diff options
author | David S. Miller <davem@davemloft.net> | 2017-10-29 11:20:28 +0900 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2017-10-29 11:20:28 +0900 |
commit | 87e3de1e4e21f8d00dd5eacbf4825b8b15bdbe87 (patch) | |
tree | 0924f65b483afcb9e0eba6201173ac4a590cd484 /drivers/net/ethernet | |
parent | 05ce8bd43f3bd62996a4a70a6f3494a66ace11ca (diff) | |
parent | 05f9d3e1ae6eaf7507e3bd95b0eef2acd4b84ea8 (diff) |
Merge branch '1GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue
Jeff Kirsher says:
====================
1GbE Intel Wired LAN Driver Updates 2017-10-27
This patchset is a proposal of how the Traffic Control subsystem can
be used to offload the configuration of the Credit Based Shaper
(defined in the IEEE 802.1Q-2014 Section 8.6.8.2) into supported
network devices.
As part of this work, we've assessed previous public discussions
related to TSN enabling: patches from Henrik Austad (Cisco), the
presentation from Eric Mann at Linux Plumbers 2012, patches from
Gangfeng Huang (National Instruments) and the current state of the
OpenAVNU project (https://github.com/AVnu/OpenAvnu/).
Overview
========
Time-sensitive Networking (TSN) is a set of standards that aim to
address resources availability for providing bandwidth reservation and
bounded latency on Ethernet based LANs. The proposal described here
aims to cover mainly what is needed to enable the following standards:
802.1Qat and 802.1Qav.
The initial target of this work is the Intel i210 NIC, but other
controllers' datasheet were also taken into account, like the Renesas
RZ/A1H RZ/A1M group and the Synopsis DesignWare Ethernet QoS
controller.
Proposal
========
Feature-wise, what is covered here is the configuration interfaces for
HW implementations of the Credit-Based shaper (CBS, 802.1Qav). CBS is
a per-queue shaper. Given that this feature is related to traffic
shaping, and that the traffic control subsystem already provides a
queueing discipline that offloads config into the device driver (i.e.
mqprio), designing a new qdisc for the specific purpose of offloading
the config for the CBS shaper seemed like a good fit.
For steering traffic into the correct queues, we use the socket option
SO_PRIORITY and then a mechanism to map priority to traffic classes /
Tx queues. The qdisc mqprio is currently used in our tests.
As for the CBS config interface, this patchset is proposing a new
qdisc called 'cbs'. Its 'tc' cmd line is:
$ tc qdisc add dev IFACE parent ID cbs locredit N hicredit M sendslope S \
idleslope I
Note that the parameters for this qdisc are the ones defined by the
802.1Q-2014 spec, so no hardware specific functionality is exposed here.
Per-stream shaping, as defined by IEEE 802.1Q-2014 Section 34.6.1, is
not yet covered by this proposal.
v2: Merged patch 6 of the original series into patch 4 based on feedback
from David Miller.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'drivers/net/ethernet')
-rw-r--r-- | drivers/net/ethernet/intel/igb/e1000_defines.h | 23 | ||||
-rw-r--r-- | drivers/net/ethernet/intel/igb/e1000_regs.h | 8 | ||||
-rw-r--r-- | drivers/net/ethernet/intel/igb/igb.h | 6 | ||||
-rw-r--r-- | drivers/net/ethernet/intel/igb/igb_main.c | 347 |
4 files changed, 384 insertions, 0 deletions
diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h index 1de82f247312..83cabff1e0ab 100644 --- a/drivers/net/ethernet/intel/igb/e1000_defines.h +++ b/drivers/net/ethernet/intel/igb/e1000_defines.h @@ -353,7 +353,18 @@ #define E1000_RXPBS_CFG_TS_EN 0x80000000 #define I210_RXPBSIZE_DEFAULT 0x000000A2 /* RXPBSIZE default */ +#define I210_RXPBSIZE_MASK 0x0000003F +#define I210_RXPBSIZE_PB_32KB 0x00000020 #define I210_TXPBSIZE_DEFAULT 0x04000014 /* TXPBSIZE default */ +#define I210_TXPBSIZE_MASK 0xC0FFFFFF +#define I210_TXPBSIZE_PB0_8KB (8 << 0) +#define I210_TXPBSIZE_PB1_8KB (8 << 6) +#define I210_TXPBSIZE_PB2_4KB (4 << 12) +#define I210_TXPBSIZE_PB3_4KB (4 << 18) + +#define I210_DTXMXPKTSZ_DEFAULT 0x00000098 + +#define I210_SR_QUEUES_NUM 2 /* SerDes Control */ #define E1000_SCTL_DISABLE_SERDES_LOOPBACK 0x0400 @@ -1051,4 +1062,16 @@ #define E1000_VLAPQF_P_VALID(_n) (0x1 << (3 + (_n) * 4)) #define E1000_VLAPQF_QUEUE_MASK 0x03 +/* TX Qav Control fields */ +#define E1000_TQAVCTRL_XMIT_MODE BIT(0) +#define E1000_TQAVCTRL_DATAFETCHARB BIT(4) +#define E1000_TQAVCTRL_DATATRANARB BIT(8) + +/* TX Qav Credit Control fields */ +#define E1000_TQAVCC_IDLESLOPE_MASK 0xFFFF +#define E1000_TQAVCC_QUEUEMODE BIT(31) + +/* Transmit Descriptor Control fields */ +#define E1000_TXDCTL_PRIORITY BIT(27) + #endif diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h index 58adbf234e07..8eee081d395f 100644 --- a/drivers/net/ethernet/intel/igb/e1000_regs.h +++ b/drivers/net/ethernet/intel/igb/e1000_regs.h @@ -421,6 +421,14 @@ do { \ #define E1000_I210_FLA 0x1201C +#define E1000_I210_DTXMXPKTSZ 0x355C + +#define E1000_I210_TXDCTL(_n) (0x0E028 + ((_n) * 0x40)) + +#define E1000_I210_TQAVCTRL 0x3570 +#define E1000_I210_TQAVCC(_n) (0x3004 + ((_n) * 0x40)) +#define E1000_I210_TQAVHC(_n) (0x300C + ((_n) * 0x40)) + #define E1000_INVM_DATA_REG(_n) (0x12120 + 4*(_n)) #define E1000_INVM_SIZE 64 /* Number of INVM Data Registers */ diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 06ffb2bc713e..92845692087a 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -281,6 +281,11 @@ struct igb_ring { u16 count; /* number of desc. in the ring */ u8 queue_index; /* logical index of the ring*/ u8 reg_idx; /* physical index of the ring */ + bool cbs_enable; /* indicates if CBS is enabled */ + s32 idleslope; /* idleSlope in kbps */ + s32 sendslope; /* sendSlope in kbps */ + s32 hicredit; /* hiCredit in bytes */ + s32 locredit; /* loCredit in bytes */ /* everything past this point are written often */ u16 next_to_clean; @@ -621,6 +626,7 @@ struct igb_adapter { #define IGB_FLAG_EEE BIT(14) #define IGB_FLAG_VLAN_PROMISC BIT(15) #define IGB_FLAG_RX_LEGACY BIT(16) +#define IGB_FLAG_FQTSS BIT(17) /* Media Auto Sense */ #define IGB_MAS_ENABLE_0 0X0001 diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 58d01a211367..b3d730f4d695 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -34,6 +34,7 @@ #include <linux/slab.h> #include <net/checksum.h> #include <net/ip6_checksum.h> +#include <net/pkt_sched.h> #include <linux/net_tstamp.h> #include <linux/mii.h> #include <linux/ethtool.h> @@ -62,6 +63,17 @@ #define BUILD 0 #define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \ __stringify(BUILD) "-k" + +enum queue_mode { + QUEUE_MODE_STRICT_PRIORITY, + QUEUE_MODE_STREAM_RESERVATION, +}; + +enum tx_queue_prio { + TX_QUEUE_PRIO_HIGH, + TX_QUEUE_PRIO_LOW, +}; + char igb_driver_name[] = "igb"; char igb_driver_version[] = DRV_VERSION; static const char igb_driver_string[] = @@ -1271,6 +1283,12 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter, ring->count = adapter->tx_ring_count; ring->queue_index = txr_idx; + ring->cbs_enable = false; + ring->idleslope = 0; + ring->sendslope = 0; + ring->hicredit = 0; + ring->locredit = 0; + u64_stats_init(&ring->tx_syncp); u64_stats_init(&ring->tx_syncp2); @@ -1598,6 +1616,284 @@ static void igb_get_hw_control(struct igb_adapter *adapter) ctrl_ext | E1000_CTRL_EXT_DRV_LOAD); } +static void enable_fqtss(struct igb_adapter *adapter, bool enable) +{ + struct net_device *netdev = adapter->netdev; + struct e1000_hw *hw = &adapter->hw; + + WARN_ON(hw->mac.type != e1000_i210); + + if (enable) + adapter->flags |= IGB_FLAG_FQTSS; + else + adapter->flags &= ~IGB_FLAG_FQTSS; + + if (netif_running(netdev)) + schedule_work(&adapter->reset_task); +} + +static bool is_fqtss_enabled(struct igb_adapter *adapter) +{ + return (adapter->flags & IGB_FLAG_FQTSS) ? true : false; +} + +static void set_tx_desc_fetch_prio(struct e1000_hw *hw, int queue, + enum tx_queue_prio prio) +{ + u32 val; + + WARN_ON(hw->mac.type != e1000_i210); + WARN_ON(queue < 0 || queue > 4); + + val = rd32(E1000_I210_TXDCTL(queue)); + + if (prio == TX_QUEUE_PRIO_HIGH) + val |= E1000_TXDCTL_PRIORITY; + else + val &= ~E1000_TXDCTL_PRIORITY; + + wr32(E1000_I210_TXDCTL(queue), val); +} + +static void set_queue_mode(struct e1000_hw *hw, int queue, enum queue_mode mode) +{ + u32 val; + + WARN_ON(hw->mac.type != e1000_i210); + WARN_ON(queue < 0 || queue > 1); + + val = rd32(E1000_I210_TQAVCC(queue)); + + if (mode == QUEUE_MODE_STREAM_RESERVATION) + val |= E1000_TQAVCC_QUEUEMODE; + else + val &= ~E1000_TQAVCC_QUEUEMODE; + + wr32(E1000_I210_TQAVCC(queue), val); +} + +/** + * igb_configure_cbs - Configure Credit-Based Shaper (CBS) + * @adapter: pointer to adapter struct + * @queue: queue number + * @enable: true = enable CBS, false = disable CBS + * @idleslope: idleSlope in kbps + * @sendslope: sendSlope in kbps + * @hicredit: hiCredit in bytes + * @locredit: loCredit in bytes + * + * Configure CBS for a given hardware queue. When disabling, idleslope, + * sendslope, hicredit, locredit arguments are ignored. Returns 0 if + * success. Negative otherwise. + **/ +static void igb_configure_cbs(struct igb_adapter *adapter, int queue, + bool enable, int idleslope, int sendslope, + int hicredit, int locredit) +{ + struct net_device *netdev = adapter->netdev; + struct e1000_hw *hw = &adapter->hw; + u32 tqavcc; + u16 value; + + WARN_ON(hw->mac.type != e1000_i210); + WARN_ON(queue < 0 || queue > 1); + + if (enable) { + set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH); + set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION); + + /* According to i210 datasheet section 7.2.7.7, we should set + * the 'idleSlope' field from TQAVCC register following the + * equation: + * + * For 100 Mbps link speed: + * + * value = BW * 0x7735 * 0.2 (E1) + * + * For 1000Mbps link speed: + * + * value = BW * 0x7735 * 2 (E2) + * + * E1 and E2 can be merged into one equation as shown below. + * Note that 'link-speed' is in Mbps. + * + * value = BW * 0x7735 * 2 * link-speed + * -------------- (E3) + * 1000 + * + * 'BW' is the percentage bandwidth out of full link speed + * which can be found with the following equation. Note that + * idleSlope here is the parameter from this function which + * is in kbps. + * + * BW = idleSlope + * ----------------- (E4) + * link-speed * 1000 + * + * That said, we can come up with a generic equation to + * calculate the value we should set it TQAVCC register by + * replacing 'BW' in E3 by E4. The resulting equation is: + * + * value = idleSlope * 0x7735 * 2 * link-speed + * ----------------- -------------- (E5) + * link-speed * 1000 1000 + * + * 'link-speed' is present in both sides of the fraction so + * it is canceled out. The final equation is the following: + * + * value = idleSlope * 61034 + * ----------------- (E6) + * 1000000 + */ + value = DIV_ROUND_UP_ULL(idleslope * 61034ULL, 1000000); + + tqavcc = rd32(E1000_I210_TQAVCC(queue)); + tqavcc &= ~E1000_TQAVCC_IDLESLOPE_MASK; + tqavcc |= value; + wr32(E1000_I210_TQAVCC(queue), tqavcc); + + wr32(E1000_I210_TQAVHC(queue), 0x80000000 + hicredit * 0x7735); + } else { + set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_LOW); + set_queue_mode(hw, queue, QUEUE_MODE_STRICT_PRIORITY); + + /* Set idleSlope to zero. */ + tqavcc = rd32(E1000_I210_TQAVCC(queue)); + tqavcc &= ~E1000_TQAVCC_IDLESLOPE_MASK; + wr32(E1000_I210_TQAVCC(queue), tqavcc); + + /* Set hiCredit to zero. */ + wr32(E1000_I210_TQAVHC(queue), 0); + } + + /* XXX: In i210 controller the sendSlope and loCredit parameters from + * CBS are not configurable by software so we don't do any 'controller + * configuration' in respect to these parameters. + */ + + netdev_dbg(netdev, "CBS %s: queue %d idleslope %d sendslope %d hiCredit %d locredit %d\n", + (enable) ? "enabled" : "disabled", queue, + idleslope, sendslope, hicredit, locredit); +} + +static int igb_save_cbs_params(struct igb_adapter *adapter, int queue, + bool enable, int idleslope, int sendslope, + int hicredit, int locredit) +{ + struct igb_ring *ring; + + if (queue < 0 || queue > adapter->num_tx_queues) + return -EINVAL; + + ring = adapter->tx_ring[queue]; + + ring->cbs_enable = enable; + ring->idleslope = idleslope; + ring->sendslope = sendslope; + ring->hicredit = hicredit; + ring->locredit = locredit; + + return 0; +} + +static bool is_any_cbs_enabled(struct igb_adapter *adapter) +{ + struct igb_ring *ring; + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) { + ring = adapter->tx_ring[i]; + + if (ring->cbs_enable) + return true; + } + + return false; +} + +static void igb_setup_tx_mode(struct igb_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct e1000_hw *hw = &adapter->hw; + u32 val; + + /* Only i210 controller supports changing the transmission mode. */ + if (hw->mac.type != e1000_i210) + return; + + if (is_fqtss_enabled(adapter)) { + int i, max_queue; + + /* Configure TQAVCTRL register: set transmit mode to 'Qav', + * set data fetch arbitration to 'round robin' and set data + * transfer arbitration to 'credit shaper algorithm. + */ + val = rd32(E1000_I210_TQAVCTRL); + val |= E1000_TQAVCTRL_XMIT_MODE | E1000_TQAVCTRL_DATATRANARB; + val &= ~E1000_TQAVCTRL_DATAFETCHARB; + wr32(E1000_I210_TQAVCTRL, val); + + /* Configure Tx and Rx packet buffers sizes as described in + * i210 datasheet section 7.2.7.7. + */ + val = rd32(E1000_TXPBS); + val &= ~I210_TXPBSIZE_MASK; + val |= I210_TXPBSIZE_PB0_8KB | I210_TXPBSIZE_PB1_8KB | + I210_TXPBSIZE_PB2_4KB | I210_TXPBSIZE_PB3_4KB; + wr32(E1000_TXPBS, val); + + val = rd32(E1000_RXPBS); + val &= ~I210_RXPBSIZE_MASK; + val |= I210_RXPBSIZE_PB_32KB; + wr32(E1000_RXPBS, val); + + /* Section 8.12.9 states that MAX_TPKT_SIZE from DTXMXPKTSZ + * register should not exceed the buffer size programmed in + * TXPBS. The smallest buffer size programmed in TXPBS is 4kB + * so according to the datasheet we should set MAX_TPKT_SIZE to + * 4kB / 64. + * + * However, when we do so, no frame from queue 2 and 3 are + * transmitted. It seems the MAX_TPKT_SIZE should not be great + * or _equal_ to the buffer size programmed in TXPBS. For this + * reason, we set set MAX_ TPKT_SIZE to (4kB - 1) / 64. + */ + val = (4096 - 1) / 64; + wr32(E1000_I210_DTXMXPKTSZ, val); + + /* Since FQTSS mode is enabled, apply any CBS configuration + * previously set. If no previous CBS configuration has been + * done, then the initial configuration is applied, which means + * CBS is disabled. + */ + max_queue = (adapter->num_tx_queues < I210_SR_QUEUES_NUM) ? + adapter->num_tx_queues : I210_SR_QUEUES_NUM; + + for (i = 0; i < max_queue; i++) { + struct igb_ring *ring = adapter->tx_ring[i]; + + igb_configure_cbs(adapter, i, ring->cbs_enable, + ring->idleslope, ring->sendslope, + ring->hicredit, ring->locredit); + } + } else { + wr32(E1000_RXPBS, I210_RXPBSIZE_DEFAULT); + wr32(E1000_TXPBS, I210_TXPBSIZE_DEFAULT); + wr32(E1000_I210_DTXMXPKTSZ, I210_DTXMXPKTSZ_DEFAULT); + + val = rd32(E1000_I210_TQAVCTRL); + /* According to Section 8.12.21, the other flags we've set when + * enabling FQTSS are not relevant when disabling FQTSS so we + * don't set they here. + */ + val &= ~E1000_TQAVCTRL_XMIT_MODE; + wr32(E1000_I210_TQAVCTRL, val); + } + + netdev_dbg(netdev, "FQTSS %s\n", (is_fqtss_enabled(adapter)) ? + "enabled" : "disabled"); +} + /** * igb_configure - configure the hardware for RX and TX * @adapter: private board structure @@ -1609,6 +1905,7 @@ static void igb_configure(struct igb_adapter *adapter) igb_get_hw_control(adapter); igb_set_rx_mode(netdev); + igb_setup_tx_mode(adapter); igb_restore_vlan(adapter); @@ -2150,6 +2447,55 @@ igb_features_check(struct sk_buff *skb, struct net_device *dev, return features; } +static int igb_offload_cbs(struct igb_adapter *adapter, + struct tc_cbs_qopt_offload *qopt) +{ + struct e1000_hw *hw = &adapter->hw; + int err; + + /* CBS offloading is only supported by i210 controller. */ + if (hw->mac.type != e1000_i210) + return -EOPNOTSUPP; + + /* CBS offloading is only supported by queue 0 and queue 1. */ + if (qopt->queue < 0 || qopt->queue > 1) + return -EINVAL; + + err = igb_save_cbs_params(adapter, qopt->queue, qopt->enable, + qopt->idleslope, qopt->sendslope, + qopt->hicredit, qopt->locredit); + if (err) + return err; + + if (is_fqtss_enabled(adapter)) { + igb_configure_cbs(adapter, qopt->queue, qopt->enable, + qopt->idleslope, qopt->sendslope, + qopt->hicredit, qopt->locredit); + + if (!is_any_cbs_enabled(adapter)) + enable_fqtss(adapter, false); + + } else { + enable_fqtss(adapter, true); + } + + return 0; +} + +static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) +{ + struct igb_adapter *adapter = netdev_priv(dev); + + switch (type) { + case TC_SETUP_CBS: + return igb_offload_cbs(adapter, type_data); + + default: + return -EOPNOTSUPP; + } +} + static const struct net_device_ops igb_netdev_ops = { .ndo_open = igb_open, .ndo_stop = igb_close, @@ -2175,6 +2521,7 @@ static const struct net_device_ops igb_netdev_ops = { .ndo_set_features = igb_set_features, .ndo_fdb_add = igb_ndo_fdb_add, .ndo_features_check = igb_features_check, + .ndo_setup_tc = igb_setup_tc, }; /** |