summaryrefslogtreecommitdiffstats
path: root/drivers/net/ethernet/intel/iavf
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/ethernet/intel/iavf')
-rw-r--r--drivers/net/ethernet/intel/iavf/Makefile2
-rw-r--r--drivers/net/ethernet/intel/iavf/iavf.h35
-rw-r--r--drivers/net/ethernet/intel/iavf/iavf_ethtool.c2
-rw-r--r--drivers/net/ethernet/intel/iavf/iavf_main.c245
-rw-r--r--drivers/net/ethernet/intel/iavf/iavf_ptp.c485
-rw-r--r--drivers/net/ethernet/intel/iavf/iavf_ptp.h47
-rw-r--r--drivers/net/ethernet/intel/iavf/iavf_trace.h6
-rw-r--r--drivers/net/ethernet/intel/iavf/iavf_txrx.c433
-rw-r--r--drivers/net/ethernet/intel/iavf/iavf_txrx.h24
-rw-r--r--drivers/net/ethernet/intel/iavf/iavf_type.h239
-rw-r--r--drivers/net/ethernet/intel/iavf/iavf_types.h34
-rw-r--r--drivers/net/ethernet/intel/iavf/iavf_virtchnl.c203
12 files changed, 1483 insertions, 272 deletions
diff --git a/drivers/net/ethernet/intel/iavf/Makefile b/drivers/net/ethernet/intel/iavf/Makefile
index 356ac9faa5bf..e13720a728ff 100644
--- a/drivers/net/ethernet/intel/iavf/Makefile
+++ b/drivers/net/ethernet/intel/iavf/Makefile
@@ -13,3 +13,5 @@ obj-$(CONFIG_IAVF) += iavf.o
iavf-y := iavf_main.o iavf_ethtool.o iavf_virtchnl.o iavf_fdir.o \
iavf_adv_rss.o iavf_txrx.o iavf_common.o iavf_adminq.o
+
+iavf-$(CONFIG_PTP_1588_CLOCK) += iavf_ptp.o
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index 532a0a595fe8..9de3e0ba3731 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -41,6 +41,7 @@
#include "iavf_txrx.h"
#include "iavf_fdir.h"
#include "iavf_adv_rss.h"
+#include "iavf_types.h"
#include <linux/bitmap.h>
#define DEFAULT_DEBUG_LEVEL_SHIFT 3
@@ -82,7 +83,7 @@ struct iavf_vsi {
#define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)
-#define IAVF_RX_DESC(R, i) (&(((union iavf_32byte_rx_desc *)((R)->desc))[i]))
+#define IAVF_RX_DESC(R, i) (&(((struct iavf_rx_desc *)((R)->desc))[i]))
#define IAVF_TX_DESC(R, i) (&(((struct iavf_tx_desc *)((R)->desc))[i]))
#define IAVF_TX_CTXTDESC(R, i) \
(&(((struct iavf_tx_context_desc *)((R)->desc))[i]))
@@ -271,6 +272,7 @@ struct iavf_adapter {
/* Lock to protect accesses to MAC and VLAN lists */
spinlock_t mac_vlan_list_lock;
char misc_vector_name[IFNAMSIZ + 9];
+ u8 rxdid;
int num_active_queues;
int num_req_queues;
@@ -343,6 +345,17 @@ struct iavf_adapter {
#define IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW BIT_ULL(39)
#define IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE BIT_ULL(40)
#define IAVF_FLAG_AQ_GET_QOS_CAPS BIT_ULL(41)
+#define IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS BIT_ULL(42)
+#define IAVF_FLAG_AQ_GET_PTP_CAPS BIT_ULL(43)
+#define IAVF_FLAG_AQ_SEND_PTP_CMD BIT_ULL(44)
+
+ /* AQ messages that must be sent after IAVF_FLAG_AQ_GET_CONFIG, in
+ * order to negotiated extended capabilities.
+ */
+#define IAVF_FLAG_AQ_EXTENDED_CAPS \
+ (IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS | \
+ IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS | \
+ IAVF_FLAG_AQ_GET_PTP_CAPS)
/* flags for processing extended capability messages during
* __IAVF_INIT_EXTENDED_CAPS. Each capability exchange requires
@@ -354,10 +367,18 @@ struct iavf_adapter {
u64 extended_caps;
#define IAVF_EXTENDED_CAP_SEND_VLAN_V2 BIT_ULL(0)
#define IAVF_EXTENDED_CAP_RECV_VLAN_V2 BIT_ULL(1)
+#define IAVF_EXTENDED_CAP_SEND_RXDID BIT_ULL(2)
+#define IAVF_EXTENDED_CAP_RECV_RXDID BIT_ULL(3)
+#define IAVF_EXTENDED_CAP_SEND_PTP BIT_ULL(4)
+#define IAVF_EXTENDED_CAP_RECV_PTP BIT_ULL(5)
#define IAVF_EXTENDED_CAPS \
(IAVF_EXTENDED_CAP_SEND_VLAN_V2 | \
- IAVF_EXTENDED_CAP_RECV_VLAN_V2)
+ IAVF_EXTENDED_CAP_RECV_VLAN_V2 | \
+ IAVF_EXTENDED_CAP_SEND_RXDID | \
+ IAVF_EXTENDED_CAP_RECV_RXDID | \
+ IAVF_EXTENDED_CAP_SEND_PTP | \
+ IAVF_EXTENDED_CAP_RECV_PTP)
/* Lock to prevent possible clobbering of
* current_netdev_promisc_flags
@@ -417,12 +438,18 @@ struct iavf_adapter {
VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF)
#define QOS_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \
VIRTCHNL_VF_OFFLOAD_QOS)
+#define IAVF_RXDID_ALLOWED(a) \
+ ((a)->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC)
+#define IAVF_PTP_ALLOWED(a) \
+ ((a)->vf_res->vf_cap_flags & VIRTCHNL_VF_CAP_PTP)
struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */
struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */
struct virtchnl_version_info pf_version;
#define PF_IS_V11(_a) (((_a)->pf_version.major == 1) && \
((_a)->pf_version.minor == 1))
struct virtchnl_vlan_caps vlan_v2_caps;
+ u64 supp_rxdids;
+ struct iavf_ptp ptp;
u16 msg_enable;
struct iavf_eth_stats current_stats;
struct virtchnl_qos_cap_list *qos_caps;
@@ -555,6 +582,10 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter);
int iavf_get_vf_config(struct iavf_adapter *adapter);
int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter);
int iavf_send_vf_offload_vlan_v2_msg(struct iavf_adapter *adapter);
+int iavf_send_vf_supported_rxdids_msg(struct iavf_adapter *adapter);
+int iavf_get_vf_supported_rxdids(struct iavf_adapter *adapter);
+int iavf_send_vf_ptp_caps_msg(struct iavf_adapter *adapter);
+int iavf_get_vf_ptp_caps(struct iavf_adapter *adapter);
void iavf_set_queue_vlan_tag_loc(struct iavf_adapter *adapter);
u16 iavf_get_num_vlans_added(struct iavf_adapter *adapter);
void iavf_irq_enable(struct iavf_adapter *adapter, bool flush);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index 74a1e9fe1821..288bb5b2e72e 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -1808,7 +1808,7 @@ static int iavf_set_rxfh(struct net_device *netdev,
static const struct ethtool_ops iavf_ethtool_ops = {
.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
ETHTOOL_COALESCE_USE_ADAPTIVE,
- .cap_rss_sym_xor_supported = true,
+ .supported_input_xfrm = RXH_XFRM_SYM_XOR,
.get_drvinfo = iavf_get_drvinfo,
.get_link = ethtool_op_get_link,
.get_ringparam = iavf_get_ringparam,
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 6faa62bced3a..6d7ba4d67a19 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -2,8 +2,10 @@
/* Copyright(c) 2013 - 2018 Intel Corporation. */
#include <linux/net/intel/libie/rx.h>
+#include <net/netdev_lock.h>
#include "iavf.h"
+#include "iavf_ptp.h"
#include "iavf_prototype.h"
/* All iavf tracepoints are defined by the include below, which must
* be included exactly once across the whole kernel with
@@ -710,6 +712,47 @@ static void iavf_configure_tx(struct iavf_adapter *adapter)
}
/**
+ * iavf_select_rx_desc_format - Select Rx descriptor format
+ * @adapter: adapter private structure
+ *
+ * Select what Rx descriptor format based on availability and enabled
+ * features.
+ *
+ * Return: the desired RXDID to select for a given Rx queue, as defined by
+ * enum virtchnl_rxdid_format.
+ */
+static u8 iavf_select_rx_desc_format(const struct iavf_adapter *adapter)
+{
+ u64 rxdids = adapter->supp_rxdids;
+
+ /* If we did not negotiate VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC, we must
+ * stick with the default value of the legacy 32 byte format.
+ */
+ if (!IAVF_RXDID_ALLOWED(adapter))
+ return VIRTCHNL_RXDID_1_32B_BASE;
+
+ /* Rx timestamping requires the use of flexible NIC descriptors */
+ if (iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP)) {
+ if (rxdids & BIT(VIRTCHNL_RXDID_2_FLEX_SQ_NIC))
+ return VIRTCHNL_RXDID_2_FLEX_SQ_NIC;
+
+ pci_warn(adapter->pdev,
+ "Unable to negotiate flexible descriptor format\n");
+ }
+
+ /* Warn if the PF does not list support for the default legacy
+ * descriptor format. This shouldn't happen, as this is the format
+ * used if VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC is not supported. It is
+ * likely caused by a bug in the PF implementation failing to indicate
+ * support for the format.
+ */
+ if (!(rxdids & VIRTCHNL_RXDID_1_32B_BASE_M))
+ netdev_warn(adapter->netdev, "PF does not list support for default Rx descriptor format\n");
+
+ return VIRTCHNL_RXDID_1_32B_BASE;
+}
+
+/**
* iavf_configure_rx - Configure Receive Unit after Reset
* @adapter: board private structure
*
@@ -719,8 +762,12 @@ static void iavf_configure_rx(struct iavf_adapter *adapter)
{
struct iavf_hw *hw = &adapter->hw;
- for (u32 i = 0; i < adapter->num_active_queues; i++)
+ adapter->rxdid = iavf_select_rx_desc_format(adapter);
+
+ for (u32 i = 0; i < adapter->num_active_queues; i++) {
adapter->rx_rings[i].tail = hw->hw_addr + IAVF_QRX_TAIL1(i);
+ adapter->rx_rings[i].rxdid = adapter->rxdid;
+ }
}
/**
@@ -2075,6 +2122,10 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter)
return iavf_send_vf_config_msg(adapter);
if (adapter->aq_required & IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS)
return iavf_send_vf_offload_vlan_v2_msg(adapter);
+ if (adapter->aq_required & IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS)
+ return iavf_send_vf_supported_rxdids_msg(adapter);
+ if (adapter->aq_required & IAVF_FLAG_AQ_GET_PTP_CAPS)
+ return iavf_send_vf_ptp_caps_msg(adapter);
if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_QUEUES) {
iavf_disable_queues(adapter);
return 0;
@@ -2239,7 +2290,10 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter)
iavf_enable_vlan_insertion_v2(adapter, ETH_P_8021AD);
return 0;
}
-
+ if (adapter->aq_required & IAVF_FLAG_AQ_SEND_PTP_CMD) {
+ iavf_virtchnl_send_ptp_cmd(adapter);
+ return IAVF_SUCCESS;
+ }
if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_STATS) {
iavf_request_stats(adapter);
return 0;
@@ -2604,6 +2658,112 @@ err:
}
/**
+ * iavf_init_send_supported_rxdids - part of querying for supported RXDID
+ * formats
+ * @adapter: board private structure
+ *
+ * Function processes send of the request for supported RXDIDs to the PF.
+ * Must clear IAVF_EXTENDED_CAP_RECV_RXDID if the message is not sent, e.g.
+ * due to the PF not negotiating VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC.
+ */
+static void iavf_init_send_supported_rxdids(struct iavf_adapter *adapter)
+{
+ int ret;
+
+ ret = iavf_send_vf_supported_rxdids_msg(adapter);
+ if (ret == -EOPNOTSUPP) {
+ /* PF does not support VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC. In this
+ * case, we did not send the capability exchange message and
+ * do not expect a response.
+ */
+ adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_RXDID;
+ }
+
+ /* We sent the message, so move on to the next step */
+ adapter->extended_caps &= ~IAVF_EXTENDED_CAP_SEND_RXDID;
+}
+
+/**
+ * iavf_init_recv_supported_rxdids - part of querying for supported RXDID
+ * formats
+ * @adapter: board private structure
+ *
+ * Function processes receipt of the supported RXDIDs message from the PF.
+ **/
+static void iavf_init_recv_supported_rxdids(struct iavf_adapter *adapter)
+{
+ int ret;
+
+ memset(&adapter->supp_rxdids, 0, sizeof(adapter->supp_rxdids));
+
+ ret = iavf_get_vf_supported_rxdids(adapter);
+ if (ret)
+ goto err;
+
+ /* We've processed the PF response to the
+ * VIRTCHNL_OP_GET_SUPPORTED_RXDIDS message we sent previously.
+ */
+ adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_RXDID;
+ return;
+
+err:
+ /* We didn't receive a reply. Make sure we try sending again when
+ * __IAVF_INIT_FAILED attempts to recover.
+ */
+ adapter->extended_caps |= IAVF_EXTENDED_CAP_SEND_RXDID;
+ iavf_change_state(adapter, __IAVF_INIT_FAILED);
+}
+
+/**
+ * iavf_init_send_ptp_caps - part of querying for extended PTP capabilities
+ * @adapter: board private structure
+ *
+ * Function processes send of the request for 1588 PTP capabilities to the PF.
+ * Must clear IAVF_EXTENDED_CAP_SEND_PTP if the message is not sent, e.g.
+ * due to the PF not negotiating VIRTCHNL_VF_PTP_CAP
+ */
+static void iavf_init_send_ptp_caps(struct iavf_adapter *adapter)
+{
+ if (iavf_send_vf_ptp_caps_msg(adapter) == -EOPNOTSUPP) {
+ /* PF does not support VIRTCHNL_VF_PTP_CAP. In this case, we
+ * did not send the capability exchange message and do not
+ * expect a response.
+ */
+ adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_PTP;
+ }
+
+ /* We sent the message, so move on to the next step */
+ adapter->extended_caps &= ~IAVF_EXTENDED_CAP_SEND_PTP;
+}
+
+/**
+ * iavf_init_recv_ptp_caps - part of querying for supported PTP capabilities
+ * @adapter: board private structure
+ *
+ * Function processes receipt of the PTP capabilities supported on this VF.
+ **/
+static void iavf_init_recv_ptp_caps(struct iavf_adapter *adapter)
+{
+ memset(&adapter->ptp.hw_caps, 0, sizeof(adapter->ptp.hw_caps));
+
+ if (iavf_get_vf_ptp_caps(adapter))
+ goto err;
+
+ /* We've processed the PF response to the VIRTCHNL_OP_1588_PTP_GET_CAPS
+ * message we sent previously.
+ */
+ adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_PTP;
+ return;
+
+err:
+ /* We didn't receive a reply. Make sure we try sending again when
+ * __IAVF_INIT_FAILED attempts to recover.
+ */
+ adapter->extended_caps |= IAVF_EXTENDED_CAP_SEND_PTP;
+ iavf_change_state(adapter, __IAVF_INIT_FAILED);
+}
+
+/**
* iavf_init_process_extended_caps - Part of driver startup
* @adapter: board private structure
*
@@ -2627,6 +2787,24 @@ static void iavf_init_process_extended_caps(struct iavf_adapter *adapter)
return;
}
+ /* Process capability exchange for RXDID formats */
+ if (adapter->extended_caps & IAVF_EXTENDED_CAP_SEND_RXDID) {
+ iavf_init_send_supported_rxdids(adapter);
+ return;
+ } else if (adapter->extended_caps & IAVF_EXTENDED_CAP_RECV_RXDID) {
+ iavf_init_recv_supported_rxdids(adapter);
+ return;
+ }
+
+ /* Process capability exchange for PTP features */
+ if (adapter->extended_caps & IAVF_EXTENDED_CAP_SEND_PTP) {
+ iavf_init_send_ptp_caps(adapter);
+ return;
+ } else if (adapter->extended_caps & IAVF_EXTENDED_CAP_RECV_PTP) {
+ iavf_init_recv_ptp_caps(adapter);
+ return;
+ }
+
/* When we reach here, no further extended capabilities exchanges are
* necessary, so we finally transition into __IAVF_INIT_CONFIG_ADAPTER
*/
@@ -2718,6 +2896,9 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter)
if (QOS_ALLOWED(adapter))
adapter->aq_required |= IAVF_FLAG_AQ_GET_QOS_CAPS;
+ /* Setup initial PTP configuration */
+ iavf_ptp_init(adapter);
+
iavf_schedule_finish_config(adapter);
return;
@@ -3143,15 +3324,18 @@ continue_reset:
}
adapter->aq_required |= IAVF_FLAG_AQ_GET_CONFIG;
- /* always set since VIRTCHNL_OP_GET_VF_RESOURCES has not been
- * sent/received yet, so VLAN_V2_ALLOWED() cannot is not reliable here,
- * however the VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS won't be sent until
- * VIRTCHNL_OP_GET_VF_RESOURCES and VIRTCHNL_VF_OFFLOAD_VLAN_V2 have
- * been successfully sent and negotiated
- */
- adapter->aq_required |= IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS;
adapter->aq_required |= IAVF_FLAG_AQ_MAP_VECTORS;
+ /* Certain capabilities require an extended negotiation process using
+ * extra messages that must be processed after getting the VF
+ * configuration. The related checks such as VLAN_V2_ALLOWED() are not
+ * reliable here, since the configuration has not yet been negotiated.
+ *
+ * Always set these flags, since them related VIRTCHNL messages won't
+ * be sent until after VIRTCHNL_OP_GET_VF_RESOURCES.
+ */
+ adapter->aq_required |= IAVF_FLAG_AQ_EXTENDED_CAPS;
+
spin_lock_bh(&adapter->mac_vlan_list_lock);
/* Delete filter for the current MAC address, it could have
@@ -3711,10 +3895,8 @@ exit:
if (test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section))
return 0;
- netdev_lock(netdev);
netif_set_real_num_rx_queues(netdev, total_qps);
netif_set_real_num_tx_queues(netdev, total_qps);
- netdev_unlock(netdev);
return ret;
}
@@ -4379,22 +4561,21 @@ static int iavf_open(struct net_device *netdev)
struct iavf_adapter *adapter = netdev_priv(netdev);
int err;
+ netdev_assert_locked(netdev);
+
if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) {
dev_err(&adapter->pdev->dev, "Unable to open device due to PF driver failure.\n");
return -EIO;
}
- netdev_lock(netdev);
while (!mutex_trylock(&adapter->crit_lock)) {
/* If we are in __IAVF_INIT_CONFIG_ADAPTER state the crit_lock
* is already taken and iavf_open is called from an upper
* device's notifier reacting on NETDEV_REGISTER event.
* We have to leave here to avoid dead lock.
*/
- if (adapter->state == __IAVF_INIT_CONFIG_ADAPTER) {
- netdev_unlock(netdev);
+ if (adapter->state == __IAVF_INIT_CONFIG_ADAPTER)
return -EBUSY;
- }
usleep_range(500, 1000);
}
@@ -4443,7 +4624,6 @@ static int iavf_open(struct net_device *netdev)
iavf_irq_enable(adapter, true);
mutex_unlock(&adapter->crit_lock);
- netdev_unlock(netdev);
return 0;
@@ -4456,7 +4636,6 @@ err_setup_tx:
iavf_free_all_tx_resources(adapter);
err_unlock:
mutex_unlock(&adapter->crit_lock);
- netdev_unlock(netdev);
return err;
}
@@ -4478,12 +4657,12 @@ static int iavf_close(struct net_device *netdev)
u64 aq_to_restore;
int status;
- netdev_lock(netdev);
+ netdev_assert_locked(netdev);
+
mutex_lock(&adapter->crit_lock);
if (adapter->state <= __IAVF_DOWN_PENDING) {
mutex_unlock(&adapter->crit_lock);
- netdev_unlock(netdev);
return 0;
}
@@ -4536,6 +4715,7 @@ static int iavf_close(struct net_device *netdev)
if (!status)
netdev_warn(netdev, "Device resources not yet released\n");
+ netdev_lock(netdev);
mutex_lock(&adapter->crit_lock);
adapter->aq_required |= aq_to_restore;
mutex_unlock(&adapter->crit_lock);
@@ -5000,6 +5180,25 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev,
return iavf_fix_strip_features(adapter, features);
}
+static int iavf_hwstamp_get(struct net_device *netdev,
+ struct kernel_hwtstamp_config *config)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
+ *config = adapter->ptp.hwtstamp_config;
+
+ return 0;
+}
+
+static int iavf_hwstamp_set(struct net_device *netdev,
+ struct kernel_hwtstamp_config *config,
+ struct netlink_ext_ack *extack)
+{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
+ return iavf_ptp_set_ts_config(adapter, config, extack);
+}
+
static int
iavf_verify_shaper(struct net_shaper_binding *binding,
const struct net_shaper *shaper,
@@ -5108,6 +5307,8 @@ static const struct net_device_ops iavf_netdev_ops = {
.ndo_set_features = iavf_set_features,
.ndo_setup_tc = iavf_setup_tc,
.net_shaper_ops = &iavf_shaper_ops,
+ .ndo_hwtstamp_get = iavf_hwstamp_get,
+ .ndo_hwtstamp_set = iavf_hwstamp_set,
};
/**
@@ -5362,6 +5563,10 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
/* Setup the wait queue for indicating virtchannel events */
init_waitqueue_head(&adapter->vc_waitqueue);
+ INIT_LIST_HEAD(&adapter->ptp.aq_cmds);
+ init_waitqueue_head(&adapter->ptp.phc_time_waitqueue);
+ mutex_init(&adapter->ptp.aq_cmd_lock);
+
queue_delayed_work(adapter->wq, &adapter->watchdog_task,
msecs_to_jiffies(5 * (pdev->devfn & 0x07)));
/* Initialization goes on in the work. Do not add more of it below. */
@@ -5518,6 +5723,8 @@ static void iavf_remove(struct pci_dev *pdev)
msleep(50);
}
+ iavf_ptp_release(adapter);
+
iavf_misc_irq_disable(adapter);
/* Shut down all the garbage mashers on the detention level */
cancel_work_sync(&adapter->reset_task);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.c b/drivers/net/ethernet/intel/iavf/iavf_ptp.c
new file mode 100644
index 000000000000..b4d5eda2e84f
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.c
@@ -0,0 +1,485 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2024 Intel Corporation. */
+
+#include "iavf.h"
+#include "iavf_ptp.h"
+
+#define iavf_clock_to_adapter(info) \
+ container_of_const(info, struct iavf_adapter, ptp.info)
+
+/**
+ * iavf_ptp_disable_rx_tstamp - Disable timestamping in Rx rings
+ * @adapter: private adapter structure
+ *
+ * Disable timestamp reporting for all Rx rings.
+ */
+static void iavf_ptp_disable_rx_tstamp(struct iavf_adapter *adapter)
+{
+ for (u32 i = 0; i < adapter->num_active_queues; i++)
+ adapter->rx_rings[i].flags &= ~IAVF_TXRX_FLAGS_HW_TSTAMP;
+}
+
+/**
+ * iavf_ptp_enable_rx_tstamp - Enable timestamping in Rx rings
+ * @adapter: private adapter structure
+ *
+ * Enable timestamp reporting for all Rx rings.
+ */
+static void iavf_ptp_enable_rx_tstamp(struct iavf_adapter *adapter)
+{
+ for (u32 i = 0; i < adapter->num_active_queues; i++)
+ adapter->rx_rings[i].flags |= IAVF_TXRX_FLAGS_HW_TSTAMP;
+}
+
+/**
+ * iavf_ptp_set_timestamp_mode - Set device timestamping mode
+ * @adapter: private adapter structure
+ * @config: pointer to kernel_hwtstamp_config
+ *
+ * Set the timestamping mode requested from the userspace.
+ *
+ * Note: this function always translates Rx timestamp requests for any packet
+ * category into HWTSTAMP_FILTER_ALL.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+static int iavf_ptp_set_timestamp_mode(struct iavf_adapter *adapter,
+ struct kernel_hwtstamp_config *config)
+{
+ /* Reserved for future extensions. */
+ if (config->flags)
+ return -EINVAL;
+
+ switch (config->tx_type) {
+ case HWTSTAMP_TX_OFF:
+ break;
+ case HWTSTAMP_TX_ON:
+ return -EOPNOTSUPP;
+ default:
+ return -ERANGE;
+ }
+
+ if (config->rx_filter == HWTSTAMP_FILTER_NONE) {
+ iavf_ptp_disable_rx_tstamp(adapter);
+ return 0;
+ } else if (config->rx_filter > HWTSTAMP_FILTER_NTP_ALL) {
+ return -ERANGE;
+ } else if (!(iavf_ptp_cap_supported(adapter,
+ VIRTCHNL_1588_PTP_CAP_RX_TSTAMP))) {
+ return -EOPNOTSUPP;
+ }
+
+ config->rx_filter = HWTSTAMP_FILTER_ALL;
+ iavf_ptp_enable_rx_tstamp(adapter);
+
+ return 0;
+}
+
+/**
+ * iavf_ptp_set_ts_config - Set timestamping configuration
+ * @adapter: private adapter structure
+ * @config: pointer to kernel_hwtstamp_config structure
+ * @extack: pointer to netlink_ext_ack structure
+ *
+ * Program the requested timestamping configuration to the device.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int iavf_ptp_set_ts_config(struct iavf_adapter *adapter,
+ struct kernel_hwtstamp_config *config,
+ struct netlink_ext_ack *extack)
+{
+ int err;
+
+ err = iavf_ptp_set_timestamp_mode(adapter, config);
+ if (err)
+ return err;
+
+ /* Save successful settings for future reference */
+ adapter->ptp.hwtstamp_config = *config;
+
+ return 0;
+}
+
+/**
+ * iavf_ptp_cap_supported - Check if a PTP capability is supported
+ * @adapter: private adapter structure
+ * @cap: the capability bitmask to check
+ *
+ * Return: true if every capability set in cap is also set in the enabled
+ * capabilities reported by the PF, false otherwise.
+ */
+bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, u32 cap)
+{
+ if (!IAVF_PTP_ALLOWED(adapter))
+ return false;
+
+ /* Only return true if every bit in cap is set in hw_caps.caps */
+ return (adapter->ptp.hw_caps.caps & cap) == cap;
+}
+
+/**
+ * iavf_allocate_ptp_cmd - Allocate a PTP command message structure
+ * @v_opcode: the virtchnl opcode
+ * @msglen: length in bytes of the associated virtchnl structure
+ *
+ * Allocates a PTP command message and pre-fills it with the provided message
+ * length and opcode.
+ *
+ * Return: allocated PTP command.
+ */
+static struct iavf_ptp_aq_cmd *iavf_allocate_ptp_cmd(enum virtchnl_ops v_opcode,
+ u16 msglen)
+{
+ struct iavf_ptp_aq_cmd *cmd;
+
+ cmd = kzalloc(struct_size(cmd, msg, msglen), GFP_KERNEL);
+ if (!cmd)
+ return NULL;
+
+ cmd->v_opcode = v_opcode;
+ cmd->msglen = msglen;
+
+ return cmd;
+}
+
+/**
+ * iavf_queue_ptp_cmd - Queue PTP command for sending over virtchnl
+ * @adapter: private adapter structure
+ * @cmd: the command structure to send
+ *
+ * Queue the given command structure into the PTP virtchnl command queue tos
+ * end to the PF.
+ */
+static void iavf_queue_ptp_cmd(struct iavf_adapter *adapter,
+ struct iavf_ptp_aq_cmd *cmd)
+{
+ mutex_lock(&adapter->ptp.aq_cmd_lock);
+ list_add_tail(&cmd->list, &adapter->ptp.aq_cmds);
+ mutex_unlock(&adapter->ptp.aq_cmd_lock);
+
+ adapter->aq_required |= IAVF_FLAG_AQ_SEND_PTP_CMD;
+ mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
+}
+
+/**
+ * iavf_send_phc_read - Send request to read PHC time
+ * @adapter: private adapter structure
+ *
+ * Send a request to obtain the PTP hardware clock time. This allocates the
+ * VIRTCHNL_OP_1588_PTP_GET_TIME message and queues it up to send to
+ * indirectly read the PHC time.
+ *
+ * This function does not wait for the reply from the PF.
+ *
+ * Return: 0 if success, error code otherwise.
+ */
+static int iavf_send_phc_read(struct iavf_adapter *adapter)
+{
+ struct iavf_ptp_aq_cmd *cmd;
+
+ if (!adapter->ptp.clock)
+ return -EOPNOTSUPP;
+
+ cmd = iavf_allocate_ptp_cmd(VIRTCHNL_OP_1588_PTP_GET_TIME,
+ sizeof(struct virtchnl_phc_time));
+ if (!cmd)
+ return -ENOMEM;
+
+ iavf_queue_ptp_cmd(adapter, cmd);
+
+ return 0;
+}
+
+/**
+ * iavf_read_phc_indirect - Indirectly read the PHC time via virtchnl
+ * @adapter: private adapter structure
+ * @ts: storage for the timestamp value
+ * @sts: system timestamp values before and after the read
+ *
+ * Used when the device does not have direct register access to the PHC time.
+ * Indirectly reads the time via the VIRTCHNL_OP_1588_PTP_GET_TIME, and waits
+ * for the reply from the PF.
+ *
+ * Based on some simple measurements using ftrace and phc2sys, this clock
+ * access method has about a ~110 usec latency even when the system is not
+ * under load. In order to achieve acceptable results when using phc2sys with
+ * the indirect clock access method, it is recommended to use more
+ * conservative proportional and integration constants with the P/I servo.
+ *
+ * Return: 0 if success, error code otherwise.
+ */
+static int iavf_read_phc_indirect(struct iavf_adapter *adapter,
+ struct timespec64 *ts,
+ struct ptp_system_timestamp *sts)
+{
+ long ret;
+ int err;
+
+ adapter->ptp.phc_time_ready = false;
+
+ ptp_read_system_prets(sts);
+
+ err = iavf_send_phc_read(adapter);
+ if (err)
+ return err;
+
+ ret = wait_event_interruptible_timeout(adapter->ptp.phc_time_waitqueue,
+ adapter->ptp.phc_time_ready,
+ HZ);
+
+ ptp_read_system_postts(sts);
+
+ if (ret < 0)
+ return ret;
+ else if (!ret)
+ return -EBUSY;
+
+ *ts = ns_to_timespec64(adapter->ptp.cached_phc_time);
+
+ return 0;
+}
+
+static int iavf_ptp_gettimex64(struct ptp_clock_info *info,
+ struct timespec64 *ts,
+ struct ptp_system_timestamp *sts)
+{
+ struct iavf_adapter *adapter = iavf_clock_to_adapter(info);
+
+ if (!adapter->ptp.clock)
+ return -EOPNOTSUPP;
+
+ return iavf_read_phc_indirect(adapter, ts, sts);
+}
+
+/**
+ * iavf_ptp_cache_phc_time - Cache PHC time for performing timestamp extension
+ * @adapter: private adapter structure
+ *
+ * Periodically cache the PHC time in order to allow for timestamp extension.
+ * This is required because the Tx and Rx timestamps only contain 32bits of
+ * nanoseconds. Timestamp extension allows calculating the corrected 64bit
+ * timestamp. This algorithm relies on the cached time being within ~1 second
+ * of the timestamp.
+ */
+static void iavf_ptp_cache_phc_time(struct iavf_adapter *adapter)
+{
+ if (!time_is_before_jiffies(adapter->ptp.cached_phc_updated + HZ))
+ return;
+
+ /* The response from virtchnl will store the time into
+ * cached_phc_time.
+ */
+ iavf_send_phc_read(adapter);
+}
+
+/**
+ * iavf_ptp_do_aux_work - Perform periodic work required for PTP support
+ * @info: PTP clock info structure
+ *
+ * Handler to take care of periodic work required for PTP operation. This
+ * includes the following tasks:
+ *
+ * 1) updating cached_phc_time
+ *
+ * cached_phc_time is used by the Tx and Rx timestamp flows in order to
+ * perform timestamp extension, by carefully comparing the timestamp
+ * 32bit nanosecond timestamps and determining the corrected 64bit
+ * timestamp value to report to userspace. This algorithm only works if
+ * the cached_phc_time is within ~1 second of the Tx or Rx timestamp
+ * event. This task periodically reads the PHC time and stores it, to
+ * ensure that timestamp extension operates correctly.
+ *
+ * Returns: time in jiffies until the periodic task should be re-scheduled.
+ */
+static long iavf_ptp_do_aux_work(struct ptp_clock_info *info)
+{
+ struct iavf_adapter *adapter = iavf_clock_to_adapter(info);
+
+ iavf_ptp_cache_phc_time(adapter);
+
+ /* Check work about twice a second */
+ return msecs_to_jiffies(500);
+}
+
+/**
+ * iavf_ptp_register_clock - Register a new PTP for userspace
+ * @adapter: private adapter structure
+ *
+ * Allocate and register a new PTP clock device if necessary.
+ *
+ * Return: 0 if success, error otherwise.
+ */
+static int iavf_ptp_register_clock(struct iavf_adapter *adapter)
+{
+ struct ptp_clock_info *ptp_info = &adapter->ptp.info;
+ struct device *dev = &adapter->pdev->dev;
+ struct ptp_clock *clock;
+
+ snprintf(ptp_info->name, sizeof(ptp_info->name), "%s-%s-clk",
+ KBUILD_MODNAME, dev_name(dev));
+ ptp_info->owner = THIS_MODULE;
+ ptp_info->gettimex64 = iavf_ptp_gettimex64;
+ ptp_info->do_aux_work = iavf_ptp_do_aux_work;
+
+ clock = ptp_clock_register(ptp_info, dev);
+ if (IS_ERR(clock))
+ return PTR_ERR(clock);
+
+ adapter->ptp.clock = clock;
+
+ dev_dbg(&adapter->pdev->dev, "PTP clock %s registered\n",
+ adapter->ptp.info.name);
+
+ return 0;
+}
+
+/**
+ * iavf_ptp_init - Initialize PTP support if capability was negotiated
+ * @adapter: private adapter structure
+ *
+ * Initialize PTP functionality, based on the capabilities that the PF has
+ * enabled for this VF.
+ */
+void iavf_ptp_init(struct iavf_adapter *adapter)
+{
+ int err;
+
+ if (!iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_READ_PHC)) {
+ pci_notice(adapter->pdev,
+ "Device does not have PTP clock support\n");
+ return;
+ }
+
+ err = iavf_ptp_register_clock(adapter);
+ if (err) {
+ pci_err(adapter->pdev,
+ "Failed to register PTP clock device (%p)\n",
+ ERR_PTR(err));
+ return;
+ }
+
+ for (int i = 0; i < adapter->num_active_queues; i++) {
+ struct iavf_ring *rx_ring = &adapter->rx_rings[i];
+
+ rx_ring->ptp = &adapter->ptp;
+ }
+
+ ptp_schedule_worker(adapter->ptp.clock, 0);
+}
+
+/**
+ * iavf_ptp_release - Disable PTP support
+ * @adapter: private adapter structure
+ *
+ * Release all PTP resources that were previously initialized.
+ */
+void iavf_ptp_release(struct iavf_adapter *adapter)
+{
+ struct iavf_ptp_aq_cmd *cmd, *tmp;
+
+ if (!adapter->ptp.clock)
+ return;
+
+ pci_dbg(adapter->pdev, "removing PTP clock %s\n",
+ adapter->ptp.info.name);
+ ptp_clock_unregister(adapter->ptp.clock);
+ adapter->ptp.clock = NULL;
+
+ /* Cancel any remaining uncompleted PTP clock commands */
+ mutex_lock(&adapter->ptp.aq_cmd_lock);
+ list_for_each_entry_safe(cmd, tmp, &adapter->ptp.aq_cmds, list) {
+ list_del(&cmd->list);
+ kfree(cmd);
+ }
+ adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD;
+ mutex_unlock(&adapter->ptp.aq_cmd_lock);
+
+ adapter->ptp.hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+ iavf_ptp_disable_rx_tstamp(adapter);
+}
+
+/**
+ * iavf_ptp_process_caps - Handle change in PTP capabilities
+ * @adapter: private adapter structure
+ *
+ * Handle any state changes necessary due to change in PTP capabilities, such
+ * as after a device reset or change in configuration from the PF.
+ */
+void iavf_ptp_process_caps(struct iavf_adapter *adapter)
+{
+ bool phc = iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_READ_PHC);
+
+ /* Check if the device gained or lost necessary access to support the
+ * PTP hardware clock. If so, driver must respond appropriately by
+ * creating or destroying the PTP clock device.
+ */
+ if (adapter->ptp.clock && !phc)
+ iavf_ptp_release(adapter);
+ else if (!adapter->ptp.clock && phc)
+ iavf_ptp_init(adapter);
+
+ /* Check if the device lost access to Rx timestamp incoming packets */
+ if (!iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP)) {
+ adapter->ptp.hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+ iavf_ptp_disable_rx_tstamp(adapter);
+ }
+}
+
+/**
+ * iavf_ptp_extend_32b_timestamp - Convert a 32b nanoseconds timestamp to 64b
+ * nanoseconds
+ * @cached_phc_time: recently cached copy of PHC time
+ * @in_tstamp: Ingress/egress 32b nanoseconds timestamp value
+ *
+ * Hardware captures timestamps which contain only 32 bits of nominal
+ * nanoseconds, as opposed to the 64bit timestamps that the stack expects.
+ *
+ * Extend the 32bit nanosecond timestamp using the following algorithm and
+ * assumptions:
+ *
+ * 1) have a recently cached copy of the PHC time
+ * 2) assume that the in_tstamp was captured 2^31 nanoseconds (~2.1
+ * seconds) before or after the PHC time was captured.
+ * 3) calculate the delta between the cached time and the timestamp
+ * 4) if the delta is smaller than 2^31 nanoseconds, then the timestamp was
+ * captured after the PHC time. In this case, the full timestamp is just
+ * the cached PHC time plus the delta.
+ * 5) otherwise, if the delta is larger than 2^31 nanoseconds, then the
+ * timestamp was captured *before* the PHC time, i.e. because the PHC
+ * cache was updated after the timestamp was captured by hardware. In this
+ * case, the full timestamp is the cached time minus the inverse delta.
+ *
+ * This algorithm works even if the PHC time was updated after a Tx timestamp
+ * was requested, but before the Tx timestamp event was reported from
+ * hardware.
+ *
+ * This calculation primarily relies on keeping the cached PHC time up to
+ * date. If the timestamp was captured more than 2^31 nanoseconds after the
+ * PHC time, it is possible that the lower 32bits of PHC time have
+ * overflowed more than once, and we might generate an incorrect timestamp.
+ *
+ * This is prevented by (a) periodically updating the cached PHC time once
+ * a second, and (b) discarding any Tx timestamp packet if it has waited for
+ * a timestamp for more than one second.
+ *
+ * Return: extended timestamp (to 64b).
+ */
+u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time, u32 in_tstamp)
+{
+ u32 low = lower_32_bits(cached_phc_time);
+ u32 delta = in_tstamp - low;
+ u64 ns;
+
+ /* Do not assume that the in_tstamp is always more recent than the
+ * cached PHC time. If the delta is large, it indicates that the
+ * in_tstamp was taken in the past, and should be converted
+ * forward.
+ */
+ if (delta > S32_MAX)
+ ns = cached_phc_time - (low - in_tstamp);
+ else
+ ns = cached_phc_time + delta;
+
+ return ns;
+}
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.h b/drivers/net/ethernet/intel/iavf/iavf_ptp.h
new file mode 100644
index 000000000000..783b8f287cd9
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024 Intel Corporation. */
+
+#ifndef _IAVF_PTP_H_
+#define _IAVF_PTP_H_
+
+#include "iavf_types.h"
+
+/* bit indicating whether a 40bit timestamp is valid */
+#define IAVF_PTP_40B_TSTAMP_VALID BIT(24)
+
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
+void iavf_ptp_init(struct iavf_adapter *adapter);
+void iavf_ptp_release(struct iavf_adapter *adapter);
+void iavf_ptp_process_caps(struct iavf_adapter *adapter);
+bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, u32 cap);
+void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter);
+int iavf_ptp_set_ts_config(struct iavf_adapter *adapter,
+ struct kernel_hwtstamp_config *config,
+ struct netlink_ext_ack *extack);
+u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time, u32 in_tstamp);
+#else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
+static inline void iavf_ptp_init(struct iavf_adapter *adapter) { }
+static inline void iavf_ptp_release(struct iavf_adapter *adapter) { }
+static inline void iavf_ptp_process_caps(struct iavf_adapter *adapter) { }
+static inline bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter,
+ u32 cap)
+{
+ return false;
+}
+
+static inline void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter) { }
+static inline int iavf_ptp_set_ts_config(struct iavf_adapter *adapter,
+ struct kernel_hwtstamp_config *config,
+ struct netlink_ext_ack *extack)
+{
+ return -1;
+}
+
+static inline u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time,
+ u32 in_tstamp)
+{
+ return 0;
+}
+
+#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
+#endif /* _IAVF_PTP_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_trace.h b/drivers/net/ethernet/intel/iavf/iavf_trace.h
index 62212011c807..c5e4d1823886 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_trace.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_trace.h
@@ -112,7 +112,7 @@ DECLARE_EVENT_CLASS(
iavf_rx_template,
TP_PROTO(struct iavf_ring *ring,
- union iavf_32byte_rx_desc *desc,
+ struct iavf_rx_desc *desc,
struct sk_buff *skb),
TP_ARGS(ring, desc, skb),
@@ -140,7 +140,7 @@ DECLARE_EVENT_CLASS(
DEFINE_EVENT(
iavf_rx_template, iavf_clean_rx_irq,
TP_PROTO(struct iavf_ring *ring,
- union iavf_32byte_rx_desc *desc,
+ struct iavf_rx_desc *desc,
struct sk_buff *skb),
TP_ARGS(ring, desc, skb));
@@ -148,7 +148,7 @@ DEFINE_EVENT(
DEFINE_EVENT(
iavf_rx_template, iavf_clean_rx_irq_rx,
TP_PROTO(struct iavf_ring *ring,
- union iavf_32byte_rx_desc *desc,
+ struct iavf_rx_desc *desc,
struct sk_buff *skb),
TP_ARGS(ring, desc, skb));
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index 26b424fd6718..422312b8b54a 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -8,6 +8,26 @@
#include "iavf.h"
#include "iavf_trace.h"
#include "iavf_prototype.h"
+#include "iavf_ptp.h"
+
+/**
+ * iavf_is_descriptor_done - tests DD bit in Rx descriptor
+ * @qw1: quad word 1 from descriptor to get Descriptor Done field from
+ * @flex: is the descriptor flex or legacy
+ *
+ * This function tests the descriptor done bit in specified descriptor. Because
+ * there are two types of descriptors (legacy and flex) the parameter rx_ring
+ * is used to distinguish.
+ *
+ * Return: true or false based on the state of DD bit in Rx descriptor.
+ */
+static bool iavf_is_descriptor_done(u64 qw1, bool flex)
+{
+ if (flex)
+ return FIELD_GET(IAVF_RXD_FLEX_DD_M, qw1);
+ else
+ return FIELD_GET(IAVF_RXD_LEGACY_DD_M, qw1);
+}
static __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size,
u32 td_tag)
@@ -766,7 +786,7 @@ int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring)
u64_stats_init(&rx_ring->syncp);
/* Round up to nearest 4K */
- rx_ring->size = rx_ring->count * sizeof(union iavf_32byte_rx_desc);
+ rx_ring->size = rx_ring->count * sizeof(struct iavf_rx_desc);
rx_ring->size = ALIGN(rx_ring->size, 4096);
rx_ring->desc = dma_alloc_coherent(fq.pp->p.dev, rx_ring->size,
&rx_ring->dma, GFP_KERNEL);
@@ -845,7 +865,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count)
.count = rx_ring->count,
};
u16 ntu = rx_ring->next_to_use;
- union iavf_rx_desc *rx_desc;
+ struct iavf_rx_desc *rx_desc;
/* do nothing if no valid netdev defined */
if (!rx_ring->netdev || !cleaned_count)
@@ -863,7 +883,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count)
/* Refresh the desc even if buffer_addrs didn't change
* because each write-back erases this info.
*/
- rx_desc->read.pkt_addr = cpu_to_le64(addr);
+ rx_desc->qw0 = cpu_to_le64(addr);
rx_desc++;
ntu++;
@@ -873,7 +893,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count)
}
/* clear the status bits for the next_to_use descriptor */
- rx_desc->wb.qword1.status_error_len = 0;
+ rx_desc->qw1 = 0;
cleaned_count--;
} while (cleaned_count);
@@ -896,60 +916,43 @@ no_buffers:
}
/**
- * iavf_rx_checksum - Indicate in skb if hw indicated a good cksum
+ * iavf_rx_csum - Indicate in skb if hw indicated a good checksum
* @vsi: the VSI we care about
* @skb: skb currently being received and modified
- * @rx_desc: the receive descriptor
+ * @decoded_pt: decoded ptype information
+ * @csum_bits: decoded Rx descriptor information
**/
-static void iavf_rx_checksum(struct iavf_vsi *vsi,
- struct sk_buff *skb,
- union iavf_rx_desc *rx_desc)
+static void iavf_rx_csum(const struct iavf_vsi *vsi, struct sk_buff *skb,
+ struct libeth_rx_pt decoded_pt,
+ struct libeth_rx_csum csum_bits)
{
- struct libeth_rx_pt decoded;
- u32 rx_error, rx_status;
bool ipv4, ipv6;
- u8 ptype;
- u64 qword;
skb->ip_summed = CHECKSUM_NONE;
- qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
- ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword);
-
- decoded = libie_rx_pt_parse(ptype);
- if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded))
- return;
-
- rx_error = FIELD_GET(IAVF_RXD_QW1_ERROR_MASK, qword);
- rx_status = FIELD_GET(IAVF_RXD_QW1_STATUS_MASK, qword);
-
/* did the hardware decode the packet and checksum? */
- if (!(rx_status & BIT(IAVF_RX_DESC_STATUS_L3L4P_SHIFT)))
+ if (unlikely(!csum_bits.l3l4p))
return;
- ipv4 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV4;
- ipv6 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV6;
+ ipv4 = libeth_rx_pt_get_ip_ver(decoded_pt) == LIBETH_RX_PT_OUTER_IPV4;
+ ipv6 = libeth_rx_pt_get_ip_ver(decoded_pt) == LIBETH_RX_PT_OUTER_IPV6;
- if (ipv4 &&
- (rx_error & (BIT(IAVF_RX_DESC_ERROR_IPE_SHIFT) |
- BIT(IAVF_RX_DESC_ERROR_EIPE_SHIFT))))
+ if (unlikely(ipv4 && (csum_bits.ipe || csum_bits.eipe)))
goto checksum_fail;
/* likely incorrect csum if alternate IP extension headers found */
- if (ipv6 &&
- rx_status & BIT(IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT))
- /* don't increment checksum err here, non-fatal err */
+ if (unlikely(ipv6 && csum_bits.ipv6exadd))
return;
/* there was some L4 error, count error and punt packet to the stack */
- if (rx_error & BIT(IAVF_RX_DESC_ERROR_L4E_SHIFT))
+ if (unlikely(csum_bits.l4e))
goto checksum_fail;
/* handle packets that were not able to be checksummed due
* to arrival speed, in this case the stack can compute
* the csum.
*/
- if (rx_error & BIT(IAVF_RX_DESC_ERROR_PPRS_SHIFT))
+ if (unlikely(csum_bits.pprs))
return;
skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -960,52 +963,196 @@ checksum_fail:
}
/**
- * iavf_rx_hash - set the hash value in the skb
+ * iavf_legacy_rx_csum - Indicate in skb if hw indicated a good checksum
+ * @vsi: the VSI we care about
+ * @qw1: quad word 1
+ * @decoded_pt: decoded packet type
+ *
+ * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte
+ * descriptor writeback format.
+ *
+ * Return: decoded checksum bits.
+ **/
+static struct libeth_rx_csum
+iavf_legacy_rx_csum(const struct iavf_vsi *vsi, u64 qw1,
+ const struct libeth_rx_pt decoded_pt)
+{
+ struct libeth_rx_csum csum_bits = {};
+
+ if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded_pt))
+ return csum_bits;
+
+ csum_bits.ipe = FIELD_GET(IAVF_RXD_LEGACY_IPE_M, qw1);
+ csum_bits.eipe = FIELD_GET(IAVF_RXD_LEGACY_EIPE_M, qw1);
+ csum_bits.l4e = FIELD_GET(IAVF_RXD_LEGACY_L4E_M, qw1);
+ csum_bits.pprs = FIELD_GET(IAVF_RXD_LEGACY_PPRS_M, qw1);
+ csum_bits.l3l4p = FIELD_GET(IAVF_RXD_LEGACY_L3L4P_M, qw1);
+ csum_bits.ipv6exadd = FIELD_GET(IAVF_RXD_LEGACY_IPV6EXADD_M, qw1);
+
+ return csum_bits;
+}
+
+/**
+ * iavf_flex_rx_csum - Indicate in skb if hw indicated a good checksum
+ * @vsi: the VSI we care about
+ * @qw1: quad word 1
+ * @decoded_pt: decoded packet type
+ *
+ * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
+ *
+ * Return: decoded checksum bits.
+ **/
+static struct libeth_rx_csum
+iavf_flex_rx_csum(const struct iavf_vsi *vsi, u64 qw1,
+ const struct libeth_rx_pt decoded_pt)
+{
+ struct libeth_rx_csum csum_bits = {};
+
+ if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded_pt))
+ return csum_bits;
+
+ csum_bits.ipe = FIELD_GET(IAVF_RXD_FLEX_XSUM_IPE_M, qw1);
+ csum_bits.eipe = FIELD_GET(IAVF_RXD_FLEX_XSUM_EIPE_M, qw1);
+ csum_bits.l4e = FIELD_GET(IAVF_RXD_FLEX_XSUM_L4E_M, qw1);
+ csum_bits.eudpe = FIELD_GET(IAVF_RXD_FLEX_XSUM_EUDPE_M, qw1);
+ csum_bits.l3l4p = FIELD_GET(IAVF_RXD_FLEX_L3L4P_M, qw1);
+ csum_bits.ipv6exadd = FIELD_GET(IAVF_RXD_FLEX_IPV6EXADD_M, qw1);
+ csum_bits.nat = FIELD_GET(IAVF_RXD_FLEX_NAT_M, qw1);
+
+ return csum_bits;
+}
+
+/**
+ * iavf_legacy_rx_hash - set the hash value in the skb
+ * @ring: descriptor ring
+ * @qw0: quad word 0
+ * @qw1: quad word 1
+ * @skb: skb currently being received and modified
+ * @decoded_pt: decoded packet type
+ *
+ * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte
+ * descriptor writeback format.
+ **/
+static void iavf_legacy_rx_hash(const struct iavf_ring *ring, __le64 qw0,
+ __le64 qw1, struct sk_buff *skb,
+ const struct libeth_rx_pt decoded_pt)
+{
+ const __le64 rss_mask = cpu_to_le64(IAVF_RXD_LEGACY_FLTSTAT_M);
+ u32 hash;
+
+ if (!libeth_rx_pt_has_hash(ring->netdev, decoded_pt))
+ return;
+
+ if ((qw1 & rss_mask) == rss_mask) {
+ hash = le64_get_bits(qw0, IAVF_RXD_LEGACY_RSS_M);
+ libeth_rx_pt_set_hash(skb, hash, decoded_pt);
+ }
+}
+
+/**
+ * iavf_flex_rx_hash - set the hash value in the skb
* @ring: descriptor ring
- * @rx_desc: specific descriptor
+ * @qw1: quad word 1
* @skb: skb currently being received and modified
- * @rx_ptype: Rx packet type
+ * @decoded_pt: decoded packet type
+ *
+ * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
**/
-static void iavf_rx_hash(struct iavf_ring *ring,
- union iavf_rx_desc *rx_desc,
- struct sk_buff *skb,
- u8 rx_ptype)
+static void iavf_flex_rx_hash(const struct iavf_ring *ring, __le64 qw1,
+ struct sk_buff *skb,
+ const struct libeth_rx_pt decoded_pt)
{
- struct libeth_rx_pt decoded;
+ bool rss_valid;
u32 hash;
- const __le64 rss_mask =
- cpu_to_le64((u64)IAVF_RX_DESC_FLTSTAT_RSS_HASH <<
- IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT);
- decoded = libie_rx_pt_parse(rx_ptype);
- if (!libeth_rx_pt_has_hash(ring->netdev, decoded))
+ if (!libeth_rx_pt_has_hash(ring->netdev, decoded_pt))
return;
- if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) {
- hash = le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss);
- libeth_rx_pt_set_hash(skb, hash, decoded);
+ rss_valid = le64_get_bits(qw1, IAVF_RXD_FLEX_RSS_VALID_M);
+ if (rss_valid) {
+ hash = le64_get_bits(qw1, IAVF_RXD_FLEX_RSS_HASH_M);
+ libeth_rx_pt_set_hash(skb, hash, decoded_pt);
}
}
/**
+ * iavf_flex_rx_tstamp - Capture Rx timestamp from the descriptor
+ * @rx_ring: descriptor ring
+ * @qw2: quad word 2 of descriptor
+ * @qw3: quad word 3 of descriptor
+ * @skb: skb currently being received
+ *
+ * Read the Rx timestamp value from the descriptor and pass it to the stack.
+ *
+ * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
+ */
+static void iavf_flex_rx_tstamp(const struct iavf_ring *rx_ring, __le64 qw2,
+ __le64 qw3, struct sk_buff *skb)
+{
+ u32 tstamp;
+ u64 ns;
+
+ /* Skip processing if timestamps aren't enabled */
+ if (!(rx_ring->flags & IAVF_TXRX_FLAGS_HW_TSTAMP))
+ return;
+
+ /* Check if this Rx descriptor has a valid timestamp */
+ if (!le64_get_bits(qw2, IAVF_PTP_40B_TSTAMP_VALID))
+ return;
+
+ /* the ts_low field only contains the valid bit and sub-nanosecond
+ * precision, so we don't need to extract it.
+ */
+ tstamp = le64_get_bits(qw3, IAVF_RXD_FLEX_QW3_TSTAMP_HIGH_M);
+
+ ns = iavf_ptp_extend_32b_timestamp(rx_ring->ptp->cached_phc_time,
+ tstamp);
+
+ *skb_hwtstamps(skb) = (struct skb_shared_hwtstamps) {
+ .hwtstamp = ns_to_ktime(ns),
+ };
+}
+
+/**
* iavf_process_skb_fields - Populate skb header fields from Rx descriptor
* @rx_ring: rx descriptor ring packet is being transacted on
* @rx_desc: pointer to the EOP Rx descriptor
* @skb: pointer to current skb being populated
- * @rx_ptype: the packet type decoded by hardware
+ * @ptype: the packet type decoded by hardware
+ * @flex: is the descriptor flex or legacy
*
* This function checks the ring, descriptor, and packet information in
* order to populate the hash, checksum, VLAN, protocol, and
* other fields within the skb.
**/
-static void
-iavf_process_skb_fields(struct iavf_ring *rx_ring,
- union iavf_rx_desc *rx_desc, struct sk_buff *skb,
- u8 rx_ptype)
+static void iavf_process_skb_fields(const struct iavf_ring *rx_ring,
+ const struct iavf_rx_desc *rx_desc,
+ struct sk_buff *skb, u32 ptype,
+ bool flex)
{
- iavf_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
-
- iavf_rx_checksum(rx_ring->vsi, skb, rx_desc);
+ struct libeth_rx_csum csum_bits;
+ struct libeth_rx_pt decoded_pt;
+ __le64 qw0 = rx_desc->qw0;
+ __le64 qw1 = rx_desc->qw1;
+ __le64 qw2 = rx_desc->qw2;
+ __le64 qw3 = rx_desc->qw3;
+
+ decoded_pt = libie_rx_pt_parse(ptype);
+
+ if (flex) {
+ iavf_flex_rx_hash(rx_ring, qw1, skb, decoded_pt);
+ iavf_flex_rx_tstamp(rx_ring, qw2, qw3, skb);
+ csum_bits = iavf_flex_rx_csum(rx_ring->vsi, le64_to_cpu(qw1),
+ decoded_pt);
+ } else {
+ iavf_legacy_rx_hash(rx_ring, qw0, qw1, skb, decoded_pt);
+ csum_bits = iavf_legacy_rx_csum(rx_ring->vsi, le64_to_cpu(qw1),
+ decoded_pt);
+ }
+ iavf_rx_csum(rx_ring->vsi, skb, decoded_pt, csum_bits);
skb_record_rx_queue(skb, rx_ring->queue_index);
@@ -1092,8 +1239,7 @@ static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer,
/**
* iavf_is_non_eop - process handling of non-EOP buffers
* @rx_ring: Rx ring being processed
- * @rx_desc: Rx descriptor for current buffer
- * @skb: Current socket buffer containing buffer in progress
+ * @fields: Rx descriptor extracted fields
*
* This function updates next to clean. If the buffer is an EOP buffer
* this function exits returning false, otherwise it will place the
@@ -1101,8 +1247,7 @@ static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer,
* that this is in fact a non-EOP buffer.
**/
static bool iavf_is_non_eop(struct iavf_ring *rx_ring,
- union iavf_rx_desc *rx_desc,
- struct sk_buff *skb)
+ struct libeth_rqe_info fields)
{
u32 ntc = rx_ring->next_to_clean + 1;
@@ -1113,8 +1258,7 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring,
prefetch(IAVF_RX_DESC(rx_ring, ntc));
/* if we are the last buffer then there is nothing else to do */
-#define IAVF_RXD_EOF BIT(IAVF_RX_DESC_STATUS_EOF_SHIFT)
- if (likely(iavf_test_staterr(rx_desc, IAVF_RXD_EOF)))
+ if (likely(fields.eop))
return false;
rx_ring->rx_stats.non_eop_descs++;
@@ -1123,6 +1267,109 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring,
}
/**
+ * iavf_extract_legacy_rx_fields - Extract fields from the Rx descriptor
+ * @rx_ring: rx descriptor ring
+ * @rx_desc: the descriptor to process
+ *
+ * Decode the Rx descriptor and extract relevant information including the
+ * size, VLAN tag, Rx packet type, end of packet field and RXE field value.
+ *
+ * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte
+ * descriptor writeback format.
+ *
+ * Return: fields extracted from the Rx descriptor.
+ */
+static struct libeth_rqe_info
+iavf_extract_legacy_rx_fields(const struct iavf_ring *rx_ring,
+ const struct iavf_rx_desc *rx_desc)
+{
+ u64 qw0 = le64_to_cpu(rx_desc->qw0);
+ u64 qw1 = le64_to_cpu(rx_desc->qw1);
+ u64 qw2 = le64_to_cpu(rx_desc->qw2);
+ struct libeth_rqe_info fields;
+ bool l2tag1p, l2tag2p;
+
+ fields.eop = FIELD_GET(IAVF_RXD_LEGACY_EOP_M, qw1);
+ fields.len = FIELD_GET(IAVF_RXD_LEGACY_LENGTH_M, qw1);
+
+ if (!fields.eop)
+ return fields;
+
+ fields.rxe = FIELD_GET(IAVF_RXD_LEGACY_RXE_M, qw1);
+ fields.ptype = FIELD_GET(IAVF_RXD_LEGACY_PTYPE_M, qw1);
+ fields.vlan = 0;
+
+ if (rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1) {
+ l2tag1p = FIELD_GET(IAVF_RXD_LEGACY_L2TAG1P_M, qw1);
+ if (l2tag1p)
+ fields.vlan = FIELD_GET(IAVF_RXD_LEGACY_L2TAG1_M, qw0);
+ } else if (rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2) {
+ l2tag2p = FIELD_GET(IAVF_RXD_LEGACY_L2TAG2P_M, qw2);
+ if (l2tag2p)
+ fields.vlan = FIELD_GET(IAVF_RXD_LEGACY_L2TAG2_M, qw2);
+ }
+
+ return fields;
+}
+
+/**
+ * iavf_extract_flex_rx_fields - Extract fields from the Rx descriptor
+ * @rx_ring: rx descriptor ring
+ * @rx_desc: the descriptor to process
+ *
+ * Decode the Rx descriptor and extract relevant information including the
+ * size, VLAN tag, Rx packet type, end of packet field and RXE field value.
+ *
+ * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
+ *
+ * Return: fields extracted from the Rx descriptor.
+ */
+static struct libeth_rqe_info
+iavf_extract_flex_rx_fields(const struct iavf_ring *rx_ring,
+ const struct iavf_rx_desc *rx_desc)
+{
+ struct libeth_rqe_info fields = {};
+ u64 qw0 = le64_to_cpu(rx_desc->qw0);
+ u64 qw1 = le64_to_cpu(rx_desc->qw1);
+ u64 qw2 = le64_to_cpu(rx_desc->qw2);
+ bool l2tag1p, l2tag2p;
+
+ fields.eop = FIELD_GET(IAVF_RXD_FLEX_EOP_M, qw1);
+ fields.len = FIELD_GET(IAVF_RXD_FLEX_PKT_LEN_M, qw0);
+
+ if (!fields.eop)
+ return fields;
+
+ fields.rxe = FIELD_GET(IAVF_RXD_FLEX_RXE_M, qw1);
+ fields.ptype = FIELD_GET(IAVF_RXD_FLEX_PTYPE_M, qw0);
+ fields.vlan = 0;
+
+ if (rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1) {
+ l2tag1p = FIELD_GET(IAVF_RXD_FLEX_L2TAG1P_M, qw1);
+ if (l2tag1p)
+ fields.vlan = FIELD_GET(IAVF_RXD_FLEX_L2TAG1_M, qw1);
+ } else if (rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2) {
+ l2tag2p = FIELD_GET(IAVF_RXD_FLEX_L2TAG2P_M, qw2);
+ if (l2tag2p)
+ fields.vlan = FIELD_GET(IAVF_RXD_FLEX_L2TAG2_2_M, qw2);
+ }
+
+ return fields;
+}
+
+static struct libeth_rqe_info
+iavf_extract_rx_fields(const struct iavf_ring *rx_ring,
+ const struct iavf_rx_desc *rx_desc,
+ bool flex)
+{
+ if (flex)
+ return iavf_extract_flex_rx_fields(rx_ring, rx_desc);
+ else
+ return iavf_extract_legacy_rx_fields(rx_ring, rx_desc);
+}
+
+/**
* iavf_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
* @rx_ring: rx descriptor ring to transact packets on
* @budget: Total limit on number of packets to process
@@ -1136,18 +1383,17 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring,
**/
static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
{
+ bool flex = rx_ring->rxdid == VIRTCHNL_RXDID_2_FLEX_SQ_NIC;
unsigned int total_rx_bytes = 0, total_rx_packets = 0;
struct sk_buff *skb = rx_ring->skb;
u16 cleaned_count = IAVF_DESC_UNUSED(rx_ring);
bool failure = false;
while (likely(total_rx_packets < (unsigned int)budget)) {
+ struct libeth_rqe_info fields;
struct libeth_fqe *rx_buffer;
- union iavf_rx_desc *rx_desc;
- unsigned int size;
- u16 vlan_tag = 0;
- u8 rx_ptype;
- u64 qword;
+ struct iavf_rx_desc *rx_desc;
+ u64 qw1;
/* return some buffers to hardware, one at a time is too slow */
if (cleaned_count >= IAVF_RX_BUFFER_WRITE) {
@@ -1158,35 +1404,32 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
rx_desc = IAVF_RX_DESC(rx_ring, rx_ring->next_to_clean);
- /* status_error_len will always be zero for unused descriptors
- * because it's cleared in cleanup, and overlaps with hdr_addr
- * which is always zero because packet split isn't used, if the
- * hardware wrote DD then the length will be non-zero
- */
- qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-
/* This memory barrier is needed to keep us from reading
* any other fields out of the rx_desc until we have
* verified the descriptor has been written back.
*/
dma_rmb();
-#define IAVF_RXD_DD BIT(IAVF_RX_DESC_STATUS_DD_SHIFT)
- if (!iavf_test_staterr(rx_desc, IAVF_RXD_DD))
+
+ qw1 = le64_to_cpu(rx_desc->qw1);
+ /* If DD field (descriptor done) is unset then other fields are
+ * not valid
+ */
+ if (!iavf_is_descriptor_done(qw1, flex))
break;
- size = FIELD_GET(IAVF_RXD_QW1_LENGTH_PBUF_MASK, qword);
+ fields = iavf_extract_rx_fields(rx_ring, rx_desc, flex);
iavf_trace(clean_rx_irq, rx_ring, rx_desc, skb);
rx_buffer = &rx_ring->rx_fqes[rx_ring->next_to_clean];
- if (!libeth_rx_sync_for_cpu(rx_buffer, size))
+ if (!libeth_rx_sync_for_cpu(rx_buffer, fields.len))
goto skip_data;
/* retrieve a buffer from the ring */
if (skb)
- iavf_add_rx_frag(skb, rx_buffer, size);
+ iavf_add_rx_frag(skb, rx_buffer, fields.len);
else
- skb = iavf_build_skb(rx_buffer, size);
+ skb = iavf_build_skb(rx_buffer, fields.len);
/* exit if we failed to retrieve a buffer */
if (!skb) {
@@ -1197,15 +1440,14 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
skip_data:
cleaned_count++;
- if (iavf_is_non_eop(rx_ring, rx_desc, skb) || unlikely(!skb))
+ if (iavf_is_non_eop(rx_ring, fields) || unlikely(!skb))
continue;
- /* ERR_MASK will only have valid bits if EOP set, and
- * what we are doing here is actually checking
- * IAVF_RX_DESC_ERROR_RXE_SHIFT, since it is the zeroth bit in
- * the error field
+ /* RXE field in descriptor is an indication of the MAC errors
+ * (like CRC, alignment, oversize etc). If it is set then iavf
+ * should finish.
*/
- if (unlikely(iavf_test_staterr(rx_desc, BIT(IAVF_RXD_QW1_ERROR_SHIFT)))) {
+ if (unlikely(fields.rxe)) {
dev_kfree_skb_any(skb);
skb = NULL;
continue;
@@ -1219,22 +1461,11 @@ skip_data:
/* probably a little skewed due to removing CRC */
total_rx_bytes += skb->len;
- qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
- rx_ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword);
-
/* populate checksum, VLAN, and protocol */
- iavf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
-
- if (qword & BIT(IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT) &&
- rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1)
- vlan_tag = le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1);
- if (rx_desc->wb.qword2.ext_status &
- cpu_to_le16(BIT(IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT)) &&
- rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2)
- vlan_tag = le16_to_cpu(rx_desc->wb.qword2.l2tag2_2);
+ iavf_process_skb_fields(rx_ring, rx_desc, skb, fields.ptype, flex);
iavf_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb);
- iavf_receive_skb(rx_ring, skb, vlan_tag);
+ iavf_receive_skb(rx_ring, skb, fields.vlan);
skb = NULL;
/* update budget accounting */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
index f97c702c0802..79ad554f2d53 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
@@ -80,25 +80,6 @@ enum iavf_dyn_idx_t {
BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
-#define iavf_rx_desc iavf_32byte_rx_desc
-
-/**
- * iavf_test_staterr - tests bits in Rx descriptor status and error fields
- * @rx_desc: pointer to receive descriptor (in le64 format)
- * @stat_err_bits: value to mask
- *
- * This function does some fast chicanery in order to return the
- * value of the mask which is really only used for boolean tests.
- * The status_error_len doesn't need to be shifted because it begins
- * at offset zero.
- */
-static inline bool iavf_test_staterr(union iavf_rx_desc *rx_desc,
- const u64 stat_err_bits)
-{
- return !!(rx_desc->wb.qword1.status_error_len &
- cpu_to_le64(stat_err_bits));
-}
-
/* How many Rx Buffers do we bundle into one write to the hardware ? */
#define IAVF_RX_INCREMENT(r, i) \
do { \
@@ -262,6 +243,8 @@ struct iavf_ring {
u16 next_to_use;
u16 next_to_clean;
+ u16 rxdid; /* Rx descriptor format */
+
u16 flags;
#define IAVF_TXR_FLAGS_WB_ON_ITR BIT(0)
#define IAVF_TXR_FLAGS_ARM_WB BIT(1)
@@ -269,6 +252,7 @@ struct iavf_ring {
#define IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1 BIT(3)
#define IAVF_TXR_FLAGS_VLAN_TAG_LOC_L2TAG2 BIT(4)
#define IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2 BIT(5)
+#define IAVF_TXRX_FLAGS_HW_TSTAMP BIT(6)
/* stats structs */
struct iavf_queue_stats stats;
@@ -295,6 +279,8 @@ struct iavf_ring {
* for this ring.
*/
+ struct iavf_ptp *ptp;
+
u32 rx_buf_len;
struct net_shaper q_shaper;
bool q_shaper_update;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h
index f6b09e57abce..f9e1319620f4 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_type.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_type.h
@@ -178,110 +178,116 @@ struct iavf_hw {
char err_str[16];
};
-/* RX Descriptors */
-union iavf_16byte_rx_desc {
- struct {
- __le64 pkt_addr; /* Packet buffer address */
- __le64 hdr_addr; /* Header buffer address */
- } read;
- struct {
- struct {
- struct {
- union {
- __le16 mirroring_status;
- __le16 fcoe_ctx_id;
- } mirr_fcoe;
- __le16 l2tag1;
- } lo_dword;
- union {
- __le32 rss; /* RSS Hash */
- __le32 fd_id; /* Flow director filter id */
- __le32 fcoe_param; /* FCoE DDP Context id */
- } hi_dword;
- } qword0;
- struct {
- /* ext status/error/pktype/length */
- __le64 status_error_len;
- } qword1;
- } wb; /* writeback */
-};
-
-union iavf_32byte_rx_desc {
- struct {
- __le64 pkt_addr; /* Packet buffer address */
- __le64 hdr_addr; /* Header buffer address */
- /* bit 0 of hdr_buffer_addr is DD bit */
- __le64 rsvd1;
- __le64 rsvd2;
- } read;
- struct {
- struct {
- struct {
- union {
- __le16 mirroring_status;
- __le16 fcoe_ctx_id;
- } mirr_fcoe;
- __le16 l2tag1;
- } lo_dword;
- union {
- __le32 rss; /* RSS Hash */
- __le32 fcoe_param; /* FCoE DDP Context id */
- /* Flow director filter id in case of
- * Programming status desc WB
- */
- __le32 fd_id;
- } hi_dword;
- } qword0;
- struct {
- /* status/error/pktype/length */
- __le64 status_error_len;
- } qword1;
- struct {
- __le16 ext_status; /* extended status */
- __le16 rsvd;
- __le16 l2tag2_1;
- __le16 l2tag2_2;
- } qword2;
- struct {
- union {
- __le32 flex_bytes_lo;
- __le32 pe_status;
- } lo_dword;
- union {
- __le32 flex_bytes_hi;
- __le32 fd_id;
- } hi_dword;
- } qword3;
- } wb; /* writeback */
-};
-
-enum iavf_rx_desc_status_bits {
- /* Note: These are predefined bit offsets */
- IAVF_RX_DESC_STATUS_DD_SHIFT = 0,
- IAVF_RX_DESC_STATUS_EOF_SHIFT = 1,
- IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT = 2,
- IAVF_RX_DESC_STATUS_L3L4P_SHIFT = 3,
- IAVF_RX_DESC_STATUS_CRCP_SHIFT = 4,
- IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT = 5, /* 2 BITS */
- IAVF_RX_DESC_STATUS_TSYNVALID_SHIFT = 7,
- /* Note: Bit 8 is reserved in X710 and XL710 */
- IAVF_RX_DESC_STATUS_EXT_UDP_0_SHIFT = 8,
- IAVF_RX_DESC_STATUS_UMBCAST_SHIFT = 9, /* 2 BITS */
- IAVF_RX_DESC_STATUS_FLM_SHIFT = 11,
- IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT = 12, /* 2 BITS */
- IAVF_RX_DESC_STATUS_LPBK_SHIFT = 14,
- IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT = 15,
- IAVF_RX_DESC_STATUS_RESERVED_SHIFT = 16, /* 2 BITS */
- /* Note: For non-tunnel packets INT_UDP_0 is the right status for
- * UDP header
- */
- IAVF_RX_DESC_STATUS_INT_UDP_0_SHIFT = 18,
- IAVF_RX_DESC_STATUS_LAST /* this entry must be last!!! */
-};
-
-#define IAVF_RXD_QW1_STATUS_SHIFT 0
-#define IAVF_RXD_QW1_STATUS_MASK ((BIT(IAVF_RX_DESC_STATUS_LAST) - 1) \
- << IAVF_RXD_QW1_STATUS_SHIFT)
+/**
+ * struct iavf_rx_desc - Receive descriptor (both legacy and flexible)
+ * @qw0: quad word 0 fields:
+ * Legacy: Descriptor Type; Mirror ID; L2TAG1P (S-TAG); Filter Status
+ * Flex: Descriptor Type; Mirror ID; UMBCAST; Packet Type; Flexible Flags
+ * Section 0; Packet Length; Header Length; Split Header Flag;
+ * Flexible Flags section 1 / Extended Status
+ * @qw1: quad word 1 fields:
+ * Legacy: Status Field; Error Field; Packet Type; Packet Length (packet,
+ * header, Split Header Flag)
+ * Flex: Status / Error 0 Field; L2TAG1P (S-TAG); Flexible Metadata
+ * Container #0; Flexible Metadata Container #1
+ * @qw2: quad word 2 fields:
+ * Legacy: Extended Status; 1st L2TAG2P (C-TAG); 2nd L2TAG2P (C-TAG)
+ * Flex: Status / Error 1 Field; Flexible Flags section 2; Timestamp Low;
+ * 1st L2TAG2 (C-TAG); 2nd L2TAG2 (C-TAG)
+ * @qw3: quad word 3 fields:
+ * Legacy: FD Filter ID / Flexible Bytes
+ * Flex: Flexible Metadata Container #2; Flexible Metadata Container #3;
+ * Flexible Metadata Container #4 / Timestamp High 0; Flexible
+ * Metadata Container #5 / Timestamp High 1;
+ */
+struct iavf_rx_desc {
+ aligned_le64 qw0;
+/* The hash signature (RSS) */
+#define IAVF_RXD_LEGACY_RSS_M GENMASK_ULL(63, 32)
+/* Stripped C-TAG VLAN from the receive packet */
+#define IAVF_RXD_LEGACY_L2TAG1_M GENMASK_ULL(33, 16)
+/* Packet type */
+#define IAVF_RXD_FLEX_PTYPE_M GENMASK_ULL(25, 16)
+/* Packet length */
+#define IAVF_RXD_FLEX_PKT_LEN_M GENMASK_ULL(45, 32)
+
+ aligned_le64 qw1;
+/* Descriptor done indication flag. */
+#define IAVF_RXD_LEGACY_DD_M BIT(0)
+/* End of packet. Set to 1 if this descriptor is the last one of the packet */
+#define IAVF_RXD_LEGACY_EOP_M BIT(1)
+/* L2 TAG 1 presence indication */
+#define IAVF_RXD_LEGACY_L2TAG1P_M BIT(2)
+/* Detectable L3 and L4 integrity check is processed by the HW */
+#define IAVF_RXD_LEGACY_L3L4P_M BIT(3)
+/* Set when an IPv6 packet contains a Destination Options Header or a Routing
+ * Header.
+ */
+#define IAVF_RXD_LEGACY_IPV6EXADD_M BIT(15)
+/* Receive MAC Errors: CRC; Alignment; Oversize; Undersizes; Length error */
+#define IAVF_RXD_LEGACY_RXE_M BIT(19)
+/* Checksum reports:
+ * - IPE: IP checksum error
+ * - L4E: L4 integrity error
+ * - EIPE: External IP header (tunneled packets)
+ */
+#define IAVF_RXD_LEGACY_IPE_M BIT(22)
+#define IAVF_RXD_LEGACY_L4E_M BIT(23)
+#define IAVF_RXD_LEGACY_EIPE_M BIT(24)
+/* Set for packets that skip checksum calculation in pre-parser */
+#define IAVF_RXD_LEGACY_PPRS_M BIT(26)
+/* Indicates the content in the Filter Status field */
+#define IAVF_RXD_LEGACY_FLTSTAT_M GENMASK_ULL(13, 12)
+/* Packet type */
+#define IAVF_RXD_LEGACY_PTYPE_M GENMASK_ULL(37, 30)
+/* Packet length */
+#define IAVF_RXD_LEGACY_LENGTH_M GENMASK_ULL(51, 38)
+/* Descriptor done indication flag */
+#define IAVF_RXD_FLEX_DD_M BIT(0)
+/* End of packet. Set to 1 if this descriptor is the last one of the packet */
+#define IAVF_RXD_FLEX_EOP_M BIT(1)
+/* Detectable L3 and L4 integrity check is processed by the HW */
+#define IAVF_RXD_FLEX_L3L4P_M BIT(3)
+/* Checksum reports:
+ * - IPE: IP checksum error
+ * - L4E: L4 integrity error
+ * - EIPE: External IP header (tunneled packets)
+ * - EUDPE: External UDP checksum error (tunneled packets)
+ */
+#define IAVF_RXD_FLEX_XSUM_IPE_M BIT(4)
+#define IAVF_RXD_FLEX_XSUM_L4E_M BIT(5)
+#define IAVF_RXD_FLEX_XSUM_EIPE_M BIT(6)
+#define IAVF_RXD_FLEX_XSUM_EUDPE_M BIT(7)
+/* Set when an IPv6 packet contains a Destination Options Header or a Routing
+ * Header.
+ */
+#define IAVF_RXD_FLEX_IPV6EXADD_M BIT(9)
+/* Receive MAC Errors: CRC; Alignment; Oversize; Undersizes; Length error */
+#define IAVF_RXD_FLEX_RXE_M BIT(10)
+/* Indicates that the RSS/HASH result is valid */
+#define IAVF_RXD_FLEX_RSS_VALID_M BIT(12)
+/* L2 TAG 1 presence indication */
+#define IAVF_RXD_FLEX_L2TAG1P_M BIT(13)
+/* Stripped L2 Tag from the receive packet */
+#define IAVF_RXD_FLEX_L2TAG1_M GENMASK_ULL(31, 16)
+/* The hash signature (RSS) */
+#define IAVF_RXD_FLEX_RSS_HASH_M GENMASK_ULL(63, 32)
+
+ aligned_le64 qw2;
+/* L2 Tag 2 Presence */
+#define IAVF_RXD_LEGACY_L2TAG2P_M BIT(0)
+/* Stripped S-TAG VLAN from the receive packet */
+#define IAVF_RXD_LEGACY_L2TAG2_M GENMASK_ULL(63, 32)
+/* Stripped S-TAG VLAN from the receive packet */
+#define IAVF_RXD_FLEX_L2TAG2_2_M GENMASK_ULL(63, 48)
+/* The packet is a UDP tunneled packet */
+#define IAVF_RXD_FLEX_NAT_M BIT(4)
+/* L2 Tag 2 Presence */
+#define IAVF_RXD_FLEX_L2TAG2P_M BIT(11)
+ aligned_le64 qw3;
+#define IAVF_RXD_FLEX_QW3_TSTAMP_HIGH_M GENMASK_ULL(63, 32)
+} __aligned(4 * sizeof(__le64));
+static_assert(sizeof(struct iavf_rx_desc) == 32);
#define IAVF_RXD_QW1_STATUS_TSYNINDX_SHIFT IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT
#define IAVF_RXD_QW1_STATUS_TSYNINDX_MASK (0x3UL << \
@@ -298,22 +304,6 @@ enum iavf_rx_desc_fltstat_values {
IAVF_RX_DESC_FLTSTAT_RSS_HASH = 3,
};
-#define IAVF_RXD_QW1_ERROR_SHIFT 19
-#define IAVF_RXD_QW1_ERROR_MASK (0xFFUL << IAVF_RXD_QW1_ERROR_SHIFT)
-
-enum iavf_rx_desc_error_bits {
- /* Note: These are predefined bit offsets */
- IAVF_RX_DESC_ERROR_RXE_SHIFT = 0,
- IAVF_RX_DESC_ERROR_RECIPE_SHIFT = 1,
- IAVF_RX_DESC_ERROR_HBO_SHIFT = 2,
- IAVF_RX_DESC_ERROR_L3L4E_SHIFT = 3, /* 3 BITS */
- IAVF_RX_DESC_ERROR_IPE_SHIFT = 3,
- IAVF_RX_DESC_ERROR_L4E_SHIFT = 4,
- IAVF_RX_DESC_ERROR_EIPE_SHIFT = 5,
- IAVF_RX_DESC_ERROR_OVERSIZE_SHIFT = 6,
- IAVF_RX_DESC_ERROR_PPRS_SHIFT = 7
-};
-
enum iavf_rx_desc_error_l3l4e_fcoe_masks {
IAVF_RX_DESC_ERROR_L3L4E_NONE = 0,
IAVF_RX_DESC_ERROR_L3L4E_PROT = 1,
@@ -322,13 +312,6 @@ enum iavf_rx_desc_error_l3l4e_fcoe_masks {
IAVF_RX_DESC_ERROR_L3L4E_DMAC_WARN = 4
};
-#define IAVF_RXD_QW1_PTYPE_SHIFT 30
-#define IAVF_RXD_QW1_PTYPE_MASK (0xFFULL << IAVF_RXD_QW1_PTYPE_SHIFT)
-
-#define IAVF_RXD_QW1_LENGTH_PBUF_SHIFT 38
-#define IAVF_RXD_QW1_LENGTH_PBUF_MASK (0x3FFFULL << \
- IAVF_RXD_QW1_LENGTH_PBUF_SHIFT)
-
#define IAVF_RXD_QW1_LENGTH_HBUF_SHIFT 52
#define IAVF_RXD_QW1_LENGTH_HBUF_MASK (0x7FFULL << \
IAVF_RXD_QW1_LENGTH_HBUF_SHIFT)
@@ -347,6 +330,8 @@ enum iavf_rx_desc_ext_status_bits {
IAVF_RX_DESC_EXT_STATUS_PELONGB_SHIFT = 11,
};
+#define IAVF_RX_DESC_EXT_STATUS_L2TAG2P_M BIT(IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT)
+
enum iavf_rx_desc_pe_status_bits {
/* Note: These are predefined bit offsets */
IAVF_RX_DESC_PE_STATUS_QPID_SHIFT = 0, /* 18 BITS */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_types.h b/drivers/net/ethernet/intel/iavf/iavf_types.h
new file mode 100644
index 000000000000..a095855122bf
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_types.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024 Intel Corporation. */
+
+#ifndef _IAVF_TYPES_H_
+#define _IAVF_TYPES_H_
+
+#include "iavf_types.h"
+
+#include <linux/avf/virtchnl.h>
+#include <linux/ptp_clock_kernel.h>
+
+/* structure used to queue PTP commands for processing */
+struct iavf_ptp_aq_cmd {
+ struct list_head list;
+ enum virtchnl_ops v_opcode:16;
+ u16 msglen;
+ u8 msg[] __counted_by(msglen);
+};
+
+struct iavf_ptp {
+ wait_queue_head_t phc_time_waitqueue;
+ struct virtchnl_ptp_caps hw_caps;
+ struct ptp_clock_info info;
+ struct ptp_clock *clock;
+ struct list_head aq_cmds;
+ u64 cached_phc_time;
+ unsigned long cached_phc_updated;
+ /* Lock protecting access to the AQ command list */
+ struct mutex aq_cmd_lock;
+ struct kernel_hwtstamp_config hwtstamp_config;
+ bool phc_time_ready:1;
+};
+
+#endif /* _IAVF_TYPES_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 15d388b431c5..a6f0e5990be2 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -4,6 +4,7 @@
#include <linux/net/intel/libie/rx.h>
#include "iavf.h"
+#include "iavf_ptp.h"
#include "iavf_prototype.h"
/**
@@ -144,9 +145,11 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter)
VIRTCHNL_VF_OFFLOAD_ENCAP |
VIRTCHNL_VF_OFFLOAD_TC_U32 |
VIRTCHNL_VF_OFFLOAD_VLAN_V2 |
+ VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC |
VIRTCHNL_VF_OFFLOAD_CRC |
VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM |
VIRTCHNL_VF_OFFLOAD_REQ_QUEUES |
+ VIRTCHNL_VF_CAP_PTP |
VIRTCHNL_VF_OFFLOAD_ADQ |
VIRTCHNL_VF_OFFLOAD_USO |
VIRTCHNL_VF_OFFLOAD_FDIR_PF |
@@ -177,6 +180,54 @@ int iavf_send_vf_offload_vlan_v2_msg(struct iavf_adapter *adapter)
NULL, 0);
}
+int iavf_send_vf_supported_rxdids_msg(struct iavf_adapter *adapter)
+{
+ adapter->aq_required &= ~IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS;
+
+ if (!IAVF_RXDID_ALLOWED(adapter))
+ return -EOPNOTSUPP;
+
+ adapter->current_op = VIRTCHNL_OP_GET_SUPPORTED_RXDIDS;
+
+ return iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_SUPPORTED_RXDIDS,
+ NULL, 0);
+}
+
+/**
+ * iavf_send_vf_ptp_caps_msg - Send request for PTP capabilities
+ * @adapter: private adapter structure
+ *
+ * Send the VIRTCHNL_OP_1588_PTP_GET_CAPS command to the PF to request the PTP
+ * capabilities available to this device. This includes the following
+ * potential access:
+ *
+ * * READ_PHC - access to read the PTP hardware clock time
+ * * RX_TSTAMP - access to request Rx timestamps on all received packets
+ *
+ * The PF will reply with the same opcode a filled out copy of the
+ * virtchnl_ptp_caps structure which defines the specifics of which features
+ * are accessible to this device.
+ *
+ * Return: 0 if success, error code otherwise.
+ */
+int iavf_send_vf_ptp_caps_msg(struct iavf_adapter *adapter)
+{
+ struct virtchnl_ptp_caps hw_caps = {
+ .caps = VIRTCHNL_1588_PTP_CAP_READ_PHC |
+ VIRTCHNL_1588_PTP_CAP_RX_TSTAMP
+ };
+
+ adapter->aq_required &= ~IAVF_FLAG_AQ_GET_PTP_CAPS;
+
+ if (!IAVF_PTP_ALLOWED(adapter))
+ return -EOPNOTSUPP;
+
+ adapter->current_op = VIRTCHNL_OP_1588_PTP_GET_CAPS;
+
+ return iavf_send_pf_msg(adapter, VIRTCHNL_OP_1588_PTP_GET_CAPS,
+ (u8 *)&hw_caps, sizeof(hw_caps));
+}
+
/**
* iavf_validate_num_queues
* @adapter: adapter structure
@@ -263,6 +314,40 @@ int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter)
return err;
}
+int iavf_get_vf_supported_rxdids(struct iavf_adapter *adapter)
+{
+ struct iavf_arq_event_info event;
+ u64 rxdids;
+ int err;
+
+ event.msg_buf = (u8 *)&rxdids;
+ event.buf_len = sizeof(rxdids);
+
+ err = iavf_poll_virtchnl_msg(&adapter->hw, &event,
+ VIRTCHNL_OP_GET_SUPPORTED_RXDIDS);
+ if (!err)
+ adapter->supp_rxdids = rxdids;
+
+ return err;
+}
+
+int iavf_get_vf_ptp_caps(struct iavf_adapter *adapter)
+{
+ struct virtchnl_ptp_caps caps = {};
+ struct iavf_arq_event_info event;
+ int err;
+
+ event.msg_buf = (u8 *)&caps;
+ event.buf_len = sizeof(caps);
+
+ err = iavf_poll_virtchnl_msg(&adapter->hw, &event,
+ VIRTCHNL_OP_1588_PTP_GET_CAPS);
+ if (!err)
+ adapter->ptp.hw_caps = caps;
+
+ return err;
+}
+
/**
* iavf_configure_queues
* @adapter: adapter structure
@@ -275,6 +360,7 @@ void iavf_configure_queues(struct iavf_adapter *adapter)
int pairs = adapter->num_active_queues;
struct virtchnl_queue_pair_info *vqpi;
u32 i, max_frame;
+ u8 rx_flags = 0;
size_t len;
max_frame = LIBIE_MAX_RX_FRM_LEN(adapter->rx_rings->pp->p.offset);
@@ -292,6 +378,9 @@ void iavf_configure_queues(struct iavf_adapter *adapter)
if (!vqci)
return;
+ if (iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP))
+ rx_flags |= VIRTCHNL_PTP_RX_TSTAMP;
+
vqci->vsi_id = adapter->vsi_res->vsi_id;
vqci->num_queue_pairs = pairs;
vqpi = vqci->qpair;
@@ -309,9 +398,12 @@ void iavf_configure_queues(struct iavf_adapter *adapter)
vqpi->rxq.dma_ring_addr = adapter->rx_rings[i].dma;
vqpi->rxq.max_pkt_size = max_frame;
vqpi->rxq.databuffer_size = adapter->rx_rings[i].rx_buf_len;
+ if (IAVF_RXDID_ALLOWED(adapter))
+ vqpi->rxq.rxdid = adapter->rxdid;
if (CRC_OFFLOAD_ALLOWED(adapter))
vqpi->rxq.crc_disable = !!(adapter->netdev->features &
NETIF_F_RXFCS);
+ vqpi->rxq.flags = rx_flags;
vqpi++;
}
@@ -1402,6 +1494,67 @@ void iavf_disable_vlan_insertion_v2(struct iavf_adapter *adapter, u16 tpid)
VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2);
}
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
+/**
+ * iavf_virtchnl_send_ptp_cmd - Send one queued PTP command
+ * @adapter: adapter private structure
+ *
+ * De-queue one PTP command request and send the command message to the PF.
+ * Clear IAVF_FLAG_AQ_SEND_PTP_CMD if no more messages are left to send.
+ */
+void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter)
+{
+ struct iavf_ptp_aq_cmd *cmd;
+ int err;
+
+ if (!adapter->ptp.clock) {
+ /* This shouldn't be possible to hit, since no messages should
+ * be queued if PTP is not initialized.
+ */
+ pci_err(adapter->pdev, "PTP is not initialized\n");
+ adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD;
+ return;
+ }
+
+ mutex_lock(&adapter->ptp.aq_cmd_lock);
+ cmd = list_first_entry_or_null(&adapter->ptp.aq_cmds,
+ struct iavf_ptp_aq_cmd, list);
+ if (!cmd) {
+ /* no further PTP messages to send */
+ adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD;
+ goto out_unlock;
+ }
+
+ if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
+ /* bail because we already have a command pending */
+ pci_err(adapter->pdev,
+ "Cannot send PTP command %d, command %d pending\n",
+ cmd->v_opcode, adapter->current_op);
+ goto out_unlock;
+ }
+
+ err = iavf_send_pf_msg(adapter, cmd->v_opcode, cmd->msg, cmd->msglen);
+ if (!err) {
+ /* Command was sent without errors, so we can remove it from
+ * the list and discard it.
+ */
+ list_del(&cmd->list);
+ kfree(cmd);
+ } else {
+ /* We failed to send the command, try again next cycle */
+ pci_err(adapter->pdev, "Failed to send PTP command %d\n",
+ cmd->v_opcode);
+ }
+
+ if (list_empty(&adapter->ptp.aq_cmds))
+ /* no further PTP messages to send */
+ adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD;
+
+out_unlock:
+ mutex_unlock(&adapter->ptp.aq_cmd_lock);
+}
+#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
+
/**
* iavf_print_link_message - print link up or down
* @adapter: adapter structure
@@ -2098,6 +2251,37 @@ static void iavf_activate_fdir_filters(struct iavf_adapter *adapter)
}
/**
+ * iavf_virtchnl_ptp_get_time - Respond to VIRTCHNL_OP_1588_PTP_GET_TIME
+ * @adapter: private adapter structure
+ * @data: the message from the PF
+ * @len: length of the message from the PF
+ *
+ * Handle the VIRTCHNL_OP_1588_PTP_GET_TIME message from the PF. This message
+ * is sent by the PF in response to the same op as a request from the VF.
+ * Extract the 64bit nanoseconds time from the message and store it in
+ * cached_phc_time. Then, notify any thread that is waiting for the update via
+ * the wait queue.
+ */
+static void iavf_virtchnl_ptp_get_time(struct iavf_adapter *adapter,
+ void *data, u16 len)
+{
+ struct virtchnl_phc_time *msg = data;
+
+ if (len != sizeof(*msg)) {
+ dev_err_once(&adapter->pdev->dev,
+ "Invalid VIRTCHNL_OP_1588_PTP_GET_TIME from PF. Got size %u, expected %zu\n",
+ len, sizeof(*msg));
+ return;
+ }
+
+ adapter->ptp.cached_phc_time = msg->time;
+ adapter->ptp.cached_phc_updated = jiffies;
+ adapter->ptp.phc_time_ready = true;
+
+ wake_up(&adapter->ptp.phc_time_waitqueue);
+}
+
+/**
* iavf_virtchnl_completion
* @adapter: adapter structure
* @v_opcode: opcode sent by PF
@@ -2509,6 +2693,25 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
aq_required;
}
break;
+ case VIRTCHNL_OP_GET_SUPPORTED_RXDIDS:
+ if (msglen != sizeof(u64))
+ return;
+
+ adapter->supp_rxdids = *(u64 *)msg;
+
+ break;
+ case VIRTCHNL_OP_1588_PTP_GET_CAPS:
+ if (msglen != sizeof(adapter->ptp.hw_caps))
+ return;
+
+ adapter->ptp.hw_caps = *(struct virtchnl_ptp_caps *)msg;
+
+ /* process any state change needed due to new capabilities */
+ iavf_ptp_process_caps(adapter);
+ break;
+ case VIRTCHNL_OP_1588_PTP_GET_TIME:
+ iavf_virtchnl_ptp_get_time(adapter, msg, msglen);
+ break;
case VIRTCHNL_OP_ENABLE_QUEUES:
/* enable transmits */
iavf_irq_enable(adapter, true);