[Intel-wired-lan] [net-next v6 1/4] igb: add support of RX network flow classification

[Intel-wired-lan] [net-next v6 1/4] igb: add support of RX network flow classification

[Brown, Aaron F]

> From: Intel-wired-lan [mailto:intel-wired-lan-bounces at lists.osuosl.org] On
> Behalf Of Gangfeng
> Sent: Tuesday, July 5, 2016 10:23 PM
> To: intel-wired-lan at lists.osuosl.org
> Cc: Gangfeng Huang <gangfeng.huang@ni.com>; Ruhao Gao
> <ruhao.gao@ni.com>
> Subject: [Intel-wired-lan] [net-next v6 1/4] igb: add support of RX network
> flow classification
> 
> From: Gangfeng Huang <gangfeng.huang@ni.com>
> 
> This patch is meant to allow for RX network flow classification to insert
> and remove Rx filter by ethtool. Ethtool interface has it's own rules
> manager
> 
> Show all filters:
> $ ethtool -n eth0
> 4 RX rings available
> Total 2 rules
> 
> Signed-off-by: Ruhao Gao <ruhao.gao@ni.com>
> Signed-off-by: Gangfeng Huang <gangfeng.huang@ni.com>
> ---
>  drivers/net/ethernet/intel/igb/igb.h         |  32 +++++
>  drivers/net/ethernet/intel/igb/igb_ethtool.c | 193
> +++++++++++++++++++++++++++
>  drivers/net/ethernet/intel/igb/igb_main.c    |  45 +++++++
>  3 files changed, 270 insertions(+)
> 

Tested-by: Aaron Brown <aaron.f.brown@intel.com>

[Intel-wired-lan] [net-next v6 0/4] igb: enable RX network flow classification

[Gangfeng]

After apply this series of patches, igb driver will supports advanced
RX filter that direct receive packets by flows to different hardware
queue. Enables tight control on routing a flow in the platform.

In our product, we use the the RX traffic classification to gurantee the
PTP(ethertype is 0x88F7) packets won't be flooded by best effort packet.
PTP packets is always be processed by Linux network stack.

step 1. 
  use the ethertype filter to filter most of packet(0x0800) to HW queue;
step 2.
  Add a rule to forward the PTP packets to another HW queue

The ethtool commands and options:

-n --show-nfc
   Retrieves the receive network flow classification configurations

-N --config-nfc
   Configures the receive network flow classification classification

Change history of this patches:
Version 1:
  Split the patch to 3 patches for review;
  Save the filters and restore them after a reset;
  In ethtool command, use key word "proto" to replace "vlan-etype:
  Fix bugs
Version 2:
  Rebase the patches on the the latest dev-queue;
Version 3:
  Report a meaningful error code for misoperation;
Version 4:
  Rebase the patches on latest dev-queue;
  Update the patch description and code comments; 
Version 5:
  Rebase the patches on latest dev-queue;
  Update the patch description; 
Version 6:
  Init the nfc_lock in igb_sw_init()

Gangfeng Huang (4):
  igb: add support of RX network flow classification
  igb: support RX flow classification by ethertype
  igb: support RX flow classification by VLAN priority
  igb: fix error code in igb_add_ethtool_nfc_entry()

 drivers/net/ethernet/intel/igb/e1000_82575.h   |   5 +
 drivers/net/ethernet/intel/igb/e1000_defines.h |   4 +
 drivers/net/ethernet/intel/igb/e1000_regs.h    |   1 +
 drivers/net/ethernet/intel/igb/igb.h           |  53 ++++
 drivers/net/ethernet/intel/igb/igb_ethtool.c   | 345 +++++++++++++++++++++++++
 drivers/net/ethernet/intel/igb/igb_main.c      |  45 ++++
 drivers/net/ethernet/intel/igb/igb_ptp.c       |   4 +-
 7 files changed, 455 insertions(+), 2 deletions(-)

-- 
2.7.2

[Intel-wired-lan] [net-next v6 1/4] igb: add support of RX network flow classification

[Gangfeng]

From: Gangfeng Huang <gangfeng.huang@ni.com>

This patch is meant to allow for RX network flow classification to insert
and remove Rx filter by ethtool. Ethtool interface has it's own rules
manager

Show all filters:
$ ethtool -n eth0
4 RX rings available
Total 2 rules

Signed-off-by: Ruhao Gao <ruhao.gao@ni.com>
Signed-off-by: Gangfeng Huang <gangfeng.huang@ni.com>
---
 drivers/net/ethernet/intel/igb/igb.h         |  32 +++++
 drivers/net/ethernet/intel/igb/igb_ethtool.c | 193 +++++++++++++++++++++++++++
 drivers/net/ethernet/intel/igb/igb_main.c    |  45 +++++++
 3 files changed, 270 insertions(+)

diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 5387b3a..042467a 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -355,6 +355,27 @@ struct hwmon_buff {
 #define IGB_N_SDP	4
 #define IGB_RETA_SIZE	128
 
+enum igb_filter_match_flags {
+	IGB_FILTER_FLAG_NONE        = 0x0,
+};
+
+#define IGB_MAX_RXNFC_FILTERS 16
+
+/* RX network flow classification data structure */
+struct igb_nfc_input {
+	/* Byte layout in order, all values with MSB first:
+	* match_flags - 1 byte
+	*/
+	u8     match_flags;
+};
+
+struct igb_nfc_filter {
+	struct hlist_node nfc_node;
+	struct igb_nfc_input filter;
+	u16 sw_idx;
+	u16 action;
+};
+
 /* board specific private data structure */
 struct igb_adapter {
 	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
@@ -473,6 +494,12 @@ struct igb_adapter {
 	int copper_tries;
 	struct e1000_info ei;
 	u16 eee_advert;
+
+	/* RX network flow classification support */
+	struct hlist_head nfc_filter_list;
+	unsigned int nfc_filter_count;
+	/* lock for RX network flow classification filter */
+	spinlock_t nfc_lock;
 };
 
 /* flags controlling PTP/1588 function */
@@ -599,4 +626,9 @@ static inline struct netdev_queue *txring_txq(const struct igb_ring *tx_ring)
 	return netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index);
 }
 
+int igb_add_filter(struct igb_adapter *adapter,
+		   struct igb_nfc_filter *input);
+int igb_erase_filter(struct igb_adapter *adapter,
+		     struct igb_nfc_filter *input);
+
 #endif /* _IGB_H_ */
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 64e91c5..2599826 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -2431,6 +2431,48 @@ static int igb_get_ts_info(struct net_device *dev,
 	}
 }
 
+static int igb_get_ethtool_nfc_entry(struct igb_adapter *adapter,
+				     struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fsp = &cmd->fs;
+	struct igb_nfc_filter *rule = NULL;
+
+	/* report total rule count */
+	cmd->data = IGB_MAX_RXNFC_FILTERS;
+
+	hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) {
+		if (fsp->location <= rule->sw_idx)
+			break;
+	}
+
+	if (!rule || fsp->location != rule->sw_idx)
+		return -EINVAL;
+
+	return -EINVAL;
+}
+
+static int igb_get_ethtool_nfc_all(struct igb_adapter *adapter,
+				   struct ethtool_rxnfc *cmd,
+				   u32 *rule_locs)
+{
+	struct igb_nfc_filter *rule;
+	int cnt = 0;
+
+	/* report total rule count */
+	cmd->data = IGB_MAX_RXNFC_FILTERS;
+
+	hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) {
+		if (cnt == cmd->rule_cnt)
+			return -EMSGSIZE;
+		rule_locs[cnt] = rule->sw_idx;
+		cnt++;
+	}
+
+	cmd->rule_cnt = cnt;
+
+	return 0;
+}
+
 static int igb_get_rss_hash_opts(struct igb_adapter *adapter,
 				 struct ethtool_rxnfc *cmd)
 {
@@ -2484,6 +2526,16 @@ static int igb_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 		cmd->data = adapter->num_rx_queues;
 		ret = 0;
 		break;
+	case ETHTOOL_GRXCLSRLCNT:
+		cmd->rule_cnt = adapter->nfc_filter_count;
+		ret = 0;
+		break;
+	case ETHTOOL_GRXCLSRULE:
+		ret = igb_get_ethtool_nfc_entry(adapter, cmd);
+		break;
+	case ETHTOOL_GRXCLSRLALL:
+		ret = igb_get_ethtool_nfc_all(adapter, cmd, rule_locs);
+		break;
 	case ETHTOOL_GRXFH:
 		ret = igb_get_rss_hash_opts(adapter, cmd);
 		break;
@@ -2598,6 +2650,142 @@ static int igb_set_rss_hash_opt(struct igb_adapter *adapter,
 	return 0;
 }
 
+int igb_add_filter(struct igb_adapter *adapter, struct igb_nfc_filter *input)
+{
+	return -EINVAL;
+}
+
+int igb_erase_filter(struct igb_adapter *adapter, struct igb_nfc_filter *input)
+{
+	return 0;
+}
+
+static int igb_update_ethtool_nfc_entry(struct igb_adapter *adapter,
+					struct igb_nfc_filter *input,
+					u16 sw_idx)
+{
+	struct igb_nfc_filter *rule, *parent;
+	int err = -EINVAL;
+
+	parent = NULL;
+	rule = NULL;
+
+	hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) {
+		/* hash found, or no matching entry */
+		if (rule->sw_idx >= sw_idx)
+			break;
+		parent = rule;
+	}
+
+	/* if there is an old rule occupying our place remove it */
+	if (rule && (rule->sw_idx == sw_idx)) {
+		if (!input)
+			err = igb_erase_filter(adapter, rule);
+
+		hlist_del(&rule->nfc_node);
+		kfree(rule);
+		adapter->nfc_filter_count--;
+	}
+
+	/* If no input this was a delete, err should be 0 if a rule was
+	 * successfully found and removed from the list else -EINVAL
+	 */
+	if (!input)
+		return err;
+
+	/* initialize node */
+	INIT_HLIST_NODE(&input->nfc_node);
+
+	/* add filter to the list */
+	if (parent)
+		hlist_add_behind(&parent->nfc_node, &input->nfc_node);
+	else
+		hlist_add_head(&input->nfc_node, &adapter->nfc_filter_list);
+
+	/* update counts */
+	adapter->nfc_filter_count++;
+
+	return 0;
+}
+
+static int igb_add_ethtool_nfc_entry(struct igb_adapter *adapter,
+				     struct ethtool_rxnfc *cmd)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct ethtool_rx_flow_spec *fsp =
+		(struct ethtool_rx_flow_spec *)&cmd->fs;
+	struct igb_nfc_filter *input, *rule;
+	int err = 0;
+
+	if (!(netdev->hw_features & NETIF_F_NTUPLE))
+		return -ENOTSUPP;
+
+	/* Don't allow programming if the action is a queue greater than
+	 * the number of online Rx queues.
+	 */
+	if ((fsp->ring_cookie == RX_CLS_FLOW_DISC) ||
+	    (fsp->ring_cookie >= adapter->num_rx_queues)) {
+		dev_err(&adapter->pdev->dev, "ethtool -N: The specified action is invalid\n");
+		return -EINVAL;
+	}
+
+	/* Don't allow indexes to exist outside of available space */
+	if (fsp->location >= IGB_MAX_RXNFC_FILTERS) {
+		dev_err(&adapter->pdev->dev, "Location out of range\n");
+		return -EINVAL;
+	}
+
+	if ((fsp->flow_type & ~FLOW_EXT) != ETHER_FLOW)
+		return -EINVAL;
+
+	input = kzalloc(sizeof(*input), GFP_KERNEL);
+	if (!input)
+		return -ENOMEM;
+
+	input->action = fsp->ring_cookie;
+	input->sw_idx = fsp->location;
+
+	spin_lock(&adapter->nfc_lock);
+
+	hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) {
+		if (!memcmp(&input->filter, &rule->filter,
+			    sizeof(input->filter))) {
+			err = -EEXIST;
+			dev_err(&adapter->pdev->dev,
+				"ethtool: this filter is already set\n");
+			goto err_out_w_lock;
+		}
+	}
+
+	err = igb_add_filter(adapter, input);
+	if (err)
+		goto err_out_w_lock;
+
+	igb_update_ethtool_nfc_entry(adapter, input, input->sw_idx);
+
+	spin_unlock(&adapter->nfc_lock);
+	return 0;
+
+err_out_w_lock:
+	spin_unlock(&adapter->nfc_lock);
+	kfree(input);
+	return err;
+}
+
+static int igb_del_ethtool_nfc_entry(struct igb_adapter *adapter,
+				     struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fsp =
+		(struct ethtool_rx_flow_spec *)&cmd->fs;
+	int err;
+
+	spin_lock(&adapter->nfc_lock);
+	err = igb_update_ethtool_nfc_entry(adapter, NULL, fsp->location);
+	spin_unlock(&adapter->nfc_lock);
+
+	return err;
+}
+
 static int igb_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 {
 	struct igb_adapter *adapter = netdev_priv(dev);
@@ -2607,6 +2795,11 @@ static int igb_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 	case ETHTOOL_SRXFH:
 		ret = igb_set_rss_hash_opt(adapter, cmd);
 		break;
+	case ETHTOOL_SRXCLSRLINS:
+		ret = igb_add_ethtool_nfc_entry(adapter, cmd);
+		break;
+	case ETHTOOL_SRXCLSRLDEL:
+		ret = igb_del_ethtool_nfc_entry(adapter, cmd);
 	default:
 		break;
 	}
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 9bcba42..e5a4949 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -176,6 +176,8 @@ static int igb_ndo_set_vf_spoofchk(struct net_device *netdev, int vf,
 static int igb_ndo_get_vf_config(struct net_device *netdev, int vf,
 				 struct ifla_vf_info *ivi);
 static void igb_check_vf_rate_limit(struct igb_adapter *);
+static void igb_nfc_filter_exit(struct igb_adapter *adapter);
+static void igb_nfc_filter_restore(struct igb_adapter *adapter);
 
 #ifdef CONFIG_PCI_IOV
 static int igb_vf_configure(struct igb_adapter *adapter, int vf);
@@ -1611,6 +1613,7 @@ static void igb_configure(struct igb_adapter *adapter)
 	igb_setup_mrqc(adapter);
 	igb_setup_rctl(adapter);
 
+	igb_nfc_filter_restore(adapter);
 	igb_configure_tx(adapter);
 	igb_configure_rx(adapter);
 
@@ -2059,6 +2062,21 @@ static int igb_set_features(struct net_device *netdev,
 	if (!(changed & (NETIF_F_RXALL | NETIF_F_NTUPLE)))
 		return 0;
 
+	if (!(features & NETIF_F_NTUPLE)) {
+		struct hlist_node *node2;
+		struct igb_nfc_filter *rule;
+
+		spin_lock(&adapter->nfc_lock);
+		hlist_for_each_entry_safe(rule, node2,
+					  &adapter->nfc_filter_list, nfc_node) {
+			igb_erase_filter(adapter, rule);
+			hlist_del(&rule->nfc_node);
+			kfree(rule);
+		}
+		spin_unlock(&adapter->nfc_lock);
+		adapter->nfc_filter_count = 0;
+	}
+
 	netdev->features = features;
 
 	if (netif_running(netdev))
@@ -3057,6 +3075,7 @@ static int igb_sw_init(struct igb_adapter *adapter)
 				  VLAN_HLEN;
 	adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
 
+	spin_lock_init(&adapter->nfc_lock);
 	spin_lock_init(&adapter->stats64_lock);
 #ifdef CONFIG_PCI_IOV
 	switch (hw->mac.type) {
@@ -3244,6 +3263,8 @@ static int __igb_close(struct net_device *netdev, bool suspending)
 	igb_down(adapter);
 	igb_free_irq(adapter);
 
+	igb_nfc_filter_exit(adapter);
+
 	igb_free_all_tx_resources(adapter);
 	igb_free_all_rx_resources(adapter);
 
@@ -8310,4 +8331,28 @@ int igb_reinit_queues(struct igb_adapter *adapter)
 
 	return err;
 }
+
+static void igb_nfc_filter_exit(struct igb_adapter *adapter)
+{
+	struct igb_nfc_filter *rule;
+
+	spin_lock(&adapter->nfc_lock);
+
+	hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node)
+		igb_erase_filter(adapter, rule);
+
+	spin_unlock(&adapter->nfc_lock);
+}
+
+static void igb_nfc_filter_restore(struct igb_adapter *adapter)
+{
+	struct igb_nfc_filter *rule;
+
+	spin_lock(&adapter->nfc_lock);
+
+	hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node)
+		igb_add_filter(adapter, rule);
+
+	spin_unlock(&adapter->nfc_lock);
+}
 /* igb_main.c */
-- 
2.7.2