diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2013-05-01 14:08:52 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2013-05-01 14:08:52 -0700 |
commit | 73287a43cc79ca06629a88d1a199cd283f42456a (patch) | |
tree | acf4456e260115bea77ee31a29f10ce17f0db45c /drivers/net/ethernet/mellanox/mlx4 | |
parent | 251df49db3327c64bf917bfdba94491fde2b4ee0 (diff) | |
parent | 20074f357da4a637430aec2879c9d864c5d2c23c (diff) | |
download | linux-73287a43cc79ca06629a88d1a199cd283f42456a.tar.gz linux-73287a43cc79ca06629a88d1a199cd283f42456a.tar.bz2 linux-73287a43cc79ca06629a88d1a199cd283f42456a.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Highlights (1721 non-merge commits, this has to be a record of some
sort):
1) Add 'random' mode to team driver, from Jiri Pirko and Eric
Dumazet.
2) Make it so that any driver that supports configuration of multiple
MAC addresses can provide the forwarding database add and del
calls by providing a default implementation and hooking that up if
the driver doesn't have an explicit set of handlers. From Vlad
Yasevich.
3) Support GSO segmentation over tunnels and other encapsulating
devices such as VXLAN, from Pravin B Shelar.
4) Support L2 GRE tunnels in the flow dissector, from Michael Dalton.
5) Implement Tail Loss Probe (TLP) detection in TCP, from Nandita
Dukkipati.
6) In the PHY layer, allow supporting wake-on-lan in situations where
the PHY registers have to be written for it to be configured.
Use it to support wake-on-lan in mv643xx_eth.
From Michael Stapelberg.
7) Significantly improve firewire IPV6 support, from YOSHIFUJI
Hideaki.
8) Allow multiple packets to be sent in a single transmission using
network coding in batman-adv, from Martin Hundebøll.
9) Add support for T5 cxgb4 chips, from Santosh Rastapur.
10) Generalize the VXLAN forwarding tables so that there is more
flexibility in configurating various aspects of the endpoints.
From David Stevens.
11) Support RSS and TSO in hardware over GRE tunnels in bxn2x driver,
from Dmitry Kravkov.
12) Zero copy support in nfnelink_queue, from Eric Dumazet and Pablo
Neira Ayuso.
13) Start adding networking selftests.
14) In situations of overload on the same AF_PACKET fanout socket, or
per-cpu packet receive queue, minimize drop by distributing the
load to other cpus/fanouts. From Willem de Bruijn and Eric
Dumazet.
15) Add support for new payload offset BPF instruction, from Daniel
Borkmann.
16) Convert several drivers over to mdoule_platform_driver(), from
Sachin Kamat.
17) Provide a minimal BPF JIT image disassembler userspace tool, from
Daniel Borkmann.
18) Rewrite F-RTO implementation in TCP to match the final
specification of it in RFC4138 and RFC5682. From Yuchung Cheng.
19) Provide netlink socket diag of netlink sockets ("Yo dawg, I hear
you like netlink, so I implemented netlink dumping of netlink
sockets.") From Andrey Vagin.
20) Remove ugly passing of rtnetlink attributes into rtnl_doit
functions, from Thomas Graf.
21) Allow userspace to be able to see if a configuration change occurs
in the middle of an address or device list dump, from Nicolas
Dichtel.
22) Support RFC3168 ECN protection for ipv6 fragments, from Hannes
Frederic Sowa.
23) Increase accuracy of packet length used by packet scheduler, from
Jason Wang.
24) Beginning set of changes to make ipv4/ipv6 fragment handling more
scalable and less susceptible to overload and locking contention,
from Jesper Dangaard Brouer.
25) Get rid of using non-type-safe NLMSG_* macros and use nlmsg_*()
instead. From Hong Zhiguo.
26) Optimize route usage in IPVS by avoiding reference counting where
possible, from Julian Anastasov.
27) Convert IPVS schedulers to RCU, also from Julian Anastasov.
28) Support cpu fanouts in xt_NFQUEUE netfilter target, from Holger
Eitzenberger.
29) Network namespace support for nf_log, ebt_log, xt_LOG, ipt_ULOG,
nfnetlink_log, and nfnetlink_queue. From Gao feng.
30) Implement RFC3168 ECN protection, from Hannes Frederic Sowa.
31) Support several new r8169 chips, from Hayes Wang.
32) Support tokenized interface identifiers in ipv6, from Daniel
Borkmann.
33) Use usbnet_link_change() helper in USB net driver, from Ming Lei.
34) Add 802.1ad vlan offload support, from Patrick McHardy.
35) Support mmap() based netlink communication, also from Patrick
McHardy.
36) Support HW timestamping in mlx4 driver, from Amir Vadai.
37) Rationalize AF_PACKET packet timestamping when transmitting, from
Willem de Bruijn and Daniel Borkmann.
38) Bring parity to what's provided by /proc/net/packet socket dumping
and the info provided by netlink socket dumping of AF_PACKET
sockets. From Nicolas Dichtel.
39) Fix peeking beyond zero sized SKBs in AF_UNIX, from Benjamin
Poirier"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1722 commits)
filter: fix va_list build error
af_unix: fix a fatal race with bit fields
bnx2x: Prevent memory leak when cnic is absent
bnx2x: correct reading of speed capabilities
net: sctp: attribute printl with __printf for gcc fmt checks
netlink: kconfig: move mmap i/o into netlink kconfig
netpoll: convert mutex into a semaphore
netlink: Fix skb ref counting.
net_sched: act_ipt forward compat with xtables
mlx4_en: fix a build error on 32bit arches
Revert "bnx2x: allow nvram test to run when device is down"
bridge: avoid OOPS if root port not found
drivers: net: cpsw: fix kernel warn on cpsw irq enable
sh_eth: use random MAC address if no valid one supplied
3c509.c: call SET_NETDEV_DEV for all device types (ISA/ISAPnP/EISA)
tg3: fix to append hardware time stamping flags
unix/stream: fix peeking with an offset larger than data in queue
unix/dgram: fix peeking with an offset larger than data in queue
unix/dgram: peek beyond 0-sized skbs
openvswitch: Remove unneeded ovs_netdev_get_ifindex()
...
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx4')
21 files changed, 968 insertions, 146 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/Makefile b/drivers/net/ethernet/mellanox/mlx4/Makefile index 293127d28b33..3e9c70f15b42 100644 --- a/drivers/net/ethernet/mellanox/mlx4/Makefile +++ b/drivers/net/ethernet/mellanox/mlx4/Makefile @@ -6,5 +6,5 @@ mlx4_core-y := alloc.o catas.o cmd.o cq.o eq.o fw.o icm.o intf.o main.o mcg.o \ obj-$(CONFIG_MLX4_EN) += mlx4_en.o mlx4_en-y := en_main.o en_tx.o en_rx.o en_ethtool.o en_port.o en_cq.o \ - en_resources.o en_netdev.o en_selftest.o + en_resources.o en_netdev.o en_selftest.o en_clock.o mlx4_en-$(CONFIG_MLX4_EN_DCB) += en_dcb_nl.o diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index fdc5f23d8e9f..1df56cc50ee9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -1490,6 +1490,69 @@ out: return ret; } +static int mlx4_master_activate_admin_state(struct mlx4_priv *priv, int slave) +{ + int port, err; + struct mlx4_vport_state *vp_admin; + struct mlx4_vport_oper_state *vp_oper; + + for (port = 1; port <= MLX4_MAX_PORTS; port++) { + vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port]; + vp_admin = &priv->mfunc.master.vf_admin[slave].vport[port]; + vp_oper->state = *vp_admin; + if (MLX4_VGT != vp_admin->default_vlan) { + err = __mlx4_register_vlan(&priv->dev, port, + vp_admin->default_vlan, &(vp_oper->vlan_idx)); + if (err) { + vp_oper->vlan_idx = NO_INDX; + mlx4_warn((&priv->dev), + "No vlan resorces slave %d, port %d\n", + slave, port); + return err; + } + mlx4_dbg((&(priv->dev)), "alloc vlan %d idx %d slave %d port %d\n", + (int)(vp_oper->state.default_vlan), + vp_oper->vlan_idx, slave, port); + } + if (vp_admin->spoofchk) { + vp_oper->mac_idx = __mlx4_register_mac(&priv->dev, + port, + vp_admin->mac); + if (0 > vp_oper->mac_idx) { + err = vp_oper->mac_idx; + vp_oper->mac_idx = NO_INDX; + mlx4_warn((&priv->dev), + "No mac resorces slave %d, port %d\n", + slave, port); + return err; + } + mlx4_dbg((&(priv->dev)), "alloc mac %llx idx %d slave %d port %d\n", + vp_oper->state.mac, vp_oper->mac_idx, slave, port); + } + } + return 0; +} + +static void mlx4_master_deactivate_admin_state(struct mlx4_priv *priv, int slave) +{ + int port; + struct mlx4_vport_oper_state *vp_oper; + + for (port = 1; port <= MLX4_MAX_PORTS; port++) { + vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port]; + if (NO_INDX != vp_oper->vlan_idx) { + __mlx4_unregister_vlan(&priv->dev, + port, vp_oper->vlan_idx); + vp_oper->vlan_idx = NO_INDX; + } + if (NO_INDX != vp_oper->mac_idx) { + __mlx4_unregister_mac(&priv->dev, port, vp_oper->mac_idx); + vp_oper->mac_idx = NO_INDX; + } + } + return; +} + static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd, u16 param, u8 toggle) { @@ -1510,6 +1573,7 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd, if (cmd == MLX4_COMM_CMD_RESET) { mlx4_warn(dev, "Received reset from slave:%d\n", slave); slave_state[slave].active = false; + mlx4_master_deactivate_admin_state(priv, slave); for (i = 0; i < MLX4_EVENT_TYPES_NUM; ++i) { slave_state[slave].event_eq[i].eqn = -1; slave_state[slave].event_eq[i].token = 0; @@ -1556,6 +1620,8 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd, if (slave_state[slave].last_cmd != MLX4_COMM_CMD_VHCR2) goto reset_slave; slave_state[slave].vhcr_dma |= param; + if (mlx4_master_activate_admin_state(priv, slave)) + goto reset_slave; slave_state[slave].active = true; mlx4_dispatch_event(dev, MLX4_DEV_EVENT_SLAVE_INIT, slave); break; @@ -1732,6 +1798,18 @@ int mlx4_multi_func_init(struct mlx4_dev *dev) if (!priv->mfunc.master.slave_state) goto err_comm; + priv->mfunc.master.vf_admin = + kzalloc(dev->num_slaves * + sizeof(struct mlx4_vf_admin_state), GFP_KERNEL); + if (!priv->mfunc.master.vf_admin) + goto err_comm_admin; + + priv->mfunc.master.vf_oper = + kzalloc(dev->num_slaves * + sizeof(struct mlx4_vf_oper_state), GFP_KERNEL); + if (!priv->mfunc.master.vf_oper) + goto err_comm_oper; + for (i = 0; i < dev->num_slaves; ++i) { s_state = &priv->mfunc.master.slave_state[i]; s_state->last_cmd = MLX4_COMM_CMD_RESET; @@ -1752,6 +1830,10 @@ int mlx4_multi_func_init(struct mlx4_dev *dev) goto err_slaves; } INIT_LIST_HEAD(&s_state->mcast_filters[port]); + priv->mfunc.master.vf_admin[i].vport[port].default_vlan = MLX4_VGT; + priv->mfunc.master.vf_oper[i].vport[port].state.default_vlan = MLX4_VGT; + priv->mfunc.master.vf_oper[i].vport[port].vlan_idx = NO_INDX; + priv->mfunc.master.vf_oper[i].vport[port].mac_idx = NO_INDX; } spin_lock_init(&s_state->lock); } @@ -1800,6 +1882,10 @@ err_slaves: for (port = 1; port <= MLX4_MAX_PORTS; port++) kfree(priv->mfunc.master.slave_state[i].vlan_filter[port]); } + kfree(priv->mfunc.master.vf_oper); +err_comm_oper: + kfree(priv->mfunc.master.vf_admin); +err_comm_admin: kfree(priv->mfunc.master.slave_state); err_comm: iounmap(priv->mfunc.comm); @@ -1837,10 +1923,8 @@ int mlx4_cmd_init(struct mlx4_dev *dev) priv->mfunc.vhcr = dma_alloc_coherent(&(dev->pdev->dev), PAGE_SIZE, &priv->mfunc.vhcr_dma, GFP_KERNEL); - if (!priv->mfunc.vhcr) { - mlx4_err(dev, "Couldn't allocate VHCR.\n"); + if (!priv->mfunc.vhcr) goto err_hcr; - } } priv->cmd.pool = pci_pool_create("mlx4_cmd", dev->pdev, @@ -1876,6 +1960,8 @@ void mlx4_multi_func_cleanup(struct mlx4_dev *dev) kfree(priv->mfunc.master.slave_state[i].vlan_filter[port]); } kfree(priv->mfunc.master.slave_state); + kfree(priv->mfunc.master.vf_admin); + kfree(priv->mfunc.master.vf_oper); } iounmap(priv->mfunc.comm); @@ -1986,3 +2072,115 @@ u32 mlx4_comm_get_version(void) { return ((u32) CMD_CHAN_IF_REV << 8) | (u32) CMD_CHAN_VER; } + +static int mlx4_get_slave_indx(struct mlx4_dev *dev, int vf) +{ + if ((vf < 0) || (vf >= dev->num_vfs)) { + mlx4_err(dev, "Bad vf number:%d (number of activated vf: %d)\n", vf, dev->num_vfs); + return -EINVAL; + } + + return vf+1; +} + +int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_vport_state *s_info; + int slave; + + if (!mlx4_is_master(dev)) + return -EPROTONOSUPPORT; + + slave = mlx4_get_slave_indx(dev, vf); + if (slave < 0) + return -EINVAL; + + s_info = &priv->mfunc.master.vf_admin[slave].vport[port]; + s_info->mac = mac; + mlx4_info(dev, "default mac on vf %d port %d to %llX will take afect only after vf restart\n", + vf, port, s_info->mac); + return 0; +} +EXPORT_SYMBOL_GPL(mlx4_set_vf_mac); + +int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_vport_state *s_info; + int slave; + + if ((!mlx4_is_master(dev)) || + !(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_VLAN_CONTROL)) + return -EPROTONOSUPPORT; + + if ((vlan > 4095) || (qos > 7)) + return -EINVAL; + + slave = mlx4_get_slave_indx(dev, vf); + if (slave < 0) + return -EINVAL; + + s_info = &priv->mfunc.master.vf_admin[slave].vport[port]; + if ((0 == vlan) && (0 == qos)) + s_info->default_vlan = MLX4_VGT; + else + s_info->default_vlan = vlan; + s_info->default_qos = qos; + return 0; +} +EXPORT_SYMBOL_GPL(mlx4_set_vf_vlan); + +int mlx4_set_vf_spoofchk(struct mlx4_dev *dev, int port, int vf, bool setting) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_vport_state *s_info; + int slave; + + if ((!mlx4_is_master(dev)) || + !(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_FSM)) + return -EPROTONOSUPPORT; + + slave = mlx4_get_slave_indx(dev, vf); + if (slave < 0) + return -EINVAL; + + s_info = &priv->mfunc.master.vf_admin[slave].vport[port]; + s_info->spoofchk = setting; + + return 0; +} +EXPORT_SYMBOL_GPL(mlx4_set_vf_spoofchk); + +int mlx4_get_vf_config(struct mlx4_dev *dev, int port, int vf, struct ifla_vf_info *ivf) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_vport_state *s_info; + int slave; + + if (!mlx4_is_master(dev)) + return -EPROTONOSUPPORT; + + slave = mlx4_get_slave_indx(dev, vf); + if (slave < 0) + return -EINVAL; + + s_info = &priv->mfunc.master.vf_admin[slave].vport[port]; + ivf->vf = vf; + + /* need to convert it to a func */ + ivf->mac[0] = ((s_info->mac >> (5*8)) & 0xff); + ivf->mac[1] = ((s_info->mac >> (4*8)) & 0xff); + ivf->mac[2] = ((s_info->mac >> (3*8)) & 0xff); + ivf->mac[3] = ((s_info->mac >> (2*8)) & 0xff); + ivf->mac[4] = ((s_info->mac >> (1*8)) & 0xff); + ivf->mac[5] = ((s_info->mac) & 0xff); + + ivf->vlan = s_info->default_vlan; + ivf->qos = s_info->default_qos; + ivf->tx_rate = s_info->tx_rate; + ivf->spoofchk = s_info->spoofchk; + + return 0; +} +EXPORT_SYMBOL_GPL(mlx4_get_vf_config); diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c index 0706623cfb96..004e4231af67 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/cq.c @@ -240,9 +240,10 @@ static void mlx4_cq_free_icm(struct mlx4_dev *dev, int cqn) __mlx4_cq_free_icm(dev, cqn); } -int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt, - struct mlx4_uar *uar, u64 db_rec, struct mlx4_cq *cq, - unsigned vector, int collapsed) +int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, + struct mlx4_mtt *mtt, struct mlx4_uar *uar, u64 db_rec, + struct mlx4_cq *cq, unsigned vector, int collapsed, + int timestamp_en) { struct mlx4_priv *priv = mlx4_priv(dev); struct mlx4_cq_table *cq_table = &priv->cq_table; @@ -276,6 +277,9 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt, memset(cq_context, 0, sizeof *cq_context); cq_context->flags = cpu_to_be32(!!collapsed << 18); + if (timestamp_en) + cq_context->flags |= cpu_to_be32(1 << 19); + cq_context->logsize_usrpage = cpu_to_be32((ilog2(nent) << 24) | uar->index); cq_context->comp_eqn = priv->eq_table.eq[vector].eqn; cq_context->log_page_size = mtt->page_shift - MLX4_ICM_PAGE_SHIFT; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c new file mode 100644 index 000000000000..fd6441071319 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c @@ -0,0 +1,151 @@ +/* + * Copyright (c) 2012 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#include <linux/mlx4/device.h> + +#include "mlx4_en.h" + +int mlx4_en_timestamp_config(struct net_device *dev, int tx_type, int rx_filter) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + struct mlx4_en_dev *mdev = priv->mdev; + int port_up = 0; + int err = 0; + + mutex_lock(&mdev->state_lock); + if (priv->port_up) { + port_up = 1; + mlx4_en_stop_port(dev, 1); + } + + mlx4_en_free_resources(priv); + + en_warn(priv, "Changing Time Stamp configuration\n"); + + priv->hwtstamp_config.tx_type = tx_type; + priv->hwtstamp_config.rx_filter = rx_filter; + + if (rx_filter != HWTSTAMP_FILTER_NONE) + dev->features &= ~NETIF_F_HW_VLAN_CTAG_RX; + else + dev->features |= NETIF_F_HW_VLAN_CTAG_RX; + + err = mlx4_en_alloc_resources(priv); + if (err) { + en_err(priv, "Failed reallocating port resources\n"); + goto out; + } + if (port_up) { + err = mlx4_en_start_port(dev); + if (err) + en_err(priv, "Failed starting port\n"); + } + +out: + mutex_unlock(&mdev->state_lock); + netdev_features_change(dev); + return err; +} + +/* mlx4_en_read_clock - read raw cycle counter (to be used by time counter) + */ +static cycle_t mlx4_en_read_clock(const struct cyclecounter *tc) +{ + struct mlx4_en_dev *mdev = + container_of(tc, struct mlx4_en_dev, cycles); + struct mlx4_dev *dev = mdev->dev; + + return mlx4_read_clock(dev) & tc->mask; +} + +u64 mlx4_en_get_cqe_ts(struct mlx4_cqe *cqe) +{ + u64 hi, lo; + struct mlx4_ts_cqe *ts_cqe = (struct mlx4_ts_cqe *)cqe; + + lo = (u64)be16_to_cpu(ts_cqe->timestamp_lo); + hi = ((u64)be32_to_cpu(ts_cqe->timestamp_hi) + !lo) << 16; + + return hi | lo; +} + +void mlx4_en_fill_hwtstamps(struct mlx4_en_dev *mdev, + struct skb_shared_hwtstamps *hwts, + u64 timestamp) +{ + u64 nsec; + + nsec = timecounter_cyc2time(&mdev->clock, timestamp); + + memset(hwts, 0, sizeof(struct skb_shared_hwtstamps)); + hwts->hwtstamp = ns_to_ktime(nsec); +} + +void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev) +{ + struct mlx4_dev *dev = mdev->dev; + u64 ns; + + memset(&mdev->cycles, 0, sizeof(mdev->cycles)); + mdev->cycles.read = mlx4_en_read_clock; + mdev->cycles.mask = CLOCKSOURCE_MASK(48); + /* Using shift to make calculation more accurate. Since current HW + * clock frequency is 427 MHz, and cycles are given using a 48 bits + * register, the biggest shift when calculating using u64, is 14 + * (max_cycles * multiplier < 2^64) + */ + mdev->cycles.shift = 14; + mdev->cycles.mult = + clocksource_khz2mult(1000 * dev->caps.hca_core_clock, mdev->cycles.shift); + + timecounter_init(&mdev->clock, &mdev->cycles, + ktime_to_ns(ktime_get_real())); + + /* Calculate period in seconds to call the overflow watchdog - to make + * sure counter is checked at least once every wrap around. + */ + ns = cyclecounter_cyc2ns(&mdev->cycles, mdev->cycles.mask); + do_div(ns, NSEC_PER_SEC / 2 / HZ); + mdev->overflow_period = ns; +} + +void mlx4_en_ptp_overflow_check(struct mlx4_en_dev *mdev) +{ + bool timeout = time_is_before_jiffies(mdev->last_overflow_check + + mdev->overflow_period); + + if (timeout) { + timecounter_read(&mdev->clock); + mdev->last_overflow_check = jiffies; + } +} diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c index b8d0854a7ad1..1e6c594d6d04 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c @@ -77,6 +77,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, struct mlx4_en_dev *mdev = priv->mdev; int err = 0; char name[25]; + int timestamp_en = 0; struct cpu_rmap *rmap = #ifdef CONFIG_RFS_ACCEL priv->dev->rx_cpu_rmap; @@ -123,8 +124,13 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, if (!cq->is_tx) cq->size = priv->rx_ring[cq->ring].actual_size; - err = mlx4_cq_alloc(mdev->dev, cq->size, &cq->wqres.mtt, &mdev->priv_uar, - cq->wqres.db.dma, &cq->mcq, cq->vector, 0); + if ((cq->is_tx && priv->hwtstamp_config.tx_type) || + (!cq->is_tx && priv->hwtstamp_config.rx_filter)) + timestamp_en = 1; + + err = mlx4_cq_alloc(mdev->dev, cq->size, &cq->wqres.mtt, + &mdev->priv_uar, cq->wqres.db.dma, &cq->mcq, + cq->vector, 0, timestamp_en); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c index b799ab12a291..0f91222ea3d7 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c @@ -186,7 +186,7 @@ static int mlx4_en_dcbnl_ieee_setpfc(struct net_device *dev, static u8 mlx4_en_dcbnl_getdcbx(struct net_device *dev) { - return DCB_CAP_DCBX_VER_IEEE; + return DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_IEEE; } static u8 mlx4_en_dcbnl_setdcbx(struct net_device *dev, u8 mode) @@ -253,3 +253,11 @@ const struct dcbnl_rtnl_ops mlx4_en_dcbnl_ops = { .getdcbx = mlx4_en_dcbnl_getdcbx, .setdcbx = mlx4_en_dcbnl_setdcbx, }; + +const struct dcbnl_rtnl_ops mlx4_en_dcbnl_pfc_ops = { + .ieee_getpfc = mlx4_en_dcbnl_ieee_getpfc, + .ieee_setpfc = mlx4_en_dcbnl_ieee_setpfc, + + .getdcbx = mlx4_en_dcbnl_getdcbx, + .setdcbx = mlx4_en_dcbnl_setdcbx, +}; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 00f25b5f297f..bcf4d118e98c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1147,6 +1147,35 @@ out: return err; } +static int mlx4_en_get_ts_info(struct net_device *dev, + struct ethtool_ts_info *info) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + struct mlx4_en_dev *mdev = priv->mdev; + int ret; + + ret = ethtool_op_get_ts_info(dev, info); + if (ret) + return ret; + + if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) { + info->so_timestamping |= + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + + info->tx_types = + (1 << HWTSTAMP_TX_OFF) | + (1 << HWTSTAMP_TX_ON); + + info->rx_filters = + (1 << HWTSTAMP_FILTER_NONE) | + (1 << HWTSTAMP_FILTER_ALL); + } + + return ret; +} + const struct ethtool_ops mlx4_en_ethtool_ops = { .get_drvinfo = mlx4_en_get_drvinfo, .get_settings = mlx4_en_get_settings, @@ -1173,6 +1202,7 @@ const struct ethtool_ops mlx4_en_ethtool_ops = { .set_rxfh_indir = mlx4_en_set_rxfh_indir, .get_channels = mlx4_en_get_channels, .set_channels = mlx4_en_set_channels, + .get_ts_info = mlx4_en_get_ts_info, }; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c index fc27800e9c38..a5c9df07a7d0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c @@ -300,6 +300,11 @@ static void *mlx4_en_add(struct mlx4_dev *dev) if (mlx4_en_init_netdev(mdev, i, &mdev->profile.prof[i])) mdev->pndev[i] = NULL; } + + /* Initialize time stamp mechanism */ + if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) + mlx4_en_init_timestamp(mdev); + return mdev; err_mr: diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 30d78f806dc3..a69a908614e6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -356,7 +356,8 @@ static void mlx4_en_filter_rfs_expire(struct mlx4_en_priv *priv) } #endif -static int mlx4_en_vlan_rx_add_vid(struct net_device *dev, unsigned short vid) +static int mlx4_en_vlan_rx_add_vid(struct net_device *dev, + __be16 proto, u16 vid) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; @@ -381,7 +382,8 @@ static int mlx4_en_vlan_rx_add_vid(struct net_device *dev, unsigned short vid) return 0; } -static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid) +static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev, + __be16 proto, u16 vid) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; @@ -1359,6 +1361,27 @@ static void mlx4_en_do_get_stats(struct work_struct *work) mutex_unlock(&mdev->state_lock); } +/* mlx4_en_service_task - Run service task for tasks that needed to be done + * periodically + */ +static void mlx4_en_service_task(struct work_struct *work) +{ + struct delayed_work *delay = to_delayed_work(work); + struct mlx4_en_priv *priv = container_of(delay, struct mlx4_en_priv, + service_task); + struct mlx4_en_dev *mdev = priv->mdev; + + mutex_lock(&mdev->state_lock); + if (mdev->device_up) { + if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) + mlx4_en_ptp_overflow_check(mdev); + + queue_delayed_work(mdev->workqueue, &priv->service_task, + SERVICE_TASK_DELAY); + } + mutex_unlock(&mdev->state_lock); +} + static void mlx4_en_linkstate(struct work_struct *work) { struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv, @@ -1863,6 +1886,7 @@ void mlx4_en_destroy_netdev(struct net_device *dev) mlx4_free_hwq_res(mdev->dev, &priv->res, MLX4_EN_PAGE_SIZE); cancel_delayed_work(&priv->stats_task); + cancel_delayed_work(&priv->service_task); /* flush any pending task for this netdev */ flush_workqueue(mdev->workqueue); @@ -1914,6 +1938,75 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) return 0; } +static int mlx4_en_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + struct mlx4_en_dev *mdev = priv->mdev; + struct hwtstamp_config config; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + /* reserved for future extensions */ + if (config.flags) + return -EINVAL; + + /* device doesn't support time stamping */ + if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)) + return -EINVAL; + + /* TX HW timestamp */ + switch (config.tx_type) { + case HWTSTAMP_TX_OFF: + case HWTSTAMP_TX_ON: + break; + default: + return -ERANGE; + } + + /* RX HW timestamp */ + switch (config.rx_filter) { + case HWTSTAMP_FILTER_NONE: + break; + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_SOME: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + config.rx_filter = HWTSTAMP_FILTER_ALL; + break; + default: + return -ERANGE; + } + + if (mlx4_en_timestamp_config(dev, config.tx_type, config.rx_filter)) { + config.tx_type = HWTSTAMP_TX_OFF; + config.rx_filter = HWTSTAMP_FILTER_NONE; + } + + return copy_to_user(ifr->ifr_data, &config, + sizeof(config)) ? -EFAULT : 0; +} + +static int mlx4_en_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +{ + switch (cmd) { + case SIOCSHWTSTAMP: + return mlx4_en_hwtstamp_ioctl(dev, ifr); + default: + return -EOPNOTSUPP; + } +} + static int mlx4_en_set_features(struct net_device *netdev, netdev_features_t features) { @@ -1931,77 +2024,40 @@ static int mlx4_en_set_features(struct net_device *netdev, } -static int mlx4_en_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, u16 flags) +static int mlx4_en_set_vf_mac(struct net_device *dev, int queue, u8 *mac) { - struct mlx4_en_priv *priv = netdev_priv(dev); - struct mlx4_dev *mdev = priv->mdev->dev; - int err; - - if (!mlx4_is_mfunc(mdev)) - return -EOPNOTSUPP; + struct mlx4_en_priv *en_priv = netdev_priv(dev); + struct mlx4_en_dev *mdev = en_priv->mdev; + u64 mac_u64 = mlx4_en_mac_to_u64(mac); - /* Hardware does not support aging addresses, allow only - * permanent addresses if ndm_state is given - */ - if (ndm->ndm_state && !(ndm->ndm_state & NUD_PERMANENT)) { - en_info(priv, "Add FDB only supports static addresses\n"); + if (!is_valid_ether_addr(mac)) return -EINVAL; - } - if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) - err = dev_uc_add_excl(dev, addr); - else if (is_multicast_ether_addr(addr)) - err = dev_mc_add_excl(dev, addr); - else - err = -EINVAL; - - /* Only return duplicate errors if NLM_F_EXCL is set */ - if (err == -EEXIST && !(flags & NLM_F_EXCL)) - err = 0; - - return err; + return mlx4_set_vf_mac(mdev->dev, en_priv->port, queue, mac_u64); } -static int mlx4_en_fdb_del(struct ndmsg *ndm, - struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr) +static int mlx4_en_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos) { - struct mlx4_en_priv *priv = netdev_priv(dev); - struct mlx4_dev *mdev = priv->mdev->dev; - int err; - - if (!mlx4_is_mfunc(mdev)) - return -EOPNOTSUPP; + struct mlx4_en_priv *en_priv = netdev_priv(dev); + struct mlx4_en_dev *mdev = en_priv->mdev; - if (ndm->ndm_state && !(ndm->ndm_state & NUD_PERMANENT)) { - en_info(priv, "Del FDB only supports static addresses\n"); - return -EINVAL; - } + return mlx4_set_vf_vlan(mdev->dev, en_priv->port, vf, vlan, qos); +} - if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) - err = dev_uc_del(dev, addr); - else if (is_multicast_ether_addr(addr)) - err = dev_mc_del(dev, addr); - else - err = -EINVAL; +static int mlx4_en_set_vf_spoofchk(struct net_device *dev, int vf, bool setting) +{ + struct mlx4_en_priv *en_priv = netdev_priv(dev); + struct mlx4_en_dev *mdev = en_priv->mdev; - return err; + return mlx4_set_vf_spoofchk(mdev->dev, en_priv->port, vf, setting); } -static int mlx4_en_fdb_dump(struct sk_buff *skb, - struct netlink_callback *cb, - struct net_device *dev, int idx) +static int mlx4_en_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivf) { - struct mlx4_en_priv *priv = netdev_priv(dev); - struct mlx4_dev *mdev = priv->mdev->dev; - - if (mlx4_is_mfunc(mdev)) - idx = ndo_dflt_fdb_dump(skb, cb, dev, idx); + struct mlx4_en_priv *en_priv = netdev_priv(dev); + struct mlx4_en_dev *mdev = en_priv->mdev; - return idx; + return mlx4_get_vf_config(mdev->dev, en_priv->port, vf, ivf); } static const struct net_device_ops mlx4_netdev_ops = { @@ -2014,6 +2070,7 @@ static const struct net_device_ops mlx4_netdev_ops = { .ndo_set_mac_address = mlx4_en_set_mac, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = mlx4_en_change_mtu, + .ndo_do_ioctl = mlx4_en_ioctl, .ndo_tx_timeout = mlx4_en_tx_timeout, .ndo_vlan_rx_add_vid = mlx4_en_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = mlx4_en_vlan_rx_kill_vid, @@ -2025,9 +2082,33 @@ static const struct net_device_ops mlx4_netdev_ops = { #ifdef CONFIG_RFS_ACCEL .ndo_rx_flow_steer = mlx4_en_filter_rfs, #endif - .ndo_fdb_add = mlx4_en_fdb_add, - .ndo_fdb_del = mlx4_en_fdb_del, - .ndo_fdb_dump = mlx4_en_fdb_dump, +}; + +static const struct net_device_ops mlx4_netdev_ops_master = { + .ndo_open = mlx4_en_open, + .ndo_stop = mlx4_en_close, + .ndo_start_xmit = mlx4_en_xmit, + .ndo_select_queue = mlx4_en_select_queue, + .ndo_get_stats = mlx4_en_get_stats, + .ndo_set_rx_mode = mlx4_en_set_rx_mode, + .ndo_set_mac_address = mlx4_en_set_mac, + .ndo_validate_addr = eth_validate_addr, + .ndo_change_mtu = mlx4_en_change_mtu, + .ndo_tx_timeout = mlx4_en_tx_timeout, + .ndo_vlan_rx_add_vid = mlx4_en_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = mlx4_en_vlan_rx_kill_vid, + .ndo_set_vf_mac = mlx4_en_set_vf_mac, + .ndo_set_vf_vlan = mlx4_en_set_vf_vlan, + .ndo_set_vf_spoofchk = mlx4_en_set_vf_spoofchk, + .ndo_get_vf_config = mlx4_en_get_vf_config, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = mlx4_en_netpoll, +#endif + .ndo_set_features = mlx4_en_set_features, + .ndo_setup_tc = mlx4_en_setup_tc, +#ifdef CONFIG_RFS_ACCEL + .ndo_rx_flow_steer = mlx4_en_filter_rfs, +#endif }; int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, @@ -2088,9 +2169,16 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, INIT_WORK(&priv->watchdog_task, mlx4_en_restart); INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate); INIT_DELAYED_WORK(&priv->stats_task, mlx4_en_do_get_stats); + INIT_DELAYED_WORK(&priv->service_task, mlx4_en_service_task); #ifdef CONFIG_MLX4_EN_DCB - if (!mlx4_is_slave(priv->mdev->dev)) - dev->dcbnl_ops = &mlx4_en_dcbnl_ops; + if (!mlx4_is_slave(priv->mdev->dev)) { + if (mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_SET_ETH_SCHED) { + dev->dcbnl_ops = &mlx4_en_dcbnl_ops; + } else { + en_info(priv, "enabling only PFC DCB ops\n"); + dev->dcbnl_ops = &mlx4_en_dcbnl_pfc_ops; + } + } #endif for (i = 0; i < MLX4_EN_MAC_HASH_SIZE; ++i) @@ -2122,6 +2210,11 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, spin_lock_init(&priv->filters_lock); #endif + /* Initialize time stamping config */ + priv->hwtstamp_config.flags = 0; + priv->hwtstamp_config.tx_type = HWTSTAMP_TX_OFF; + priv->hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; + /* Allocate page for receive rings */ err = mlx4_alloc_hwq_res(mdev->dev, &priv->res, MLX4_EN_PAGE_SIZE, MLX4_EN_PAGE_SIZE); @@ -2134,7 +2227,10 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, /* * Initialize netdev entry points */ - dev->netdev_ops = &mlx4_netdev_ops; + if (mlx4_is_master(priv->mdev->dev)) + dev->netdev_ops = &mlx4_netdev_ops_master; + else + dev->netdev_ops = &mlx4_netdev_ops; dev->watchdog_timeo = MLX4_EN_WATCHDOG_TIMEOUT; netif_set_real_num_tx_queues(dev, priv->tx_ring_num); netif_set_real_num_rx_queues(dev, priv->rx_ring_num); @@ -2152,8 +2248,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, dev->hw_features |= NETIF_F_RXCSUM | NETIF_F_RXHASH; dev->features = dev->hw_features | NETIF_F_HIGHDMA | - NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX | - NETIF_F_HW_VLAN_FILTER; + NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_FILTER; dev->hw_features |= NETIF_F_LOOPBACK; if (mdev->dev->caps.steering_mode == @@ -2199,6 +2295,11 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, } mlx4_en_set_default_moderation(priv); queue_delayed_work(mdev->workqueue, &priv->stats_task, STATS_DELAY); + + if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) + queue_delayed_work(mdev->workqueue, &priv->service_task, + SERVICE_TASK_DELAY); + return 0; out: diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c index 10c24c784b70..91f2b2c43c12 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c @@ -42,6 +42,7 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride, int user_prio, struct mlx4_qp_context *context) { struct mlx4_en_dev *mdev = priv->mdev; + struct net_device *dev = priv->dev; memset(context, 0, sizeof *context); context->flags = cpu_to_be32(7 << 16 | rss << MLX4_RSS_QPC_FLAG_OFFSET); @@ -65,6 +66,8 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride, context->cqn_send = cpu_to_be32(cqn); context->cqn_recv = cpu_to_be32(cqn); context->db_rec_addr = cpu_to_be64(priv->res.db.dma << 2); + if (!(dev->features & NETIF_F_HW_VLAN_CTAG_RX)) + context->param3 |= cpu_to_be32(1 << 30); } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index c7f856308e1a..02aee1ebd203 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -320,6 +320,8 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv, } ring->buf = ring->wqres.buf.direct.buf; + ring->hwtstamp_rx_filter = priv->hwtstamp_config.rx_filter; + return 0; err_hwq: @@ -554,6 +556,7 @@ static void mlx4_en_refill_rx_buffers(struct mlx4_en_priv *priv, int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int budget) { struct mlx4_en_priv *priv = netdev_priv(dev); + struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_cqe *cqe; struct mlx4_en_rx_ring *ring = &priv->rx_ring[cq->ring]; struct mlx4_en_rx_alloc *frags; @@ -565,6 +568,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud int polled = 0; int ip_summed; int factor = priv->cqe_factor; + u64 timestamp; if (!priv->port_up) return 0; @@ -669,19 +673,27 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud gro_skb->data_len = length; gro_skb->ip_summed = CHECKSUM_UNNECESSARY; - if (cqe->vlan_my_qpn & - cpu_to_be32(MLX4_CQE_VLAN_PRESENT_MASK)) { + if ((cqe->vlan_my_qpn & + cpu_to_be32(MLX4_CQE_VLAN_PRESENT_MASK)) && + (dev->features & NETIF_F_HW_VLAN_CTAG_RX)) { u16 vid = be16_to_cpu(cqe->sl_vid); - __vlan_hwaccel_put_tag(gro_skb, vid); + __vlan_hwaccel_put_tag(gro_skb, htons(ETH_P_8021Q), vid); } if (dev->features & NETIF_F_RXHASH) gro_skb->rxhash = be32_to_cpu(cqe->immed_rss_invalid); skb_record_rx_queue(gro_skb, cq->ring); - napi_gro_frags(&cq->napi); + if (ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL) { + timestamp = mlx4_en_get_cqe_ts(cqe); + mlx4_en_fill_hwtstamps(mdev, + skb_hwtstamps(gro_skb), + timestamp); + } + + napi_gro_frags(&cq->napi); goto next; } @@ -714,9 +726,16 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud if (dev->features & NETIF_F_RXHASH) skb->rxhash = be32_to_cpu(cqe->immed_rss_invalid); - if (be32_to_cpu(cqe->vlan_my_qpn) & - MLX4_CQE_VLAN_PRESENT_MASK) - __vlan_hwaccel_put_tag(skb, be16_to_cpu(cqe->sl_vid)); + if ((be32_to_cpu(cqe->vlan_my_qpn) & + MLX4_CQE_VLAN_PRESENT_MASK) && + (dev->features & NETIF_F_HW_VLAN_CTAG_RX)) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), be16_to_cpu(cqe->sl_vid)); + + if (ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL) { + timestamp = mlx4_en_get_cqe_ts(cqe); + mlx4_en_fill_hwtstamps(mdev, skb_hwtstamps(skb), + timestamp); + } /* Push it up the stack */ netif_receive_skb(skb); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c index 3488c6d9e6b5..2448f0d669e6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c @@ -58,10 +58,9 @@ static int mlx4_en_test_loopback_xmit(struct mlx4_en_priv *priv) /* build the pkt before xmit */ skb = netdev_alloc_skb(priv->dev, MLX4_LOOPBACK_TEST_PAYLOAD + ETH_HLEN + NET_IP_ALIGN); - if (!skb) { - en_err(priv, "-LOOPBACK_TEST_XMIT- failed to create skb for xmit\n"); + if (!skb) return -ENOMEM; - } + skb_reserve(skb, NET_IP_ALIGN); ethh = (struct ethhdr *)skb_put(skb, sizeof(struct ethhdr)); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 49308cc65ee7..4e6877a032a8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -118,6 +118,8 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, } else ring->bf_enabled = true; + ring->hwtstamp_tx_type = priv->hwtstamp_config.tx_type; + return 0; err_map: @@ -192,8 +194,9 @@ void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv, static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring *ring, - int index, u8 owner) + int index, u8 owner, u64 timestamp) { + struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_en_tx_info *tx_info = &ring->tx_info[index]; struct mlx4_en_tx_desc *tx_desc = ring->buf + index * TXBB_SIZE; struct mlx4_wqe_data_seg *data = (void *) tx_desc + tx_info->data_offset; @@ -204,6 +207,12 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, int i; __be32 *ptr = (__be32 *)tx_desc; __be32 stamp = cpu_to_be32(STAMP_VAL | (!!owner << STAMP_SHIFT)); + struct skb_shared_hwtstamps hwts; + + if (timestamp) { + mlx4_en_fill_hwtstamps(mdev, &hwts, timestamp); + skb_tstamp_tx(skb, &hwts); + } /* Optimize the common case when there are no wraparounds */ if (likely((void *) tx_desc + tx_info->nr_txbb * TXBB_SIZE <= end)) { @@ -289,7 +298,7 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring) while (ring->cons != ring->prod) { ring->last_nr_txbb = mlx4_en_free_tx_desc(priv, ring, ring->cons & ring->size_mask, - !!(ring->cons & ring->size)); + !!(ring->cons & ring->size), 0); ring->cons += ring->last_nr_txbb; cnt++; } @@ -318,6 +327,7 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq) u32 packets = 0; u32 bytes = 0; int factor = priv->cqe_factor; + u64 timestamp = 0; if (!priv->port_up) return; @@ -341,11 +351,14 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq) do { txbbs_skipped += ring->last_nr_txbb; ring_index = (ring_index + ring->last_nr_txbb) & size_mask; + if (ring->tx_info[ring_index].ts_requested) + timestamp = mlx4_en_get_cqe_ts(cqe); + /* free next descriptor */ ring->last_nr_txbb = mlx4_en_free_tx_desc( priv, ring, ring_index, !!((ring->cons + txbbs_skipped) & - ring->size)); + ring->size), timestamp); packets++; bytes += ring->tx_info[ring_index].nr_bytes; } while (ring_index != new_index); @@ -629,6 +642,16 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) tx_info->skb = skb; tx_info->nr_txbb = nr_txbb; + /* + * For timestamping add flag to skb_shinfo and + * set flag for further reference + */ + if (ring->hwtstamp_tx_type == HWTSTAMP_TX_ON && + skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + tx_info->ts_requested = 1; + } + /* Prepare ctrl segement apart opcode+ownership, which depends on * whether LSO is used */ tx_desc->ctrl.vlan_tag = cpu_to_be16(vlan_tag); @@ -729,6 +752,8 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) if (bounce) tx_desc = mlx4_en_bounce_to_desc(priv, ring, index, desc_size); + skb_tx_timestamp(skb); + if (ring->bf_enabled && desc_size <= MAX_BF && !bounce && !vlan_tx_tag_present(skb)) { *(__be32 *) (&tx_desc->ctrl.vlan_tag) |= cpu_to_be32(ring->doorbell_qpn); op_own |= htonl((bf_index & 0xffff) << 8); diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index f6245579962d..b147bdd40768 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -91,7 +91,7 @@ static void dump_dev_cap_flags(struct mlx4_dev *dev, u64 flags) [ 8] = "P_Key violation counter", [ 9] = "Q_Key violation counter", [10] = "VMM", - [12] = "DPDP", + [12] = "Dual Port Different Protocol (DPDP) support", [15] = "Big LSO headers", [16] = "MW support", [17] = "APM support", @@ -109,6 +109,8 @@ static void dump_dev_cap_flags(struct mlx4_dev *dev, u64 flags) [41] = "Unicast VEP steering support", [42] = "Multicast VEP steering support", [48] = "Counters support", + [53] = "Port ETS Scheduler support", + [55] = "Port link type sensing support", [59] = "Port management change event support", [61] = "64 byte EQE support", [62] = "64 byte CQE support", @@ -128,7 +130,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags) [1] = "RSS Toeplitz Hash Function support", [2] = "RSS XOR Hash Function support", [3] = "Device manage flow steering support", - [4] = "Automatic mac reassignment support" + [4] = "Automatic MAC reassignment support", + [5] = "Time stamping support" }; int i; @@ -442,6 +445,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) #define QUERY_DEV_CAP_MAX_MSG_SZ_OFFSET 0x38 #define QUERY_DEV_CAP_MAX_GID_OFFSET 0x3b #define QUERY_DEV_CAP_RATE_SUPPORT_OFFSET 0x3c +#define QUERY_DEV_CAP_CQ_TS_SUPPORT_OFFSET 0x3e #define QUERY_DEV_CAP_MAX_PKEY_OFFSET 0x3f #define QUERY_DEV_CAP_EXT_FLAGS_OFFSET 0x40 #define QUERY_DEV_CAP_FLAGS_OFFSET 0x44 @@ -464,6 +468,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) #define QUERY_DEV_CAP_RSVD_XRC_OFFSET 0x66 #define QUERY_DEV_CAP_MAX_XRC_OFFSET 0x67 #define QUERY_DEV_CAP_MAX_COUNTERS_OFFSET 0x68 +#define QUERY_DEV_CAP_EXT_2_FLAGS_OFFSET 0x70 #define QUERY_DEV_CAP_FLOW_STEERING_RANGE_EN_OFFSET 0x76 #define QUERY_DEV_CAP_FLOW_STEERING_MAX_QP_OFFSET 0x77 #define QUERY_DEV_CAP_RDMARC_ENTRY_SZ_OFFSET 0x80 @@ -558,6 +563,9 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev_cap->fs_max_num_qp_per_entry = field; MLX4_GET(stat_rate, outbox, QUERY_DEV_CAP_RATE_SUPPORT_OFFSET); dev_cap->stat_rate_support = stat_rate; + MLX4_GET(field, outbox, QUERY_DEV_CAP_CQ_TS_SUPPORT_OFFSET); + if (field & 0x80) + dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_TS; MLX4_GET(ext_flags, outbox, QUERY_DEV_CAP_EXT_FLAGS_OFFSET); MLX4_GET(flags, outbox, QUERY_DEV_CAP_FLAGS_OFFSET); dev_cap->flags = flags | (u64)ext_flags << 32; @@ -648,6 +656,12 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) MLX4_GET(dev_cap->max_counters, outbox, QUERY_DEV_CAP_MAX_COUNTERS_OFFSET); + MLX4_GET(field32, outbox, QUERY_DEV_CAP_EXT_2_FLAGS_OFFSET); + if (field32 & (1 << 26)) + dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_VLAN_CONTROL; + if (field32 & (1 << 20)) + dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_FSM; + if (dev->flags & MLX4_FLAG_OLD_PORT_CMDS) { for (i = 1; i <= dev_cap->num_ports; ++i) { MLX4_GET(field, outbox, QUERY_DEV_CAP_VL_PORT_OFFSET); @@ -777,6 +791,11 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave, flags &= ~MLX4_DEV_CAP_FLAG_MEM_WINDOW; MLX4_PUT(outbox->buf, flags, QUERY_DEV_CAP_EXT_FLAGS_OFFSET); + /* For guests, disable timestamp */ + MLX4_GET(field, outbox->buf, QUERY_DEV_CAP_CQ_TS_SUPPORT_OFFSET); + field &= 0x7f; + MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_CQ_TS_SUPPORT_OFFSET); + /* For guests, report Blueflame disabled */ MLX4_GET(field, outbox->buf, QUERY_DEV_CAP_BF_OFFSET); field &= 0x7f; @@ -804,6 +823,7 @@ int mlx4_QUERY_PORT_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_cmd_mailbox *outbox, struct mlx4_cmd_info *cmd) { + struct mlx4_priv *priv = mlx4_priv(dev); u64 def_mac; u8 port_type; u16 short_field; @@ -821,6 +841,9 @@ int mlx4_QUERY_PORT_wrapper(struct mlx4_dev *dev, int slave, /* set slave default_mac address */ MLX4_GET(def_mac, outbox->buf, QUERY_PORT_MAC_OFFSET); def_mac += slave << 8; + /* if config MAC in DB use it */ + if (priv->mfunc.master.vf_oper[slave].vport[vhcr->in_modifier].state.mac) + def_mac = priv->mfunc.master.vf_oper[slave].vport[vhcr->in_modifier].state.mac; MLX4_PUT(outbox->buf, def_mac, QUERY_PORT_MAC_OFFSET); /* get port type - currently only eth is enabled */ @@ -1006,6 +1029,9 @@ int mlx4_QUERY_FW(struct mlx4_dev *dev) #define QUERY_FW_COMM_BASE_OFFSET 0x40 #define QUERY_FW_COMM_BAR_OFFSET 0x48 +#define QUERY_FW_CLOCK_OFFSET 0x50 +#define QUERY_FW_CLOCK_BAR 0x58 + mailbox = mlx4_alloc_cmd_mailbox(dev); if (IS_ERR(mailbox)) return PTR_ERR(mailbox); @@ -1080,6 +1106,12 @@ int mlx4_QUERY_FW(struct mlx4_dev *dev) fw->comm_bar, fw->comm_base); mlx4_dbg(dev, "FW size %d KB\n", fw->fw_pages >> 2); + MLX4_GET(fw->clock_offset, outbox, QUERY_FW_CLOCK_OFFSET); + MLX4_GET(fw->clock_bar, outbox, QUERY_FW_CLOCK_BAR); + fw->clock_bar = (fw->clock_bar >> 6) * 2; + mlx4_dbg(dev, "Internal clock bar:%d offset:0x%llx\n", + fw->clock_bar, fw->clock_offset); + /* * Round up number of system pages needed in case * MLX4_ICM_PAGE_SIZE < PAGE_SIZE. @@ -1367,6 +1399,7 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev, u8 byte_field; #define QUERY_HCA_GLOBAL_CAPS_OFFSET 0x04 +#define QUERY_HCA_CORE_CLOCK_OFFSET 0x0c mailbox = mlx4_alloc_cmd_mailbox(dev); if (IS_ERR(mailbox)) @@ -1381,6 +1414,7 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev, goto out; MLX4_GET(param->global_caps, outbox, QUERY_HCA_GLOBAL_CAPS_OFFSET); + MLX4_GET(param->hca_core_clock, outbox, QUERY_HCA_CORE_CLOCK_OFFSET); /* QPC/EEC/CQC/EQC/RDMARC attributes */ diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h index 151c2bb380a6..fdf41665a059 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.h +++ b/drivers/net/ethernet/mellanox/mlx4/fw.h @@ -162,6 +162,7 @@ struct mlx4_init_hca_param { u64 global_caps; u16 log_mc_entry_sz; u16 log_mc_hash_sz; + u16 hca_core_clock; /* Internal Clock Frequency (in MHz) */ u8 log_num_qps; u8 log_num_srqs; u8 log_num_cqs; diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 16abde20e1fc..0d32a82458bf 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -513,6 +513,8 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) mlx4_log_num_mgm_entry_size = hca_param.log_mc_entry_sz; + dev->caps.hca_core_clock = hca_param.hca_core_clock; + memset(&dev_cap, 0, sizeof(dev_cap)); dev->caps.max_qp_dest_rdma = 1 << hca_param.log_rd_per_qp; err = mlx4_dev_cap(dev, &dev_cap); @@ -1226,8 +1228,53 @@ static void unmap_bf_area(struct mlx4_dev *dev) io_mapping_free(mlx4_priv(dev)->bf_mapping); } +cycle_t mlx4_read_clock(struct mlx4_dev *dev) +{ + u32 clockhi, clocklo, clockhi1; + cycle_t cycles; + int i; + struct mlx4_priv *priv = mlx4_priv(dev); + + for (i = 0; i < 10; i++) { + clockhi = swab32(readl(priv->clock_mapping)); + clocklo = swab32(readl(priv->clock_mapping + 4)); + clockhi1 = swab32(readl(priv->clock_mapping)); + if (clockhi == clockhi1) + break; + } + + cycles = (u64) clockhi << 32 | (u64) clocklo; + + return cycles; +} +EXPORT_SYMBOL_GPL(mlx4_read_clock); + + +static int map_internal_clock(struct mlx4_dev *dev) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + + priv->clock_mapping = + ioremap(pci_resource_start(dev->pdev, priv->fw.clock_bar) + + priv->fw.clock_offset, MLX4_CLOCK_SIZE); + + if (!priv->clock_mapping) + return -ENOMEM; + + return 0; +} + +static void unmap_internal_clock(struct mlx4_dev *dev) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + + if (priv->clock_mapping) + iounmap(priv->clock_mapping); +} + static void mlx4_close_hca(struct mlx4_dev *dev) { + unmap_internal_clock(dev); unmap_bf_area(dev); if (mlx4_is_slave(dev)) mlx4_slave_exit(dev); @@ -1445,6 +1492,37 @@ static int mlx4_init_hca(struct mlx4_dev *dev) mlx4_err(dev, "INIT_HCA command failed, aborting.\n"); goto err_free_icm; } + /* + * If TS is supported by FW + * read HCA frequency by QUERY_HCA command + */ + if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) { + memset(&init_hca, 0, sizeof(init_hca)); + err = mlx4_QUERY_HCA(dev, &init_hca); + if (err) { + mlx4_err(dev, "QUERY_HCA command failed, disable timestamp.\n"); + dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_TS; + } else { + dev->caps.hca_core_clock = + init_hca.hca_core_clock; + } + + /* In case we got HCA frequency 0 - disable timestamping + * to avoid dividing by zero + */ + if (!dev->caps.hca_core_clock) { + dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_TS; + mlx4_err(dev, + "HCA frequency is 0. Timestamping is not supported."); + } else if (map_internal_clock(dev)) { + /* + * Map internal clock, + * in case of failure disable timestamping + */ + dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_TS; + mlx4_err(dev, "Failed to map internal clock. Timestamping is not supported.\n"); + } + } } else { err = mlx4_init_slave(dev); if (err) { @@ -1478,6 +1556,7 @@ static int mlx4_init_hca(struct mlx4_dev *dev) return 0; unmap_bf: + unmap_internal_clock(dev); unmap_bf_area(dev); err_close: diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index 52685524708d..ffc78d2cb0cf 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -1125,28 +1125,11 @@ static int mlx4_QP_ATTACH(struct mlx4_dev *dev, struct mlx4_qp *qp, return err; } -int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], - u8 port, int block_mcast_loopback, - enum mlx4_protocol prot, u64 *reg_id) +int mlx4_trans_to_dmfs_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, + u8 gid[16], u8 port, + int block_mcast_loopback, + enum mlx4_protocol prot, u64 *reg_id) { - - switch (dev->caps.steering_mode) { - case MLX4_STEERING_MODE_A0: - if (prot == MLX4_PROT_ETH) - return 0; - - case MLX4_STEERING_MODE_B0: - if (prot == MLX4_PROT_ETH) - gid[7] |= (MLX4_MC_STEER << 1); - - if (mlx4_is_mfunc(dev)) - return mlx4_QP_ATTACH(dev, qp, gid, 1, - block_mcast_loopback, prot); - return mlx4_qp_attach_common(dev, qp, gid, - block_mcast_loopback, prot, - MLX4_MC_STEER); - - case MLX4_STEERING_MODE_DEVICE_MANAGED: { struct mlx4_spec_list spec = { {NULL} }; __be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16); @@ -1180,8 +1163,32 @@ int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], list_add_tail(&spec.list, &rule.list); return mlx4_flow_attach(dev, &rule, reg_id); - } +} +int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], + u8 port, int block_mcast_loopback, + enum mlx4_protocol prot, u64 *reg_id) +{ + switch (dev->caps.steering_mode) { + case MLX4_STEERING_MODE_A0: + if (prot == MLX4_PROT_ETH) + return 0; + + case MLX4_STEERING_MODE_B0: + if (prot == MLX4_PROT_ETH) + gid[7] |= (MLX4_MC_STEER << 1); + + if (mlx4_is_mfunc(dev)) + return mlx4_QP_ATTACH(dev, qp, gid, 1, + block_mcast_loopback, prot); + return mlx4_qp_attach_common(dev, qp, gid, + block_mcast_loopback, prot, + MLX4_MC_STEER); + + case MLX4_STEERING_MODE_DEVICE_MANAGED: + return mlx4_trans_to_dmfs_attach(dev, qp, gid, port, + block_mcast_loopback, + prot, reg_id); default: return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index d738454116a0..eac3dae10efe 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -87,7 +87,8 @@ enum { MLX4_HCR_SIZE = 0x0001c, MLX4_CLR_INT_SIZE = 0x00008, MLX4_SLAVE_COMM_BASE = 0x0, - MLX4_COMM_PAGESIZE = 0x1000 + MLX4_COMM_PAGESIZE = 0x1000, + MLX4_CLOCK_SIZE = 0x00008 }; enum { @@ -403,6 +404,7 @@ struct mlx4_fw { u64 clr_int_base; u64 catas_offset; u64 comm_base; + u64 clock_offset; struct mlx4_icm *fw_icm; struct mlx4_icm *aux_icm; u32 catas_size; @@ -410,6 +412,7 @@ struct mlx4_fw { u8 clr_int_bar; u8 catas_bar; u8 comm_bar; + u8 clock_bar; }; struct mlx4_comm { @@ -470,6 +473,30 @@ struct mlx4_slave_state { enum slave_port_state port_state[MLX4_MAX_PORTS + 1]; }; +#define MLX4_VGT 4095 +#define NO_INDX (-1) + +struct mlx4_vport_state { + u64 mac; + u16 default_vlan; + u8 default_qos; + u32 tx_rate; + bool spoofchk; +}; + +struct mlx4_vf_admin_state { + struct mlx4_vport_state vport[MLX4_MAX_PORTS + 1]; +}; + +struct mlx4_vport_oper_state { + struct mlx4_vport_state state; + int mac_idx; + int vlan_idx; +}; +struct mlx4_vf_oper_state { + struct mlx4_vport_oper_state vport[MLX4_MAX_PORTS + 1]; +}; + struct slave_list { struct mutex mutex; struct list_head res_list[MLX4_NUM_OF_RESOURCE_TYPE]; @@ -500,6 +527,8 @@ struct mlx4_master_qp0_state { struct mlx4_mfunc_master_ctx { struct mlx4_slave_state *slave_state; + struct mlx4_vf_admin_state *vf_admin; + struct mlx4_vf_oper_state *vf_oper; struct mlx4_master_qp0_state qp0_state[MLX4_MAX_PORTS + 1]; int init_port_ref[MLX4_MAX_PORTS + 1]; u16 max_mtu[MLX4_MAX_PORTS + 1]; @@ -826,6 +855,7 @@ struct mlx4_priv { struct list_head bf_list; struct mutex bf_mutex; struct io_mapping *bf_mapping; + void __iomem *clock_mapping; int reserved_mtts; int fs_hash_mode; u8 virt2phys_pkey[MLX4_MFUNC_MAX][MLX4_MAX_PORTS][MLX4_MAX_PORT_PKEYS]; @@ -1127,6 +1157,8 @@ int mlx4_change_port_types(struct mlx4_dev *dev, void mlx4_init_mac_table(struct mlx4_dev *dev, struct mlx4_mac_table *table); void mlx4_init_vlan_table(struct mlx4_dev *dev, struct mlx4_vlan_table *table); +void __mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index); +int __mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index); int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port, int pkey_tbl_sz); /* resource tracker functions*/ @@ -1190,6 +1222,10 @@ int mlx4_qp_detach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], int block_mcast_loopback, enum mlx4_protocol prot, enum mlx4_steer_type steer); +int mlx4_trans_to_dmfs_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, + u8 gid[16], u8 port, + int block_mcast_loopback, + enum mlx4_protocol prot, u64 *reg_id); int mlx4_SET_MCAST_FLTR_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox, diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index f710b7ce0dcb..b1d7657b2bf5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -40,6 +40,7 @@ #include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/if_vlan.h> +#include <linux/net_tstamp.h> #ifdef CONFIG_MLX4_EN_DCB #include <linux/dcbnl.h> #endif @@ -77,6 +78,7 @@ #define STAMP_SHIFT 31 #define STAMP_VAL 0x7fffffff #define STATS_DELAY (HZ / 4) +#define SERVICE_TASK_DELAY (HZ / 4) #define MAX_NUM_OF_FS_RULES 256 #define MLX4_EN_FILTER_HASH_SHIFT 4 @@ -207,6 +209,7 @@ struct mlx4_en_tx_info { u8 linear; u8 data_offset; u8 inl; + u8 ts_requested; }; @@ -262,6 +265,7 @@ struct mlx4_en_tx_ring { struct mlx4_bf bf; bool bf_enabled; struct netdev_queue *tx_queue; + int hwtstamp_tx_type; }; struct mlx4_en_rx_desc { @@ -288,6 +292,7 @@ struct mlx4_en_rx_ring { unsigned long packets; unsigned long csum_ok; unsigned long csum_none; + int hwtstamp_rx_filter; }; struct mlx4_en_cq { @@ -348,6 +353,10 @@ struct mlx4_en_dev { u32 priv_pdn; spinlock_t uar_lock; u8 mac_removed[MLX4_MAX_PORTS + 1]; + struct cyclecounter cycles; + struct timecounter clock; + unsigned long last_overflow_check; + unsigned long overflow_period; }; @@ -512,6 +521,7 @@ struct mlx4_en_priv { struct work_struct watchdog_task; struct work_struct linkstate_task; struct delayed_work stats_task; + struct delayed_work service_task; struct mlx4_en_perf_stats pstats; struct mlx4_en_pkt_stats pkstats; struct mlx4_en_port_stats port_stats; @@ -525,6 +535,7 @@ struct mlx4_en_priv { struct device *ddev; int base_tx_qpn; struct hlist_head mac_hash[MLX4_EN_MAC_HASH_SIZE]; + struct hwtstamp_config hwtstamp_config; #ifdef CONFIG_MLX4_EN_DCB struct ieee_ets ets; @@ -624,6 +635,7 @@ int mlx4_en_QUERY_PORT(struct mlx4_en_dev *mdev, u8 port); #ifdef CONFIG_MLX4_EN_DCB extern const struct dcbnl_rtnl_ops mlx4_en_dcbnl_ops; +extern const struct dcbnl_rtnl_ops mlx4_en_dcbnl_pfc_ops; #endif int mlx4_en_setup_tc(struct net_device *dev, u8 up); @@ -636,9 +648,21 @@ void mlx4_en_cleanup_filters(struct mlx4_en_priv *priv, #define MLX4_EN_NUM_SELF_TEST 5 void mlx4_en_ex_selftest(struct net_device *dev, u32 *flags, u64 *buf); u64 mlx4_en_mac_to_u64(u8 *addr); +void mlx4_en_ptp_overflow_check(struct mlx4_en_dev *mdev); /* - * Globals + * Functions for time stamping + */ +u64 mlx4_en_get_cqe_ts(struct mlx4_cqe *cqe); +void mlx4_en_fill_hwtstamps(struct mlx4_en_dev *mdev, + struct skb_shared_hwtstamps *hwts, + u64 timestamp); +void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev); +int mlx4_en_timestamp_config(struct net_device *dev, + int tx_type, + int rx_filter); + +/* Globals */ extern const struct ethtool_ops mlx4_en_ethtool_ops; diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index 10c57c86388b..946e0af5faef 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -32,6 +32,7 @@ #include <linux/errno.h> #include <linux/if_ether.h> +#include <linux/if_vlan.h> #include <linux/export.h> #include <linux/mlx4/cmd.h> @@ -140,8 +141,9 @@ int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac) } if (mac == (MLX4_MAC_MASK & be64_to_cpu(table->entries[i]))) { - /* MAC already registered, Must not have duplicates */ - err = -EEXIST; + /* MAC already registered, increment ref count */ + err = i; + ++table->refs[i]; goto out; } } @@ -164,7 +166,7 @@ int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac) table->entries[free] = 0; goto out; } - + table->refs[free] = 1; err = free; ++table->total; out: @@ -205,12 +207,16 @@ void __mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac) struct mlx4_mac_table *table = &info->mac_table; int index; - index = find_index(dev, table, mac); - mutex_lock(&table->mutex); + index = find_index(dev, table, mac); if (validate_index(dev, table, index)) goto out; + if (--table->refs[index]) { + mlx4_dbg(dev, "Have more references for index %d," + "no need to modify mac table\n", index); + goto out; + } table->entries[index] = 0; mlx4_set_port_mac_table(dev, port, table->entries); @@ -304,7 +310,7 @@ int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx) } EXPORT_SYMBOL_GPL(mlx4_find_cached_vlan); -static int __mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, +int __mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index) { struct mlx4_vlan_table *table = &mlx4_priv(dev)->port[port].vlan_table; @@ -378,7 +384,7 @@ int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index) } EXPORT_SYMBOL_GPL(mlx4_register_vlan); -static void __mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index) +void __mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index) { struct mlx4_vlan_table *table = &mlx4_priv(dev)->port[port].vlan_table; @@ -517,7 +523,8 @@ static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod, /* Mtu is configured as the max MTU among all the * the functions on the port. */ mtu = be16_to_cpu(gen_context->mtu); - mtu = min_t(int, mtu, dev->caps.eth_mtu_cap[port]); + mtu = min_t(int, mtu, dev->caps.eth_mtu_cap[port] + + ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN); prev_mtu = slave_st->mtu[port]; slave_st->mtu[port] = mtu; if (mtu > master->max_mtu[port]) diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 1391b52f443a..e12e0d2e0ee0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -75,6 +75,7 @@ struct res_gid { u8 gid[16]; enum mlx4_protocol prot; enum mlx4_steer_type steer; + u64 reg_id; }; enum res_qp_states { @@ -352,6 +353,47 @@ static void update_gid(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *inbox, } } +static int update_vport_qp_param(struct mlx4_dev *dev, + struct mlx4_cmd_mailbox *inbox, + u8 slave) +{ + struct mlx4_qp_context *qpc = inbox->buf + 8; + struct mlx4_vport_oper_state *vp_oper; + struct mlx4_priv *priv; + u32 qp_type; + int port; + + port = (qpc->pri_path.sched_queue & 0x40) ? 2 : 1; + priv = mlx4_priv(dev); + vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port]; + + if (MLX4_VGT != vp_oper->state.default_vlan) { + qp_type = (be32_to_cpu(qpc->flags) >> 16) & 0xff; + if (MLX4_QP_ST_RC == qp_type) + return -EINVAL; + + qpc->pri_path.vlan_index = vp_oper->vlan_idx; + qpc->pri_path.fl = (1 << 6) | (1 << 2); /* set cv bit and hide_cqe_vlan bit*/ + qpc->pri_path.feup |= 1 << 3; /* set fvl bit */ + qpc->pri_path.sched_queue &= 0xC7; + qpc->pri_path.sched_queue |= (vp_oper->state.default_qos) << 3; + mlx4_dbg(dev, "qp %d port %d Q 0x%x set vlan to %d vidx %d feup %x fl %x\n", + be32_to_cpu(qpc->local_qpn) & 0xffffff, port, + (int)(qpc->pri_path.sched_queue), vp_oper->state.default_vlan, + vp_oper->vlan_idx, (int)(qpc->pri_path.feup), + (int)(qpc->pri_path.fl)); + } + if (vp_oper->state.spoofchk) { + qpc->pri_path.feup |= 1 << 5; /* set fsm bit */; + qpc->pri_path.grh_mylmc = (0x80 & qpc->pri_path.grh_mylmc) + vp_oper->mac_idx; + mlx4_dbg(dev, "spoof qp %d port %d feup 0x%x, myLmc 0x%x mindx %d\n", + be32_to_cpu(qpc->local_qpn) & 0xffffff, port, + (int)qpc->pri_path.feup, (int)qpc->pri_path.grh_mylmc, + vp_oper->mac_idx); + } + return 0; +} + static int mpt_mask(struct mlx4_dev *dev) { return dev->caps.num_mpts - 1; @@ -2797,6 +2839,9 @@ int mlx4_INIT2RTR_QP_wrapper(struct mlx4_dev *dev, int slave, update_pkey_index(dev, slave, inbox); update_gid(dev, inbox, (u8)slave); adjust_proxy_tun_qkey(dev, vhcr, qpc); + err = update_vport_qp_param(dev, inbox, slave); + if (err) + return err; return mlx4_GEN_QP_wrapper(dev, slave, vhcr, inbox, outbox, cmd); } @@ -2934,7 +2979,7 @@ static struct res_gid *find_gid(struct mlx4_dev *dev, int slave, static int add_mcg_res(struct mlx4_dev *dev, int slave, struct res_qp *rqp, u8 *gid, enum mlx4_protocol prot, - enum mlx4_steer_type steer) + enum mlx4_steer_type steer, u64 reg_id) { struct res_gid *res; int err; @@ -2951,6 +2996,7 @@ static int add_mcg_res(struct mlx4_dev *dev, int slave, struct res_qp *rqp, memcpy(res->gid, gid, 16); res->prot = prot; res->steer = steer; + res->reg_id = reg_id; list_add_tail(&res->list, &rqp->mcg_list); err = 0; } @@ -2961,7 +3007,7 @@ static int add_mcg_res(struct mlx4_dev *dev, int slave, struct res_qp *rqp, static int rem_mcg_res(struct mlx4_dev *dev, int slave, struct res_qp *rqp, u8 *gid, enum mlx4_protocol prot, - enum mlx4_steer_type steer) + enum mlx4_steer_type steer, u64 *reg_id) { struct res_gid *res; int err; @@ -2971,6 +3017,7 @@ static int rem_mcg_res(struct mlx4_dev *dev, int slave, struct res_qp *rqp, if (!res || res->prot != prot || res->steer != steer) err = -EINVAL; else { + *reg_id = res->reg_id; list_del(&res->list); kfree(res); err = 0; @@ -2980,6 +3027,37 @@ static int rem_mcg_res(struct mlx4_dev *dev, int slave, struct res_qp *rqp, return err; } +static int qp_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], + int block_loopback, enum mlx4_protocol prot, + enum mlx4_steer_type type, u64 *reg_id) +{ + switch (dev->caps.steering_mode) { + case MLX4_STEERING_MODE_DEVICE_MANAGED: + return mlx4_trans_to_dmfs_attach(dev, qp, gid, gid[5], + block_loopback, prot, + reg_id); + case MLX4_STEERING_MODE_B0: + return mlx4_qp_attach_common(dev, qp, gid, + block_loopback, prot, type); + default: + return -EINVAL; + } +} + +static int qp_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], + enum mlx4_protocol prot, enum mlx4_steer_type type, + u64 reg_id) +{ + switch (dev->caps.steering_mode) { + case MLX4_STEERING_MODE_DEVICE_MANAGED: + return mlx4_flow_detach(dev, reg_id); + case MLX4_STEERING_MODE_B0: + return mlx4_qp_detach_common(dev, qp, gid, prot, type); + default: + return -EINVAL; + } +} + int mlx4_QP_ATTACH_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox, @@ -2992,14 +3070,12 @@ int mlx4_QP_ATTACH_wrapper(struct mlx4_dev *dev, int slave, int err; int qpn; struct res_qp *rqp; + u64 reg_id = 0; int attach = vhcr->op_modifier; int block_loopback = vhcr->in_modifier >> 31; u8 steer_type_mask = 2; enum mlx4_steer_type type = (gid[7] & steer_type_mask) >> 1; - if (dev->caps.steering_mode != MLX4_STEERING_MODE_B0) - return -EINVAL; - qpn = vhcr->in_modifier & 0xffffff; err = get_res(dev, slave, qpn, RES_QP, &rqp); if (err) @@ -3007,30 +3083,32 @@ int mlx4_QP_ATTACH_wrapper(struct mlx4_dev *dev, int slave, qp.qpn = qpn; if (attach) { - err = add_mcg_res(dev, slave, rqp, gid, prot, type); - if (err) + err = qp_attach(dev, &qp, gid, block_loopback, prot, + type, ®_id); + if (err) { + pr_err("Fail to attach rule to qp 0x%x\n", qpn); goto ex_put; - - err = mlx4_qp_attach_common(dev, &qp, gid, - block_loopback, prot, type); + } + err = add_mcg_res(dev, slave, rqp, gid, prot, type, reg_id); if (err) - goto ex_rem; + goto ex_detach; } else { - err = rem_mcg_res(dev, slave, rqp, gid, prot, type); + err = rem_mcg_res(dev, slave, rqp, gid, prot, type, ®_id); if (err) goto ex_put; - err = mlx4_qp_detach_common(dev, &qp, gid, prot, type); - } + err = qp_detach(dev, &qp, gid, prot, type, reg_id); + if (err) + pr_err("Fail to detach rule from qp 0x%x reg_id = 0x%llx\n", + qpn, reg_id); + } put_res(dev, slave, qpn, RES_QP); - return 0; + return err; -ex_rem: - /* ignore error return below, already in error */ - (void) rem_mcg_res(dev, slave, rqp, gid, prot, type); +ex_detach: + qp_detach(dev, &qp, gid, prot, type, reg_id); ex_put: put_res(dev, slave, qpn, RES_QP); - return err; } @@ -3266,9 +3344,16 @@ static void detach_qp(struct mlx4_dev *dev, int slave, struct res_qp *rqp) struct mlx4_qp qp; /* dummy for calling attach/detach */ list_for_each_entry_safe(rgid, tmp, &rqp->mcg_list, list) { - qp.qpn = rqp->local_qpn; - (void) mlx4_qp_detach_common(dev, &qp, rgid->gid, rgid->prot, - rgid->steer); + switch (dev->caps.steering_mode) { + case MLX4_STEERING_MODE_DEVICE_MANAGED: + mlx4_flow_detach(dev, rgid->reg_id); + break; + case MLX4_STEERING_MODE_B0: + qp.qpn = rqp->local_qpn; + (void) mlx4_qp_detach_common(dev, &qp, rgid->gid, + rgid->prot, rgid->steer); + break; + } list_del(&rgid->list); kfree(rgid); } |