Skip to contentSkip to conversation

ice: Implement ethtool ops for channels

PATCH New Tony Nguyen 2 participants 30 messages Jul 25, 2019 – Jul 31, 2019

Subsystems (2)
lore
Share & tools
lore

Tony Nguyen

author maintainer
#0 lore raw

PATCH v4 1/15 ice: Implement ethtool ops for channels

From: Henry Tieman <[email protected]>

Add code to query and set the number of queues on the primary VSI for a PF. This is accessed from the 'ethtool -l' and 'ethtool -L' commands, respectively.

---
 drivers/net/ethernet/intel/ice/ice.h         |  4 +
 drivers/net/ethernet/intel/ice/ice_dcb_lib.c |  9 +-
 drivers/net/ethernet/intel/ice/ice_dcb_lib.h |  2 +
 drivers/net/ethernet/intel/ice/ice_ethtool.c | 85 ++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_lib.c     | 52 ++++++++---
 drivers/net/ethernet/intel/ice/ice_lib.h     |  2 +-
 drivers/net/ethernet/intel/ice/ice_main.c    | 91 +++++++++++++++++++-
 7 files changed, 230 insertions(+), 15 deletions(-)
drivers/net/ethernet/intel/ice/ice.h +4 -0
index 794d97460fc7..07950ac4869f 100644
@@ -298,6 +298,8 @@ struct ice_vsi {
 	u16 num_txq;			 /* Used Tx queues */
 	u16 alloc_rxq;			 /* Allocated Rx queues */
 	u16 num_rxq;			 /* Used Rx queues */
+	u16 req_txq;			 /* User requested Tx queues */
+	u16 req_rxq;			 /* User requested Rx queues */
 	u16 num_rx_desc;
 	u16 num_tx_desc;
 	struct ice_tc_cfg tc_cfg;
@@ -455,6 +457,7 @@ ice_find_vsi_by_type(struct ice_pf *pf, enum ice_vsi_type type)
 int ice_vsi_setup_tx_rings(struct ice_vsi *vsi);
 int ice_vsi_setup_rx_rings(struct ice_vsi *vsi);
 void ice_set_ethtool_ops(struct net_device *netdev);
+int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx);
 int ice_up(struct ice_vsi *vsi);
 int ice_down(struct ice_vsi *vsi);
 int ice_vsi_cfg(struct ice_vsi *vsi);
@@ -462,6 +465,7 @@ struct ice_vsi *ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi);
 int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);
 int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);
 void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size);
+int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset);
 void ice_print_link_msg(struct ice_vsi *vsi, bool isup);
 #ifdef CONFIG_DCB
 int ice_pf_ena_all_vsi(struct ice_pf *pf, bool locked);
drivers/net/ethernet/intel/ice/ice_dcb_lib.c +7 -2
index fe88b127ca42..f80628a13f2a 100644
@@ -85,11 +85,16 @@ void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi)
 			break;
 
 		qoffset = vsi->tc_cfg.tc_info[n].qoffset;
+
 		qcount = vsi->tc_cfg.tc_info[n].qcount_tx;
 		for (i = qoffset; i < (qoffset + qcount); i++) {
 			tx_ring = vsi->tx_rings[i];
-			rx_ring = vsi->rx_rings[i];
 			tx_ring->dcb_tc = n;
+		}
+
+		qcount = vsi->tc_cfg.tc_info[n].qcount_rx;
+		for (i = qoffset; i < (qoffset + qcount); i++) {
+			rx_ring = vsi->rx_rings[i];
 			rx_ring->dcb_tc = n;
 		}
 	}
@@ -103,7 +108,7 @@ void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi)
  * calling this function. Reconfiguring DCB based on
  * local_dcbx_cfg.
  */
-static void ice_pf_dcb_recfg(struct ice_pf *pf)
+void ice_pf_dcb_recfg(struct ice_pf *pf)
 {
 	struct ice_dcbx_cfg *dcbcfg = &pf->hw.port_info->local_dcbx_cfg;
 	u8 tc_map = 0;
drivers/net/ethernet/intel/ice/ice_dcb_lib.h +2 -0
index 819081053ff5..be2ab6f20b21 100644
@@ -13,6 +13,7 @@
 void ice_dcb_rebuild(struct ice_pf *pf);
 u8 ice_dcb_get_ena_tc(struct ice_dcbx_cfg *dcbcfg);
 u8 ice_dcb_get_num_tc(struct ice_dcbx_cfg *dcbcfg);
+void ice_pf_dcb_recfg(struct ice_pf *pf);
 void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi);
 int ice_init_pf_dcb(struct ice_pf *pf, bool locked);
 void ice_update_dcb_stats(struct ice_pf *pf);
@@ -55,6 +56,7 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_ring __always_unused *tx_ring,
 }
 
 #define ice_update_dcb_stats(pf) do {} while (0)
+#define ice_pf_dcb_recfg(pf) do {} while (0)
 #define ice_vsi_cfg_dcb_rings(vsi) do {} while (0)
 #define ice_dcb_process_lldp_set_mib_change(pf, event) do {} while (0)
 #define ice_set_cgd_num(tlan_ctx, ring) do {} while (0)
drivers/net/ethernet/intel/ice/ice_ethtool.c +85 -0

97 lines not on this page · raw message

drivers/net/ethernet/intel/ice/ice_lib.c +41 -11

114 lines not on this page · raw message

drivers/net/ethernet/intel/ice/ice_lib.h +1 -1
index 6e43ef03bfc3..7409a69f631d 100644
@@ -70,7 +70,7 @@ int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id);
 int
 ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id);
 
-int ice_vsi_rebuild(struct ice_vsi *vsi);
+int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi);
 
 bool ice_is_reset_in_progress(unsigned long *state);
 
drivers/net/ethernet/intel/ice/ice_main.c +90 -1

109 lines not on this page · raw message

Signature · 1 line
2.20.1
author maintainer
#1 lore raw

PATCH v4 2/15 ice: Use the software based tail when checking for hung Tx ring

From: Brett Creeley <[email protected]>

Currently in ice_get_tx_pending we try to read a Tx ring's tail. This is then compared with the software based head (next_to_clean) to determine if we have pending work. This will never work because reading of the Tx ring's tail is no longer supported. Fix this by using the software based tail (next_to_use) to determine if there is pending work.

---
 drivers/net/ethernet/intel/ice/ice_main.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
drivers/net/ethernet/intel/ice/ice_main.c +3 -3
index eb3ee6ca9ecc..6f02c29d7830 100644
@@ -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) ?
Signature · 1 line
2.20.1
#2 lore raw

PATCH v4 2/15 ice: Use the software based tail when checking for hung Tx ring

Quoted 16 lines

-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Thursday, July 25, 2019 1:55 AM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S23 v4 02/15] ice: Use the software based tail when checking for hung Tx ring

From: Brett Creeley <[email protected]>

Currently in ice_get_tx_pending we try to read a Tx ring's tail. This is then compared with the software based head (next_to_clean) to determine if we have pending work. This will never work because reading of the Tx ring's tail is no longer supported. Fix this by using the software based tail (next_to_use) to determine if there is pending work.

Quoted 4 lines
---
 drivers/net/ethernet/intel/ice/ice_main.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
author maintainer
#3 lore raw

PATCH v4 3/15 ice: Assume that more than one Rx queue is rare in ice_napi_poll

In reply to Tony Nguyen

From: Brett Creeley <[email protected]>

Currently we divide budget by the number of Rx queues per Rx ring container in ice_napi_poll even if there is only 1. This is an unnecessary divide for the normal case of 1 Rx ring per Rx ring container. Fix this by using an unlikely() call in the case where we actually need to divide.

Also, we will always set budget_per_ring even if there are no Rx rings in the Rx ring container so we don't need to initialize it to 0.

---
 drivers/net/ethernet/intel/ice/ice_txrx.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)
drivers/net/ethernet/intel/ice/ice_txrx.c +10 -5
index 92a3d40f53ed..5d2689956ade 100644
@@ -1415,8 +1415,8 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 				container_of(napi, struct ice_q_vector, napi);
 	struct ice_vsi *vsi = q_vector->vsi;
 	bool clean_complete = true;
-	int budget_per_ring = 0;
 	struct ice_ring *ring;
+	int budget_per_ring;
 	int work_done = 0;
 
 	/* Since the actual Tx work is minimal, we can give the Tx a larger
@@ -1430,11 +1430,16 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 	if (budget <= 0)
 		return budget;
 
-	/* We attempt to distribute budget to each Rx queue fairly, but don't
-	 * allow the budget to go below 1 because that would exit polling early.
-	 */
-	if (q_vector->num_ring_rx)
+	/* normally we have 1 Rx ring per q_vector */
+	if (unlikely(q_vector->num_ring_rx > 1))
+		/* We attempt to distribute budget to each Rx queue fairly, but
+		 * don't allow the budget to go below 1 because that would exit
+		 * polling early.
+		 */
 		budget_per_ring = max(budget / q_vector->num_ring_rx, 1);
+	else
+		/* Max of 1 Rx ring in this q_vector so give it the budget */
+		budget_per_ring = budget;
 
 	ice_for_each_ring(ring, q_vector->rx) {
 		int cleaned;
Signature · 1 line
2.20.1
#4 lore raw

PATCH v4 3/15 ice: Assume that more than one Rx queue is rare in ice_napi_poll

Quoted 15 lines

-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Thursday, July 25, 2019 1:55 AM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S23 v4 03/15] ice: Assume that more than one Rx queue is rare in ice_napi_poll

From: Brett Creeley <[email protected]>

Currently we divide budget by the number of Rx queues per Rx ring container in ice_napi_poll even if there is only 1. This is an unnecessary divide for the normal case of 1 Rx ring per Rx ring container. Fix this by using an unlikely() call in the case where we actually need to divide.

Quoted 7 lines

Also, we will always set budget_per_ring even if there are no Rx rings in the Rx ring container so we don't need to initialize it to 0.

---
 drivers/net/ethernet/intel/ice/ice_txrx.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)
author maintainer
#5 lore raw

PATCH v4 4/15 ice: Restructure VFs initialization flows

In reply to Tony Nguyen

From: Akeem G Abodunrin <[email protected]>

This patch restructures how VFs are configured, and resources allocated. Instead of freeing resources that were never allocated, and resetting empty VFs that have never been created - the new flow will just allocate resources for number of requested VFs based on the availability.

During VFs initialization process, global interrupt is disabled, and rearmed after getting MSIX vectors for VFs. This allows immediate mailbox communications, instead of delaying it till later and VFs.
PF communications resulted to using polling instead of actual interrupt. The issue manifested when creating higher number of VFs (128 VFs) per PF.

---
v4: Reduce scope of vf in ice_config_res_vfs()

---
 drivers/net/ethernet/intel/ice/ice.h          |  1 +
 .../net/ethernet/intel/ice/ice_virtchnl_pf.c  | 69 +++++++++++++------
 2 files changed, 48 insertions(+), 22 deletions(-)
drivers/net/ethernet/intel/ice/ice.h +1 -0
index 07950ac4869f..112bdb662ea2 100644
@@ -220,6 +220,7 @@ 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_virtchnl_pf.c +47 -22

104 lines not on this page · raw message

Signature · 1 line
2.20.1
#6 lore raw

PATCH v4 4/15 ice: Restructure VFs initialization flows

Quoted 21 lines

-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Thursday, July 25, 2019 1:56 AM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S23 v4 04/15] ice: Restructure VFs initialization flows

From: Akeem G Abodunrin <[email protected]>

This patch restructures how VFs are configured, and resources allocated. Instead of freeing resources that were never allocated, and resetting empty VFs that have never been created - the new flow will just allocate resources for number of requested VFs based on the availability.

During VFs initialization process, global interrupt is disabled, and rearmed after getting MSIX vectors for VFs. This allows immediate mailbox communications, instead of delaying it till later and VFs.
PF communications resulted to using polling instead of actual interrupt. The issue manifested when creating higher number of VFs (128 VFs) per PF.

Quoted 7 lines

---
v4: Reduce scope of vf in ice_config_res_vfs()

---
 drivers/net/ethernet/intel/ice/ice.h          |  1 +
 .../net/ethernet/intel/ice/ice_virtchnl_pf.c  | 69 +++++++++++++------
 2 files changed, 48 insertions(+), 22 deletions(-)
author maintainer
#7 lore raw

PATCH v4 5/15 ice: fix set pause param autoneg check

In reply to Tony Nguyen

From: Paul Greenwalt <[email protected]>

When ETHTOOL_GLINKSETTINGS is defined get pause param pause->autoneg reports SW configured setting, however when not defined get pause param pause->autoneg reports the link status. Set pause param needs to compare pause->autoneg with the same source as get pause param to block the user from changing autoneg with the set pause param option, or the user may be incorrectly blocked from changing Rx|Tx pause settings.

---
 drivers/net/ethernet/intel/ice/ice_ethtool.c | 28 +++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)
drivers/net/ethernet/intel/ice/ice_ethtool.c +27 -1
index 1fe048cfb737..ba29aede99ad 100644
@@ -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 +2882,31 @@ 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 = devm_kzalloc(&vsi->back->pdev->dev, 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) {
+		devm_kfree(&vsi->back->pdev->dev, pcaps);
+		return -EIO;
+	}
+
+	is_an = ((pcaps->caps & ICE_AQC_PHY_AN_MODE) ?
+			AUTONEG_ENABLE : AUTONEG_DISABLE);
+
+	devm_kfree(&vsi->back->pdev->dev, pcaps);
+
+	if (pause->autoneg != is_an) {
 		netdev_info(netdev, "To change autoneg please use: ethtool -s <dev> autoneg <on|off>\n");
 		return -EOPNOTSUPP;
 	}
Signature · 1 line
2.20.1
#8 lore raw

PATCH v4 5/15 ice: fix set pause param autoneg check

Quoted 18 lines

-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Thursday, July 25, 2019 1:56 AM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S23 v4 05/15] ice: fix set pause param autoneg check

From: Paul Greenwalt <[email protected]>

When ETHTOOL_GLINKSETTINGS is defined get pause param pause-

Quoted 1 line

autoneg reports SW configured setting, however when not defined get

pause param
pause->autoneg reports the link status. Set pause param needs to compare pause->autoneg with the same source as get pause param to block the user from changing autoneg with the set pause param option, or the user may be incorrectly blocked from changing Rx|Tx pause settings.

Quoted 4 lines
---
 drivers/net/ethernet/intel/ice/ice_ethtool.c | 28 +++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)
author maintainer
#9 lore raw

PATCH v4 6/15 ice: Set WB_ON_ITR when we don't re-enable interrupts

In reply to Tony Nguyen

From: Brett Creeley <[email protected]>

Currently when busy polling is enabled we aren't setting/enabling WB_ON_ITR in the driver. This doesn't break the driver, but it does cause issues. If we don't enable WB_ON_ITR mode we will still get write-backs from hardware during polling when a cache line has been filled, but if a cache line is not filled we will not get the write-back because WB_ON_ITR is not set. Fix this by enabling WB_ON_ITR in the driver when interrupts are disabled.

---
v3: Moved defines to group with similar registers

---
 .../net/ethernet/intel/ice/ice_hw_autogen.h   |  3 ++
 drivers/net/ethernet/intel/ice/ice_txrx.c     | 54 +++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_txrx.h     | 13 +++++
 3 files changed, 70 insertions(+)
drivers/net/ethernet/intel/ice/ice_hw_autogen.h +3 -0
index 87652d722a30..6f78ff5534af 100644
@@ -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_txrx.c +54 -0

72 lines not on this page · raw message

drivers/net/ethernet/intel/ice/ice_txrx.h +13 -0
index ec76aba347b9..94a9280193e2 100644
@@ -144,6 +144,19 @@ enum ice_rx_dtype {
 #define ICE_DFLT_INTRL	0
 #define ICE_MAX_INTRL	236
 
+#define ICE_WB_ON_ITR_USECS	2
+#define ICE_IN_WB_ON_ITR_MODE	255
+/* Sets WB_ON_ITR and assumes INTENA bit is already cleared, which allows
+ * setting the MSK_M bit to tell hardware to ignore the INTENA_M bit. Also,
+ * set the write-back latency to the usecs passed in.
+ */
+#define ICE_GLINT_DYN_CTL_WB_ON_ITR(usecs, itr_idx)	\
+	((((usecs) << (GLINT_DYN_CTL_INTERVAL_S - ICE_ITR_GRAN_S)) & \
+	  GLINT_DYN_CTL_INTERVAL_M) | \
+	 (((itr_idx) << GLINT_DYN_CTL_ITR_INDX_S) & \
+	  GLINT_DYN_CTL_ITR_INDX_M) | GLINT_DYN_CTL_INTENA_MSK_M | \
+	 GLINT_DYN_CTL_WB_ON_ITR_M)
+
 /* Legacy or Advanced Mode Queue */
 #define ICE_TX_ADVANCED	0
 #define ICE_TX_LEGACY	1
Signature · 1 line
2.20.1
#10 lore raw

PATCH v4 6/15 ice: Set WB_ON_ITR when we don't re-enable interrupts

Quoted 19 lines

-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Thursday, July 25, 2019 1:56 AM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S23 v4 06/15] ice: Set WB_ON_ITR when we don't re-enable interrupts

From: Brett Creeley <[email protected]>

Currently when busy polling is enabled we aren't setting/enabling WB_ON_ITR in the driver. This doesn't break the driver, but it does cause issues. If we don't enable WB_ON_ITR mode we will still get write-backs from hardware during polling when a cache line has been filled, but if a cache line is not filled we will not get the write-back because WB_ON_ITR is not set. Fix this by enabling WB_ON_ITR in the driver when interrupts are disabled.

Quoted 7 lines

---
v3: Moved defines to group with similar registers

---
 .../net/ethernet/intel/ice/ice_hw_autogen.h   |  3 ++
 drivers/net/ethernet/intel/ice/ice_txrx.c     | 54 +++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_txrx.h     | 13 +++++
 3 files changed, 70 insertions(+)
author maintainer
#11 lore raw

PATCH v4 7/15 ice: Fix kernel hang with DCB reset in CEE mode

In reply to Tony Nguyen

From: Usha Ketineni <[email protected]>

This patch fixes the set local MIB AQ call failures in the DCB rebuild path by setting the defaults for the ETS recommended DCB configuration. Also, willing bits for the DCB configuration needs to be set correctly. Resets works fine in IEEE mode as the ETS recommended DCB configuration is populated but not in CEE mode.
Without this patch, PFR causes the kernel hang in CEE mode.

---
 drivers/net/ethernet/intel/ice/ice_dcb_lib.c | 149 +++++++++++--------
 1 file changed, 88 insertions(+), 61 deletions(-)
drivers/net/ethernet/intel/ice/ice_dcb_lib.c +88 -61
index f80628a13f2a..d285aba3fea7 100644
@@ -208,16 +208,87 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked)
 	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) {
@@ -229,9 +300,15 @@ 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");
@@ -239,8 +316,7 @@ 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");
@@ -248,22 +324,22 @@ 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");
@@ -506,55 +582,6 @@ 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
Signature · 1 line
2.20.1
#12 lore raw

PATCH v4 7/15 ice: Fix kernel hang with DCB reset in CEE mode

Quoted 17 lines

-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Thursday, July 25, 2019 1:56 AM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S23 v4 07/15] ice: Fix kernel hang with DCB reset in CEE mode

From: Usha Ketineni <[email protected]>

This patch fixes the set local MIB AQ call failures in the DCB rebuild path by setting the defaults for the ETS recommended DCB configuration. Also, willing bits for the DCB configuration needs to be set correctly. Resets works fine in IEEE mode as the ETS recommended DCB configuration is populated but not in CEE mode.
Without this patch, PFR causes the kernel hang in CEE mode.

Quoted 4 lines
---
 drivers/net/ethernet/intel/ice/ice_dcb_lib.c | 149 +++++++++++--------
 1 file changed, 88 insertions(+), 61 deletions(-)
author maintainer
#13 lore raw

PATCH v4 8/15 ice: allow empty rx descriptors

In reply to Tony Nguyen

From: Mitch Williams <[email protected]>

In some circumstances, the hardware will hand us a receive descriptor which has no data attached, but is otherwise valid. The receive code was improperly ignoring these descriptors, which result in an infinite loop.

To fix this, change the receive code to process all descriptors, regardless of the size of the associated data. Add checks to the memory-handling functions to allow for zero size.

---
 drivers/net/ethernet/intel/ice/ice_txrx.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)
drivers/net/ethernet/intel/ice/ice_txrx.c +12 -3
index 9a54406922f0..75b0afe02015 100644
@@ -607,6 +607,8 @@ ice_add_rx_frag(struct ice_rx_buf *rx_buf, struct sk_buff *skb,
 	unsigned int truesize = ICE_RXBUF_2048;
 #endif
 
+	if (!size)
+		return;
 	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buf->page,
 			rx_buf->page_offset, size, truesize);
 
@@ -662,6 +664,8 @@ ice_get_rx_buf(struct ice_ring *rx_ring, struct sk_buff **skb,
 	prefetchw(rx_buf->page);
 	*skb = rx_buf->skb;
 
+	if (!size)
+		return rx_buf;
 	/* we are reusing so sync this buffer for CPU use */
 	dma_sync_single_range_for_cpu(rx_ring->dev, rx_buf->dma,
 				      rx_buf->page_offset, size,
@@ -745,8 +749,11 @@ ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf,
  */
 static void ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf)
 {
-		/* hand second half of page back to the ring */
+	if (!rx_buf)
+		return;
+
 	if (ice_can_reuse_rx_page(rx_buf)) {
+		/* hand second half of page back to the ring */
 		ice_reuse_rx_page(rx_ring, rx_buf);
 		rx_ring->rx_stats.page_reuse_count++;
 	} else {
@@ -1032,8 +1039,9 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		size = le16_to_cpu(rx_desc->wb.pkt_len) &
 			ICE_RX_FLX_DESC_PKT_LEN_M;
 
+		/* retrieve a buffer from the ring */
 		rx_buf = ice_get_rx_buf(rx_ring, &skb, size);
-		/* allocate (if needed) and populate skb */
+
 		if (skb)
 			ice_add_rx_frag(rx_buf, skb, size);
 		else
@@ -1042,7 +1050,8 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
 			rx_ring->rx_stats.alloc_buf_failed++;
-			rx_buf->pagecnt_bias++;
+			if (rx_buf)
+				rx_buf->pagecnt_bias++;
 			break;
 		}
 
Signature · 1 line
2.20.1
#14 lore raw

PATCH v4 8/15 ice: allow empty rx descriptors

Quoted 14 lines

-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Thursday, July 25, 2019 1:56 AM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S23 v4 08/15] ice: allow empty rx descriptors

From: Mitch Williams <[email protected]>

In some circumstances, the hardware will hand us a receive descriptor which has no data attached, but is otherwise valid. The receive code was improperly ignoring these descriptors, which result in an infinite loop.

Quoted 8 lines

To fix this, change the receive code to process all descriptors, regardless of the size of the associated data. Add checks to the memory-handling functions to allow for zero size.

---
 drivers/net/ethernet/intel/ice/ice_txrx.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)
author maintainer
#15 lore raw

PATCH v4 9/15 ice: Do not always bring up PF VSI in ice_ena_vsi()

In reply to Tony Nguyen

During rebuild ice_ena_vsi() is called to recover the VSI state. This function assumes the PF VSI is always to be enabled, however, it's possible that during reset/rebuild the interface can be brought down. If this occurs, we can attempt to bring up the PF VSI on a downed interface which can lead to various crashes. If the interface is not running, do not bring up the associated VSI.

---
 drivers/net/ethernet/intel/ice/ice_main.c | 2 --
 1 file changed, 2 deletions(-)
drivers/net/ethernet/intel/ice/ice_main.c +0 -2
index 6f02c29d7830..be872336e08e 100644
@@ -3737,8 +3737,6 @@ 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);
 		}
 	}
 
Signature · 1 line
2.20.1
#16 lore raw

PATCH v4 9/15 ice: Do not always bring up PF VSI in ice_ena_vsi()

Quoted 15 lines

-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Thursday, July 25, 2019 1:56 AM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S23 v4 09/15] ice: Do not always bring up PF VSI in ice_ena_vsi()

During rebuild ice_ena_vsi() is called to recover the VSI state. This function assumes the PF VSI is always to be enabled, however, it's possible that during reset/rebuild the interface can be brought down. If this occurs, we can attempt to bring up the PF VSI on a downed interface which can lead to various crashes. If the interface is not running, do not bring up the associated VSI.

Quoted 4 lines
---
 drivers/net/ethernet/intel/ice/ice_main.c | 2 --
 1 file changed, 2 deletions(-)
author maintainer
#17 lore raw

PATCH v4 10/15 ice: update GLINT_DYN_CTL and GLINT_VECT2FUNC register access

In reply to Tony Nguyen

From: Paul Greenwalt <[email protected]>

Register access for GLINT_DYN_CTL and GLINT_VECT2FUNC should be within the PF space and not the absolute device space.

---
 .../net/ethernet/intel/ice/ice_virtchnl_pf.c  | 24 +++++++++++--------
 .../net/ethernet/intel/ice/ice_virtchnl_pf.h  |  3 ++-
 2 files changed, 16 insertions(+), 11 deletions(-)
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +14 -10
index 93b835a24bb1..54b0e88af4ca 100644
@@ -474,19 +474,20 @@ ice_vf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, u16 vf_id)
 }
 
 /**
- * ice_calc_vf_first_vector_idx - Calculate absolute MSIX vector index in HW
+ * ice_calc_vf_first_vector_idx - Calculate MSIX vector index in the PF space
  * @pf: pointer to PF structure
  * @vf: pointer to VF that the first MSIX vector index is being calculated for
  *
- * This returns the first MSIX vector index in HW that is used by this VF and
- * this will always be the OICR index in the AVF driver so any functionality
+ * This returns the first MSIX vector index in PF space that is used by this VF.
+ * This index is used when accessing PF relative registers such as
+ * GLINT_VECT2FUNC and GLINT_DYN_CTL.
+ * This will always be the OICR index in the AVF driver so any functionality
  * using vf->first_vector_idx for queue configuration will have to increment by
  * 1 to avoid meddling with the OICR index.
  */
 static int ice_calc_vf_first_vector_idx(struct ice_pf *pf, struct ice_vf *vf)
 {
-	return pf->hw.func_caps.common_cap.msix_vector_first_id +
-		pf->sriov_base_vector + vf->vf_id * pf->num_vf_msix;
+	return pf->sriov_base_vector + vf->vf_id * pf->num_vf_msix;
 }
 
 /**
@@ -597,27 +598,30 @@ static int ice_alloc_vf_res(struct ice_vf *vf)
  */
 static void ice_ena_vf_mappings(struct ice_vf *vf)
 {
+	int abs_vf_id, abs_first, abs_last;
 	struct ice_pf *pf = vf->pf;
 	struct ice_vsi *vsi;
 	int first, last, v;
 	struct ice_hw *hw;
-	int abs_vf_id;
 	u32 reg;
 
 	hw = &pf->hw;
 	vsi = pf->vsi[vf->lan_vsi_idx];
 	first = vf->first_vector_idx;
 	last = (first + pf->num_vf_msix) - 1;
+	abs_first = first + pf->hw.func_caps.common_cap.msix_vector_first_id;
+	abs_last = (abs_first + pf->num_vf_msix) - 1;
 	abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id;
 
 	/* VF Vector allocation */
-	reg = (((first << VPINT_ALLOC_FIRST_S) & VPINT_ALLOC_FIRST_M) |
-	       ((last << VPINT_ALLOC_LAST_S) & VPINT_ALLOC_LAST_M) |
+	reg = (((abs_first << VPINT_ALLOC_FIRST_S) & VPINT_ALLOC_FIRST_M) |
+	       ((abs_last << VPINT_ALLOC_LAST_S) & VPINT_ALLOC_LAST_M) |
 	       VPINT_ALLOC_VALID_M);
 	wr32(hw, VPINT_ALLOC(vf->vf_id), reg);
 
-	reg = (((first << VPINT_ALLOC_PCI_FIRST_S) & VPINT_ALLOC_PCI_FIRST_M) |
-	       ((last << VPINT_ALLOC_PCI_LAST_S) & VPINT_ALLOC_PCI_LAST_M) |
+	reg = (((abs_first << VPINT_ALLOC_PCI_FIRST_S)
+		 & VPINT_ALLOC_PCI_FIRST_M) |
+	       ((abs_last << VPINT_ALLOC_PCI_LAST_S) & VPINT_ALLOC_PCI_LAST_M) |
 	       VPINT_ALLOC_PCI_VALID_M);
 	wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), reg);
 	/* map the interrupts to its functions */
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +2 -1
index ada69120ff38..424bc0538956 100644
@@ -45,7 +45,8 @@ struct ice_vf {
 
 	s16 vf_id;			/* VF ID in the PF space */
 	u16 lan_vsi_idx;		/* index into PF struct */
-	int first_vector_idx;		/* first vector index of this VF */
+	/* first vector index of this VF in the PF space */
+	int first_vector_idx;
 	struct ice_sw *vf_sw_id;	/* switch ID the VF VSIs connect to */
 	struct virtchnl_version_info vf_ver;
 	u32 driver_caps;		/* reported by VF driver */
Signature · 1 line
2.20.1
#18 lore raw

PATCH v4 10/15 ice: update GLINT_DYN_CTL and GLINT_VECT2FUNC register access

Quoted 10 lines

-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Thursday, July 25, 2019 1:56 AM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S23 v4 10/15] ice: update GLINT_DYN_CTL and GLINT_VECT2FUNC register access

From: Paul Greenwalt <[email protected]>

Quoted 8 lines

Register access for GLINT_DYN_CTL and GLINT_VECT2FUNC should be within the PF space and not the absolute device space.

---
 .../net/ethernet/intel/ice/ice_virtchnl_pf.c  | 24 +++++++++++--------
.../net/ethernet/intel/ice/ice_virtchnl_pf.h  |  3 ++-
 2 files changed, 16 insertions(+), 11 deletions(-)
author maintainer
#19 lore raw

PATCH v4 11/15 ice: Reduce wait times during VF bringup/reset

In reply to Tony Nguyen

From: Brett Creeley <[email protected]>

Currently there are a couple places where the VF is waiting too long when checking the status of registers. This is causing the AVF driver to spin for longer than necessary in the __IAVF_STARTUP state. Sometimes it causes the AVF to go into the __IAVF_COMM_FAILED, which may retrigger the __IAVF_STARTUP state. Try to reduce the chance of this happening by removing unnecessary wait times in VF bringup/resets.

---
 .../net/ethernet/intel/ice/ice_virtchnl_pf.c  | 26 +++++++++++--------
 .../net/ethernet/intel/ice/ice_virtchnl_pf.h  |  4 +++
 2 files changed, 19 insertions(+), 11 deletions(-)
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +15 -11
index 54b0e88af4ca..8a5bf9730fdf 100644
@@ -382,12 +382,15 @@ static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr)
 
 	wr32(hw, PF_PCI_CIAA,
 	     VF_DEVICE_STATUS | (vf_abs_id << PF_PCI_CIAA_VF_NUM_S));
-	for (i = 0; i < 100; i++) {
+	for (i = 0; i < ICE_PCI_CIAD_WAIT_COUNT; i++) {
 		reg = rd32(hw, PF_PCI_CIAD);
-		if ((reg & VF_TRANS_PENDING_M) != 0)
-			dev_err(&pf->pdev->dev,
-				"VF %d PCI transactions stuck\n", vf->vf_id);
-		udelay(1);
+		/* no transactions pending so stop polling */
+		if ((reg & VF_TRANS_PENDING_M) == 0)
+			break;
+
+		dev_err(&pf->pdev->dev,
+			"VF %d PCI transactions stuck\n", vf->vf_id);
+		udelay(ICE_PCI_CIAD_WAIT_DELAY_US);
 	}
 }
 
@@ -1068,7 +1071,6 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr)
 	 * finished resetting.
 	 */
 	for (i = 0, v = 0; i < 10 && v < pf->num_alloc_vfs; i++) {
-		usleep_range(10000, 20000);
 
 		/* Check each VF in sequence */
 		while (v < pf->num_alloc_vfs) {
@@ -1076,8 +1078,11 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr)
 
 			vf = &pf->vf[v];
 			reg = rd32(hw, VPGEN_VFRSTAT(vf->vf_id));
-			if (!(reg & VPGEN_VFRSTAT_VFRD_M))
+			if (!(reg & VPGEN_VFRSTAT_VFRD_M)) {
+				/* only delay if the check failed */
+				usleep_range(10, 20);
 				break;
+			}
 
 			/* If the current VF has finished resetting, move on
 			 * to the next VF in sequence.
@@ -1091,7 +1096,6 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr)
 	 */
 	if (v < pf->num_alloc_vfs)
 		dev_warn(&pf->pdev->dev, "VF reset check timeout\n");
-	usleep_range(10000, 20000);
 
 	/* free VF resources to begin resetting the VSI state */
 	for (v = 0; v < pf->num_alloc_vfs; v++) {
@@ -1165,12 +1169,14 @@ static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr)
 		 * poll the status register to make sure that the reset
 		 * completed successfully.
 		 */
-		usleep_range(10000, 20000);
 		reg = rd32(hw, VPGEN_VFRSTAT(vf->vf_id));
 		if (reg & VPGEN_VFRSTAT_VFRD_M) {
 			rsd = true;
 			break;
 		}
+
+		/* only sleep if the reset is not done */
+		usleep_range(10, 20);
 	}
 
 	/* Display a warning if VF didn't manage to reset in time, but need to
@@ -1180,8 +1186,6 @@ static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr)
 		dev_warn(&pf->pdev->dev, "VF reset check timeout on VF %d\n",
 			 vf->vf_id);
 
-	usleep_range(10000, 20000);
-
 	/* disable promiscuous modes in case they were enabled
 	 * ignore any error if disabling process failed
 	 */
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +4 -0
index 424bc0538956..79bb47f73879 100644
@@ -22,6 +22,10 @@
 #define VF_DEVICE_STATUS		0xAA
 #define VF_TRANS_PENDING_M		0x20
 
+/* wait defines for polling PF_PCI_CIAD register status */
+#define ICE_PCI_CIAD_WAIT_COUNT		100
+#define ICE_PCI_CIAD_WAIT_DELAY_US	1
+
 /* Specific VF states */
 enum ice_vf_states {
 	ICE_VF_STATE_INIT = 0,
Signature · 1 line
2.20.1
#20 lore raw

PATCH v4 11/15 ice: Reduce wait times during VF bringup/reset

Quoted 17 lines

-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Thursday, July 25, 2019 1:56 AM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S23 v4 11/15] ice: Reduce wait times during VF bringup/reset

From: Brett Creeley <[email protected]>

Currently there are a couple places where the VF is waiting too long when checking the status of registers. This is causing the AVF driver to spin for longer than necessary in the __IAVF_STARTUP state. Sometimes it causes the AVF to go into the __IAVF_COMM_FAILED, which may retrigger the __IAVF_STARTUP state. Try to reduce the chance of this happening by removing unnecessary wait times in VF bringup/resets.

Quoted 5 lines
---
 .../net/ethernet/intel/ice/ice_virtchnl_pf.c  | 26 +++++++++++--------
.../net/ethernet/intel/ice/ice_virtchnl_pf.h  |  4 +++
 2 files changed, 19 insertions(+), 11 deletions(-)
author maintainer
#21 lore raw

PATCH v4 12/15 ice: Increase size of Mailbox receive queue for many VFs

In reply to Tony Nguyen

From: Brett Creeley <[email protected]>

Currently we use the ICE_MBXQ_LEN for both the Mailbox send and receive queues that are used to communicate with VFs. This is fine for the send queue because the PF driver will lock the queue for every single send, but for the Mailbox receive queue every VF is posting to its Mailbox send queue and the hardware is then handing the message to the PF on its Mailbox receive queue. This becomes a problem with many VFs because it seems to overburden the Mailbox receive queue on the PF. Fix this by increasing the Mailbox receive queue for the PF to 512 entries.

The number 512 was determined based on the number of VFs supported by the device. We can have a total of 256 VFs so in the worst case this allows the VFs to put 2 messages in the PFs Mailbox receive queue at the same time.

---
 drivers/net/ethernet/intel/ice/ice.h      | 3 ++-
 drivers/net/ethernet/intel/ice/ice_main.c | 4 ++--
 2 files changed, 4 insertions(+), 3 deletions(-)
drivers/net/ethernet/intel/ice/ice.h +2 -1
index 112bdb662ea2..36a8ee873ae1 100644
@@ -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
drivers/net/ethernet/intel/ice/ice_main.c +2 -2
index be872336e08e..833f0efc93f9 100644
@@ -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;
 }
Signature · 1 line
2.20.1
#22 lore raw

PATCH v4 12/15 ice: Increase size of Mailbox receive queue for many VFs

Quoted 23 lines

-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Thursday, July 25, 2019 1:56 AM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S23 v4 12/15] ice: Increase size of Mailbox receive queue for many VFs

From: Brett Creeley <[email protected]>

Currently we use the ICE_MBXQ_LEN for both the Mailbox send and receive queues that are used to communicate with VFs. This is fine for the send queue because the PF driver will lock the queue for every single send, but for the Mailbox receive queue every VF is posting to its Mailbox send queue and the hardware is then handing the message to the PF on its Mailbox receive queue. This becomes a problem with many VFs because it seems to overburden the Mailbox receive queue on the PF. Fix this by increasing the Mailbox receive queue for the PF to 512 entries.

The number 512 was determined based on the number of VFs supported by the device. We can have a total of 256 VFs so in the worst case this allows the VFs to put 2 messages in the PFs Mailbox receive queue at the same time.

Quoted 5 lines
---
 drivers/net/ethernet/intel/ice/ice.h      | 3 ++-
 drivers/net/ethernet/intel/ice/ice_main.c | 4 ++--
 2 files changed, 4 insertions(+), 3 deletions(-)
author maintainer
#23 lore raw

PATCH v4 13/15 ice: Move VF resources definition to SR-IOV specific file

In reply to Tony Nguyen

From: Akeem G Abodunrin <[email protected]>

In order to use some of the VF resources definition in the SR-IOV specific virtchnl header file, this patch moves applicable code to ice_virtchnl_pf.h file accordingly... and they should have been defined in the destination file originally.

---
 drivers/net/ethernet/intel/ice/ice.h             | 10 ----------
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h | 13 +++++++++++++
 2 files changed, 13 insertions(+), 10 deletions(-)
drivers/net/ethernet/intel/ice/ice.h +0 -10
index 36a8ee873ae1..8398dd45a8a2 100644
@@ -87,16 +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
 
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +13 -0
index 79bb47f73879..4d94853f119a 100644
@@ -26,6 +26,19 @@
 #define ICE_PCI_CIAD_WAIT_COUNT		100
 #define ICE_PCI_CIAD_WAIT_DELAY_US	1
 
+/* VF resources default values and limitation */
+#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_MAX_POLICY_INTR_PER_VF	33
+#define ICE_MIN_INTR_PER_VF		(ICE_MIN_QS_PER_VF + 1)
+#define ICE_DFLT_INTR_PER_VF		(ICE_DFLT_QS_PER_VF + 1)
+
 /* Specific VF states */
 enum ice_vf_states {
 	ICE_VF_STATE_INIT = 0,
Signature · 1 line
2.20.1
#24 lore raw

PATCH v4 13/15 ice: Move VF resources definition to SR-IOV specific file

Quoted 15 lines

-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Thursday, July 25, 2019 1:56 AM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S23 v4 13/15] ice: Move VF resources definition to SR-IOV specific file

From: Akeem G Abodunrin <[email protected]>

In order to use some of the VF resources definition in the SR-IOV specific virtchnl header file, this patch moves applicable code to ice_virtchnl_pf.h file accordingly... and they should have been defined in the destination file originally.

Quoted 5 lines
---
 drivers/net/ethernet/intel/ice/ice.h             | 10 ----------
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h | 13 +++++++++++++
 2 files changed, 13 insertions(+), 10 deletions(-)
author maintainer
#25 lore raw

PATCH v4 14/15 ice: Change type for queue counts

In reply to Tony Nguyen

From: Pawel Kaminski <[email protected]>

These queue variables are being assigned values that are type u16. Change the local variables to match these types. Since these represent queue counts, they should never be negative.

---
v3: Change type back to u16
Fix format specifiers and min_t type
Redo commit message

v2: Change type from u16 to unsigned int
Reword commit message

---
 .../net/ethernet/intel/ice/ice_virtchnl_pf.c  | 25 ++++++++++---------
 1 file changed, 13 insertions(+), 12 deletions(-)
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +13 -12
index 8a5bf9730fdf..61cf1c5af928 100644
@@ -2337,11 +2337,11 @@ static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg)
 	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
 	struct virtchnl_vf_res_request *vfres =
 		(struct virtchnl_vf_res_request *)msg;
-	int req_queues = vfres->num_queue_pairs;
+	u16 req_queues = vfres->num_queue_pairs;
 	struct ice_pf *pf = vf->pf;
-	int max_allowed_vf_queues;
-	int tx_rx_queue_left;
-	int cur_queues;
+	u16 max_allowed_vf_queues;
+	u16 tx_rx_queue_left;
+	u16 cur_queues;
 
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
 		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
@@ -2349,29 +2349,30 @@ static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg)
 	}
 
 	cur_queues = vf->num_vf_qs;
-	tx_rx_queue_left = min_t(int, pf->q_left_tx, pf->q_left_rx);
+	tx_rx_queue_left = min_t(u16, pf->q_left_tx, pf->q_left_rx);
 	max_allowed_vf_queues = tx_rx_queue_left + cur_queues;
-	if (req_queues <= 0) {
+	if (!req_queues) {
 		dev_err(&pf->pdev->dev,
-			"VF %d tried to request %d queues. Ignoring.\n",
-			vf->vf_id, req_queues);
+			"VF %d tried to request 0 queues. Ignoring.\n",
+			vf->vf_id);
 	} else if (req_queues > ICE_MAX_BASE_QS_PER_VF) {
 		dev_err(&pf->pdev->dev,
 			"VF %d tried to request more than %d queues.\n",
 			vf->vf_id, ICE_MAX_BASE_QS_PER_VF);
 		vfres->num_queue_pairs = ICE_MAX_BASE_QS_PER_VF;
-	} else if (req_queues - cur_queues > tx_rx_queue_left) {
+	} else if (req_queues > cur_queues &&
+		   req_queues - cur_queues > tx_rx_queue_left) {
 		dev_warn(&pf->pdev->dev,
-			 "VF %d requested %d more queues, but only %d left.\n",
+			 "VF %d requested %u more queues, but only %u left.\n",
 			 vf->vf_id, req_queues - cur_queues, tx_rx_queue_left);
-		vfres->num_queue_pairs = min_t(int, max_allowed_vf_queues,
+		vfres->num_queue_pairs = min_t(u16, max_allowed_vf_queues,
 					       ICE_MAX_BASE_QS_PER_VF);
 	} else {
 		/* request is successful, then reset VF */
 		vf->num_req_qs = req_queues;
 		ice_vc_dis_vf(vf);
 		dev_info(&pf->pdev->dev,
-			 "VF %d granted request of %d queues.\n",
+			 "VF %d granted request of %u queues.\n",
 			 vf->vf_id, req_queues);
 		return 0;
 	}
Signature · 1 line
2.20.1
#26 lore raw

PATCH v4 14/15 ice: Change type for queue counts

Quoted 21 lines

-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Thursday, July 25, 2019 1:56 AM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S23 v4 14/15] ice: Change type for queue counts

From: Pawel Kaminski <[email protected]>

These queue variables are being assigned values that are type u16. Change the local variables to match these types. Since these represent queue counts, they should never be negative.

---
v3: Change type back to u16
Fix format specifiers and min_t type
Redo commit message

Quoted 5 lines

v2: Change type from u16 to unsigned int
Reword commit message

---
 .../net/ethernet/intel/ice/ice_virtchnl_pf.c  | 25 ++++++++++---------
 1 file changed, 13 insertions(+), 12 deletions(-)
author maintainer
#27 lore raw

PATCH v4 15/15 ice: improve print for VF's when adding/deleting MAC filters

In reply to Tony Nguyen

From: Brett Creeley <[email protected]>

When we fail to add/delete MAC filters in the VF, the print doesn't distinguish between the two. Fix that by printing whether or not we failed to add/delete the MAC filter respectively.

---
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +2 -2
index 61cf1c5af928..1b1d1ea0c8f9 100644
@@ -2283,8 +2283,8 @@ ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set)
 
 	if (v_ret) {
 		dev_err(&pf->pdev->dev,
-			"can't update MAC filters for VF %d, error %d\n",
-			vf->vf_id, v_ret);
+			"can't %s MAC filters for VF %d, error %d\n",
+			set ? "add" : "remove", vf->vf_id, v_ret);
 	} else {
 		if (set)
 			vf->num_mac += mac_count;
Signature · 1 line
2.20.1
#28 lore raw

PATCH v4 15/15 ice: improve print for VF's when adding/deleting MAC filters

Quoted 10 lines

-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Thursday, July 25, 2019 1:56 AM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S23 v4 15/15] ice: improve print for VF's when adding/deleting MAC filters

From: Brett Creeley <[email protected]>

Quoted 8 lines

When we fail to add/delete MAC filters in the VF, the print doesn't distinguish between the two. Fix that by printing whether or not we failed to add/delete the MAC filter respectively.

---
 drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
#29 lore raw

PATCH v4 1/15 ice: Implement ethtool ops for channels

In reply to Tony Nguyen
Quoted 16 lines

-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Thursday, July 25, 2019 1:55 AM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S23 v4 01/15] ice: Implement ethtool ops for channels

From: Henry Tieman <[email protected]>

Add code to query and set the number of queues on the primary VSI for a PF. This is accessed from the 'ethtool -l' and 'ethtool -L' commands, respectively.

Quoted 9 lines
---
 drivers/net/ethernet/intel/ice/ice.h         |  4 +
 drivers/net/ethernet/intel/ice/ice_dcb_lib.c |  9 +-
drivers/net/ethernet/intel/ice/ice_dcb_lib.h |  2 +
drivers/net/ethernet/intel/ice/ice_ethtool.c | 85 ++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_lib.c     | 52 ++++++++---
 drivers/net/ethernet/intel/ice/ice_lib.h     |  2 +-
 drivers/net/ethernet/intel/ice/ice_main.c    | 91 +++++++++++++++++++-
 7 files changed, 230 insertions(+), 15 deletions(-)