linux/drivers/net/ethernet/ti/am65-cpsw-qos.h

228 lines
7.8 KiB
C
Raw Permalink Normal View History

ethernet: ti: am65-cpsw-qos: add TAPRIO offload support AM65 CPSW h/w supports Enhanced Scheduled Traffic (EST – defined in P802.1Qbv/D2.2 that later got included in IEEE 802.1Q-2018) configuration. EST allows express queue traffic to be scheduled (placed) on the wire at specific repeatable time intervals. In Linux kernel, EST configuration is done through tc command and the taprio scheduler in the net core implements a software only scheduler (SCH_TAPRIO). If the NIC is capable of EST configuration, user indicate "flag 2" in the command which is then parsed by taprio scheduler in net core and indicate that the command is to be offloaded to h/w. taprio then offloads the command to the driver by calling ndo_setup_tc() ndo ops. This patch implements ndo_setup_tc() to offload EST configuration to CPSW h/w. Currently driver supports only SetGateStates operation. EST operates on a repeating time interval generated by the CPTS EST function generator. Each Ethernet port has a global EST fetch RAM that can be configured as 2 buffers, each of 64 locations or one large buffer of 128 locations. In 2 buffer configuration, a ping pong mechanism is used to hold the active schedule (oper) in one buffer and new (admin) command in the other. Each 22-bit fetch command consists of a 14-bit fetch count (14 MSB’s) and an 8-bit priority fetch allow (8 LSB’s) that will be applied for the fetch count time in wireside clocks. Driver process each of the sched-entry in the offload command and update the fetch RAM. Driver configures duration in sched-entry into the fetch count and Gate mask into the priority fetch bits of the RAM. Then configures the CPTS EST function generator to activate the schedule. Currently driver supports only 2 buffer configuration which means driver supports a max cycle time of ~8 msec. CPSW supports a configurable number of priority queues (up to 8) and needs to be switched to this mode from the default round robin mode before EST can be offloaded. User configures these through ethtool commands (-L for changing number of queues and --set-priv-flags to disable round robin mode). Driver doesn't enable EST if pf_p0_rx_ptype_rrobin privat flag is set. The flag is common for all ports, and so can't be just overridden by taprio configuration w/o user involvement. Command fails if pf_p0_rx_ptype_rrobin is already set in the driver. Scheds (commands) configuration depends on interface speed so driver translates the duration to the fetch count based on link speed. Each schedule can be constructed with several command entries in fetch RAM depending on interval. For example if each sched has timer interval < ~130us on 1000 Mb link then each sched consumes one command and have 1:1 mapping. When Ethernet link goes down, driver purge the configuration if link is down for more than 1 second. The patch allows to update the timer and scheds memory only if it's really needed, and skip cases required the user to stop timer by configuring only shceds memory. Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> Signed-off-by: Murali Karicheri <m-karicheri2@ti.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-13 09:26:15 -04:00
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (C) 2020 Texas Instruments Incorporated - http://www.ti.com/
*/
#ifndef AM65_CPSW_QOS_H_
#define AM65_CPSW_QOS_H_
#include <linux/netdevice.h>
#include <net/pkt_sched.h>
struct am65_cpsw_common;
net: ethernet: ti: am65-cpsw: add mqprio qdisc offload in channel mode This patch adds MQPRIO Qdisc offload in full 'channel' mode which allows not only setting up pri:tc mapping, but also configuring TX shapers (rate-limiting) on external port FIFOs. The MQPRIO Qdisc offload is expected to work with or without VLAN/priority tagged packets. The CPSW external Port FIFO has 8 Priority queues. The rate-limit can be set for each of these priority queues. Which Priority queue a packet is assigned to depends on PN_REG_TX_PRI_MAP register which maps header priority to switch priority. The header priority of a packet is assigned via the RX_PRI_MAP_REG which maps packet priority to header priority. The packet priority is either the VLAN priority (for VLAN tagged packets) or the thread/channel offset. For simplicity, we assign the same priority queue to all queues of a Traffic Class so it can be rate-limited correctly. Configuration example: ethtool -L eth1 tx 5 ethtool --set-priv-flags eth1 p0-rx-ptype-rrobin off tc qdisc add dev eth1 parent root handle 100: mqprio num_tc 3 \ map 0 0 1 2 0 0 0 0 0 0 0 0 0 0 0 0 \ queues 1@0 1@1 1@2 hw 1 mode channel \ shaper bw_rlimit min_rate 0 100mbit 200mbit max_rate 0 101mbit 202mbit tc qdisc replace dev eth2 handle 100: parent root mqprio num_tc 1 \ map 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 queues 1@0 hw 1 ip link add link eth1 name eth1.100 type vlan id 100 ip link set eth1.100 type vlan egress 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 In the above example two ports share the same TX CPPI queue 0 for low priority traffic. 3 traffic classes are defined for eth1 and mapped to: TC0 - low priority, TX CPPI queue 0 -> ext Port 1 fifo0, no rate limit TC1 - prio 2, TX CPPI queue 1 -> ext Port 1 fifo1, CIR=100Mbit/s, EIR=1Mbit/s TC2 - prio 3, TX CPPI queue 2 -> ext Port 1 fifo2, CIR=200Mbit/s, EIR=2Mbit/s Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Roger Quadros <rogerq@kernel.org> Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-12-19 12:58:03 +02:00
struct am65_cpsw_port;
ethernet: ti: am65-cpsw-qos: add TAPRIO offload support AM65 CPSW h/w supports Enhanced Scheduled Traffic (EST – defined in P802.1Qbv/D2.2 that later got included in IEEE 802.1Q-2018) configuration. EST allows express queue traffic to be scheduled (placed) on the wire at specific repeatable time intervals. In Linux kernel, EST configuration is done through tc command and the taprio scheduler in the net core implements a software only scheduler (SCH_TAPRIO). If the NIC is capable of EST configuration, user indicate "flag 2" in the command which is then parsed by taprio scheduler in net core and indicate that the command is to be offloaded to h/w. taprio then offloads the command to the driver by calling ndo_setup_tc() ndo ops. This patch implements ndo_setup_tc() to offload EST configuration to CPSW h/w. Currently driver supports only SetGateStates operation. EST operates on a repeating time interval generated by the CPTS EST function generator. Each Ethernet port has a global EST fetch RAM that can be configured as 2 buffers, each of 64 locations or one large buffer of 128 locations. In 2 buffer configuration, a ping pong mechanism is used to hold the active schedule (oper) in one buffer and new (admin) command in the other. Each 22-bit fetch command consists of a 14-bit fetch count (14 MSB’s) and an 8-bit priority fetch allow (8 LSB’s) that will be applied for the fetch count time in wireside clocks. Driver process each of the sched-entry in the offload command and update the fetch RAM. Driver configures duration in sched-entry into the fetch count and Gate mask into the priority fetch bits of the RAM. Then configures the CPTS EST function generator to activate the schedule. Currently driver supports only 2 buffer configuration which means driver supports a max cycle time of ~8 msec. CPSW supports a configurable number of priority queues (up to 8) and needs to be switched to this mode from the default round robin mode before EST can be offloaded. User configures these through ethtool commands (-L for changing number of queues and --set-priv-flags to disable round robin mode). Driver doesn't enable EST if pf_p0_rx_ptype_rrobin privat flag is set. The flag is common for all ports, and so can't be just overridden by taprio configuration w/o user involvement. Command fails if pf_p0_rx_ptype_rrobin is already set in the driver. Scheds (commands) configuration depends on interface speed so driver translates the duration to the fetch count based on link speed. Each schedule can be constructed with several command entries in fetch RAM depending on interval. For example if each sched has timer interval < ~130us on 1000 Mb link then each sched consumes one command and have 1:1 mapping. When Ethernet link goes down, driver purge the configuration if link is down for more than 1 second. The patch allows to update the timer and scheds memory only if it's really needed, and skip cases required the user to stop timer by configuring only shceds memory. Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> Signed-off-by: Murali Karicheri <m-karicheri2@ti.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-13 09:26:15 -04:00
struct am65_cpsw_est {
int buf;
/* has to be the last one */
struct tc_taprio_qopt_offload taprio;
};
net: ethernet: ti: am65-cpsw: add mqprio qdisc offload in channel mode This patch adds MQPRIO Qdisc offload in full 'channel' mode which allows not only setting up pri:tc mapping, but also configuring TX shapers (rate-limiting) on external port FIFOs. The MQPRIO Qdisc offload is expected to work with or without VLAN/priority tagged packets. The CPSW external Port FIFO has 8 Priority queues. The rate-limit can be set for each of these priority queues. Which Priority queue a packet is assigned to depends on PN_REG_TX_PRI_MAP register which maps header priority to switch priority. The header priority of a packet is assigned via the RX_PRI_MAP_REG which maps packet priority to header priority. The packet priority is either the VLAN priority (for VLAN tagged packets) or the thread/channel offset. For simplicity, we assign the same priority queue to all queues of a Traffic Class so it can be rate-limited correctly. Configuration example: ethtool -L eth1 tx 5 ethtool --set-priv-flags eth1 p0-rx-ptype-rrobin off tc qdisc add dev eth1 parent root handle 100: mqprio num_tc 3 \ map 0 0 1 2 0 0 0 0 0 0 0 0 0 0 0 0 \ queues 1@0 1@1 1@2 hw 1 mode channel \ shaper bw_rlimit min_rate 0 100mbit 200mbit max_rate 0 101mbit 202mbit tc qdisc replace dev eth2 handle 100: parent root mqprio num_tc 1 \ map 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 queues 1@0 hw 1 ip link add link eth1 name eth1.100 type vlan id 100 ip link set eth1.100 type vlan egress 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 In the above example two ports share the same TX CPPI queue 0 for low priority traffic. 3 traffic classes are defined for eth1 and mapped to: TC0 - low priority, TX CPPI queue 0 -> ext Port 1 fifo0, no rate limit TC1 - prio 2, TX CPPI queue 1 -> ext Port 1 fifo1, CIR=100Mbit/s, EIR=1Mbit/s TC2 - prio 3, TX CPPI queue 2 -> ext Port 1 fifo2, CIR=200Mbit/s, EIR=2Mbit/s Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Roger Quadros <rogerq@kernel.org> Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-12-19 12:58:03 +02:00
struct am65_cpsw_mqprio {
struct tc_mqprio_qopt_offload mqprio_hw;
u64 max_rate_total;
bool shaper_en;
};
struct am65_cpsw_iet {
u8 preemptible_tcs;
u32 original_max_blks;
int verify_time_ms;
};
struct am65_cpsw_ale_ratelimit {
unsigned long cookie;
u64 rate_packet_ps;
};
ethernet: ti: am65-cpsw-qos: add TAPRIO offload support AM65 CPSW h/w supports Enhanced Scheduled Traffic (EST – defined in P802.1Qbv/D2.2 that later got included in IEEE 802.1Q-2018) configuration. EST allows express queue traffic to be scheduled (placed) on the wire at specific repeatable time intervals. In Linux kernel, EST configuration is done through tc command and the taprio scheduler in the net core implements a software only scheduler (SCH_TAPRIO). If the NIC is capable of EST configuration, user indicate "flag 2" in the command which is then parsed by taprio scheduler in net core and indicate that the command is to be offloaded to h/w. taprio then offloads the command to the driver by calling ndo_setup_tc() ndo ops. This patch implements ndo_setup_tc() to offload EST configuration to CPSW h/w. Currently driver supports only SetGateStates operation. EST operates on a repeating time interval generated by the CPTS EST function generator. Each Ethernet port has a global EST fetch RAM that can be configured as 2 buffers, each of 64 locations or one large buffer of 128 locations. In 2 buffer configuration, a ping pong mechanism is used to hold the active schedule (oper) in one buffer and new (admin) command in the other. Each 22-bit fetch command consists of a 14-bit fetch count (14 MSB’s) and an 8-bit priority fetch allow (8 LSB’s) that will be applied for the fetch count time in wireside clocks. Driver process each of the sched-entry in the offload command and update the fetch RAM. Driver configures duration in sched-entry into the fetch count and Gate mask into the priority fetch bits of the RAM. Then configures the CPTS EST function generator to activate the schedule. Currently driver supports only 2 buffer configuration which means driver supports a max cycle time of ~8 msec. CPSW supports a configurable number of priority queues (up to 8) and needs to be switched to this mode from the default round robin mode before EST can be offloaded. User configures these through ethtool commands (-L for changing number of queues and --set-priv-flags to disable round robin mode). Driver doesn't enable EST if pf_p0_rx_ptype_rrobin privat flag is set. The flag is common for all ports, and so can't be just overridden by taprio configuration w/o user involvement. Command fails if pf_p0_rx_ptype_rrobin is already set in the driver. Scheds (commands) configuration depends on interface speed so driver translates the duration to the fetch count based on link speed. Each schedule can be constructed with several command entries in fetch RAM depending on interval. For example if each sched has timer interval < ~130us on 1000 Mb link then each sched consumes one command and have 1:1 mapping. When Ethernet link goes down, driver purge the configuration if link is down for more than 1 second. The patch allows to update the timer and scheds memory only if it's really needed, and skip cases required the user to stop timer by configuring only shceds memory. Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> Signed-off-by: Murali Karicheri <m-karicheri2@ti.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-13 09:26:15 -04:00
struct am65_cpsw_qos {
struct am65_cpsw_est *est_admin;
struct am65_cpsw_est *est_oper;
ktime_t link_down_time;
int link_speed;
net: ethernet: ti: am65-cpsw: add mqprio qdisc offload in channel mode This patch adds MQPRIO Qdisc offload in full 'channel' mode which allows not only setting up pri:tc mapping, but also configuring TX shapers (rate-limiting) on external port FIFOs. The MQPRIO Qdisc offload is expected to work with or without VLAN/priority tagged packets. The CPSW external Port FIFO has 8 Priority queues. The rate-limit can be set for each of these priority queues. Which Priority queue a packet is assigned to depends on PN_REG_TX_PRI_MAP register which maps header priority to switch priority. The header priority of a packet is assigned via the RX_PRI_MAP_REG which maps packet priority to header priority. The packet priority is either the VLAN priority (for VLAN tagged packets) or the thread/channel offset. For simplicity, we assign the same priority queue to all queues of a Traffic Class so it can be rate-limited correctly. Configuration example: ethtool -L eth1 tx 5 ethtool --set-priv-flags eth1 p0-rx-ptype-rrobin off tc qdisc add dev eth1 parent root handle 100: mqprio num_tc 3 \ map 0 0 1 2 0 0 0 0 0 0 0 0 0 0 0 0 \ queues 1@0 1@1 1@2 hw 1 mode channel \ shaper bw_rlimit min_rate 0 100mbit 200mbit max_rate 0 101mbit 202mbit tc qdisc replace dev eth2 handle 100: parent root mqprio num_tc 1 \ map 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 queues 1@0 hw 1 ip link add link eth1 name eth1.100 type vlan id 100 ip link set eth1.100 type vlan egress 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 In the above example two ports share the same TX CPPI queue 0 for low priority traffic. 3 traffic classes are defined for eth1 and mapped to: TC0 - low priority, TX CPPI queue 0 -> ext Port 1 fifo0, no rate limit TC1 - prio 2, TX CPPI queue 1 -> ext Port 1 fifo1, CIR=100Mbit/s, EIR=1Mbit/s TC2 - prio 3, TX CPPI queue 2 -> ext Port 1 fifo2, CIR=200Mbit/s, EIR=2Mbit/s Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Roger Quadros <rogerq@kernel.org> Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-12-19 12:58:03 +02:00
struct am65_cpsw_mqprio mqprio;
struct am65_cpsw_iet iet;
struct am65_cpsw_ale_ratelimit ale_bc_ratelimit;
struct am65_cpsw_ale_ratelimit ale_mc_ratelimit;
ethernet: ti: am65-cpsw-qos: add TAPRIO offload support AM65 CPSW h/w supports Enhanced Scheduled Traffic (EST – defined in P802.1Qbv/D2.2 that later got included in IEEE 802.1Q-2018) configuration. EST allows express queue traffic to be scheduled (placed) on the wire at specific repeatable time intervals. In Linux kernel, EST configuration is done through tc command and the taprio scheduler in the net core implements a software only scheduler (SCH_TAPRIO). If the NIC is capable of EST configuration, user indicate "flag 2" in the command which is then parsed by taprio scheduler in net core and indicate that the command is to be offloaded to h/w. taprio then offloads the command to the driver by calling ndo_setup_tc() ndo ops. This patch implements ndo_setup_tc() to offload EST configuration to CPSW h/w. Currently driver supports only SetGateStates operation. EST operates on a repeating time interval generated by the CPTS EST function generator. Each Ethernet port has a global EST fetch RAM that can be configured as 2 buffers, each of 64 locations or one large buffer of 128 locations. In 2 buffer configuration, a ping pong mechanism is used to hold the active schedule (oper) in one buffer and new (admin) command in the other. Each 22-bit fetch command consists of a 14-bit fetch count (14 MSB’s) and an 8-bit priority fetch allow (8 LSB’s) that will be applied for the fetch count time in wireside clocks. Driver process each of the sched-entry in the offload command and update the fetch RAM. Driver configures duration in sched-entry into the fetch count and Gate mask into the priority fetch bits of the RAM. Then configures the CPTS EST function generator to activate the schedule. Currently driver supports only 2 buffer configuration which means driver supports a max cycle time of ~8 msec. CPSW supports a configurable number of priority queues (up to 8) and needs to be switched to this mode from the default round robin mode before EST can be offloaded. User configures these through ethtool commands (-L for changing number of queues and --set-priv-flags to disable round robin mode). Driver doesn't enable EST if pf_p0_rx_ptype_rrobin privat flag is set. The flag is common for all ports, and so can't be just overridden by taprio configuration w/o user involvement. Command fails if pf_p0_rx_ptype_rrobin is already set in the driver. Scheds (commands) configuration depends on interface speed so driver translates the duration to the fetch count based on link speed. Each schedule can be constructed with several command entries in fetch RAM depending on interval. For example if each sched has timer interval < ~130us on 1000 Mb link then each sched consumes one command and have 1:1 mapping. When Ethernet link goes down, driver purge the configuration if link is down for more than 1 second. The patch allows to update the timer and scheds memory only if it's really needed, and skip cases required the user to stop timer by configuring only shceds memory. Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> Signed-off-by: Murali Karicheri <m-karicheri2@ti.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-13 09:26:15 -04:00
};
#define AM65_CPSW_REG_CTL 0x004
#define AM65_CPSW_PN_REG_CTL 0x004
#define AM65_CPSW_PN_REG_FIFO_STATUS 0x050
#define AM65_CPSW_PN_REG_EST_CTL 0x060
#define AM65_CPSW_PN_REG_PRI_CIR(pri) (0x140 + 4 * (pri))
net: ethernet: ti: am65-cpsw: add mqprio qdisc offload in channel mode This patch adds MQPRIO Qdisc offload in full 'channel' mode which allows not only setting up pri:tc mapping, but also configuring TX shapers (rate-limiting) on external port FIFOs. The MQPRIO Qdisc offload is expected to work with or without VLAN/priority tagged packets. The CPSW external Port FIFO has 8 Priority queues. The rate-limit can be set for each of these priority queues. Which Priority queue a packet is assigned to depends on PN_REG_TX_PRI_MAP register which maps header priority to switch priority. The header priority of a packet is assigned via the RX_PRI_MAP_REG which maps packet priority to header priority. The packet priority is either the VLAN priority (for VLAN tagged packets) or the thread/channel offset. For simplicity, we assign the same priority queue to all queues of a Traffic Class so it can be rate-limited correctly. Configuration example: ethtool -L eth1 tx 5 ethtool --set-priv-flags eth1 p0-rx-ptype-rrobin off tc qdisc add dev eth1 parent root handle 100: mqprio num_tc 3 \ map 0 0 1 2 0 0 0 0 0 0 0 0 0 0 0 0 \ queues 1@0 1@1 1@2 hw 1 mode channel \ shaper bw_rlimit min_rate 0 100mbit 200mbit max_rate 0 101mbit 202mbit tc qdisc replace dev eth2 handle 100: parent root mqprio num_tc 1 \ map 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 queues 1@0 hw 1 ip link add link eth1 name eth1.100 type vlan id 100 ip link set eth1.100 type vlan egress 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 In the above example two ports share the same TX CPPI queue 0 for low priority traffic. 3 traffic classes are defined for eth1 and mapped to: TC0 - low priority, TX CPPI queue 0 -> ext Port 1 fifo0, no rate limit TC1 - prio 2, TX CPPI queue 1 -> ext Port 1 fifo1, CIR=100Mbit/s, EIR=1Mbit/s TC2 - prio 3, TX CPPI queue 2 -> ext Port 1 fifo2, CIR=200Mbit/s, EIR=2Mbit/s Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Roger Quadros <rogerq@kernel.org> Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-12-19 12:58:03 +02:00
#define AM65_CPSW_P0_REG_PRI_EIR(pri) (0x160 + 4 * (pri))
#define AM65_CPSW_PN_REG_CTL 0x004
#define AM65_CPSW_PN_REG_TX_PRI_MAP 0x018
#define AM65_CPSW_PN_REG_RX_PRI_MAP 0x020
#define AM65_CPSW_PN_REG_FIFO_STATUS 0x050
#define AM65_CPSW_PN_REG_EST_CTL 0x060
#define AM65_CPSW_PN_REG_PRI_CIR(pri) (0x140 + 4 * (pri))
#define AM65_CPSW_PN_REG_PRI_EIR(pri) (0x160 + 4 * (pri))
/* AM65_CPSW_REG_CTL register fields */
#define AM65_CPSW_CTL_EST_EN BIT(18)
/* AM65_CPSW_PN_REG_CTL register fields */
#define AM65_CPSW_PN_CTL_EST_PORT_EN BIT(17)
/* AM65_CPSW_PN_REG_EST_CTL register fields */
#define AM65_CPSW_PN_EST_ONEBUF BIT(0)
#define AM65_CPSW_PN_EST_BUFSEL BIT(1)
#define AM65_CPSW_PN_EST_TS_EN BIT(2)
#define AM65_CPSW_PN_EST_TS_FIRST BIT(3)
#define AM65_CPSW_PN_EST_ONEPRI BIT(4)
#define AM65_CPSW_PN_EST_TS_PRI_MSK GENMASK(7, 5)
/* AM65_CPSW_PN_REG_FIFO_STATUS register fields */
#define AM65_CPSW_PN_FST_TX_PRI_ACTIVE_MSK GENMASK(7, 0)
#define AM65_CPSW_PN_FST_TX_E_MAC_ALLOW_MSK GENMASK(15, 8)
#define AM65_CPSW_PN_FST_EST_CNT_ERR BIT(16)
#define AM65_CPSW_PN_FST_EST_ADD_ERR BIT(17)
#define AM65_CPSW_PN_FST_EST_BUFACT BIT(18)
/* EST FETCH COMMAND RAM */
#define AM65_CPSW_FETCH_RAM_CMD_NUM 0x80
#define AM65_CPSW_FETCH_CNT_MSK GENMASK(21, 8)
#define AM65_CPSW_FETCH_CNT_MAX (AM65_CPSW_FETCH_CNT_MSK >> 8)
#define AM65_CPSW_FETCH_CNT_OFFSET 8
#define AM65_CPSW_FETCH_ALLOW_MSK GENMASK(7, 0)
#define AM65_CPSW_FETCH_ALLOW_MAX AM65_CPSW_FETCH_ALLOW_MSK
net: ethernet: ti: am65-cpsw: add mqprio qdisc offload in channel mode This patch adds MQPRIO Qdisc offload in full 'channel' mode which allows not only setting up pri:tc mapping, but also configuring TX shapers (rate-limiting) on external port FIFOs. The MQPRIO Qdisc offload is expected to work with or without VLAN/priority tagged packets. The CPSW external Port FIFO has 8 Priority queues. The rate-limit can be set for each of these priority queues. Which Priority queue a packet is assigned to depends on PN_REG_TX_PRI_MAP register which maps header priority to switch priority. The header priority of a packet is assigned via the RX_PRI_MAP_REG which maps packet priority to header priority. The packet priority is either the VLAN priority (for VLAN tagged packets) or the thread/channel offset. For simplicity, we assign the same priority queue to all queues of a Traffic Class so it can be rate-limited correctly. Configuration example: ethtool -L eth1 tx 5 ethtool --set-priv-flags eth1 p0-rx-ptype-rrobin off tc qdisc add dev eth1 parent root handle 100: mqprio num_tc 3 \ map 0 0 1 2 0 0 0 0 0 0 0 0 0 0 0 0 \ queues 1@0 1@1 1@2 hw 1 mode channel \ shaper bw_rlimit min_rate 0 100mbit 200mbit max_rate 0 101mbit 202mbit tc qdisc replace dev eth2 handle 100: parent root mqprio num_tc 1 \ map 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 queues 1@0 hw 1 ip link add link eth1 name eth1.100 type vlan id 100 ip link set eth1.100 type vlan egress 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 In the above example two ports share the same TX CPPI queue 0 for low priority traffic. 3 traffic classes are defined for eth1 and mapped to: TC0 - low priority, TX CPPI queue 0 -> ext Port 1 fifo0, no rate limit TC1 - prio 2, TX CPPI queue 1 -> ext Port 1 fifo1, CIR=100Mbit/s, EIR=1Mbit/s TC2 - prio 3, TX CPPI queue 2 -> ext Port 1 fifo2, CIR=200Mbit/s, EIR=2Mbit/s Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Roger Quadros <rogerq@kernel.org> Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-12-19 12:58:03 +02:00
/* number of priority queues per port FIFO */
#define AM65_CPSW_PN_FIFO_PRIO_NUM 8
#if IS_ENABLED(CONFIG_TI_AM65_CPSW_QOS)
ethernet: ti: am65-cpsw-qos: add TAPRIO offload support AM65 CPSW h/w supports Enhanced Scheduled Traffic (EST – defined in P802.1Qbv/D2.2 that later got included in IEEE 802.1Q-2018) configuration. EST allows express queue traffic to be scheduled (placed) on the wire at specific repeatable time intervals. In Linux kernel, EST configuration is done through tc command and the taprio scheduler in the net core implements a software only scheduler (SCH_TAPRIO). If the NIC is capable of EST configuration, user indicate "flag 2" in the command which is then parsed by taprio scheduler in net core and indicate that the command is to be offloaded to h/w. taprio then offloads the command to the driver by calling ndo_setup_tc() ndo ops. This patch implements ndo_setup_tc() to offload EST configuration to CPSW h/w. Currently driver supports only SetGateStates operation. EST operates on a repeating time interval generated by the CPTS EST function generator. Each Ethernet port has a global EST fetch RAM that can be configured as 2 buffers, each of 64 locations or one large buffer of 128 locations. In 2 buffer configuration, a ping pong mechanism is used to hold the active schedule (oper) in one buffer and new (admin) command in the other. Each 22-bit fetch command consists of a 14-bit fetch count (14 MSB’s) and an 8-bit priority fetch allow (8 LSB’s) that will be applied for the fetch count time in wireside clocks. Driver process each of the sched-entry in the offload command and update the fetch RAM. Driver configures duration in sched-entry into the fetch count and Gate mask into the priority fetch bits of the RAM. Then configures the CPTS EST function generator to activate the schedule. Currently driver supports only 2 buffer configuration which means driver supports a max cycle time of ~8 msec. CPSW supports a configurable number of priority queues (up to 8) and needs to be switched to this mode from the default round robin mode before EST can be offloaded. User configures these through ethtool commands (-L for changing number of queues and --set-priv-flags to disable round robin mode). Driver doesn't enable EST if pf_p0_rx_ptype_rrobin privat flag is set. The flag is common for all ports, and so can't be just overridden by taprio configuration w/o user involvement. Command fails if pf_p0_rx_ptype_rrobin is already set in the driver. Scheds (commands) configuration depends on interface speed so driver translates the duration to the fetch count based on link speed. Each schedule can be constructed with several command entries in fetch RAM depending on interval. For example if each sched has timer interval < ~130us on 1000 Mb link then each sched consumes one command and have 1:1 mapping. When Ethernet link goes down, driver purge the configuration if link is down for more than 1 second. The patch allows to update the timer and scheds memory only if it's really needed, and skip cases required the user to stop timer by configuring only shceds memory. Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> Signed-off-by: Murali Karicheri <m-karicheri2@ti.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-13 09:26:15 -04:00
int am65_cpsw_qos_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
void *type_data);
void am65_cpsw_qos_link_up(struct net_device *ndev, int link_speed);
void am65_cpsw_qos_link_down(struct net_device *ndev);
int am65_cpsw_qos_ndo_tx_p0_set_maxrate(struct net_device *ndev, int queue, u32 rate_mbps);
void am65_cpsw_qos_tx_p0_rate_init(struct am65_cpsw_common *common);
void am65_cpsw_iet_commit_preemptible_tcs(struct am65_cpsw_port *port);
void am65_cpsw_iet_common_enable(struct am65_cpsw_common *common);
#else
static inline int am65_cpsw_qos_ndo_setup_tc(struct net_device *ndev,
enum tc_setup_type type,
void *type_data)
{
return -EOPNOTSUPP;
}
static inline void am65_cpsw_qos_link_up(struct net_device *ndev,
int link_speed)
{ }
static inline void am65_cpsw_qos_link_down(struct net_device *ndev)
{ }
static inline int am65_cpsw_qos_ndo_tx_p0_set_maxrate(struct net_device *ndev,
int queue,
u32 rate_mbps)
{
return 0;
}
static inline void am65_cpsw_qos_tx_p0_rate_init(struct am65_cpsw_common *common)
{ }
static inline void am65_cpsw_iet_commit_preemptible_tcs(struct am65_cpsw_port *port)
{ }
static inline void am65_cpsw_iet_common_enable(struct am65_cpsw_common *common)
{ }
#endif
ethernet: ti: am65-cpsw-qos: add TAPRIO offload support AM65 CPSW h/w supports Enhanced Scheduled Traffic (EST – defined in P802.1Qbv/D2.2 that later got included in IEEE 802.1Q-2018) configuration. EST allows express queue traffic to be scheduled (placed) on the wire at specific repeatable time intervals. In Linux kernel, EST configuration is done through tc command and the taprio scheduler in the net core implements a software only scheduler (SCH_TAPRIO). If the NIC is capable of EST configuration, user indicate "flag 2" in the command which is then parsed by taprio scheduler in net core and indicate that the command is to be offloaded to h/w. taprio then offloads the command to the driver by calling ndo_setup_tc() ndo ops. This patch implements ndo_setup_tc() to offload EST configuration to CPSW h/w. Currently driver supports only SetGateStates operation. EST operates on a repeating time interval generated by the CPTS EST function generator. Each Ethernet port has a global EST fetch RAM that can be configured as 2 buffers, each of 64 locations or one large buffer of 128 locations. In 2 buffer configuration, a ping pong mechanism is used to hold the active schedule (oper) in one buffer and new (admin) command in the other. Each 22-bit fetch command consists of a 14-bit fetch count (14 MSB’s) and an 8-bit priority fetch allow (8 LSB’s) that will be applied for the fetch count time in wireside clocks. Driver process each of the sched-entry in the offload command and update the fetch RAM. Driver configures duration in sched-entry into the fetch count and Gate mask into the priority fetch bits of the RAM. Then configures the CPTS EST function generator to activate the schedule. Currently driver supports only 2 buffer configuration which means driver supports a max cycle time of ~8 msec. CPSW supports a configurable number of priority queues (up to 8) and needs to be switched to this mode from the default round robin mode before EST can be offloaded. User configures these through ethtool commands (-L for changing number of queues and --set-priv-flags to disable round robin mode). Driver doesn't enable EST if pf_p0_rx_ptype_rrobin privat flag is set. The flag is common for all ports, and so can't be just overridden by taprio configuration w/o user involvement. Command fails if pf_p0_rx_ptype_rrobin is already set in the driver. Scheds (commands) configuration depends on interface speed so driver translates the duration to the fetch count based on link speed. Each schedule can be constructed with several command entries in fetch RAM depending on interval. For example if each sched has timer interval < ~130us on 1000 Mb link then each sched consumes one command and have 1:1 mapping. When Ethernet link goes down, driver purge the configuration if link is down for more than 1 second. The patch allows to update the timer and scheds memory only if it's really needed, and skip cases required the user to stop timer by configuring only shceds memory. Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> Signed-off-by: Murali Karicheri <m-karicheri2@ti.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-13 09:26:15 -04:00
#define AM65_CPSW_REG_CTL 0x004
#define AM65_CPSW_PN_REG_CTL 0x004
#define AM65_CPSW_PN_REG_MAX_BLKS 0x008
#define AM65_CPSW_PN_REG_TX_PRI_MAP 0x018
#define AM65_CPSW_PN_REG_RX_PRI_MAP 0x020
#define AM65_CPSW_PN_REG_IET_CTRL 0x040
#define AM65_CPSW_PN_REG_IET_STATUS 0x044
#define AM65_CPSW_PN_REG_IET_VERIFY 0x048
#define AM65_CPSW_PN_REG_FIFO_STATUS 0x050
#define AM65_CPSW_PN_REG_EST_CTL 0x060
#define AM65_CPSW_PN_REG_PRI_CIR(pri) (0x140 + 4 * (pri))
#define AM65_CPSW_PN_REG_PRI_EIR(pri) (0x160 + 4 * (pri))
/* AM65_CPSW_REG_CTL register fields */
#define AM65_CPSW_CTL_IET_EN BIT(17)
#define AM65_CPSW_CTL_EST_EN BIT(18)
/* AM65_CPSW_PN_REG_CTL register fields */
#define AM65_CPSW_PN_CTL_IET_PORT_EN BIT(16)
#define AM65_CPSW_PN_CTL_EST_PORT_EN BIT(17)
/* AM65_CPSW_PN_REG_EST_CTL register fields */
#define AM65_CPSW_PN_EST_ONEBUF BIT(0)
#define AM65_CPSW_PN_EST_BUFSEL BIT(1)
#define AM65_CPSW_PN_EST_TS_EN BIT(2)
#define AM65_CPSW_PN_EST_TS_FIRST BIT(3)
#define AM65_CPSW_PN_EST_ONEPRI BIT(4)
#define AM65_CPSW_PN_EST_TS_PRI_MSK GENMASK(7, 5)
/* AM65_CPSW_PN_REG_IET_CTRL register fields */
#define AM65_CPSW_PN_IET_MAC_PENABLE BIT(0)
#define AM65_CPSW_PN_IET_MAC_DISABLEVERIFY BIT(2)
#define AM65_CPSW_PN_IET_MAC_LINKFAIL BIT(3)
#define AM65_CPSW_PN_IET_MAC_MAC_ADDFRAGSIZE_MASK GENMASK(10, 8)
#define AM65_CPSW_PN_IET_MAC_MAC_ADDFRAGSIZE_OFFSET 8
#define AM65_CPSW_PN_IET_MAC_PREMPT_MASK GENMASK(23, 16)
#define AM65_CPSW_PN_IET_MAC_PREMPT_OFFSET 16
#define AM65_CPSW_PN_IET_MAC_SET_ADDFRAGSIZE(n) (((n) << AM65_CPSW_PN_IET_MAC_MAC_ADDFRAGSIZE_OFFSET) & \
AM65_CPSW_PN_IET_MAC_MAC_ADDFRAGSIZE_MASK)
#define AM65_CPSW_PN_IET_MAC_GET_ADDFRAGSIZE(n) (((n) & AM65_CPSW_PN_IET_MAC_MAC_ADDFRAGSIZE_MASK) >> \
AM65_CPSW_PN_IET_MAC_MAC_ADDFRAGSIZE_OFFSET)
#define AM65_CPSW_PN_IET_MAC_SET_PREEMPT(n) (((n) << AM65_CPSW_PN_IET_MAC_PREMPT_OFFSET) & \
AM65_CPSW_PN_IET_MAC_PREMPT_MASK)
#define AM65_CPSW_PN_IET_MAC_GET_PREEMPT(n) (((n) & AM65_CPSW_PN_IET_MAC_PREMPT_MASK) >> \
AM65_CPSW_PN_IET_MAC_PREMPT_OFFSET)
/* AM65_CPSW_PN_REG_IET_STATUS register fields */
#define AM65_CPSW_PN_MAC_STATUS GENMASK(3, 0)
#define AM65_CPSW_PN_MAC_VERIFIED BIT(0)
#define AM65_CPSW_PN_MAC_VERIFY_FAIL BIT(1)
#define AM65_CPSW_PN_MAC_RESPOND_ERR BIT(2)
#define AM65_CPSW_PN_MAC_VERIFY_ERR BIT(3)
/* AM65_CPSW_PN_REG_IET_VERIFY register fields */
#define AM65_CPSW_PN_MAC_VERIFY_CNT_MASK GENMASK(23, 0)
#define AM65_CPSW_PN_MAC_GET_VERIFY_CNT(n) ((n) & AM65_CPSW_PN_MAC_VERIFY_CNT_MASK)
/* 10 msec converted to NSEC */
#define AM65_CPSW_IET_VERIFY_CNT_MS (10)
#define AM65_CPSW_IET_VERIFY_CNT_NS (AM65_CPSW_IET_VERIFY_CNT_MS * \
NSEC_PER_MSEC)
/* AM65_CPSW_PN_REG_FIFO_STATUS register fields */
#define AM65_CPSW_PN_FST_TX_PRI_ACTIVE_MSK GENMASK(7, 0)
#define AM65_CPSW_PN_FST_TX_E_MAC_ALLOW_MSK GENMASK(15, 8)
#define AM65_CPSW_PN_FST_EST_CNT_ERR BIT(16)
#define AM65_CPSW_PN_FST_EST_ADD_ERR BIT(17)
#define AM65_CPSW_PN_FST_EST_BUFACT BIT(18)
/* EST FETCH COMMAND RAM */
#define AM65_CPSW_FETCH_RAM_CMD_NUM 0x80
#define AM65_CPSW_FETCH_CNT_MSK GENMASK(21, 8)
#define AM65_CPSW_FETCH_CNT_MAX (AM65_CPSW_FETCH_CNT_MSK >> 8)
#define AM65_CPSW_FETCH_CNT_OFFSET 8
#define AM65_CPSW_FETCH_ALLOW_MSK GENMASK(7, 0)
#define AM65_CPSW_FETCH_ALLOW_MAX AM65_CPSW_FETCH_ALLOW_MSK
/* AM65_CPSW_PN_REG_MAX_BLKS fields for IET and No IET cases */
/* 7 blocks for pn_rx_max_blks, 13 for pn_tx_max_blks*/
#define AM65_CPSW_PN_TX_RX_MAX_BLKS_IET 0xD07
/* Slave IET Stats. register offsets */
#define AM65_CPSW_STATN_IET_RX_ASSEMBLY_ERROR 0x140
#define AM65_CPSW_STATN_IET_RX_ASSEMBLY_OK 0x144
#define AM65_CPSW_STATN_IET_RX_SMD_ERROR 0x148
#define AM65_CPSW_STATN_IET_RX_FRAG 0x14c
#define AM65_CPSW_STATN_IET_TX_HOLD 0x150
#define AM65_CPSW_STATN_IET_TX_FRAG 0x154
/* number of priority queues per port FIFO */
#define AM65_CPSW_PN_FIFO_PRIO_NUM 8
ethernet: ti: am65-cpsw-qos: add TAPRIO offload support AM65 CPSW h/w supports Enhanced Scheduled Traffic (EST – defined in P802.1Qbv/D2.2 that later got included in IEEE 802.1Q-2018) configuration. EST allows express queue traffic to be scheduled (placed) on the wire at specific repeatable time intervals. In Linux kernel, EST configuration is done through tc command and the taprio scheduler in the net core implements a software only scheduler (SCH_TAPRIO). If the NIC is capable of EST configuration, user indicate "flag 2" in the command which is then parsed by taprio scheduler in net core and indicate that the command is to be offloaded to h/w. taprio then offloads the command to the driver by calling ndo_setup_tc() ndo ops. This patch implements ndo_setup_tc() to offload EST configuration to CPSW h/w. Currently driver supports only SetGateStates operation. EST operates on a repeating time interval generated by the CPTS EST function generator. Each Ethernet port has a global EST fetch RAM that can be configured as 2 buffers, each of 64 locations or one large buffer of 128 locations. In 2 buffer configuration, a ping pong mechanism is used to hold the active schedule (oper) in one buffer and new (admin) command in the other. Each 22-bit fetch command consists of a 14-bit fetch count (14 MSB’s) and an 8-bit priority fetch allow (8 LSB’s) that will be applied for the fetch count time in wireside clocks. Driver process each of the sched-entry in the offload command and update the fetch RAM. Driver configures duration in sched-entry into the fetch count and Gate mask into the priority fetch bits of the RAM. Then configures the CPTS EST function generator to activate the schedule. Currently driver supports only 2 buffer configuration which means driver supports a max cycle time of ~8 msec. CPSW supports a configurable number of priority queues (up to 8) and needs to be switched to this mode from the default round robin mode before EST can be offloaded. User configures these through ethtool commands (-L for changing number of queues and --set-priv-flags to disable round robin mode). Driver doesn't enable EST if pf_p0_rx_ptype_rrobin privat flag is set. The flag is common for all ports, and so can't be just overridden by taprio configuration w/o user involvement. Command fails if pf_p0_rx_ptype_rrobin is already set in the driver. Scheds (commands) configuration depends on interface speed so driver translates the duration to the fetch count based on link speed. Each schedule can be constructed with several command entries in fetch RAM depending on interval. For example if each sched has timer interval < ~130us on 1000 Mb link then each sched consumes one command and have 1:1 mapping. When Ethernet link goes down, driver purge the configuration if link is down for more than 1 second. The patch allows to update the timer and scheds memory only if it's really needed, and skip cases required the user to stop timer by configuring only shceds memory. Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org> Signed-off-by: Murali Karicheri <m-karicheri2@ti.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-13 09:26:15 -04:00
#endif /* AM65_CPSW_QOS_H_ */