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

Jeff Kirsher says:

====================
Intel Wired LAN Driver Updates 2015-05-28

This series contains updates to ethtool, ixgbe, i40e and i40evf.

John adds helper routines for ethtool to pass VF to rx_flow_spec.  Since
the ring_cookie is 64 bits wide which is much larger than what could be
used for actual queue index values, provide helper routines to pack a VF
index into the cookie.  Then John provides a ixgbe patch to allow flow
director to use the entire queue space.

Neerav provides a i40e patch to collect XOFF Rx stats, where it was not
being collected before.

Anjali provides ATR support for tunneled packets, as well as stats to
count tunnel ATR hits.  Cleaned up PF struct members which are
unnecessary, since we can use the stat index macro directly.  Cleaned
up flow director ATR/SB messages to a higher debug level since they
are not useful unless silicon validation is happening.

Greg provides a patch to disable offline diagnostics if VFs are enabled
since ethtool offline diagnostic tests are not designed (out of scope)
to disable VF functions for testing and re-enable afterward.  Also cleans
up TODO comment that is no longer needed.

Vasu provides a fix an FCoE EOF case where i40e_fcoe_ctxt_eof() maybe
called before i40e_fcoe_eof_is_supported() is called.

Jesse adds skb->xmit_more support for i40evf.  Then provides a performance
enhancement for i40evf by inlining some functions which provides a 15%
gain in small packet performance.  Also cleans up the use of time_stamp
since it is no longer used to determine if there is a tx_hang and was
a part of a previous tx_hang design which is no longer used.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/intel/i40e/i40e.h

@@ -182,6 +182,7 @@ struct i40e_lump_tracking {
 enum i40e_fd_stat_idx {
 	I40E_FD_STAT_ATR,
 	I40E_FD_STAT_SB,
+	I40E_FD_STAT_ATR_TUNNEL,
 	I40E_FD_STAT_PF_COUNT
 };
 #define I40E_FD_STAT_PF_IDX(pf_id) ((pf_id) * I40E_FD_STAT_PF_COUNT)
@@ -189,6 +190,8 @@ enum i40e_fd_stat_idx {
 			(I40E_FD_STAT_PF_IDX(pf_id) + I40E_FD_STAT_ATR)
 #define I40E_FD_SB_STAT_IDX(pf_id)  \
 			(I40E_FD_STAT_PF_IDX(pf_id) + I40E_FD_STAT_SB)
+#define I40E_FD_ATR_TUNNEL_STAT_IDX(pf_id) \
+			(I40E_FD_STAT_PF_IDX(pf_id) + I40E_FD_STAT_ATR_TUNNEL)
 
 struct i40e_fdir_filter {
 	struct hlist_node fdir_node;
@@ -263,8 +266,6 @@ struct i40e_pf {
 
 	struct hlist_head fdir_filter_list;
 	u16 fdir_pf_active_filters;
-	u16 fd_sb_cnt_idx;
-	u16 fd_atr_cnt_idx;
 	unsigned long fd_flush_timestamp;
 	u32 fd_flush_cnt;
 	u32 fd_add_err;

drivers/net/ethernet/intel/i40e/i40e_ethtool.c

@@ -147,6 +147,7 @@ static struct i40e_stats i40e_gstrings_stats[] = {
 	I40E_PF_STAT("rx_hwtstamp_cleared", rx_hwtstamp_cleared),
 	I40E_PF_STAT("fdir_flush_cnt", fd_flush_cnt),
 	I40E_PF_STAT("fdir_atr_match", stats.fd_atr_match),
+	I40E_PF_STAT("fdir_atr_tunnel_match", stats.fd_atr_tunnel_match),
 	I40E_PF_STAT("fdir_sb_match", stats.fd_sb_match),
 
 	/* LPI stats */
@@ -1548,6 +1549,17 @@ static int i40e_loopback_test(struct net_device *netdev, u64 *data)
 	return *data;
 }
 
+static inline bool i40e_active_vfs(struct i40e_pf *pf)
+{
+	struct i40e_vf *vfs = pf->vf;
+	int i;
+
+	for (i = 0; i < pf->num_alloc_vfs; i++)
+		if (vfs[i].vf_states & I40E_VF_STAT_ACTIVE)
+			return true;
+	return false;
+}
+
 static void i40e_diag_test(struct net_device *netdev,
 			   struct ethtool_test *eth_test, u64 *data)
 {
@@ -1560,6 +1572,20 @@ static void i40e_diag_test(struct net_device *netdev,
 		netif_info(pf, drv, netdev, "offline testing starting\n");
 
 		set_bit(__I40E_TESTING, &pf->state);
+
+		if (i40e_active_vfs(pf)) {
+			dev_warn(&pf->pdev->dev,
+				 "Please take active VFS offline and restart the adapter before running NIC diagnostics\n");
+			data[I40E_ETH_TEST_REG]		= 1;
+			data[I40E_ETH_TEST_EEPROM]	= 1;
+			data[I40E_ETH_TEST_INTR]	= 1;
+			data[I40E_ETH_TEST_LOOPBACK]	= 1;
+			data[I40E_ETH_TEST_LINK]	= 1;
+			eth_test->flags |= ETH_TEST_FL_FAILED;
+			clear_bit(__I40E_TESTING, &pf->state);
+			goto skip_ol_tests;
+		}
+
 		/* If the device is online then take it offline */
 		if (if_running)
 			/* indicate we're in test mode */
@@ -1605,6 +1631,8 @@ static void i40e_diag_test(struct net_device *netdev,
 		data[I40E_ETH_TEST_LOOPBACK] = 0;
 	}
 
+skip_ol_tests:
+
 	netif_info(pf, drv, netdev, "testing finished\n");
 }
 
@@ -2265,7 +2293,7 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
 	input->pctype = 0;
 	input->dest_vsi = vsi->id;
 	input->fd_status = I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID;
-	input->cnt_index  = pf->fd_sb_cnt_idx;
+	input->cnt_index  = I40E_FD_SB_STAT_IDX(pf->hw.pf_id);
 	input->flow_type = fsp->flow_type;
 	input->ip4_proto = fsp->h_u.usr_ip4_spec.proto;
 

drivers/net/ethernet/intel/i40e/i40e_fcoe.c

@@ -118,7 +118,7 @@ static inline int i40e_fcoe_fc_eof(struct sk_buff *skb, u8 *eof)
  *
  * The FC EOF is converted to the value understood by HW for descriptor
  * programming. Never call this w/o calling i40e_fcoe_eof_is_supported()
- * first.
+ * first and that already checks for all supported valid eof values.
  **/
 static inline u32 i40e_fcoe_ctxt_eof(u8 eof)
 {
@@ -132,9 +132,12 @@ static inline u32 i40e_fcoe_ctxt_eof(u8 eof)
 	case FC_EOF_A:
 		return I40E_TX_DESC_CMD_L4T_EOFT_EOF_A;
 	default:
-		/* FIXME: still returns 0 */
-		pr_err("Unrecognized EOF %x\n", eof);
-		return 0;
+		/* Supported valid eof shall be already checked by
+		 * calling i40e_fcoe_eof_is_supported() first,
+		 * therefore this default case shall never hit.
+		 */
+		WARN_ON(1);
+		return -EINVAL;
 	}
 }
 

drivers/net/ethernet/intel/i40e/i40e_main.c

@@ -39,7 +39,7 @@ static const char i40e_driver_string[] =
 
 #define DRV_VERSION_MAJOR 1
 #define DRV_VERSION_MINOR 3
-#define DRV_VERSION_BUILD 2
+#define DRV_VERSION_BUILD 4
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD)    DRV_KERN
@@ -772,9 +772,8 @@ static void i40e_update_prio_xoff_rx(struct i40e_pf *pf)
 
 	dcb_cfg = &hw->local_dcbx_config;
 
-	/* See if DCB enabled with PFC TC */
-	if (!(pf->flags & I40E_FLAG_DCB_ENABLED) ||
-	    !(dcb_cfg->pfc.pfcenable)) {
+	/* Collect Link XOFF stats when PFC is disabled */
+	if (!dcb_cfg->pfc.pfcenable) {
 		i40e_update_link_xoff_rx(pf);
 		return;
 	}
@@ -1097,12 +1096,18 @@ static void i40e_update_pf_stats(struct i40e_pf *pf)
 			   &osd->rx_jabber, &nsd->rx_jabber);
 
 	/* FDIR stats */
-	i40e_stat_update32(hw, I40E_GLQF_PCNT(pf->fd_atr_cnt_idx),
+	i40e_stat_update32(hw,
+			   I40E_GLQF_PCNT(I40E_FD_ATR_STAT_IDX(pf->hw.pf_id)),
 			   pf->stat_offsets_loaded,
 			   &osd->fd_atr_match, &nsd->fd_atr_match);
-	i40e_stat_update32(hw, I40E_GLQF_PCNT(pf->fd_sb_cnt_idx),
+	i40e_stat_update32(hw,
+			   I40E_GLQF_PCNT(I40E_FD_SB_STAT_IDX(pf->hw.pf_id)),
 			   pf->stat_offsets_loaded,
 			   &osd->fd_sb_match, &nsd->fd_sb_match);
+	i40e_stat_update32(hw,
+		      I40E_GLQF_PCNT(I40E_FD_ATR_TUNNEL_STAT_IDX(pf->hw.pf_id)),
+		      pf->stat_offsets_loaded,
+		      &osd->fd_atr_tunnel_match, &nsd->fd_atr_tunnel_match);
 
 	val = rd32(hw, I40E_PRTPM_EEE_STAT);
 	nsd->tx_lpi_status =
@@ -4739,6 +4744,7 @@ static int i40e_up_complete(struct i40e_vsi *vsi)
 		pf->fd_add_err = pf->fd_atr_cnt = 0;
 		if (pf->fd_tcp_rule > 0) {
 			pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED;
+			if (I40E_DEBUG_FD & pf->hw.debug_mask)
 				dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 exist\n");
 			pf->fd_tcp_rule = 0;
 		}
@@ -5428,6 +5434,7 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf)
 		if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) &&
 		    (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) {
 			pf->auto_disable_flags &= ~I40E_FLAG_FD_SB_ENABLED;
+			if (I40E_DEBUG_FD & pf->hw.debug_mask)
 				dev_info(&pf->pdev->dev, "FD Sideband/ntuple is being enabled since we have space in the table now\n");
 		}
 	}
@@ -5436,6 +5443,7 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf)
 		if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&
 		    (pf->auto_disable_flags & I40E_FLAG_FD_ATR_ENABLED)) {
 			pf->auto_disable_flags &= ~I40E_FLAG_FD_ATR_ENABLED;
+			if (I40E_DEBUG_FD & pf->hw.debug_mask)
 				dev_info(&pf->pdev->dev, "ATR is being enabled since we have space in the table now\n");
 		}
 	}
@@ -5469,6 +5477,7 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf)
 
 		if (!(time_after(jiffies, min_flush_time)) &&
 		    (fd_room < I40E_FDIR_BUFFER_HEAD_ROOM_FOR_ATR)) {
+			if (I40E_DEBUG_FD & pf->hw.debug_mask)
 				dev_info(&pf->pdev->dev, "ATR disabled, not enough FD filter space.\n");
 			disable_atr = true;
 		}
@@ -5496,6 +5505,7 @@ static void i40e_fdir_flush_and_replay(struct i40e_pf *pf)
 			if (!disable_atr)
 				pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
 			clear_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state);
+			if (I40E_DEBUG_FD & pf->hw.debug_mask)
 				dev_info(&pf->pdev->dev, "FD Filter table flushed and FD-SB replayed.\n");
 		}
 	}
@@ -7676,12 +7686,8 @@ static int i40e_sw_init(struct i40e_pf *pf)
 	    (pf->hw.func_caps.fd_filters_best_effort > 0)) {
 		pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
 		pf->atr_sample_rate = I40E_DEFAULT_ATR_SAMPLE_RATE;
-		/* Setup a counter for fd_atr per PF */
-		pf->fd_atr_cnt_idx = I40E_FD_ATR_STAT_IDX(pf->hw.pf_id);
 		if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) {
 			pf->flags |= I40E_FLAG_FD_SB_ENABLED;
-			/* Setup a counter for fd_sb per PF */
-			pf->fd_sb_cnt_idx = I40E_FD_SB_STAT_IDX(pf->hw.pf_id);
 		} else {
 			dev_info(&pf->pdev->dev,
 				 "Flow Director Sideband mode Disabled in MFP mode\n");
@@ -7771,6 +7777,7 @@ bool i40e_set_ntuple(struct i40e_pf *pf, netdev_features_t features)
 		pf->fd_add_err = pf->fd_atr_cnt = pf->fd_tcp_rule = 0;
 		pf->fdir_pf_active_filters = 0;
 		pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
+		if (I40E_DEBUG_FD & pf->hw.debug_mask)
 			dev_info(&pf->pdev->dev, "ATR re-enabled.\n");
 		/* if ATR was auto disabled it can be re-enabled. */
 		if ((pf->flags & I40E_FLAG_FD_ATR_ENABLED) &&

drivers/net/ethernet/intel/i40e/i40e_txrx.h

@@ -139,6 +139,7 @@ enum i40e_dyn_idx_t {
 #define I40E_TX_FLAGS_FSO		(u32)(1 << 7)
 #define I40E_TX_FLAGS_TSYN		(u32)(1 << 8)
 #define I40E_TX_FLAGS_FD_SB		(u32)(1 << 9)
+#define I40E_TX_FLAGS_VXLAN_TUNNEL	(u32)(1 << 10)
 #define I40E_TX_FLAGS_VLAN_MASK		0xffff0000
 #define I40E_TX_FLAGS_VLAN_PRIO_MASK	0xe0000000
 #define I40E_TX_FLAGS_VLAN_PRIO_SHIFT	29
@@ -146,7 +147,6 @@ enum i40e_dyn_idx_t {
 
 struct i40e_tx_buffer {
 	struct i40e_tx_desc *next_to_watch;
-	unsigned long time_stamp;
 	union {
 		struct sk_buff *skb;
 		void *raw_buf;

drivers/net/ethernet/intel/i40e/i40e_type.h

@@ -1133,6 +1133,7 @@ struct i40e_hw_port_stats {
 	/* flow director stats */
 	u64 fd_atr_match;
 	u64 fd_sb_match;
+	u64 fd_atr_tunnel_match;
 	/* EEE LPI */
 	u32 tx_lpi_status;
 	u32 rx_lpi_status;

drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c

@@ -980,6 +980,13 @@ static int i40e_pci_sriov_enable(struct pci_dev *pdev, int num_vfs)
 	int pre_existing_vfs = pci_num_vf(pdev);
 	int err = 0;
 
+	if (pf->state & __I40E_TESTING) {
+		dev_warn(&pdev->dev,
+			 "Cannot enable SR-IOV virtual functions while the device is undergoing diagnostic testing\n");
+		err = -EPERM;
+		goto err_out;
+	}
+
 	dev_info(&pdev->dev, "Allocating %d VFs.\n", num_vfs);
 	if (pre_existing_vfs && pre_existing_vfs != num_vfs)
 		i40e_free_vfs(pf);

drivers/net/ethernet/intel/i40evf/i40e_txrx.h

@@ -138,6 +138,7 @@ enum i40e_dyn_idx_t {
 #define I40E_TX_FLAGS_FCCRC		(u32)(1 << 6)
 #define I40E_TX_FLAGS_FSO		(u32)(1 << 7)
 #define I40E_TX_FLAGS_FD_SB		(u32)(1 << 9)
+#define I40E_TX_FLAGS_VXLAN_TUNNEL	(u32)(1 << 10)
 #define I40E_TX_FLAGS_VLAN_MASK		0xffff0000
 #define I40E_TX_FLAGS_VLAN_PRIO_MASK	0xe0000000
 #define I40E_TX_FLAGS_VLAN_PRIO_SHIFT	29
@@ -145,7 +146,6 @@ enum i40e_dyn_idx_t {
 
 struct i40e_tx_buffer {
 	struct i40e_tx_desc *next_to_watch;
-	unsigned long time_stamp;
 	union {
 		struct sk_buff *skb;
 		void *raw_buf;

drivers/net/ethernet/intel/i40evf/i40e_type.h

@@ -1108,6 +1108,7 @@ struct i40e_hw_port_stats {
 	/* flow director stats */
 	u64 fd_atr_match;
 	u64 fd_sb_match;
+	u64 fd_atr_tunnel_match;
 	/* EEE LPI */
 	u32 tx_lpi_status;
 	u32 rx_lpi_status;

drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c

@@ -2594,19 +2594,36 @@ static int ixgbe_add_ethtool_fdir_entry(struct ixgbe_adapter *adapter,
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct ixgbe_fdir_filter *input;
 	union ixgbe_atr_input mask;
+	u8 queue;
 	int err;
 
 	if (!(adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE))
 		return -EOPNOTSUPP;
 
-	/*
-	 * Don't allow programming if the action is a queue greater than
-	 * the number of online Rx queues.
+	/* ring_cookie is a masked into a set of queues and ixgbe pools or
+	 * we use the drop index.
 	 */
-	if ((fsp->ring_cookie != RX_CLS_FLOW_DISC) &&
-	    (fsp->ring_cookie >= adapter->num_rx_queues))
+	if (fsp->ring_cookie == RX_CLS_FLOW_DISC) {
+		queue = IXGBE_FDIR_DROP_QUEUE;
+	} else {
+		u32 ring = ethtool_get_flow_spec_ring(fsp->ring_cookie);
+		u8 vf = ethtool_get_flow_spec_ring_vf(fsp->ring_cookie);
+
+		if (!vf && (ring >= adapter->num_rx_queues))
+			return -EINVAL;
+		else if (vf &&
+			 ((vf > adapter->num_vfs) ||
+			   ring >= adapter->num_rx_queues_per_pool))
 			return -EINVAL;
 
+		/* Map the ring onto the absolute queue index */
+		if (!vf)
+			queue = adapter->rx_ring[ring]->reg_idx;
+		else
+			queue = ((vf - 1) *
+				adapter->num_rx_queues_per_pool) + ring;
+	}
+
 	/* Don't allow indexes to exist outside of available space */
 	if (fsp->location >= ((1024 << adapter->fdir_pballoc) - 2)) {
 		e_err(drv, "Location out of range\n");
@@ -2683,10 +2700,7 @@ static int ixgbe_add_ethtool_fdir_entry(struct ixgbe_adapter *adapter,
 
 	/* program filters to filter memory */
 	err = ixgbe_fdir_write_perfect_filter_82599(hw,
-				&input->filter, input->sw_idx,
-				(input->action == IXGBE_FDIR_DROP_QUEUE) ?
-				IXGBE_FDIR_DROP_QUEUE :
-				adapter->rx_ring[input->action]->reg_idx);
+				&input->filter, input->sw_idx, queue);
 	if (err)
 		goto err_out_w_lock;
 

include/uapi/linux/ethtool.h

@@ -796,6 +796,31 @@ struct ethtool_rx_flow_spec {
 	__u32		location;
 };
 
+/* How rings are layed out when accessing virtual functions or
+ * offloaded queues is device specific. To allow users to do flow
+ * steering and specify these queues the ring cookie is partitioned
+ * into a 32bit queue index with an 8 bit virtual function id.
+ * This also leaves the 3bytes for further specifiers. It is possible
+ * future devices may support more than 256 virtual functions if
+ * devices start supporting PCIe w/ARI. However at the moment I
+ * do not know of any devices that support this so I do not reserve
+ * space for this at this time. If a future patch consumes the next
+ * byte it should be aware of this possiblity.
+ */
+#define ETHTOOL_RX_FLOW_SPEC_RING	0x00000000FFFFFFFFLL
+#define ETHTOOL_RX_FLOW_SPEC_RING_VF	0x000000FF00000000LL
+#define ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF 32
+static inline __u64 ethtool_get_flow_spec_ring(__u64 ring_cookie)
+{
+	return ETHTOOL_RX_FLOW_SPEC_RING & ring_cookie;
+};
+
+static inline __u64 ethtool_get_flow_spec_ring_vf(__u64 ring_cookie)
+{
+	return (ETHTOOL_RX_FLOW_SPEC_RING_VF & ring_cookie) >>
+				ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF;
+};
+
 /**
  * struct ethtool_rxnfc - command to get or set RX flow classification rules
  * @cmd: Specific command number - %ETHTOOL_GRXFH, %ETHTOOL_SRXFH,