_info->page = NULL; + i++; + if (i == rx_ring->count) + i = 0; } - size = sizeof(struct igb_rx_buffer) * rx_ring->count; - memset(rx_ring->rx_buffer_info, 0, size); - - /* Zero out the descriptor ring */ - memset(rx_ring->desc, 0, rx_ring->size); - rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; @@ -4014,8 +4108,7 @@ static int igb_set_mac(struct net_device *netdev, void *p) memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len); /* set the correct pool for the new PF MAC address in entry 0 */ - igb_rar_set_qsel(adapter, hw->mac.addr, 0, - adapter->vfs_allocated_count); + igb_set_default_mac_filter(adapter); return 0; } @@ -4059,49 +4152,6 @@ static int igb_write_mc_addr_list(struct net_device *netdev) return netdev_mc_count(netdev); } -/** - * igb_write_uc_addr_list - write unicast addresses to RAR table - * @netdev: network interface device structure - * - * Writes unicast address list to the RAR table. - * Returns: -ENOMEM on failure/insufficient address space - * 0 on no addresses written - * X on writing X addresses to the RAR table - **/ -static int igb_write_uc_addr_list(struct net_device *netdev) -{ - struct igb_adapter *adapter = netdev_priv(netdev); - struct e1000_hw *hw = &adapter->hw; - unsigned int vfn = adapter->vfs_allocated_count; - unsigned int rar_entries = hw->mac.rar_entry_count - (vfn + 1); - int count = 0; - - /* return ENOMEM indicating insufficient memory for addresses */ - if (netdev_uc_count(netdev) > rar_entries) - return -ENOMEM; - - if (!netdev_uc_empty(netdev) && rar_entries) { - struct netdev_hw_addr *ha; - - netdev_for_each_uc_addr(ha, netdev) { - if (!rar_entries) - break; - igb_rar_set_qsel(adapter, ha->addr, - rar_entries--, - vfn); - count++; - } - } - /* write the addresses in reverse order to avoid write combining */ - for (; rar_entries > 0 ; rar_entries--) { - wr32(E1000_RAH(rar_entries), 0); - wr32(E1000_RAL(rar_entries), 0); - } - wrfl(); - - return count; -} - static int igb_vlan_promisc_enable(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; @@ -4240,7 +4290,7 @@ static void igb_set_rx_mode(struct net_device *netdev) struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; unsigned int vfn = adapter->vfs_allocated_count; - u32 rctl = 0, vmolr = 0; + u32 rctl = 0, vmolr = 0, rlpml = MAX_JUMBO_FRAME_SIZE; int count; /* Check for Promiscuous and All Multicast modes */ @@ -4274,8 +4324,7 @@ static void igb_set_rx_mode(struct net_device *netdev) * sufficient space to store all the addresses then enable * unicast promiscuous mode */ - count = igb_write_uc_addr_list(netdev); - if (count < 0) { + if (__dev_uc_sync(netdev, igb_uc_sync, igb_uc_unsync)) { rctl |= E1000_RCTL_UPE; vmolr |= E1000_VMOLR_ROPE; } @@ -4298,6 +4347,14 @@ static void igb_set_rx_mode(struct net_device *netdev) E1000_RCTL_VFE); wr32(E1000_RCTL, rctl); +#if (PAGE_SIZE < 8192) + if (!adapter->vfs_allocated_count) { + if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB) + rlpml = IGB_MAX_FRAME_BUILD_SKB; + } +#endif + wr32(E1000_RLPML, rlpml); + /* In order to support SR-IOV and eventually VMDq it is necessary to set * the VMOLR to enable the appropriate modes. Without this workaround * we will have issues with VLAN tag stripping not being done for frames @@ -4312,12 +4369,17 @@ static void igb_set_rx_mode(struct net_device *netdev) vmolr |= rd32(E1000_VMOLR(vfn)) & ~(E1000_VMOLR_ROPE | E1000_VMOLR_MPME | E1000_VMOLR_ROMPE); - /* enable Rx jumbo frames, no need for restriction */ + /* enable Rx jumbo frames, restrict as needed to support build_skb */ vmolr &= ~E1000_VMOLR_RLPML_MASK; - vmolr |= MAX_JUMBO_FRAME_SIZE | E1000_VMOLR_LPE; +#if (PAGE_SIZE < 8192) + if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB) + vmolr |= IGB_MAX_FRAME_BUILD_SKB; + else +#endif + vmolr |= MAX_JUMBO_FRAME_SIZE; + vmolr |= E1000_VMOLR_LPE; wr32(E1000_VMOLR(vfn), vmolr); - wr32(E1000_RLPML, MAX_JUMBO_FRAME_SIZE); igb_restore_vf_multicasts(adapter); } @@ -5256,18 +5318,32 @@ static void igb_tx_map(struct igb_ring *tx_ring, dma_error: dev_err(tx_ring->dev, "TX DMA map failed\n"); + tx_buffer = &tx_ring->tx_buffer_info[i]; /* clear dma mappings for failed tx_buffer_info map */ - for (;;) { + while (tx_buffer != first) { + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + + if (i--) + i += tx_ring->count; tx_buffer = &tx_ring->tx_buffer_info[i]; - igb_unmap_and_free_tx_resource(tx_ring, tx_buffer); - if (tx_buffer == first) - break; - if (i == 0) - i = tx_ring->count; - i--; } + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + + dev_kfree_skb_any(tx_buffer->skb); + tx_buffer->skb = NULL; + tx_ring->next_to_use = i; } @@ -5339,7 +5415,8 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, return NETDEV_TX_OK; out_drop: - igb_unmap_and_free_tx_resource(tx_ring, first); + dev_kfree_skb_any(first->skb); + first->skb = NULL; return NETDEV_TX_OK; } @@ -6304,7 +6381,6 @@ static void igb_vf_reset_msg(struct igb_adapter *adapter, u32 vf) { struct e1000_hw *hw = &adapter->hw; unsigned char *vf_mac = adapter->vf_data[vf].vf_mac_addresses; - int rar_entry = hw->mac.rar_entry_count - (vf + 1); u32 reg, msgbuf[3]; u8 *addr = (u8 *)(&msgbuf[1]); @@ -6312,7 +6388,7 @@ static void igb_vf_reset_msg(struct igb_adapter *adapter, u32 vf) igb_vf_reset(adapter, vf); /* set vf mac address */ - igb_rar_set_qsel(adapter, vf_mac, rar_entry, vf); + igb_set_vf_mac(adapter, vf, vf_mac); /* enable transmit and receive for vf */ reg = rd32(E1000_VFTE); @@ -6332,18 +6408,238 @@ static void igb_vf_reset_msg(struct igb_adapter *adapter, u32 vf) igb_write_mbx(hw, msgbuf, 3, vf); } +static void igb_flush_mac_table(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + int i; + + for (i = 0; i < hw->mac.rar_entry_count; i++) { + adapter->mac_table[i].state &= ~IGB_MAC_STATE_IN_USE; + memset(adapter->mac_table[i].addr, 0, ETH_ALEN); + adapter->mac_table[i].queue = 0; + igb_rar_set_index(adapter, i); + } +} + +static int igb_available_rars(struct igb_adapter *adapter, u8 queue) +{ + struct e1000_hw *hw = &adapter->hw; + /* do not count rar entries reserved for VFs MAC addresses */ + int rar_entries = hw->mac.rar_entry_count - + adapter->vfs_allocated_count; + int i, count = 0; + + for (i = 0; i < rar_entries; i++) { + /* do not count default entries */ + if (adapter->mac_table[i].state & IGB_MAC_STATE_DEFAULT) + continue; + + /* do not count "in use" entries for different queues */ + if ((adapter->mac_table[i].state & IGB_MAC_STATE_IN_USE) && + (adapter->mac_table[i].queue != queue)) + continue; + + count++; + } + + return count; +} + +/* Set default MAC address for the PF in the first RAR entry */ +static void igb_set_default_mac_filter(struct igb_adapter *adapter) +{ + struct igb_mac_addr *mac_table = &adapter->mac_table[0]; + + ether_addr_copy(mac_table->addr, adapter->hw.mac.addr); + mac_table->queue = adapter->vfs_allocated_count; + mac_table->state = IGB_MAC_STATE_DEFAULT | IGB_MAC_STATE_IN_USE; + + igb_rar_set_index(adapter, 0); +} + +int igb_add_mac_filter(struct igb_adapter *adapter, const u8 *addr, + const u8 queue) +{ + struct e1000_hw *hw = &adapter->hw; + int rar_entries = hw->mac.rar_entry_count - + adapter->vfs_allocated_count; + int i; + + if (is_zero_ether_addr(addr)) + return -EINVAL; + + /* Search for the first empty entry in the MAC table. + * Do not touch entries at the end of the table reserved for the VF MAC + * addresses. + */ + for (i = 0; i < rar_entries; i++) { + if (adapter->mac_table[i].state & IGB_MAC_STATE_IN_USE) + continue; + + ether_addr_copy(adapter->mac_table[i].addr, addr); + adapter->mac_table[i].queue = queue; + adapter->mac_table[i].state |= IGB_MAC_STATE_IN_USE; + + igb_rar_set_index(adapter, i); + return i; + } + + return -ENOSPC; +} + +int igb_del_mac_filter(struct igb_adapter *adapter, const u8 *addr, + const u8 queue) +{ + struct e1000_hw *hw = &adapter->hw; + int rar_entries = hw->mac.rar_entry_count - + adapter->vfs_allocated_count; + int i; + + if (is_zero_ether_addr(addr)) + return -EINVAL; + + /* Search for matching entry in the MAC table based on given address + * and queue. Do not touch entries at the end of the table reserved + * for the VF MAC addresses. + */ + for (i = 0; i < rar_entries; i++) { + if (!(adapter->mac_table[i].state & IGB_MAC_STATE_IN_USE)) + continue; + if (adapter->mac_table[i].queue != queue) + continue; + if (!ether_addr_equal(adapter->mac_table[i].addr, addr)) + continue; + + adapter->mac_table[i].state &= ~IGB_MAC_STATE_IN_USE; + memset(adapter->mac_table[i].addr, 0, ETH_ALEN); + adapter->mac_table[i].queue = 0; + + igb_rar_set_index(adapter, i); + return 0; + } + + return -ENOENT; +} + +static int igb_uc_sync(struct net_device *netdev, const unsigned char *addr) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + int ret; + + ret = igb_add_mac_filter(adapter, addr, adapter->vfs_allocated_count); + + return min_t(int, ret, 0); +} + +static int igb_uc_unsync(struct net_device *netdev, const unsigned char *addr) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + + igb_del_mac_filter(adapter, addr, adapter->vfs_allocated_count); + + return 0; +} + +int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf, + const u32 info, const u8 *addr) +{ + struct pci_dev *pdev = adapter->pdev; + struct vf_data_storage *vf_data = &adapter->vf_data[vf]; + struct list_head *pos; + struct vf_mac_filter *entry = NULL; + int ret = 0; + + switch (info) { + case E1000_VF_MAC_FILTER_CLR: + /* remove all unicast MAC filters related to the current VF */ + list_for_each(pos, &adapter->vf_macs.l) { + entry = list_entry(pos, struct vf_mac_filter, l); + if (entry->vf == vf) { + entry->vf = -1; + entry->free = true; + igb_del_mac_filter(adapter, entry->vf_mac, vf); + } + } + break; + case E1000_VF_MAC_FILTER_ADD: + if (vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) { + dev_warn(&pdev->dev, + "VF %d requested MAC filter but is administratively denied\n", + vf); + return -EINVAL; + } + + if (!is_valid_ether_addr(addr)) { + dev_warn(&pdev->dev, + "VF %d attempted to set invalid MAC filter\n", + vf); + return -EINVAL; + } + + /* try to find empty slot in the list */ + list_for_each(pos, &adapter->vf_macs.l) { + entry = list_entry(pos, struct vf_mac_filter, l); + if (entry->free) + break; + } + + if (entry && entry->free) { + entry->free = false; + entry->vf = vf; + ether_addr_copy(entry->vf_mac, addr); + + ret = igb_add_mac_filter(adapter, addr, vf); + ret = min_t(int, ret, 0); + } else { + ret = -ENOSPC; + } + + if (ret == -ENOSPC) + dev_warn(&pdev->dev, + "VF %d has requested MAC filter but there is no space for it\n", + vf); + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} + static int igb_set_vf_mac_addr(struct igb_adapter *adapter, u32 *msg, int vf) { + struct pci_dev *pdev = adapter->pdev; + struct vf_data_storage *vf_data = &adapter->vf_data[vf]; + u32 info = msg[0] & E1000_VT_MSGINFO_MASK; + /* The VF MAC Address is stored in a packed array of bytes * starting at the second 32 bit word of the msg array */ - unsigned char *addr = (char *)&msg[1]; - int err = -1; + unsigned char *addr = (unsigned char *)&msg[1]; + int ret = 0; - if (is_valid_ether_addr(addr)) - err = igb_set_vf_mac(adapter, vf, addr); + if (!info) { + if (vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) { + dev_warn(&pdev->dev, + "VF %d attempted to override administratively set MAC address\nReload the VF driver to resume operations\n", + vf); + return -EINVAL; + } - return err; + if (!is_valid_ether_addr(addr)) { + dev_warn(&pdev->dev, + "VF %d attempted to set invalid MAC\n", + vf); + return -EINVAL; + } + + ret = igb_set_vf_mac(adapter, vf, addr); + } else { + ret = igb_set_vf_mac_filter(adapter, vf, info, addr); + } + + return ret; } static void igb_rcv_ack_from_vf(struct igb_adapter *adapter, u32 vf) @@ -6400,13 +6696,7 @@ static void igb_rcv_msg_from_vf(struct igb_adapter *adapter, u32 vf) switch ((msgbuf[0] & 0xFFFF)) { case E1000_VF_SET_MAC_ADDR: - retval = -EINVAL; - if (!(vf_data->flags & IGB_VF_FLAG_PF_SET_MAC)) - retval = igb_set_vf_mac_addr(adapter, msgbuf, vf); - else - dev_warn(&pdev->dev, - "VF %d attempted to override administratively set MAC address\nReload the VF driver to resume operations\n", - vf); + retval = igb_set_vf_mac_addr(adapter, msgbuf, vf); break; case E1000_VF_SET_PROMISC: retval = igb_set_vf_promisc(adapter, msgbuf, vf); @@ -6686,7 +6976,6 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) DMA_TO_DEVICE); /* clear tx_buffer data */ - tx_buffer->skb = NULL; dma_unmap_len_set(tx_buffer, len, 0); /* clear last DMA location and unmap remaining buffers */ @@ -6822,8 +7111,14 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring, nta++; rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; - /* transfer page from old buffer to new buffer */ - *new_buff = *old_buff; + /* Transfer page from old buffer to new buffer. + * Move each member individually to avoid possible store + * forwarding stalls. + */ + new_buff->dma = old_buff->dma; + new_buff->page = old_buff->page; + new_buff->page_offset = old_buff->page_offset; + new_buff->pagecnt_bias = old_buff->pagecnt_bias; } static inline bool igb_page_is_reserved(struct page *page) @@ -6831,11 +7126,10 @@ static inline bool igb_page_is_reserved(struct page *page) return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); } -static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, - struct page *page, - unsigned int truesize) +static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer) { - unsigned int pagecnt_bias = rx_buffer->pagecnt_bias--; + unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; + struct page *page = rx_buffer->page; /* avoid re-using remote pages */ if (unlikely(igb_page_is_reserved(page))) @@ -6843,16 +7137,13 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely(page_ref_count(page) != pagecnt_bias)) + if (unlikely((page_ref_count(page) - pagecnt_bias) > 1)) return false; - - /* flip page offset to other buffer */ - rx_buffer->page_offset ^= IGB_RX_BUFSZ; #else - /* move offset up to the next cache line */ - rx_buffer->page_offset += truesize; +#define IGB_LAST_OFFSET \ + (SKB_WITH_OVERHEAD(PAGE_SIZE) - IGB_RXBUFFER_2048) - if (rx_buffer->page_offset > (PAGE_SIZE - IGB_RX_BUFSZ)) + if (rx_buffer->page_offset > IGB_LAST_OFFSET) return false; #endif @@ -6860,7 +7151,7 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, * the pagecnt_bias and page count so that we fully restock the * number of references the driver holds. */ - if (unlikely(pagecnt_bias == 1)) { + if (unlikely(!pagecnt_bias)) { page_ref_add(page, USHRT_MAX); rx_buffer->pagecnt_bias = USHRT_MAX; } @@ -6872,34 +7163,56 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, * igb_add_rx_frag - Add contents of Rx buffer to sk_buff * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: buffer containing page to add - * @rx_desc: descriptor containing length of buffer written by hardware * @skb: sk_buff to place the data into + * @size: size of buffer to be added * * This function will add the data contained in rx_buffer->page to the skb. - * This is done either through a direct copy if the data in the buffer is - * less than the skb header size, otherwise it will just attach the page as - * a frag to the skb. - * - * The function will then update the page offset if necessary and return - * true if the buffer can be reused by the adapter. **/ -static bool igb_add_rx_frag(struct igb_ring *rx_ring, +static void igb_add_rx_frag(struct igb_ring *rx_ring, struct igb_rx_buffer *rx_buffer, - unsigned int size, - union e1000_adv_rx_desc *rx_desc, - struct sk_buff *skb) + struct sk_buff *skb, + unsigned int size) { - struct page *page = rx_buffer->page; - unsigned char *va = page_address(page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) - unsigned int truesize = IGB_RX_BUFSZ; + unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = ring_uses_build_skb(rx_ring) ? + SKB_DATA_ALIGN(IGB_SKB_PAD + size) : + SKB_DATA_ALIGN(size); +#endif + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, + rx_buffer->page_offset, size, truesize); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif +} + +static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring, + struct igb_rx_buffer *rx_buffer, + union e1000_adv_rx_desc *rx_desc, + unsigned int size) +{ + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; #else unsigned int truesize = SKB_DATA_ALIGN(size); #endif - unsigned int pull_len; + unsigned int headlen; + struct sk_buff *skb; + + /* prefetch first cache line of first page */ + prefetch(va); +#if L1_CACHE_BYTES < 128 + prefetch(va + L1_CACHE_BYTES); +#endif - if (unlikely(skb_is_nonlinear(skb))) - goto add_tail_frag; + /* allocate a skb to store the frags */ + skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN); + if (unlikely(!skb)) + return NULL; if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) { igb_ptp_rx_pktstamp(rx_ring->q_vector, va, skb); @@ -6907,95 +7220,73 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring, size -= IGB_TS_HDR_LEN; } - if (likely(size <= IGB_RX_HDR_LEN)) { - memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); - - /* page is not reserved, we can reuse buffer as-is */ - if (likely(!igb_page_is_reserved(page))) - return true; - - /* this page cannot be reused so discard it */ - return false; - } - - /* we need the header to contain the greater of either ETH_HLEN or - * 60 bytes if the skb->len is less than 60 for skb_pad. - */ - pull_len = eth_get_headlen(va, IGB_RX_HDR_LEN); + /* Determine available headroom for copy */ + headlen = size; + if (headlen > IGB_RX_HDR_LEN) + headlen = eth_get_headlen(va, IGB_RX_HDR_LEN); /* align pull length to size of long to optimize memcpy performance */ - memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long))); + memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); /* update all of the pointers */ - va += pull_len; - size -= pull_len; - -add_tail_frag: - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, - (unsigned long)va & ~PAGE_MASK, size, truesize); + size -= headlen; + if (size) { + skb_add_rx_frag(skb, 0, rx_buffer->page, + (va + headlen) - page_address(rx_buffer->page), + size, truesize); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif + } else { + rx_buffer->pagecnt_bias++; + } - return igb_can_reuse_rx_page(rx_buffer, page, truesize); + return skb; } -static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring, - union e1000_adv_rx_desc *rx_desc, - struct sk_buff *skb) +static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, + struct igb_rx_buffer *rx_buffer, + union e1000_adv_rx_desc *rx_desc, + unsigned int size) { - unsigned int size = le16_to_cpu(rx_desc->wb.upper.length); - struct igb_rx_buffer *rx_buffer; - struct page *page; - - rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; - page = rx_buffer->page; - prefetchw(page); - - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, - rx_buffer->dma, - rx_buffer->page_offset, - size, - DMA_FROM_DEVICE); - - if (likely(!skb)) { - void *page_addr = page_address(page) + - rx_buffer->page_offset; + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + + SKB_DATA_ALIGN(IGB_SKB_PAD + size); +#endif + struct sk_buff *skb; - /* prefetch first cache line of first page */ - prefetch(page_addr); + /* prefetch first cache line of first page */ + prefetch(va); #if L1_CACHE_BYTES < 128 - prefetch(page_addr + L1_CACHE_BYTES); + prefetch(va + L1_CACHE_BYTES); #endif - /* allocate a skb to store the frags */ - skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN); - if (unlikely(!skb)) { - rx_ring->rx_stats.alloc_failed++; - return NULL; - } + /* build an skb around the page buffer */ + skb = build_skb(va - IGB_SKB_PAD, truesize); + if (unlikely(!skb)) + return NULL; - /* we will be copying header into skb->data in - * pskb_may_pull so it is in our interest to prefetch - * it now to avoid a possible cache miss - */ - prefetchw(skb->data); - } + /* update pointers within the skb to store the data */ + skb_reserve(skb, IGB_SKB_PAD); + __skb_put(skb, size); - /* pull page into skb */ - if (igb_add_rx_frag(rx_ring, rx_buffer, size, rx_desc, skb)) { - /* hand second half of page back to the ring */ - igb_reuse_rx_page(rx_ring, rx_buffer); - } else { - /* We are not reusing the buffer so unmap it and free - * any references we are holding to it - */ - dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, - PAGE_SIZE, DMA_FROM_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); - __page_frag_cache_drain(page, rx_buffer->pagecnt_bias); + /* pull timestamp out of packet data */ + if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { + igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb); + __skb_pull(skb, IGB_TS_HDR_LEN); } - /* clear contents of rx_buffer */ - rx_buffer->page = NULL; + /* update buffer offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif return skb; } @@ -7154,6 +7445,47 @@ static void igb_process_skb_fields(struct igb_ring *rx_ring, skb->protocol = eth_type_trans(skb, rx_ring->netdev); } +static struct igb_rx_buffer *igb_get_rx_buffer(struct igb_ring *rx_ring, + const unsigned int size) +{ + struct igb_rx_buffer *rx_buffer; + + rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + prefetchw(rx_buffer->page); + + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + size, + DMA_FROM_DEVICE); + + rx_buffer->pagecnt_bias--; + + return rx_buffer; +} + +static void igb_put_rx_buffer(struct igb_ring *rx_ring, + struct igb_rx_buffer *rx_buffer) +{ + if (igb_can_reuse_rx_page(rx_buffer)) { + /* hand second half of page back to the ring */ + igb_reuse_rx_page(rx_ring, rx_buffer); + } else { + /* We are not reusing the buffer so unmap it and free + * any references we are holding to it + */ + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + igb_rx_pg_size(rx_ring), DMA_FROM_DEVICE, + IGB_RX_DMA_ATTR); + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); + } + + /* clear contents of rx_buffer */ + rx_buffer->page = NULL; +} + static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) { struct igb_ring *rx_ring = q_vector->rx.ring; @@ -7163,6 +7495,8 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) while (likely(total_packets < budget)) { union e1000_adv_rx_desc *rx_desc; + struct igb_rx_buffer *rx_buffer; + unsigned int size; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IGB_RX_BUFFER_WRITE) { @@ -7171,8 +7505,8 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) } rx_desc = IGB_RX_DESC(rx_ring, rx_ring->next_to_clean); - - if (!rx_desc->wb.upper.status_error) + size = le16_to_cpu(rx_desc->wb.upper.length); + if (!size) break; /* This memory barrier is needed to keep us from reading @@ -7181,13 +7515,25 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) */ dma_rmb(); + rx_buffer = igb_get_rx_buffer(rx_ring, size); + /* retrieve a buffer from the ring */ - skb = igb_fetch_rx_buffer(rx_ring, rx_desc, skb); + if (skb) + igb_add_rx_frag(rx_ring, rx_buffer, skb, size); + else if (ring_uses_build_skb(rx_ring)) + skb = igb_build_skb(rx_ring, rx_buffer, rx_desc, size); + else + skb = igb_construct_skb(rx_ring, rx_buffer, + rx_desc, size); /* exit if we failed to retrieve a buffer */ - if (!skb) + if (!skb) { + rx_ring->rx_stats.alloc_failed++; + rx_buffer->pagecnt_bias++; break; + } + igb_put_rx_buffer(rx_ring, rx_buffer); cleaned_count++; /* fetch next buffer in frame if non-eop */ @@ -7231,6 +7577,11 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) return total_packets; } +static inline unsigned int igb_rx_offset(struct igb_ring *rx_ring) +{ + return ring_uses_build_skb(rx_ring) ? IGB_SKB_PAD : 0; +} + static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, struct igb_rx_buffer *bi) { @@ -7242,21 +7593,23 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, return true; /* alloc new page for storage */ - page = dev_alloc_page(); + page = dev_alloc_pages(igb_rx_pg_order(rx_ring)); if (unlikely(!page)) { rx_ring->rx_stats.alloc_failed++; return false; } /* map page for use */ - dma = dma_map_page_attrs(rx_ring->dev, page, 0, PAGE_SIZE, - DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC); + dma = dma_map_page_attrs(rx_ring->dev, page, 0, + igb_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IGB_RX_DMA_ATTR); /* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use */ if (dma_mapping_error(rx_ring->dev, dma)) { - __free_page(page); + __free_pages(page, igb_rx_pg_order(rx_ring)); rx_ring->rx_stats.alloc_failed++; return false; @@ -7264,7 +7617,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, bi->dma = dma; bi->page = page; - bi->page_offset = 0; + bi->page_offset = igb_rx_offset(rx_ring); bi->pagecnt_bias = 1; return true; @@ -7279,6 +7632,7 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) union e1000_adv_rx_desc *rx_desc; struct igb_rx_buffer *bi; u16 i = rx_ring->next_to_use; + u16 bufsz; /* nothing to do */ if (!cleaned_count) @@ -7288,14 +7642,15 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) bi = &rx_ring->rx_buffer_info[i]; i -= rx_ring->count; + bufsz = igb_rx_bufsz(rx_ring); + do { if (!igb_alloc_mapped_page(rx_ring, bi)) break; /* sync the buffer for use by the device */ dma_sync_single_range_for_device(rx_ring->dev, bi->dma, - bi->page_offset, - IGB_RX_BUFSZ, + bi->page_offset, bufsz, DMA_FROM_DEVICE); /* Refresh the desc even if buffer_addrs didn't change @@ -7312,8 +7667,8 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) i -= rx_ring->count; } - /* clear the status bits for the next_to_use descriptor */ - rx_desc->wb.upper.status_error = 0; + /* clear the length for the next_to_use descriptor */ + rx_desc->wb.upper.length = 0; cleaned_count--; } while (cleaned_count); @@ -7630,6 +7985,36 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake, return 0; } +static void igb_deliver_wake_packet(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + struct sk_buff *skb; + u32 wupl; + + wupl = rd32(E1000_WUPL) & E1000_WUPL_MASK; + + /* WUPM stores only the first 128 bytes of the wake packet. + * Read the packet only if we have the whole thing. + */ + if ((wupl == 0) || (wupl > E1000_WUPM_BYTES)) + return; + + skb = netdev_alloc_skb_ip_align(netdev, E1000_WUPM_BYTES); + if (!skb) + return; + + skb_put(skb, wupl); + + /* Ensure reads are 32-bit aligned */ + wupl = roundup(wupl, 4); + + memcpy_fromio(skb->data, hw->hw_addr + E1000_WUPM_REG(0), wupl); + + skb->protocol = eth_type_trans(skb, netdev); + netif_rx(skb); +} + #ifdef CONFIG_PM #ifdef CONFIG_PM_SLEEP static int igb_suspend(struct device *dev) @@ -7659,7 +8044,7 @@ static int igb_resume(struct device *dev) struct net_device *netdev = pci_get_drvdata(pdev); struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; - u32 err; + u32 err, val; pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); @@ -7690,6 +8075,10 @@ static int igb_resume(struct device *dev) */ igb_get_hw_control(adapter); + val = rd32(E1000_WUS); + if (val & WAKE_PKT_WUS) + igb_deliver_wake_packet(netdev); + wr32(E1000_WUS, ~0); rtnl_lock(); @@ -7948,11 +8337,16 @@ static void igb_io_resume(struct pci_dev *pdev) igb_get_hw_control(adapter); } -static void igb_rar_set_qsel(struct igb_adapter *adapter, u8 *addr, u32 index, - u8 qsel) +/** + * igb_rar_set_index - Sync RAL[index] and RAH[index] registers with MAC table + * @adapter: Pointer to adapter structure + * @index: Index of the RAR entry which need to be synced with MAC table + **/ +static void igb_rar_set_index(struct igb_adapter *adapter, u32 index) { struct e1000_hw *hw = &adapter->hw; u32 rar_low, rar_high; + u8 *addr = adapter->mac_table[index].addr; /* HW expects these to be in network order when they are plugged * into the registers which are little endian. In order to guarantee @@ -7963,12 +8357,16 @@ static void igb_rar_set_qsel(struct igb_adapter *adapter, u8 *addr, u32 index, rar_high = le16_to_cpup((__le16 *)(addr + 4)); /* Indicate to hardware the Address is Valid. */ - rar_high |= E1000_RAH_AV; + if (adapter->mac_table[index].state & IGB_MAC_STATE_IN_USE) { + rar_high |= E1000_RAH_AV; - if (hw->mac.type == e1000_82575) - rar_high |= E1000_RAH_POOL_1 * qsel; - else - rar_high |= E1000_RAH_POOL_1 << qsel; + if (hw->mac.type == e1000_82575) + rar_high |= E1000_RAH_POOL_1 * + adapter->mac_table[index].queue; + else + rar_high |= E1000_RAH_POOL_1 << + adapter->mac_table[index].queue; + } wr32(E1000_RAL(index), rar_low); wrfl(); @@ -7984,10 +8382,13 @@ static int igb_set_vf_mac(struct igb_adapter *adapter, * towards the first, as a result a collision should not be possible */ int rar_entry = hw->mac.rar_entry_count - (vf + 1); + unsigned char *vf_mac_addr = adapter->vf_data[vf].vf_mac_addresses; - memcpy(adapter->vf_data[vf].vf_mac_addresses, mac_addr, ETH_ALEN); - - igb_rar_set_qsel(adapter, mac_addr, rar_entry, vf); + ether_addr_copy(vf_mac_addr, mac_addr); + ether_addr_copy(adapter->mac_table[rar_entry].addr, mac_addr); + adapter->mac_table[rar_entry].queue = vf; + adapter->mac_table[rar_entry].state |= IGB_MAC_STATE_IN_USE; + igb_rar_set_index(adapter, rar_entry); return 0; } diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index c4477552ce9e..7a3fd4d74592 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -764,8 +764,7 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter) * incoming frame. The value is stored in little endian format starting on * byte 8. **/ -void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, - unsigned char *va, +void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, struct sk_buff *skb) { __le64 *regval = (__le64 *)va; diff --git a/drivers/net/ethernet/intel/igbvf/ethtool.c b/drivers/net/ethernet/intel/igbvf/ethtool.c index 8dea1b1367ef..34faa113a8a0 100644 --- a/drivers/net/ethernet/intel/igbvf/ethtool.c +++ b/drivers/net/ethernet/intel/igbvf/ethtool.c @@ -71,45 +71,45 @@ static const char igbvf_gstrings_test[][ETH_GSTRING_LEN] = { #define IGBVF_TEST_LEN ARRAY_SIZE(igbvf_gstrings_test) -static int igbvf_get_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int igbvf_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct igbvf_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; u32 status; - ecmd->supported = SUPPORTED_1000baseT_Full; + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_add_link_mode(cmd, supported, 1000baseT_Full); + ethtool_link_ksettings_zero_link_mode(cmd, advertising); + ethtool_link_ksettings_add_link_mode(cmd, advertising, 1000baseT_Full); - ecmd->advertising = ADVERTISED_1000baseT_Full; - - ecmd->port = -1; - ecmd->transceiver = XCVR_DUMMY1; + cmd->base.port = -1; status = er32(STATUS); if (status & E1000_STATUS_LU) { if (status & E1000_STATUS_SPEED_1000) - ethtool_cmd_speed_set(ecmd, SPEED_1000); + cmd->base.speed = SPEED_1000; else if (status & E1000_STATUS_SPEED_100) - ethtool_cmd_speed_set(ecmd, SPEED_100); + cmd->base.speed = SPEED_100; else - ethtool_cmd_speed_set(ecmd, SPEED_10); + cmd->base.speed = SPEED_10; if (status & E1000_STATUS_FD) - ecmd->duplex = DUPLEX_FULL; + cmd->base.duplex = DUPLEX_FULL; else - ecmd->duplex = DUPLEX_HALF; + cmd->base.duplex = DUPLEX_HALF; } else { - ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN); - ecmd->duplex = DUPLEX_UNKNOWN; + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; } - ecmd->autoneg = AUTONEG_DISABLE; + cmd->base.autoneg = AUTONEG_DISABLE; return 0; } -static int igbvf_set_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int igbvf_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *cmd) { return -EOPNOTSUPP; } @@ -443,8 +443,6 @@ static void igbvf_get_strings(struct net_device *netdev, u32 stringset, } static const struct ethtool_ops igbvf_ethtool_ops = { - .get_settings = igbvf_get_settings, - .set_settings = igbvf_set_settings, .get_drvinfo = igbvf_get_drvinfo, .get_regs_len = igbvf_get_regs_len, .get_regs = igbvf_get_regs, @@ -467,6 +465,8 @@ static const struct ethtool_ops igbvf_ethtool_ops = { .get_ethtool_stats = igbvf_get_ethtool_stats, .get_coalesce = igbvf_get_coalesce, .set_coalesce = igbvf_set_coalesce, + .get_link_ksettings = igbvf_get_link_ksettings, + .set_link_ksettings = igbvf_set_link_ksettings, }; void igbvf_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/intel/igbvf/igbvf.h b/drivers/net/ethernet/intel/igbvf/igbvf.h index 6f4290d6dc9f..bf69f01f8467 100644 --- a/drivers/net/ethernet/intel/igbvf/igbvf.h +++ b/drivers/net/ethernet/intel/igbvf/igbvf.h @@ -101,6 +101,8 @@ enum latency_range { #define IGBVF_MNG_VLAN_NONE (-1) +#define IGBVF_MAX_MAC_FILTERS 3 + /* Number of packet split data buffers (not including the header buffer) */ #define PS_PAGE_BUFFERS (MAX_PS_BUFFERS - 1) @@ -241,7 +243,6 @@ struct igbvf_adapter { /* OS defined structs */ struct net_device *netdev; struct pci_dev *pdev; - struct net_device_stats net_stats; spinlock_t stats_lock; /* prevent concurrent stats updates */ /* structs defined in e1000_hw.h */ diff --git a/drivers/net/ethernet/intel/igbvf/mbx.h b/drivers/net/ethernet/intel/igbvf/mbx.h index f800bf8eedae..30d58c4a444e 100644 --- a/drivers/net/ethernet/intel/igbvf/mbx.h +++ b/drivers/net/ethernet/intel/igbvf/mbx.h @@ -62,6 +62,10 @@ #define E1000_VF_RESET 0x01 /* VF requests reset */ #define E1000_VF_SET_MAC_ADDR 0x02 /* VF requests PF to set MAC addr */ +/* VF requests PF to clear all unicast MAC filters */ +#define E1000_VF_MAC_FILTER_CLR (0x01 << E1000_VT_MSGINFO_SHIFT) +/* VF requests PF to add unicast MAC filter */ +#define E1000_VF_MAC_FILTER_ADD (0x02 << E1000_VT_MSGINFO_SHIFT) #define E1000_VF_SET_MULTICAST 0x03 /* VF requests PF to set MC addr */ #define E1000_VF_SET_VLAN 0x04 /* VF requests PF to set VLAN */ #define E1000_VF_SET_LPE 0x05 /* VF requests PF to set VMOLR.LPE */ diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 839ba110f7fb..1b9cbbe88f6f 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -400,8 +400,8 @@ next_desc: adapter->total_rx_packets += total_packets; adapter->total_rx_bytes += total_bytes; - adapter->net_stats.rx_bytes += total_bytes; - adapter->net_stats.rx_packets += total_packets; + netdev->stats.rx_bytes += total_bytes; + netdev->stats.rx_packets += total_packets; return cleaned; } @@ -864,8 +864,8 @@ static bool igbvf_clean_tx_irq(struct igbvf_ring *tx_ring) } } - adapter->net_stats.tx_bytes += total_bytes; - adapter->net_stats.tx_packets += total_packets; + netdev->stats.tx_bytes += total_bytes; + netdev->stats.tx_packets += total_packets; return count < tx_ring->count; } @@ -1433,12 +1433,52 @@ static void igbvf_set_multi(struct net_device *netdev) } /** + * igbvf_set_uni - Configure unicast MAC filters + * @netdev: network interface device structure + * + * This routine is responsible for configuring the hardware for proper + * unicast filters. + **/ +static int igbvf_set_uni(struct net_device *netdev) +{ + struct igbvf_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + + if (netdev_uc_count(netdev) > IGBVF_MAX_MAC_FILTERS) { + pr_err("Too many unicast filters - No Space\n"); + return -ENOSPC; + } + + /* Clear all unicast MAC filters */ + hw->mac.ops.set_uc_addr(hw, E1000_VF_MAC_FILTER_CLR, NULL); + + if (!netdev_uc_empty(netdev)) { + struct netdev_hw_addr *ha; + + /* Add MAC filters one by one */ + netdev_for_each_uc_addr(ha, netdev) { + hw->mac.ops.set_uc_addr(hw, E1000_VF_MAC_FILTER_ADD, + ha->addr); + udelay(200); + } + } + + return 0; +} + +static void igbvf_set_rx_mode(struct net_device *netdev) +{ + igbvf_set_multi(netdev); + igbvf_set_uni(netdev); +} + +/** * igbvf_configure - configure the hardware for Rx and Tx * @adapter: private board structure **/ static void igbvf_configure(struct igbvf_adapter *adapter) { - igbvf_set_multi(adapter->netdev); + igbvf_set_rx_mode(adapter->netdev); igbvf_restore_vlan(adapter); @@ -1798,7 +1838,7 @@ void igbvf_update_stats(struct igbvf_adapter *adapter) UPDATE_VF_COUNTER(VFGPRLBC, gprlbc); /* Fill out the OS statistics structure */ - adapter->net_stats.multicast = adapter->stats.mprc; + adapter->netdev->stats.multicast = adapter->stats.mprc; } static void igbvf_print_link_info(struct igbvf_adapter *adapter) @@ -2334,21 +2374,6 @@ static void igbvf_reset_task(struct work_struct *work) } /** - * igbvf_get_stats - Get System Network Statistics - * @netdev: network interface device structure - * - * Returns the address of the device statistics structure. - * The statistics are actually updated from the timer callback. - **/ -static struct net_device_stats *igbvf_get_stats(struct net_device *netdev) -{ - struct igbvf_adapter *adapter = netdev_priv(netdev); - - /* only return the current stats */ - return &adapter->net_stats; -} - -/** * igbvf_change_mtu - Change the Maximum Transfer Unit * @netdev: network interface device structure * @new_mtu: new value for maximum frame size @@ -2635,8 +2660,7 @@ static const struct net_device_ops igbvf_netdev_ops = { .ndo_open = igbvf_open, .ndo_stop = igbvf_close, .ndo_start_xmit = igbvf_xmit_frame, - .ndo_get_stats = igbvf_get_stats, - .ndo_set_rx_mode = igbvf_set_multi, + .ndo_set_rx_mode = igbvf_set_rx_mode, .ndo_set_mac_address = igbvf_set_mac, .ndo_change_mtu = igbvf_change_mtu, .ndo_do_ioctl = igbvf_ioctl, diff --git a/drivers/net/ethernet/intel/igbvf/vf.c b/drivers/net/ethernet/intel/igbvf/vf.c index 335ba6642145..528be116184e 100644 --- a/drivers/net/ethernet/intel/igbvf/vf.c +++ b/drivers/net/ethernet/intel/igbvf/vf.c @@ -36,6 +36,7 @@ static void e1000_update_mc_addr_list_vf(struct e1000_hw *hw, u8 *, u32, u32, u32); static void e1000_rar_set_vf(struct e1000_hw *, u8 *, u32); static s32 e1000_read_mac_addr_vf(struct e1000_hw *); +static s32 e1000_set_uc_addr_vf(struct e1000_hw *hw, u32 subcmd, u8 *addr); static s32 e1000_set_vfta_vf(struct e1000_hw *, u16, bool); /** @@ -66,6 +67,8 @@ static s32 e1000_init_mac_params_vf(struct e1000_hw *hw) mac->ops.rar_set = e1000_rar_set_vf; /* read mac address */ mac->ops.read_mac_addr = e1000_read_mac_addr_vf; + /* set mac filter */ + mac->ops.set_uc_addr = e1000_set_uc_addr_vf; /* set vlan filter table array */ mac->ops.set_vfta = e1000_set_vfta_vf; @@ -338,6 +341,44 @@ static s32 e1000_read_mac_addr_vf(struct e1000_hw *hw) } /** + * e1000_set_uc_addr_vf - Set or clear unicast filters + * @hw: pointer to the HW structure + * @sub_cmd: add or clear filters + * @addr: pointer to the filter MAC address + **/ +static s32 e1000_set_uc_addr_vf(struct e1000_hw *hw, u32 sub_cmd, u8 *addr) +{ + struct e1000_mbx_info *mbx = &hw->mbx; + u32 msgbuf[3], msgbuf_chk; + u8 *msg_addr = (u8 *)(&msgbuf[1]); + s32 ret_val; + + memset(msgbuf, 0, sizeof(msgbuf)); + msgbuf[0] |= sub_cmd; + msgbuf[0] |= E1000_VF_SET_MAC_ADDR; + msgbuf_chk = msgbuf[0]; + + if (addr) + memcpy(msg_addr, addr, ETH_ALEN); + + ret_val = mbx->ops.write_posted(hw, msgbuf, 3); + + if (!ret_val) + ret_val = mbx->ops.read_posted(hw, msgbuf, 3); + + msgbuf[0] &= ~E1000_VT_MSGTYPE_CTS; + + if (!ret_val) { + msgbuf[0] &= ~E1000_VT_MSGTYPE_CTS; + + if (msgbuf[0] == (msgbuf_chk | E1000_VT_MSGTYPE_NACK)) + return -ENOSPC; + } + + return ret_val; +} + +/** * e1000_check_for_link_vf - Check for link for a virtual interface * @hw: pointer to the HW structure * diff --git a/drivers/net/ethernet/intel/igbvf/vf.h b/drivers/net/ethernet/intel/igbvf/vf.h index f00a41d9a1ca..4cf78b0dec50 100644 --- a/drivers/net/ethernet/intel/igbvf/vf.h +++ b/drivers/net/ethernet/intel/igbvf/vf.h @@ -179,6 +179,7 @@ struct e1000_mac_operations { s32 (*get_bus_info)(struct e1000_hw *); s32 (*get_link_up_info)(struct e1000_hw *, u16 *, u16 *); void (*update_mc_addr_list)(struct e1000_hw *, u8 *, u32, u32, u32); + s32 (*set_uc_addr)(struct e1000_hw *, u32, u8 *); s32 (*reset_hw)(struct e1000_hw *); s32 (*init_hw)(struct e1000_hw *); s32 (*setup_link)(struct e1000_hw *); diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c index e5d72559cca9..d10a0d242dda 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c @@ -94,24 +94,30 @@ static struct ixgb_stats ixgb_gstrings_stats[] = { #define IXGB_STATS_LEN ARRAY_SIZE(ixgb_gstrings_stats) static int -ixgb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) +ixgb_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct ixgb_adapter *adapter = netdev_priv(netdev); - ecmd->supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE); - ecmd->advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_FIBRE); - ecmd->port = PORT_FIBRE; - ecmd->transceiver = XCVR_EXTERNAL; + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_add_link_mode(cmd, supported, 10000baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE); + + ethtool_link_ksettings_zero_link_mode(cmd, advertising); + ethtool_link_ksettings_add_link_mode(cmd, advertising, 10000baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE); + + cmd->base.port = PORT_FIBRE; if (netif_carrier_ok(adapter->netdev)) { - ethtool_cmd_speed_set(ecmd, SPEED_10000); - ecmd->duplex = DUPLEX_FULL; + cmd->base.speed = SPEED_10000; + cmd->base.duplex = DUPLEX_FULL; } else { - ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN); - ecmd->duplex = DUPLEX_UNKNOWN; + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; } - ecmd->autoneg = AUTONEG_DISABLE; + cmd->base.autoneg = AUTONEG_DISABLE; return 0; } @@ -126,13 +132,14 @@ void ixgb_set_speed_duplex(struct net_device *netdev) } static int -ixgb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) +ixgb_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *cmd) { struct ixgb_adapter *adapter = netdev_priv(netdev); - u32 speed = ethtool_cmd_speed(ecmd); + u32 speed = cmd->base.speed; - if (ecmd->autoneg == AUTONEG_ENABLE || - (speed + ecmd->duplex != SPEED_10000 + DUPLEX_FULL)) + if (cmd->base.autoneg == AUTONEG_ENABLE || + (speed + cmd->base.duplex != SPEED_10000 + DUPLEX_FULL)) return -EINVAL; if (netif_running(adapter->netdev)) { @@ -630,8 +637,6 @@ ixgb_get_strings(struct net_device *netdev, u32 stringset, u8 *data) } static const struct ethtool_ops ixgb_ethtool_ops = { - .get_settings = ixgb_get_settings, - .set_settings = ixgb_set_settings, .get_drvinfo = ixgb_get_drvinfo, .get_regs_len = ixgb_get_regs_len, .get_regs = ixgb_get_regs, @@ -649,6 +654,8 @@ static const struct ethtool_ops ixgb_ethtool_ops = { .set_phys_id = ixgb_set_phys_id, .get_sset_count = ixgb_get_sset_count, .get_ethtool_stats = ixgb_get_ethtool_stats, + .get_link_ksettings = ixgb_get_link_ksettings, + .set_link_ksettings = ixgb_set_link_ksettings, }; void ixgb_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index fbd220d137b3..5a713199653c 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -86,7 +86,6 @@ static void ixgb_set_multi(struct net_device *netdev); static void ixgb_watchdog(unsigned long data); static netdev_tx_t ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev); -static struct net_device_stats *ixgb_get_stats(struct net_device *netdev); static int ixgb_change_mtu(struct net_device *netdev, int new_mtu); static int ixgb_set_mac(struct net_device *netdev, void *p); static irqreturn_t ixgb_intr(int irq, void *data); @@ -367,7 +366,6 @@ static const struct net_device_ops ixgb_netdev_ops = { .ndo_open = ixgb_open, .ndo_stop = ixgb_close, .ndo_start_xmit = ixgb_xmit_frame, - .ndo_get_stats = ixgb_get_stats, .ndo_set_rx_mode = ixgb_set_multi, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = ixgb_set_mac, @@ -1597,20 +1595,6 @@ ixgb_tx_timeout_task(struct work_struct *work) } /** - * ixgb_get_stats - Get System Network Statistics - * @netdev: network interface device structure - * - * Returns the address of the device statistics structure. - * The statistics are actually updated from the timer callback. - **/ - -static struct net_device_stats * -ixgb_get_stats(struct net_device *netdev) -{ - return &netdev->stats; -} - -/** * ixgb_change_mtu - Change the Maximum Transfer Unit * @netdev: network interface device structure * @new_mtu: new value for maximum frame size diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index b1ecc2627a5a..76263762bea1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -86,17 +86,62 @@ /* Supported Rx Buffer Sizes */ #define IXGBE_RXBUFFER_256 256 /* Used for skb receive header */ +#define IXGBE_RXBUFFER_1536 1536 #define IXGBE_RXBUFFER_2K 2048 #define IXGBE_RXBUFFER_3K 3072 #define IXGBE_RXBUFFER_4K 4096 #define IXGBE_MAX_RXBUFFER 16384 /* largest size for a single descriptor */ -#define IXGBE_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +/* Attempt to maximize the headroom available for incoming frames. We + * use a 2K buffer for receives and need 1536/1534 to store the data for + * the frame. This leaves us with 512 bytes of room. From that we need + * to deduct the space needed for the shared info and the padding needed + * to IP align the frame. + * + * Note: For cache line sizes 256 or larger this value is going to end + * up negative. In these cases we should fall back to the 3K + * buffers. + */ #if (PAGE_SIZE < 8192) -#define IXGBE_MAX_FRAME_BUILD_SKB \ - (SKB_WITH_OVERHEAD(IXGBE_RXBUFFER_2K) - IXGBE_SKB_PAD) +#define IXGBE_MAX_2K_FRAME_BUILD_SKB (IXGBE_RXBUFFER_1536 - NET_IP_ALIGN) +#define IXGBE_2K_TOO_SMALL_WITH_PADDING \ +((NET_SKB_PAD + IXGBE_RXBUFFER_1536) > SKB_WITH_OVERHEAD(IXGBE_RXBUFFER_2K)) + +static inline int ixgbe_compute_pad(int rx_buf_len) +{ + int page_size, pad_size; + + page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2); + pad_size = SKB_WITH_OVERHEAD(page_size) - rx_buf_len; + + return pad_size; +} + +static inline int ixgbe_skb_pad(void) +{ + int rx_buf_len; + + /* If a 2K buffer cannot handle a standard Ethernet frame then + * optimize padding for a 3K buffer instead of a 1.5K buffer. + * + * For a 3K buffer we need to add enough padding to allow for + * tailroom due to NET_IP_ALIGN possibly shifting us out of + * cache-line alignment. + */ + if (IXGBE_2K_TOO_SMALL_WITH_PADDING) + rx_buf_len = IXGBE_RXBUFFER_3K + SKB_DATA_ALIGN(NET_IP_ALIGN); + else + rx_buf_len = IXGBE_RXBUFFER_1536; + + /* if needed make room for NET_IP_ALIGN */ + rx_buf_len -= NET_IP_ALIGN; + + return ixgbe_compute_pad(rx_buf_len); +} + +#define IXGBE_SKB_PAD ixgbe_skb_pad() #else -#define IXGBE_MAX_FRAME_BUILD_SKB IXGBE_RXBUFFER_2K +#define IXGBE_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) #endif /* @@ -190,7 +235,11 @@ struct vf_macvlans { struct ixgbe_tx_buffer { union ixgbe_adv_tx_desc *next_to_watch; unsigned long time_stamp; - struct sk_buff *skb; + union { + struct sk_buff *skb; + /* XDP uses address ptr on irq_clean */ + void *data; + }; unsigned int bytecount; unsigned short gso_segs; __be16 protocol; @@ -243,6 +292,7 @@ enum ixgbe_ring_state_t { __IXGBE_TX_XPS_INIT_DONE, __IXGBE_TX_DETECT_HANG, __IXGBE_HANG_CHECK_ARMED, + __IXGBE_TX_XDP_RING, }; #define ring_uses_build_skb(ring) \ @@ -269,10 +319,17 @@ struct ixgbe_fwd_adapter { set_bit(__IXGBE_RX_RSC_ENABLED, &(ring)->state) #define clear_ring_rsc_enabled(ring) \ clear_bit(__IXGBE_RX_RSC_ENABLED, &(ring)->state) +#define ring_is_xdp(ring) \ + test_bit(__IXGBE_TX_XDP_RING, &(ring)->state) +#define set_ring_xdp(ring) \ + set_bit(__IXGBE_TX_XDP_RING, &(ring)->state) +#define clear_ring_xdp(ring) \ + clear_bit(__IXGBE_TX_XDP_RING, &(ring)->state) struct ixgbe_ring { struct ixgbe_ring *next; /* pointer to next ring in q_vector */ struct ixgbe_q_vector *q_vector; /* backpointer to host q_vector */ struct net_device *netdev; /* netdev ring belongs to */ + struct bpf_prog *xdp_prog; struct device *dev; /* device for DMA mapping */ struct ixgbe_fwd_adapter *l2_accel_priv; void *desc; /* descriptor ring memory */ @@ -334,6 +391,7 @@ enum ixgbe_ring_f_enum { #define IXGBE_MAX_FCOE_INDICES 8 #define MAX_RX_QUEUES (IXGBE_MAX_FDIR_INDICES + 1) #define MAX_TX_QUEUES (IXGBE_MAX_FDIR_INDICES + 1) +#define MAX_XDP_QUEUES (IXGBE_MAX_FDIR_INDICES + 1) #define IXGBE_MAX_L2A_QUEUES 4 #define IXGBE_BAD_L2A_QUEUE 3 #define IXGBE_MAX_MACVLANS 31 @@ -361,7 +419,7 @@ static inline unsigned int ixgbe_rx_bufsz(struct ixgbe_ring *ring) return IXGBE_RXBUFFER_3K; #if (PAGE_SIZE < 8192) if (ring_uses_build_skb(ring)) - return IXGBE_MAX_FRAME_BUILD_SKB; + return IXGBE_MAX_2K_FRAME_BUILD_SKB; #endif return IXGBE_RXBUFFER_2K; } @@ -510,6 +568,7 @@ struct ixgbe_adapter { unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; /* OS defined structs */ struct net_device *netdev; + struct bpf_prog *xdp_prog; struct pci_dev *pdev; unsigned long state; @@ -576,6 +635,10 @@ struct ixgbe_adapter { __be16 vxlan_port; __be16 geneve_port; + /* XDP */ + int num_xdp_queues; + struct ixgbe_ring *xdp_ring[MAX_XDP_QUEUES]; + /* TX */ struct ixgbe_ring *tx_ring[MAX_TX_QUEUES] ____cacheline_aligned_in_smp; @@ -622,6 +685,7 @@ struct ixgbe_adapter { u64 tx_busy; unsigned int tx_ring_count; + unsigned int xdp_ring_count; unsigned int rx_ring_count; u32 link_speed; @@ -705,7 +769,7 @@ struct ixgbe_adapter { u8 rss_indir_tbl[IXGBE_MAX_RETA_ENTRIES]; #define IXGBE_RSS_KEY_SIZE 40 /* size of RSS Hash Key in bytes */ - u32 rss_key[IXGBE_RSS_KEY_SIZE / sizeof(u32)]; + u32 *rss_key; }; static inline u8 ixgbe_max_rss_indices(struct ixgbe_adapter *adapter) @@ -762,6 +826,7 @@ enum ixgbe_boards { board_X540, board_X550, board_X550EM_x, + board_x550em_x_fw, board_x550em_a, board_x550em_a_fw, }; @@ -771,6 +836,7 @@ extern const struct ixgbe_info ixgbe_82599_info; extern const struct ixgbe_info ixgbe_X540_info; extern const struct ixgbe_info ixgbe_X550_info; extern const struct ixgbe_info ixgbe_X550EM_x_info; +extern const struct ixgbe_info ixgbe_x550em_x_fw_info; extern const struct ixgbe_info ixgbe_x550em_a_info; extern const struct ixgbe_info ixgbe_x550em_a_fw_info; #ifdef CONFIG_IXGBE_DCB @@ -790,7 +856,7 @@ void ixgbe_down(struct ixgbe_adapter *adapter); void ixgbe_reinit_locked(struct ixgbe_adapter *adapter); void ixgbe_reset(struct ixgbe_adapter *adapter); void ixgbe_set_ethtool_ops(struct net_device *netdev); -int ixgbe_setup_rx_resources(struct ixgbe_ring *); +int ixgbe_setup_rx_resources(struct ixgbe_adapter *, struct ixgbe_ring *); int ixgbe_setup_tx_resources(struct ixgbe_ring *); void ixgbe_free_rx_resources(struct ixgbe_ring *); void ixgbe_free_tx_resources(struct ixgbe_ring *); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 90fa5bf23d1b..7e5e336d7dcc 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -179,6 +179,7 @@ static u32 ixgbe_get_supported_10gtypes(struct ixgbe_hw *hw) case IXGBE_DEV_ID_82598_BX: case IXGBE_DEV_ID_82599_KR: case IXGBE_DEV_ID_X550EM_X_KR: + case IXGBE_DEV_ID_X550EM_X_XFI: return SUPPORTED_10000baseKR_Full; default: return SUPPORTED_10000baseKX4_Full | @@ -186,60 +187,62 @@ static u32 ixgbe_get_supported_10gtypes(struct ixgbe_hw *hw) } } -static int ixgbe_get_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int ixgbe_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; ixgbe_link_speed supported_link; bool autoneg = false; + u32 supported, advertising; + + ethtool_convert_link_mode_to_legacy_u32(&supported, + cmd->link_modes.supported); hw->mac.ops.get_link_capabilities(hw, &supported_link, &autoneg); /* set the supported link speeds */ if (supported_link & IXGBE_LINK_SPEED_10GB_FULL) - ecmd->supported |= ixgbe_get_supported_10gtypes(hw); + supported |= ixgbe_get_supported_10gtypes(hw); if (supported_link & IXGBE_LINK_SPEED_1GB_FULL) - ecmd->supported |= (ixgbe_isbackplane(hw->phy.media_type)) ? + supported |= (ixgbe_isbackplane(hw->phy.media_type)) ? SUPPORTED_1000baseKX_Full : SUPPORTED_1000baseT_Full; if (supported_link & IXGBE_LINK_SPEED_100_FULL) - ecmd->supported |= SUPPORTED_100baseT_Full; + supported |= SUPPORTED_100baseT_Full; if (supported_link & IXGBE_LINK_SPEED_10_FULL) - ecmd->supported |= SUPPORTED_10baseT_Full; + supported |= SUPPORTED_10baseT_Full; /* default advertised speed if phy.autoneg_advertised isn't set */ - ecmd->advertising = ecmd->supported; + advertising = supported; /* set the advertised speeds */ if (hw->phy.autoneg_advertised) { - ecmd->advertising = 0; + advertising = 0; if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10_FULL) - ecmd->advertising |= ADVERTISED_10baseT_Full; + advertising |= ADVERTISED_10baseT_Full; if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL) - ecmd->advertising |= ADVERTISED_100baseT_Full; + advertising |= ADVERTISED_100baseT_Full; if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL) - ecmd->advertising |= ecmd->supported & ADVRTSD_MSK_10G; + advertising |= supported & ADVRTSD_MSK_10G; if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) { - if (ecmd->supported & SUPPORTED_1000baseKX_Full) - ecmd->advertising |= ADVERTISED_1000baseKX_Full; + if (supported & SUPPORTED_1000baseKX_Full) + advertising |= ADVERTISED_1000baseKX_Full; else - ecmd->advertising |= ADVERTISED_1000baseT_Full; + advertising |= ADVERTISED_1000baseT_Full; } } else { if (hw->phy.multispeed_fiber && !autoneg) { if (supported_link & IXGBE_LINK_SPEED_10GB_FULL) - ecmd->advertising = ADVERTISED_10000baseT_Full; + advertising = ADVERTISED_10000baseT_Full; } } if (autoneg) { - ecmd->supported |= SUPPORTED_Autoneg; - ecmd->advertising |= ADVERTISED_Autoneg; - ecmd->autoneg = AUTONEG_ENABLE; + supported |= SUPPORTED_Autoneg; + advertising |= ADVERTISED_Autoneg; + cmd->base.autoneg = AUTONEG_ENABLE; } else - ecmd->autoneg = AUTONEG_DISABLE; - - ecmd->transceiver = XCVR_EXTERNAL; + cmd->base.autoneg = AUTONEG_DISABLE; /* Determine the remaining settings based on the PHY type. */ switch (adapter->hw.phy.type) { @@ -248,14 +251,14 @@ static int ixgbe_get_settings(struct net_device *netdev, case ixgbe_phy_x550em_ext_t: case ixgbe_phy_fw: case ixgbe_phy_cu_unknown: - ecmd->supported |= SUPPORTED_TP; - ecmd->advertising |= ADVERTISED_TP; - ecmd->port = PORT_TP; + supported |= SUPPORTED_TP; + advertising |= ADVERTISED_TP; + cmd->base.port = PORT_TP; break; case ixgbe_phy_qt: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_FIBRE; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_FIBRE; break; case ixgbe_phy_nl: case ixgbe_phy_sfp_passive_tyco: @@ -273,9 +276,9 @@ static int ixgbe_get_settings(struct net_device *netdev, case ixgbe_sfp_type_da_cu: case ixgbe_sfp_type_da_cu_core0: case ixgbe_sfp_type_da_cu_core1: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_DA; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_DA; break; case ixgbe_sfp_type_sr: case ixgbe_sfp_type_lr: @@ -285,102 +288,113 @@ static int ixgbe_get_settings(struct net_device *netdev, case ixgbe_sfp_type_1g_sx_core1: case ixgbe_sfp_type_1g_lx_core0: case ixgbe_sfp_type_1g_lx_core1: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_FIBRE; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_FIBRE; break; case ixgbe_sfp_type_not_present: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_NONE; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_NONE; break; case ixgbe_sfp_type_1g_cu_core0: case ixgbe_sfp_type_1g_cu_core1: - ecmd->supported |= SUPPORTED_TP; - ecmd->advertising |= ADVERTISED_TP; - ecmd->port = PORT_TP; + supported |= SUPPORTED_TP; + advertising |= ADVERTISED_TP; + cmd->base.port = PORT_TP; break; case ixgbe_sfp_type_unknown: default: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_OTHER; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_OTHER; break; } break; case ixgbe_phy_xaui: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_NONE; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_NONE; break; case ixgbe_phy_unknown: case ixgbe_phy_generic: case ixgbe_phy_sfp_unsupported: default: - ecmd->supported |= SUPPORTED_FIBRE; - ecmd->advertising |= ADVERTISED_FIBRE; - ecmd->port = PORT_OTHER; + supported |= SUPPORTED_FIBRE; + advertising |= ADVERTISED_FIBRE; + cmd->base.port = PORT_OTHER; break; } /* Indicate pause support */ - ecmd->supported |= SUPPORTED_Pause; + supported |= SUPPORTED_Pause; switch (hw->fc.requested_mode) { case ixgbe_fc_full: - ecmd->advertising |= ADVERTISED_Pause; + advertising |= ADVERTISED_Pause; break; case ixgbe_fc_rx_pause: - ecmd->advertising |= ADVERTISED_Pause | + advertising |= ADVERTISED_Pause | ADVERTISED_Asym_Pause; break; case ixgbe_fc_tx_pause: - ecmd->advertising |= ADVERTISED_Asym_Pause; + advertising |= ADVERTISED_Asym_Pause; break; default: - ecmd->advertising &= ~(ADVERTISED_Pause | + advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); } if (netif_carrier_ok(netdev)) { switch (adapter->link_speed) { case IXGBE_LINK_SPEED_10GB_FULL: - ethtool_cmd_speed_set(ecmd, SPEED_10000); + cmd->base.speed = SPEED_10000; break; case IXGBE_LINK_SPEED_5GB_FULL: - ethtool_cmd_speed_set(ecmd, SPEED_5000); + cmd->base.speed = SPEED_5000; break; case IXGBE_LINK_SPEED_2_5GB_FULL: - ethtool_cmd_speed_set(ecmd, SPEED_2500); + cmd->base.speed = SPEED_2500; break; case IXGBE_LINK_SPEED_1GB_FULL: - ethtool_cmd_speed_set(ecmd, SPEED_1000); + cmd->base.speed = SPEED_1000; break; case IXGBE_LINK_SPEED_100_FULL: - ethtool_cmd_speed_set(ecmd, SPEED_100); + cmd->base.speed = SPEED_100; break; case IXGBE_LINK_SPEED_10_FULL: - ethtool_cmd_speed_set(ecmd, SPEED_10); + cmd->base.speed = SPEED_10; break; default: break; } - ecmd->duplex = DUPLEX_FULL; + cmd->base.duplex = DUPLEX_FULL; } else { - ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN); - ecmd->duplex = DUPLEX_UNKNOWN; + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; } + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); + return 0; } -static int ixgbe_set_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int ixgbe_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *cmd) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; u32 advertised, old; s32 err = 0; + u32 supported, advertising; + + ethtool_convert_link_mode_to_legacy_u32(&supported, + cmd->link_modes.supported); + ethtool_convert_link_mode_to_legacy_u32(&advertising, + cmd->link_modes.advertising); if ((hw->phy.media_type == ixgbe_media_type_copper) || (hw->phy.multispeed_fiber)) { @@ -388,12 +402,12 @@ static int ixgbe_set_settings(struct net_device *netdev, * this function does not support duplex forcing, but can * limit the advertising of the adapter to the specified speed */ - if (ecmd->advertising & ~ecmd->supported) + if (advertising & ~supported) return -EINVAL; /* only allow one speed at a time if no autoneg */ - if (!ecmd->autoneg && hw->phy.multispeed_fiber) { - if (ecmd->advertising == + if (!cmd->base.autoneg && hw->phy.multispeed_fiber) { + if (advertising == (ADVERTISED_10000baseT_Full | ADVERTISED_1000baseT_Full)) return -EINVAL; @@ -401,16 +415,16 @@ static int ixgbe_set_settings(struct net_device *netdev, old = hw->phy.autoneg_advertised; advertised = 0; - if (ecmd->advertising & ADVERTISED_10000baseT_Full) + if (advertising & ADVERTISED_10000baseT_Full) advertised |= IXGBE_LINK_SPEED_10GB_FULL; - if (ecmd->advertising & ADVERTISED_1000baseT_Full) + if (advertising & ADVERTISED_1000baseT_Full) advertised |= IXGBE_LINK_SPEED_1GB_FULL; - if (ecmd->advertising & ADVERTISED_100baseT_Full) + if (advertising & ADVERTISED_100baseT_Full) advertised |= IXGBE_LINK_SPEED_100_FULL; - if (ecmd->advertising & ADVERTISED_10baseT_Full) + if (advertising & ADVERTISED_10baseT_Full) advertised |= IXGBE_LINK_SPEED_10_FULL; if (old == advertised) @@ -428,10 +442,11 @@ static int ixgbe_set_settings(struct net_device *netdev, clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state); } else { /* in this case we currently only support 10Gb/FULL */ - u32 speed = ethtool_cmd_speed(ecmd); - if ((ecmd->autoneg == AUTONEG_ENABLE) || - (ecmd->advertising != ADVERTISED_10000baseT_Full) || - (speed + ecmd->duplex != SPEED_10000 + DUPLEX_FULL)) + u32 speed = cmd->base.speed; + + if ((cmd->base.autoneg == AUTONEG_ENABLE) || + (advertising != ADVERTISED_10000baseT_Full) || + (speed + cmd->base.duplex != SPEED_10000 + DUPLEX_FULL)) return -EINVAL; } @@ -1056,15 +1071,19 @@ static int ixgbe_set_ringparam(struct net_device *netdev, if (!netif_running(adapter->netdev)) { for (i = 0; i < adapter->num_tx_queues; i++) adapter->tx_ring[i]->count = new_tx_count; + for (i = 0; i < adapter->num_xdp_queues; i++) + adapter->xdp_ring[i]->count = new_tx_count; for (i = 0; i < adapter->num_rx_queues; i++) adapter->rx_ring[i]->count = new_rx_count; adapter->tx_ring_count = new_tx_count; + adapter->xdp_ring_count = new_tx_count; adapter->rx_ring_count = new_rx_count; goto clear_reset; } /* allocate temporary buffer to store rings in */ i = max_t(int, adapter->num_tx_queues, adapter->num_rx_queues); + i = max_t(int, i, adapter->num_xdp_queues); temp_ring = vmalloc(i * sizeof(struct ixgbe_ring)); if (!temp_ring) { @@ -1096,12 +1115,33 @@ static int ixgbe_set_ringparam(struct net_device *netdev, } } + for (i = 0; i < adapter->num_xdp_queues; i++) { + memcpy(&temp_ring[i], adapter->xdp_ring[i], + sizeof(struct ixgbe_ring)); + + temp_ring[i].count = new_tx_count; + err = ixgbe_setup_tx_resources(&temp_ring[i]); + if (err) { + while (i) { + i--; + ixgbe_free_tx_resources(&temp_ring[i]); + } + goto err_setup; + } + } + for (i = 0; i < adapter->num_tx_queues; i++) { ixgbe_free_tx_resources(adapter->tx_ring[i]); memcpy(adapter->tx_ring[i], &temp_ring[i], sizeof(struct ixgbe_ring)); } + for (i = 0; i < adapter->num_xdp_queues; i++) { + ixgbe_free_tx_resources(adapter->xdp_ring[i]); + + memcpy(adapter->xdp_ring[i], &temp_ring[i], + sizeof(struct ixgbe_ring)); + } adapter->tx_ring_count = new_tx_count; } @@ -1113,7 +1153,7 @@ static int ixgbe_set_ringparam(struct net_device *netdev, sizeof(struct ixgbe_ring)); temp_ring[i].count = new_rx_count; - err = ixgbe_setup_rx_resources(&temp_ring[i]); + err = ixgbe_setup_rx_resources(adapter, &temp_ring[i]); if (err) { while (i) { i--; @@ -1746,7 +1786,7 @@ static int ixgbe_setup_desc_rings(struct ixgbe_adapter *adapter) rx_ring->netdev = adapter->netdev; rx_ring->reg_idx = adapter->rx_ring[0]->reg_idx; - err = ixgbe_setup_rx_resources(rx_ring); + err = ixgbe_setup_rx_resources(adapter, rx_ring); if (err) { ret_val = 4; goto err_nomem; @@ -2927,9 +2967,7 @@ static int ixgbe_rss_indir_tbl_max(struct ixgbe_adapter *adapter) static u32 ixgbe_get_rxfh_key_size(struct net_device *netdev) { - struct ixgbe_adapter *adapter = netdev_priv(netdev); - - return sizeof(adapter->rss_key); + return IXGBE_RSS_KEY_SIZE; } static u32 ixgbe_rss_indir_size(struct net_device *netdev) @@ -3402,8 +3440,6 @@ static int ixgbe_set_priv_flags(struct net_device *netdev, u32 priv_flags) } static const struct ethtool_ops ixgbe_ethtool_ops = { - .get_settings = ixgbe_get_settings, - .set_settings = ixgbe_set_settings, .get_drvinfo = ixgbe_get_drvinfo, .get_regs_len = ixgbe_get_regs_len, .get_regs = ixgbe_get_regs, @@ -3442,6 +3478,8 @@ static const struct ethtool_ops ixgbe_ethtool_ops = { .get_ts_info = ixgbe_get_ts_info, .get_module_info = ixgbe_get_module_info, .get_module_eeprom = ixgbe_get_module_eeprom, + .get_link_ksettings = ixgbe_get_link_ksettings, + .set_link_ksettings = ixgbe_set_link_ksettings, }; void ixgbe_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index 1b8be7d813bd..b45fdc98033d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -267,12 +267,14 @@ static bool ixgbe_cache_ring_sriov(struct ixgbe_adapter *adapter) **/ static bool ixgbe_cache_ring_rss(struct ixgbe_adapter *adapter) { - int i; + int i, reg_idx; for (i = 0; i < adapter->num_rx_queues; i++) adapter->rx_ring[i]->reg_idx = i; - for (i = 0; i < adapter->num_tx_queues; i++) - adapter->tx_ring[i]->reg_idx = i; + for (i = 0, reg_idx = 0; i < adapter->num_tx_queues; i++, reg_idx++) + adapter->tx_ring[i]->reg_idx = reg_idx; + for (i = 0; i < adapter->num_xdp_queues; i++, reg_idx++) + adapter->xdp_ring[i]->reg_idx = reg_idx; return true; } @@ -308,6 +310,11 @@ static void ixgbe_cache_ring_register(struct ixgbe_adapter *adapter) ixgbe_cache_ring_rss(adapter); } +static int ixgbe_xdp_queues(struct ixgbe_adapter *adapter) +{ + return adapter->xdp_prog ? nr_cpu_ids : 0; +} + #define IXGBE_RSS_64Q_MASK 0x3F #define IXGBE_RSS_16Q_MASK 0xF #define IXGBE_RSS_8Q_MASK 0x7 @@ -382,6 +389,7 @@ static bool ixgbe_set_dcb_sriov_queues(struct ixgbe_adapter *adapter) adapter->num_rx_queues_per_pool = tcs; adapter->num_tx_queues = vmdq_i * tcs; + adapter->num_xdp_queues = 0; adapter->num_rx_queues = vmdq_i * tcs; #ifdef IXGBE_FCOE @@ -479,6 +487,7 @@ static bool ixgbe_set_dcb_queues(struct ixgbe_adapter *adapter) netdev_set_tc_queue(dev, i, rss_i, rss_i * i); adapter->num_tx_queues = rss_i * tcs; + adapter->num_xdp_queues = 0; adapter->num_rx_queues = rss_i * tcs; return true; @@ -549,6 +558,7 @@ static bool ixgbe_set_sriov_queues(struct ixgbe_adapter *adapter) adapter->num_rx_queues = vmdq_i * rss_i; adapter->num_tx_queues = vmdq_i * rss_i; + adapter->num_xdp_queues = 0; /* disable ATR as it is not supported when VMDq is enabled */ adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; @@ -669,6 +679,7 @@ static bool ixgbe_set_rss_queues(struct ixgbe_adapter *adapter) #endif /* IXGBE_FCOE */ adapter->num_rx_queues = rss_i; adapter->num_tx_queues = rss_i; + adapter->num_xdp_queues = ixgbe_xdp_queues(adapter); return true; } @@ -689,6 +700,7 @@ static void ixgbe_set_num_queues(struct ixgbe_adapter *adapter) /* Start with base case */ adapter->num_rx_queues = 1; adapter->num_tx_queues = 1; + adapter->num_xdp_queues = 0; adapter->num_rx_pools = adapter->num_rx_queues; adapter->num_rx_queues_per_pool = 1; @@ -719,8 +731,11 @@ static int ixgbe_acquire_msix_vectors(struct ixgbe_adapter *adapter) struct ixgbe_hw *hw = &adapter->hw; int i, vectors, vector_threshold; - /* We start by asking for one vector per queue pair */ + /* We start by asking for one vector per queue pair with XDP queues + * being stacked with TX queues. + */ vectors = max(adapter->num_rx_queues, adapter->num_tx_queues); + vectors = max(vectors, adapter->num_xdp_queues); /* It is easy to be greedy for MSI-X vectors. However, it really * doesn't do much good if we have a lot more vectors than CPUs. We'll @@ -800,6 +815,8 @@ static void ixgbe_add_ring(struct ixgbe_ring *ring, * @v_idx: index of vector in adapter struct * @txr_count: total number of Tx rings to allocate * @txr_idx: index of first Tx ring to allocate + * @xdp_count: total number of XDP rings to allocate + * @xdp_idx: index of first XDP ring to allocate * @rxr_count: total number of Rx rings to allocate * @rxr_idx: index of first Rx ring to allocate * @@ -808,6 +825,7 @@ static void ixgbe_add_ring(struct ixgbe_ring *ring, static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, int v_count, int v_idx, int txr_count, int txr_idx, + int xdp_count, int xdp_idx, int rxr_count, int rxr_idx) { struct ixgbe_q_vector *q_vector; @@ -817,7 +835,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, int ring_count, size; u8 tcs = netdev_get_num_tc(adapter->netdev); - ring_count = txr_count + rxr_count; + ring_count = txr_count + rxr_count + xdp_count; size = sizeof(struct ixgbe_q_vector) + (sizeof(struct ixgbe_ring) * ring_count); @@ -909,6 +927,33 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, ring++; } + while (xdp_count) { + /* assign generic ring traits */ + ring->dev = &adapter->pdev->dev; + ring->netdev = adapter->netdev; + + /* configure backlink on ring */ + ring->q_vector = q_vector; + + /* update q_vector Tx values */ + ixgbe_add_ring(ring, &q_vector->tx); + + /* apply Tx specific ring traits */ + ring->count = adapter->tx_ring_count; + ring->queue_index = xdp_idx; + set_ring_xdp(ring); + + /* assign ring to adapter */ + adapter->xdp_ring[xdp_idx] = ring; + + /* update count and index */ + xdp_count--; + xdp_idx++; + + /* push pointer to next ring */ + ring++; + } + while (rxr_count) { /* assign generic ring traits */ ring->dev = &adapter->pdev->dev; @@ -1002,17 +1047,18 @@ static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter) int q_vectors = adapter->num_q_vectors; int rxr_remaining = adapter->num_rx_queues; int txr_remaining = adapter->num_tx_queues; - int rxr_idx = 0, txr_idx = 0, v_idx = 0; + int xdp_remaining = adapter->num_xdp_queues; + int rxr_idx = 0, txr_idx = 0, xdp_idx = 0, v_idx = 0; int err; /* only one q_vector if MSI-X is disabled. */ if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) q_vectors = 1; - if (q_vectors >= (rxr_remaining + txr_remaining)) { + if (q_vectors >= (rxr_remaining + txr_remaining + xdp_remaining)) { for (; rxr_remaining; v_idx++) { err = ixgbe_alloc_q_vector(adapter, q_vectors, v_idx, - 0, 0, 1, rxr_idx); + 0, 0, 0, 0, 1, rxr_idx); if (err) goto err_out; @@ -1026,8 +1072,11 @@ static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter) for (; v_idx < q_vectors; v_idx++) { int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - v_idx); int tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - v_idx); + int xqpv = DIV_ROUND_UP(xdp_remaining, q_vectors - v_idx); + err = ixgbe_alloc_q_vector(adapter, q_vectors, v_idx, tqpv, txr_idx, + xqpv, xdp_idx, rqpv, rxr_idx); if (err) @@ -1036,14 +1085,17 @@ static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter) /* update counts and index */ rxr_remaining -= rqpv; txr_remaining -= tqpv; + xdp_remaining -= xqpv; rxr_idx++; txr_idx++; + xdp_idx += xqpv; } return 0; err_out: adapter->num_tx_queues = 0; + adapter->num_xdp_queues = 0; adapter->num_rx_queues = 0; adapter->num_q_vectors = 0; @@ -1066,6 +1118,7 @@ static void ixgbe_free_q_vectors(struct ixgbe_adapter *adapter) int v_idx = adapter->num_q_vectors; adapter->num_tx_queues = 0; + adapter->num_xdp_queues = 0; adapter->num_rx_queues = 0; adapter->num_q_vectors = 0; @@ -1172,9 +1225,10 @@ int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter) ixgbe_cache_ring_register(adapter); - e_dev_info("Multiqueue %s: Rx Queue count = %u, Tx Queue count = %u\n", + e_dev_info("Multiqueue %s: Rx Queue count = %u, Tx Queue count = %u XDP Queue count = %u\n", (adapter->num_rx_queues > 1) ? "Enabled" : "Disabled", - adapter->num_rx_queues, adapter->num_tx_queues); + adapter->num_rx_queues, adapter->num_tx_queues, + adapter->num_xdp_queues); set_bit(__IXGBE_DOWN, &adapter->state); @@ -1195,6 +1249,7 @@ err_alloc_q_vectors: void ixgbe_clear_interrupt_scheme(struct ixgbe_adapter *adapter) { adapter->num_tx_queues = 0; + adapter->num_xdp_queues = 0; adapter->num_rx_queues = 0; ixgbe_free_q_vectors(adapter); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index a7a430a7be2c..22a29df1d29e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -49,6 +49,9 @@ #include <linux/if_macvlan.h> #include <linux/if_bridge.h> #include <linux/prefetch.h> +#include <linux/bpf.h> +#include <linux/bpf_trace.h> +#include <linux/atomic.h> #include <scsi/fc/fc_fcoe.h> #include <net/udp_tunnel.h> #include <net/pkt_cls.h> @@ -85,6 +88,7 @@ static const struct ixgbe_info *ixgbe_info_tbl[] = { [board_X540] = &ixgbe_X540_info, [board_X550] = &ixgbe_X550_info, [board_X550EM_x] = &ixgbe_X550EM_x_info, + [board_x550em_x_fw] = &ixgbe_x550em_x_fw_info, [board_x550em_a] = &ixgbe_x550em_a_info, [board_x550em_a_fw] = &ixgbe_x550em_a_fw_info, }; @@ -131,9 +135,11 @@ static const struct pci_device_id ixgbe_pci_tbl[] = { {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550T), board_X550}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550T1), board_X550}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_KX4), board_X550EM_x}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_XFI), board_X550EM_x}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_KR), board_X550EM_x}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_10G_T), board_X550EM_x}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_SFP), board_X550EM_x}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_1G_T), board_x550em_x_fw}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_KR), board_x550em_a }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_KR_L), board_x550em_a }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SFP_N), board_x550em_a }, @@ -508,7 +514,7 @@ static const struct ixgbe_reg_info ixgbe_reg_info_tbl[] = { */ static void ixgbe_regdump(struct ixgbe_hw *hw, struct ixgbe_reg_info *reginfo) { - int i = 0, j = 0; + int i; char rname[16]; u32 regs[64]; @@ -570,21 +576,38 @@ static void ixgbe_regdump(struct ixgbe_hw *hw, struct ixgbe_reg_info *reginfo) regs[i] = IXGBE_READ_REG(hw, IXGBE_TXDCTL(i)); break; default: - pr_info("%-15s %08x\n", reginfo->name, - IXGBE_READ_REG(hw, reginfo->ofs)); + pr_info("%-15s %08x\n", + reginfo->name, IXGBE_READ_REG(hw, reginfo->ofs)); return; } - for (i = 0; i < 8; i++) { - snprintf(rname, 16, "%s[%d-%d]", reginfo->name, i*8, i*8+7); - pr_err("%-15s", rname); + i = 0; + while (i < 64) { + int j; + char buf[9 * 8 + 1]; + char *p = buf; + + snprintf(rname, 16, "%s[%d-%d]", reginfo->name, i, i + 7); for (j = 0; j < 8; j++) - pr_cont(" %08x", regs[i*8+j]); - pr_cont("\n"); + p += sprintf(p, " %08x", regs[i++]); + pr_err("%-15s%s\n", rname, buf); } } +static void ixgbe_print_buffer(struct ixgbe_ring *ring, int n) +{ + struct ixgbe_tx_buffer *tx_buffer; + + tx_buffer = &ring->tx_buffer_info[ring->next_to_clean]; + pr_info(" %5d %5X %5X %016llX %08X %p %016llX\n", + n, ring->next_to_use, ring->next_to_clean, + (u64)dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + tx_buffer->next_to_watch, + (u64)tx_buffer->time_stamp); +} + /* * ixgbe_dump - Print registers, tx-rings and rx-rings */ @@ -594,14 +617,13 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter) struct ixgbe_hw *hw = &adapter->hw; struct ixgbe_reg_info *reginfo; int n = 0; - struct ixgbe_ring *tx_ring; + struct ixgbe_ring *ring; struct ixgbe_tx_buffer *tx_buffer; union ixgbe_adv_tx_desc *tx_desc; struct my_u0 { u64 a; u64 b; } *u0; struct ixgbe_ring *rx_ring; union ixgbe_adv_rx_desc *rx_desc; struct ixgbe_rx_buffer *rx_buffer_info; - u32 staterr; int i = 0; if (!netif_msg_hw(adapter)) @@ -635,14 +657,13 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter) "Queue [NTU] [NTC] [bi(ntc)->dma ]", "leng", "ntw", "timestamp"); for (n = 0; n < adapter->num_tx_queues; n++) { - tx_ring = adapter->tx_ring[n]; - tx_buffer = &tx_ring->tx_buffer_info[tx_ring->next_to_clean]; - pr_info(" %5d %5X %5X %016llX %08X %p %016llX\n", - n, tx_ring->next_to_use, tx_ring->next_to_clean, - (u64)dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - tx_buffer->next_to_watch, - (u64)tx_buffer->time_stamp); + ring = adapter->tx_ring[n]; + ixgbe_print_buffer(ring, n); + } + + for (n = 0; n < adapter->num_xdp_queues; n++) { + ring = adapter->xdp_ring[n]; + ixgbe_print_buffer(ring, n); } /* Print TX Rings */ @@ -687,21 +708,32 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter) */ for (n = 0; n < adapter->num_tx_queues; n++) { - tx_ring = adapter->tx_ring[n]; + ring = adapter->tx_ring[n]; pr_info("------------------------------------\n"); - pr_info("TX QUEUE INDEX = %d\n", tx_ring->queue_index); + pr_info("TX QUEUE INDEX = %d\n", ring->queue_index); pr_info("------------------------------------\n"); pr_info("%s%s %s %s %s %s\n", "T [desc] [address 63:0 ] ", "[PlPOIdStDDt Ln] [bi->dma ] ", "leng", "ntw", "timestamp", "bi->skb"); - for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) { - tx_desc = IXGBE_TX_DESC(tx_ring, i); - tx_buffer = &tx_ring->tx_buffer_info[i]; + for (i = 0; ring->desc && (i < ring->count); i++) { + tx_desc = IXGBE_TX_DESC(ring, i); + tx_buffer = &ring->tx_buffer_info[i]; u0 = (struct my_u0 *)tx_desc; if (dma_unmap_len(tx_buffer, len) > 0) { - pr_info("T [0x%03X] %016llX %016llX %016llX %08X %p %016llX %p", + const char *ring_desc; + + if (i == ring->next_to_use && + i == ring->next_to_clean) + ring_desc = " NTC/U"; + else if (i == ring->next_to_use) + ring_desc = " NTU"; + else if (i == ring->next_to_clean) + ring_desc = " NTC"; + else + ring_desc = ""; + pr_info("T [0x%03X] %016llX %016llX %016llX %08X %p %016llX %p%s", i, le64_to_cpu(u0->a), le64_to_cpu(u0->b), @@ -709,16 +741,8 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter) dma_unmap_len(tx_buffer, len), tx_buffer->next_to_watch, (u64)tx_buffer->time_stamp, - tx_buffer->skb); - if (i == tx_ring->next_to_use && - i == tx_ring->next_to_clean) - pr_cont(" NTC/U\n"); - else if (i == tx_ring->next_to_use) - pr_cont(" NTU\n"); - else if (i == tx_ring->next_to_clean) - pr_cont(" NTC\n"); - else - pr_cont("\n"); + tx_buffer->skb, + ring_desc); if (netif_msg_pktdata(adapter) && tx_buffer->skb) @@ -797,34 +821,44 @@ rx_ring_summary: pr_info("------------------------------------\n"); pr_info("RX QUEUE INDEX = %d\n", rx_ring->queue_index); pr_info("------------------------------------\n"); - pr_info("%s%s%s", + pr_info("%s%s%s\n", "R [desc] [ PktBuf A0] ", "[ HeadBuf DD] [bi->dma ] [bi->skb ] ", - "<-- Adv Rx Read format\n"); - pr_info("%s%s%s", + "<-- Adv Rx Read format"); + pr_info("%s%s%s\n", "RWB[desc] [PcsmIpSHl PtRs] ", "[vl er S cks ln] ---------------- [bi->skb ] ", - "<-- Adv Rx Write-Back format\n"); + "<-- Adv Rx Write-Back format"); for (i = 0; i < rx_ring->count; i++) { + const char *ring_desc; + + if (i == rx_ring->next_to_use) + ring_desc = " NTU"; + else if (i == rx_ring->next_to_clean) + ring_desc = " NTC"; + else + ring_desc = ""; + rx_buffer_info = &rx_ring->rx_buffer_info[i]; rx_desc = IXGBE_RX_DESC(rx_ring, i); u0 = (struct my_u0 *)rx_desc; - staterr = le32_to_cpu(rx_desc->wb.upper.status_error); - if (staterr & IXGBE_RXD_STAT_DD) { + if (rx_desc->wb.upper.length) { /* Descriptor Done */ - pr_info("RWB[0x%03X] %016llX " - "%016llX ---------------- %p", i, + pr_info("RWB[0x%03X] %016llX %016llX ---------------- %p%s\n", + i, le64_to_cpu(u0->a), le64_to_cpu(u0->b), - rx_buffer_info->skb); + rx_buffer_info->skb, + ring_desc); } else { - pr_info("R [0x%03X] %016llX " - "%016llX %016llX %p", i, + pr_info("R [0x%03X] %016llX %016llX %016llX %p%s\n", + i, le64_to_cpu(u0->a), le64_to_cpu(u0->b), (u64)rx_buffer_info->dma, - rx_buffer_info->skb); + rx_buffer_info->skb, + ring_desc); if (netif_msg_pktdata(adapter) && rx_buffer_info->dma) { @@ -835,14 +869,6 @@ rx_ring_summary: ixgbe_rx_bufsz(rx_ring), true); } } - - if (i == rx_ring->next_to_use) - pr_cont(" NTU\n"); - else if (i == rx_ring->next_to_clean) - pr_cont(" NTC\n"); - else - pr_cont("\n"); - } } } @@ -972,6 +998,10 @@ static void ixgbe_update_xoff_rx_lfc(struct ixgbe_adapter *adapter) for (i = 0; i < adapter->num_tx_queues; i++) clear_bit(__IXGBE_HANG_CHECK_ARMED, &adapter->tx_ring[i]->state); + + for (i = 0; i < adapter->num_xdp_queues; i++) + clear_bit(__IXGBE_HANG_CHECK_ARMED, + &adapter->xdp_ring[i]->state); } static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter) @@ -1016,6 +1046,14 @@ static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter) if (xoff[tc]) clear_bit(__IXGBE_HANG_CHECK_ARMED, &tx_ring->state); } + + for (i = 0; i < adapter->num_xdp_queues; i++) { + struct ixgbe_ring *xdp_ring = adapter->xdp_ring[i]; + + tc = xdp_ring->dcb_tc; + if (xoff[tc]) + clear_bit(__IXGBE_HANG_CHECK_ARMED, &xdp_ring->state); + } } static u64 ixgbe_get_tx_completed(struct ixgbe_ring *ring) @@ -1167,7 +1205,10 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, total_packets += tx_buffer->gso_segs; /* free the skb */ - napi_consume_skb(tx_buffer->skb, napi_budget); + if (ring_is_xdp(tx_ring)) + page_frag_free(tx_buffer->data); + else + napi_consume_skb(tx_buffer->skb, napi_budget); /* unmap skb header data */ dma_unmap_single(tx_ring->dev, @@ -1228,7 +1269,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, if (check_for_tx_hang(tx_ring) && ixgbe_check_tx_hang(tx_ring)) { /* schedule immediate reset if we believe we hung */ struct ixgbe_hw *hw = &adapter->hw; - e_err(drv, "Detected Tx Unit Hang\n" + e_err(drv, "Detected Tx Unit Hang %s\n" " Tx Queue <%d>\n" " TDH, TDT <%x>, <%x>\n" " next_to_use <%x>\n" @@ -1236,13 +1277,16 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, "tx_buffer_info[next_to_clean]\n" " time_stamp <%lx>\n" " jiffies <%lx>\n", + ring_is_xdp(tx_ring) ? "(XDP)" : "", tx_ring->queue_index, IXGBE_READ_REG(hw, IXGBE_TDH(tx_ring->reg_idx)), IXGBE_READ_REG(hw, IXGBE_TDT(tx_ring->reg_idx)), tx_ring->next_to_use, i, tx_ring->tx_buffer_info[i].time_stamp, jiffies); - netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); + if (!ring_is_xdp(tx_ring)) + netif_stop_subqueue(tx_ring->netdev, + tx_ring->queue_index); e_info(probe, "tx hang %d detected on queue %d, resetting adapter\n", @@ -1255,6 +1299,9 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, return true; } + if (ring_is_xdp(tx_ring)) + return !!budget; + netdev_tx_completed_queue(txring_txq(tx_ring), total_packets, total_bytes); @@ -1846,6 +1893,10 @@ static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring, * @rx_desc: pointer to the EOP Rx descriptor * @skb: pointer to current skb being fixed * + * Check if the skb is valid in the XDP case it will be an error pointer. + * Return true in this case to abort processing and advance to next + * descriptor. + * * Check for corrupted packet headers caused by senders on the local L2 * embedded NIC switch not setting up their Tx Descriptors right. These * should be very rare. @@ -1864,6 +1915,10 @@ static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, { struct net_device *netdev = rx_ring->netdev; + /* XDP packets use error pointer so abort at this point */ + if (IS_ERR(skb)) + return true; + /* verify that the packet does not have any known errors */ if (unlikely(ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_FRAME_ERR_MASK) && @@ -2039,7 +2094,7 @@ static void ixgbe_put_rx_buffer(struct ixgbe_ring *rx_ring, /* hand second half of page back to the ring */ ixgbe_reuse_rx_page(rx_ring, rx_buffer); } else { - if (IXGBE_CB(skb)->dma == rx_buffer->dma) { + if (!IS_ERR(skb) && IXGBE_CB(skb)->dma == rx_buffer->dma) { /* the page has been released from the ring */ IXGBE_CB(skb)->page_released = true; } else { @@ -2060,21 +2115,22 @@ static void ixgbe_put_rx_buffer(struct ixgbe_ring *rx_ring, static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring, struct ixgbe_rx_buffer *rx_buffer, - union ixgbe_adv_rx_desc *rx_desc, - unsigned int size) + struct xdp_buff *xdp, + union ixgbe_adv_rx_desc *rx_desc) { - void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; + unsigned int size = xdp->data_end - xdp->data; #if (PAGE_SIZE < 8192) unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2; #else - unsigned int truesize = SKB_DATA_ALIGN(size); + unsigned int truesize = SKB_DATA_ALIGN(xdp->data_end - + xdp->data_hard_start); #endif struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(va); + prefetch(xdp->data); #if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); + prefetch(xdp->data + L1_CACHE_BYTES); #endif /* allocate a skb to store the frags */ @@ -2087,7 +2143,7 @@ static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring, IXGBE_CB(skb)->dma = rx_buffer->dma; skb_add_rx_frag(skb, 0, rx_buffer->page, - rx_buffer->page_offset, + xdp->data - page_address(rx_buffer->page), size, truesize); #if (PAGE_SIZE < 8192) rx_buffer->page_offset ^= truesize; @@ -2095,7 +2151,8 @@ static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring, rx_buffer->page_offset += truesize; #endif } else { - memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); + memcpy(__skb_put(skb, size), + xdp->data, ALIGN(size, sizeof(long))); rx_buffer->pagecnt_bias++; } @@ -2104,32 +2161,32 @@ static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring, static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, struct ixgbe_rx_buffer *rx_buffer, - union ixgbe_adv_rx_desc *rx_desc, - unsigned int size) + struct xdp_buff *xdp, + union ixgbe_adv_rx_desc *rx_desc) { - void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2; #else unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + - SKB_DATA_ALIGN(IXGBE_SKB_PAD + size); + SKB_DATA_ALIGN(xdp->data_end - + xdp->data_hard_start); #endif struct sk_buff *skb; /* prefetch first cache line of first page */ - prefetch(va); + prefetch(xdp->data); #if L1_CACHE_BYTES < 128 - prefetch(va + L1_CACHE_BYTES); + prefetch(xdp->data + L1_CACHE_BYTES); #endif /* build an skb to around the page buffer */ - skb = build_skb(va - IXGBE_SKB_PAD, truesize); + skb = build_skb(xdp->data_hard_start, truesize); if (unlikely(!skb)) return NULL; /* update pointers within the skb to store the data */ - skb_reserve(skb, IXGBE_SKB_PAD); - __skb_put(skb, size); + skb_reserve(skb, xdp->data - xdp->data_hard_start); + __skb_put(skb, xdp->data_end - xdp->data); /* record DMA address if this is the start of a chain of buffers */ if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)) @@ -2145,6 +2202,65 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, return skb; } +#define IXGBE_XDP_PASS 0 +#define IXGBE_XDP_CONSUMED 1 +#define IXGBE_XDP_TX 2 + +static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, + struct xdp_buff *xdp); + +static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, + struct ixgbe_ring *rx_ring, + struct xdp_buff *xdp) +{ + int result = IXGBE_XDP_PASS; + struct bpf_prog *xdp_prog; + u32 act; + + rcu_read_lock(); + xdp_prog = READ_ONCE(rx_ring->xdp_prog); + + if (!xdp_prog) + goto xdp_out; + + act = bpf_prog_run_xdp(xdp_prog, xdp); + switch (act) { + case XDP_PASS: + break; + case XDP_TX: + result = ixgbe_xmit_xdp_ring(adapter, xdp); + break; + default: + bpf_warn_invalid_xdp_action(act); + case XDP_ABORTED: + trace_xdp_exception(rx_ring->netdev, xdp_prog, act); + /* fallthrough -- handle aborts by dropping packet */ + case XDP_DROP: + result = IXGBE_XDP_CONSUMED; + break; + } +xdp_out: + rcu_read_unlock(); + return ERR_PTR(-result); +} + +static void ixgbe_rx_buffer_flip(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *rx_buffer, + unsigned int size) +{ +#if (PAGE_SIZE < 8192) + unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2; + + rx_buffer->page_offset ^= truesize; +#else + unsigned int truesize = ring_uses_build_skb(rx_ring) ? + SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) : + SKB_DATA_ALIGN(size); + + rx_buffer->page_offset += truesize; +#endif +} + /** * ixgbe_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf * @q_vector: structure containing interrupt and ring information @@ -2163,17 +2279,19 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, const int budget) { unsigned int total_rx_bytes = 0, total_rx_packets = 0; -#ifdef IXGBE_FCOE struct ixgbe_adapter *adapter = q_vector->adapter; +#ifdef IXGBE_FCOE int ddp_bytes; unsigned int mss = 0; #endif /* IXGBE_FCOE */ u16 cleaned_count = ixgbe_desc_unused(rx_ring); + bool xdp_xmit = false; while (likely(total_rx_packets < budget)) { union ixgbe_adv_rx_desc *rx_desc; struct ixgbe_rx_buffer *rx_buffer; struct sk_buff *skb; + struct xdp_buff xdp; unsigned int size; /* return some buffers to hardware, one at a time is too slow */ @@ -2196,14 +2314,34 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, rx_buffer = ixgbe_get_rx_buffer(rx_ring, rx_desc, &skb, size); /* retrieve a buffer from the ring */ - if (skb) + if (!skb) { + xdp.data = page_address(rx_buffer->page) + + rx_buffer->page_offset; + xdp.data_hard_start = xdp.data - + ixgbe_rx_offset(rx_ring); + xdp.data_end = xdp.data + size; + + skb = ixgbe_run_xdp(adapter, rx_ring, &xdp); + } + + if (IS_ERR(skb)) { + if (PTR_ERR(skb) == -IXGBE_XDP_TX) { + xdp_xmit = true; + ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size); + } else { + rx_buffer->pagecnt_bias++; + } + total_rx_packets++; + total_rx_bytes += size; + } else if (skb) { ixgbe_add_rx_frag(rx_ring, rx_buffer, skb, size); - else if (ring_uses_build_skb(rx_ring)) + } else if (ring_uses_build_skb(rx_ring)) { skb = ixgbe_build_skb(rx_ring, rx_buffer, - rx_desc, size); - else + &xdp, rx_desc); + } else { skb = ixgbe_construct_skb(rx_ring, rx_buffer, - rx_desc, size); + &xdp, rx_desc); + } /* exit if we failed to retrieve a buffer */ if (!skb) { @@ -2260,6 +2398,16 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, total_rx_packets++; } + if (xdp_xmit) { + struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()]; + + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. + */ + wmb(); + writel(ring->next_to_use, ring->tail); + } + u64_stats_update_begin(&rx_ring->syncp); rx_ring->stats.packets += total_rx_packets; rx_ring->stats.bytes += total_rx_bytes; @@ -3364,6 +3512,8 @@ static void ixgbe_configure_tx(struct ixgbe_adapter *adapter) /* Setup the HW Tx Head and Tail descriptor pointers */ for (i = 0; i < adapter->num_tx_queues; i++) ixgbe_configure_tx_ring(adapter, adapter->tx_ring[i]); + for (i = 0; i < adapter->num_xdp_queues; i++) + ixgbe_configure_tx_ring(adapter, adapter->xdp_ring[i]); } static void ixgbe_enable_rx_drop(struct ixgbe_adapter *adapter, @@ -3489,6 +3639,28 @@ void ixgbe_store_key(struct ixgbe_adapter *adapter) } /** + * ixgbe_init_rss_key - Initialize adapter RSS key + * @adapter: device handle + * + * Allocates and initializes the RSS key if it is not allocated. + **/ +static inline int ixgbe_init_rss_key(struct ixgbe_adapter *adapter) +{ + u32 *rss_key; + + if (!adapter->rss_key) { + rss_key = kzalloc(IXGBE_RSS_KEY_SIZE, GFP_KERNEL); + if (unlikely(!rss_key)) + return -ENOMEM; + + netdev_rss_key_fill(rss_key, IXGBE_RSS_KEY_SIZE); + adapter->rss_key = rss_key; + } + + return 0; +} + +/** * ixgbe_store_reta - Write the RETA table to HW * @adapter: device handle * @@ -3590,7 +3762,7 @@ static void ixgbe_setup_vfreta(struct ixgbe_adapter *adapter) /* Fill out hash function seeds */ for (i = 0; i < 10; i++) IXGBE_WRITE_REG(hw, IXGBE_PFVFRSSRK(i, pf_pool), - adapter->rss_key[i]); + *(adapter->rss_key + i)); /* Fill out the redirection table */ for (i = 0, j = 0; i < 64; i++, j++) { @@ -3651,7 +3823,6 @@ static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter) if (adapter->flags2 & IXGBE_FLAG2_RSS_FIELD_IPV6_UDP) rss_field |= IXGBE_MRQC_RSS_FIELD_IPV6_UDP; - netdev_rss_key_fill(adapter->rss_key, sizeof(adapter->rss_key)); if ((hw->mac.type >= ixgbe_mac_X550) && (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) { unsigned int pf_pool = adapter->num_vfs; @@ -3802,7 +3973,7 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, /* Limit the maximum frame size so we don't overrun the skb */ if (ring_uses_build_skb(ring) && !test_bit(__IXGBE_RX_3K_BUFFER, &ring->state)) - rxdctl |= IXGBE_MAX_FRAME_BUILD_SKB | + rxdctl |= IXGBE_MAX_2K_FRAME_BUILD_SKB | IXGBE_RXDCTL_RLPML_EN; #endif } @@ -3972,8 +4143,8 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter) if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state); - if ((max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN)) || - (max_frame > IXGBE_MAX_FRAME_BUILD_SKB)) + if (IXGBE_2K_TOO_SMALL_WITH_PADDING || + (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN))) set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state); #endif } @@ -5505,7 +5676,10 @@ static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring) union ixgbe_adv_tx_desc *eop_desc, *tx_desc; /* Free all the Tx ring sk_buffs */ - dev_kfree_skb_any(tx_buffer->skb); + if (ring_is_xdp(tx_ring)) + page_frag_free(tx_buffer->data); + else + dev_kfree_skb_any(tx_buffer->skb); /* unmap skb header data */ dma_unmap_single(tx_ring->dev, @@ -5546,7 +5720,8 @@ static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring) } /* reset BQL for queue */ - netdev_tx_reset_queue(txring_txq(tx_ring)); + if (!ring_is_xdp(tx_ring)) + netdev_tx_reset_queue(txring_txq(tx_ring)); /* reset next_to_use and next_to_clean */ tx_ring->next_to_use = 0; @@ -5575,6 +5750,8 @@ static void ixgbe_clean_all_tx_rings(struct ixgbe_adapter *adapter) for (i = 0; i < adapter->num_tx_queues; i++) ixgbe_clean_tx_ring(adapter->tx_ring[i]); + for (i = 0; i < adapter->num_xdp_queues; i++) + ixgbe_clean_tx_ring(adapter->xdp_ring[i]); } static void ixgbe_fdir_filter_exit(struct ixgbe_adapter *adapter) @@ -5669,6 +5846,11 @@ void ixgbe_down(struct ixgbe_adapter *adapter) u8 reg_idx = adapter->tx_ring[i]->reg_idx; IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH); } + for (i = 0; i < adapter->num_xdp_queues; i++) { + u8 reg_idx = adapter->xdp_ring[i]->reg_idx; + + IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH); + } /* Disable the Tx DMA engine on 82599 and later MAC */ switch (hw->mac.type) { @@ -5854,6 +6036,9 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, if (!adapter->mac_table) return -ENOMEM; + if (ixgbe_init_rss_key(adapter)) + return -ENOMEM; + /* Set MAC specific capability flags and exceptions */ switch (hw->mac.type) { case ixgbe_mac_82598EB: @@ -5944,10 +6129,8 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, /* assign number of SR-IOV VFs */ if (hw->mac.type != ixgbe_mac_82598EB) { if (max_vfs > IXGBE_MAX_VFS_DRV_LIMIT) { - adapter->num_vfs = 0; + max_vfs = 0; e_dev_warn("max_vfs parameter out of range. Not assigning any SR-IOV VFs\n"); - } else { - adapter->num_vfs = max_vfs; } } #endif /* CONFIG_PCI_IOV */ @@ -6041,7 +6224,7 @@ err: **/ static int ixgbe_setup_all_tx_resources(struct ixgbe_adapter *adapter) { - int i, err = 0; + int i, j = 0, err = 0; for (i = 0; i < adapter->num_tx_queues; i++) { err = ixgbe_setup_tx_resources(adapter->tx_ring[i]); @@ -6051,10 +6234,20 @@ static int ixgbe_setup_all_tx_resources(struct ixgbe_adapter *adapter) e_err(probe, "Allocation for Tx Queue %u failed\n", i); goto err_setup_tx; } + for (j = 0; j < adapter->num_xdp_queues; j++) { + err = ixgbe_setup_tx_resources(adapter->xdp_ring[j]); + if (!err) + continue; + + e_err(probe, "Allocation for Tx Queue %u failed\n", j); + goto err_setup_tx; + } return 0; err_setup_tx: /* rewind the index freeing the rings as we go */ + while (j--) + ixgbe_free_tx_resources(adapter->xdp_ring[j]); while (i--) ixgbe_free_tx_resources(adapter->tx_ring[i]); return err; @@ -6066,7 +6259,8 @@ err_setup_tx: * * Returns 0 on success, negative on failure **/ -int ixgbe_setup_rx_resources(struct ixgbe_ring *rx_ring) +int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter, + struct ixgbe_ring *rx_ring) { struct device *dev = rx_ring->dev; int orig_node = dev_to_node(dev); @@ -6105,6 +6299,8 @@ int ixgbe_setup_rx_resources(struct ixgbe_ring *rx_ring) rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; + rx_ring->xdp_prog = adapter->xdp_prog; + return 0; err: vfree(rx_ring->rx_buffer_info); @@ -6128,7 +6324,7 @@ static int ixgbe_setup_all_rx_resources(struct ixgbe_adapter *adapter) int i, err = 0; for (i = 0; i < adapter->num_rx_queues; i++) { - err = ixgbe_setup_rx_resources(adapter->rx_ring[i]); + err = ixgbe_setup_rx_resources(adapter, adapter->rx_ring[i]); if (!err) continue; @@ -6184,6 +6380,9 @@ static void ixgbe_free_all_tx_resources(struct ixgbe_adapter *adapter) for (i = 0; i < adapter->num_tx_queues; i++) if (adapter->tx_ring[i]->desc) ixgbe_free_tx_resources(adapter->tx_ring[i]); + for (i = 0; i < adapter->num_xdp_queues; i++) + if (adapter->xdp_ring[i]->desc) + ixgbe_free_tx_resources(adapter->xdp_ring[i]); } /** @@ -6196,6 +6395,7 @@ void ixgbe_free_rx_resources(struct ixgbe_ring *rx_ring) { ixgbe_clean_rx_ring(rx_ring); + rx_ring->xdp_prog = NULL; vfree(rx_ring->rx_buffer_info); rx_ring->rx_buffer_info = NULL; @@ -6602,6 +6802,14 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) bytes += tx_ring->stats.bytes; packets += tx_ring->stats.packets; } + for (i = 0; i < adapter->num_xdp_queues; i++) { + struct ixgbe_ring *xdp_ring = adapter->xdp_ring[i]; + + restart_queue += xdp_ring->tx_stats.restart_queue; + tx_busy += xdp_ring->tx_stats.tx_busy; + bytes += xdp_ring->stats.bytes; + packets += xdp_ring->stats.packets; + } adapter->restart_queue = restart_queue; adapter->tx_busy = tx_busy; netdev->stats.tx_bytes = bytes; @@ -6795,6 +7003,9 @@ static void ixgbe_fdir_reinit_subtask(struct ixgbe_adapter *adapter) for (i = 0; i < adapter->num_tx_queues; i++) set_bit(__IXGBE_TX_FDIR_INIT_DONE, &(adapter->tx_ring[i]->state)); + for (i = 0; i < adapter->num_xdp_queues; i++) + set_bit(__IXGBE_TX_FDIR_INIT_DONE, + &adapter->xdp_ring[i]->state); /* re-enable flow director interrupts */ IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_FLOW_DIR); } else { @@ -6828,6 +7039,8 @@ static void ixgbe_check_hang_subtask(struct ixgbe_adapter *adapter) if (netif_carrier_ok(adapter->netdev)) { for (i = 0; i < adapter->num_tx_queues; i++) set_check_for_tx_hang(adapter->tx_ring[i]); + for (i = 0; i < adapter->num_xdp_queues; i++) + set_check_for_tx_hang(adapter->xdp_ring[i]); } if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) { @@ -7058,6 +7271,13 @@ static bool ixgbe_ring_tx_pending(struct ixgbe_adapter *adapter) return true; } + for (i = 0; i < adapter->num_xdp_queues; i++) { + struct ixgbe_ring *ring = adapter->xdp_ring[i]; + + if (ring->next_to_use != ring->next_to_clean) + return true; + } + return false; } @@ -8015,6 +8235,62 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, #endif } +static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, + struct xdp_buff *xdp) +{ + struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()]; + struct ixgbe_tx_buffer *tx_buffer; + union ixgbe_adv_tx_desc *tx_desc; + u32 len, cmd_type; + dma_addr_t dma; + u16 i; + + len = xdp->data_end - xdp->data; + + if (unlikely(!ixgbe_desc_unused(ring))) + return IXGBE_XDP_CONSUMED; + + dma = dma_map_single(ring->dev, xdp->data, len, DMA_TO_DEVICE); + if (dma_mapping_error(ring->dev, dma)) + return IXGBE_XDP_CONSUMED; + + /* record the location of the first descriptor for this packet */ + tx_buffer = &ring->tx_buffer_info[ring->next_to_use]; + tx_buffer->bytecount = len; + tx_buffer->gso_segs = 1; + tx_buffer->protocol = 0; + + i = ring->next_to_use; + tx_desc = IXGBE_TX_DESC(ring, i); + + dma_unmap_len_set(tx_buffer, len, len); + dma_unmap_addr_set(tx_buffer, dma, dma); + tx_buffer->data = xdp->data; + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + /* put descriptor type bits */ + cmd_type = IXGBE_ADVTXD_DTYP_DATA | + IXGBE_ADVTXD_DCMD_DEXT | + IXGBE_ADVTXD_DCMD_IFCS; + cmd_type |= len | IXGBE_TXD_CMD; + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + tx_desc->read.olinfo_status = + cpu_to_le32(len << IXGBE_ADVTXD_PAYLEN_SHIFT); + + /* Avoid any potential race with xdp_xmit and cleanup */ + smp_wmb(); + + /* set next_to_watch value indicating a packet is present */ + i++; + if (i == ring->count) + i = 0; + + tx_buffer->next_to_watch = tx_desc; + ring->next_to_use = i; + + return IXGBE_XDP_TX; +} + netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, struct ixgbe_adapter *adapter, struct ixgbe_ring *tx_ring) @@ -8306,6 +8582,23 @@ static void ixgbe_netpoll(struct net_device *netdev) #endif +static void ixgbe_get_ring_stats64(struct rtnl_link_stats64 *stats, + struct ixgbe_ring *ring) +{ + u64 bytes, packets; + unsigned int start; + + if (ring) { + do { + start = u64_stats_fetch_begin_irq(&ring->syncp); + packets = ring->stats.packets; + bytes = ring->stats.bytes; + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + stats->tx_packets += packets; + stats->tx_bytes += bytes; + } +} + static void ixgbe_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) { @@ -8331,18 +8624,13 @@ static void ixgbe_get_stats64(struct net_device *netdev, for (i = 0; i < adapter->num_tx_queues; i++) { struct ixgbe_ring *ring = ACCESS_ONCE(adapter->tx_ring[i]); - u64 bytes, packets; - unsigned int start; - if (ring) { - do { - start = u64_stats_fetch_begin_irq(&ring->syncp); - packets = ring->stats.packets; - bytes = ring->stats.bytes; - } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); - stats->tx_packets += packets; - stats->tx_bytes += bytes; - } + ixgbe_get_ring_stats64(stats, ring); + } + for (i = 0; i < adapter->num_xdp_queues; i++) { + struct ixgbe_ring *ring = ACCESS_ONCE(adapter->xdp_ring[i]); + + ixgbe_get_ring_stats64(stats, ring); } rcu_read_unlock(); @@ -8948,7 +9236,9 @@ static int __ixgbe_setup_tc(struct net_device *dev, u32 handle, __be16 proto, if (tc->type != TC_SETUP_MQPRIO) return -EINVAL; - return ixgbe_setup_tc(dev, tc->tc); + tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return ixgbe_setup_tc(dev, tc->mqprio->num_tc); } #ifdef CONFIG_PCI_IOV @@ -9459,6 +9749,68 @@ ixgbe_features_check(struct sk_buff *skb, struct net_device *dev, return features; } +static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) +{ + int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct bpf_prog *old_prog; + + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) + return -EINVAL; + + if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) + return -EINVAL; + + /* verify ixgbe ring attributes are sufficient for XDP */ + for (i = 0; i < adapter->num_rx_queues; i++) { + struct ixgbe_ring *ring = adapter->rx_ring[i]; + + if (ring_is_rsc_enabled(ring)) + return -EINVAL; + + if (frame_size > ixgbe_rx_bufsz(ring)) + return -EINVAL; + } + + if (nr_cpu_ids > MAX_XDP_QUEUES) + return -ENOMEM; + + old_prog = xchg(&adapter->xdp_prog, prog); + + /* If transitioning XDP modes reconfigure rings */ + if (!!prog != !!old_prog) { + int err = ixgbe_setup_tc(dev, netdev_get_num_tc(dev)); + + if (err) { + rcu_assign_pointer(adapter->xdp_prog, old_prog); + return -EINVAL; + } + } else { + for (i = 0; i < adapter->num_rx_queues; i++) + xchg(&adapter->rx_ring[i]->xdp_prog, adapter->xdp_prog); + } + + if (old_prog) + bpf_prog_put(old_prog); + + return 0; +} + +static int ixgbe_xdp(struct net_device *dev, struct netdev_xdp *xdp) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + + switch (xdp->command) { + case XDP_SETUP_PROG: + return ixgbe_xdp_setup(dev, xdp->prog); + case XDP_QUERY_PROG: + xdp->prog_attached = !!(adapter->xdp_prog); + return 0; + default: + return -EINVAL; + } +} + static const struct net_device_ops ixgbe_netdev_ops = { .ndo_open = ixgbe_open, .ndo_stop = ixgbe_close, @@ -9504,6 +9856,7 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_udp_tunnel_add = ixgbe_add_udp_tunnel_port, .ndo_udp_tunnel_del = ixgbe_del_udp_tunnel_port, .ndo_features_check = ixgbe_features_check, + .ndo_xdp = ixgbe_xdp, }; /** @@ -9808,7 +10161,7 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ixgbe_init_mbx_params_pf(hw); hw->mbx.ops = ii->mbx_ops; pci_sriov_set_totalvfs(pdev, IXGBE_MAX_VFS_DRV_LIMIT); - ixgbe_enable_sriov(adapter); + ixgbe_enable_sriov(adapter, max_vfs); skip_sriov: #endif @@ -9934,6 +10287,9 @@ skip_sriov: if (err) goto err_sw_init; + for (i = 0; i < adapter->num_xdp_queues; i++) + u64_stats_init(&adapter->xdp_ring[i]->syncp); + /* WOL not supported for all devices */ adapter->wol = 0; hw->eeprom.ops.read(hw, 0x2c, &adapter->eeprom_cap); @@ -10059,6 +10415,7 @@ err_sw_init: iounmap(adapter->io_addr); kfree(adapter->jump_tables[0]); kfree(adapter->mac_table); + kfree(adapter->rss_key); err_ioremap: disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state); free_netdev(netdev); @@ -10143,6 +10500,7 @@ static void ixgbe_remove(struct pci_dev *pdev) } kfree(adapter->mac_table); + kfree(adapter->rss_key); disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state); free_netdev(netdev); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index e55b2602f371..654a402f0e9e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -792,7 +792,8 @@ s32 ixgbe_setup_phy_link_speed_generic(struct ixgbe_hw *hw, hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_10_FULL; /* Setup link based on the new speed settings */ - hw->phy.ops.setup_link(hw); + if (hw->phy.ops.setup_link) + hw->phy.ops.setup_link(hw); return 0; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 044cb44747cf..8baf298a8516 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -46,88 +46,96 @@ #include "ixgbe_sriov.h" #ifdef CONFIG_PCI_IOV -static int __ixgbe_enable_sriov(struct ixgbe_adapter *adapter) +static inline void ixgbe_alloc_vf_macvlans(struct ixgbe_adapter *adapter, + unsigned int num_vfs) { struct ixgbe_hw *hw = &adapter->hw; - int num_vf_macvlans, i; struct vf_macvlans *mv_list; - - adapter->flags |= IXGBE_FLAG_SRIOV_ENABLED; - e_info(probe, "SR-IOV enabled with %d VFs\n", adapter->num_vfs); - - /* Enable VMDq flag so device will be set in VM mode */ - adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED; - if (!adapter->ring_feature[RING_F_VMDQ].limit) - adapter->ring_feature[RING_F_VMDQ].limit = 1; - adapter->ring_feature[RING_F_VMDQ].offset = adapter->num_vfs; + int num_vf_macvlans, i; num_vf_macvlans = hw->mac.num_rar_entries - - (IXGBE_MAX_PF_MACVLANS + 1 + adapter->num_vfs); + (IXGBE_MAX_PF_MACVLANS + 1 + num_vfs); + if (!num_vf_macvlans) + return; - adapter->mv_list = mv_list = kcalloc(num_vf_macvlans, - sizeof(struct vf_macvlans), - GFP_KERNEL); + mv_list = kcalloc(num_vf_macvlans, sizeof(struct vf_macvlans), + GFP_KERNEL); if (mv_list) { /* Initialize list of VF macvlans */ INIT_LIST_HEAD(&adapter->vf_mvs.l); for (i = 0; i < num_vf_macvlans; i++) { - mv_list->vf = -1; - mv_list->free = true; - list_add(&mv_list->l, &adapter->vf_mvs.l); - mv_list++; + mv_list[i].vf = -1; + mv_list[i].free = true; + list_add(&mv_list[i].l, &adapter->vf_mvs.l); } + adapter->mv_list = mv_list; } +} + +static int __ixgbe_enable_sriov(struct ixgbe_adapter *adapter, + unsigned int num_vfs) +{ + struct ixgbe_hw *hw = &adapter->hw; + int i; + + adapter->flags |= IXGBE_FLAG_SRIOV_ENABLED; + + /* Enable VMDq flag so device will be set in VM mode */ + adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED; + if (!adapter->ring_feature[RING_F_VMDQ].limit) + adapter->ring_feature[RING_F_VMDQ].limit = 1; + + /* Allocate memory for per VF control structures */ + adapter->vfinfo = kcalloc(num_vfs, sizeof(struct vf_data_storage), + GFP_KERNEL); + if (!adapter->vfinfo) + return -ENOMEM; + + adapter->num_vfs = num_vfs; + + ixgbe_alloc_vf_macvlans(adapter, num_vfs); + adapter->ring_feature[RING_F_VMDQ].offset = num_vfs; /* Initialize default switching mode VEB */ IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN); adapter->bridge_mode = BRIDGE_MODE_VEB; - /* If call to enable VFs succeeded then allocate memory - * for per VF control structures. - */ - adapter->vfinfo = - kcalloc(adapter->num_vfs, - sizeof(struct vf_data_storage), GFP_KERNEL); - if (adapter->vfinfo) { - /* limit trafffic classes based on VFs enabled */ - if ((adapter->hw.mac.type == ixgbe_mac_82599EB) && - (adapter->num_vfs < 16)) { - adapter->dcb_cfg.num_tcs.pg_tcs = MAX_TRAFFIC_CLASS; - adapter->dcb_cfg.num_tcs.pfc_tcs = MAX_TRAFFIC_CLASS; - } else if (adapter->num_vfs < 32) { - adapter->dcb_cfg.num_tcs.pg_tcs = 4; - adapter->dcb_cfg.num_tcs.pfc_tcs = 4; - } else { - adapter->dcb_cfg.num_tcs.pg_tcs = 1; - adapter->dcb_cfg.num_tcs.pfc_tcs = 1; - } - - /* Disable RSC when in SR-IOV mode */ - adapter->flags2 &= ~(IXGBE_FLAG2_RSC_CAPABLE | - IXGBE_FLAG2_RSC_ENABLED); + /* limit trafffic classes based on VFs enabled */ + if ((adapter->hw.mac.type == ixgbe_mac_82599EB) && (num_vfs < 16)) { + adapter->dcb_cfg.num_tcs.pg_tcs = MAX_TRAFFIC_CLASS; + adapter->dcb_cfg.num_tcs.pfc_tcs = MAX_TRAFFIC_CLASS; + } else if (num_vfs < 32) { + adapter->dcb_cfg.num_tcs.pg_tcs = 4; + adapter->dcb_cfg.num_tcs.pfc_tcs = 4; + } else { + adapter->dcb_cfg.num_tcs.pg_tcs = 1; + adapter->dcb_cfg.num_tcs.pfc_tcs = 1; + } - for (i = 0; i < adapter->num_vfs; i++) { - /* enable spoof checking for all VFs */ - adapter->vfinfo[i].spoofchk_enabled = true; + /* Disable RSC when in SR-IOV mode */ + adapter->flags2 &= ~(IXGBE_FLAG2_RSC_CAPABLE | + IXGBE_FLAG2_RSC_ENABLED); - /* We support VF RSS querying only for 82599 and x540 - * devices at the moment. These devices share RSS - * indirection table and RSS hash key with PF therefore - * we want to disable the querying by default. - */ - adapter->vfinfo[i].rss_query_enabled = 0; + for (i = 0; i < num_vfs; i++) { + /* enable spoof checking for all VFs */ + adapter->vfinfo[i].spoofchk_enabled = true; - /* Untrust all VFs */ - adapter->vfinfo[i].trusted = false; + /* We support VF RSS querying only for 82599 and x540 + * devices at the moment. These devices share RSS + * indirection table and RSS hash key with PF therefore + * we want to disable the querying by default. + */ + adapter->vfinfo[i].rss_query_enabled = 0; - /* set the default xcast mode */ - adapter->vfinfo[i].xcast_mode = IXGBEVF_XCAST_MODE_NONE; - } + /* Untrust all VFs */ + adapter->vfinfo[i].trusted = false; - return 0; + /* set the default xcast mode */ + adapter->vfinfo[i].xcast_mode = IXGBEVF_XCAST_MODE_NONE; } - return -ENOMEM; + e_info(probe, "SR-IOV enabled with %d VFs\n", num_vfs); + return 0; } /** @@ -165,12 +173,13 @@ static void ixgbe_get_vfs(struct ixgbe_adapter *adapter) /* Note this function is called when the user wants to enable SR-IOV * VFs using the now deprecated module parameter */ -void ixgbe_enable_sriov(struct ixgbe_adapter *adapter) +void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, unsigned int max_vfs) { int pre_existing_vfs = 0; + unsigned int num_vfs; pre_existing_vfs = pci_num_vf(adapter->pdev); - if (!pre_existing_vfs && !adapter->num_vfs) + if (!pre_existing_vfs && !max_vfs) return; /* If there are pre-existing VFs then we have to force @@ -180,7 +189,7 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter) * have been created via the new PCI SR-IOV sysfs interface. */ if (pre_existing_vfs) { - adapter->num_vfs = pre_existing_vfs; + num_vfs = pre_existing_vfs; dev_warn(&adapter->pdev->dev, "Virtual Functions already enabled for this device - Please reload all VF drivers to avoid spoofed packet errors\n"); } else { @@ -192,17 +201,16 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter) * physical function. If the user requests greater than * 63 VFs then it is an error - reset to default of zero. */ - adapter->num_vfs = min_t(unsigned int, adapter->num_vfs, IXGBE_MAX_VFS_DRV_LIMIT); + num_vfs = min_t(unsigned int, max_vfs, IXGBE_MAX_VFS_DRV_LIMIT); - err = pci_enable_sriov(adapter->pdev, adapter->num_vfs); + err = pci_enable_sriov(adapter->pdev, num_vfs); if (err) { e_err(probe, "Failed to enable PCI sriov: %d\n", err); - adapter->num_vfs = 0; return; } } - if (!__ixgbe_enable_sriov(adapter)) { + if (!__ixgbe_enable_sriov(adapter, num_vfs)) { ixgbe_get_vfs(adapter); return; } @@ -298,6 +306,7 @@ static int ixgbe_pci_sriov_enable(struct pci_dev *dev, int num_vfs) #ifdef CONFIG_PCI_IOV struct ixgbe_adapter *adapter = pci_get_drvdata(dev); int err = 0; + u8 num_tc; int i; int pre_existing_vfs = pci_num_vf(dev); @@ -310,23 +319,41 @@ static int ixgbe_pci_sriov_enable(struct pci_dev *dev, int num_vfs) return err; /* While the SR-IOV capability structure reports total VFs to be 64, - * we have to limit the actual number allocated based on two factors. + * we limit the actual number allocated as below based on two factors. + * Num_TCs MAX_VFs + * 1 63 + * <=4 31 + * >4 15 * First, we reserve some transmit/receive resources for the PF. * Second, VMDQ also uses the same pools that SR-IOV does. We need to * account for this, so that we don't accidentally allocate more VFs * than we have available pools. The PCI bus driver already checks for * other values out of range. */ - if ((num_vfs + adapter->num_rx_pools) > IXGBE_MAX_VF_FUNCTIONS) - return -EPERM; + num_tc = netdev_get_num_tc(adapter->netdev); - adapter->num_vfs = num_vfs; + if (num_tc > 4) { + if ((num_vfs + adapter->num_rx_pools) > IXGBE_MAX_VFS_8TC) { + e_dev_err("Currently the device is configured with %d TCs, Creating more than %d VFs is not allowed\n", num_tc, IXGBE_MAX_VFS_8TC); + return -EPERM; + } + } else if ((num_tc > 1) && (num_tc <= 4)) { + if ((num_vfs + adapter->num_rx_pools) > IXGBE_MAX_VFS_4TC) { + e_dev_err("Currently the device is configured with %d TCs, Creating more than %d VFs is not allowed\n", num_tc, IXGBE_MAX_VFS_4TC); + return -EPERM; + } + } else { + if ((num_vfs + adapter->num_rx_pools) > IXGBE_MAX_VFS_1TC) { + e_dev_err("Currently the device is configured with %d TCs, Creating more than %d VFs is not allowed\n", num_tc, IXGBE_MAX_VFS_1TC); + return -EPERM; + } + } - err = __ixgbe_enable_sriov(adapter); + err = __ixgbe_enable_sriov(adapter, num_vfs); if (err) return err; - for (i = 0; i < adapter->num_vfs; i++) + for (i = 0; i < num_vfs; i++) ixgbe_vf_configuration(dev, (i | 0x10000000)); /* reset before enabling SRIOV to avoid mailbox issues */ @@ -650,58 +677,6 @@ update_vlvfb: } } -static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf) -{ - struct ixgbe_hw *hw = &adapter->hw; - struct vf_data_storage *vfinfo = &adapter->vfinfo[vf]; - u8 num_tcs = netdev_get_num_tc(adapter->netdev); - - /* remove VLAN filters beloning to this VF */ - ixgbe_clear_vf_vlans(adapter, vf); - - /* add back PF assigned VLAN or VLAN 0 */ - ixgbe_set_vf_vlan(adapter, true, vfinfo->pf_vlan, vf); - - /* reset offloads to defaults */ - ixgbe_set_vmolr(hw, vf, !vfinfo->pf_vlan); - - /* set outgoing tags for VFs */ - if (!vfinfo->pf_vlan && !vfinfo->pf_qos && !num_tcs) { - ixgbe_clear_vmvir(adapter, vf); - } else { - if (vfinfo->pf_qos || !num_tcs) - ixgbe_set_vmvir(adapter, vfinfo->pf_vlan, - vfinfo->pf_qos, vf); - else - ixgbe_set_vmvir(adapter, vfinfo->pf_vlan, - adapter->default_up, vf); - - if (vfinfo->spoofchk_enabled) - hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf); - } - - /* reset multicast table array for vf */ - adapter->vfinfo[vf].num_vf_mc_hashes = 0; - - /* Flush and reset the mta with the new values */ - ixgbe_set_rx_mode(adapter->netdev); - - ixgbe_del_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf); - - /* reset VF api back to unknown */ - adapter->vfinfo[vf].vf_api = ixgbe_mbox_api_10; -} - -static int ixgbe_set_vf_mac(struct ixgbe_adapter *adapter, - int vf, unsigned char *mac_addr) -{ - ixgbe_del_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf); - memcpy(adapter->vfinfo[vf].vf_mac_addresses, mac_addr, ETH_ALEN); - ixgbe_add_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf); - - return 0; -} - static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter, int vf, int index, unsigned char *mac_addr) { @@ -757,6 +732,59 @@ static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter, return 0; } +static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct vf_data_storage *vfinfo = &adapter->vfinfo[vf]; + u8 num_tcs = netdev_get_num_tc(adapter->netdev); + + /* remove VLAN filters beloning to this VF */ + ixgbe_clear_vf_vlans(adapter, vf); + + /* add back PF assigned VLAN or VLAN 0 */ + ixgbe_set_vf_vlan(adapter, true, vfinfo->pf_vlan, vf); + + /* reset offloads to defaults */ + ixgbe_set_vmolr(hw, vf, !vfinfo->pf_vlan); + + /* set outgoing tags for VFs */ + if (!vfinfo->pf_vlan && !vfinfo->pf_qos && !num_tcs) { + ixgbe_clear_vmvir(adapter, vf); + } else { + if (vfinfo->pf_qos || !num_tcs) + ixgbe_set_vmvir(adapter, vfinfo->pf_vlan, + vfinfo->pf_qos, vf); + else + ixgbe_set_vmvir(adapter, vfinfo->pf_vlan, + adapter->default_up, vf); + + if (vfinfo->spoofchk_enabled) + hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf); + } + + /* reset multicast table array for vf */ + adapter->vfinfo[vf].num_vf_mc_hashes = 0; + + /* Flush and reset the mta with the new values */ + ixgbe_set_rx_mode(adapter->netdev); + + ixgbe_del_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf); + ixgbe_set_vf_macvlan(adapter, vf, 0, NULL); + + /* reset VF api back to unknown */ + adapter->vfinfo[vf].vf_api = ixgbe_mbox_api_10; +} + +static int ixgbe_set_vf_mac(struct ixgbe_adapter *adapter, + int vf, unsigned char *mac_addr) +{ + ixgbe_del_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf); + memcpy(adapter->vfinfo[vf].vf_mac_addresses, mac_addr, ETH_ALEN); + ixgbe_add_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf); + + return 0; +} + int ixgbe_vf_configuration(struct pci_dev *pdev, unsigned int event_mask) { struct ixgbe_adapter *adapter = pci_get_drvdata(pdev); @@ -1085,7 +1113,7 @@ static int ixgbe_get_vf_rss_key(struct ixgbe_adapter *adapter, return -EOPNOTSUPP; } - memcpy(rss_key, adapter->rss_key, sizeof(adapter->rss_key)); + memcpy(rss_key, adapter->rss_key, IXGBE_RSS_KEY_SIZE); return 0; } @@ -1319,18 +1347,26 @@ void ixgbe_ping_all_vfs(struct ixgbe_adapter *adapter) int ixgbe_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) { struct ixgbe_adapter *adapter = netdev_priv(netdev); - if (!is_valid_ether_addr(mac) || (vf >= adapter->num_vfs)) + + if (vf >= adapter->num_vfs) + return -EINVAL; + + if (is_zero_ether_addr(mac)) { + adapter->vfinfo[vf].pf_set_mac = false; + dev_info(&adapter->pdev->dev, "removing MAC on VF %d\n", vf); + } else if (is_valid_ether_addr(mac)) { + adapter->vfinfo[vf].pf_set_mac = true; + dev_info(&adapter->pdev->dev, "setting MAC %pM on VF %d\n", + mac, vf); + dev_info(&adapter->pdev->dev, "Reload the VF driver to make this change effective."); + if (test_bit(__IXGBE_DOWN, &adapter->state)) { + dev_warn(&adapter->pdev->dev, "The VF MAC address has been set, but the PF device is not up.\n"); + dev_warn(&adapter->pdev->dev, "Bring the PF device up before attempting to use the VF device.\n"); + } + } else { return -EINVAL; - adapter->vfinfo[vf].pf_set_mac = true; - dev_info(&adapter->pdev->dev, "setting MAC %pM on VF %d\n", mac, vf); - dev_info(&adapter->pdev->dev, "Reload the VF driver to make this" - " change effective."); - if (test_bit(__IXGBE_DOWN, &adapter->state)) { - dev_warn(&adapter->pdev->dev, "The VF MAC address has been set," - " but the PF device is not up.\n"); - dev_warn(&adapter->pdev->dev, "Bring the PF device up before" - " attempting to use the VF device.\n"); } + return ixgbe_set_vf_mac(adapter, vf, mac); } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h index 0c7977d27b71..cf67b9b18ed7 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h @@ -33,6 +33,9 @@ * 63 (IXGBE_MAX_VF_FUNCTIONS - 1) */ #define IXGBE_MAX_VFS_DRV_LIMIT (IXGBE_MAX_VF_FUNCTIONS - 1) +#define IXGBE_MAX_VFS_1TC IXGBE_MAX_VF_FUNCTIONS +#define IXGBE_MAX_VFS_4TC 32 +#define IXGBE_MAX_VFS_8TC 16 #ifdef CONFIG_PCI_IOV void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter); @@ -56,7 +59,7 @@ int ixgbe_ndo_get_vf_config(struct net_device *netdev, void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter); int ixgbe_disable_sriov(struct ixgbe_adapter *adapter); #ifdef CONFIG_PCI_IOV -void ixgbe_enable_sriov(struct ixgbe_adapter *adapter); +void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, unsigned int max_vfs); #endif int ixgbe_pci_sriov_configure(struct pci_dev *dev, int num_vfs); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index 1d07f2ead914..9c2460c5ef1b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -85,6 +85,7 @@ #define IXGBE_DEV_ID_X550EM_X_SFP 0x15AC #define IXGBE_DEV_ID_X550EM_X_10G_T 0x15AD #define IXGBE_DEV_ID_X550EM_X_1G_T 0x15AE +#define IXGBE_DEV_ID_X550EM_X_XFI 0x15B0 #define IXGBE_DEV_ID_X550EM_A_KR 0x15C2 #define IXGBE_DEV_ID_X550EM_A_KR_L 0x15C3 #define IXGBE_DEV_ID_X550EM_A_SFP_N 0x15C4 @@ -1387,9 +1388,6 @@ struct ixgbe_thermal_sensor_data { #define ATH_PHY_ID 0x03429050 #define AQ_FW_REV 0x20 -/* PHY Types */ -#define IXGBE_M88E1145_E_PHY_ID 0x01410CD0 - /* Special PHY Init Routine */ #define IXGBE_PHY_INIT_OFFSET_NL 0x002B #define IXGBE_PHY_INIT_END_NL 0xFFFF @@ -3128,7 +3126,9 @@ enum ixgbe_phy_type { ixgbe_phy_aq, ixgbe_phy_x550em_kr, ixgbe_phy_x550em_kx4, + ixgbe_phy_x550em_xfi, ixgbe_phy_x550em_ext_t, + ixgbe_phy_ext_1g_t, ixgbe_phy_cu_unknown, ixgbe_phy_qt, ixgbe_phy_xaui, @@ -3754,15 +3754,6 @@ struct ixgbe_info { #define IXGBE_KRM_TX_COEFF_CTRL_1_CZERO_EN BIT(3) #define IXGBE_KRM_TX_COEFF_CTRL_1_OVRRD_EN BIT(31) -#define IXGBE_KX4_LINK_CNTL_1 0x4C -#define IXGBE_KX4_LINK_CNTL_1_TETH_AN_CAP_KX BIT(16) -#define IXGBE_KX4_LINK_CNTL_1_TETH_AN_CAP_KX4 BIT(17) -#define IXGBE_KX4_LINK_CNTL_1_TETH_EEE_CAP_KX BIT(24) -#define IXGBE_KX4_LINK_CNTL_1_TETH_EEE_CAP_KX4 BIT(25) -#define IXGBE_KX4_LINK_CNTL_1_TETH_AN_ENABLE BIT(29) -#define IXGBE_KX4_LINK_CNTL_1_TETH_FORCE_LINK_UP BIT(30) -#define IXGBE_KX4_LINK_CNTL_1_TETH_AN_RESTART BIT(31) - #define IXGBE_SB_IOSF_INDIRECT_CTRL 0x00011144 #define IXGBE_SB_IOSF_INDIRECT_DATA 0x00011148 @@ -3779,12 +3770,14 @@ struct ixgbe_info { #define IXGBE_SB_IOSF_CTRL_BUSY_SHIFT 31 #define IXGBE_SB_IOSF_CTRL_BUSY BIT(IXGBE_SB_IOSF_CTRL_BUSY_SHIFT) #define IXGBE_SB_IOSF_TARGET_KR_PHY 0 -#define IXGBE_SB_IOSF_TARGET_KX4_UNIPHY 1 -#define IXGBE_SB_IOSF_TARGET_KX4_PCS0 2 -#define IXGBE_SB_IOSF_TARGET_KX4_PCS1 3 #define IXGBE_NW_MNG_IF_SEL 0x00011178 #define IXGBE_NW_MNG_IF_SEL_MDIO_ACT BIT(1) +#define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_10M BIT(17) +#define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_100M BIT(18) +#define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_1G BIT(19) +#define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_2_5G BIT(20) +#define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_10G BIT(21) #define IXGBE_NW_MNG_IF_SEL_ENABLE_10_100M BIT(23) #define IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE BIT(24) #define IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD_SHIFT 3 diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c index 84a467a8ed3d..6ea0d6a5fb90 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c @@ -95,6 +95,7 @@ s32 ixgbe_reset_hw_X540(struct ixgbe_hw *hw) { s32 status; u32 ctrl, i; + u32 swfw_mask = hw->phy.phy_semaphore_mask; /* Call adapter stop to disable tx/rx and clear interrupts */ status = hw->mac.ops.stop_adapter(hw); @@ -105,10 +106,17 @@ s32 ixgbe_reset_hw_X540(struct ixgbe_hw *hw) ixgbe_clear_tx_pending(hw); mac_reset_top: + status = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask); + if (status) { + hw_dbg(hw, "semaphore failed with %d", status); + return IXGBE_ERR_SWFW_SYNC; + } + ctrl = IXGBE_CTRL_RST; ctrl |= IXGBE_READ_REG(hw, IXGBE_CTRL); IXGBE_WRITE_REG(hw, IXGBE_CTRL, ctrl); IXGBE_WRITE_FLUSH(hw); + hw->mac.ops.release_swfw_sync(hw, swfw_mask); usleep_range(1000, 1200); /* Poll for reset bit to self-clear indicating reset is complete */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 200f847fd8f3..2ba024b575ea 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -49,6 +49,18 @@ static s32 ixgbe_get_invariants_X550_x(struct ixgbe_hw *hw) return 0; } +static s32 ixgbe_get_invariants_X550_x_fw(struct ixgbe_hw *hw) +{ + struct ixgbe_phy_info *phy = &hw->phy; + + /* Start with X540 invariants, since so similar */ + ixgbe_get_invariants_X540(hw); + + phy->ops.set_phy_power = NULL; + + return 0; +} + static s32 ixgbe_get_invariants_X550_a(struct ixgbe_hw *hw) { struct ixgbe_mac_info *mac = &hw->mac; @@ -320,6 +332,9 @@ static s32 ixgbe_identify_phy_x550em(struct ixgbe_hw *hw) case IXGBE_DEV_ID_X550EM_X_KX4: hw->phy.type = ixgbe_phy_x550em_kx4; break; + case IXGBE_DEV_ID_X550EM_X_XFI: + hw->phy.type = ixgbe_phy_x550em_xfi; + break; case IXGBE_DEV_ID_X550EM_X_KR: case IXGBE_DEV_ID_X550EM_A_KR: case IXGBE_DEV_ID_X550EM_A_KR_L: @@ -331,9 +346,21 @@ static s32 ixgbe_identify_phy_x550em(struct ixgbe_hw *hw) else hw->phy.phy_semaphore_mask = IXGBE_GSSR_PHY0_SM; /* Fallthrough */ - case IXGBE_DEV_ID_X550EM_X_1G_T: case IXGBE_DEV_ID_X550EM_X_10G_T: return ixgbe_identify_phy_generic(hw); + case IXGBE_DEV_ID_X550EM_X_1G_T: + hw->phy.type = ixgbe_phy_ext_1g_t; + break; + case IXGBE_DEV_ID_X550EM_A_1G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T_L: + hw->phy.type = ixgbe_phy_fw; + hw->phy.ops.read_reg = NULL; + hw->phy.ops.write_reg = NULL; + if (hw->bus.lan_id) + hw->phy.phy_semaphore_mask |= IXGBE_GSSR_PHY1_SM; + else + hw->phy.phy_semaphore_mask |= IXGBE_GSSR_PHY0_SM; + break; default: break; } @@ -2145,6 +2172,8 @@ static void ixgbe_init_mac_link_ops_X550em(struct ixgbe_hw *hw) ixgbe_set_soft_rate_select_speed; break; case ixgbe_media_type_copper: + if (hw->device_id == IXGBE_DEV_ID_X550EM_X_1G_T) + break; mac->ops.setup_link = ixgbe_setup_mac_link_t_X550em; mac->ops.setup_fc = ixgbe_setup_fc_generic; mac->ops.check_link = ixgbe_check_link_t_X550em; @@ -2215,8 +2244,39 @@ static s32 ixgbe_get_link_capabilities_X550em(struct ixgbe_hw *hw, else *speed = IXGBE_LINK_SPEED_10GB_FULL; } else { - *speed = IXGBE_LINK_SPEED_10GB_FULL | - IXGBE_LINK_SPEED_1GB_FULL; + switch (hw->phy.type) { + case ixgbe_phy_x550em_kx4: + *speed = IXGBE_LINK_SPEED_1GB_FULL | + IXGBE_LINK_SPEED_2_5GB_FULL | + IXGBE_LINK_SPEED_10GB_FULL; + break; + case ixgbe_phy_x550em_xfi: + *speed = IXGBE_LINK_SPEED_1GB_FULL | + IXGBE_LINK_SPEED_10GB_FULL; + break; + case ixgbe_phy_ext_1g_t: + case ixgbe_phy_sgmii: + *speed = IXGBE_LINK_SPEED_1GB_FULL; + break; + case ixgbe_phy_x550em_kr: + if (hw->mac.type == ixgbe_mac_x550em_a) { + /* check different backplane modes */ + if (hw->phy.nw_mng_if_sel & + IXGBE_NW_MNG_IF_SEL_PHY_SPEED_2_5G) { + *speed = IXGBE_LINK_SPEED_2_5GB_FULL; + break; + } else if (hw->device_id == + IXGBE_DEV_ID_X550EM_A_KR_L) { + *speed = IXGBE_LINK_SPEED_1GB_FULL; + break; + } + } + /* fall through */ + default: + *speed = IXGBE_LINK_SPEED_10GB_FULL | + IXGBE_LINK_SPEED_1GB_FULL; + break; + } *autoneg = true; } return 0; @@ -2473,44 +2533,6 @@ static s32 ixgbe_setup_kr_speed_x550em(struct ixgbe_hw *hw, return ixgbe_restart_an_internal_phy_x550em(hw); } -/** ixgbe_setup_kx4_x550em - Configure the KX4 PHY. - * @hw: pointer to hardware structure - * - * Configures the integrated KX4 PHY. - **/ -static s32 ixgbe_setup_kx4_x550em(struct ixgbe_hw *hw) -{ - s32 status; - u32 reg_val; - - status = hw->mac.ops.read_iosf_sb_reg(hw, IXGBE_KX4_LINK_CNTL_1, - IXGBE_SB_IOSF_TARGET_KX4_PCS0 + - hw->bus.lan_id, ®_val); - if (status) - return status; - - reg_val &= ~(IXGBE_KX4_LINK_CNTL_1_TETH_AN_CAP_KX4 | - IXGBE_KX4_LINK_CNTL_1_TETH_AN_CAP_KX); - - reg_val |= IXGBE_KX4_LINK_CNTL_1_TETH_AN_ENABLE; - - /* Advertise 10G support. */ - if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL) - reg_val |= IXGBE_KX4_LINK_CNTL_1_TETH_AN_CAP_KX4; - - /* Advertise 1G support. */ - if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) - reg_val |= IXGBE_KX4_LINK_CNTL_1_TETH_AN_CAP_KX; - - /* Restart auto-negotiation. */ - reg_val |= IXGBE_KX4_LINK_CNTL_1_TETH_AN_RESTART; - status = hw->mac.ops.write_iosf_sb_reg(hw, IXGBE_KX4_LINK_CNTL_1, - IXGBE_SB_IOSF_TARGET_KX4_PCS0 + - hw->bus.lan_id, reg_val); - - return status; -} - /** * ixgbe_setup_kr_x550em - Configure the KR PHY * @hw: pointer to hardware structure @@ -2521,6 +2543,9 @@ static s32 ixgbe_setup_kr_x550em(struct ixgbe_hw *hw) if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_2_5GB_FULL) return 0; + if (ixgbe_check_reset_blocked(hw)) + return 0; + return ixgbe_setup_kr_speed_x550em(hw, hw->phy.autoneg_advertised); } @@ -3134,7 +3159,7 @@ static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw) /* Set functions pointers based on phy type */ switch (hw->phy.type) { case ixgbe_phy_x550em_kx4: - phy->ops.setup_link = ixgbe_setup_kx4_x550em; + phy->ops.setup_link = NULL; phy->ops.read_reg = ixgbe_read_phy_reg_x550em; phy->ops.write_reg = ixgbe_write_phy_reg_x550em; break; @@ -3143,6 +3168,12 @@ static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw) phy->ops.read_reg = ixgbe_read_phy_reg_x550em; phy->ops.write_reg = ixgbe_write_phy_reg_x550em; break; + case ixgbe_phy_x550em_xfi: + /* link is managed by HW */ + phy->ops.setup_link = NULL; + phy->ops.read_reg = ixgbe_read_phy_reg_x550em; + phy->ops.write_reg = ixgbe_write_phy_reg_x550em; + break; case ixgbe_phy_x550em_ext_t: /* Save NW management interface connected on board. This is used * to determine internal PHY mode @@ -3164,10 +3195,18 @@ static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw) phy->ops.handle_lasi = ixgbe_handle_lasi_ext_t_x550em; phy->ops.reset = ixgbe_reset_phy_t_X550em; break; + case ixgbe_phy_sgmii: + phy->ops.setup_link = NULL; + break; case ixgbe_phy_fw: phy->ops.setup_link = ixgbe_setup_fw_link; phy->ops.reset = ixgbe_reset_phy_fw; break; + case ixgbe_phy_ext_1g_t: + phy->ops.setup_link = NULL; + phy->ops.read_reg = NULL; + phy->ops.write_reg = NULL; + break; default: break; } @@ -3193,6 +3232,7 @@ static enum ixgbe_media_type ixgbe_get_media_type_X550em(struct ixgbe_hw *hw) /* Fallthrough */ case IXGBE_DEV_ID_X550EM_X_KR: case IXGBE_DEV_ID_X550EM_X_KX4: + case IXGBE_DEV_ID_X550EM_X_XFI: case IXGBE_DEV_ID_X550EM_A_KR: case IXGBE_DEV_ID_X550EM_A_KR_L: media_type = ixgbe_media_type_backplane; @@ -3300,6 +3340,7 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) u32 ctrl = 0; u32 i; bool link_up = false; + u32 swfw_mask = hw->phy.phy_semaphore_mask; /* Call adapter stop to disable Tx/Rx and clear interrupts */ status = hw->mac.ops.stop_adapter(hw); @@ -3345,9 +3386,16 @@ mac_reset_top: ctrl = IXGBE_CTRL_RST; } + status = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask); + if (status) { + hw_dbg(hw, "semaphore failed with %d", status); + return IXGBE_ERR_SWFW_SYNC; + } + ctrl |= IXGBE_READ_REG(hw, IXGBE_CTRL); IXGBE_WRITE_REG(hw, IXGBE_CTRL, ctrl); IXGBE_WRITE_FLUSH(hw); + hw->mac.ops.release_swfw_sync(hw, swfw_mask); usleep_range(1000, 1200); /* Poll for reset bit to self-clear meaning reset is complete */ @@ -3780,7 +3828,7 @@ static struct ixgbe_mac_operations mac_ops_x550em_a = { .get_media_type = ixgbe_get_media_type_X550em, .get_san_mac_addr = NULL, .get_wwn_prefix = NULL, - .setup_link = NULL, /* defined later */ + .setup_link = &ixgbe_setup_mac_link_X540, .get_link_capabilities = ixgbe_get_link_capabilities_X550em, .get_bus_info = ixgbe_get_bus_info_X550em, .setup_sfp = ixgbe_setup_sfp_modules_X550em, @@ -3862,6 +3910,17 @@ static const struct ixgbe_phy_operations phy_ops_X550EM_x = { .write_reg = &ixgbe_write_phy_reg_generic, }; +static const struct ixgbe_phy_operations phy_ops_x550em_x_fw = { + X550_COMMON_PHY + .check_overtemp = NULL, + .init = ixgbe_init_phy_ops_X550em, + .identify = ixgbe_identify_phy_x550em, + .read_reg = NULL, + .write_reg = NULL, + .read_reg_mdi = NULL, + .write_reg_mdi = NULL, +}; + static const struct ixgbe_phy_operations phy_ops_x550em_a = { X550_COMMON_PHY .check_overtemp = &ixgbe_tn_check_overtemp, @@ -3924,6 +3983,16 @@ const struct ixgbe_info ixgbe_X550EM_x_info = { .link_ops = &link_ops_x550em_x, }; +const struct ixgbe_info ixgbe_x550em_x_fw_info = { + .mac = ixgbe_mac_X550EM_x, + .get_invariants = ixgbe_get_invariants_X550_x_fw, + .mac_ops = &mac_ops_X550EM_x, + .eeprom_ops = &eeprom_ops_X550EM_x, + .phy_ops = &phy_ops_x550em_x_fw, + .mbx_ops = &mbx_ops_generic, + .mvals = ixgbe_mvals_X550EM_x, +}; + const struct ixgbe_info ixgbe_x550em_a_info = { .mac = ixgbe_mac_x550em_a, .get_invariants = &ixgbe_get_invariants_X550_a, diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c index 1f6c0ecd50bb..ff9d05f308ee 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c +++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c @@ -80,7 +80,7 @@ static struct ixgbe_stats ixgbevf_gstrings_stats[] = { #define IXGBEVF_QUEUE_STATS_LEN ( \ (((struct ixgbevf_adapter *)netdev_priv(netdev))->num_tx_queues + \ ((struct ixgbevf_adapter *)netdev_priv(netdev))->num_rx_queues) * \ - (sizeof(struct ixgbe_stats) / sizeof(u64))) + (sizeof(struct ixgbevf_stats) / sizeof(u64))) #define IXGBEVF_GLOBAL_STATS_LEN ARRAY_SIZE(ixgbevf_gstrings_stats) #define IXGBEVF_STATS_LEN (IXGBEVF_GLOBAL_STATS_LEN + IXGBEVF_QUEUE_STATS_LEN) @@ -91,18 +91,18 @@ static const char ixgbe_gstrings_test[][ETH_GSTRING_LEN] = { #define IXGBEVF_TEST_LEN (sizeof(ixgbe_gstrings_test) / ETH_GSTRING_LEN) -static int ixgbevf_get_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) +static int ixgbevf_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; u32 link_speed = 0; bool link_up; - ecmd->supported = SUPPORTED_10000baseT_Full; - ecmd->autoneg = AUTONEG_DISABLE; - ecmd->transceiver = XCVR_DUMMY1; - ecmd->port = -1; + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_add_link_mode(cmd, supported, 10000baseT_Full); + cmd->base.autoneg = AUTONEG_DISABLE; + cmd->base.port = -1; hw->mac.get_link_status = 1; hw->mac.ops.check_link(hw, &link_speed, &link_up, false); @@ -122,11 +122,11 @@ static int ixgbevf_get_settings(struct net_device *netdev, break; } - ethtool_cmd_speed_set(ecmd, speed); - ecmd->duplex = DUPLEX_FULL; + cmd->base.speed = speed; + cmd->base.duplex = DUPLEX_FULL; } else { - ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN); - ecmd->duplex = DUPLEX_UNKNOWN; + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; } return 0; @@ -855,7 +855,8 @@ static int ixgbevf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, if (adapter->hw.mac.type >= ixgbe_mac_X550_vf) { if (key) - memcpy(key, adapter->rss_key, sizeof(adapter->rss_key)); + memcpy(key, adapter->rss_key, + ixgbevf_get_rxfh_key_size(netdev)); if (indir) { int i; @@ -885,7 +886,6 @@ static int ixgbevf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, } static const struct ethtool_ops ixgbevf_ethtool_ops = { - .get_settings = ixgbevf_get_settings, .get_drvinfo = ixgbevf_get_drvinfo, .get_regs_len = ixgbevf_get_regs_len, .get_regs = ixgbevf_get_regs, @@ -905,6 +905,7 @@ static const struct ethtool_ops ixgbevf_ethtool_ops = { .get_rxfh_indir_size = ixgbevf_get_rxfh_indir_size, .get_rxfh_key_size = ixgbevf_get_rxfh_key_size, .get_rxfh = ixgbevf_get_rxfh, + .get_link_ksettings = ixgbevf_get_link_ksettings, }; void ixgbevf_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h index a8cbc2dda0dd..581f44bbd7b3 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h @@ -319,7 +319,7 @@ struct ixgbevf_adapter { spinlock_t mbx_lock; unsigned long last_reset; - u32 rss_key[IXGBEVF_VFRSSRK_REGS]; + u32 *rss_key; u8 rss_indir_tbl[IXGBEVF_X550_VFRETA_SIZE]; }; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 80bab261a0ec..eee29bddddc1 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1660,6 +1660,28 @@ static void ixgbevf_rx_desc_queue_enable(struct ixgbevf_adapter *adapter, reg_idx); } +/** + * ixgbevf_init_rss_key - Initialize adapter RSS key + * @adapter: device handle + * + * Allocates and initializes the RSS key if it is not allocated. + **/ +static inline int ixgbevf_init_rss_key(struct ixgbevf_adapter *adapter) +{ + u32 *rss_key; + + if (!adapter->rss_key) { + rss_key = kzalloc(IXGBEVF_RSS_HASH_KEY_SIZE, GFP_KERNEL); + if (unlikely(!rss_key)) + return -ENOMEM; + + netdev_rss_key_fill(rss_key, IXGBEVF_RSS_HASH_KEY_SIZE); + adapter->rss_key = rss_key; + } + + return 0; +} + static void ixgbevf_setup_vfmrqc(struct ixgbevf_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; @@ -1668,9 +1690,8 @@ static void ixgbevf_setup_vfmrqc(struct ixgbevf_adapter *adapter) u8 i, j; /* Fill out hash function seeds */ - netdev_rss_key_fill(adapter->rss_key, sizeof(adapter->rss_key)); for (i = 0; i < IXGBEVF_VFRSSRK_REGS; i++) - IXGBE_WRITE_REG(hw, IXGBE_VFRSSRK(i), adapter->rss_key[i]); + IXGBE_WRITE_REG(hw, IXGBE_VFRSSRK(i), *(adapter->rss_key + i)); for (i = 0, j = 0; i < IXGBEVF_X550_VFRETA_SIZE; i++, j++) { if (j == rss_i) @@ -2611,6 +2632,12 @@ static int ixgbevf_sw_init(struct ixgbevf_adapter *adapter) hw->mbx.ops.init_params(hw); + if (hw->mac.type >= ixgbe_mac_X550_vf) { + err = ixgbevf_init_rss_key(adapter); + if (err) + goto out; + } + /* assume legacy case in which PF would only give VF 2 queues */ hw->mac.max_tx_queues = 2; hw->mac.max_rx_queues = 2; @@ -4127,6 +4154,7 @@ err_register: err_sw_init: ixgbevf_reset_interrupt_capability(adapter); iounmap(adapter->io_addr); + kfree(adapter->rss_key); err_ioremap: disable_dev = !test_and_set_bit(__IXGBEVF_DISABLED, &adapter->state); free_netdev(netdev); @@ -4173,6 +4201,7 @@ static void ixgbevf_remove(struct pci_dev *pdev) hw_dbg(&adapter->hw, "Remove complete\n"); + kfree(adapter->rss_key); disable_dev = !test_and_set_bit(__IXGBEVF_DISABLED, &adapter->state); free_netdev(netdev); diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c index 8a5db9d7219d..b6d0c01eab10 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.c +++ b/drivers/net/ethernet/intel/ixgbevf/vf.c @@ -333,7 +333,7 @@ int ixgbevf_get_reta_locked(struct ixgbe_hw *hw, u32 *reta, int num_rx_queues) switch (hw->api_version) { case ixgbe_mbox_api_13: case ixgbe_mbox_api_12: - if (hw->mac.type >= ixgbe_mac_X550_vf) + if (hw->mac.type < ixgbe_mac_X550_vf) break; default: return -EOPNOTSUPP; @@ -399,7 +399,7 @@ int ixgbevf_get_rss_key_locked(struct ixgbe_hw *hw, u8 *rss_key) switch (hw->api_version) { case ixgbe_mbox_api_13: case ixgbe_mbox_api_12: - if (hw->mac.type >= ixgbe_mac_X550_vf) + if (hw->mac.type < ixgbe_mac_X550_vf) break; default: return -EOPNOTSUPP; @@ -419,7 +419,7 @@ int ixgbevf_get_rss_key_locked(struct ixgbe_hw *hw, u8 *rss_key) msgbuf[0] &= ~IXGBE_VT_MSGTYPE_CTS; /* If the operation has been refused by a PF return -EPERM */ - if (msgbuf[0] == (IXGBE_VF_GET_RETA | IXGBE_VT_MSGTYPE_NACK)) + if (msgbuf[0] == (IXGBE_VF_GET_RSS_KEY | IXGBE_VT_MSGTYPE_NACK)) return -EPERM; /* If we didn't get an ACK there must have been |