Commit ac2eb56e authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue 



Jeff Kirsher says:

====================
100GbE Intel Wired LAN Driver Updates 2019-08-20

This series contains updates to ice driver only.

Brett fixes the detection of a hung transmit ring by checking the
software based tail (next_to_use) to determine if there is pending work.
Updates the driver to assume that using more than one receive queue per
receive ring container is a rare case, so use unlikely() in the case
were we actually need to divide our budget for multiple queues.  Fixed
an issue where the write back on ITR bit was not being set when
interrupts are disabled, which was causing only write backs when polling
only when a cache line is filled.  Cleans up unnecessary wait times
during VF bring up and reset paths.  Increased the mailbox size for
receive queues that are used to communicate with VFs to accommodate the
large number of VFs that the driver can support.

Akeem restructures the initialization flows for VFs, including how VFs
are configured and resources allocated to improve flows so that when we
clean up resources, we do not try to free resources that were never
allocated.  Organizes code to ensure that VF specific code is located in
the SR-IOV specific file.

Paul fixes an issue when setting the pause parameter which was
incorrectly blocking users from changing receive or transmit pause
settings.  Ensure register access for MSIX vector index is only done in
the PF space and not absolute device space.

Usha fixes a potential kernel hang in the DCB rebuild path when in CEE
mode, where the ETS recommended DCB configuration is not being set or
set correctly.

Mitch updates the driver to process all receive descriptors, regardless
of the size of the associated data.

Tony fixes and issue during the reset/rebuild path of a PF VSI where we
were assuming that the PF VSI was always to be enabled, which can
attempt to bring up a PF VSI on a downed interface which can lead to
various crashes.

Pawel fixes up variable definitions to match the type of data being
stored.

v2: Dropped patch 1 of the series to add ethtool support to query/add
    channels on a VSI, while we re-qork the functionality to match the
    ethtool expected behavior to report combined (Tx and Rx) numbers.
v3: Updated patch 4 to use kzalloc() and kfree() instead devm_kzalloc()
    and devm_kfree().
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents f588af84 be6f7ef6

drivers/net/ethernet/intel/ice/ice.h

+3 −11
Original line number Diff line number Diff line
@@ -69,7 +69,8 @@ extern const char ice_drv_ver[]; 
#define ICE_INT_NAME_STR_LEN	(IFNAMSIZ + 16)

#define ICE_ETHTOOL_FWVER_LEN	32

#define ICE_AQ_LEN		64

#define ICE_MBXQ_LEN		64

#define ICE_MBXSQ_LEN		64

#define ICE_MBXRQ_LEN		512

#define ICE_MIN_MSIX		2

#define ICE_NO_VSI		0xffff

#define ICE_MAX_TXQS		2048
@@ -86,16 +87,6 @@ extern const char ice_drv_ver[]; 
#define ICE_RES_MISC_VEC_ID	(ICE_RES_VALID_BIT - 1)

#define ICE_INVAL_Q_INDEX	0xffff

#define ICE_INVAL_VFID		256

#define ICE_MAX_VF_COUNT	256

#define ICE_MAX_QS_PER_VF		256

#define ICE_MIN_QS_PER_VF		1

#define ICE_DFLT_QS_PER_VF		4

#define ICE_NONQ_VECS_VF		1

#define ICE_MAX_SCATTER_QS_PER_VF	16

#define ICE_MAX_BASE_QS_PER_VF		16

#define ICE_MAX_INTR_PER_VF		65

#define ICE_MIN_INTR_PER_VF		(ICE_MIN_QS_PER_VF + 1)

#define ICE_DFLT_INTR_PER_VF		(ICE_DFLT_QS_PER_VF + 1)



#define ICE_MAX_RESET_WAIT		20
@@ -220,6 +211,7 @@ enum ice_state { 
	__ICE_CFG_BUSY,

	__ICE_SERVICE_SCHED,

	__ICE_SERVICE_DIS,

	__ICE_OICR_INTR_DIS,		/* Global OICR interrupt disabled */

	__ICE_STATE_NBITS		/* must be last */

};

drivers/net/ethernet/intel/ice/ice_dcb_lib.c

+88 −61
Original line number Diff line number Diff line
@@ -203,16 +203,87 @@ out: 
	return ret;

}



/**

 * ice_cfg_etsrec_defaults - Set default ETS recommended DCB config

 * @pi: port information structure

 */

static void ice_cfg_etsrec_defaults(struct ice_port_info *pi)

{

	struct ice_dcbx_cfg *dcbcfg = &pi->local_dcbx_cfg;

	u8 i;



	/* Ensure ETS recommended DCB configuration is not already set */

	if (dcbcfg->etsrec.maxtcs)

		return;



	/* In CEE mode, set the default to 1 TC */

	dcbcfg->etsrec.maxtcs = 1;

	for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) {

		dcbcfg->etsrec.tcbwtable[i] = i ? 0 : 100;

		dcbcfg->etsrec.tsatable[i] = i ? ICE_IEEE_TSA_STRICT :

						 ICE_IEEE_TSA_ETS;

	}

}



/**

 * ice_dcb_need_recfg - Check if DCB needs reconfig

 * @pf: board private structure

 * @old_cfg: current DCB config

 * @new_cfg: new DCB config

 */

static bool

ice_dcb_need_recfg(struct ice_pf *pf, struct ice_dcbx_cfg *old_cfg,

		   struct ice_dcbx_cfg *new_cfg)

{

	bool need_reconfig = false;



	/* Check if ETS configuration has changed */

	if (memcmp(&new_cfg->etscfg, &old_cfg->etscfg,

		   sizeof(new_cfg->etscfg))) {

		/* If Priority Table has changed reconfig is needed */

		if (memcmp(&new_cfg->etscfg.prio_table,

			   &old_cfg->etscfg.prio_table,

			   sizeof(new_cfg->etscfg.prio_table))) {

			need_reconfig = true;

			dev_dbg(&pf->pdev->dev, "ETS UP2TC changed.\n");

		}



		if (memcmp(&new_cfg->etscfg.tcbwtable,

			   &old_cfg->etscfg.tcbwtable,

			   sizeof(new_cfg->etscfg.tcbwtable)))

			dev_dbg(&pf->pdev->dev, "ETS TC BW Table changed.\n");



		if (memcmp(&new_cfg->etscfg.tsatable,

			   &old_cfg->etscfg.tsatable,

			   sizeof(new_cfg->etscfg.tsatable)))

			dev_dbg(&pf->pdev->dev, "ETS TSA Table changed.\n");

	}



	/* Check if PFC configuration has changed */

	if (memcmp(&new_cfg->pfc, &old_cfg->pfc, sizeof(new_cfg->pfc))) {

		need_reconfig = true;

		dev_dbg(&pf->pdev->dev, "PFC config change detected.\n");

	}



	/* Check if APP Table has changed */

	if (memcmp(&new_cfg->app, &old_cfg->app, sizeof(new_cfg->app))) {

		need_reconfig = true;

		dev_dbg(&pf->pdev->dev, "APP Table change detected.\n");

	}



	dev_dbg(&pf->pdev->dev, "dcb need_reconfig=%d\n", need_reconfig);

	return need_reconfig;

}



/**

 * ice_dcb_rebuild - rebuild DCB post reset

 * @pf: physical function instance

 */

void ice_dcb_rebuild(struct ice_pf *pf)

{

	struct ice_dcbx_cfg *local_dcbx_cfg, *desired_dcbx_cfg, *prev_cfg;

	struct ice_aqc_port_ets_elem buf = { 0 };

	struct ice_dcbx_cfg *prev_cfg;

	enum ice_status ret;

	u8 willing;



	ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL);

	if (ret) {
@@ -224,9 +295,15 @@ void ice_dcb_rebuild(struct ice_pf *pf) 
	if (!test_bit(ICE_FLAG_DCB_ENA, pf->flags))

		return;



	local_dcbx_cfg = &pf->hw.port_info->local_dcbx_cfg;

	desired_dcbx_cfg = &pf->hw.port_info->desired_dcbx_cfg;



	/* Save current willing state and force FW to unwilling */

	willing = pf->hw.port_info->local_dcbx_cfg.etscfg.willing;

	pf->hw.port_info->local_dcbx_cfg.etscfg.willing = 0x0;

	local_dcbx_cfg->etscfg.willing = 0x0;

	local_dcbx_cfg->pfc.willing = 0x0;

	local_dcbx_cfg->app_mode = ICE_DCBX_APPS_NON_WILLING;



	ice_cfg_etsrec_defaults(pf->hw.port_info);

	ret = ice_set_dcb_cfg(pf->hw.port_info);

	if (ret) {

		dev_err(&pf->pdev->dev, "Failed to set DCB to unwilling\n");
@@ -234,8 +311,7 @@ void ice_dcb_rebuild(struct ice_pf *pf) 
	}



	/* Retrieve DCB config and ensure same as current in SW */

	prev_cfg = devm_kmemdup(&pf->pdev->dev,

				&pf->hw.port_info->local_dcbx_cfg,

	prev_cfg = devm_kmemdup(&pf->pdev->dev, local_dcbx_cfg,

				sizeof(*prev_cfg), GFP_KERNEL);

	if (!prev_cfg) {

		dev_err(&pf->pdev->dev, "Failed to alloc space for DCB cfg\n");
@@ -243,22 +319,22 @@ void ice_dcb_rebuild(struct ice_pf *pf) 
	}



	ice_init_dcb(&pf->hw);

	if (memcmp(prev_cfg, &pf->hw.port_info->local_dcbx_cfg,

		   sizeof(*prev_cfg))) {

	if (ice_dcb_need_recfg(pf, prev_cfg, local_dcbx_cfg)) {

		/* difference in cfg detected - disable DCB till next MIB */

		dev_err(&pf->pdev->dev, "Set local MIB not accurate\n");

		devm_kfree(&pf->pdev->dev, prev_cfg);

		goto dcb_error;

	}



	/* fetched config congruent to previous configuration */

	devm_kfree(&pf->pdev->dev, prev_cfg);



	/* Configuration replayed - reset willing state to previous */

	pf->hw.port_info->local_dcbx_cfg.etscfg.willing = willing;

	/* Set the local desired config */

	memset(&pf->hw.port_info->local_dcbx_cfg, 0, sizeof(*local_dcbx_cfg));

	memcpy(local_dcbx_cfg, desired_dcbx_cfg, sizeof(*local_dcbx_cfg));

	ice_cfg_etsrec_defaults(pf->hw.port_info);

	ret = ice_set_dcb_cfg(pf->hw.port_info);

	if (ret) {

		dev_err(&pf->pdev->dev, "Fail restoring prev willing state\n");

		dev_err(&pf->pdev->dev, "Failed to set desired config\n");

		goto dcb_error;

	}

	dev_info(&pf->pdev->dev, "DCB restored after reset\n");
@@ -501,55 +577,6 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_ring *tx_ring, 
	return 0;

}



/**

 * ice_dcb_need_recfg - Check if DCB needs reconfig

 * @pf: board private structure

 * @old_cfg: current DCB config

 * @new_cfg: new DCB config

 */

static bool ice_dcb_need_recfg(struct ice_pf *pf, struct ice_dcbx_cfg *old_cfg,

			       struct ice_dcbx_cfg *new_cfg)

{

	bool need_reconfig = false;



	/* Check if ETS configuration has changed */

	if (memcmp(&new_cfg->etscfg, &old_cfg->etscfg,

		   sizeof(new_cfg->etscfg))) {

		/* If Priority Table has changed reconfig is needed */

		if (memcmp(&new_cfg->etscfg.prio_table,

			   &old_cfg->etscfg.prio_table,

			   sizeof(new_cfg->etscfg.prio_table))) {

			need_reconfig = true;

			dev_dbg(&pf->pdev->dev, "ETS UP2TC changed.\n");

		}



		if (memcmp(&new_cfg->etscfg.tcbwtable,

			   &old_cfg->etscfg.tcbwtable,

			   sizeof(new_cfg->etscfg.tcbwtable)))

			dev_dbg(&pf->pdev->dev, "ETS TC BW Table changed.\n");



		if (memcmp(&new_cfg->etscfg.tsatable,

			   &old_cfg->etscfg.tsatable,

			   sizeof(new_cfg->etscfg.tsatable)))

			dev_dbg(&pf->pdev->dev, "ETS TSA Table changed.\n");

	}



	/* Check if PFC configuration has changed */

	if (memcmp(&new_cfg->pfc, &old_cfg->pfc, sizeof(new_cfg->pfc))) {

		need_reconfig = true;

		dev_dbg(&pf->pdev->dev, "PFC config change detected.\n");

	}



	/* Check if APP Table has changed */

	if (memcmp(&new_cfg->app, &old_cfg->app, sizeof(new_cfg->app))) {

		need_reconfig = true;

		dev_dbg(&pf->pdev->dev, "APP Table change detected.\n");

	}



	dev_dbg(&pf->pdev->dev, "dcb need_reconfig=%d\n", need_reconfig);

	return need_reconfig;

}



/**

 * ice_dcb_process_lldp_set_mib_change - Process MIB change

 * @pf: ptr to ice_pf

drivers/net/ethernet/intel/ice/ice_ethtool.c

+26 −1
Original line number Diff line number Diff line
@@ -2856,6 +2856,7 @@ static int 
ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)

{

	struct ice_netdev_priv *np = netdev_priv(netdev);

	struct ice_aqc_get_phy_caps_data *pcaps;

	struct ice_link_status *hw_link_info;

	struct ice_pf *pf = np->vsi->back;

	struct ice_dcbx_cfg *dcbx_cfg;
@@ -2866,6 +2867,7 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) 
	u8 aq_failures;

	bool link_up;

	int err = 0;

	u32 is_an;



	pi = vsi->port_info;

	hw_link_info = &pi->phy.link_info;
@@ -2880,7 +2882,30 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) 
		return -EOPNOTSUPP;

	}



	if (pause->autoneg != (hw_link_info->an_info & ICE_AQ_AN_COMPLETED)) {

	/* Get pause param reports configured and negotiated flow control pause

	 * when ETHTOOL_GLINKSETTINGS is defined. Since ETHTOOL_GLINKSETTINGS is

	 * defined get pause param pause->autoneg reports SW configured setting,

	 * so compare pause->autoneg with SW configured to prevent the user from

	 * using set pause param to chance autoneg.

	 */

	pcaps = kzalloc(sizeof(*pcaps), GFP_KERNEL);

	if (!pcaps)

		return -ENOMEM;



	/* Get current PHY config */

	status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps,

				     NULL);

	if (status) {

		kfree(pcaps);

		return -EIO;

	}



	is_an = ((pcaps->caps & ICE_AQC_PHY_AN_MODE) ?

			AUTONEG_ENABLE : AUTONEG_DISABLE);



	kfree(pcaps);



	if (pause->autoneg != is_an) {

		netdev_info(netdev, "To change autoneg please use: ethtool -s <dev> autoneg <on|off>\n");

		return -EOPNOTSUPP;

	}

drivers/net/ethernet/intel/ice/ice_hw_autogen.h

+3 −0
Original line number Diff line number Diff line
@@ -127,8 +127,11 @@ 
#define GLINT_DYN_CTL_CLEARPBA_M		BIT(1)

#define GLINT_DYN_CTL_SWINT_TRIG_M		BIT(2)

#define GLINT_DYN_CTL_ITR_INDX_S		3

#define GLINT_DYN_CTL_ITR_INDX_M		ICE_M(0x3, 3)

#define GLINT_DYN_CTL_INTERVAL_S		5

#define GLINT_DYN_CTL_INTERVAL_M		ICE_M(0xFFF, 5)

#define GLINT_DYN_CTL_SW_ITR_INDX_M		ICE_M(0x3, 25)

#define GLINT_DYN_CTL_WB_ON_ITR_M		BIT(30)

#define GLINT_DYN_CTL_INTENA_MSK_M		BIT(31)

#define GLINT_ITR(_i, _INT)			(0x00154000 + ((_i) * 8192 + (_INT) * 4))

#define GLINT_RATE(_INT)			(0x0015A000 + ((_INT) * 4))

drivers/net/ethernet/intel/ice/ice_main.c

+5 −7
Original line number Diff line number Diff line
@@ -41,12 +41,12 @@ static void ice_update_pf_stats(struct ice_pf *pf); 
 * ice_get_tx_pending - returns number of Tx descriptors not processed

 * @ring: the ring of descriptors

 */

static u32 ice_get_tx_pending(struct ice_ring *ring)

static u16 ice_get_tx_pending(struct ice_ring *ring)

{

	u32 head, tail;

	u16 head, tail;



	head = ring->next_to_clean;

	tail = readl(ring->tail);

	tail = ring->next_to_use;



	if (head != tail)

		return (head < tail) ?
@@ -1507,8 +1507,8 @@ static void ice_set_ctrlq_len(struct ice_hw *hw) 
	hw->adminq.num_sq_entries = ICE_AQ_LEN;

	hw->adminq.rq_buf_size = ICE_AQ_MAX_BUF_LEN;

	hw->adminq.sq_buf_size = ICE_AQ_MAX_BUF_LEN;

	hw->mailboxq.num_rq_entries = ICE_MBXQ_LEN;

	hw->mailboxq.num_sq_entries = ICE_MBXQ_LEN;

	hw->mailboxq.num_rq_entries = ICE_MBXRQ_LEN;

	hw->mailboxq.num_sq_entries = ICE_MBXSQ_LEN;

	hw->mailboxq.rq_buf_size = ICE_MBXQ_MAX_BUF_LEN;

	hw->mailboxq.sq_buf_size = ICE_MBXQ_MAX_BUF_LEN;

}
@@ -3701,8 +3701,6 @@ static int ice_ena_vsi(struct ice_vsi *vsi, bool locked) 
				err = netd->netdev_ops->ndo_open(netd);

				rtnl_unlock();

			}

		} else {

			err = ice_vsi_open(vsi);

		}

	}

CRA Git | Maintained and supported by SUSTech CRA and CCSE