summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--drivers/net/ethernet/intel/igb/e1000_defines.h23
-rw-r--r--drivers/net/ethernet/intel/igb/e1000_regs.h8
-rw-r--r--drivers/net/ethernet/intel/igb/igb.h6
-rw-r--r--drivers/net/ethernet/intel/igb/igb_main.c347
-rw-r--r--include/linux/netdevice.h1
-rw-r--r--include/net/pkt_sched.h9
-rw-r--r--include/uapi/linux/pkt_sched.h19
-rw-r--r--net/sched/Kconfig11
-rw-r--r--net/sched/Makefile1
-rw-r--r--net/sched/sch_cbs.c373
-rw-r--r--net/sched/sch_generic.c8
-rw-r--r--net/sched/sch_mq.c10
-rw-r--r--net/sched/sch_mqprio.c7
13 files changed, 813 insertions, 10 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,
};
/**
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 6c7960c8338a..5e02f79b2110 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -776,6 +776,7 @@ enum tc_setup_type {
TC_SETUP_CLSMATCHALL,
TC_SETUP_CLSBPF,
TC_SETUP_BLOCK,
+ TC_SETUP_CBS,
};
/* These structures hold the attributes of xdp state that are being passed
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index b8ecafce4ba1..02f2db26e30c 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -140,4 +140,13 @@ static inline struct net *qdisc_net(struct Qdisc *q)
return dev_net(q->dev_queue->dev);
}
+struct tc_cbs_qopt_offload {
+ u8 enable;
+ s32 queue;
+ s32 hicredit;
+ s32 locredit;
+ s32 idleslope;
+ s32 sendslope;
+};
+
#endif
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index e7cc3d3c7421..0e88cc262ca0 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -904,4 +904,23 @@ struct tc_pie_xstats {
__u32 maxq; /* maximum queue size */
__u32 ecn_mark; /* packets marked with ecn*/
};
+
+/* CBS */
+struct tc_cbs_qopt {
+ __u8 offload;
+ __u8 _pad[3];
+ __s32 hicredit;
+ __s32 locredit;
+ __s32 idleslope;
+ __s32 sendslope;
+};
+
+enum {
+ TCA_CBS_UNSPEC,
+ TCA_CBS_PARMS,
+ __TCA_CBS_MAX,
+};
+
+#define TCA_CBS_MAX (__TCA_CBS_MAX - 1)
+
#endif
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index e70ed26485a2..c03d86a7775e 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -172,6 +172,17 @@ config NET_SCH_TBF
To compile this code as a module, choose M here: the
module will be called sch_tbf.
+config NET_SCH_CBS
+ tristate "Credit Based Shaper (CBS)"
+ ---help---
+ Say Y here if you want to use the Credit Based Shaper (CBS) packet
+ scheduling algorithm.
+
+ See the top of <file:net/sched/sch_cbs.c> for more details.
+
+ To compile this code as a module, choose M here: the
+ module will be called sch_cbs.
+
config NET_SCH_GRED
tristate "Generic Random Early Detection (GRED)"
---help---
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 7b915d226de7..80c8f92d162d 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -52,6 +52,7 @@ obj-$(CONFIG_NET_SCH_FQ_CODEL) += sch_fq_codel.o
obj-$(CONFIG_NET_SCH_FQ) += sch_fq.o
obj-$(CONFIG_NET_SCH_HHF) += sch_hhf.o
obj-$(CONFIG_NET_SCH_PIE) += sch_pie.o
+obj-$(CONFIG_NET_SCH_CBS) += sch_cbs.o
obj-$(CONFIG_NET_CLS_U32) += cls_u32.o
obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o
diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
new file mode 100644
index 000000000000..bdb533b7fb8c
--- /dev/null
+++ b/net/sched/sch_cbs.c
@@ -0,0 +1,373 @@
+/*
+ * net/sched/sch_cbs.c Credit Based Shaper
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Vinicius Costa Gomes <vinicius.gomes@intel.com>
+ *
+ */
+
+/* Credit Based Shaper (CBS)
+ * =========================
+ *
+ * This is a simple rate-limiting shaper aimed at TSN applications on
+ * systems with known traffic workloads.
+ *
+ * Its algorithm is defined by the IEEE 802.1Q-2014 Specification,
+ * Section 8.6.8.2, and explained in more detail in the Annex L of the
+ * same specification.
+ *
+ * There are four tunables to be considered:
+ *
+ * 'idleslope': Idleslope is the rate of credits that is
+ * accumulated (in kilobits per second) when there is at least
+ * one packet waiting for transmission. Packets are transmitted
+ * when the current value of credits is equal or greater than
+ * zero. When there is no packet to be transmitted the amount of
+ * credits is set to zero. This is the main tunable of the CBS
+ * algorithm.
+ *
+ * 'sendslope':
+ * Sendslope is the rate of credits that is depleted (it should be a
+ * negative number of kilobits per second) when a transmission is
+ * ocurring. It can be calculated as follows, (IEEE 802.1Q-2014 Section
+ * 8.6.8.2 item g):
+ *
+ * sendslope = idleslope - port_transmit_rate
+ *
+ * 'hicredit': Hicredit defines the maximum amount of credits (in
+ * bytes) that can be accumulated. Hicredit depends on the
+ * characteristics of interfering traffic,
+ * 'max_interference_size' is the maximum size of any burst of
+ * traffic that can delay the transmission of a frame that is
+ * available for transmission for this traffic class, (IEEE
+ * 802.1Q-2014 Annex L, Equation L-3):
+ *
+ * hicredit = max_interference_size * (idleslope / port_transmit_rate)
+ *
+ * 'locredit': Locredit is the minimum amount of credits that can
+ * be reached. It is a function of the traffic flowing through
+ * this qdisc (IEEE 802.1Q-2014 Annex L, Equation L-2):
+ *
+ * locredit = max_frame_size * (sendslope / port_transmit_rate)
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <net/netlink.h>
+#include <net/sch_generic.h>
+#include <net/pkt_sched.h>
+
+#define BYTES_PER_KBIT (1000LL / 8)
+
+struct cbs_sched_data {
+ bool offload;
+ int queue;
+ s64 port_rate; /* in bytes/s */
+ s64 last; /* timestamp in ns */
+ s64 credits; /* in bytes */
+ s32 locredit; /* in bytes */
+ s32 hicredit; /* in bytes */
+ s64 sendslope; /* in bytes/s */
+ s64 idleslope; /* in bytes/s */
+ struct qdisc_watchdog watchdog;
+ int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch);
+ struct sk_buff *(*dequeue)(struct Qdisc *sch);
+};
+
+static int cbs_enqueue_offload(struct sk_buff *skb, struct Qdisc *sch)
+{
+ return qdisc_enqueue_tail(skb, sch);
+}
+
+static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch)
+{
+ struct cbs_sched_data *q = qdisc_priv(sch);
+
+ if (sch->q.qlen == 0 && q->credits > 0) {
+ /* We need to stop accumulating credits when there's
+ * no enqueued packets and q->credits is positive.
+ */
+ q->credits = 0;
+ q->last = ktime_get_ns();
+ }
+
+ return qdisc_enqueue_tail(skb, sch);
+}
+
+static int cbs_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+ struct sk_buff **to_free)
+{
+ struct cbs_sched_data *q = qdisc_priv(sch);
+
+ return q->enqueue(skb, sch);
+}
+
+/* timediff is in ns, slope is in bytes/s */
+static s64 timediff_to_credits(s64 timediff, s64 slope)
+{
+ return div64_s64(timediff * slope, NSEC_PER_SEC);
+}
+
+static s64 delay_from_credits(s64 credits, s64 slope)
+{
+ if (unlikely(slope == 0))
+ return S64_MAX;
+
+ return div64_s64(-credits * NSEC_PER_SEC, slope);
+}
+
+static s64 credits_from_len(unsigned int len, s64 slope, s64 port_rate)
+{
+ if (unlikely(port_rate == 0))
+ return S64_MAX;
+
+ return div64_s64(len * slope, port_rate);
+}
+
+static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch)
+{
+ struct cbs_sched_data *q = qdisc_priv(sch);
+ s64 now = ktime_get_ns();
+ struct sk_buff *skb;
+ s64 credits;
+ int len;
+
+ if (q->credits < 0) {
+ credits = timediff_to_credits(now - q->last, q->idleslope);
+
+ credits = q->credits + credits;
+ q->credits = min_t(s64, credits, q->hicredit);
+
+ if (q->credits < 0) {
+ s64 delay;
+
+ delay = delay_from_credits(q->credits, q->idleslope);
+ qdisc_watchdog_schedule_ns(&q->watchdog, now + delay);
+
+ q->last = now;
+
+ return NULL;
+ }
+ }
+
+ skb = qdisc_dequeue_head(sch);
+ if (!skb)
+ return NULL;
+
+ len = qdisc_pkt_len(skb);
+
+ /* As sendslope is a negative number, this will decrease the
+ * amount of q->credits.
+ */
+ credits = credits_from_len(len, q->sendslope, q->port_rate);
+ credits += q->credits;
+
+ q->credits = max_t(s64, credits, q->locredit);
+ q->last = now;
+
+ return skb;
+}
+
+static struct sk_buff *cbs_dequeue_offload(struct Qdisc *sch)
+{
+ return qdisc_dequeue_head(sch);
+}
+
+static struct sk_buff *cbs_dequeue(struct Qdisc *sch)
+{
+ struct cbs_sched_data *q = qdisc_priv(sch);
+
+ return q->dequeue(sch);
+}
+
+static const struct nla_policy cbs_policy[TCA_CBS_MAX + 1] = {
+ [TCA_CBS_PARMS] = { .len = sizeof(struct tc_cbs_qopt) },
+};
+
+static void cbs_disable_offload(struct net_device *dev,
+ struct cbs_sched_data *q)
+{
+ struct tc_cbs_qopt_offload cbs = { };
+ const struct net_device_ops *ops;
+ int err;
+
+ if (!q->offload)
+ return;
+
+ q->enqueue = cbs_enqueue_soft;
+ q->dequeue = cbs_dequeue_soft;
+
+ ops = dev->netdev_ops;
+ if (!ops->ndo_setup_tc)
+ return;
+
+ cbs.queue = q->queue;
+ cbs.enable = 0;
+
+ err = ops->ndo_setup_tc(dev, TC_SETUP_CBS, &cbs);
+ if (err < 0)
+ pr_warn("Couldn't disable CBS offload for queue %d\n",
+ cbs.queue);
+}
+
+static int cbs_enable_offload(struct net_device *dev, struct cbs_sched_data *q,
+ const struct tc_cbs_qopt *opt)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+ struct tc_cbs_qopt_offload cbs = { };
+ int err;
+
+ if (!ops->ndo_setup_tc)
+ return -EOPNOTSUPP;
+
+ cbs.queue = q->queue;
+
+ cbs.enable = 1;
+ cbs.hicredit = opt->hicredit;
+ cbs.locredit = opt->locredit;
+ cbs.idleslope = opt->idleslope;
+ cbs.sendslope = opt->sendslope;
+
+ err = ops->ndo_setup_tc(dev, TC_SETUP_CBS, &cbs);
+ if (err < 0)
+ return err;
+
+ q->enqueue = cbs_enqueue_offload;
+ q->dequeue = cbs_dequeue_offload;
+
+ return 0;
+}
+
+static int cbs_change(struct Qdisc *sch, struct nlattr *opt)
+{
+ struct cbs_sched_data *q = qdisc_priv(sch);
+ struct net_device *dev = qdisc_dev(sch);
+ struct nlattr *tb[TCA_CBS_MAX + 1];
+ struct tc_cbs_qopt *qopt;
+ int err;
+
+ err = nla_parse_nested(tb, TCA_CBS_MAX, opt, cbs_policy, NULL);
+ if (err < 0)
+ return err;
+
+ if (!tb[TCA_CBS_PARMS])
+ return -EINVAL;
+
+ qopt = nla_data(tb[TCA_CBS_PARMS]);
+
+ if (!qopt->offload) {
+ struct ethtool_link_ksettings ecmd;
+ s64 link_speed;
+
+ if (!__ethtool_get_link_ksettings(dev, &ecmd))
+ link_speed = ecmd.base.speed;
+ else
+ link_speed = SPEED_1000;
+
+ q->port_rate = link_speed * 1000 * BYTES_PER_KBIT;
+
+ cbs_disable_offload(dev, q);
+ } else {
+ err = cbs_enable_offload(dev, q, qopt);
+ if (err < 0)
+ return err;
+ }
+
+ /* Everything went OK, save the parameters used. */
+ q->hicredit = qopt->hicredit;
+ q->locredit = qopt->locredit;
+ q->idleslope = qopt->idleslope * BYTES_PER_KBIT;
+ q->sendslope = qopt->sendslope * BYTES_PER_KBIT;
+ q->offload = qopt->offload;
+
+ return 0;
+}
+
+static int cbs_init(struct Qdisc *sch, struct nlattr *opt)
+{
+ struct cbs_sched_data *q = qdisc_priv(sch);
+ struct net_device *dev = qdisc_dev(sch);
+
+ if (!opt)
+ return -EINVAL;
+
+ q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0);
+
+ q->enqueue = cbs_enqueue_soft;
+ q->dequeue = cbs_dequeue_soft;
+
+ qdisc_watchdog_init(&q->watchdog, sch);
+
+ return cbs_change(sch, opt);
+}
+
+static void cbs_destroy(struct Qdisc *sch)
+{
+ struct cbs_sched_data *q = qdisc_priv(sch);
+ struct net_device *dev = qdisc_dev(sch);
+
+ qdisc_watchdog_cancel(&q->watchdog);
+
+ cbs_disable_offload(dev, q);
+}
+
+static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+ struct cbs_sched_data *q = qdisc_priv(sch);
+ struct tc_cbs_qopt opt = { };
+ struct nlattr *nest;
+
+ nest = nla_nest_start(skb, TCA_OPTIONS);
+ if (!nest)
+ goto nla_put_failure;
+
+ opt.hicredit = q->hicredit;
+ opt.locredit = q->locredit;
+ opt.sendslope = div64_s64(q->sendslope, BYTES_PER_KBIT);
+ opt.idleslope = div64_s64(q->idleslope, BYTES_PER_KBIT);
+ opt.offload = q->offload;
+
+ if (nla_put(skb, TCA_CBS_PARMS, sizeof(opt), &opt))
+ goto nla_put_failure;
+
+ return nla_nest_end(skb, nest);
+
+nla_put_failure:
+ nla_nest_cancel(skb, nest);
+ return -1;
+}
+
+static struct Qdisc_ops cbs_qdisc_ops __read_mostly = {
+ .id = "cbs",
+ .priv_size = sizeof(struct cbs_sched_data),
+ .enqueue = cbs_enqueue,
+ .dequeue = cbs_dequeue,
+ .peek = qdisc_peek_dequeued,
+ .init = cbs_init,
+ .reset = qdisc_reset_queue,
+ .destroy = cbs_destroy,
+ .change = cbs_change,
+ .dump = cbs_dump,
+ .owner = THIS_MODULE,
+};
+
+static int __init cbs_module_init(void)
+{
+ return register_qdisc(&cbs_qdisc_ops);
+}
+
+static void __exit cbs_module_exit(void)
+{
+ unregister_qdisc(&cbs_qdisc_ops);
+}
+module_init(cbs_module_init)
+module_exit(cbs_module_exit)
+MODULE_LICENSE("GPL");
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 6ced7c89c141..aa74aa42b5d7 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -603,8 +603,14 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
struct Qdisc *sch;
unsigned int size = QDISC_ALIGN(sizeof(*sch)) + ops->priv_size;
int err = -ENOBUFS;
- struct net_device *dev = dev_queue->dev;
+ struct net_device *dev;
+
+ if (!dev_queue) {
+ err = -EINVAL;
+ goto errout;
+ }
+ dev = dev_queue->dev;
p = kzalloc_node(size, GFP_KERNEL,
netdev_queue_numa_node_read(dev_queue));
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index f3a3e507422b..213b586a06a0 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -130,15 +130,7 @@ static struct netdev_queue *mq_queue_get(struct Qdisc *sch, unsigned long cl)
static struct netdev_queue *mq_select_queue(struct Qdisc *sch,
struct tcmsg *tcm)
{
- unsigned int ntx = TC_H_MIN(tcm->tcm_parent);
- struct netdev_queue *dev_queue = mq_queue_get(sch, ntx);
-
- if (!dev_queue) {
- struct net_device *dev = qdisc_dev(sch);
-
- return netdev_get_tx_queue(dev, 0);
- }
- return dev_queue;
+ return mq_queue_get(sch, TC_H_MIN(tcm->tcm_parent));
}
static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 51c2b289c69b..4d5ed45123f0 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -575,6 +575,12 @@ static void mqprio_walk(struct Qdisc *sch, struct qdisc_walker *arg)
}
}
+static struct netdev_queue *mqprio_select_queue(struct Qdisc *sch,
+ struct tcmsg *tcm)
+{
+ return mqprio_queue_get(sch, TC_H_MIN(tcm->tcm_parent));
+}
+
static const struct Qdisc_class_ops mqprio_class_ops = {
.graft = mqprio_graft,
.leaf = mqprio_leaf,
@@ -582,6 +588,7 @@ static const struct Qdisc_class_ops mqprio_class_ops = {
.walk = mqprio_walk,
.dump = mqprio_dump_class,
.dump_stats = mqprio_dump_class_stats,
+ .select_queue = mqprio_select_queue,
};
static struct Qdisc_ops mqprio_qdisc_ops __read_mostly = {
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-21 23:11:07 +0000