[dpdk-dev] [PATCH v4 44/58] net/txgbe: add flow control support

[Jiawen Wu <jiawenwu@trustnetic.com>]

Add flow control support.

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
---
 doc/guides/nics/features/txgbe.ini  |   1 +
 doc/guides/nics/txgbe.rst           |   1 +
 drivers/net/txgbe/base/txgbe_hw.c   | 425 ++++++++++++++++++++++++++++
 drivers/net/txgbe/base/txgbe_hw.h   |   6 +
 drivers/net/txgbe/base/txgbe_type.h |  22 ++
 drivers/net/txgbe/txgbe_ethdev.c    | 122 +++++++-
 drivers/net/txgbe/txgbe_ethdev.h    |   7 +
 7 files changed, 583 insertions(+), 1 deletion(-)

diff --git a/doc/guides/nics/features/txgbe.ini b/doc/guides/nics/features/txgbe.ini
index 6cbc3a65a..f69785787 100644
--- a/doc/guides/nics/features/txgbe.ini
+++ b/doc/guides/nics/features/txgbe.ini
@@ -22,6 +22,7 @@ VMDq                 = Y
 SR-IOV               = Y
 DCB                  = Y
 VLAN filter          = Y
+Flow control         = Y
 Rate limitation      = Y
 CRC offload          = P
 VLAN offload         = P
diff --git a/doc/guides/nics/txgbe.rst b/doc/guides/nics/txgbe.rst
index 54aebee78..95919478b 100644
--- a/doc/guides/nics/txgbe.rst
+++ b/doc/guides/nics/txgbe.rst
@@ -20,6 +20,7 @@ Features
 - Port hardware statistics
 - Jumbo frames
 - Link state information
+- Link flow control
 - Interrupt mode for RX
 - Scattered and gather for TX and RX
 - DCB
diff --git a/drivers/net/txgbe/base/txgbe_hw.c b/drivers/net/txgbe/base/txgbe_hw.c
index e4c6c2d64..7a6c30999 100644
--- a/drivers/net/txgbe/base/txgbe_hw.c
+++ b/drivers/net/txgbe/base/txgbe_hw.c
@@ -25,6 +25,211 @@ static s32 txgbe_mta_vector(struct txgbe_hw *hw, u8 *mc_addr);
 static s32 txgbe_get_san_mac_addr_offset(struct txgbe_hw *hw,
 					 u16 *san_mac_offset);
 
+/**
+ * txgbe_device_supports_autoneg_fc - Check if device supports autonegotiation
+ * of flow control
+ * @hw: pointer to hardware structure
+ *
+ * This function returns true if the device supports flow control
+ * autonegotiation, and false if it does not.
+ *
+ **/
+bool txgbe_device_supports_autoneg_fc(struct txgbe_hw *hw)
+{
+	bool supported = false;
+	u32 speed;
+	bool link_up;
+
+	DEBUGFUNC("txgbe_device_supports_autoneg_fc");
+
+	switch (hw->phy.media_type) {
+	case txgbe_media_type_fiber_qsfp:
+	case txgbe_media_type_fiber:
+		hw->mac.check_link(hw, &speed, &link_up, false);
+		/* if link is down, assume supported */
+		if (link_up)
+			supported = speed == TXGBE_LINK_SPEED_1GB_FULL ?
+			true : false;
+		else
+			supported = true;
+
+		break;
+	case txgbe_media_type_backplane:
+		supported = true;
+		break;
+	case txgbe_media_type_copper:
+		/* only some copper devices support flow control autoneg */
+		switch (hw->device_id) {
+		case TXGBE_DEV_ID_RAPTOR_XAUI:
+		case TXGBE_DEV_ID_RAPTOR_SGMII:
+			supported = true;
+			break;
+		default:
+			supported = false;
+		}
+	default:
+		break;
+	}
+
+	if (!supported)
+		DEBUGOUT("Device %x does not support flow control autoneg",
+			      hw->device_id);
+	return supported;
+}
+
+/**
+ *  txgbe_setup_fc - Set up flow control
+ *  @hw: pointer to hardware structure
+ *
+ *  Called at init time to set up flow control.
+ **/
+s32 txgbe_setup_fc(struct txgbe_hw *hw)
+{
+	s32 err = 0;
+	u32 reg = 0;
+	u16 reg_cu = 0;
+	u32 value = 0;
+	u64 reg_bp = 0;
+	bool locked = false;
+
+	DEBUGFUNC("txgbe_setup_fc");
+
+	/* Validate the requested mode */
+	if (hw->fc.strict_ieee && hw->fc.requested_mode == txgbe_fc_rx_pause) {
+		DEBUGOUT("txgbe_fc_rx_pause not valid in strict IEEE mode\n");
+		err = TXGBE_ERR_INVALID_LINK_SETTINGS;
+		goto out;
+	}
+
+	/*
+	 * 10gig parts do not have a word in the EEPROM to determine the
+	 * default flow control setting, so we explicitly set it to full.
+	 */
+	if (hw->fc.requested_mode == txgbe_fc_default)
+		hw->fc.requested_mode = txgbe_fc_full;
+
+	/*
+	 * Set up the 1G and 10G flow control advertisement registers so the
+	 * HW will be able to do fc autoneg once the cable is plugged in.  If
+	 * we link at 10G, the 1G advertisement is harmless and vice versa.
+	 */
+	switch (hw->phy.media_type) {
+	case txgbe_media_type_backplane:
+		/* some MAC's need RMW protection on AUTOC */
+		err = hw->mac.prot_autoc_read(hw, &locked, &reg_bp);
+		if (err != 0)
+			goto out;
+
+		/* fall through - only backplane uses autoc */
+	case txgbe_media_type_fiber_qsfp:
+	case txgbe_media_type_fiber:
+	case txgbe_media_type_copper:
+		hw->phy.read_reg(hw, TXGBE_MD_AUTO_NEG_ADVT,
+				     TXGBE_MD_DEV_AUTO_NEG, &reg_cu);
+		break;
+	default:
+		break;
+	}
+
+	/*
+	 * The possible values of fc.requested_mode are:
+	 * 0: Flow control is completely disabled
+	 * 1: Rx flow control is enabled (we can receive pause frames,
+	 *    but not send pause frames).
+	 * 2: Tx flow control is enabled (we can send pause frames but
+	 *    we do not support receiving pause frames).
+	 * 3: Both Rx and Tx flow control (symmetric) are enabled.
+	 * other: Invalid.
+	 */
+	switch (hw->fc.requested_mode) {
+	case txgbe_fc_none:
+		/* Flow control completely disabled by software override. */
+		reg &= ~(SR_MII_MMD_AN_ADV_PAUSE_SYM |
+			SR_MII_MMD_AN_ADV_PAUSE_ASM);
+		if (hw->phy.media_type == txgbe_media_type_backplane)
+			reg_bp &= ~(TXGBE_AUTOC_SYM_PAUSE |
+				    TXGBE_AUTOC_ASM_PAUSE);
+		else if (hw->phy.media_type == txgbe_media_type_copper)
+			reg_cu &= ~(TXGBE_TAF_SYM_PAUSE | TXGBE_TAF_ASM_PAUSE);
+		break;
+	case txgbe_fc_tx_pause:
+		/*
+		 * Tx Flow control is enabled, and Rx Flow control is
+		 * disabled by software override.
+		 */
+		reg |= SR_MII_MMD_AN_ADV_PAUSE_ASM;
+		reg &= ~SR_MII_MMD_AN_ADV_PAUSE_SYM;
+		if (hw->phy.media_type == txgbe_media_type_backplane) {
+			reg_bp |= TXGBE_AUTOC_ASM_PAUSE;
+			reg_bp &= ~TXGBE_AUTOC_SYM_PAUSE;
+		} else if (hw->phy.media_type == txgbe_media_type_copper) {
+			reg_cu |= TXGBE_TAF_ASM_PAUSE;
+			reg_cu &= ~TXGBE_TAF_SYM_PAUSE;
+		}
+		reg |= SR_MII_MMD_AN_ADV_PAUSE_ASM;
+		reg_bp |= SR_AN_MMD_ADV_REG1_PAUSE_ASM;
+		break;
+	case txgbe_fc_rx_pause:
+		/*
+		 * Rx Flow control is enabled and Tx Flow control is
+		 * disabled by software override. Since there really
+		 * isn't a way to advertise that we are capable of RX
+		 * Pause ONLY, we will advertise that we support both
+		 * symmetric and asymmetric Rx PAUSE, as such we fall
+		 * through to the fc_full statement.  Later, we will
+		 * disable the adapter's ability to send PAUSE frames.
+		 */
+	case txgbe_fc_full:
+		/* Flow control (both Rx and Tx) is enabled by SW override. */
+		reg |= SR_MII_MMD_AN_ADV_PAUSE_SYM |
+			SR_MII_MMD_AN_ADV_PAUSE_ASM;
+		if (hw->phy.media_type == txgbe_media_type_backplane)
+			reg_bp |= TXGBE_AUTOC_SYM_PAUSE |
+				  TXGBE_AUTOC_ASM_PAUSE;
+		else if (hw->phy.media_type == txgbe_media_type_copper)
+			reg_cu |= TXGBE_TAF_SYM_PAUSE | TXGBE_TAF_ASM_PAUSE;
+		reg |= SR_MII_MMD_AN_ADV_PAUSE_SYM |
+			SR_MII_MMD_AN_ADV_PAUSE_ASM;
+		reg_bp |= SR_AN_MMD_ADV_REG1_PAUSE_SYM |
+			SR_AN_MMD_ADV_REG1_PAUSE_ASM;
+		break;
+	default:
+		DEBUGOUT("Flow control param set incorrectly\n");
+		err = TXGBE_ERR_CONFIG;
+		goto out;
+	}
+
+	/*
+	 * Enable auto-negotiation between the MAC & PHY;
+	 * the MAC will advertise clause 37 flow control.
+	 */
+	value = rd32_epcs(hw, SR_MII_MMD_AN_ADV);
+	value = (value & ~(SR_MII_MMD_AN_ADV_PAUSE_ASM |
+		SR_MII_MMD_AN_ADV_PAUSE_SYM)) | reg;
+	wr32_epcs(hw, SR_MII_MMD_AN_ADV, value);
+
+	/*
+	 * AUTOC restart handles negotiation of 1G and 10G on backplane
+	 * and copper. There is no need to set the PCS1GCTL register.
+	 *
+	 */
+	if (hw->phy.media_type == txgbe_media_type_backplane) {
+		value = rd32_epcs(hw, SR_AN_MMD_ADV_REG1);
+		value = (value & ~(SR_AN_MMD_ADV_REG1_PAUSE_ASM |
+			SR_AN_MMD_ADV_REG1_PAUSE_SYM)) |
+			reg_bp;
+		wr32_epcs(hw, SR_AN_MMD_ADV_REG1, value);
+	} else if ((hw->phy.media_type == txgbe_media_type_copper) &&
+		    (txgbe_device_supports_autoneg_fc(hw))) {
+		hw->phy.write_reg(hw, TXGBE_MD_AUTO_NEG_ADVT,
+				      TXGBE_MD_DEV_AUTO_NEG, reg_cu);
+	}
+
+	DEBUGOUT("Set up FC; reg = 0x%08X\n", reg);
+out:
+	return err;
+}
+
 /**
  *  txgbe_start_hw - Prepare hardware for Tx/Rx
  *  @hw: pointer to hardware structure
@@ -36,6 +241,7 @@ static s32 txgbe_get_san_mac_addr_offset(struct txgbe_hw *hw,
  **/
 s32 txgbe_start_hw(struct txgbe_hw *hw)
 {
+	s32 err;
 	u16 device_caps;
 
 	DEBUGFUNC("txgbe_start_hw");
@@ -49,6 +255,13 @@ s32 txgbe_start_hw(struct txgbe_hw *hw)
 	/* Clear statistics registers */
 	hw->mac.clear_hw_cntrs(hw);
 
+	/* Setup flow control */
+	err = txgbe_setup_fc(hw);
+	if (err != 0 && err != TXGBE_NOT_IMPLEMENTED) {
+		DEBUGOUT("Flow control setup failed, returning %d\n", err);
+		return err;
+	}
+
 	/* Cache bit indicating need for crosstalk fix */
 	switch (hw->mac.type) {
 	case txgbe_mac_raptor:
@@ -673,6 +886,136 @@ s32 txgbe_update_mc_addr_list(struct txgbe_hw *hw, u8 *mc_addr_list,
 	return 0;
 }
 
+/**
+ *  txgbe_fc_enable - Enable flow control
+ *  @hw: pointer to hardware structure
+ *
+ *  Enable flow control according to the current settings.
+ **/
+s32 txgbe_fc_enable(struct txgbe_hw *hw)
+{
+	s32 err = 0;
+	u32 mflcn_reg, fccfg_reg;
+	u32 pause_time;
+	u32 fcrtl, fcrth;
+	int i;
+
+	DEBUGFUNC("txgbe_fc_enable");
+
+	/* Validate the water mark configuration */
+	if (!hw->fc.pause_time) {
+		err = TXGBE_ERR_INVALID_LINK_SETTINGS;
+		goto out;
+	}
+
+	/* Low water mark of zero causes XOFF floods */
+	for (i = 0; i < TXGBE_DCB_TC_MAX; i++) {
+		if ((hw->fc.current_mode & txgbe_fc_tx_pause) &&
+		    hw->fc.high_water[i]) {
+			if (!hw->fc.low_water[i] ||
+			    hw->fc.low_water[i] >= hw->fc.high_water[i]) {
+				DEBUGOUT("Invalid water mark configuration\n");
+				err = TXGBE_ERR_INVALID_LINK_SETTINGS;
+				goto out;
+			}
+		}
+	}
+
+	/* Negotiate the fc mode to use */
+	hw->mac.fc_autoneg(hw);
+
+	/* Disable any previous flow control settings */
+	mflcn_reg = rd32(hw, TXGBE_RXFCCFG);
+	mflcn_reg &= ~(TXGBE_RXFCCFG_FC | TXGBE_RXFCCFG_PFC);
+
+	fccfg_reg = rd32(hw, TXGBE_TXFCCFG);
+	fccfg_reg &= ~(TXGBE_TXFCCFG_FC | TXGBE_TXFCCFG_PFC);
+
+	/*
+	 * The possible values of fc.current_mode are:
+	 * 0: Flow control is completely disabled
+	 * 1: Rx flow control is enabled (we can receive pause frames,
+	 *    but not send pause frames).
+	 * 2: Tx flow control is enabled (we can send pause frames but
+	 *    we do not support receiving pause frames).
+	 * 3: Both Rx and Tx flow control (symmetric) are enabled.
+	 * other: Invalid.
+	 */
+	switch (hw->fc.current_mode) {
+	case txgbe_fc_none:
+		/*
+		 * Flow control is disabled by software override or autoneg.
+		 * The code below will actually disable it in the HW.
+		 */
+		break;
+	case txgbe_fc_rx_pause:
+		/*
+		 * Rx Flow control is enabled and Tx Flow control is
+		 * disabled by software override. Since there really
+		 * isn't a way to advertise that we are capable of RX
+		 * Pause ONLY, we will advertise that we support both
+		 * symmetric and asymmetric Rx PAUSE.  Later, we will
+		 * disable the adapter's ability to send PAUSE frames.
+		 */
+		mflcn_reg |= TXGBE_RXFCCFG_FC;
+		break;
+	case txgbe_fc_tx_pause:
+		/*
+		 * Tx Flow control is enabled, and Rx Flow control is
+		 * disabled by software override.
+		 */
+		fccfg_reg |= TXGBE_TXFCCFG_FC;
+		break;
+	case txgbe_fc_full:
+		/* Flow control (both Rx and Tx) is enabled by SW override. */
+		mflcn_reg |= TXGBE_RXFCCFG_FC;
+		fccfg_reg |= TXGBE_TXFCCFG_FC;
+		break;
+	default:
+		DEBUGOUT("Flow control param set incorrectly\n");
+		err = TXGBE_ERR_CONFIG;
+		goto out;
+	}
+
+	/* Set 802.3x based flow control settings. */
+	wr32(hw, TXGBE_RXFCCFG, mflcn_reg);
+	wr32(hw, TXGBE_TXFCCFG, fccfg_reg);
+
+	/* Set up and enable Rx high/low water mark thresholds, enable XON. */
+	for (i = 0; i < TXGBE_DCB_TC_MAX; i++) {
+		if ((hw->fc.current_mode & txgbe_fc_tx_pause) &&
+		    hw->fc.high_water[i]) {
+			fcrtl = TXGBE_FCWTRLO_TH(hw->fc.low_water[i]) |
+				TXGBE_FCWTRLO_XON;
+			fcrth = TXGBE_FCWTRHI_TH(hw->fc.high_water[i]) |
+				TXGBE_FCWTRHI_XOFF;
+		} else {
+			/*
+			 * In order to prevent Tx hangs when the internal Tx
+			 * switch is enabled we must set the high water mark
+			 * to the Rx packet buffer size - 24KB.  This allows
+			 * the Tx switch to function even under heavy Rx
+			 * workloads.
+			 */
+			fcrtl = 0;
+			fcrth = rd32(hw, TXGBE_PBRXSIZE(i)) - 24576;
+		}
+		wr32(hw, TXGBE_FCWTRLO(i), fcrtl);
+		wr32(hw, TXGBE_FCWTRHI(i), fcrth);
+	}
+
+	/* Configure pause time (2 TCs per register) */
+	pause_time = TXGBE_RXFCFSH_TIME(hw->fc.pause_time);
+	for (i = 0; i < (TXGBE_DCB_TC_MAX / 2); i++)
+		wr32(hw, TXGBE_FCXOFFTM(i), pause_time * 0x00010001);
+
+	/* Configure flow control refresh threshold value */
+	wr32(hw, TXGBE_RXFCRFSH, hw->fc.pause_time / 2);
+
+out:
+	return err;
+}
+
 /**
  *  txgbe_acquire_swfw_sync - Acquire SWFW semaphore
  *  @hw: pointer to hardware structure
@@ -2090,6 +2433,82 @@ s32 txgbe_setup_sfp_modules(struct txgbe_hw *hw)
 	return err;
 }
 
+/**
+ *  txgbe_prot_autoc_read_raptor - Hides MAC differences needed for AUTOC read
+ *  @hw: pointer to hardware structure
+ *  @locked: Return the if we locked for this read.
+ *  @value: Value we read from AUTOC
+ *
+ *  For this part we need to wrap read-modify-writes with a possible
+ *  FW/SW lock.  It is assumed this lock will be freed with the next
+ *  prot_autoc_write_raptor().
+ */
+s32 txgbe_prot_autoc_read_raptor(struct txgbe_hw *hw, bool *locked, u64 *value)
+{
+	s32 err;
+	bool lock_state = false;
+
+	 /* If LESM is on then we need to hold the SW/FW semaphore. */
+	if (txgbe_verify_lesm_fw_enabled_raptor(hw)) {
+		err = hw->mac.acquire_swfw_sync(hw,
+					TXGBE_MNGSEM_SWPHY);
+		if (err != 0)
+			return TXGBE_ERR_SWFW_SYNC;
+
+		lock_state = true;
+	}
+
+	if (locked)
+		*locked = lock_state;
+
+	*value = txgbe_autoc_read(hw);
+	return 0;
+}
+
+/**
+ * txgbe_prot_autoc_write_raptor - Hides MAC differences needed for AUTOC write
+ * @hw: pointer to hardware structure
+ * @autoc: value to write to AUTOC
+ * @locked: bool to indicate whether the SW/FW lock was already taken by
+ *           previous prot_autoc_read_raptor.
+ *
+ * This part may need to hold the SW/FW lock around all writes to
+ * AUTOC. Likewise after a write we need to do a pipeline reset.
+ */
+s32 txgbe_prot_autoc_write_raptor(struct txgbe_hw *hw, bool locked, u64 autoc)
+{
+	int err = 0;
+
+	/* Blocked by MNG FW so bail */
+	if (txgbe_check_reset_blocked(hw))
+		goto out;
+
+	/* We only need to get the lock if:
+	 *  - We didn't do it already (in the read part of a read-modify-write)
+	 *  - LESM is enabled.
+	 */
+	if (!locked && txgbe_verify_lesm_fw_enabled_raptor(hw)) {
+		err = hw->mac.acquire_swfw_sync(hw,
+					TXGBE_MNGSEM_SWPHY);
+		if (err != 0)
+			return TXGBE_ERR_SWFW_SYNC;
+
+		locked = true;
+	}
+
+	txgbe_autoc_write(hw, autoc);
+	err = txgbe_reset_pipeline_raptor(hw);
+
+out:
+	/* Free the SW/FW semaphore as we either grabbed it here or
+	 * already had it when this function was called.
+	 */
+	if (locked)
+		hw->mac.release_swfw_sync(hw, TXGBE_MNGSEM_SWPHY);
+
+	return err;
+}
+
 /**
  *  txgbe_init_ops_pf - Inits func ptrs and MAC type
  *  @hw: pointer to hardware structure
@@ -2147,6 +2566,8 @@ s32 txgbe_init_ops_pf(struct txgbe_hw *hw)
 	mac->get_wwn_prefix = txgbe_get_wwn_prefix;
 	mac->autoc_read = txgbe_autoc_read;
 	mac->autoc_write = txgbe_autoc_write;
+	mac->prot_autoc_read = txgbe_prot_autoc_read_raptor;
+	mac->prot_autoc_write = txgbe_prot_autoc_write_raptor;
 
 	/* RAR, Multicast, VLAN */
 	mac->set_rar = txgbe_set_rar;
@@ -2164,6 +2585,10 @@ s32 txgbe_init_ops_pf(struct txgbe_hw *hw)
 	mac->set_mac_anti_spoofing = txgbe_set_mac_anti_spoofing;
 	mac->set_ethertype_anti_spoofing = txgbe_set_ethertype_anti_spoofing;
 
+	/* Flow Control */
+	mac->fc_enable = txgbe_fc_enable;
+	mac->setup_fc = txgbe_setup_fc;
+
 	/* Link */
 	mac->get_link_capabilities = txgbe_get_link_capabilities_raptor;
 	mac->check_link = txgbe_check_mac_link;
diff --git a/drivers/net/txgbe/base/txgbe_hw.h b/drivers/net/txgbe/base/txgbe_hw.h
index ffc2ae1d6..1e1cbb2eb 100644
--- a/drivers/net/txgbe/base/txgbe_hw.h
+++ b/drivers/net/txgbe/base/txgbe_hw.h
@@ -28,6 +28,10 @@ s32 txgbe_enable_sec_rx_path(struct txgbe_hw *hw);
 s32 txgbe_disable_sec_tx_path(struct txgbe_hw *hw);
 s32 txgbe_enable_sec_tx_path(struct txgbe_hw *hw);
 
+s32 txgbe_fc_enable(struct txgbe_hw *hw);
+bool txgbe_device_supports_autoneg_fc(struct txgbe_hw *hw);
+s32 txgbe_setup_fc(struct txgbe_hw *hw);
+
 s32 txgbe_validate_mac_addr(u8 *mac_addr);
 s32 txgbe_acquire_swfw_sync(struct txgbe_hw *hw, u32 mask);
 void txgbe_release_swfw_sync(struct txgbe_hw *hw, u32 mask);
@@ -96,5 +100,7 @@ s32 txgbe_reset_hw(struct txgbe_hw *hw);
 s32 txgbe_start_hw_raptor(struct txgbe_hw *hw);
 s32 txgbe_init_phy_raptor(struct txgbe_hw *hw);
 s32 txgbe_enable_rx_dma_raptor(struct txgbe_hw *hw, u32 regval);
+s32 txgbe_prot_autoc_read_raptor(struct txgbe_hw *hw, bool *locked, u64 *value);
+s32 txgbe_prot_autoc_write_raptor(struct txgbe_hw *hw, bool locked, u64 value);
 bool txgbe_verify_lesm_fw_enabled_raptor(struct txgbe_hw *hw);
 #endif /* _TXGBE_HW_H_ */
diff --git a/drivers/net/txgbe/base/txgbe_type.h b/drivers/net/txgbe/base/txgbe_type.h
index 34994bb3b..d851648de 100644
--- a/drivers/net/txgbe/base/txgbe_type.h
+++ b/drivers/net/txgbe/base/txgbe_type.h
@@ -153,6 +153,14 @@ enum txgbe_media_type {
 	txgbe_media_type_virtual
 };
 
+/* Flow Control Settings */
+enum txgbe_fc_mode {
+	txgbe_fc_none = 0,
+	txgbe_fc_rx_pause,
+	txgbe_fc_tx_pause,
+	txgbe_fc_full,
+	txgbe_fc_default
+};
 
 /* Smart Speed Settings */
 #define TXGBE_SMARTSPEED_MAX_RETRIES	3
@@ -222,6 +230,19 @@ struct txgbe_bus_info {
 	u16 instance_id;
 };
 
+/* Flow control parameters */
+struct txgbe_fc_info {
+	u32 high_water[TXGBE_DCB_TC_MAX]; /* Flow Ctrl High-water */
+	u32 low_water[TXGBE_DCB_TC_MAX]; /* Flow Ctrl Low-water */
+	u16 pause_time; /* Flow Control Pause timer */
+	bool send_xon; /* Flow control send XON */
+	bool strict_ieee; /* Strict IEEE mode */
+	bool disable_fc_autoneg; /* Do not autonegotiate FC */
+	bool fc_was_autonegged; /* Is current_mode the result of autonegging? */
+	enum txgbe_fc_mode current_mode; /* FC mode in effect */
+	enum txgbe_fc_mode requested_mode; /* FC mode requested by caller */
+};
+
 /* Statistics counters collected by the MAC */
 /* PB[] RxTx */
 struct txgbe_pb_stats {
@@ -633,6 +654,7 @@ struct txgbe_hw {
 	void *back;
 	struct txgbe_mac_info mac;
 	struct txgbe_addr_filter_info addr_ctrl;
+	struct txgbe_fc_info fc;
 	struct txgbe_phy_info phy;
 	struct txgbe_link_info link;
 	struct txgbe_rom_info rom;
diff --git a/drivers/net/txgbe/txgbe_ethdev.c b/drivers/net/txgbe/txgbe_ethdev.c
index fa98f05b5..a2cc7f715 100644
--- a/drivers/net/txgbe/txgbe_ethdev.c
+++ b/drivers/net/txgbe/txgbe_ethdev.c
@@ -404,11 +404,12 @@ eth_txgbe_dev_init(struct rte_eth_dev *eth_dev, void *init_params __rte_unused)
 	struct txgbe_vfta *shadow_vfta = TXGBE_DEV_VFTA(eth_dev);
 	struct txgbe_hwstrip *hwstrip = TXGBE_DEV_HWSTRIP(eth_dev);
 	struct txgbe_dcb_config *dcb_config = TXGBE_DEV_DCB_CONFIG(eth_dev);
+	struct txgbe_bw_conf *bw_conf = TXGBE_DEV_BW_CONF(eth_dev);
 	struct rte_intr_handle *intr_handle = &pci_dev->intr_handle;
 	const struct rte_memzone *mz;
 	uint32_t ctrl_ext;
 	uint16_t csum;
-	int err;
+	int err, i;
 
 	PMD_INIT_FUNC_TRACE();
 
@@ -473,6 +474,16 @@ eth_txgbe_dev_init(struct rte_eth_dev *eth_dev, void *init_params __rte_unused)
 	memset(dcb_config, 0, sizeof(struct txgbe_dcb_config));
 	txgbe_dcb_init(hw, dcb_config);
 
+	/* Get Hardware Flow Control setting */
+	hw->fc.requested_mode = txgbe_fc_full;
+	hw->fc.current_mode = txgbe_fc_full;
+	hw->fc.pause_time = TXGBE_FC_PAUSE_TIME;
+	for (i = 0; i < TXGBE_DCB_TC_MAX; i++) {
+		hw->fc.low_water[i] = TXGBE_FC_XON_LOTH;
+		hw->fc.high_water[i] = TXGBE_FC_XOFF_HITH;
+	}
+	hw->fc.send_xon = 1;
+
 	err = hw->rom.init_params(hw);
 	if (err != 0) {
 		PMD_INIT_LOG(ERR, "The EEPROM init failed: %d", err);
@@ -590,6 +601,9 @@ eth_txgbe_dev_init(struct rte_eth_dev *eth_dev, void *init_params __rte_unused)
 	/* enable support intr */
 	txgbe_enable_intr(eth_dev);
 
+	/* initialize bandwidth configuration info */
+	memset(bw_conf, 0, sizeof(struct txgbe_bw_conf));
+
 	return 0;
 }
 
@@ -2682,6 +2696,110 @@ txgbe_dev_interrupt_handler(void *param)
 	txgbe_dev_interrupt_action(dev, dev->intr_handle);
 }
 
+static int
+txgbe_flow_ctrl_get(struct rte_eth_dev *dev, struct rte_eth_fc_conf *fc_conf)
+{
+	struct txgbe_hw *hw;
+	uint32_t mflcn_reg;
+	uint32_t fccfg_reg;
+	int rx_pause;
+	int tx_pause;
+
+	hw = TXGBE_DEV_HW(dev);
+
+	fc_conf->pause_time = hw->fc.pause_time;
+	fc_conf->high_water = hw->fc.high_water[0];
+	fc_conf->low_water = hw->fc.low_water[0];
+	fc_conf->send_xon = hw->fc.send_xon;
+	fc_conf->autoneg = !hw->fc.disable_fc_autoneg;
+
+	/*
+	 * Return rx_pause status according to actual setting of
+	 * RXFCCFG register.
+	 */
+	mflcn_reg = rd32(hw, TXGBE_RXFCCFG);
+	if (mflcn_reg & (TXGBE_RXFCCFG_FC | TXGBE_RXFCCFG_PFC))
+		rx_pause = 1;
+	else
+		rx_pause = 0;
+
+	/*
+	 * Return tx_pause status according to actual setting of
+	 * TXFCCFG register.
+	 */
+	fccfg_reg = rd32(hw, TXGBE_TXFCCFG);
+	if (fccfg_reg & (TXGBE_TXFCCFG_FC | TXGBE_TXFCCFG_PFC))
+		tx_pause = 1;
+	else
+		tx_pause = 0;
+
+	if (rx_pause && tx_pause)
+		fc_conf->mode = RTE_FC_FULL;
+	else if (rx_pause)
+		fc_conf->mode = RTE_FC_RX_PAUSE;
+	else if (tx_pause)
+		fc_conf->mode = RTE_FC_TX_PAUSE;
+	else
+		fc_conf->mode = RTE_FC_NONE;
+
+	return 0;
+}
+
+static int
+txgbe_flow_ctrl_set(struct rte_eth_dev *dev, struct rte_eth_fc_conf *fc_conf)
+{
+	struct txgbe_hw *hw;
+	int err;
+	uint32_t rx_buf_size;
+	uint32_t max_high_water;
+	enum txgbe_fc_mode rte_fcmode_2_txgbe_fcmode[] = {
+		txgbe_fc_none,
+		txgbe_fc_rx_pause,
+		txgbe_fc_tx_pause,
+		txgbe_fc_full
+	};
+
+	PMD_INIT_FUNC_TRACE();
+
+	hw = TXGBE_DEV_HW(dev);
+	rx_buf_size = rd32(hw, TXGBE_PBRXSIZE(0));
+	PMD_INIT_LOG(DEBUG, "Rx packet buffer size = 0x%x", rx_buf_size);
+
+	/*
+	 * At least reserve one Ethernet frame for watermark
+	 * high_water/low_water in kilo bytes for txgbe
+	 */
+	max_high_water = (rx_buf_size - RTE_ETHER_MAX_LEN) >> 10;
+	if (fc_conf->high_water > max_high_water ||
+	    fc_conf->high_water < fc_conf->low_water) {
+		PMD_INIT_LOG(ERR, "Invalid high/low water setup value in KB");
+		PMD_INIT_LOG(ERR, "High_water must <= 0x%x", max_high_water);
+		return -EINVAL;
+	}
+
+	hw->fc.requested_mode = rte_fcmode_2_txgbe_fcmode[fc_conf->mode];
+	hw->fc.pause_time     = fc_conf->pause_time;
+	hw->fc.high_water[0]  = fc_conf->high_water;
+	hw->fc.low_water[0]   = fc_conf->low_water;
+	hw->fc.send_xon       = fc_conf->send_xon;
+	hw->fc.disable_fc_autoneg = !fc_conf->autoneg;
+
+	err = txgbe_fc_enable(hw);
+
+	/* Not negotiated is not an error case */
+	if (err == 0 || err == TXGBE_ERR_FC_NOT_NEGOTIATED) {
+		wr32m(hw, TXGBE_MACRXFLT, TXGBE_MACRXFLT_CTL_MASK,
+		      (fc_conf->mac_ctrl_frame_fwd
+		       ? TXGBE_MACRXFLT_CTL_NOPS : TXGBE_MACRXFLT_CTL_DROP));
+		txgbe_flush(hw);
+
+		return 0;
+	}
+
+	PMD_INIT_LOG(ERR, "txgbe_fc_enable = 0x%x", err);
+	return -EIO;
+}
+
 int
 txgbe_dev_rss_reta_update(struct rte_eth_dev *dev,
 			  struct rte_eth_rss_reta_entry64 *reta_conf,
@@ -3167,6 +3285,8 @@ static const struct eth_dev_ops txgbe_eth_dev_ops = {
 	.rx_queue_release           = txgbe_dev_rx_queue_release,
 	.tx_queue_setup             = txgbe_dev_tx_queue_setup,
 	.tx_queue_release           = txgbe_dev_tx_queue_release,
+	.flow_ctrl_get              = txgbe_flow_ctrl_get,
+	.flow_ctrl_set              = txgbe_flow_ctrl_set,
 	.mac_addr_add               = txgbe_add_rar,
 	.mac_addr_remove            = txgbe_remove_rar,
 	.mac_addr_set               = txgbe_set_default_mac_addr,
diff --git a/drivers/net/txgbe/txgbe_ethdev.h b/drivers/net/txgbe/txgbe_ethdev.h
index 733b90363..99ca6aa9d 100644
--- a/drivers/net/txgbe/txgbe_ethdev.h
+++ b/drivers/net/txgbe/txgbe_ethdev.h
@@ -327,6 +327,13 @@ txgbe_ethertype_filter_insert(struct txgbe_filter_info *filter_info,
 	return (i < TXGBE_ETF_ID_MAX ? i : -1);
 }
 
+/* High threshold controlling when to start sending XOFF frames. */
+#define TXGBE_FC_XOFF_HITH              128 /*KB*/
+/* Low threshold controlling when to start sending XON frames. */
+#define TXGBE_FC_XON_LOTH               64 /*KB*/
+
+/* Timer value included in XOFF frames. */
+#define TXGBE_FC_PAUSE_TIME 0x680
 
 #define TXGBE_LINK_DOWN_CHECK_TIMEOUT 4000 /* ms */
 #define TXGBE_LINK_UP_CHECK_TIMEOUT   1000 /* ms */
-- 
2.18.4