[net-next-2.6 00/16][pull request] Intel Wired LAN Driver Updates

[net-next-2.6 00/16][pull request] Intel Wired LAN Driver Updates

[Jeff Kirsher]

The following series contains e1000e cleanup patches, the addition of igb
PF support for i350 devices and several ixgbe cleanup patches.

The following are changes since commit 2360d2e8f01043632d6b651672bec66c49892f94:
  enic: Update MAINTAINERS

and are available in the git repository at:
  master.kernel.org:/pub/scm/linux/kernel/git/jkirsher/net-next-2.6 master

Atita Shirwaikar (1):
  ixgbe: Adding 100MB FULL support in ethtool

Bruce Allan (4):
  e1000e: replace unbounded sprintf with snprintf
  e1000e: use correct pointer when memcpy'ing a 2-dimensional array
  e1000e: do not wakeup Tx queue until ready
  e1000e: return appropriate errors for 'ethtool -r'

Carolyn Wyborny (1):
  igb: Enable PF side of SR-IOV support for i350 devices

Don Skidmore (3):
  ixgbe: fix namespace issue with ixgbe_dcb_txq_to_tc
  ixgbe: cleanup namespace complaint by removing little used function
  ixgbe: cleanup ixgbe_init_mbx_params_pf namespace issue

John Fastabend (7):
  ixgbe: DCB, only reprogram HW if the FCoE priority is changed
  ixgbe: DCB, remove round robin mode on 82598 devices
  ixgbe: DCB, abstract out dcb_config from DCB hardware configuration
  ixgbe: DCB, implement 802.1Qaz routines
  ixgbe: DCB, do not reset on CEE pg changes
  ixgbe: DCB, remove RESET bit it is no longer needed
  ixgbe: dcb, use hardware independent routines

 drivers/net/e1000e/ethtool.c        |   13 ++-
 drivers/net/e1000e/netdev.c         |   13 +-
 drivers/net/igb/e1000_82575.c       |   10 ++-
 drivers/net/igb/e1000_mbx.c         |   38 +++----
 drivers/net/igb/igb_main.c          |    9 +-
 drivers/net/ixgbe/ixgbe.h           |    5 +-
 drivers/net/ixgbe/ixgbe_common.h    |    4 +-
 drivers/net/ixgbe/ixgbe_dcb.c       |  176 +++++++++++++++++++++++++++++-
 drivers/net/ixgbe/ixgbe_dcb.h       |   10 ++-
 drivers/net/ixgbe/ixgbe_dcb_82598.c |   94 ++++++++--------
 drivers/net/ixgbe/ixgbe_dcb_82598.h |   23 ++++-
 drivers/net/ixgbe/ixgbe_dcb_82599.c |  115 +++++++++++--------
 drivers/net/ixgbe/ixgbe_dcb_82599.h |   24 ++++-
 drivers/net/ixgbe/ixgbe_dcb_nl.c    |  211 ++++++++++++++++++++++++++--------
 drivers/net/ixgbe/ixgbe_ethtool.c   |   34 ++++++-
 drivers/net/ixgbe/ixgbe_main.c      |   18 +--
 drivers/net/ixgbe/ixgbe_mbx.c       |    2 +
 drivers/net/ixgbe/ixgbe_mbx.h       |    2 +
 include/linux/dcbnl.h               |    5 +
 19 files changed, 601 insertions(+), 205 deletions(-)

-- 
1.7.4

[net-next-2.6 01/16] e1000e: replace unbounded sprintf with snprintf

[Jeff Kirsher]

From: Bruce Allan <bruce.w.allan@intel.com>

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/e1000e/netdev.c |    8 ++++++--
 1 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c
index 5b916b0..80614c9 100644
--- a/drivers/net/e1000e/netdev.c
+++ b/drivers/net/e1000e/netdev.c
@@ -1843,7 +1843,9 @@ static int e1000_request_msix(struct e1000_adapter *adapter)
 	int err = 0, vector = 0;
 
 	if (strlen(netdev->name) < (IFNAMSIZ - 5))
-		sprintf(adapter->rx_ring->name, "%s-rx-0", netdev->name);
+		snprintf(adapter->rx_ring->name,
+			 sizeof(adapter->rx_ring->name) - 1,
+			 "%s-rx-0", netdev->name);
 	else
 		memcpy(adapter->rx_ring->name, netdev->name, IFNAMSIZ);
 	err = request_irq(adapter->msix_entries[vector].vector,
@@ -1856,7 +1858,9 @@ static int e1000_request_msix(struct e1000_adapter *adapter)
 	vector++;
 
 	if (strlen(netdev->name) < (IFNAMSIZ - 5))
-		sprintf(adapter->tx_ring->name, "%s-tx-0", netdev->name);
+		snprintf(adapter->tx_ring->name,
+			 sizeof(adapter->tx_ring->name) - 1,
+			 "%s-tx-0", netdev->name);
 	else
 		memcpy(adapter->tx_ring->name, netdev->name, IFNAMSIZ);
 	err = request_irq(adapter->msix_entries[vector].vector,
-- 
1.7.4

[net-next-2.6 02/16] e1000e: use correct pointer when memcpy'ing a 2-dimensional array

[Jeff Kirsher]

From: Bruce Allan <bruce.w.allan@intel.com>

*e1000_gstrings_test is not the same size as e1000_gstrings_test.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/e1000e/ethtool.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/drivers/net/e1000e/ethtool.c b/drivers/net/e1000e/ethtool.c
index daa7fe4..0c08599 100644
--- a/drivers/net/e1000e/ethtool.c
+++ b/drivers/net/e1000e/ethtool.c
@@ -2006,7 +2006,7 @@ static void e1000_get_strings(struct net_device *netdev, u32 stringset,
 
 	switch (stringset) {
 	case ETH_SS_TEST:
-		memcpy(data, *e1000_gstrings_test, sizeof(e1000_gstrings_test));
+		memcpy(data, e1000_gstrings_test, sizeof(e1000_gstrings_test));
 		break;
 	case ETH_SS_STATS:
 		for (i = 0; i < E1000_GLOBAL_STATS_LEN; i++) {
-- 
1.7.4

[net-next-2.6 03/16] e1000e: do not wakeup Tx queue until ready

[Jeff Kirsher]

From: Bruce Allan <bruce.w.allan@intel.com>

When restarting the adapter via calls to e1000e_down() followed by
e1000e_up() (for example when restarting autonegotiation via ethtool),
packets can be queued for transmit before link is actually up and
netif_carrier_on is set.  This was causing the watchdog_task to do an
extra unnecessary reset of the adapter.  Delaying the wakeup of the Tx
queue until link is up prevents the reset.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/e1000e/netdev.c |    5 +----
 1 files changed, 1 insertions(+), 4 deletions(-)

diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c
index 80614c9..3c95d6b 100644
--- a/drivers/net/e1000e/netdev.c
+++ b/drivers/net/e1000e/netdev.c
@@ -3324,8 +3324,6 @@ int e1000e_up(struct e1000_adapter *adapter)
 		e1000_configure_msix(adapter);
 	e1000_irq_enable(adapter);
 
-	netif_wake_queue(adapter->netdev);
-
 	/* fire a link change interrupt to start the watchdog */
 	if (adapter->msix_entries)
 		ew32(ICS, E1000_ICS_LSC | E1000_ICR_OTHER);
@@ -3638,8 +3636,6 @@ static int e1000_open(struct net_device *netdev)
 
 	e1000_irq_enable(adapter);
 
-	netif_start_queue(netdev);
-
 	adapter->idle_check = true;
 	pm_runtime_put(&pdev->dev);
 
@@ -4265,6 +4261,7 @@ static void e1000_watchdog_task(struct work_struct *work)
 				phy->ops.cfg_on_link_up(hw);
 
 			netif_carrier_on(netdev);
+			netif_wake_queue(netdev);
 
 			if (!test_bit(__E1000_DOWN, &adapter->state))
 				mod_timer(&adapter->phy_info_timer,
-- 
1.7.4

Re: [net-next-2.6 03/16] e1000e: do not wakeup Tx queue until ready

[David Miller]

From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Tue,  8 Feb 2011 04:29:14 -0800

> From: Bruce Allan <bruce.w.allan@intel.com>
> 
> When restarting the adapter via calls to e1000e_down() followed by
> e1000e_up() (for example when restarting autonegotiation via ethtool),
> packets can be queued for transmit before link is actually up and
> netif_carrier_on is set.  This was causing the watchdog_task to do an
> extra unnecessary reset of the adapter.  Delaying the wakeup of the Tx
> queue until link is up prevents the reset.
> 
> Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
> Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com>
> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

You should not control the TX queue based upon link status information.
That's the job of netif_carrier_{on,off}().

The TX queue state should be set based solely upon that state of the
TX ring, whether it is full or not.

When the netif carrier is off, the packet scheduler is blocked from
sending packets to the driver.

If that isn't happening, that's a bug which you need to track down.
Maybe you're not doing netif_carrier_off() early enough.

RE: [net-next-2.6 03/16] e1000e: do not wakeup Tx queue until ready

[Allan, Bruce W]

>-----Original Message-----
>From: David Miller [mailto:davem@davemloft.net]
>Sent: Tuesday, February 08, 2011 12:21 PM
>To: Kirsher, Jeffrey T
>Cc: Allan, Bruce W; netdev@vger.kernel.org; gospo@redhat.com;
>bphilips@novell.com
>Subject: Re: [net-next-2.6 03/16] e1000e: do not wakeup Tx queue until ready
>
>You should not control the TX queue based upon link status information.
>That's the job of netif_carrier_{on,off}().
>
>The TX queue state should be set based solely upon that state of the
>TX ring, whether it is full or not.
>
>When the netif carrier is off, the packet scheduler is blocked from
>sending packets to the driver.
>
>If that isn't happening, that's a bug which you need to track down.
>Maybe you're not doing netif_carrier_off() early enough.

That's what I understood, but the driver was still getting packets
scheduled, at least that's what appeared to happen.  I'll dig deeper.

Thanks,
Bruce.

[net-next-2.6 04/16] e1000e: return appropriate errors for 'ethtool -r'

[Jeff Kirsher]

From: Bruce Allan <bruce.w.allan@intel.com>

...when invoked while interface is not up or when auto-negotiation is
disabled as done by other drivers.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/e1000e/ethtool.c |   11 +++++++++--
 1 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/e1000e/ethtool.c b/drivers/net/e1000e/ethtool.c
index 0c08599..65ef9b5 100644
--- a/drivers/net/e1000e/ethtool.c
+++ b/drivers/net/e1000e/ethtool.c
@@ -1963,8 +1963,15 @@ static int e1000_set_coalesce(struct net_device *netdev,
 static int e1000_nway_reset(struct net_device *netdev)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
-	if (netif_running(netdev))
-		e1000e_reinit_locked(adapter);
+
+	if (!netif_running(netdev))
+		return -EAGAIN;
+
+	if (!adapter->hw.mac.autoneg)
+		return -EINVAL;
+
+	e1000e_reinit_locked(adapter);
+
 	return 0;
 }
 
-- 
1.7.4

[net-next-2.6 05/16] igb: Enable PF side of SR-IOV support for i350 devices

[Jeff Kirsher]

From: Carolyn Wyborny <carolyn.wyborny@intel.com>

This patch adds full support for SR-IOV by enabling the PF side.
VF side has already been committed.

Signed-off-by: Carolyn Wyborny <carolyn.wyborny@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/igb/e1000_82575.c |   10 ++++++++--
 drivers/net/igb/e1000_mbx.c   |   38 ++++++++++++++++++--------------------
 drivers/net/igb/igb_main.c    |    9 +++++++--
 3 files changed, 33 insertions(+), 24 deletions(-)

diff --git a/drivers/net/igb/e1000_82575.c b/drivers/net/igb/e1000_82575.c
index c1552b6..65c1833 100644
--- a/drivers/net/igb/e1000_82575.c
+++ b/drivers/net/igb/e1000_82575.c
@@ -238,9 +238,15 @@ static s32 igb_get_invariants_82575(struct e1000_hw *hw)
 		size = 14;
 	nvm->word_size = 1 << size;
 
-	/* if 82576 then initialize mailbox parameters */
-	if (mac->type == e1000_82576)
+	/* if part supports SR-IOV then initialize mailbox parameters */
+	switch (mac->type) {
+	case e1000_82576:
+	case e1000_i350:
 		igb_init_mbx_params_pf(hw);
+		break;
+	default:
+		break;
+	}
 
 	/* setup PHY parameters */
 	if (phy->media_type != e1000_media_type_copper) {
diff --git a/drivers/net/igb/e1000_mbx.c b/drivers/net/igb/e1000_mbx.c
index c474cdb..78d48c7 100644
--- a/drivers/net/igb/e1000_mbx.c
+++ b/drivers/net/igb/e1000_mbx.c
@@ -422,26 +422,24 @@ s32 igb_init_mbx_params_pf(struct e1000_hw *hw)
 {
 	struct e1000_mbx_info *mbx = &hw->mbx;
 
-	if (hw->mac.type == e1000_82576) {
-		mbx->timeout = 0;
-		mbx->usec_delay = 0;
-
-		mbx->size = E1000_VFMAILBOX_SIZE;
-
-		mbx->ops.read = igb_read_mbx_pf;
-		mbx->ops.write = igb_write_mbx_pf;
-		mbx->ops.read_posted = igb_read_posted_mbx;
-		mbx->ops.write_posted = igb_write_posted_mbx;
-		mbx->ops.check_for_msg = igb_check_for_msg_pf;
-		mbx->ops.check_for_ack = igb_check_for_ack_pf;
-		mbx->ops.check_for_rst = igb_check_for_rst_pf;
-
-		mbx->stats.msgs_tx = 0;
-		mbx->stats.msgs_rx = 0;
-		mbx->stats.reqs = 0;
-		mbx->stats.acks = 0;
-		mbx->stats.rsts = 0;
-	}
+	mbx->timeout = 0;
+	mbx->usec_delay = 0;
+
+	mbx->size = E1000_VFMAILBOX_SIZE;
+
+	mbx->ops.read = igb_read_mbx_pf;
+	mbx->ops.write = igb_write_mbx_pf;
+	mbx->ops.read_posted = igb_read_posted_mbx;
+	mbx->ops.write_posted = igb_write_posted_mbx;
+	mbx->ops.check_for_msg = igb_check_for_msg_pf;
+	mbx->ops.check_for_ack = igb_check_for_ack_pf;
+	mbx->ops.check_for_rst = igb_check_for_rst_pf;
+
+	mbx->stats.msgs_tx = 0;
+	mbx->stats.msgs_rx = 0;
+	mbx->stats.reqs = 0;
+	mbx->stats.acks = 0;
+	mbx->stats.rsts = 0;
 
 	return 0;
 }
diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 200cc32..cb6bf7b 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -2287,9 +2287,14 @@ static int __devinit igb_sw_init(struct igb_adapter *adapter)
 
 	spin_lock_init(&adapter->stats64_lock);
 #ifdef CONFIG_PCI_IOV
-	if (hw->mac.type == e1000_82576)
+	switch (hw->mac.type) {
+	case e1000_82576:
+	case e1000_i350:
 		adapter->vfs_allocated_count = (max_vfs > 7) ? 7 : max_vfs;
-
+		break;
+	default:
+		break;
+	}
 #endif /* CONFIG_PCI_IOV */
 	adapter->rss_queues = min_t(u32, IGB_MAX_RX_QUEUES, num_online_cpus());
 
-- 
1.7.4

[net-next-2.6 06/16] ixgbe: DCB, only reprogram HW if the FCoE priority is changed

[Jeff Kirsher]

From: John Fastabend <john.r.fastabend@intel.com>

If the FCoE priority is not changing do not set the RESET and
APP_UPCHG bits. This causes unneeded HW resets and which can
cause unneeded LLDP frames and negotiations.

The current check is not sufficient because the FCoE priority
can change twice during a negotiation which results in the
bits being set. This occurs when the switch changes the
priority or when the link is reset with switches that do not
include the APP priority until after PFC has been negotiated.

This results in set_app being called with the local APP
priority. Then the negotiation completes and set_app
is called again with the peer APP priority. The check
fails so the device is reset and the above occurs again
resulting in an endless loop of resets.

By only resetting the device if the APP priority has really
changed we short circuit the loop.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Tested-by: Ross Brattain <ross.b.brattain@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ixgbe/ixgbe_dcb_nl.c |   38 ++++++++++++++++++++++++++------------
 1 files changed, 26 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ixgbe/ixgbe_dcb_nl.c
index bf566e8..4805835 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_nl.c
@@ -353,6 +353,7 @@ static void ixgbe_dcbnl_get_pfc_cfg(struct net_device *netdev, int priority,
 static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	bool do_reset;
 	int ret;
 
 	if (!adapter->dcb_set_bitmap)
@@ -368,7 +369,9 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 	 * Only take down the adapter if the configuration change
 	 * requires a reset.
 	 */
-	if (adapter->dcb_set_bitmap & BIT_RESETLINK) {
+	do_reset = adapter->dcb_set_bitmap & (BIT_RESETLINK | BIT_APP_UPCHG);
+
+	if (do_reset) {
 		while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state))
 			msleep(1);
 
@@ -408,7 +411,7 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 		}
 	}
 
-	if (adapter->dcb_set_bitmap & BIT_RESETLINK) {
+	if (do_reset) {
 		if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) {
 			ixgbe_init_interrupt_scheme(adapter);
 			if (netif_running(netdev))
@@ -430,7 +433,7 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 	if (adapter->dcb_cfg.pfc_mode_enable)
 		adapter->hw.fc.current_mode = ixgbe_fc_pfc;
 
-	if (adapter->dcb_set_bitmap & BIT_RESETLINK)
+	if (do_reset)
 		clear_bit(__IXGBE_RESETTING, &adapter->state);
 	adapter->dcb_set_bitmap = 0x00;
 	return ret;
@@ -568,18 +571,29 @@ static u8 ixgbe_dcbnl_setapp(struct net_device *netdev,
 	case DCB_APP_IDTYPE_ETHTYPE:
 #ifdef IXGBE_FCOE
 		if (id == ETH_P_FCOE) {
-			u8 tc;
-			struct ixgbe_adapter *adapter;
+			u8 old_tc;
+			struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
-			adapter = netdev_priv(netdev);
-			tc = adapter->fcoe.tc;
+			/* Get current programmed tc */
+			old_tc = adapter->fcoe.tc;
 			rval = ixgbe_fcoe_setapp(adapter, up);
-			if ((!rval) && (tc != adapter->fcoe.tc) &&
-			    (adapter->flags & IXGBE_FLAG_DCB_ENABLED) &&
-			    (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) {
+
+			if (rval ||
+			   !(adapter->flags & IXGBE_FLAG_DCB_ENABLED) ||
+			   !(adapter->flags & IXGBE_FLAG_FCOE_ENABLED))
+				break;
+
+			/* The FCoE application priority may be changed multiple
+			 * times in quick sucession with switches that build up
+			 * TLVs. To avoid creating uneeded device resets this
+			 * checks the actual HW configuration and clears
+			 * BIT_APP_UPCHG if a HW configuration change is not
+			 * need
+			 */
+			if (old_tc == adapter->fcoe.tc)
+				adapter->dcb_set_bitmap &= ~BIT_APP_UPCHG;
+			else
 				adapter->dcb_set_bitmap |= BIT_APP_UPCHG;
-				adapter->dcb_set_bitmap |= BIT_RESETLINK;
-			}
 		}
 #endif
 		break;
-- 
1.7.4

[net-next-2.6 07/16] ixgbe: DCB, remove round robin mode on 82598 devices

[Jeff Kirsher]

From: John Fastabend <john.r.fastabend@intel.com>

Remove round robin configuration code for 82598 parts it
is not settable and is always false.

If we need/want this in the future we can add it back properly.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Tested-by: Ross Brattain <ross.b.brattain@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ixgbe/ixgbe_dcb.h       |    1 -
 drivers/net/ixgbe/ixgbe_dcb_82598.c |    6 ++----
 drivers/net/ixgbe/ixgbe_main.c      |    1 -
 3 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ixgbe/ixgbe_dcb.h b/drivers/net/ixgbe/ixgbe_dcb.h
index 1cfe38e..d0b2450 100644
--- a/drivers/net/ixgbe/ixgbe_dcb.h
+++ b/drivers/net/ixgbe/ixgbe_dcb.h
@@ -139,7 +139,6 @@ struct ixgbe_dcb_config {
 	struct tc_configuration tc_config[MAX_TRAFFIC_CLASS];
 	u8     bw_percentage[2][MAX_BW_GROUP]; /* One each for Tx/Rx */
 	bool   pfc_mode_enable;
-	bool   round_robin_enable;
 
 	enum dcb_rx_pba_cfg rx_pba_cfg;
 
diff --git a/drivers/net/ixgbe/ixgbe_dcb_82598.c b/drivers/net/ixgbe/ixgbe_dcb_82598.c
index 9a5e89c..19aa806 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_82598.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_82598.c
@@ -146,10 +146,8 @@ static s32 ixgbe_dcb_config_tx_desc_arbiter_82598(struct ixgbe_hw *hw,
 
 	/* Enable arbiter */
 	reg &= ~IXGBE_DPMCS_ARBDIS;
-	if (!(dcb_config->round_robin_enable)) {
-		/* Enable DFP and Recycle mode */
-		reg |= (IXGBE_DPMCS_TDPAC | IXGBE_DPMCS_TRM);
-	}
+	/* Enable DFP and Recycle mode */
+	reg |= (IXGBE_DPMCS_TDPAC | IXGBE_DPMCS_TRM);
 	reg |= IXGBE_DPMCS_TSOEF;
 	/* Configure Max TSO packet size 34KB including payload and headers */
 	reg |= (0x4 << IXGBE_DPMCS_MTSOS_SHIFT);
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index 602078b..ef4a517 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -5169,7 +5169,6 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter)
 	adapter->dcb_cfg.bw_percentage[DCB_RX_CONFIG][0] = 100;
 	adapter->dcb_cfg.rx_pba_cfg = pba_equal;
 	adapter->dcb_cfg.pfc_mode_enable = false;
-	adapter->dcb_cfg.round_robin_enable = false;
 	adapter->dcb_set_bitmap = 0x00;
 	ixgbe_copy_dcb_cfg(&adapter->dcb_cfg, &adapter->temp_dcb_cfg,
 			   adapter->ring_feature[RING_F_DCB].indices);
-- 
1.7.4

[net-next-2.6 08/16] ixgbe: DCB, abstract out dcb_config from DCB hardware configuration

[Jeff Kirsher]

From: John Fastabend <john.r.fastabend@intel.com>

Currently the routines that configure the HW for DCB require a
ixgbe_dcb_config structure. This structure was designed to support
the CEE standard and does not match the IEEE standard well.

This patch changes the HW routines in ixgbe_dcb_8259x.{ch} to use
raw pfc and bandwidth values. This requires some parsing of the DCB
configuration but makes the HW routines independent of the data
structure that contains the DCB configuration.

The primary advantage to doing this is we can do HW setup directly
from the 802.1Qaz ops without having to arbitrarily encapsulate this
data into the CEE structure.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Tested-by: Ross Brattain <ross.b.brattain@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ixgbe/ixgbe_dcb.c       |   74 ++++++++++++++++++++++-
 drivers/net/ixgbe/ixgbe_dcb.h       |    1 +
 drivers/net/ixgbe/ixgbe_dcb_82598.c |   86 ++++++++++++++------------
 drivers/net/ixgbe/ixgbe_dcb_82598.h |   23 ++++++-
 drivers/net/ixgbe/ixgbe_dcb_82599.c |  115 ++++++++++++++++++++---------------
 drivers/net/ixgbe/ixgbe_dcb_82599.h |   24 ++++++-
 drivers/net/ixgbe/ixgbe_dcb_nl.c    |    9 ++-
 7 files changed, 230 insertions(+), 102 deletions(-)

diff --git a/drivers/net/ixgbe/ixgbe_dcb.c b/drivers/net/ixgbe/ixgbe_dcb.c
index d16c260..d9bb670 100644
--- a/drivers/net/ixgbe/ixgbe_dcb.c
+++ b/drivers/net/ixgbe/ixgbe_dcb.c
@@ -141,6 +141,59 @@ out:
 	return ret_val;
 }
 
+void ixgbe_dcb_unpack_pfc(struct ixgbe_dcb_config *cfg, u8 *pfc_en)
+{
+	int i;
+
+	*pfc_en = 0;
+	for (i = 0; i < MAX_TRAFFIC_CLASS; i++)
+		*pfc_en |= (cfg->tc_config[i].dcb_pfc & 0xF) << i;
+}
+
+void ixgbe_dcb_unpack_refill(struct ixgbe_dcb_config *cfg, int direction,
+			     u16 *refill)
+{
+	struct tc_bw_alloc *p;
+	int i;
+
+	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
+		p = &cfg->tc_config[i].path[direction];
+		refill[i] = p->data_credits_refill;
+	}
+}
+
+void ixgbe_dcb_unpack_max(struct ixgbe_dcb_config *cfg, u16 *max)
+{
+	int i;
+
+	for (i = 0; i < MAX_TRAFFIC_CLASS; i++)
+		max[i] = cfg->tc_config[i].desc_credits_max;
+}
+
+void ixgbe_dcb_unpack_bwgid(struct ixgbe_dcb_config *cfg, int direction,
+			    u8 *bwgid)
+{
+	struct tc_bw_alloc *p;
+	int i;
+
+	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
+		p = &cfg->tc_config[i].path[direction];
+		bwgid[i] = p->bwg_id;
+	}
+}
+
+void ixgbe_dcb_unpack_prio(struct ixgbe_dcb_config *cfg, int direction,
+			    u8 *ptype)
+{
+	struct tc_bw_alloc *p;
+	int i;
+
+	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
+		p = &cfg->tc_config[i].path[direction];
+		ptype[i] = p->prio_type;
+	}
+}
+
 /**
  * ixgbe_dcb_hw_config - Config and enable DCB
  * @hw: pointer to hardware structure
@@ -152,13 +205,30 @@ s32 ixgbe_dcb_hw_config(struct ixgbe_hw *hw,
                         struct ixgbe_dcb_config *dcb_config)
 {
 	s32 ret = 0;
+	u8 pfc_en;
+	u8 ptype[MAX_TRAFFIC_CLASS];
+	u8 bwgid[MAX_TRAFFIC_CLASS];
+	u16 refill[MAX_TRAFFIC_CLASS];
+	u16 max[MAX_TRAFFIC_CLASS];
+
+	/* Unpack CEE standard containers */
+	ixgbe_dcb_unpack_pfc(dcb_config, &pfc_en);
+	ixgbe_dcb_unpack_refill(dcb_config, DCB_TX_CONFIG, refill);
+	ixgbe_dcb_unpack_max(dcb_config, max);
+	ixgbe_dcb_unpack_bwgid(dcb_config, DCB_TX_CONFIG, bwgid);
+	ixgbe_dcb_unpack_prio(dcb_config, DCB_TX_CONFIG, ptype);
+
 	switch (hw->mac.type) {
 	case ixgbe_mac_82598EB:
-		ret = ixgbe_dcb_hw_config_82598(hw, dcb_config);
+		ret = ixgbe_dcb_hw_config_82598(hw, dcb_config->rx_pba_cfg,
+						pfc_en, refill, max, bwgid,
+						ptype);
 		break;
 	case ixgbe_mac_82599EB:
 	case ixgbe_mac_X540:
-		ret = ixgbe_dcb_hw_config_82599(hw, dcb_config);
+		ret = ixgbe_dcb_hw_config_82599(hw, dcb_config->rx_pba_cfg,
+						pfc_en, refill, max, bwgid,
+						ptype);
 		break;
 	default:
 		break;
diff --git a/drivers/net/ixgbe/ixgbe_dcb.h b/drivers/net/ixgbe/ixgbe_dcb.h
index d0b2450..aa6cb5f 100644
--- a/drivers/net/ixgbe/ixgbe_dcb.h
+++ b/drivers/net/ixgbe/ixgbe_dcb.h
@@ -147,6 +147,7 @@ struct ixgbe_dcb_config {
 };
 
 /* DCB driver APIs */
+void ixgbe_dcb_unpack_pfc(struct ixgbe_dcb_config *cfg, u8 *pfc_en);
 
 /* DCB credits calculation */
 s32 ixgbe_dcb_calculate_tc_credits(struct ixgbe_hw *,
diff --git a/drivers/net/ixgbe/ixgbe_dcb_82598.c b/drivers/net/ixgbe/ixgbe_dcb_82598.c
index 19aa806..d128806 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_82598.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_82598.c
@@ -38,15 +38,14 @@
  *
  * Configure packet buffers for DCB mode.
  */
-static s32 ixgbe_dcb_config_packet_buffers_82598(struct ixgbe_hw *hw,
-						 struct ixgbe_dcb_config *dcb_config)
+static s32 ixgbe_dcb_config_packet_buffers_82598(struct ixgbe_hw *hw, u8 rx_pba)
 {
 	s32 ret_val = 0;
 	u32 value = IXGBE_RXPBSIZE_64KB;
 	u8  i = 0;
 
 	/* Setup Rx packet buffer sizes */
-	switch (dcb_config->rx_pba_cfg) {
+	switch (rx_pba) {
 	case pba_80_48:
 		/* Setup the first four at 80KB */
 		value = IXGBE_RXPBSIZE_80KB;
@@ -78,10 +77,11 @@ static s32 ixgbe_dcb_config_packet_buffers_82598(struct ixgbe_hw *hw,
  *
  * Configure Rx Data Arbiter and credits for each traffic class.
  */
-static s32 ixgbe_dcb_config_rx_arbiter_82598(struct ixgbe_hw *hw,
-                                      struct ixgbe_dcb_config *dcb_config)
+s32 ixgbe_dcb_config_rx_arbiter_82598(struct ixgbe_hw *hw,
+					u16 *refill,
+					u16 *max,
+					u8 *prio_type)
 {
-	struct tc_bw_alloc    *p;
 	u32    reg           = 0;
 	u32    credit_refill = 0;
 	u32    credit_max    = 0;
@@ -102,13 +102,12 @@ static s32 ixgbe_dcb_config_rx_arbiter_82598(struct ixgbe_hw *hw,
 
 	/* Configure traffic class credits and priority */
 	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
-		p = &dcb_config->tc_config[i].path[DCB_RX_CONFIG];
-		credit_refill = p->data_credits_refill;
-		credit_max    = p->data_credits_max;
+		credit_refill = refill[i];
+		credit_max    = max[i];
 
 		reg = credit_refill | (credit_max << IXGBE_RT2CR_MCL_SHIFT);
 
-		if (p->prio_type == prio_link)
+		if (prio_type[i] == prio_link)
 			reg |= IXGBE_RT2CR_LSP;
 
 		IXGBE_WRITE_REG(hw, IXGBE_RT2CR(i), reg);
@@ -135,10 +134,12 @@ static s32 ixgbe_dcb_config_rx_arbiter_82598(struct ixgbe_hw *hw,
  *
  * Configure Tx Descriptor Arbiter and credits for each traffic class.
  */
-static s32 ixgbe_dcb_config_tx_desc_arbiter_82598(struct ixgbe_hw *hw,
-                                           struct ixgbe_dcb_config *dcb_config)
+s32 ixgbe_dcb_config_tx_desc_arbiter_82598(struct ixgbe_hw *hw,
+						u16 *refill,
+						u16 *max,
+						u8 *bwg_id,
+						u8 *prio_type)
 {
-	struct tc_bw_alloc *p;
 	u32    reg, max_credits;
 	u8     i;
 
@@ -156,16 +157,15 @@ static s32 ixgbe_dcb_config_tx_desc_arbiter_82598(struct ixgbe_hw *hw,
 
 	/* Configure traffic class credits and priority */
 	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
-		p = &dcb_config->tc_config[i].path[DCB_TX_CONFIG];
-		max_credits = dcb_config->tc_config[i].desc_credits_max;
+		max_credits = max[i];
 		reg = max_credits << IXGBE_TDTQ2TCCR_MCL_SHIFT;
-		reg |= p->data_credits_refill;
-		reg |= (u32)(p->bwg_id) << IXGBE_TDTQ2TCCR_BWG_SHIFT;
+		reg |= refill[i];
+		reg |= (u32)(bwg_id[i]) << IXGBE_TDTQ2TCCR_BWG_SHIFT;
 
-		if (p->prio_type == prio_group)
+		if (prio_type[i] == prio_group)
 			reg |= IXGBE_TDTQ2TCCR_GSP;
 
-		if (p->prio_type == prio_link)
+		if (prio_type[i] == prio_link)
 			reg |= IXGBE_TDTQ2TCCR_LSP;
 
 		IXGBE_WRITE_REG(hw, IXGBE_TDTQ2TCCR(i), reg);
@@ -181,10 +181,12 @@ static s32 ixgbe_dcb_config_tx_desc_arbiter_82598(struct ixgbe_hw *hw,
  *
  * Configure Tx Data Arbiter and credits for each traffic class.
  */
-static s32 ixgbe_dcb_config_tx_data_arbiter_82598(struct ixgbe_hw *hw,
-                                           struct ixgbe_dcb_config *dcb_config)
+s32 ixgbe_dcb_config_tx_data_arbiter_82598(struct ixgbe_hw *hw,
+						u16 *refill,
+						u16 *max,
+						u8 *bwg_id,
+						u8 *prio_type)
 {
-	struct tc_bw_alloc *p;
 	u32 reg;
 	u8 i;
 
@@ -198,15 +200,14 @@ static s32 ixgbe_dcb_config_tx_data_arbiter_82598(struct ixgbe_hw *hw,
 
 	/* Configure traffic class credits and priority */
 	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
-		p = &dcb_config->tc_config[i].path[DCB_TX_CONFIG];
-		reg = p->data_credits_refill;
-		reg |= (u32)(p->data_credits_max) << IXGBE_TDPT2TCCR_MCL_SHIFT;
-		reg |= (u32)(p->bwg_id) << IXGBE_TDPT2TCCR_BWG_SHIFT;
+		reg = refill[i];
+		reg |= (u32)(max[i]) << IXGBE_TDPT2TCCR_MCL_SHIFT;
+		reg |= (u32)(bwg_id[i]) << IXGBE_TDPT2TCCR_BWG_SHIFT;
 
-		if (p->prio_type == prio_group)
+		if (prio_type[i] == prio_group)
 			reg |= IXGBE_TDPT2TCCR_GSP;
 
-		if (p->prio_type == prio_link)
+		if (prio_type[i] == prio_link)
 			reg |= IXGBE_TDPT2TCCR_LSP;
 
 		IXGBE_WRITE_REG(hw, IXGBE_TDPT2TCCR(i), reg);
@@ -227,13 +228,12 @@ static s32 ixgbe_dcb_config_tx_data_arbiter_82598(struct ixgbe_hw *hw,
  *
  * Configure Priority Flow Control for each traffic class.
  */
-s32 ixgbe_dcb_config_pfc_82598(struct ixgbe_hw *hw,
-                               struct ixgbe_dcb_config *dcb_config)
+s32 ixgbe_dcb_config_pfc_82598(struct ixgbe_hw *hw, u8 pfc_en)
 {
 	u32 reg, rx_pba_size;
 	u8  i;
 
-	if (!dcb_config->pfc_mode_enable)
+	if (!pfc_en)
 		goto out;
 
 	/* Enable Transmit Priority Flow Control */
@@ -254,19 +254,20 @@ s32 ixgbe_dcb_config_pfc_82598(struct ixgbe_hw *hw,
 	 * for each traffic class.
 	 */
 	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
+		int enabled = pfc_en & (1 << i);
 		rx_pba_size = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i));
 		rx_pba_size >>= IXGBE_RXPBSIZE_SHIFT;
 		reg = (rx_pba_size - hw->fc.low_water) << 10;
 
-		if (dcb_config->tc_config[i].dcb_pfc == pfc_enabled_tx ||
-		    dcb_config->tc_config[i].dcb_pfc == pfc_enabled_full)
+		if (enabled == pfc_enabled_tx ||
+		    enabled == pfc_enabled_full)
 			reg |= IXGBE_FCRTL_XONE;
 
 		IXGBE_WRITE_REG(hw, IXGBE_FCRTL(i), reg);
 
 		reg = (rx_pba_size - hw->fc.high_water) << 10;
-		if (dcb_config->tc_config[i].dcb_pfc == pfc_enabled_tx ||
-		    dcb_config->tc_config[i].dcb_pfc == pfc_enabled_full)
+		if (enabled == pfc_enabled_tx ||
+		    enabled == pfc_enabled_full)
 			reg |= IXGBE_FCRTH_FCEN;
 
 		IXGBE_WRITE_REG(hw, IXGBE_FCRTH(i), reg);
@@ -323,13 +324,16 @@ static s32 ixgbe_dcb_config_tc_stats_82598(struct ixgbe_hw *hw)
  * Configure dcb settings and enable dcb mode.
  */
 s32 ixgbe_dcb_hw_config_82598(struct ixgbe_hw *hw,
-                              struct ixgbe_dcb_config *dcb_config)
+			      u8 rx_pba, u8 pfc_en, u16 *refill,
+			      u16 *max, u8 *bwg_id, u8 *prio_type)
 {
-	ixgbe_dcb_config_packet_buffers_82598(hw, dcb_config);
-	ixgbe_dcb_config_rx_arbiter_82598(hw, dcb_config);
-	ixgbe_dcb_config_tx_desc_arbiter_82598(hw, dcb_config);
-	ixgbe_dcb_config_tx_data_arbiter_82598(hw, dcb_config);
-	ixgbe_dcb_config_pfc_82598(hw, dcb_config);
+	ixgbe_dcb_config_packet_buffers_82598(hw, rx_pba);
+	ixgbe_dcb_config_rx_arbiter_82598(hw, refill, max, prio_type);
+	ixgbe_dcb_config_tx_desc_arbiter_82598(hw, refill, max,
+					       bwg_id, prio_type);
+	ixgbe_dcb_config_tx_data_arbiter_82598(hw, refill, max,
+					       bwg_id, prio_type);
+	ixgbe_dcb_config_pfc_82598(hw, pfc_en);
 	ixgbe_dcb_config_tc_stats_82598(hw);
 
 	return 0;
diff --git a/drivers/net/ixgbe/ixgbe_dcb_82598.h b/drivers/net/ixgbe/ixgbe_dcb_82598.h
index abc03cc..0d2a758 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_82598.h
+++ b/drivers/net/ixgbe/ixgbe_dcb_82598.h
@@ -71,9 +71,28 @@
 /* DCB hardware-specific driver APIs */
 
 /* DCB PFC functions */
-s32 ixgbe_dcb_config_pfc_82598(struct ixgbe_hw *, struct ixgbe_dcb_config *);
+s32 ixgbe_dcb_config_pfc_82598(struct ixgbe_hw *, u8 pfc_en);
 
 /* DCB hw initialization */
-s32 ixgbe_dcb_hw_config_82598(struct ixgbe_hw *, struct ixgbe_dcb_config *);
+s32 ixgbe_dcb_config_rx_arbiter_82598(struct ixgbe_hw *hw,
+					u16 *refill,
+					u16 *max,
+					u8 *prio_type);
+
+s32 ixgbe_dcb_config_tx_desc_arbiter_82598(struct ixgbe_hw *hw,
+						u16 *refill,
+						u16 *max,
+						u8 *bwg_id,
+						u8 *prio_type);
+
+s32 ixgbe_dcb_config_tx_data_arbiter_82598(struct ixgbe_hw *hw,
+						u16 *refill,
+						u16 *max,
+						u8 *bwg_id,
+						u8 *prio_type);
+
+s32 ixgbe_dcb_hw_config_82598(struct ixgbe_hw *hw,
+			      u8 rx_pba, u8 pfc_en, u16 *refill,
+			      u16 *max, u8 *bwg_id, u8 *prio_type);
 
 #endif /* _DCB_82598_CONFIG_H */
diff --git a/drivers/net/ixgbe/ixgbe_dcb_82599.c b/drivers/net/ixgbe/ixgbe_dcb_82599.c
index 374e1f7..b0d97a9 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_82599.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_82599.c
@@ -33,19 +33,18 @@
 /**
  * ixgbe_dcb_config_packet_buffers_82599 - Configure DCB packet buffers
  * @hw: pointer to hardware structure
- * @dcb_config: pointer to ixgbe_dcb_config structure
+ * @rx_pba: method to distribute packet buffer
  *
  * Configure packet buffers for DCB mode.
  */
-static s32 ixgbe_dcb_config_packet_buffers_82599(struct ixgbe_hw *hw,
-                                          struct ixgbe_dcb_config *dcb_config)
+static s32 ixgbe_dcb_config_packet_buffers_82599(struct ixgbe_hw *hw, u8 rx_pba)
 {
 	s32 ret_val = 0;
 	u32 value = IXGBE_RXPBSIZE_64KB;
 	u8  i = 0;
 
 	/* Setup Rx packet buffer sizes */
-	switch (dcb_config->rx_pba_cfg) {
+	switch (rx_pba) {
 	case pba_80_48:
 		/* Setup the first four at 80KB */
 		value = IXGBE_RXPBSIZE_80KB;
@@ -75,14 +74,19 @@ static s32 ixgbe_dcb_config_packet_buffers_82599(struct ixgbe_hw *hw,
 /**
  * ixgbe_dcb_config_rx_arbiter_82599 - Config Rx Data arbiter
  * @hw: pointer to hardware structure
- * @dcb_config: pointer to ixgbe_dcb_config structure
+ * @refill: refill credits index by traffic class
+ * @max: max credits index by traffic class
+ * @bwg_id: bandwidth grouping indexed by traffic class
+ * @prio_type: priority type indexed by traffic class
  *
  * Configure Rx Packet Arbiter and credits for each traffic class.
  */
-static s32 ixgbe_dcb_config_rx_arbiter_82599(struct ixgbe_hw *hw,
-                                      struct ixgbe_dcb_config *dcb_config)
+s32 ixgbe_dcb_config_rx_arbiter_82599(struct ixgbe_hw *hw,
+				      u16 *refill,
+				      u16 *max,
+				      u8 *bwg_id,
+				      u8 *prio_type)
 {
-	struct tc_bw_alloc    *p;
 	u32    reg           = 0;
 	u32    credit_refill = 0;
 	u32    credit_max    = 0;
@@ -103,15 +107,13 @@ static s32 ixgbe_dcb_config_rx_arbiter_82599(struct ixgbe_hw *hw,
 
 	/* Configure traffic class credits and priority */
 	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
-		p = &dcb_config->tc_config[i].path[DCB_RX_CONFIG];
-
-		credit_refill = p->data_credits_refill;
-		credit_max    = p->data_credits_max;
+		credit_refill = refill[i];
+		credit_max    = max[i];
 		reg = credit_refill | (credit_max << IXGBE_RTRPT4C_MCL_SHIFT);
 
-		reg |= (u32)(p->bwg_id) << IXGBE_RTRPT4C_BWG_SHIFT;
+		reg |= (u32)(bwg_id[i]) << IXGBE_RTRPT4C_BWG_SHIFT;
 
-		if (p->prio_type == prio_link)
+		if (prio_type[i] == prio_link)
 			reg |= IXGBE_RTRPT4C_LSP;
 
 		IXGBE_WRITE_REG(hw, IXGBE_RTRPT4C(i), reg);
@@ -130,14 +132,19 @@ static s32 ixgbe_dcb_config_rx_arbiter_82599(struct ixgbe_hw *hw,
 /**
  * ixgbe_dcb_config_tx_desc_arbiter_82599 - Config Tx Desc. arbiter
  * @hw: pointer to hardware structure
- * @dcb_config: pointer to ixgbe_dcb_config structure
+ * @refill: refill credits index by traffic class
+ * @max: max credits index by traffic class
+ * @bwg_id: bandwidth grouping indexed by traffic class
+ * @prio_type: priority type indexed by traffic class
  *
  * Configure Tx Descriptor Arbiter and credits for each traffic class.
  */
-static s32 ixgbe_dcb_config_tx_desc_arbiter_82599(struct ixgbe_hw *hw,
-                                           struct ixgbe_dcb_config *dcb_config)
+s32 ixgbe_dcb_config_tx_desc_arbiter_82599(struct ixgbe_hw *hw,
+					   u16 *refill,
+					   u16 *max,
+					   u8 *bwg_id,
+					   u8 *prio_type)
 {
-	struct tc_bw_alloc *p;
 	u32    reg, max_credits;
 	u8     i;
 
@@ -149,16 +156,15 @@ static s32 ixgbe_dcb_config_tx_desc_arbiter_82599(struct ixgbe_hw *hw,
 
 	/* Configure traffic class credits and priority */
 	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
-		p = &dcb_config->tc_config[i].path[DCB_TX_CONFIG];
-		max_credits = dcb_config->tc_config[i].desc_credits_max;
+		max_credits = max[i];
 		reg = max_credits << IXGBE_RTTDT2C_MCL_SHIFT;
-		reg |= p->data_credits_refill;
-		reg |= (u32)(p->bwg_id) << IXGBE_RTTDT2C_BWG_SHIFT;
+		reg |= refill[i];
+		reg |= (u32)(bwg_id[i]) << IXGBE_RTTDT2C_BWG_SHIFT;
 
-		if (p->prio_type == prio_group)
+		if (prio_type[i] == prio_group)
 			reg |= IXGBE_RTTDT2C_GSP;
 
-		if (p->prio_type == prio_link)
+		if (prio_type[i] == prio_link)
 			reg |= IXGBE_RTTDT2C_LSP;
 
 		IXGBE_WRITE_REG(hw, IXGBE_RTTDT2C(i), reg);
@@ -177,14 +183,19 @@ static s32 ixgbe_dcb_config_tx_desc_arbiter_82599(struct ixgbe_hw *hw,
 /**
  * ixgbe_dcb_config_tx_data_arbiter_82599 - Config Tx Data arbiter
  * @hw: pointer to hardware structure
- * @dcb_config: pointer to ixgbe_dcb_config structure
+ * @refill: refill credits index by traffic class
+ * @max: max credits index by traffic class
+ * @bwg_id: bandwidth grouping indexed by traffic class
+ * @prio_type: priority type indexed by traffic class
  *
  * Configure Tx Packet Arbiter and credits for each traffic class.
  */
-static s32 ixgbe_dcb_config_tx_data_arbiter_82599(struct ixgbe_hw *hw,
-                                           struct ixgbe_dcb_config *dcb_config)
+s32 ixgbe_dcb_config_tx_data_arbiter_82599(struct ixgbe_hw *hw,
+					   u16 *refill,
+					   u16 *max,
+					   u8 *bwg_id,
+					   u8 *prio_type)
 {
-	struct tc_bw_alloc *p;
 	u32 reg;
 	u8 i;
 
@@ -205,15 +216,14 @@ static s32 ixgbe_dcb_config_tx_data_arbiter_82599(struct ixgbe_hw *hw,
 
 	/* Configure traffic class credits and priority */
 	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
-		p = &dcb_config->tc_config[i].path[DCB_TX_CONFIG];
-		reg = p->data_credits_refill;
-		reg |= (u32)(p->data_credits_max) << IXGBE_RTTPT2C_MCL_SHIFT;
-		reg |= (u32)(p->bwg_id) << IXGBE_RTTPT2C_BWG_SHIFT;
+		reg = refill[i];
+		reg |= (u32)(max[i]) << IXGBE_RTTPT2C_MCL_SHIFT;
+		reg |= (u32)(bwg_id[i]) << IXGBE_RTTPT2C_BWG_SHIFT;
 
-		if (p->prio_type == prio_group)
+		if (prio_type[i] == prio_group)
 			reg |= IXGBE_RTTPT2C_GSP;
 
-		if (p->prio_type == prio_link)
+		if (prio_type[i] == prio_link)
 			reg |= IXGBE_RTTPT2C_LSP;
 
 		IXGBE_WRITE_REG(hw, IXGBE_RTTPT2C(i), reg);
@@ -233,17 +243,16 @@ static s32 ixgbe_dcb_config_tx_data_arbiter_82599(struct ixgbe_hw *hw,
 /**
  * ixgbe_dcb_config_pfc_82599 - Configure priority flow control
  * @hw: pointer to hardware structure
- * @dcb_config: pointer to ixgbe_dcb_config structure
+ * @pfc_en: enabled pfc bitmask
  *
  * Configure Priority Flow Control (PFC) for each traffic class.
  */
-s32 ixgbe_dcb_config_pfc_82599(struct ixgbe_hw *hw,
-                               struct ixgbe_dcb_config *dcb_config)
+s32 ixgbe_dcb_config_pfc_82599(struct ixgbe_hw *hw, u8 pfc_en)
 {
 	u32 i, reg, rx_pba_size;
 
 	/* If PFC is disabled globally then fall back to LFC. */
-	if (!dcb_config->pfc_mode_enable) {
+	if (!pfc_en) {
 		for (i = 0; i < MAX_TRAFFIC_CLASS; i++)
 			hw->mac.ops.fc_enable(hw, i);
 		goto out;
@@ -251,19 +260,18 @@ s32 ixgbe_dcb_config_pfc_82599(struct ixgbe_hw *hw,
 
 	/* Configure PFC Tx thresholds per TC */
 	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
+		int enabled = pfc_en & (1 << i);
 		rx_pba_size = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i));
 		rx_pba_size >>= IXGBE_RXPBSIZE_SHIFT;
 
 		reg = (rx_pba_size - hw->fc.low_water) << 10;
 
-		if (dcb_config->tc_config[i].dcb_pfc == pfc_enabled_full ||
-		    dcb_config->tc_config[i].dcb_pfc == pfc_enabled_tx)
+		if (enabled)
 			reg |= IXGBE_FCRTL_XONE;
 		IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), reg);
 
 		reg = (rx_pba_size - hw->fc.high_water) << 10;
-		if (dcb_config->tc_config[i].dcb_pfc == pfc_enabled_full ||
-		    dcb_config->tc_config[i].dcb_pfc == pfc_enabled_tx)
+		if (enabled)
 			reg |= IXGBE_FCRTH_FCEN;
 		IXGBE_WRITE_REG(hw, IXGBE_FCRTH_82599(i), reg);
 	}
@@ -349,7 +357,6 @@ static s32 ixgbe_dcb_config_tc_stats_82599(struct ixgbe_hw *hw)
 /**
  * ixgbe_dcb_config_82599 - Configure general DCB parameters
  * @hw: pointer to hardware structure
- * @dcb_config: pointer to ixgbe_dcb_config structure
  *
  * Configure general DCB parameters.
  */
@@ -406,19 +413,27 @@ static s32 ixgbe_dcb_config_82599(struct ixgbe_hw *hw)
 /**
  * ixgbe_dcb_hw_config_82599 - Configure and enable DCB
  * @hw: pointer to hardware structure
- * @dcb_config: pointer to ixgbe_dcb_config structure
+ * @rx_pba: method to distribute packet buffer
+ * @refill: refill credits index by traffic class
+ * @max: max credits index by traffic class
+ * @bwg_id: bandwidth grouping indexed by traffic class
+ * @prio_type: priority type indexed by traffic class
+ * @pfc_en: enabled pfc bitmask
  *
  * Configure dcb settings and enable dcb mode.
  */
 s32 ixgbe_dcb_hw_config_82599(struct ixgbe_hw *hw,
-                              struct ixgbe_dcb_config *dcb_config)
+			      u8 rx_pba, u8 pfc_en, u16 *refill,
+			      u16 *max, u8 *bwg_id, u8 *prio_type)
 {
-	ixgbe_dcb_config_packet_buffers_82599(hw, dcb_config);
+	ixgbe_dcb_config_packet_buffers_82599(hw, rx_pba);
 	ixgbe_dcb_config_82599(hw);
-	ixgbe_dcb_config_rx_arbiter_82599(hw, dcb_config);
-	ixgbe_dcb_config_tx_desc_arbiter_82599(hw, dcb_config);
-	ixgbe_dcb_config_tx_data_arbiter_82599(hw, dcb_config);
-	ixgbe_dcb_config_pfc_82599(hw, dcb_config);
+	ixgbe_dcb_config_rx_arbiter_82599(hw, refill, max, bwg_id, prio_type);
+	ixgbe_dcb_config_tx_desc_arbiter_82599(hw, refill, max,
+					       bwg_id, prio_type);
+	ixgbe_dcb_config_tx_data_arbiter_82599(hw, refill, max,
+					       bwg_id, prio_type);
+	ixgbe_dcb_config_pfc_82599(hw, pfc_en);
 	ixgbe_dcb_config_tc_stats_82599(hw);
 
 	return 0;
diff --git a/drivers/net/ixgbe/ixgbe_dcb_82599.h b/drivers/net/ixgbe/ixgbe_dcb_82599.h
index 3841649..5b0ca85 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_82599.h
+++ b/drivers/net/ixgbe/ixgbe_dcb_82599.h
@@ -102,11 +102,29 @@
 /* DCB hardware-specific driver APIs */
 
 /* DCB PFC functions */
-s32 ixgbe_dcb_config_pfc_82599(struct ixgbe_hw *hw,
-                               struct ixgbe_dcb_config *dcb_config);
+s32 ixgbe_dcb_config_pfc_82599(struct ixgbe_hw *hw, u8 pfc_en);
 
 /* DCB hw initialization */
+s32 ixgbe_dcb_config_rx_arbiter_82599(struct ixgbe_hw *hw,
+					u16 *refill,
+					u16 *max,
+					u8 *bwg_id,
+					u8 *prio_type);
+
+s32 ixgbe_dcb_config_tx_desc_arbiter_82599(struct ixgbe_hw *hw,
+						u16 *refill,
+						u16 *max,
+						u8 *bwg_id,
+						u8 *prio_type);
+
+s32 ixgbe_dcb_config_tx_data_arbiter_82599(struct ixgbe_hw *hw,
+						u16 *refill,
+						u16 *max,
+						u8 *bwg_id,
+						u8 *prio_type);
+
 s32 ixgbe_dcb_hw_config_82599(struct ixgbe_hw *hw,
-                              struct ixgbe_dcb_config *config);
+			      u8 rx_pba, u8 pfc_en, u16 *refill,
+			      u16 *max, u8 *bwg_id, u8 *prio_type);
 
 #endif /* _DCB_82599_CONFIG_H */
diff --git a/drivers/net/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ixgbe/ixgbe_dcb_nl.c
index 4805835..6ab1f1a 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_nl.c
@@ -422,12 +422,13 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 		}
 		ret = DCB_HW_CHG_RST;
 	} else if (adapter->dcb_set_bitmap & BIT_PFC) {
+		u8 pfc_en;
+		ixgbe_dcb_unpack_pfc(&adapter->dcb_cfg, &pfc_en);
+
 		if (adapter->hw.mac.type == ixgbe_mac_82598EB)
-			ixgbe_dcb_config_pfc_82598(&adapter->hw,
-			                           &adapter->dcb_cfg);
+			ixgbe_dcb_config_pfc_82598(&adapter->hw, pfc_en);
 		else if (adapter->hw.mac.type == ixgbe_mac_82599EB)
-			ixgbe_dcb_config_pfc_82599(&adapter->hw,
-			                           &adapter->dcb_cfg);
+			ixgbe_dcb_config_pfc_82599(&adapter->hw, pfc_en);
 		ret = DCB_HW_CHG;
 	}
 	if (adapter->dcb_cfg.pfc_mode_enable)
-- 
1.7.4

[net-next-2.6 09/16] ixgbe: DCB, implement 802.1Qaz routines

[Jeff Kirsher]

From: John Fastabend <john.r.fastabend@intel.com>

Implements 802.1Qaz support for ixgbe driver. Additionally,
this adds IEEE_8021QAZ_TSA_{} defines to dcbnl.h this is to
avoid having to use cryptic numeric codes for the TSA type.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Tested-by: Ross Brattain <ross.b.brattain@intel.com>
---
 drivers/net/ixgbe/ixgbe.h           |    4 ++
 drivers/net/ixgbe/ixgbe_dcb.c       |  102 +++++++++++++++++++++++++++++++++++
 drivers/net/ixgbe/ixgbe_dcb.h       |    4 ++
 drivers/net/ixgbe/ixgbe_dcb_82598.c |    2 +-
 drivers/net/ixgbe/ixgbe_dcb_nl.c    |   91 +++++++++++++++++++++++++++++++
 include/linux/dcbnl.h               |    5 ++
 6 files changed, 207 insertions(+), 1 deletions(-)

diff --git a/drivers/net/ixgbe/ixgbe.h b/drivers/net/ixgbe/ixgbe.h
index 3b8c924..d04afde 100644
--- a/drivers/net/ixgbe/ixgbe.h
+++ b/drivers/net/ixgbe/ixgbe.h
@@ -334,6 +334,10 @@ struct ixgbe_adapter {
 	u16 bd_number;
 	struct work_struct reset_task;
 	struct ixgbe_q_vector *q_vector[MAX_MSIX_Q_VECTORS];
+
+	/* DCB parameters */
+	struct ieee_pfc *ixgbe_ieee_pfc;
+	struct ieee_ets *ixgbe_ieee_ets;
 	struct ixgbe_dcb_config dcb_cfg;
 	struct ixgbe_dcb_config temp_dcb_cfg;
 	u8 dcb_set_bitmap;
diff --git a/drivers/net/ixgbe/ixgbe_dcb.c b/drivers/net/ixgbe/ixgbe_dcb.c
index d9bb670..0d7830f 100644
--- a/drivers/net/ixgbe/ixgbe_dcb.c
+++ b/drivers/net/ixgbe/ixgbe_dcb.c
@@ -34,6 +34,41 @@
 #include "ixgbe_dcb_82599.h"
 
 /**
+ * ixgbe_ieee_credits - This calculates the ieee traffic class
+ * credits from the configured bandwidth percentages. Credits
+ * are the smallest unit programable into the underlying
+ * hardware. The IEEE 802.1Qaz specification do not use bandwidth
+ * groups so this is much simplified from the CEE case.
+ */
+s32 ixgbe_ieee_credits(__u8 *bw, __u16 *refill, __u16 *max, int max_frame)
+{
+	int min_percent = 100;
+	int min_credit, multiplier;
+	int i;
+
+	min_credit = ((max_frame / 2) + DCB_CREDIT_QUANTUM - 1) /
+			DCB_CREDIT_QUANTUM;
+
+	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
+		if (bw[i] < min_percent && bw[i])
+			min_percent = bw[i];
+	}
+
+	multiplier = (min_credit / min_percent) + 1;
+
+	/* Find out the hw credits for each TC */
+	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
+		int val = min(bw[i] * multiplier, MAX_CREDIT_REFILL);
+		if (val < min_credit)
+			val = min_credit;
+		refill[i] = val;
+
+		max[i] = (bw[i] * MAX_CREDIT)/100;
+	}
+	return 0;
+}
+
+/**
  * ixgbe_dcb_calculate_tc_credits - Calculates traffic class credits
  * @ixgbe_dcb_config: Struct containing DCB settings.
  * @direction: Configuring either Tx or Rx.
@@ -236,3 +271,70 @@ s32 ixgbe_dcb_hw_config(struct ixgbe_hw *hw,
 	return ret;
 }
 
+/* Helper routines to abstract HW specifics from DCB netlink ops */
+s32 ixgbe_dcb_hw_pfc_config(struct ixgbe_hw *hw, u8 pfc_en)
+{
+	int ret = -EINVAL;
+
+	switch (hw->mac.type) {
+	case ixgbe_mac_82598EB:
+		ret = ixgbe_dcb_config_pfc_82598(hw, pfc_en);
+		break;
+	case ixgbe_mac_82599EB:
+	case ixgbe_mac_X540:
+		ret = ixgbe_dcb_config_pfc_82599(hw, pfc_en);
+		break;
+	default:
+		break;
+	}
+	return ret;
+}
+
+s32 ixgbe_dcb_hw_ets_config(struct ixgbe_hw *hw,
+			    u16 *refill, u16 *max, u8 *bwg_id, u8 *tsa)
+{
+	int i;
+	u8 prio_type[IEEE_8021QAZ_MAX_TCS];
+
+	/* Map TSA onto CEE prio type */
+	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+		switch (tsa[i]) {
+		case IEEE_8021QAZ_TSA_STRICT:
+			prio_type[i] = 2;
+			break;
+		case IEEE_8021QAZ_TSA_ETS:
+			prio_type[i] = 0;
+			break;
+		default:
+			/* Hardware only supports priority strict or
+			 * ETS transmission selection algorithms if
+			 * we receive some other value from dcbnl
+			 * throw an error
+			 */
+			return -EINVAL;
+		}
+	}
+
+	switch (hw->mac.type) {
+	case ixgbe_mac_82598EB:
+		ixgbe_dcb_config_rx_arbiter_82598(hw, refill, max,
+							prio_type);
+		ixgbe_dcb_config_tx_desc_arbiter_82598(hw, refill, max,
+							bwg_id, prio_type);
+		ixgbe_dcb_config_tx_data_arbiter_82598(hw, refill, max,
+							bwg_id, prio_type);
+		break;
+	case ixgbe_mac_82599EB:
+	case ixgbe_mac_X540:
+		ixgbe_dcb_config_rx_arbiter_82599(hw, refill, max,
+						  bwg_id, prio_type);
+		ixgbe_dcb_config_tx_desc_arbiter_82599(hw, refill, max,
+						       bwg_id, prio_type);
+		ixgbe_dcb_config_tx_data_arbiter_82599(hw, refill, max,
+						       bwg_id, prio_type);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
diff --git a/drivers/net/ixgbe/ixgbe_dcb.h b/drivers/net/ixgbe/ixgbe_dcb.h
index aa6cb5f..4e4a641 100644
--- a/drivers/net/ixgbe/ixgbe_dcb.h
+++ b/drivers/net/ixgbe/ixgbe_dcb.h
@@ -150,10 +150,14 @@ struct ixgbe_dcb_config {
 void ixgbe_dcb_unpack_pfc(struct ixgbe_dcb_config *cfg, u8 *pfc_en);
 
 /* DCB credits calculation */
+s32 ixgbe_ieee_credits(__u8 *bw, __u16 *refill, __u16 *max, int max_frame);
 s32 ixgbe_dcb_calculate_tc_credits(struct ixgbe_hw *,
 				   struct ixgbe_dcb_config *, int, u8);
 
 /* DCB hw initialization */
+s32 ixgbe_dcb_hw_ets_config(struct ixgbe_hw *hw,
+			    u16 *refill, u16 *max, u8 *bwg_id, u8 *prio_type);
+s32 ixgbe_dcb_hw_pfc_config(struct ixgbe_hw *hw, u8 pfc_en);
 s32 ixgbe_dcb_hw_config(struct ixgbe_hw *, struct ixgbe_dcb_config *);
 
 /* DCB definitions for credit calculation */
diff --git a/drivers/net/ixgbe/ixgbe_dcb_82598.c b/drivers/net/ixgbe/ixgbe_dcb_82598.c
index d128806..2965edc 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_82598.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_82598.c
@@ -291,7 +291,7 @@ out:
  * Configure queue statistics registers, all queues belonging to same traffic
  * class uses a single set of queue statistics counters.
  */
-static s32 ixgbe_dcb_config_tc_stats_82598(struct ixgbe_hw *hw)
+s32 ixgbe_dcb_config_tc_stats_82598(struct ixgbe_hw *hw)
 {
 	u32 reg = 0;
 	u8  i   = 0;
diff --git a/drivers/net/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ixgbe/ixgbe_dcb_nl.c
index 6ab1f1a..e75a3c9 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_nl.c
@@ -606,7 +606,98 @@ static u8 ixgbe_dcbnl_setapp(struct net_device *netdev,
 	return rval;
 }
 
+static int ixgbe_dcbnl_ieee_getets(struct net_device *dev,
+				   struct ieee_ets *ets)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ieee_ets *my_ets = adapter->ixgbe_ieee_ets;
+
+	/* No IEEE PFC settings available */
+	if (!my_ets)
+		return -EINVAL;
+
+	ets->ets_cap = MAX_TRAFFIC_CLASS;
+	ets->cbs = my_ets->cbs;
+	memcpy(ets->tc_tx_bw, my_ets->tc_tx_bw, sizeof(ets->tc_tx_bw));
+	memcpy(ets->tc_rx_bw, my_ets->tc_rx_bw, sizeof(ets->tc_rx_bw));
+	memcpy(ets->tc_tsa, my_ets->tc_tsa, sizeof(ets->tc_tsa));
+	memcpy(ets->prio_tc, my_ets->prio_tc, sizeof(ets->prio_tc));
+	return 0;
+}
+
+static int ixgbe_dcbnl_ieee_setets(struct net_device *dev,
+				   struct ieee_ets *ets)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	__u16 refill[IEEE_8021QAZ_MAX_TCS], max[IEEE_8021QAZ_MAX_TCS];
+	int max_frame = dev->mtu + ETH_HLEN + ETH_FCS_LEN;
+	int err;
+	/* naively give each TC a bwg to map onto CEE hardware */
+	__u8 bwg_id[IEEE_8021QAZ_MAX_TCS] = {0, 1, 2, 3, 4, 5, 6, 7};
+
+	if (!adapter->ixgbe_ieee_ets) {
+		adapter->ixgbe_ieee_ets = kmalloc(sizeof(struct ieee_ets),
+						  GFP_KERNEL);
+		if (!adapter->ixgbe_ieee_ets)
+			return -ENOMEM;
+	}
+
+
+	memcpy(adapter->ixgbe_ieee_ets, ets, sizeof(*adapter->ixgbe_ieee_ets));
+
+	ixgbe_ieee_credits(ets->tc_tx_bw, refill, max, max_frame);
+	err = ixgbe_dcb_hw_ets_config(&adapter->hw, refill, max,
+				      bwg_id, ets->tc_tsa);
+	return err;
+}
+
+static int ixgbe_dcbnl_ieee_getpfc(struct net_device *dev,
+				   struct ieee_pfc *pfc)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	struct ieee_pfc *my_pfc = adapter->ixgbe_ieee_pfc;
+	int i;
+
+	/* No IEEE PFC settings available */
+	if (!my_pfc)
+		return -EINVAL;
+
+	pfc->pfc_cap = MAX_TRAFFIC_CLASS;
+	pfc->pfc_en = my_pfc->pfc_en;
+	pfc->mbc = my_pfc->mbc;
+	pfc->delay = my_pfc->delay;
+
+	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
+		pfc->requests[i] = adapter->stats.pxoffrxc[i];
+		pfc->indications[i] = adapter->stats.pxofftxc[i];
+	}
+
+	return 0;
+}
+
+static int ixgbe_dcbnl_ieee_setpfc(struct net_device *dev,
+				   struct ieee_pfc *pfc)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+	int err;
+
+	if (!adapter->ixgbe_ieee_pfc) {
+		adapter->ixgbe_ieee_pfc = kmalloc(sizeof(struct ieee_pfc),
+						  GFP_KERNEL);
+		if (!adapter->ixgbe_ieee_pfc)
+			return -ENOMEM;
+	}
+
+	memcpy(adapter->ixgbe_ieee_pfc, pfc, sizeof(*adapter->ixgbe_ieee_pfc));
+	err = ixgbe_dcb_hw_pfc_config(&adapter->hw, pfc->pfc_en);
+	return err;
+}
+
 const struct dcbnl_rtnl_ops dcbnl_ops = {
+	.ieee_getets	= ixgbe_dcbnl_ieee_getets,
+	.ieee_setets	= ixgbe_dcbnl_ieee_setets,
+	.ieee_getpfc	= ixgbe_dcbnl_ieee_getpfc,
+	.ieee_setpfc	= ixgbe_dcbnl_ieee_setpfc,
 	.getstate	= ixgbe_dcbnl_get_state,
 	.setstate	= ixgbe_dcbnl_set_state,
 	.getpermhwaddr	= ixgbe_dcbnl_get_perm_hw_addr,
diff --git a/include/linux/dcbnl.h b/include/linux/dcbnl.h
index 68cd248..cd8d518 100644
--- a/include/linux/dcbnl.h
+++ b/include/linux/dcbnl.h
@@ -25,6 +25,11 @@
 /* IEEE 802.1Qaz std supported values */
 #define IEEE_8021QAZ_MAX_TCS	8
 
+#define IEEE_8021QAZ_TSA_STRICT		0
+#define IEEE_8021QAZ_TSA_CB_SHABER	1
+#define IEEE_8021QAZ_TSA_ETS		2
+#define IEEE_8021QAZ_TSA_VENDOR		255
+
 /* This structure contains the IEEE 802.1Qaz ETS managed object
  *
  * @willing: willing bit in ETS configuratin TLV
-- 
1.7.4

[net-next-2.6 10/16] ixgbe: DCB, do not reset on CEE pg changes

[Jeff Kirsher]

From: John Fastabend <john.r.fastabend@intel.com>

The 82599 and 82598 devices do not require hardware resets to
configure CEE pg settings. This patch changes DCB configuration
to set the CEE pg values directly from the dcbnl ops routine.

This reduces the number of resets seen on the wire and allows
LLDP to reach a steady state faster.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Tested-by: Ross Brattain <ross.b.brattain@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ixgbe/ixgbe_dcb.h    |    4 +++
 drivers/net/ixgbe/ixgbe_dcb_nl.c |   48 +++++++++++++++++++++++++++----------
 2 files changed, 39 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ixgbe/ixgbe_dcb.h b/drivers/net/ixgbe/ixgbe_dcb.h
index 4e4a641..e593511 100644
--- a/drivers/net/ixgbe/ixgbe_dcb.h
+++ b/drivers/net/ixgbe/ixgbe_dcb.h
@@ -148,6 +148,10 @@ struct ixgbe_dcb_config {
 
 /* DCB driver APIs */
 void ixgbe_dcb_unpack_pfc(struct ixgbe_dcb_config *cfg, u8 *pfc_en);
+void ixgbe_dcb_unpack_refill(struct ixgbe_dcb_config *, int, u16 *);
+void ixgbe_dcb_unpack_max(struct ixgbe_dcb_config *, u16 *);
+void ixgbe_dcb_unpack_bwgid(struct ixgbe_dcb_config *, int, u8 *);
+void ixgbe_dcb_unpack_prio(struct ixgbe_dcb_config *, int, u8 *);
 
 /* DCB credits calculation */
 s32 ixgbe_ieee_credits(__u8 *bw, __u16 *refill, __u16 *max, int max_frame);
diff --git a/drivers/net/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ixgbe/ixgbe_dcb_nl.c
index e75a3c9..b3a8d24 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_nl.c
@@ -225,10 +225,8 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc,
 	    (adapter->temp_dcb_cfg.tc_config[tc].path[0].bwg_percent !=
 	     adapter->dcb_cfg.tc_config[tc].path[0].bwg_percent) ||
 	    (adapter->temp_dcb_cfg.tc_config[tc].path[0].up_to_tc_bitmap !=
-	     adapter->dcb_cfg.tc_config[tc].path[0].up_to_tc_bitmap)) {
+	     adapter->dcb_cfg.tc_config[tc].path[0].up_to_tc_bitmap))
 		adapter->dcb_set_bitmap |= BIT_PG_TX;
-		adapter->dcb_set_bitmap |= BIT_RESETLINK;
-	}
 }
 
 static void ixgbe_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id,
@@ -239,10 +237,8 @@ static void ixgbe_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id,
 	adapter->temp_dcb_cfg.bw_percentage[0][bwg_id] = bw_pct;
 
 	if (adapter->temp_dcb_cfg.bw_percentage[0][bwg_id] !=
-	    adapter->dcb_cfg.bw_percentage[0][bwg_id]) {
+	    adapter->dcb_cfg.bw_percentage[0][bwg_id])
 		adapter->dcb_set_bitmap |= BIT_PG_TX;
-		adapter->dcb_set_bitmap |= BIT_RESETLINK;
-	}
 }
 
 static void ixgbe_dcbnl_set_pg_tc_cfg_rx(struct net_device *netdev, int tc,
@@ -269,10 +265,8 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_rx(struct net_device *netdev, int tc,
 	    (adapter->temp_dcb_cfg.tc_config[tc].path[1].bwg_percent !=
 	     adapter->dcb_cfg.tc_config[tc].path[1].bwg_percent) ||
 	    (adapter->temp_dcb_cfg.tc_config[tc].path[1].up_to_tc_bitmap !=
-	     adapter->dcb_cfg.tc_config[tc].path[1].up_to_tc_bitmap)) {
+	     adapter->dcb_cfg.tc_config[tc].path[1].up_to_tc_bitmap))
 		adapter->dcb_set_bitmap |= BIT_PG_RX;
-		adapter->dcb_set_bitmap |= BIT_RESETLINK;
-	}
 }
 
 static void ixgbe_dcbnl_set_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id,
@@ -283,10 +277,8 @@ static void ixgbe_dcbnl_set_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id,
 	adapter->temp_dcb_cfg.bw_percentage[1][bwg_id] = bw_pct;
 
 	if (adapter->temp_dcb_cfg.bw_percentage[1][bwg_id] !=
-	    adapter->dcb_cfg.bw_percentage[1][bwg_id]) {
+	    adapter->dcb_cfg.bw_percentage[1][bwg_id])
 		adapter->dcb_set_bitmap |= BIT_PG_RX;
-		adapter->dcb_set_bitmap |= BIT_RESETLINK;
-	}
 }
 
 static void ixgbe_dcbnl_get_pg_tc_cfg_tx(struct net_device *netdev, int tc,
@@ -421,7 +413,9 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 				ixgbe_up(adapter);
 		}
 		ret = DCB_HW_CHG_RST;
-	} else if (adapter->dcb_set_bitmap & BIT_PFC) {
+	}
+
+	if (adapter->dcb_set_bitmap & BIT_PFC) {
 		u8 pfc_en;
 		ixgbe_dcb_unpack_pfc(&adapter->dcb_cfg, &pfc_en);
 
@@ -431,6 +425,34 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 			ixgbe_dcb_config_pfc_82599(&adapter->hw, pfc_en);
 		ret = DCB_HW_CHG;
 	}
+
+	if (adapter->dcb_set_bitmap & (BIT_PG_TX|BIT_PG_RX)) {
+		u16 refill[MAX_TRAFFIC_CLASS], max[MAX_TRAFFIC_CLASS];
+		u8 bwg_id[MAX_TRAFFIC_CLASS], prio_type[MAX_TRAFFIC_CLASS];
+		int max_frame = adapter->netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
+
+#ifdef CONFIG_FCOE
+		if (adapter->netdev->features & NETIF_F_FCOE_MTU)
+			max_frame = max(max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE);
+#endif
+
+		ixgbe_dcb_calculate_tc_credits(&adapter->hw, &adapter->dcb_cfg,
+					       max_frame, DCB_TX_CONFIG);
+		ixgbe_dcb_calculate_tc_credits(&adapter->hw, &adapter->dcb_cfg,
+					       max_frame, DCB_RX_CONFIG);
+
+		ixgbe_dcb_unpack_refill(&adapter->dcb_cfg,
+					DCB_TX_CONFIG, refill);
+		ixgbe_dcb_unpack_max(&adapter->dcb_cfg, max);
+		ixgbe_dcb_unpack_bwgid(&adapter->dcb_cfg,
+				       DCB_TX_CONFIG, bwg_id);
+		ixgbe_dcb_unpack_prio(&adapter->dcb_cfg,
+				      DCB_TX_CONFIG, prio_type);
+
+		ixgbe_dcb_hw_ets_config(&adapter->hw, refill, max,
+					bwg_id, prio_type);
+	}
+
 	if (adapter->dcb_cfg.pfc_mode_enable)
 		adapter->hw.fc.current_mode = ixgbe_fc_pfc;
 
-- 
1.7.4

[net-next-2.6 11/16] ixgbe: DCB, remove RESET bit it is no longer needed

[Jeff Kirsher]

From: John Fastabend <john.r.fastabend@intel.com>

This removes the RESET bit previously used to force a device
reset when DCB bandwidth configurations were changed. This can
now be done dynamically without a reset so the bit is no longer
needed. The only remaining operations that force a device reset
are DCB enable/disable and FCoE application priority changes.
DCB enable/disable is a hardware requirement.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Tested-by: Ross Brattain <ross.b.brattain@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ixgbe/ixgbe_dcb_nl.c |   37 ++++++++++++-------------------------
 1 files changed, 12 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ixgbe/ixgbe_dcb_nl.c
index b3a8d24..c94adec 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_nl.c
@@ -37,7 +37,6 @@
 #define BIT_PG_RX	0x04
 #define BIT_PG_TX	0x08
 #define BIT_APP_UPCHG	0x10
-#define BIT_RESETLINK   0x40
 #define BIT_LINKSPEED   0x80
 
 /* Responses for the DCB_C_SET_ALL command */
@@ -345,7 +344,6 @@ static void ixgbe_dcbnl_get_pfc_cfg(struct net_device *netdev, int priority,
 static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
-	bool do_reset;
 	int ret;
 
 	if (!adapter->dcb_set_bitmap)
@@ -358,23 +356,17 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 		return DCB_NO_HW_CHG;
 
 	/*
-	 * Only take down the adapter if the configuration change
-	 * requires a reset.
+	 * Only take down the adapter if an app change occured. FCoE
+	 * may shuffle tx rings in this case and this can not be done
+	 * without a reset currently.
 	 */
-	do_reset = adapter->dcb_set_bitmap & (BIT_RESETLINK | BIT_APP_UPCHG);
-
-	if (do_reset) {
+	if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) {
 		while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state))
 			msleep(1);
 
-		if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) {
-			if (netif_running(netdev))
-				netdev->netdev_ops->ndo_stop(netdev);
-			ixgbe_clear_interrupt_scheme(adapter);
-		} else {
-			if (netif_running(netdev))
-				ixgbe_down(adapter);
-		}
+		if (netif_running(netdev))
+			netdev->netdev_ops->ndo_stop(netdev);
+		ixgbe_clear_interrupt_scheme(adapter);
 	}
 
 	if (adapter->dcb_cfg.pfc_mode_enable) {
@@ -403,15 +395,10 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 		}
 	}
 
-	if (do_reset) {
-		if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) {
-			ixgbe_init_interrupt_scheme(adapter);
-			if (netif_running(netdev))
-				netdev->netdev_ops->ndo_open(netdev);
-		} else {
-			if (netif_running(netdev))
-				ixgbe_up(adapter);
-		}
+	if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) {
+		ixgbe_init_interrupt_scheme(adapter);
+		if (netif_running(netdev))
+			netdev->netdev_ops->ndo_open(netdev);
 		ret = DCB_HW_CHG_RST;
 	}
 
@@ -456,7 +443,7 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 	if (adapter->dcb_cfg.pfc_mode_enable)
 		adapter->hw.fc.current_mode = ixgbe_fc_pfc;
 
-	if (do_reset)
+	if (adapter->dcb_set_bitmap & BIT_APP_UPCHG)
 		clear_bit(__IXGBE_RESETTING, &adapter->state);
 	adapter->dcb_set_bitmap = 0x00;
 	return ret;
-- 
1.7.4

[net-next-2.6 12/16] ixgbe: dcb, use hardware independent routines

[Jeff Kirsher]

From: John Fastabend <john.r.fastabend@intel.com>

This consolidates hardware specifics to ixgbe_dcb.c this simplifies
code that was previously branching based on hardware type.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Tested-by: Ross Brattain <ross.b.brattain@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ixgbe/ixgbe_dcb_nl.c |    6 +-----
 1 files changed, 1 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ixgbe/ixgbe_dcb_nl.c
index c94adec..a977df3 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_nl.c
@@ -405,11 +405,7 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 	if (adapter->dcb_set_bitmap & BIT_PFC) {
 		u8 pfc_en;
 		ixgbe_dcb_unpack_pfc(&adapter->dcb_cfg, &pfc_en);
-
-		if (adapter->hw.mac.type == ixgbe_mac_82598EB)
-			ixgbe_dcb_config_pfc_82598(&adapter->hw, pfc_en);
-		else if (adapter->hw.mac.type == ixgbe_mac_82599EB)
-			ixgbe_dcb_config_pfc_82599(&adapter->hw, pfc_en);
+		ixgbe_dcb_hw_pfc_config(&adapter->hw, pfc_en);
 		ret = DCB_HW_CHG;
 	}
 
-- 
1.7.4

[net-next-2.6 13/16] ixgbe: fix namespace issue with ixgbe_dcb_txq_to_tc

[Jeff Kirsher]

From: Don Skidmore <donald.c.skidmore@intel.com>

We didn't need the prototype and it was causing namespace complaints so
I made it static.

Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com>
Tested-by: Stephen Ko <stephen.s.ko@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ixgbe/ixgbe.h      |    1 -
 drivers/net/ixgbe/ixgbe_main.c |    2 +-
 2 files changed, 1 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ixgbe/ixgbe.h b/drivers/net/ixgbe/ixgbe.h
index d04afde..12769b5 100644
--- a/drivers/net/ixgbe/ixgbe.h
+++ b/drivers/net/ixgbe/ixgbe.h
@@ -525,7 +525,6 @@ extern void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *,
 extern void ixgbe_alloc_rx_buffers(struct ixgbe_ring *, u16);
 extern void ixgbe_write_eitr(struct ixgbe_q_vector *);
 extern int ethtool_ioctl(struct ifreq *ifr);
-extern u8 ixgbe_dcb_txq_to_tc(struct ixgbe_adapter *adapter, u8 index);
 extern s32 ixgbe_reinit_fdir_tables_82599(struct ixgbe_hw *hw);
 extern s32 ixgbe_init_fdir_signature_82599(struct ixgbe_hw *hw, u32 pballoc);
 extern s32 ixgbe_init_fdir_perfect_82599(struct ixgbe_hw *hw, u32 pballoc);
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index ef4a517..f5bdc0a 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -648,7 +648,7 @@ void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *tx_ring,
  *
  * Returns : a tc index for use in range 0-7, or 0-3
  */
-u8 ixgbe_dcb_txq_to_tc(struct ixgbe_adapter *adapter, u8 reg_idx)
+static u8 ixgbe_dcb_txq_to_tc(struct ixgbe_adapter *adapter, u8 reg_idx)
 {
 	int tc = -1;
 	int dcb_i = adapter->ring_feature[RING_F_DCB].indices;
-- 
1.7.4

[net-next-2.6 14/16] ixgbe: cleanup namespace complaint by removing little used function

[Jeff Kirsher]

From: Don Skidmore <donald.c.skidmore@intel.com>

We had a support function that just walked a few pointers to get
from the ixgbe_hw struct to the netdev pointer.  This was causing
a namespace warning so I removed it and just reference the pointers
directly.

Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com>
Tested-by: Stephen Ko <stephen.s.ko@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ixgbe/ixgbe_common.h |    4 ++--
 drivers/net/ixgbe/ixgbe_main.c   |   10 ----------
 2 files changed, 2 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ixgbe/ixgbe_common.h b/drivers/net/ixgbe/ixgbe_common.h
index 66ed045..90cceb4 100644
--- a/drivers/net/ixgbe/ixgbe_common.h
+++ b/drivers/net/ixgbe/ixgbe_common.h
@@ -29,6 +29,7 @@
 #define _IXGBE_COMMON_H_
 
 #include "ixgbe_type.h"
+#include "ixgbe.h"
 
 u32 ixgbe_get_pcie_msix_count_generic(struct ixgbe_hw *hw);
 s32 ixgbe_init_ops_generic(struct ixgbe_hw *hw);
@@ -110,9 +111,8 @@ void ixgbe_set_vlan_anti_spoofing(struct ixgbe_hw *hw, bool enable, int vf);
 
 #define IXGBE_WRITE_FLUSH(a) IXGBE_READ_REG(a, IXGBE_STATUS)
 
-extern struct net_device *ixgbe_get_hw_dev(struct ixgbe_hw *hw);
 #define hw_dbg(hw, format, arg...) \
-	netdev_dbg(ixgbe_get_hw_dev(hw), format, ##arg)
+	netdev_dbg(((struct ixgbe_adapter *)(hw->back))->netdev, format, ##arg)
 #define e_dev_info(format, arg...) \
 	dev_info(&adapter->pdev->dev, format, ## arg)
 #define e_dev_warn(format, arg...) \
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index f5bdc0a..2dab240 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -7699,16 +7699,6 @@ static int ixgbe_notify_dca(struct notifier_block *nb, unsigned long event,
 
 #endif /* CONFIG_IXGBE_DCA */
 
-/**
- * ixgbe_get_hw_dev return device
- * used by hardware layer to print debugging information
- **/
-struct net_device *ixgbe_get_hw_dev(struct ixgbe_hw *hw)
-{
-	struct ixgbe_adapter *adapter = hw->back;
-	return adapter->netdev;
-}
-
 module_exit(ixgbe_exit_module);
 
 /* ixgbe_main.c */
-- 
1.7.4

[net-next-2.6 15/16] ixgbe: cleanup ixgbe_init_mbx_params_pf namespace issue

[Jeff Kirsher]

From: Don Skidmore <donald.c.skidmore@intel.com>

The function ixgbe_init_mbx_params_pf isn't used unless CONFIG_PCI_IOV
is defined.  This is causing namespace warnings.  So I wrapped its
definition in CONFIG_PCI_IOV too.

Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com>
Tested-by: Stephen Ko <stephen.s.ko@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ixgbe/ixgbe_mbx.c |    2 ++
 drivers/net/ixgbe/ixgbe_mbx.h |    2 ++
 2 files changed, 4 insertions(+), 0 deletions(-)

diff --git a/drivers/net/ixgbe/ixgbe_mbx.c b/drivers/net/ixgbe/ixgbe_mbx.c
index ea82c5a..f215c4c 100644
--- a/drivers/net/ixgbe/ixgbe_mbx.c
+++ b/drivers/net/ixgbe/ixgbe_mbx.c
@@ -437,6 +437,7 @@ out_no_read:
 	return ret_val;
 }
 
+#ifdef CONFIG_PCI_IOV
 /**
  *  ixgbe_init_mbx_params_pf - set initial values for pf mailbox
  *  @hw: pointer to the HW structure
@@ -465,6 +466,7 @@ void ixgbe_init_mbx_params_pf(struct ixgbe_hw *hw)
 		break;
 	}
 }
+#endif /* CONFIG_PCI_IOV */
 
 struct ixgbe_mbx_operations mbx_ops_generic = {
 	.read                   = ixgbe_read_mbx_pf,
diff --git a/drivers/net/ixgbe/ixgbe_mbx.h b/drivers/net/ixgbe/ixgbe_mbx.h
index 3df9b15..ada0ce3 100644
--- a/drivers/net/ixgbe/ixgbe_mbx.h
+++ b/drivers/net/ixgbe/ixgbe_mbx.h
@@ -86,7 +86,9 @@ s32 ixgbe_write_mbx(struct ixgbe_hw *, u32 *, u16, u16);
 s32 ixgbe_check_for_msg(struct ixgbe_hw *, u16);
 s32 ixgbe_check_for_ack(struct ixgbe_hw *, u16);
 s32 ixgbe_check_for_rst(struct ixgbe_hw *, u16);
+#ifdef CONFIG_PCI_IOV
 void ixgbe_init_mbx_params_pf(struct ixgbe_hw *);
+#endif /* CONFIG_PCI_IOV */
 
 extern struct ixgbe_mbx_operations mbx_ops_generic;
 
-- 
1.7.4

[net-next-2.6 16/16] ixgbe: Adding 100MB FULL support in ethtool

[Jeff Kirsher]

From: Atita Shirwaikar <atita.shirwaikar@intel.com>

Current driver does not show 100MB support in ethtool.
Adding support for the same.

Signed-off-by: Atita Shirwaikar <atita.shirwaikar@intel.com>
Tested-by: Stephen Ko <stephen.s.ko@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ixgbe/ixgbe_ethtool.c |   34 ++++++++++++++++++++++++++++++++--
 drivers/net/ixgbe/ixgbe_main.c    |    5 ++++-
 2 files changed, 36 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ixgbe/ixgbe_ethtool.c b/drivers/net/ixgbe/ixgbe_ethtool.c
index 2002ea8..309272f 100644
--- a/drivers/net/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ixgbe/ixgbe_ethtool.c
@@ -152,7 +152,17 @@ static int ixgbe_get_settings(struct net_device *netdev,
 		ecmd->supported |= (SUPPORTED_1000baseT_Full |
 		                    SUPPORTED_Autoneg);
 
+		switch (hw->mac.type) {
+		case ixgbe_mac_X540:
+			ecmd->supported |= SUPPORTED_100baseT_Full;
+			break;
+		default:
+			break;
+		}
+
 		ecmd->advertising = ADVERTISED_Autoneg;
+		if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL)
+			ecmd->advertising |= ADVERTISED_100baseT_Full;
 		if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL)
 			ecmd->advertising |= ADVERTISED_10000baseT_Full;
 		if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL)
@@ -167,6 +177,15 @@ static int ixgbe_get_settings(struct net_device *netdev,
 			ecmd->advertising |= (ADVERTISED_10000baseT_Full |
 					      ADVERTISED_1000baseT_Full);
 
+		switch (hw->mac.type) {
+		case ixgbe_mac_X540:
+			if (!(ecmd->advertising & ADVERTISED_100baseT_Full))
+				ecmd->advertising |= (ADVERTISED_100baseT_Full);
+			break;
+		default:
+			break;
+		}
+
 		if (hw->phy.media_type == ixgbe_media_type_copper) {
 			ecmd->supported |= SUPPORTED_TP;
 			ecmd->advertising |= ADVERTISED_TP;
@@ -271,8 +290,19 @@ static int ixgbe_get_settings(struct net_device *netdev,
 
 	hw->mac.ops.check_link(hw, &link_speed, &link_up, false);
 	if (link_up) {
-		ecmd->speed = (link_speed == IXGBE_LINK_SPEED_10GB_FULL) ?
-		               SPEED_10000 : SPEED_1000;
+		switch (link_speed) {
+		case IXGBE_LINK_SPEED_10GB_FULL:
+			ecmd->speed = SPEED_10000;
+			break;
+		case IXGBE_LINK_SPEED_1GB_FULL:
+			ecmd->speed = SPEED_1000;
+			break;
+		case IXGBE_LINK_SPEED_100_FULL:
+			ecmd->speed = SPEED_100;
+			break;
+		default:
+			break;
+		}
 		ecmd->duplex = DUPLEX_FULL;
 	} else {
 		ecmd->speed = -1;
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index 2dab240..7947063 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -6094,7 +6094,10 @@ static void ixgbe_watchdog_task(struct work_struct *work)
 			       (link_speed == IXGBE_LINK_SPEED_10GB_FULL ?
 			       "10 Gbps" :
 			       (link_speed == IXGBE_LINK_SPEED_1GB_FULL ?
-			       "1 Gbps" : "unknown speed")),
+			       "1 Gbps" :
+			       (link_speed == IXGBE_LINK_SPEED_100_FULL ?
+			       "100 Mbps" :
+			       "unknown speed"))),
 			       ((flow_rx && flow_tx) ? "RX/TX" :
 			       (flow_rx ? "RX" :
 			       (flow_tx ? "TX" : "None"))));
-- 
1.7.4

Re: [net-next-2.6 00/16][pull request] Intel Wired LAN Driver Updates

[Jeff Kirsher]

On Tue, Feb 8, 2011 at 04:29, Jeff Kirsher <jeffrey.t.kirsher@intel.com> wrote:
> The following series contains e1000e cleanup patches, the addition of igb
> PF support for i350 devices and several ixgbe cleanup patches.
>
> The following are changes since commit 2360d2e8f01043632d6b651672bec66c49892f94:
>  enic: Update MAINTAINERS
>
> and are available in the git repository at:
>  master.kernel.org:/pub/scm/linux/kernel/git/jkirsher/net-next-2.6 master
>
> Atita Shirwaikar (1):
>  ixgbe: Adding 100MB FULL support in ethtool
>
> Bruce Allan (4):
>  e1000e: replace unbounded sprintf with snprintf
>  e1000e: use correct pointer when memcpy'ing a 2-dimensional array
>  e1000e: do not wakeup Tx queue until ready
>  e1000e: return appropriate errors for 'ethtool -r'
>
> Carolyn Wyborny (1):
>  igb: Enable PF side of SR-IOV support for i350 devices
>
> Don Skidmore (3):
>  ixgbe: fix namespace issue with ixgbe_dcb_txq_to_tc
>  ixgbe: cleanup namespace complaint by removing little used function
>  ixgbe: cleanup ixgbe_init_mbx_params_pf namespace issue
>
> John Fastabend (7):
>  ixgbe: DCB, only reprogram HW if the FCoE priority is changed
>  ixgbe: DCB, remove round robin mode on 82598 devices
>  ixgbe: DCB, abstract out dcb_config from DCB hardware configuration
>  ixgbe: DCB, implement 802.1Qaz routines
>  ixgbe: DCB, do not reset on CEE pg changes
>  ixgbe: DCB, remove RESET bit it is no longer needed
>  ixgbe: dcb, use hardware independent routines
>
>  drivers/net/e1000e/ethtool.c        |   13 ++-
>  drivers/net/e1000e/netdev.c         |   13 +-
>  drivers/net/igb/e1000_82575.c       |   10 ++-
>  drivers/net/igb/e1000_mbx.c         |   38 +++----
>  drivers/net/igb/igb_main.c          |    9 +-
>  drivers/net/ixgbe/ixgbe.h           |    5 +-
>  drivers/net/ixgbe/ixgbe_common.h    |    4 +-
>  drivers/net/ixgbe/ixgbe_dcb.c       |  176 +++++++++++++++++++++++++++++-
>  drivers/net/ixgbe/ixgbe_dcb.h       |   10 ++-
>  drivers/net/ixgbe/ixgbe_dcb_82598.c |   94 ++++++++--------
>  drivers/net/ixgbe/ixgbe_dcb_82598.h |   23 ++++-
>  drivers/net/ixgbe/ixgbe_dcb_82599.c |  115 +++++++++++--------
>  drivers/net/ixgbe/ixgbe_dcb_82599.h |   24 ++++-
>  drivers/net/ixgbe/ixgbe_dcb_nl.c    |  211 ++++++++++++++++++++++++++--------
>  drivers/net/ixgbe/ixgbe_ethtool.c   |   34 ++++++-
>  drivers/net/ixgbe/ixgbe_main.c      |   18 +--
>  drivers/net/ixgbe/ixgbe_mbx.c       |    2 +
>  drivers/net/ixgbe/ixgbe_mbx.h       |    2 +
>  include/linux/dcbnl.h               |    5 +
>  19 files changed, 601 insertions(+), 205 deletions(-)
>
> --

I will drop patch 3 (e1000e: do not wakeup Tx queue until ready) while
Bruce takes a second look at the patch.  I will be re-posting a pull
request once I have updated my net-next tree without that patch.

-- 
Cheers,
Jeff