Merge branch '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue

Jeff Kirsher says:

====================
100GbE Intel Wired LAN Driver Updates 2019-01-15

This series contains updates to the ice driver only.

Bruce fixes an unused variable build warning, which was introduced with
the commit 2fd527b7 ("net: ndo_bridge_setlink: Add extack").  Added
ethtool support for get_eeprom and get_eeprom_len operations.  Added
support for bringing down the PHY link optional when the interface is
administratively downed.

Anirudh refactors the transmit scheduler functions, which results in
reduced code duplication and adds a helper function, which all the
scheduler functions call instead.  Added an LED blinking handler to
ethtool.  Reworked the queue management code to allow for reuse in
future XDP feature support.  Updates the driver to be able to preserve
the aggregator list after reset by moving it out of port_info and into
ice_hw.  Added the ability to offload SCTP checksum calculation to the
hardware.  Added support for new PHY types, which support higher link
speeds.

Md Fahad makes sure that RSS lookup table and hash key get configured
during the rebuild path after a reset.

Brett updates the driver to set the physical link state according to the
netdev state (up/down).  Added support for adaptive/dynamic interrupt
moderation in the ice driver, along with the ethtool operations needed.

Tony adds software timestamping support by using
ethtool_op_get_ts_info().
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/intel/ice/ice.h

@@ -26,6 +26,7 @@
 #include <linux/bitmap.h>
 #include <linux/log2.h>
 #include <linux/ip.h>
+#include <linux/sctp.h>
 #include <linux/ipv6.h>
 #include <linux/if_bridge.h>
 #include <linux/avf/virtchnl.h>
@@ -110,6 +111,9 @@ extern const char ice_drv_ver[];
 #define ice_for_each_alloc_rxq(vsi, i) \
 	for ((i) = 0; (i) < (vsi)->alloc_rxq; (i)++)
 
+#define ice_for_each_q_vector(vsi, i) \
+	for ((i) = 0; (i) < (vsi)->num_q_vectors; (i)++)
+
 struct ice_tc_info {
 	u16 qoffset;
 	u16 qcount_tx;
@@ -129,6 +133,17 @@ struct ice_res_tracker {
 	u16 list[1];
 };
 
+struct ice_qs_cfg {
+	struct mutex *qs_mutex;  /* will be assgined to &pf->avail_q_mutex */
+	unsigned long *pf_map;
+	unsigned long pf_map_size;
+	unsigned int q_count;
+	unsigned int scatter_count;
+	u16 *vsi_map;
+	u16 vsi_map_offset;
+	u8 mapping_mode;
+};
+
 struct ice_sw {
 	struct ice_pf *pf;
 	u16 sw_id;		/* switch ID for this switch */
@@ -270,6 +285,7 @@ enum ice_pf_flags {
 	ICE_FLAG_RSS_ENA,
 	ICE_FLAG_SRIOV_ENA,
 	ICE_FLAG_SRIOV_CAPABLE,
+	ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA,
 	ICE_PF_FLAGS_NBITS		/* must be last */
 };
 

drivers/net/ethernet/intel/ice/ice_adminq_cmd.h

@@ -657,8 +657,13 @@ struct ice_aqc_get_topo {
 
 /* Update TSE (indirect 0x0403)
  * Get TSE (indirect 0x0404)
+ * Add TSE (indirect 0x0401)
+ * Delete TSE (indirect 0x040F)
+ * Move TSE (indirect 0x0408)
+ * Suspend Nodes (indirect 0x0409)
+ * Resume Nodes (indirect 0x040A)
  */
-struct ice_aqc_get_cfg_elem {
+struct ice_aqc_sched_elem_cmd {
 	__le16 num_elem_req;	/* Used by commands */
 	__le16 num_elem_resp;	/* Used by responses */
 	__le32 reserved;
@@ -674,18 +679,6 @@ struct ice_aqc_suspend_resume_elem {
 	__le32 teid[1];
 };
 
-/* Add TSE (indirect 0x0401)
- * Delete TSE (indirect 0x040F)
- * Move TSE (indirect 0x0408)
- */
-struct ice_aqc_add_move_delete_elem {
-	__le16 num_grps_req;
-	__le16 num_grps_updated;
-	__le32 reserved;
-	__le32 addr_high;
-	__le32 addr_low;
-};
-
 struct ice_aqc_elem_info_bw {
 	__le16 bw_profile_idx;
 	__le16 bw_alloc;
@@ -854,11 +847,46 @@ struct ice_aqc_get_phy_caps {
 #define ICE_PHY_TYPE_LOW_40GBASE_KR4		BIT_ULL(33)
 #define ICE_PHY_TYPE_LOW_40G_XLAUI_AOC_ACC	BIT_ULL(34)
 #define ICE_PHY_TYPE_LOW_40G_XLAUI		BIT_ULL(35)
+#define ICE_PHY_TYPE_LOW_50GBASE_CR2		BIT_ULL(36)
+#define ICE_PHY_TYPE_LOW_50GBASE_SR2		BIT_ULL(37)
+#define ICE_PHY_TYPE_LOW_50GBASE_LR2		BIT_ULL(38)
+#define ICE_PHY_TYPE_LOW_50GBASE_KR2		BIT_ULL(39)
+#define ICE_PHY_TYPE_LOW_50G_LAUI2_AOC_ACC	BIT_ULL(40)
+#define ICE_PHY_TYPE_LOW_50G_LAUI2		BIT_ULL(41)
+#define ICE_PHY_TYPE_LOW_50G_AUI2_AOC_ACC	BIT_ULL(42)
+#define ICE_PHY_TYPE_LOW_50G_AUI2		BIT_ULL(43)
+#define ICE_PHY_TYPE_LOW_50GBASE_CP		BIT_ULL(44)
+#define ICE_PHY_TYPE_LOW_50GBASE_SR		BIT_ULL(45)
+#define ICE_PHY_TYPE_LOW_50GBASE_FR		BIT_ULL(46)
+#define ICE_PHY_TYPE_LOW_50GBASE_LR		BIT_ULL(47)
+#define ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4	BIT_ULL(48)
+#define ICE_PHY_TYPE_LOW_50G_AUI1_AOC_ACC	BIT_ULL(49)
+#define ICE_PHY_TYPE_LOW_50G_AUI1		BIT_ULL(50)
+#define ICE_PHY_TYPE_LOW_100GBASE_CR4		BIT_ULL(51)
+#define ICE_PHY_TYPE_LOW_100GBASE_SR4		BIT_ULL(52)
+#define ICE_PHY_TYPE_LOW_100GBASE_LR4		BIT_ULL(53)
+#define ICE_PHY_TYPE_LOW_100GBASE_KR4		BIT_ULL(54)
+#define ICE_PHY_TYPE_LOW_100G_CAUI4_AOC_ACC	BIT_ULL(55)
+#define ICE_PHY_TYPE_LOW_100G_CAUI4		BIT_ULL(56)
+#define ICE_PHY_TYPE_LOW_100G_AUI4_AOC_ACC	BIT_ULL(57)
+#define ICE_PHY_TYPE_LOW_100G_AUI4		BIT_ULL(58)
+#define ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4	BIT_ULL(59)
+#define ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4	BIT_ULL(60)
+#define ICE_PHY_TYPE_LOW_100GBASE_CP2		BIT_ULL(61)
+#define ICE_PHY_TYPE_LOW_100GBASE_SR2		BIT_ULL(62)
+#define ICE_PHY_TYPE_LOW_100GBASE_DR		BIT_ULL(63)
 #define ICE_PHY_TYPE_LOW_MAX_INDEX		63
+/* The second set of defines is for phy_type_high. */
+#define ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4	BIT_ULL(0)
+#define ICE_PHY_TYPE_HIGH_100G_CAUI2_AOC_ACC	BIT_ULL(1)
+#define ICE_PHY_TYPE_HIGH_100G_CAUI2		BIT_ULL(2)
+#define ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC	BIT_ULL(3)
+#define ICE_PHY_TYPE_HIGH_100G_AUI2		BIT_ULL(4)
+#define ICE_PHY_TYPE_HIGH_MAX_INDEX		19
 
 struct ice_aqc_get_phy_caps_data {
 	__le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */
-	__le64 reserved;
+	__le64 phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */
 	u8 caps;
 #define ICE_AQC_PHY_EN_TX_LINK_PAUSE			BIT(0)
 #define ICE_AQC_PHY_EN_RX_LINK_PAUSE			BIT(1)
@@ -923,7 +951,7 @@ struct ice_aqc_set_phy_cfg {
 /* Set PHY config command data structure */
 struct ice_aqc_set_phy_cfg_data {
 	__le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */
-	__le64 rsvd0;
+	__le64 phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */
 	u8 caps;
 #define ICE_AQ_PHY_ENA_TX_PAUSE_ABILITY		BIT(0)
 #define ICE_AQ_PHY_ENA_RX_PAUSE_ABILITY		BIT(1)
@@ -1032,10 +1060,12 @@ struct ice_aqc_get_link_status_data {
 #define ICE_AQ_LINK_SPEED_20GB		BIT(6)
 #define ICE_AQ_LINK_SPEED_25GB		BIT(7)
 #define ICE_AQ_LINK_SPEED_40GB		BIT(8)
+#define ICE_AQ_LINK_SPEED_50GB		BIT(9)
+#define ICE_AQ_LINK_SPEED_100GB		BIT(10)
 #define ICE_AQ_LINK_SPEED_UNKNOWN	BIT(15)
 	__le32 reserved3; /* Aligns next field to 8-byte boundary */
 	__le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */
-	__le64 reserved4;
+	__le64 phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */
 };
 
 /* Set event mask command (direct 0x0613) */
@@ -1055,6 +1085,16 @@ struct ice_aqc_set_event_mask {
 	u8	reserved1[6];
 };
 
+/* Set Port Identification LED (direct, 0x06E9) */
+struct ice_aqc_set_port_id_led {
+	u8 lport_num;
+	u8 lport_num_valid;
+	u8 ident_mode;
+#define ICE_AQC_PORT_IDENT_LED_BLINK	BIT(0)
+#define ICE_AQC_PORT_IDENT_LED_ORIG	0
+	u8 rsvd[13];
+};
+
 /* NVM Read command (indirect 0x0701)
  * NVM Erase commands (direct 0x0702)
  * NVM Update commands (indirect 0x0703)
@@ -1341,12 +1381,12 @@ struct ice_aq_desc {
 		struct ice_aqc_get_phy_caps get_phy;
 		struct ice_aqc_set_phy_cfg set_phy;
 		struct ice_aqc_restart_an restart_an;
+		struct ice_aqc_set_port_id_led set_port_id_led;
 		struct ice_aqc_get_sw_cfg get_sw_conf;
 		struct ice_aqc_sw_rules sw_rules;
 		struct ice_aqc_get_topo get_topo;
-		struct ice_aqc_get_cfg_elem get_update_elem;
+		struct ice_aqc_sched_elem_cmd sched_elem_cmd;
 		struct ice_aqc_query_txsched_res query_sched_res;
-		struct ice_aqc_add_move_delete_elem add_move_delete_elem;
 		struct ice_aqc_nvm nvm;
 		struct ice_aqc_pf_vf_msg virt;
 		struct ice_aqc_get_set_rss_lut get_set_rss_lut;
@@ -1442,6 +1482,7 @@ enum ice_adminq_opc {
 	ice_aqc_opc_restart_an				= 0x0605,
 	ice_aqc_opc_get_link_status			= 0x0607,
 	ice_aqc_opc_set_event_mask			= 0x0613,
+	ice_aqc_opc_set_port_id_led			= 0x06E9,
 
 	/* NVM commands */
 	ice_aqc_opc_nvm_read				= 0x0701,

drivers/net/ethernet/intel/ice/ice_common.h

@@ -28,6 +28,8 @@ ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res,
 		enum ice_aq_res_access_type access, u32 timeout);
 void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res);
 enum ice_status ice_init_nvm(struct ice_hw *hw);
+enum ice_status ice_read_sr_buf(struct ice_hw *hw, u16 offset, u16 *words,
+				u16 *data);
 enum ice_status
 ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 		struct ice_aq_desc *desc, void *buf, u16 buf_size,
@@ -70,9 +72,10 @@ ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode,
 		    struct ice_aqc_get_phy_caps_data *caps,
 		    struct ice_sq_cd *cd);
 void
-ice_update_phy_type(u64 *phy_type_low, u16 link_speeds_bitmap);
+ice_update_phy_type(u64 *phy_type_low, u64 *phy_type_high,
+		    u16 link_speeds_bitmap);
 enum ice_status
-ice_aq_manage_mac_write(struct ice_hw *hw, u8 *mac_addr, u8 flags,
+ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags,
 			struct ice_sq_cd *cd);
 enum ice_status ice_clear_pf_cfg(struct ice_hw *hw);
 enum ice_status
@@ -86,6 +89,10 @@ enum ice_status
 ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link,
 			   struct ice_sq_cd *cd);
 enum ice_status
+ice_aq_set_port_id_led(struct ice_port_info *pi, bool is_orig_mode,
+		       struct ice_sq_cd *cd);
+
+enum ice_status
 ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids,
 		u32 *q_teids, enum ice_disq_rst_src rst_src, u16 vmvf_num,
 		struct ice_sq_cd *cmd_details);

drivers/net/ethernet/intel/ice/ice_hw_autogen.h

@@ -110,6 +110,7 @@
 #define GLINT_DYN_CTL_CLEARPBA_M		BIT(1)
 #define GLINT_DYN_CTL_SWINT_TRIG_M		BIT(2)
 #define GLINT_DYN_CTL_ITR_INDX_S		3
+#define GLINT_DYN_CTL_INTERVAL_S		5
 #define GLINT_DYN_CTL_SW_ITR_INDX_M		ICE_M(0x3, 25)
 #define GLINT_DYN_CTL_INTENA_MSK_M		BIT(31)
 #define GLINT_ITR(_i, _INT)			(0x00154000 + ((_i) * 8192 + (_INT) * 4))

drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h

@@ -346,6 +346,7 @@ enum ice_tx_desc_cmd_bits {
 	ICE_TX_DESC_CMD_IIPT_IPV4		= 0x0040, /* 2 BITS */
 	ICE_TX_DESC_CMD_IIPT_IPV4_CSUM		= 0x0060, /* 2 BITS */
 	ICE_TX_DESC_CMD_L4T_EOFT_TCP		= 0x0100, /* 2 BITS */
+	ICE_TX_DESC_CMD_L4T_EOFT_SCTP		= 0x0200, /* 2 BITS */
 	ICE_TX_DESC_CMD_L4T_EOFT_UDP		= 0x0300, /* 2 BITS */
 };
 
@@ -488,5 +489,7 @@ static inline struct ice_rx_ptype_decoded ice_decode_rx_desc_ptype(u16 ptype)
 #define ICE_LINK_SPEED_20000MBPS	20000
 #define ICE_LINK_SPEED_25000MBPS	25000
 #define ICE_LINK_SPEED_40000MBPS	40000
+#define ICE_LINK_SPEED_50000MBPS	50000
+#define ICE_LINK_SPEED_100000MBPS	100000
 
 #endif /* _ICE_LAN_TX_RX_H_ */

drivers/net/ethernet/intel/ice/ice_lib.h

@@ -15,7 +15,7 @@ void ice_update_eth_stats(struct ice_vsi *vsi);
 
 int ice_vsi_cfg_rxqs(struct ice_vsi *vsi);
 
-int ice_vsi_cfg_txqs(struct ice_vsi *vsi);
+int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi);
 
 void ice_vsi_cfg_msix(struct ice_vsi *vsi);
 
@@ -31,7 +31,8 @@ int ice_vsi_start_rx_rings(struct ice_vsi *vsi);
 
 int ice_vsi_stop_rx_rings(struct ice_vsi *vsi);
 
-int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
+int
+ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
 			  u16 rel_vmvf_num);
 
 int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena);

drivers/net/ethernet/intel/ice/ice_main.c

@@ -1389,7 +1389,6 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
 {
 	struct ice_hw *hw = &pf->hw;
 	int oicr_idx, err = 0;
-	u8 itr_gran;
 	u32 val;
 
 	if (!pf->int_name[0])
@@ -1453,10 +1452,8 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
 	       PFINT_MBX_CTL_CAUSE_ENA_M);
 	wr32(hw, PFINT_MBX_CTL, val);
 
-	itr_gran = hw->itr_gran;
-
 	wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->hw_oicr_idx),
-	     ITR_TO_REG(ICE_ITR_8K, itr_gran));
+	     ITR_REG_ALIGN(ICE_ITR_8K) >> ICE_ITR_GRAN_S);
 
 	ice_flush(hw);
 	ice_irq_dynamic_ena(hw, NULL, NULL);
@@ -1531,6 +1528,7 @@ static int ice_cfg_netdev(struct ice_vsi *vsi)
 
 	csumo_features = NETIF_F_RXCSUM	  |
 			 NETIF_F_IP_CSUM  |
+			 NETIF_F_SCTP_CRC |
 			 NETIF_F_IPV6_CSUM;
 
 	vlano_features = NETIF_F_HW_VLAN_CTAG_FILTER |
@@ -1997,6 +1995,23 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf)
 	return 0;
 }
 
+/**
+ * ice_verify_itr_gran - verify driver's assumption of ITR granularity
+ * @pf: pointer to the PF structure
+ *
+ * There is no error returned here because the driver will be able to handle a
+ * different ITR granularity, but interrupt moderation will not be accurate if
+ * the driver's assumptions are not verified. This assumption is made so we can
+ * use constants in the hot path instead of accessing structure members.
+ */
+static void ice_verify_itr_gran(struct ice_pf *pf)
+{
+	if (pf->hw.itr_gran != (ICE_ITR_GRAN_S << 1))
+		dev_warn(&pf->pdev->dev,
+			 "%d ITR granularity assumption is invalid, actual ITR granularity is %d. Interrupt moderation will be inaccurate!\n",
+			 (ICE_ITR_GRAN_S << 1), pf->hw.itr_gran);
+}
+
 /**
  * ice_verify_cacheline_size - verify driver's assumption of 64 Byte cache lines
  * @pf: pointer to the PF structure
@@ -2163,6 +2178,7 @@ static int ice_probe(struct pci_dev *pdev,
 	mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period));
 
 	ice_verify_cacheline_size(pf);
+	ice_verify_itr_gran(pf);
 
 	return 0;
 
@@ -2546,7 +2562,8 @@ static int ice_vsi_cfg(struct ice_vsi *vsi)
 		if (err)
 			return err;
 	}
-	err = ice_vsi_cfg_txqs(vsi);
+
+	err = ice_vsi_cfg_lan_txqs(vsi);
 	if (!err)
 		err = ice_vsi_cfg_rxqs(vsi);
 
@@ -2944,13 +2961,92 @@ static void ice_napi_disable_all(struct ice_vsi *vsi)
 	}
 }
 
+/**
+ * ice_force_phys_link_state - Force the physical link state
+ * @vsi: VSI to force the physical link state to up/down
+ * @link_up: true/false indicates to set the physical link to up/down
+ *
+ * Force the physical link state by getting the current PHY capabilities from
+ * hardware and setting the PHY config based on the determined capabilities. If
+ * link changes a link event will be triggered because both the Enable Automatic
+ * Link Update and LESM Enable bits are set when setting the PHY capabilities.
+ *
+ * Returns 0 on success, negative on failure
+ */
+static int ice_force_phys_link_state(struct ice_vsi *vsi, bool link_up)
+{
+	struct ice_aqc_get_phy_caps_data *pcaps;
+	struct ice_aqc_set_phy_cfg_data *cfg;
+	struct ice_port_info *pi;
+	struct device *dev;
+	int retcode;
+
+	if (!vsi || !vsi->port_info || !vsi->back)
+		return -EINVAL;
+	if (vsi->type != ICE_VSI_PF)
+		return 0;
+
+	dev = &vsi->back->pdev->dev;
+
+	pi = vsi->port_info;
+
+	pcaps = devm_kzalloc(dev, sizeof(*pcaps), GFP_KERNEL);
+	if (!pcaps)
+		return -ENOMEM;
+
+	retcode = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps,
+				      NULL);
+	if (retcode) {
+		dev_err(dev,
+			"Failed to get phy capabilities, VSI %d error %d\n",
+			vsi->vsi_num, retcode);
+		retcode = -EIO;
+		goto out;
+	}
+
+	/* No change in link */
+	if (link_up == !!(pcaps->caps & ICE_AQC_PHY_EN_LINK) &&
+	    link_up == !!(pi->phy.link_info.link_info & ICE_AQ_LINK_UP))
+		goto out;
+
+	cfg = devm_kzalloc(dev, sizeof(*cfg), GFP_KERNEL);
+	if (!cfg) {
+		retcode = -ENOMEM;
+		goto out;
+	}
+
+	cfg->phy_type_low = pcaps->phy_type_low;
+	cfg->phy_type_high = pcaps->phy_type_high;
+	cfg->caps = pcaps->caps | ICE_AQ_PHY_ENA_AUTO_LINK_UPDT;
+	cfg->low_power_ctrl = pcaps->low_power_ctrl;
+	cfg->eee_cap = pcaps->eee_cap;
+	cfg->eeer_value = pcaps->eeer_value;
+	cfg->link_fec_opt = pcaps->link_fec_options;
+	if (link_up)
+		cfg->caps |= ICE_AQ_PHY_ENA_LINK;
+	else
+		cfg->caps &= ~ICE_AQ_PHY_ENA_LINK;
+
+	retcode = ice_aq_set_phy_cfg(&vsi->back->hw, pi->lport, cfg, NULL);
+	if (retcode) {
+		dev_err(dev, "Failed to set phy config, VSI %d error %d\n",
+			vsi->vsi_num, retcode);
+		retcode = -EIO;
+	}
+
+	devm_kfree(dev, cfg);
+out:
+	devm_kfree(dev, pcaps);
+	return retcode;
+}
+
 /**
  * ice_down - Shutdown the connection
  * @vsi: The VSI being stopped
  */
 int ice_down(struct ice_vsi *vsi)
 {
-	int i, tx_err, rx_err;
+	int i, tx_err, rx_err, link_err = 0;
 
 	/* Caller of this function is expected to set the
 	 * vsi->state __ICE_DOWN bit
@@ -2961,7 +3057,8 @@ int ice_down(struct ice_vsi *vsi)
 	}
 
 	ice_vsi_dis_irq(vsi);
-	tx_err = ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, 0);
+
+	tx_err = ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, 0);
 	if (tx_err)
 		netdev_err(vsi->netdev,
 			   "Failed stop Tx rings, VSI %d error %d\n",
@@ -2975,13 +3072,21 @@ int ice_down(struct ice_vsi *vsi)
 
 	ice_napi_disable_all(vsi);
 
+	if (test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, vsi->back->flags)) {
+		link_err = ice_force_phys_link_state(vsi, false);
+		if (link_err)
+			netdev_err(vsi->netdev,
+				   "Failed to set physical link down, VSI %d error %d\n",
+				   vsi->vsi_num, link_err);
+	}
+
 	ice_for_each_txq(vsi, i)
 		ice_clean_tx_ring(vsi->tx_rings[i]);
 
 	ice_for_each_rxq(vsi, i)
 		ice_clean_rx_ring(vsi->rx_rings[i]);
 
-	if (tx_err || rx_err) {
+	if (tx_err || rx_err || link_err) {
 		netdev_err(vsi->netdev,
 			   "Failed to close VSI 0x%04X on switch 0x%04X\n",
 			   vsi->vsi_num, vsi->vsw->sw_id);
@@ -3641,7 +3746,8 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode)
  */
 static int
 ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
-		   u16 __always_unused flags, struct netlink_ext_ack *extack)
+		   u16 __always_unused flags,
+		   struct netlink_ext_ack __always_unused *extack)
 {
 	struct ice_netdev_priv *np = netdev_priv(dev);
 	struct ice_pf *pf = np->vsi->back;
@@ -3814,8 +3920,14 @@ static int ice_open(struct net_device *netdev)
 
 	netif_carrier_off(netdev);
 
-	err = ice_vsi_open(vsi);
+	err = ice_force_phys_link_state(vsi, true);
+	if (err) {
+		netdev_err(netdev,
+			   "Failed to set physical link up, error %d\n", err);
+		return err;
+	}
 
+	err = ice_vsi_open(vsi);
 	if (err)
 		netdev_err(netdev, "Failed to open VSI 0x%04X on switch 0x%04X\n",
 			   vsi->vsi_num, vsi->vsw->sw_id);

drivers/net/ethernet/intel/ice/ice_nvm.c

@@ -124,6 +124,62 @@ ice_read_sr_word_aq(struct ice_hw *hw, u16 offset, u16 *data)
 	return status;
 }
 
+/**
+ * ice_read_sr_buf_aq - Reads Shadow RAM buf via AQ
+ * @hw: pointer to the HW structure
+ * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF)
+ * @words: (in) number of words to read; (out) number of words actually read
+ * @data: words read from the Shadow RAM
+ *
+ * Reads 16 bit words (data buf) from the SR using the ice_read_sr_aq
+ * method. Ownership of the NVM is taken before reading the buffer and later
+ * released.
+ */
+static enum ice_status
+ice_read_sr_buf_aq(struct ice_hw *hw, u16 offset, u16 *words, u16 *data)
+{
+	enum ice_status status;
+	bool last_cmd = false;
+	u16 words_read = 0;
+	u16 i = 0;
+
+	do {
+		u16 read_size, off_w;
+
+		/* Calculate number of bytes we should read in this step.
+		 * It's not allowed to read more than one page at a time or
+		 * to cross page boundaries.
+		 */
+		off_w = offset % ICE_SR_SECTOR_SIZE_IN_WORDS;
+		read_size = off_w ?
+			min(*words,
+			    (u16)(ICE_SR_SECTOR_SIZE_IN_WORDS - off_w)) :
+			min((*words - words_read), ICE_SR_SECTOR_SIZE_IN_WORDS);
+
+		/* Check if this is last command, if so set proper flag */
+		if ((words_read + read_size) >= *words)
+			last_cmd = true;
+
+		status = ice_read_sr_aq(hw, offset, read_size,
+					data + words_read, last_cmd);
+		if (status)
+			goto read_nvm_buf_aq_exit;
+
+		/* Increment counter for words already read and move offset to
+		 * new read location
+		 */
+		words_read += read_size;
+		offset += read_size;
+	} while (words_read < *words);
+
+	for (i = 0; i < *words; i++)
+		data[i] = le16_to_cpu(((__le16 *)data)[i]);
+
+read_nvm_buf_aq_exit:
+	*words = words_read;
+	return status;
+}
+
 /**
  * ice_acquire_nvm - Generic request for acquiring the NVM ownership
  * @hw: pointer to the HW structure
@@ -234,3 +290,28 @@ enum ice_status ice_init_nvm(struct ice_hw *hw)
 
 	return status;
 }
+
+/**
+ * ice_read_sr_buf - Reads Shadow RAM buf and acquire lock if necessary
+ * @hw: pointer to the HW structure
+ * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF)
+ * @words: (in) number of words to read; (out) number of words actually read
+ * @data: words read from the Shadow RAM
+ *
+ * Reads 16 bit words (data buf) from the SR using the ice_read_nvm_buf_aq
+ * method. The buf read is preceded by the NVM ownership take
+ * and followed by the release.
+ */
+enum ice_status
+ice_read_sr_buf(struct ice_hw *hw, u16 offset, u16 *words, u16 *data)
+{
+	enum ice_status status;
+
+	status = ice_acquire_nvm(hw, ICE_RES_READ);
+	if (!status) {
+		status = ice_read_sr_buf_aq(hw, offset, words, data);
+		ice_release_nvm(hw);
+	}
+
+	return status;
+}

drivers/net/ethernet/intel/ice/ice_sched.c

@@ -85,36 +85,58 @@ ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid)
 }
 
 /**
- * ice_aq_query_sched_elems - query scheduler elements
+ * ice_aqc_send_sched_elem_cmd - send scheduling elements cmd
  * @hw: pointer to the hw struct
- * @elems_req: number of elements to query
+ * @cmd_opc: cmd opcode
+ * @elems_req: number of elements to request
  * @buf: pointer to buffer
  * @buf_size: buffer size in bytes
- * @elems_ret: returns total number of elements returned
+ * @elems_resp: returns total number of elements response
  * @cd: pointer to command details structure or NULL
  *
- * Query scheduling elements (0x0404)
+ * This function sends a scheduling elements cmd (cmd_opc)
  */
 static enum ice_status
-ice_aq_query_sched_elems(struct ice_hw *hw, u16 elems_req,
-			 struct ice_aqc_get_elem *buf, u16 buf_size,
-			 u16 *elems_ret, struct ice_sq_cd *cd)
+ice_aqc_send_sched_elem_cmd(struct ice_hw *hw, enum ice_adminq_opc cmd_opc,
+			    u16 elems_req, void *buf, u16 buf_size,
+			    u16 *elems_resp, struct ice_sq_cd *cd)
 {
-	struct ice_aqc_get_cfg_elem *cmd;
+	struct ice_aqc_sched_elem_cmd *cmd;
 	struct ice_aq_desc desc;
 	enum ice_status status;
 
-	cmd = &desc.params.get_update_elem;
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_sched_elems);
+	cmd = &desc.params.sched_elem_cmd;
+	ice_fill_dflt_direct_cmd_desc(&desc, cmd_opc);
 	cmd->num_elem_req = cpu_to_le16(elems_req);
 	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
 	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
-	if (!status && elems_ret)
-		*elems_ret = le16_to_cpu(cmd->num_elem_resp);
+	if (!status && elems_resp)
+		*elems_resp = le16_to_cpu(cmd->num_elem_resp);
 
 	return status;
 }
 
+/**
+ * ice_aq_query_sched_elems - query scheduler elements
+ * @hw: pointer to the hw struct
+ * @elems_req: number of elements to query
+ * @buf: pointer to buffer
+ * @buf_size: buffer size in bytes
+ * @elems_ret: returns total number of elements returned
+ * @cd: pointer to command details structure or NULL
+ *
+ * Query scheduling elements (0x0404)
+ */
+static enum ice_status
+ice_aq_query_sched_elems(struct ice_hw *hw, u16 elems_req,
+			 struct ice_aqc_get_elem *buf, u16 buf_size,
+			 u16 *elems_ret, struct ice_sq_cd *cd)
+{
+	return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_get_sched_elems,
+					   elems_req, (void *)buf, buf_size,
+					   elems_ret, cd);
+}
+
 /**
  * ice_sched_query_elem - query element information from hw
  * @hw: pointer to the hw struct
@@ -218,20 +240,9 @@ ice_aq_delete_sched_elems(struct ice_hw *hw, u16 grps_req,
 			  struct ice_aqc_delete_elem *buf, u16 buf_size,
 			  u16 *grps_del, struct ice_sq_cd *cd)
 {
-	struct ice_aqc_add_move_delete_elem *cmd;
-	struct ice_aq_desc desc;
-	enum ice_status status;
-
-	cmd = &desc.params.add_move_delete_elem;
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_delete_sched_elems);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
-	cmd->num_grps_req = cpu_to_le16(grps_req);
-
-	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
-	if (!status && grps_del)
-		*grps_del = le16_to_cpu(cmd->num_grps_updated);
-
-	return status;
+	return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_delete_sched_elems,
+					   grps_req, (void *)buf, buf_size,
+					   grps_del, cd);
 }
 
 /**
@@ -442,52 +453,9 @@ ice_aq_add_sched_elems(struct ice_hw *hw, u16 grps_req,
 		       struct ice_aqc_add_elem *buf, u16 buf_size,
 		       u16 *grps_added, struct ice_sq_cd *cd)
 {
-	struct ice_aqc_add_move_delete_elem *cmd;
-	struct ice_aq_desc desc;
-	enum ice_status status;
-
-	cmd = &desc.params.add_move_delete_elem;
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_sched_elems);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
-
-	cmd->num_grps_req = cpu_to_le16(grps_req);
-	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
-	if (!status && grps_added)
-		*grps_added = le16_to_cpu(cmd->num_grps_updated);
-
-	return status;
-}
-
-/**
- * ice_suspend_resume_elems - suspend/resume scheduler elements
- * @hw: pointer to the hw struct
- * @elems_req: number of elements to suspend
- * @buf: pointer to buffer
- * @buf_size: buffer size in bytes
- * @elems_ret: returns total number of elements suspended
- * @cd: pointer to command details structure or NULL
- * @cmd_code: command code for suspend or resume
- *
- * suspend/resume scheduler elements
- */
-static enum ice_status
-ice_suspend_resume_elems(struct ice_hw *hw, u16 elems_req,
-			 struct ice_aqc_suspend_resume_elem *buf, u16 buf_size,
-			 u16 *elems_ret, struct ice_sq_cd *cd,
-			 enum ice_adminq_opc cmd_code)
-{
-	struct ice_aqc_get_cfg_elem *cmd;
-	struct ice_aq_desc desc;
-	enum ice_status status;
-
-	cmd = &desc.params.get_update_elem;
-	ice_fill_dflt_direct_cmd_desc(&desc, cmd_code);
-	cmd->num_elem_req = cpu_to_le16(elems_req);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
-	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
-	if (!status && elems_ret)
-		*elems_ret = le16_to_cpu(cmd->num_elem_resp);
-	return status;
+	return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_add_sched_elems,
+					   grps_req, (void *)buf, buf_size,
+					   grps_added, cd);
 }
 
 /**
@@ -506,8 +474,9 @@ ice_aq_suspend_sched_elems(struct ice_hw *hw, u16 elems_req,
 			   struct ice_aqc_suspend_resume_elem *buf,
 			   u16 buf_size, u16 *elems_ret, struct ice_sq_cd *cd)
 {
-	return ice_suspend_resume_elems(hw, elems_req, buf, buf_size, elems_ret,
-					cd, ice_aqc_opc_suspend_sched_elems);
+	return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_suspend_sched_elems,
+					   elems_req, (void *)buf, buf_size,
+					   elems_ret, cd);
 }
 
 /**
@@ -526,8 +495,9 @@ ice_aq_resume_sched_elems(struct ice_hw *hw, u16 elems_req,
 			  struct ice_aqc_suspend_resume_elem *buf,
 			  u16 buf_size, u16 *elems_ret, struct ice_sq_cd *cd)
 {
-	return ice_suspend_resume_elems(hw, elems_req, buf, buf_size, elems_ret,
-					cd, ice_aqc_opc_resume_sched_elems);
+	return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_resume_sched_elems,
+					   elems_req, (void *)buf, buf_size,
+					   elems_ret, cd);
 }
 
 /**
@@ -591,23 +561,18 @@ ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids,
 }
 
 /**
- * ice_sched_clear_tx_topo - clears the schduler tree nodes
- * @pi: port information structure
+ * ice_sched_clear_agg - clears the agg related information
+ * @hw: pointer to the hardware structure
  *
- * This function removes all the nodes from HW as well as from SW DB.
+ * This function removes agg list and free up agg related memory
+ * previously allocated.
  */
-static void ice_sched_clear_tx_topo(struct ice_port_info *pi)
+void ice_sched_clear_agg(struct ice_hw *hw)
 {
 	struct ice_sched_agg_info *agg_info;
 	struct ice_sched_agg_info *atmp;
-	struct ice_hw *hw;
-
-	if (!pi)
-		return;
-
-	hw = pi->hw;
 
-	list_for_each_entry_safe(agg_info, atmp, &pi->agg_list, list_entry) {
+	list_for_each_entry_safe(agg_info, atmp, &hw->agg_list, list_entry) {
 		struct ice_sched_agg_vsi_info *agg_vsi_info;
 		struct ice_sched_agg_vsi_info *vtmp;
 
@@ -616,8 +581,21 @@ static void ice_sched_clear_tx_topo(struct ice_port_info *pi)
 			list_del(&agg_vsi_info->list_entry);
 			devm_kfree(ice_hw_to_dev(hw), agg_vsi_info);
 		}
+		list_del(&agg_info->list_entry);
+		devm_kfree(ice_hw_to_dev(hw), agg_info);
 	}
+}
 
+/**
+ * ice_sched_clear_tx_topo - clears the scheduler tree nodes
+ * @pi: port information structure
+ *
+ * This function removes all the nodes from HW as well as from SW DB.
+ */
+static void ice_sched_clear_tx_topo(struct ice_port_info *pi)
+{
+	if (!pi)
+		return;
 	if (pi->root) {
 		ice_free_sched_node(pi, pi->root);
 		pi->root = NULL;
@@ -1035,7 +1013,6 @@ enum ice_status ice_sched_init_port(struct ice_port_info *pi)
 	/* initialize the port for handling the scheduler tree */
 	pi->port_state = ICE_SCHED_PORT_STATE_READY;
 	mutex_init(&pi->sched_lock);
-	INIT_LIST_HEAD(&pi->agg_list);
 
 err_init_port:
 	if (status && pi->root) {
@@ -1618,7 +1595,8 @@ ice_sched_rm_agg_vsi_info(struct ice_port_info *pi, u16 vsi_handle)
 	struct ice_sched_agg_info *agg_info;
 	struct ice_sched_agg_info *atmp;
 
-	list_for_each_entry_safe(agg_info, atmp, &pi->agg_list, list_entry) {
+	list_for_each_entry_safe(agg_info, atmp, &pi->hw->agg_list,
+				 list_entry) {
 		struct ice_sched_agg_vsi_info *agg_vsi_info;
 		struct ice_sched_agg_vsi_info *vtmp;
 

drivers/net/ethernet/intel/ice/ice_sched.h

@@ -28,6 +28,8 @@ enum ice_status ice_sched_init_port(struct ice_port_info *pi);
 enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw);
 void ice_sched_clear_port(struct ice_port_info *pi);
 void ice_sched_cleanup_all(struct ice_hw *hw);
+void ice_sched_clear_agg(struct ice_hw *hw);
+
 struct ice_sched_node *
 ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid);
 enum ice_status

drivers/net/ethernet/intel/ice/ice_sriov.c

@@ -85,6 +85,12 @@ u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed)
 		case ICE_AQ_LINK_SPEED_40GB:
 			speed = ICE_LINK_SPEED_40000MBPS;
 			break;
+		case ICE_AQ_LINK_SPEED_50GB:
+			speed = ICE_LINK_SPEED_50000MBPS;
+			break;
+		case ICE_AQ_LINK_SPEED_100GB:
+			speed = ICE_LINK_SPEED_100000MBPS;
+			break;
 		default:
 			speed = ICE_LINK_SPEED_UNKNOWN;
 			break;
@@ -116,6 +122,9 @@ u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed)
 			break;
 		case ICE_AQ_LINK_SPEED_40GB:
 			/* fall through */
+		case ICE_AQ_LINK_SPEED_50GB:
+			/* fall through */
+		case ICE_AQ_LINK_SPEED_100GB:
 			speed = (u32)VIRTCHNL_LINK_SPEED_40GB;
 			break;
 		default:

drivers/net/ethernet/intel/ice/ice_txrx.c

@@ -1052,6 +1052,69 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 	return failure ? budget : (int)total_rx_pkts;
 }
 
+/**
+ * ice_buildreg_itr - build value for writing to the GLINT_DYN_CTL register
+ * @itr_idx: interrupt throttling index
+ * @reg_itr: interrupt throttling value adjusted based on ITR granularity
+ */
+static u32 ice_buildreg_itr(int itr_idx, u16 reg_itr)
+{
+	return GLINT_DYN_CTL_INTENA_M | GLINT_DYN_CTL_CLEARPBA_M |
+		(itr_idx << GLINT_DYN_CTL_ITR_INDX_S) |
+		(reg_itr << GLINT_DYN_CTL_INTERVAL_S);
+}
+
+/**
+ * ice_update_ena_itr - Update ITR and re-enable MSIX interrupt
+ * @vsi: the VSI associated with the q_vector
+ * @q_vector: q_vector for which ITR is being updated and interrupt enabled
+ */
+static void
+ice_update_ena_itr(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
+{
+	struct ice_hw *hw = &vsi->back->hw;
+	struct ice_ring_container *rc;
+	u32 itr_val;
+
+	/* This block of logic allows us to get away with only updating
+	 * one ITR value with each interrupt. The idea is to perform a
+	 * pseudo-lazy update with the following criteria.
+	 *
+	 * 1. Rx is given higher priority than Tx if both are in same state
+	 * 2. If we must reduce an ITR that is given highest priority.
+	 * 3. We then give priority to increasing ITR based on amount.
+	 */
+	if (q_vector->rx.target_itr < q_vector->rx.current_itr) {
+		rc = &q_vector->rx;
+		/* Rx ITR needs to be reduced, this is highest priority */
+		itr_val = ice_buildreg_itr(rc->itr_idx, rc->target_itr);
+		rc->current_itr = rc->target_itr;
+	} else if ((q_vector->tx.target_itr < q_vector->tx.current_itr) ||
+		   ((q_vector->rx.target_itr - q_vector->rx.current_itr) <
+		    (q_vector->tx.target_itr - q_vector->tx.current_itr))) {
+		rc = &q_vector->tx;
+		/* Tx ITR needs to be reduced, this is second priority
+		 * Tx ITR needs to be increased more than Rx, fourth priority
+		 */
+		itr_val = ice_buildreg_itr(rc->itr_idx, rc->target_itr);
+		rc->current_itr = rc->target_itr;
+	} else if (q_vector->rx.current_itr != q_vector->rx.target_itr) {
+		rc = &q_vector->rx;
+		/* Rx ITR needs to be increased, third priority */
+		itr_val = ice_buildreg_itr(rc->itr_idx, rc->target_itr);
+		rc->current_itr = rc->target_itr;
+	} else {
+		/* Still have to re-enable the interrupts */
+		itr_val = ice_buildreg_itr(ICE_ITR_NONE, 0);
+	}
+
+	if (!test_bit(__ICE_DOWN, vsi->state)) {
+		int vector = vsi->hw_base_vector + q_vector->v_idx;
+
+		wr32(hw, GLINT_DYN_CTL(vector), itr_val);
+	}
+}
+
 /**
  * ice_napi_poll - NAPI polling Rx/Tx cleanup routine
  * @napi: napi struct with our devices info in it
@@ -1108,7 +1171,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 	 */
 	if (likely(napi_complete_done(napi, work_done)))
 		if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
-			ice_irq_dynamic_ena(&vsi->back->hw, vsi, q_vector);
+			ice_update_ena_itr(vsi, q_vector);
 
 	return min(work_done, budget - 1);
 }
@@ -1402,6 +1465,12 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 		offset |= l4_len << ICE_TX_DESC_LEN_L4_LEN_S;
 		break;
 	case IPPROTO_SCTP:
+		/* enable SCTP checksum offload */
+		cmd |= ICE_TX_DESC_CMD_L4T_EOFT_SCTP;
+		l4_len = sizeof(struct sctphdr) >> 2;
+		offset |= l4_len << ICE_TX_DESC_LEN_L4_LEN_S;
+		break;
+
 	default:
 		if (first->tx_flags & ICE_TX_FLAGS_TSO)
 			return -1;

drivers/net/ethernet/intel/ice/ice_txrx.h

@@ -116,16 +116,17 @@ enum ice_rx_dtype {
 /* indices into GLINT_ITR registers */
 #define ICE_RX_ITR	ICE_IDX_ITR0
 #define ICE_TX_ITR	ICE_IDX_ITR1
-#define ICE_ITR_DYNAMIC	0x8000  /* use top bit as a flag */
-#define ICE_ITR_8K	125
+#define ICE_ITR_8K	124
 #define ICE_ITR_20K	50
-#define ICE_DFLT_TX_ITR	ICE_ITR_20K
-#define ICE_DFLT_RX_ITR	ICE_ITR_20K
-/* apply ITR granularity translation to program the register. itr_gran is either
- * 2 or 4 usecs so we need to divide by 2 first then shift by that value
- */
-#define ITR_TO_REG(val, itr_gran) (((val) & ~ICE_ITR_DYNAMIC) >> \
-				   ((itr_gran) / 2))
+#define ICE_ITR_MAX	8160
+#define ICE_DFLT_TX_ITR	(ICE_ITR_20K | ICE_ITR_DYNAMIC)
+#define ICE_DFLT_RX_ITR	(ICE_ITR_20K | ICE_ITR_DYNAMIC)
+#define ICE_ITR_DYNAMIC	0x8000  /* used as flag for itr_setting */
+#define ITR_IS_DYNAMIC(setting) (!!((setting) & ICE_ITR_DYNAMIC))
+#define ITR_TO_REG(setting)	((setting) & ~ICE_ITR_DYNAMIC)
+#define ICE_ITR_GRAN_S		1	/* Assume ITR granularity is 2us */
+#define ICE_ITR_MASK		0x1FFE	/* ITR register value alignment mask */
+#define ITR_REG_ALIGN(setting)	__ALIGN_MASK(setting, ~ICE_ITR_MASK)
 
 #define ICE_DFLT_INTRL	0
 
@@ -180,13 +181,20 @@ enum ice_latency_range {
 };
 
 struct ice_ring_container {
-	/* array of pointers to rings */
+	/* head of linked-list of rings */
 	struct ice_ring *ring;
+	unsigned long next_update;	/* jiffies value of next queue update */
 	unsigned int total_bytes;	/* total bytes processed this int */
 	unsigned int total_pkts;	/* total packets processed this int */
 	enum ice_latency_range latency_range;
-	int itr_idx;	/* index in the interrupt vector */
-	u16 itr;
+	int itr_idx;		/* index in the interrupt vector */
+	u16 target_itr;		/* value in usecs divided by the hw->itr_gran */
+	u16 current_itr;	/* value in usecs divided by the hw->itr_gran */
+	/* high bit set means dynamic ITR, rest is used to store user
+	 * readable ITR value in usecs and must be converted before programming
+	 * to a register.
+	 */
+	u16 itr_setting;
 };
 
 /* iterator for handling rings in ring container */

drivers/net/ethernet/intel/ice/ice_type.h

@@ -90,6 +90,7 @@ enum ice_vsi_type {
 struct ice_link_status {
 	/* Refer to ice_aq_phy_type for bits definition */
 	u64 phy_type_low;
+	u64 phy_type_high;
 	u16 max_frame_size;
 	u16 link_speed;
 	u16 req_speeds;
@@ -118,6 +119,7 @@ struct ice_phy_info {
 	struct ice_link_status link_info;
 	struct ice_link_status link_info_old;
 	u64 phy_type_low;
+	u64 phy_type_high;
 	enum ice_media_type media_type;
 	u8 get_link_info;
 };
@@ -272,7 +274,6 @@ struct ice_port_info {
 	struct ice_mac_info mac;
 	struct ice_phy_info phy;
 	struct mutex sched_lock;	/* protect access to TXSched tree */
-	struct list_head agg_list;	/* lists all aggregator */
 	u8 lport;
 #define ICE_LPORT_MASK		0xff
 	u8 is_vf;
@@ -326,6 +327,7 @@ struct ice_hw {
 	u8 max_cgds;
 	u8 sw_entry_point_layer;
 	u16 max_children[ICE_AQC_TOPO_MAX_LEVEL_NUM];
+	struct list_head agg_list;	/* lists all aggregator */
 
 	struct ice_vsi_ctx *vsi_ctx[ICE_MAX_VSI];
 	u8 evb_veb;		/* true for VEB, false for VEPA */

drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c

@@ -224,13 +224,15 @@ void ice_free_vfs(struct ice_pf *pf)
 
 	/* Avoid wait time by stopping all VFs at the same time */
 	for (i = 0; i < pf->num_alloc_vfs; i++) {
+		struct ice_vsi *vsi;
+
 		if (!test_bit(ICE_VF_STATE_ENA, pf->vf[i].vf_states))
 			continue;
 
+		vsi = pf->vsi[pf->vf[i].lan_vsi_idx];
 		/* stop rings without wait time */
-		ice_vsi_stop_tx_rings(pf->vsi[pf->vf[i].lan_vsi_idx],
-				      ICE_NO_RESET, i);
-		ice_vsi_stop_rx_rings(pf->vsi[pf->vf[i].lan_vsi_idx]);
+		ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, i);
+		ice_vsi_stop_rx_rings(vsi);
 
 		clear_bit(ICE_VF_STATE_ENA, pf->vf[i].vf_states);
 	}
@@ -831,6 +833,7 @@ static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr)
 {
 	struct ice_pf *pf = vf->pf;
 	struct ice_hw *hw = &pf->hw;
+	struct ice_vsi *vsi;
 	bool rsd = false;
 	u32 reg;
 	int i;
@@ -843,17 +846,18 @@ static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr)
 
 	ice_trigger_vf_reset(vf, is_vflr);
 
+	vsi = pf->vsi[vf->lan_vsi_idx];
+
 	if (test_bit(ICE_VF_STATE_ENA, vf->vf_states)) {
-		ice_vsi_stop_tx_rings(pf->vsi[vf->lan_vsi_idx], ICE_VF_RESET,
-				      vf->vf_id);
-		ice_vsi_stop_rx_rings(pf->vsi[vf->lan_vsi_idx]);
+		ice_vsi_stop_lan_tx_rings(vsi, ICE_VF_RESET, vf->vf_id);
+		ice_vsi_stop_rx_rings(vsi);
 		clear_bit(ICE_VF_STATE_ENA, vf->vf_states);
 	} else {
 		/* Call Disable LAN Tx queue AQ call even when queues are not
 		 * enabled. This is needed for successful completiom of VFR
 		 */
-		ice_dis_vsi_txq(pf->vsi[vf->lan_vsi_idx]->port_info, 0,
-				NULL, NULL, ICE_VF_RESET, vf->vf_id, NULL);
+		ice_dis_vsi_txq(vsi->port_info, 0, NULL, NULL, ICE_VF_RESET,
+				vf->vf_id, NULL);
 	}
 
 	/* poll VPGEN_VFRSTAT reg to make sure
@@ -1614,7 +1618,7 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg)
 		goto error_param;
 	}
 
-	if (ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, vf->vf_id)) {
+	if (ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id)) {
 		dev_err(&vsi->back->pdev->dev,
 			"Failed to stop tx rings on VSI %d\n",
 			vsi->vsi_num);
@@ -1784,7 +1788,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 	vsi->num_txq = qci->num_queue_pairs;
 	vsi->num_rxq = qci->num_queue_pairs;
 
-	if (!ice_vsi_cfg_txqs(vsi) && !ice_vsi_cfg_rxqs(vsi))
+	if (!ice_vsi_cfg_lan_txqs(vsi) && !ice_vsi_cfg_rxqs(vsi))
 		aq_ret = 0;
 	else
 		aq_ret = ICE_ERR_PARAM;