[net-next-2.6 PATCH v5 0/3] Introduce n-tuple ethtool support

[net-next-2.6 PATCH v5 0/3] Introduce n-tuple ethtool support

[Jeff Kirsher]

One more round of fixes, based on feedback from Patrick McHardy

1) Change the list count to an unsigned value
2) Fix a memory leak
3) Removed an unnecessary list traversal in the ethtool core
4) Moved all list destruction to a helper function, allowing the driver
to control when it clears the list (aside from when free_netdev() kills
the cached list).

---

Peter Waskiewicz (3):
      ixgbe: Bump driver version up
      ixgbe: Add support for the new ethtool n-tuple programming interface
      ethtool: Introduce n-tuple filter programming support


 drivers/net/ixgbe/ixgbe.h         |    4 
 drivers/net/ixgbe/ixgbe_82599.c   |  106 ++++++++++--
 drivers/net/ixgbe/ixgbe_ethtool.c |  111 ++++++++++++
 drivers/net/ixgbe/ixgbe_main.c    |   18 ++
 drivers/net/ixgbe/ixgbe_type.h    |    9 +
 include/linux/ethtool.h           |   50 ++++++
 include/linux/netdevice.h         |    3 
 net/core/dev.c                    |    6 +
 net/core/ethtool.c                |  332 +++++++++++++++++++++++++++++++++++++
 9 files changed, 619 insertions(+), 20 deletions(-)

-- 
Cheers,
Jeff

[net-next-2.6 PATCH v5 1/3] ethtool: Introduce n-tuple filter programming support

[Jeff Kirsher]

From: Peter Waskiewicz <peter.p.waskiewicz.jr@intel.com>

This patchset enables the ethtool layer to program n-tuple
filters to an underlying device.  The idea is to allow capable
hardware to have static rules applied that can assist steering
flows into appropriate queues.

Hardware that is known to support these types of filters today
are ixgbe and niu.

Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 include/linux/ethtool.h   |   50 +++++++
 include/linux/netdevice.h |    3 
 net/core/dev.c            |    6 +
 net/core/ethtool.c        |  332 +++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 390 insertions(+), 1 deletions(-)

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index ef4a2d8..a3cac53 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -14,6 +14,7 @@
 #define _LINUX_ETHTOOL_H
 
 #include <linux/types.h>
+#include <linux/rculist.h>
 
 /* This should work for both 32 and 64 bit userland. */
 struct ethtool_cmd {
@@ -242,6 +243,7 @@ enum ethtool_stringset {
 	ETH_SS_TEST		= 0,
 	ETH_SS_STATS,
 	ETH_SS_PRIV_FLAGS,
+	ETH_SS_NTUPLE_FILTERS,
 };
 
 /* for passing string sets for data tagging */
@@ -290,6 +292,7 @@ struct ethtool_perm_addr {
  */
 enum ethtool_flags {
 	ETH_FLAG_LRO		= (1 << 15),	/* LRO is enabled */
+	ETH_FLAG_NTUPLE		= (1 << 27),	/* N-tuple filters enabled */
 };
 
 /* The following structures are for supporting RX network flow
@@ -363,6 +366,35 @@ struct ethtool_rxnfc {
 	__u32				rule_locs[0];
 };
 
+struct ethtool_rx_ntuple_flow_spec {
+	__u32		 flow_type;
+	union {
+		struct ethtool_tcpip4_spec		tcp_ip4_spec;
+		struct ethtool_tcpip4_spec		udp_ip4_spec;
+		struct ethtool_tcpip4_spec		sctp_ip4_spec;
+		struct ethtool_ah_espip4_spec		ah_ip4_spec;
+		struct ethtool_ah_espip4_spec		esp_ip4_spec;
+		struct ethtool_rawip4_spec		raw_ip4_spec;
+		struct ethtool_ether_spec		ether_spec;
+		struct ethtool_usrip4_spec		usr_ip4_spec;
+		__u8					hdata[64];
+	} h_u, m_u; /* entry, mask */
+
+	__u16	        vlan_tag;
+	__u16	        vlan_tag_mask;
+	__u64		data;      /* user-defined flow spec data */
+	__u64		data_mask; /* user-defined flow spec mask */
+
+	/* signed to distinguish between queue and actions (DROP) */
+	__s32		action;
+#define ETHTOOL_RXNTUPLE_ACTION_DROP -1
+};
+
+struct ethtool_rx_ntuple {
+	__u32					cmd;
+	struct ethtool_rx_ntuple_flow_spec	fs;
+};
+
 #define ETHTOOL_FLASH_MAX_FILENAME	128
 enum ethtool_flash_op_type {
 	ETHTOOL_FLASH_ALL_REGIONS	= 0,
@@ -377,6 +409,18 @@ struct ethtool_flash {
 
 #ifdef __KERNEL__
 
+struct ethtool_rx_ntuple_flow_spec_container {
+	struct ethtool_rx_ntuple_flow_spec fs;
+	struct list_head list;
+};
+
+struct ethtool_rx_ntuple_list {
+#define ETHTOOL_MAX_NTUPLE_LIST_ENTRY 1024
+#define ETHTOOL_MAX_NTUPLE_STRING_PER_ENTRY 14
+	struct list_head	list;
+	unsigned int		count;
+};
+
 struct net_device;
 
 /* Some generic methods drivers may use in their ethtool_ops */
@@ -394,6 +438,7 @@ u32 ethtool_op_get_ufo(struct net_device *dev);
 int ethtool_op_set_ufo(struct net_device *dev, u32 data);
 u32 ethtool_op_get_flags(struct net_device *dev);
 int ethtool_op_set_flags(struct net_device *dev, u32 data);
+void ethtool_ntuple_flush(struct net_device *dev);
 
 /**
  * &ethtool_ops - Alter and report network device settings
@@ -500,6 +545,8 @@ struct ethtool_ops {
 	int	(*set_rxnfc)(struct net_device *, struct ethtool_rxnfc *);
 	int     (*flash_device)(struct net_device *, struct ethtool_flash *);
 	int	(*reset)(struct net_device *, u32 *);
+	int	(*set_rx_ntuple)(struct net_device *, struct ethtool_rx_ntuple *);
+	int	(*get_rx_ntuple)(struct net_device *, u32 stringset, void *);
 };
 #endif /* __KERNEL__ */
 
@@ -559,6 +606,9 @@ struct ethtool_ops {
 #define	ETHTOOL_FLASHDEV	0x00000033 /* Flash firmware to device */
 #define	ETHTOOL_RESET		0x00000034 /* Reset hardware */
 
+#define ETHTOOL_SRXNTUPLE	0x00000035 /* Add an n-tuple filter to device */
+#define ETHTOOL_GRXNTUPLE	0x00000036 /* Get n-tuple filters from device */
+
 /* compatibility with older code */
 #define SPARC_ETH_GSET		ETHTOOL_GSET
 #define SPARC_ETH_SSET		ETHTOOL_SSET
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e535700..cdf53a8 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -746,6 +746,7 @@ struct net_device {
 #define NETIF_F_FCOE_CRC	(1 << 24) /* FCoE CRC32 */
 #define NETIF_F_SCTP_CSUM	(1 << 25) /* SCTP checksum offload */
 #define NETIF_F_FCOE_MTU	(1 << 26) /* Supports max FCoE MTU, 2158 bytes*/
+#define NETIF_F_NTUPLE		(1 << 27) /* N-tuple filters supported */
 
 	/* Segmentation offload features */
 #define NETIF_F_GSO_SHIFT	16
@@ -954,6 +955,8 @@ struct net_device {
 	/* max exchange id for FCoE LRO by ddp */
 	unsigned int		fcoe_ddp_xid;
 #endif
+	/* n-tuple filter list attached to this device */
+	struct ethtool_rx_ntuple_list ethtool_ntuple_list;
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 94c1eee..8b3ad65 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5419,6 +5419,8 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name,
 
 	netdev_init_queues(dev);
 
+	INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list);
+	dev->ethtool_ntuple_list.count = 0;
 	INIT_LIST_HEAD(&dev->napi_list);
 	INIT_LIST_HEAD(&dev->unreg_list);
 	INIT_LIST_HEAD(&dev->link_watch_list);
@@ -5447,6 +5449,7 @@ EXPORT_SYMBOL(alloc_netdev_mq);
 void free_netdev(struct net_device *dev)
 {
 	struct napi_struct *p, *n;
+	struct ethtool_rx_ntuple_flow_spec_container *fsc, *f;
 
 	release_net(dev_net(dev));
 
@@ -5455,6 +5458,9 @@ void free_netdev(struct net_device *dev)
 	/* Flush device addresses */
 	dev_addr_flush(dev);
 
+	/* Clear ethtool n-tuple list */
+	ethtool_ntuple_flush(dev);
+
 	list_for_each_entry_safe(p, n, &dev->napi_list, dev_list)
 		netif_napi_del(p);
 
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index d8aee58..f22ce4b 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -120,7 +120,7 @@ int ethtool_op_set_ufo(struct net_device *dev, u32 data)
  * NETIF_F_xxx values in include/linux/netdevice.h
  */
 static const u32 flags_dup_features =
-	ETH_FLAG_LRO;
+	(ETH_FLAG_LRO | ETH_FLAG_NTUPLE);
 
 u32 ethtool_op_get_flags(struct net_device *dev)
 {
@@ -139,9 +139,26 @@ int ethtool_op_set_flags(struct net_device *dev, u32 data)
 	else
 		dev->features &= ~NETIF_F_LRO;
 
+	if (data & ETH_FLAG_NTUPLE)
+		dev->features |= NETIF_F_NTUPLE;
+	else
+		dev->features &= ~NETIF_F_NTUPLE;
+
 	return 0;
 }
 
+void ethtool_ntuple_flush(struct net_device *dev)
+{
+	struct ethtool_rx_ntuple_flow_spec_container *fsc, *f;
+
+	list_for_each_entry_safe(fsc, f, &dev->ethtool_ntuple_list.list, list) {
+		list_del(&fsc->list);
+		kfree(fsc);
+	}
+	dev->ethtool_ntuple_list.count = 0;
+}
+EXPORT_SYMBOL(ethtool_ntuple_flush);
+
 /* Handlers for each ethtool command */
 
 static int ethtool_get_settings(struct net_device *dev, void __user *useraddr)
@@ -266,6 +283,307 @@ err_out:
 	return ret;
 }
 
+static int __rx_ntuple_filter_add(struct ethtool_rx_ntuple_list *list,
+                                  struct ethtool_rx_ntuple_flow_spec *spec)
+{
+	struct ethtool_rx_ntuple_flow_spec_container *fsc;
+
+	/* don't add filters forever */
+	if (list->count >= ETHTOOL_MAX_NTUPLE_LIST_ENTRY)
+		return 0;
+
+	fsc = kmalloc(sizeof(*fsc), GFP_ATOMIC);
+	if (!fsc)
+		return -ENOMEM;
+
+	/* Copy the whole filter over */
+	fsc->fs.flow_type = spec->flow_type;
+	memcpy(&fsc->fs.h_u, &spec->h_u, sizeof(spec->h_u));
+	memcpy(&fsc->fs.m_u, &spec->m_u, sizeof(spec->m_u));
+
+	fsc->fs.vlan_tag = spec->vlan_tag;
+	fsc->fs.vlan_tag_mask = spec->vlan_tag_mask;
+	fsc->fs.data = spec->data;
+	fsc->fs.data_mask = spec->data_mask;
+	fsc->fs.action = spec->action;
+
+	/* add to the list */
+	list_add_tail_rcu(&fsc->list, &list->list);
+	list->count++;
+
+	return 0;
+}
+
+static int ethtool_set_rx_ntuple(struct net_device *dev, void __user *useraddr)
+{
+	struct ethtool_rx_ntuple cmd;
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	int ret;
+
+	if (!ops->set_rx_ntuple)
+		return -EOPNOTSUPP;
+
+	if (!(dev->features & NETIF_F_NTUPLE))
+		return -EINVAL;
+
+	if (copy_from_user(&cmd, useraddr, sizeof(cmd)))
+		return -EFAULT;
+
+	ret = ops->set_rx_ntuple(dev, &cmd);
+
+	/*
+	 * Cache filter in dev struct for GET operation only if
+	 * the underlying driver doesn't have its own GET operation, and
+	 * only if the filter was added successfully.
+	 */
+	if (!ops->get_rx_ntuple && !ret)
+		if (__rx_ntuple_filter_add(&dev->ethtool_ntuple_list, &cmd.fs))
+			return -ENOMEM;
+
+	return ret;
+}
+
+static int ethtool_get_rx_ntuple(struct net_device *dev, void __user *useraddr)
+{
+	struct ethtool_gstrings gstrings;
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	struct ethtool_rx_ntuple_flow_spec_container *fsc;
+	u8 *data;
+	char *p;
+	int ret, i, num_strings = 0;
+
+	if (!ops->get_sset_count)
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&gstrings, useraddr, sizeof(gstrings)))
+		return -EFAULT;
+
+	ret = ops->get_sset_count(dev, gstrings.string_set);
+	if (ret < 0)
+		return ret;
+
+	gstrings.len = ret;
+
+	data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER);
+	if (!data)
+		return -ENOMEM;
+
+	if (ops->get_rx_ntuple) {
+		/* driver-specific filter grab */
+		ret = ops->get_rx_ntuple(dev, gstrings.string_set, data);
+		goto copy;
+	}
+
+	/* default ethtool filter grab */
+	i = 0;
+	p = (char *)data;
+	list_for_each_entry(fsc, &dev->ethtool_ntuple_list.list, list) {
+		sprintf(p, "Filter %d:\n", i);
+		p += ETH_GSTRING_LEN;
+		num_strings++;
+
+		switch (fsc->fs.flow_type) {
+		case TCP_V4_FLOW:
+			sprintf(p, "\tFlow Type: TCP\n");
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			break;
+		case UDP_V4_FLOW:
+			sprintf(p, "\tFlow Type: UDP\n");
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			break;
+		case SCTP_V4_FLOW:
+			sprintf(p, "\tFlow Type: SCTP\n");
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			break;
+		case AH_ESP_V4_FLOW:
+			sprintf(p, "\tFlow Type: AH ESP\n");
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			break;
+		case ESP_V4_FLOW:
+			sprintf(p, "\tFlow Type: ESP\n");
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			break;
+		case IP_USER_FLOW:
+			sprintf(p, "\tFlow Type: Raw IP\n");
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			break;
+		case IPV4_FLOW:
+			sprintf(p, "\tFlow Type: IPv4\n");
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			break;
+		default:
+			sprintf(p, "\tFlow Type: Unknown\n");
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			goto unknown_filter;
+		};
+
+		/* now the rest of the filters */
+		switch (fsc->fs.flow_type) {
+		case TCP_V4_FLOW:
+		case UDP_V4_FLOW:
+		case SCTP_V4_FLOW:
+			sprintf(p, "\tSrc IP addr: 0x%x\n",
+			        fsc->fs.h_u.tcp_ip4_spec.ip4src);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tSrc IP mask: 0x%x\n",
+			        fsc->fs.m_u.tcp_ip4_spec.ip4src);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tDest IP addr: 0x%x\n",
+			        fsc->fs.h_u.tcp_ip4_spec.ip4dst);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tDest IP mask: 0x%x\n",
+			        fsc->fs.m_u.tcp_ip4_spec.ip4dst);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tSrc Port: %d, mask: 0x%x\n",
+			        fsc->fs.h_u.tcp_ip4_spec.psrc,
+			        fsc->fs.m_u.tcp_ip4_spec.psrc);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tDest Port: %d, mask: 0x%x\n",
+			        fsc->fs.h_u.tcp_ip4_spec.pdst,
+			        fsc->fs.m_u.tcp_ip4_spec.pdst);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tTOS: %d, mask: 0x%x\n",
+			        fsc->fs.h_u.tcp_ip4_spec.tos,
+			        fsc->fs.m_u.tcp_ip4_spec.tos);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			break;
+		case AH_ESP_V4_FLOW:
+		case ESP_V4_FLOW:
+			sprintf(p, "\tSrc IP addr: 0x%x\n",
+			        fsc->fs.h_u.ah_ip4_spec.ip4src);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tSrc IP mask: 0x%x\n",
+			        fsc->fs.m_u.ah_ip4_spec.ip4src);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tDest IP addr: 0x%x\n",
+			        fsc->fs.h_u.ah_ip4_spec.ip4dst);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tDest IP mask: 0x%x\n",
+			        fsc->fs.m_u.ah_ip4_spec.ip4dst);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tSPI: %d, mask: 0x%x\n",
+			        fsc->fs.h_u.ah_ip4_spec.spi,
+			        fsc->fs.m_u.ah_ip4_spec.spi);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tTOS: %d, mask: 0x%x\n",
+			        fsc->fs.h_u.ah_ip4_spec.tos,
+			        fsc->fs.m_u.ah_ip4_spec.tos);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			break;
+		case IP_USER_FLOW:
+			sprintf(p, "\tSrc IP addr: 0x%x\n",
+			        fsc->fs.h_u.raw_ip4_spec.ip4src);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tSrc IP mask: 0x%x\n",
+			        fsc->fs.m_u.raw_ip4_spec.ip4src);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tDest IP addr: 0x%x\n",
+			        fsc->fs.h_u.raw_ip4_spec.ip4dst);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tDest IP mask: 0x%x\n",
+			        fsc->fs.m_u.raw_ip4_spec.ip4dst);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			break;
+		case IPV4_FLOW:
+			sprintf(p, "\tSrc IP addr: 0x%x\n",
+			        fsc->fs.h_u.usr_ip4_spec.ip4src);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tSrc IP mask: 0x%x\n",
+			        fsc->fs.m_u.usr_ip4_spec.ip4src);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tDest IP addr: 0x%x\n",
+			        fsc->fs.h_u.usr_ip4_spec.ip4dst);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tDest IP mask: 0x%x\n",
+			        fsc->fs.m_u.usr_ip4_spec.ip4dst);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tL4 bytes: 0x%x, mask: 0x%x\n",
+			        fsc->fs.h_u.usr_ip4_spec.l4_4_bytes,
+			        fsc->fs.m_u.usr_ip4_spec.l4_4_bytes);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tTOS: %d, mask: 0x%x\n",
+			        fsc->fs.h_u.usr_ip4_spec.tos,
+			        fsc->fs.m_u.usr_ip4_spec.tos);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tIP Version: %d, mask: 0x%x\n",
+			        fsc->fs.h_u.usr_ip4_spec.ip_ver,
+			        fsc->fs.m_u.usr_ip4_spec.ip_ver);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			sprintf(p, "\tProtocol: %d, mask: 0x%x\n",
+			        fsc->fs.h_u.usr_ip4_spec.proto,
+			        fsc->fs.m_u.usr_ip4_spec.proto);
+			p += ETH_GSTRING_LEN;
+			num_strings++;
+			break;
+		};
+		sprintf(p, "\tVLAN: %d, mask: 0x%x\n",
+		        fsc->fs.vlan_tag, fsc->fs.vlan_tag_mask);
+		p += ETH_GSTRING_LEN;
+		num_strings++;
+		sprintf(p, "\tUser-defined: 0x%Lx\n", fsc->fs.data);
+		p += ETH_GSTRING_LEN;
+		num_strings++;
+		sprintf(p, "\tUser-defined mask: 0x%Lx\n", fsc->fs.data_mask);
+		p += ETH_GSTRING_LEN;
+		num_strings++;
+		if (fsc->fs.action == ETHTOOL_RXNTUPLE_ACTION_DROP)
+			sprintf(p, "\tAction: Drop\n");
+		else
+			sprintf(p, "\tAction: Direct to queue %d\n",
+			        fsc->fs.action);
+		p += ETH_GSTRING_LEN;
+		num_strings++;
+unknown_filter:
+		i++;
+	}
+copy:
+	/* indicate to userspace how many strings we actually have */
+	gstrings.len = num_strings;
+	ret = -EFAULT;
+	if (copy_to_user(useraddr, &gstrings, sizeof(gstrings)))
+		goto out;
+	useraddr += sizeof(gstrings);
+	if (copy_to_user(useraddr, data, gstrings.len * ETH_GSTRING_LEN))
+		goto out;
+	ret = 0;
+
+out:
+	kfree(data);
+	return ret;
+}
+
 static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
 {
 	struct ethtool_regs regs;
@@ -305,6 +623,7 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
 static int ethtool_reset(struct net_device *dev, char __user *useraddr)
 {
 	struct ethtool_value reset;
+	struct ethtool_rx_ntuple_flow_spec_container *fsc, *f;
 	int ret;
 
 	if (!dev->ethtool_ops->reset)
@@ -313,6 +632,9 @@ static int ethtool_reset(struct net_device *dev, char __user *useraddr)
 	if (copy_from_user(&reset, useraddr, sizeof(reset)))
 		return -EFAULT;
 
+	/* Clear ethtool n-tuple list */
+	ethtool_ntuple_flush(dev);
+
 	ret = dev->ethtool_ops->reset(dev, &reset.data);
 	if (ret)
 		return ret;
@@ -351,6 +673,8 @@ static int ethtool_set_wol(struct net_device *dev, char __user *useraddr)
 
 static int ethtool_nway_reset(struct net_device *dev)
 {
+	struct ethtool_rx_ntuple_flow_spec_container *fsc, *f;
+
 	if (!dev->ethtool_ops->nway_reset)
 		return -EOPNOTSUPP;
 
@@ -1112,6 +1436,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	case ETHTOOL_RESET:
 		rc = ethtool_reset(dev, useraddr);
 		break;
+	case ETHTOOL_SRXNTUPLE:
+		rc = ethtool_set_rx_ntuple(dev, useraddr);
+		break;
+	case ETHTOOL_GRXNTUPLE:
+		rc = ethtool_get_rx_ntuple(dev, useraddr);
+		break;
 	default:
 		rc = -EOPNOTSUPP;
 	}

[net-next-2.6 PATCH v5 2/3] ixgbe: Add support for the new ethtool n-tuple programming interface

[Jeff Kirsher]

From: Peter Waskiewicz <peter.p.waskiewicz.jr@intel.com>

This patch adds n-tuple filter programming to 82599.

Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/ixgbe/ixgbe.h         |    4 +
 drivers/net/ixgbe/ixgbe_82599.c   |  106 +++++++++++++++++++++++++++++++----
 drivers/net/ixgbe/ixgbe_ethtool.c |  111 ++++++++++++++++++++++++++++++++++++-
 drivers/net/ixgbe/ixgbe_main.c    |   16 +++++
 drivers/net/ixgbe/ixgbe_type.h    |    9 +++
 5 files changed, 228 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ixgbe/ixgbe.h b/drivers/net/ixgbe/ixgbe.h
index bffbe0d..19e94ee 100644
--- a/drivers/net/ixgbe/ixgbe.h
+++ b/drivers/net/ixgbe/ixgbe.h
@@ -453,6 +453,10 @@ extern s32 ixgbe_init_fdir_perfect_82599(struct ixgbe_hw *hw, u32 pballoc);
 extern s32 ixgbe_fdir_add_signature_filter_82599(struct ixgbe_hw *hw,
                                                  struct ixgbe_atr_input *input,
                                                  u8 queue);
+extern s32 ixgbe_fdir_add_perfect_filter_82599(struct ixgbe_hw *hw,
+                                      struct ixgbe_atr_input *input,
+                                      struct ixgbe_atr_input_masks *input_masks,
+                                      u16 soft_id, u8 queue);
 extern s32 ixgbe_atr_set_vlan_id_82599(struct ixgbe_atr_input *input,
                                        u16 vlan_id);
 extern s32 ixgbe_atr_set_src_ipv4_82599(struct ixgbe_atr_input *input,
diff --git a/drivers/net/ixgbe/ixgbe_82599.c b/drivers/net/ixgbe/ixgbe_82599.c
index d4ed6ad..4fa8633 100644
--- a/drivers/net/ixgbe/ixgbe_82599.c
+++ b/drivers/net/ixgbe/ixgbe_82599.c
@@ -1439,6 +1439,9 @@ s32 ixgbe_init_fdir_perfect_82599(struct ixgbe_hw *hw, u32 pballoc)
 	/* Send interrupt when 64 filters are left */
 	fdirctrl |= 4 << IXGBE_FDIRCTRL_FULL_THRESH_SHIFT;
 
+	/* Initialize the drop queue to Rx queue 127 */
+	fdirctrl |= (127 << IXGBE_FDIRCTRL_DROP_Q_SHIFT);
+
 	switch (pballoc) {
 	case IXGBE_FDIR_PBALLOC_64K:
 		/* 2k - 1 perfect filters */
@@ -1628,6 +1631,7 @@ static u16 ixgbe_atr_compute_hash_82599(struct ixgbe_atr_input *atr_input,
  *  ixgbe_atr_set_vlan_id_82599 - Sets the VLAN id in the ATR input stream
  *  @input: input stream to modify
  *  @vlan: the VLAN id to load
+ *  @vlan_mask: bitwise mask for the VLAN
  **/
 s32 ixgbe_atr_set_vlan_id_82599(struct ixgbe_atr_input *input, u16 vlan)
 {
@@ -1641,6 +1645,7 @@ s32 ixgbe_atr_set_vlan_id_82599(struct ixgbe_atr_input *input, u16 vlan)
  *  ixgbe_atr_set_src_ipv4_82599 - Sets the source IPv4 address
  *  @input: input stream to modify
  *  @src_addr: the IP address to load
+ *  @src_addr_mask: bitwise mask for the source IP address
  **/
 s32 ixgbe_atr_set_src_ipv4_82599(struct ixgbe_atr_input *input, u32 src_addr)
 {
@@ -1658,6 +1663,7 @@ s32 ixgbe_atr_set_src_ipv4_82599(struct ixgbe_atr_input *input, u32 src_addr)
  *  ixgbe_atr_set_dst_ipv4_82599 - Sets the destination IPv4 address
  *  @input: input stream to modify
  *  @dst_addr: the IP address to load
+ *  @dst_addr_mask: bitwise mask for the destination IP address
  **/
 s32 ixgbe_atr_set_dst_ipv4_82599(struct ixgbe_atr_input *input, u32 dst_addr)
 {
@@ -1680,8 +1686,8 @@ s32 ixgbe_atr_set_dst_ipv4_82599(struct ixgbe_atr_input *input, u32 dst_addr)
  *  @src_addr_4: the fourth 4 bytes of the IP address to load
  **/
 s32 ixgbe_atr_set_src_ipv6_82599(struct ixgbe_atr_input *input,
-                                        u32 src_addr_1, u32 src_addr_2,
-                                        u32 src_addr_3, u32 src_addr_4)
+                                 u32 src_addr_1, u32 src_addr_2,
+                                 u32 src_addr_3, u32 src_addr_4)
 {
 	input->byte_stream[IXGBE_ATR_SRC_IPV6_OFFSET] = src_addr_4 & 0xff;
 	input->byte_stream[IXGBE_ATR_SRC_IPV6_OFFSET + 1] =
@@ -1723,8 +1729,8 @@ s32 ixgbe_atr_set_src_ipv6_82599(struct ixgbe_atr_input *input,
  *  @dst_addr_4: the fourth 4 bytes of the IP address to load
  **/
 s32 ixgbe_atr_set_dst_ipv6_82599(struct ixgbe_atr_input *input,
-                                        u32 dst_addr_1, u32 dst_addr_2,
-                                        u32 dst_addr_3, u32 dst_addr_4)
+                                 u32 dst_addr_1, u32 dst_addr_2,
+                                 u32 dst_addr_3, u32 dst_addr_4)
 {
 	input->byte_stream[IXGBE_ATR_DST_IPV6_OFFSET] = dst_addr_4 & 0xff;
 	input->byte_stream[IXGBE_ATR_DST_IPV6_OFFSET + 1] =
@@ -1761,6 +1767,7 @@ s32 ixgbe_atr_set_dst_ipv6_82599(struct ixgbe_atr_input *input,
  *  ixgbe_atr_set_src_port_82599 - Sets the source port
  *  @input: input stream to modify
  *  @src_port: the source port to load
+ *  @src_port_mask: bitwise mask for the source port
  **/
 s32 ixgbe_atr_set_src_port_82599(struct ixgbe_atr_input *input, u16 src_port)
 {
@@ -1774,6 +1781,7 @@ s32 ixgbe_atr_set_src_port_82599(struct ixgbe_atr_input *input, u16 src_port)
  *  ixgbe_atr_set_dst_port_82599 - Sets the destination port
  *  @input: input stream to modify
  *  @dst_port: the destination port to load
+ *  @dst_port_mask: bitwise mask for the destination port
  **/
 s32 ixgbe_atr_set_dst_port_82599(struct ixgbe_atr_input *input, u16 dst_port)
 {
@@ -1802,7 +1810,7 @@ s32 ixgbe_atr_set_flex_byte_82599(struct ixgbe_atr_input *input, u16 flex_byte)
  *  @vm_pool: the Virtual Machine pool to load
  **/
 s32 ixgbe_atr_set_vm_pool_82599(struct ixgbe_atr_input *input,
-                                       u8 vm_pool)
+                                u8 vm_pool)
 {
 	input->byte_stream[IXGBE_ATR_VM_POOL_OFFSET] = vm_pool;
 
@@ -1826,8 +1834,7 @@ s32 ixgbe_atr_set_l4type_82599(struct ixgbe_atr_input *input, u8 l4type)
  *  @input: input stream to search
  *  @vlan: the VLAN id to load
  **/
-static s32 ixgbe_atr_get_vlan_id_82599(struct ixgbe_atr_input *input,
-                                       u16 *vlan)
+static s32 ixgbe_atr_get_vlan_id_82599(struct ixgbe_atr_input *input, u16 *vlan)
 {
 	*vlan = input->byte_stream[IXGBE_ATR_VLAN_OFFSET];
 	*vlan |= input->byte_stream[IXGBE_ATR_VLAN_OFFSET + 1] << 8;
@@ -2083,23 +2090,26 @@ s32 ixgbe_fdir_add_signature_filter_82599(struct ixgbe_hw *hw,
  *  ixgbe_fdir_add_perfect_filter_82599 - Adds a perfect filter
  *  @hw: pointer to hardware structure
  *  @input: input bitstream
+ *  @input_masks: bitwise masks for relevant fields
+ *  @soft_id: software index into the silicon hash tables for filter storage
  *  @queue: queue index to direct traffic to
  *
  *  Note that the caller to this function must lock before calling, since the
  *  hardware writes must be protected from one another.
  **/
 s32 ixgbe_fdir_add_perfect_filter_82599(struct ixgbe_hw *hw,
-                                               struct ixgbe_atr_input *input,
-                                               u16 soft_id,
-                                               u8 queue)
+                                      struct ixgbe_atr_input *input,
+                                      struct ixgbe_atr_input_masks *input_masks,
+                                      u16 soft_id, u8 queue)
 {
 	u32 fdircmd = 0;
 	u32 fdirhash;
-	u32 src_ipv4, dst_ipv4;
+	u32 src_ipv4 = 0, dst_ipv4 = 0;
 	u32 src_ipv6_1, src_ipv6_2, src_ipv6_3, src_ipv6_4;
 	u16 src_port, dst_port, vlan_id, flex_bytes;
 	u16 bucket_hash;
 	u8  l4type;
+	u8  fdirm = 0;
 
 	/* Get our input values */
 	ixgbe_atr_get_l4type_82599(input, &l4type);
@@ -2154,7 +2164,6 @@ s32 ixgbe_fdir_add_perfect_filter_82599(struct ixgbe_hw *hw,
 		/* IPv4 */
 		ixgbe_atr_get_src_ipv4_82599(input, &src_ipv4);
 		IXGBE_WRITE_REG(hw, IXGBE_FDIRIPSA, src_ipv4);
-
 	}
 
 	ixgbe_atr_get_dst_ipv4_82599(input, &dst_ipv4);
@@ -2163,7 +2172,78 @@ s32 ixgbe_fdir_add_perfect_filter_82599(struct ixgbe_hw *hw,
 	IXGBE_WRITE_REG(hw, IXGBE_FDIRVLAN, (vlan_id |
 	                            (flex_bytes << IXGBE_FDIRVLAN_FLEX_SHIFT)));
 	IXGBE_WRITE_REG(hw, IXGBE_FDIRPORT, (src_port |
-	                       (dst_port << IXGBE_FDIRPORT_DESTINATION_SHIFT)));
+	              (dst_port << IXGBE_FDIRPORT_DESTINATION_SHIFT)));
+
+	/*
+	 * Program the relevant mask registers.  If src/dst_port or src/dst_addr
+	 * are zero, then assume a full mask for that field.  Also assume that
+	 * a VLAN of 0 is unspecified, so mask that out as well.  L4type
+	 * cannot be masked out in this implementation.
+	 *
+	 * This also assumes IPv4 only.  IPv6 masking isn't supported at this
+	 * point in time.
+	 */
+	if (src_ipv4 == 0)
+		IXGBE_WRITE_REG(hw, IXGBE_FDIRSIP4M, 0xffffffff);
+	else
+		IXGBE_WRITE_REG(hw, IXGBE_FDIRSIP4M, input_masks->src_ip_mask);
+
+	if (dst_ipv4 == 0)
+		IXGBE_WRITE_REG(hw, IXGBE_FDIRDIP4M, 0xffffffff);
+	else
+		IXGBE_WRITE_REG(hw, IXGBE_FDIRDIP4M, input_masks->dst_ip_mask);
+
+	switch (l4type & IXGBE_ATR_L4TYPE_MASK) {
+	case IXGBE_ATR_L4TYPE_TCP:
+		if (src_port == 0)
+			IXGBE_WRITE_REG(hw, IXGBE_FDIRTCPM, 0xffff);
+		else
+			IXGBE_WRITE_REG(hw, IXGBE_FDIRTCPM,
+			                input_masks->src_port_mask);
+
+		if (dst_port == 0)
+			IXGBE_WRITE_REG(hw, IXGBE_FDIRTCPM,
+			               (IXGBE_READ_REG(hw, IXGBE_FDIRTCPM) |
+			                (0xffff << 16)));
+		else
+			IXGBE_WRITE_REG(hw, IXGBE_FDIRTCPM,
+			               (IXGBE_READ_REG(hw, IXGBE_FDIRTCPM) |
+			                (input_masks->dst_port_mask << 16)));
+		break;
+	case IXGBE_ATR_L4TYPE_UDP:
+		if (src_port == 0)
+			IXGBE_WRITE_REG(hw, IXGBE_FDIRUDPM, 0xffff);
+		else
+			IXGBE_WRITE_REG(hw, IXGBE_FDIRUDPM,
+			                input_masks->src_port_mask);
+
+		if (dst_port == 0)
+			IXGBE_WRITE_REG(hw, IXGBE_FDIRUDPM,
+			               (IXGBE_READ_REG(hw, IXGBE_FDIRUDPM) |
+			                (0xffff << 16)));
+		else
+			IXGBE_WRITE_REG(hw, IXGBE_FDIRUDPM,
+			               (IXGBE_READ_REG(hw, IXGBE_FDIRUDPM) |
+			                (input_masks->src_port_mask << 16)));
+		break;
+	default:
+		/* this already would have failed above */
+		break;
+	}
+
+	/* Program the last mask register, FDIRM */
+	if (input_masks->vlan_id_mask || !vlan_id)
+		/* Mask both VLAN and VLANP - bits 0 and 1 */
+		fdirm |= 0x3;
+
+	if (input_masks->data_mask || !flex_bytes)
+		/* Flex bytes need masking, so mask the whole thing - bit 4 */
+		fdirm |= 0x10;
+
+	/* Now mask VM pool and destination IPv6 - bits 5 and 2 */
+	fdirm |= 0x24;
+
+	IXGBE_WRITE_REG(hw, IXGBE_FDIRM, fdirm);
 
 	fdircmd |= IXGBE_FDIRCMD_CMD_ADD_FLOW;
 	fdircmd |= IXGBE_FDIRCMD_FILTER_UPDATE;
diff --git a/drivers/net/ixgbe/ixgbe_ethtool.c b/drivers/net/ixgbe/ixgbe_ethtool.c
index 07a9410..0d23434 100644
--- a/drivers/net/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ixgbe/ixgbe_ethtool.c
@@ -979,6 +979,9 @@ static int ixgbe_get_sset_count(struct net_device *netdev, int sset)
 		return IXGBE_TEST_LEN;
 	case ETH_SS_STATS:
 		return IXGBE_STATS_LEN;
+	case ETH_SS_NTUPLE_FILTERS:
+		return (ETHTOOL_MAX_NTUPLE_LIST_ENTRY *
+		        ETHTOOL_MAX_NTUPLE_STRING_PER_ENTRY);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -2150,23 +2153,124 @@ static int ixgbe_set_coalesce(struct net_device *netdev,
 static int ixgbe_set_flags(struct net_device *netdev, u32 data)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	bool need_reset = false;
 
 	ethtool_op_set_flags(netdev, data);
 
-	if (!(adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE))
-		return 0;
-
 	/* if state changes we need to update adapter->flags and reset */
 	if ((!!(data & ETH_FLAG_LRO)) != 
 	    (!!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED))) {
 		adapter->flags2 ^= IXGBE_FLAG2_RSC_ENABLED;
+		need_reset = true;
+	}
+
+	/*
+	 * Check if Flow Director n-tuple support was enabled or disabled.  If
+	 * the state changed, we need to reset.
+	 */
+	if ((adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE) &&
+	    (!(data & ETH_FLAG_NTUPLE))) {
+		/* turn off Flow Director perfect, set hash and reset */
+		adapter->flags &= ~IXGBE_FLAG_FDIR_PERFECT_CAPABLE;
+		adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE;
+		need_reset = true;
+	} else if ((!(adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE)) &&
+	           (data & ETH_FLAG_NTUPLE)) {
+		/* turn off Flow Director hash, enable perfect and reset */
+		adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE;
+		adapter->flags |= IXGBE_FLAG_FDIR_PERFECT_CAPABLE;
+		need_reset = true;
+	} else {
+		/* no state change */
+	}
+
+	if (need_reset) {
 		if (netif_running(netdev))
 			ixgbe_reinit_locked(adapter);
 		else
 			ixgbe_reset(adapter);
 	}
+
 	return 0;
+}
+
+static int ixgbe_set_rx_ntuple(struct net_device *dev,
+                               struct ethtool_rx_ntuple *cmd)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ethtool_rx_ntuple_flow_spec fs = cmd->fs;
+	struct ixgbe_atr_input input_struct;
+	struct ixgbe_atr_input_masks input_masks;
+	int target_queue;
+
+	if (adapter->hw.mac.type == ixgbe_mac_82598EB)
+		return -EOPNOTSUPP;
+
+	/*
+	 * Don't allow programming if the action is a queue greater than
+	 * the number of online Tx queues.
+	 */
+	if ((fs.action >= adapter->num_tx_queues) ||
+	    (fs.action < ETHTOOL_RXNTUPLE_ACTION_DROP))
+		return -EINVAL;
+
+	memset(&input_struct, 0, sizeof(struct ixgbe_atr_input));
+	memset(&input_masks, 0, sizeof(struct ixgbe_atr_input_masks));
+
+	input_masks.src_ip_mask = fs.m_u.tcp_ip4_spec.ip4src;
+	input_masks.dst_ip_mask = fs.m_u.tcp_ip4_spec.ip4dst;
+	input_masks.src_port_mask = fs.m_u.tcp_ip4_spec.psrc;
+	input_masks.dst_port_mask = fs.m_u.tcp_ip4_spec.pdst;
+	input_masks.vlan_id_mask = fs.vlan_tag_mask;
+	/* only use the lowest 2 bytes for flex bytes */
+	input_masks.data_mask = (fs.data_mask & 0xffff);
+
+	switch (fs.flow_type) {
+	case TCP_V4_FLOW:
+		ixgbe_atr_set_l4type_82599(&input_struct, IXGBE_ATR_L4TYPE_TCP);
+		break;
+	case UDP_V4_FLOW:
+		ixgbe_atr_set_l4type_82599(&input_struct, IXGBE_ATR_L4TYPE_UDP);
+		break;
+	case SCTP_V4_FLOW:
+		ixgbe_atr_set_l4type_82599(&input_struct, IXGBE_ATR_L4TYPE_SCTP);
+		break;
+	default:
+		return -1;
+	}
 
+	/* Mask bits from the inputs based on user-supplied mask */
+	ixgbe_atr_set_src_ipv4_82599(&input_struct,
+	            (fs.h_u.tcp_ip4_spec.ip4src & ~fs.m_u.tcp_ip4_spec.ip4src));
+	ixgbe_atr_set_dst_ipv4_82599(&input_struct,
+	            (fs.h_u.tcp_ip4_spec.ip4dst & ~fs.m_u.tcp_ip4_spec.ip4dst));
+	/* 82599 expects these to be byte-swapped for perfect filtering */
+	ixgbe_atr_set_src_port_82599(&input_struct,
+	       ((ntohs(fs.h_u.tcp_ip4_spec.psrc)) & ~fs.m_u.tcp_ip4_spec.psrc));
+	ixgbe_atr_set_dst_port_82599(&input_struct,
+	       ((ntohs(fs.h_u.tcp_ip4_spec.pdst)) & ~fs.m_u.tcp_ip4_spec.pdst));
+
+	/* VLAN and Flex bytes are either completely masked or not */
+	if (!fs.vlan_tag_mask)
+		ixgbe_atr_set_vlan_id_82599(&input_struct, fs.vlan_tag);
+
+	if (!input_masks.data_mask)
+		/* make sure we only use the first 2 bytes of user data */
+		ixgbe_atr_set_flex_byte_82599(&input_struct,
+		                              (fs.data & 0xffff));
+
+	/* determine if we need to drop or route the packet */
+	if (fs.action == ETHTOOL_RXNTUPLE_ACTION_DROP)
+		target_queue = MAX_RX_QUEUES - 1;
+	else
+		target_queue = fs.action;
+
+	spin_lock(&adapter->fdir_perfect_lock);
+	ixgbe_fdir_add_perfect_filter_82599(&adapter->hw, &input_struct,
+	                                    &input_masks, 0, target_queue);
+	spin_unlock(&adapter->fdir_perfect_lock);
+
+	return 0;
 }
 
 static const struct ethtool_ops ixgbe_ethtool_ops = {
@@ -2204,6 +2308,7 @@ static const struct ethtool_ops ixgbe_ethtool_ops = {
 	.set_coalesce           = ixgbe_set_coalesce,
 	.get_flags              = ethtool_op_get_flags,
 	.set_flags              = ixgbe_set_flags,
+	.set_rx_ntuple          = ixgbe_set_rx_ntuple,
 };
 
 void ixgbe_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index 2a3c831..f04b539 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -3253,6 +3253,9 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
 
 	netif_carrier_off(netdev);
 
+	/* clear n-tuple filters that are cached */
+	ethtool_ntuple_flush(netdev);
+
 	if (!pci_channel_offline(adapter->pdev))
 		ixgbe_reset(adapter);
 	ixgbe_clean_all_tx_rings(adapter);
@@ -4187,6 +4190,7 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct pci_dev *pdev = adapter->pdev;
+	struct net_device *dev = adapter->netdev;
 	unsigned int rss;
 #ifdef CONFIG_IXGBE_DCB
 	int j;
@@ -4214,10 +4218,18 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter)
 		adapter->max_msix_q_vectors = MAX_MSIX_Q_VECTORS_82599;
 		adapter->flags2 |= IXGBE_FLAG2_RSC_CAPABLE;
 		adapter->flags2 |= IXGBE_FLAG2_RSC_ENABLED;
-		adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE;
+		if (dev->features & NETIF_F_NTUPLE) {
+			/* Flow Director perfect filter enabled */
+			adapter->flags |= IXGBE_FLAG_FDIR_PERFECT_CAPABLE;
+			adapter->atr_sample_rate = 0;
+			spin_lock_init(&adapter->fdir_perfect_lock);
+		} else {
+			/* Flow Director hash filters enabled */
+			adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE;
+			adapter->atr_sample_rate = 20;
+		}
 		adapter->ring_feature[RING_F_FDIR].indices =
 		                                         IXGBE_MAX_FDIR_INDICES;
-		adapter->atr_sample_rate = 20;
 		adapter->fdir_pballoc = 0;
 #ifdef IXGBE_FCOE
 		adapter->flags |= IXGBE_FLAG_FCOE_CAPABLE;
diff --git a/drivers/net/ixgbe/ixgbe_type.h b/drivers/net/ixgbe/ixgbe_type.h
index 0db67c1..2be9074 100644
--- a/drivers/net/ixgbe/ixgbe_type.h
+++ b/drivers/net/ixgbe/ixgbe_type.h
@@ -2129,6 +2129,15 @@ struct ixgbe_atr_input {
 	u8 byte_stream[42];
 };
 
+struct ixgbe_atr_input_masks {
+	u32 src_ip_mask;
+	u32 dst_ip_mask;
+	u16 src_port_mask;
+	u16 dst_port_mask;
+	u16 vlan_id_mask;
+	u16 data_mask;
+};
+
 enum ixgbe_eeprom_type {
 	ixgbe_eeprom_uninitialized = 0,
 	ixgbe_eeprom_spi,

[net-next-2.6 PATCH v5 3/3] ixgbe: Bump driver version up

[Jeff Kirsher]

From: Peter Waskiewicz <peter.p.waskiewicz.jr@intel.com>

Driver has gone under significant changes, the version should
reflect that.

Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---

 drivers/net/ixgbe/ixgbe_main.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index f04b539..382bf89 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -51,7 +51,7 @@ char ixgbe_driver_name[] = "ixgbe";
 static const char ixgbe_driver_string[] =
                               "Intel(R) 10 Gigabit PCI Express Network Driver";
 
-#define DRV_VERSION "2.0.44-k2"
+#define DRV_VERSION "2.0.62-k2"
 const char ixgbe_driver_version[] = DRV_VERSION;
 static char ixgbe_copyright[] = "Copyright (c) 1999-2010 Intel Corporation.";
 

Re: [net-next-2.6 PATCH v5 0/3] Introduce n-tuple ethtool support

[David Miller]

From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Wed, 10 Feb 2010 18:07:18 -0800

> One more round of fixes, based on feedback from Patrick McHardy
> 
> 1) Change the list count to an unsigned value
> 2) Fix a memory leak
> 3) Removed an unnecessary list traversal in the ethtool core
> 4) Moved all list destruction to a helper function, allowing the driver
> to control when it clears the list (aside from when free_netdev() kills
> the cached list).

All applied, thanks.

Pj, can you look a shoring up the behavior of one more thing for me?

When rules get added, it first installs the filter by calling into
the driver.

_Then_ is tries to add the software copy of the rule to the device
list.  This does an allocation which may fail.

If it does fail, we return -ENOMEM but we left the device configured
with the new rule.

Probably better to do it something like:

	p = NULL;
	if (need_sw_rule_list)
		p = alloc_rule();
		if (!p)
			return -ENOMEM;
	}

	ret = op->install_rule();
	if (ret) {
		kfree(p);
		return ret;
	}
	
	if (need_sw_rule_list)
		sw_rule_insert(dev, p);

You get the idea, we can do the kfree() unconditonally because kfree(NULL)
is OK, etc.

Re: [net-next-2.6 PATCH v5 0/3] Introduce n-tuple ethtool support

[David Miller]

From: David Miller <davem@davemloft.net>
Date: Wed, 10 Feb 2010 19:54:45 -0800 (PST)

> All applied, thanks.

Guys please check your changes for warnings in the build:

net/core/dev.c: In function ‘free_netdev’:
net/core/dev.c:5452: warning: unused variable ‘f’
net/core/dev.c:5452: warning: unused variable ‘fsc’
  CC [M]  drivers/net/e1000e/lib.o
  CC [M]  drivers/net/e1000e/phy.o
  CC      net/core/ethtool.o
  CC [M]  drivers/net/e1000e/param.o
net/core/ethtool.c: In function ‘ethtool_reset’:
net/core/ethtool.c:626: warning: unused variable ‘f’
net/core/ethtool.c:626: warning: unused variable ‘fsc’
net/core/ethtool.c: In function ‘ethtool_nway_reset’:
net/core/ethtool.c:676: warning: unused variable ‘f’
net/core/ethtool.c:676: warning: unused variable ‘fsc’

I'll fix this up, but you know... :-/

Re: [net-next-2.6 PATCH v5 0/3] Introduce n-tuple ethtool support

[Peter P Waskiewicz Jr]

On Wed, 2010-02-10 at 19:54 -0800, David Miller wrote:
> From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
> Date: Wed, 10 Feb 2010 18:07:18 -0800
> 
> > One more round of fixes, based on feedback from Patrick McHardy
> > 
> > 1) Change the list count to an unsigned value
> > 2) Fix a memory leak
> > 3) Removed an unnecessary list traversal in the ethtool core
> > 4) Moved all list destruction to a helper function, allowing the driver
> > to control when it clears the list (aside from when free_netdev() kills
> > the cached list).
> 
> All applied, thanks.
> 
> Pj, can you look a shoring up the behavior of one more thing for me?
> 
> When rules get added, it first installs the filter by calling into
> the driver.
> 
> _Then_ is tries to add the software copy of the rule to the device
> list.  This does an allocation which may fail.
> 
> If it does fail, we return -ENOMEM but we left the device configured
> with the new rule.
> 
> Probably better to do it something like:
> 
> 	p = NULL;
> 	if (need_sw_rule_list)
> 		p = alloc_rule();
> 		if (!p)
> 			return -ENOMEM;
> 	}
> 
> 	ret = op->install_rule();
> 	if (ret) {
> 		kfree(p);
> 		return ret;
> 	}
> 	
> 	if (need_sw_rule_list)
> 		sw_rule_insert(dev, p);
> 
> You get the idea, we can do the kfree() unconditonally because kfree(NULL)
> is OK, etc.

No problem.  I'll get a patch together asap for 2.6.34.

Also, probably for 2.6.35, I'm going to try and add a remove capability.

Cheers,
-PJ

[net-next-2.6 PATCH v5 0/3] Introduce n-tuple ethtool support

[robert]

Nice. Next step would be to control the RSS-traffic. Doing this we 
can easily get total separation between "control" and "data" plane.
We did a dirty hack to separate out bgp/ssh to one queue/cpu. 
I think just a RSS_mask would be a good start - each bit controlling 
if queue should receive RSS traffic or not.

Cheers
				--ro


Jeff Kirsher writes:
 > One more round of fixes, based on feedback from Patrick McHardy
 > 
 > 1) Change the list count to an unsigned value
 > 2) Fix a memory leak
 > 3) Removed an unnecessary list traversal in the ethtool core
 > 4) Moved all list destruction to a helper function, allowing the driver
 > to control when it clears the list (aside from when free_netdev() kills
 > the cached list).
 > 
 > ---
 > 
 > Peter Waskiewicz (3):
 >       ixgbe: Bump driver version up
 >       ixgbe: Add support for the new ethtool n-tuple programming interface
 >       ethtool: Introduce n-tuple filter programming support
 > 
 > 
 >  drivers/net/ixgbe/ixgbe.h         |    4 
 >  drivers/net/ixgbe/ixgbe_82599.c   |  106 ++++++++++--
 >  drivers/net/ixgbe/ixgbe_ethtool.c |  111 ++++++++++++
 >  drivers/net/ixgbe/ixgbe_main.c    |   18 ++
 >  drivers/net/ixgbe/ixgbe_type.h    |    9 +
 >  include/linux/ethtool.h           |   50 ++++++
 >  include/linux/netdevice.h         |    3 
 >  net/core/dev.c                    |    6 +
 >  net/core/ethtool.c                |  332 +++++++++++++++++++++++++++++++++++++
 >  9 files changed, 619 insertions(+), 20 deletions(-)
 > 
 > -- 
 > Cheers,
 > Jeff
 > --
 > To unsubscribe from this list: send the line "unsubscribe netdev" in
 > the body of a message to majordomo@vger.kernel.org
 > More majordomo info at  http://vger.kernel.org/majordomo-info.html

includes build break - was Re: [net-next-2.6 PATCH v5 0/3] Introduce n-tuple ethtool support

[Oliver Hartkopp]

David Miller wrote:
> From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
> Date: Wed, 10 Feb 2010 18:07:18 -0800
> 
>> One more round of fixes, based on feedback from Patrick McHardy
>>
>> 1) Change the list count to an unsigned value
>> 2) Fix a memory leak
>> 3) Removed an unnecessary list traversal in the ethtool core
>> 4) Moved all list destruction to a helper function, allowing the driver
>> to control when it clears the list (aside from when free_netdev() kills
>> the cached list).
> 
> All applied, thanks.
> 

Hi Peter,

compiling the latest net-next-2.6 i got this problem:
 
  CHECK   include/linux (358 files)
/home/hartko/net-next-2.6/usr/include/linux/ethtool.h:17: included file 'linux/rculist.h' is not exported

Which has been introduced by

http://git.kernel.org/?p=linux/kernel/git/davem/net-next-2.6.git;a=commitdiff;h=15682bc488d4af8c9bb998844a94281025e0a333

("ethtool: Introduce n-tuple filter programming support")

The patch below fixes the issue.

Signed-off-by: Oliver Hartkopp <oliver@hartkopp.net>

---

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index a3cac53..83a9a53 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -14,7 +14,9 @@
 #define _LINUX_ETHTOOL_H
 
 #include <linux/types.h>
+#ifdef __KERNEL__
 #include <linux/rculist.h>
+#endif
 
 /* This should work for both 32 and 64 bit userland. */
 struct ethtool_cmd {

Re: includes build break - was Re: [net-next-2.6 PATCH v5 0/3] Introduce n-tuple ethtool support

[David Miller]

From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Sun, 14 Feb 2010 12:56:28 +0100

> The patch below fixes the issue.
> 
> Signed-off-by: Oliver Hartkopp <oliver@hartkopp.net>

Oliver, thanks for your patch.

I'm going to fix this slightly differently by moving
the rculist.h include down into the existing __KERNEL__
ifdef protected code block.

Thanks!