[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20180612101856.GA29936@apalos>
Date: Tue, 12 Jun 2018 13:18:56 +0300
From: Ilias Apalodimas <ilias.apalodimas@...aro.org>
To: Ivan Khoronzhuk <ivan.khoronzhuk@...aro.org>
Cc: grygorii.strashko@...com, davem@...emloft.net, corbet@....net,
akpm@...ux-foundation.org, netdev@...r.kernel.org,
linux-doc@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-omap@...r.kernel.org, vinicius.gomes@...el.com,
henrik@...tad.us, jesus.sanchez-palencia@...el.com, p-varis@...com,
spatton@...com, francois.ozog@...aro.org, yogeshs@...com,
nsekhar@...com
Subject: Re: [PATCH net-next 4/6] net: ethernet: ti: cpsw: add CBS Qdisc
offload
On Mon, Jun 11, 2018 at 04:30:45PM +0300, Ivan Khoronzhuk wrote:
> The cpsw has up to 4 FIFOs per port and upper 3 FIFOs can feed rate
> limited queue with shaping. In order to set and enable shaping for
> those 3 FIFOs queues the network device with CBS qdisc attached is
> needed. The CBS configuration is added for dual-emac/single port mode
> only, but potentially can be used in switch mode also, based on
> switchdev for instance.
>
> Despite the FIFO shapers can work w/o cpdma level shapers the base
> usage must be in combine with cpdma level shapers as described in TRM,
> that are set as maximum rates for interface queues with sysfs.
>
> One of the possible configuration with txq shapers and CBS shapers:
>
> Configured with echo RATE >
> /sys/class/net/eth0/queues/tx-0/tx_maxrate
> /---------------------------------------------------
> /
> / cpdma level shapers
> +----+ +----+ +----+ +----+ +----+ +----+ +----+ +----+
> | c7 | | c6 | | c5 | | c4 | | c3 | | c2 | | c1 | | c0 |
> \ / \ / \ / \ / \ / \ / \ / \ /
> \ / \ / \ / \ / \ / \ / \ / \ /
> \/ \/ \/ \/ \/ \/ \/ \/
> +---------|------|------|------|-------------------------------------+
> | +----+ | | +---+ |
> | | +----+ | | |
> | v v v v |
> | +----+ +----+ +----+ +----+ p p+----+ +----+ +----+ +----+ |
> | | | | | | | | | o o| | | | | | | | |
> | | f3 | | f2 | | f1 | | f0 | r CPSW r| f3 | | f2 | | f1 | | f0 | |
> | | | | | | | | | t t| | | | | | | | |
> | \ / \ / \ / \ / 0 1\ / \ / \ / \ / |
> | \ X \ / \ / \ / \ / \ / \ / \ / |
> | \/ \ \/ \/ \/ \/ \/ \/ \/ |
> +-------\------------------------------------------------------------+
> \
> \ FIFO shaper, set with CBS offload added in this patch,
> \ FIFO0 cannot be rate limited
> ------------------------------------------------------
>
> CBS shaper configuration is supposed to be used with root MQPRIO Qdisc
> offload allowing to add sk_prio->tc->txq maps that direct traffic to
> appropriate tx queue and maps L2 priority to FIFO shaper.
>
> The CBS shaper is intended to be used for AVB where L2 priority
> (pcp field) is used to differentiate class of traffic. So additionally
> vlan needs to be created with appropriate egress sk_prio->l2 prio map.
>
> If CBS has several tx queues assigned to it, the sum of their
> bandwidth has not overlap bandwidth set for CBS. It's recomended the
> CBS bandwidth to be a little bit more.
>
> The CBS shaper is configured with CBS qdisc offload interface using tc
> tool from iproute2 packet.
>
> For instance:
>
> $ tc qdisc replace dev eth0 handle 100: parent root mqprio num_tc 3 \
> map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@1 2@2 hw 1
>
> $ tc -g class show dev eth0
> +---(100:ffe2) mqprio
> | +---(100:3) mqprio
> | +---(100:4) mqprio
> |
> +---(100:ffe1) mqprio
> | +---(100:2) mqprio
> |
> +---(100:ffe0) mqprio
> +---(100:1) mqprio
>
> $ tc qdisc add dev eth0 parent 100:1 cbs locredit -1440 \
> hicredit 60 sendslope -960000 idleslope 40000 offload 1
>
> $ tc qdisc add dev eth0 parent 100:2 cbs locredit -1470 \
> hicredit 62 sendslope -980000 idleslope 20000 offload 1
>
> The above code set CBS shapers for tc0 and tc1, for that txq0 and
> txq1 is used. Pay attention, the real set bandwidth can differ a bit
> due to discreteness of configuration parameters.
>
> Here parameters like locredit, hicredit and sendslope are ignored
> internally and are supposed to be set with assumption that maximum
> frame size for frame - 1500.
>
> It's supposed that interface speed is not changed while reconnection,
> not always is true, so inform user in case speed of interface was
> changed, as it can impact on dependent shapers configuration.
>
> For more examples see Documentation.
>
> Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@...aro.org>
> ---
> drivers/net/ethernet/ti/cpsw.c | 221 +++++++++++++++++++++++++++++++++
> 1 file changed, 221 insertions(+)
>
> diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
> index fd967d2bce5d..87a5586c5ea5 100644
> --- a/drivers/net/ethernet/ti/cpsw.c
> +++ b/drivers/net/ethernet/ti/cpsw.c
> @@ -46,6 +46,8 @@
> #include "cpts.h"
> #include "davinci_cpdma.h"
>
> +#include <net/pkt_sched.h>
> +
> #define CPSW_DEBUG (NETIF_MSG_HW | NETIF_MSG_WOL | \
> NETIF_MSG_DRV | NETIF_MSG_LINK | \
> NETIF_MSG_IFUP | NETIF_MSG_INTR | \
> @@ -154,8 +156,12 @@ do { \
> #define IRQ_NUM 2
> #define CPSW_MAX_QUEUES 8
> #define CPSW_CPDMA_DESCS_POOL_SIZE_DEFAULT 256
> +#define CPSW_FIFO_QUEUE_TYPE_SHIFT 16
> +#define CPSW_FIFO_SHAPE_EN_SHIFT 16
> +#define CPSW_FIFO_RATE_EN_SHIFT 20
> #define CPSW_TC_NUM 4
> #define CPSW_FIFO_SHAPERS_NUM (CPSW_TC_NUM - 1)
> +#define CPSW_PCT_MASK 0x7f
>
> #define CPSW_RX_VLAN_ENCAP_HDR_PRIO_SHIFT 29
> #define CPSW_RX_VLAN_ENCAP_HDR_PRIO_MSK GENMASK(2, 0)
> @@ -457,6 +463,8 @@ struct cpsw_priv {
> bool rx_pause;
> bool tx_pause;
> bool mqprio_hw;
> + int fifo_bw[CPSW_TC_NUM];
> + int shp_cfg_speed;
> u32 emac_port;
> struct cpsw_common *cpsw;
> };
> @@ -1081,6 +1089,38 @@ static void cpsw_set_slave_mac(struct cpsw_slave *slave,
> slave_write(slave, mac_lo(priv->mac_addr), SA_LO);
> }
>
> +static bool cpsw_shp_is_off(struct cpsw_priv *priv)
> +{
> + struct cpsw_common *cpsw = priv->cpsw;
> + struct cpsw_slave *slave;
> + u32 shift, mask, val;
> +
> + val = readl_relaxed(&cpsw->regs->ptype);
> +
> + slave = &cpsw->slaves[cpsw_slave_index(cpsw, priv)];
> + shift = CPSW_FIFO_SHAPE_EN_SHIFT + 3 * slave->slave_num;
> + mask = 7 << shift;
> + val = val & mask;
> +
> + return !val;
> +}
> +
> +static void cpsw_fifo_shp_on(struct cpsw_priv *priv, int fifo, int on)
> +{
> + struct cpsw_common *cpsw = priv->cpsw;
> + struct cpsw_slave *slave;
> + u32 shift, mask, val;
> +
> + val = readl_relaxed(&cpsw->regs->ptype);
> +
> + slave = &cpsw->slaves[cpsw_slave_index(cpsw, priv)];
> + shift = CPSW_FIFO_SHAPE_EN_SHIFT + 3 * slave->slave_num;
> + mask = (1 << --fifo) << shift;
> + val = on ? val | mask : val & ~mask;
> +
> + writel_relaxed(val, &cpsw->regs->ptype);
> +}
> +
> static void _cpsw_adjust_link(struct cpsw_slave *slave,
> struct cpsw_priv *priv, bool *link)
> {
> @@ -1120,6 +1160,12 @@ static void _cpsw_adjust_link(struct cpsw_slave *slave,
> mac_control |= BIT(4);
>
> *link = true;
> +
> + if (priv->shp_cfg_speed &&
> + priv->shp_cfg_speed != slave->phy->speed &&
> + !cpsw_shp_is_off(priv))
> + dev_warn(priv->dev,
> + "Speed was changed, CBS sahper speeds are changed!");
> } else {
> mac_control = 0;
> /* disable forwarding */
> @@ -1589,6 +1635,178 @@ static int cpsw_tc_to_fifo(int tc, int num_tc)
> return CPSW_FIFO_SHAPERS_NUM - tc;
> }
>
> +static int cpsw_set_fifo_bw(struct cpsw_priv *priv, int fifo, int bw)
> +{
> + struct cpsw_common *cpsw = priv->cpsw;
> + u32 val = 0, send_pct, shift;
> + struct cpsw_slave *slave;
> + int pct = 0, i;
> +
> + if (bw > priv->shp_cfg_speed * 1000)
> + goto err;
> +
> + /* shaping has to stay enabled for highest fifos linearly
> + * and fifo bw no more then interface can allow
> + */
> + slave = &cpsw->slaves[cpsw_slave_index(cpsw, priv)];
> + send_pct = slave_read(slave, SEND_PERCENT);
> + for (i = CPSW_FIFO_SHAPERS_NUM; i > 0; i--) {
> + if (!bw) {
> + if (i >= fifo || !priv->fifo_bw[i])
> + continue;
> +
> + dev_warn(priv->dev, "Prev FIFO%d is shaped", i);
> + continue;
> + }
> +
> + if (!priv->fifo_bw[i] && i > fifo) {
> + dev_err(priv->dev, "Upper FIFO%d is not shaped", i);
> + return -EINVAL;
> + }
> +
> + shift = (i - 1) * 8;
> + if (i == fifo) {
> + send_pct &= ~(CPSW_PCT_MASK << shift);
> + val = DIV_ROUND_UP(bw, priv->shp_cfg_speed * 10);
> + if (!val)
> + val = 1;
> +
> + send_pct |= val << shift;
> + pct += val;
> + continue;
> + }
> +
> + if (priv->fifo_bw[i])
> + pct += (send_pct >> shift) & CPSW_PCT_MASK;
> + }
> +
> + if (pct >= 100)
> + goto err;
> +
> + slave_write(slave, send_pct, SEND_PERCENT);
> + priv->fifo_bw[fifo] = bw;
> +
> + dev_warn(priv->dev, "set FIFO%d bw = %d\n", fifo,
> + DIV_ROUND_CLOSEST(val * priv->shp_cfg_speed, 100));
> +
> + return 0;
> +err:
> + dev_err(priv->dev, "Bandwidth doesn't fit in tc configuration");
> + return -EINVAL;
> +}
> +
> +static int cpsw_set_fifo_rlimit(struct cpsw_priv *priv, int fifo, int bw)
> +{
> + struct cpsw_common *cpsw = priv->cpsw;
> + struct cpsw_slave *slave;
> + u32 tx_in_ctl_rg, val;
> + int ret;
> +
> + ret = cpsw_set_fifo_bw(priv, fifo, bw);
> + if (ret)
> + return ret;
> +
> + slave = &cpsw->slaves[cpsw_slave_index(cpsw, priv)];
> + tx_in_ctl_rg = cpsw->version == CPSW_VERSION_1 ?
> + CPSW1_TX_IN_CTL : CPSW2_TX_IN_CTL;
> +
> + if (!bw)
> + cpsw_fifo_shp_on(priv, fifo, bw);
> +
> + val = slave_read(slave, tx_in_ctl_rg);
> + if (cpsw_shp_is_off(priv)) {
> + /* disable FIFOs rate limited queues */
> + val &= ~(0xf << CPSW_FIFO_RATE_EN_SHIFT);
> +
> + /* set type of FIFO queues to normal priority mode */
> + val &= ~(3 << CPSW_FIFO_QUEUE_TYPE_SHIFT);
> +
> + /* set type of FIFO queues to be rate limited */
> + if (bw)
> + val |= 2 << CPSW_FIFO_QUEUE_TYPE_SHIFT;
> + else
> + priv->shp_cfg_speed = 0;
> + }
> +
> + /* toggle a FIFO rate limited queue */
> + if (bw)
> + val |= BIT(fifo + CPSW_FIFO_RATE_EN_SHIFT);
> + else
> + val &= ~BIT(fifo + CPSW_FIFO_RATE_EN_SHIFT);
> + slave_write(slave, val, tx_in_ctl_rg);
> +
> + /* FIFO transmit shape enable */
> + cpsw_fifo_shp_on(priv, fifo, bw);
> + return 0;
> +}
> +
> +/* Defaults:
> + * class A - prio 3
> + * class B - prio 2
> + * shaping for class A should be set first
> + */
> +static int cpsw_set_cbs(struct net_device *ndev,
> + struct tc_cbs_qopt_offload *qopt)
> +{
> + struct cpsw_priv *priv = netdev_priv(ndev);
> + struct cpsw_common *cpsw = priv->cpsw;
> + struct cpsw_slave *slave;
> + int prev_speed = 0;
> + int tc, ret, fifo;
> + u32 bw = 0;
> +
> + tc = netdev_txq_to_tc(priv->ndev, qopt->queue);
> +
> + /* enable channels in backward order, as highest FIFOs must be rate
> + * limited first and for compliance with CPDMA rate limited channels
> + * that also used in bacward order. FIFO0 cannot be rate limited.
> + */
> + fifo = cpsw_tc_to_fifo(tc, ndev->num_tc);
> + if (!fifo) {
> + dev_err(priv->dev, "Last tc%d can't be rate limited", tc);
> + return -EINVAL;
> + }
> +
> + /* do nothing, it's disabled anyway */
> + if (!qopt->enable && !priv->fifo_bw[fifo])
> + return 0;
> +
> + /* shapers can be set if link speed is known */
> + slave = &cpsw->slaves[cpsw_slave_index(cpsw, priv)];
> + if (slave->phy && slave->phy->link) {
> + if (priv->shp_cfg_speed &&
> + priv->shp_cfg_speed != slave->phy->speed)
> + prev_speed = priv->shp_cfg_speed;
> +
> + priv->shp_cfg_speed = slave->phy->speed;
> + }
> +
> + if (!priv->shp_cfg_speed) {
> + dev_err(priv->dev, "Link speed is not known");
> + return -1;
> + }
> +
> + ret = pm_runtime_get_sync(cpsw->dev);
> + if (ret < 0) {
> + pm_runtime_put_noidle(cpsw->dev);
> + return ret;
> + }
> +
> + bw = qopt->enable ? qopt->idleslope : 0;
> + ret = cpsw_set_fifo_rlimit(priv, fifo, bw);
> + if (ret) {
> + priv->shp_cfg_speed = prev_speed;
> + prev_speed = 0;
> + }
> +
> + if (bw && prev_speed)
> + dev_warn(priv->dev,
> + "Speed was changed, CBS sahper speeds are changed!");
> +
> + pm_runtime_put_sync(cpsw->dev);
> + return ret;
> +}
> +
> static int cpsw_ndo_open(struct net_device *ndev)
> {
> struct cpsw_priv *priv = netdev_priv(ndev);
> @@ -2263,6 +2481,9 @@ static int cpsw_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
> void *type_data)
> {
> switch (type) {
> + case TC_SETUP_QDISC_CBS:
> + return cpsw_set_cbs(ndev, type_data);
> +
> case TC_SETUP_QDISC_MQPRIO:
> return cpsw_set_tc(ndev, type_data);
>
> --
> 2.17.1
>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@...aro.org>
Powered by blists - more mailing lists