i40e: add ability to reset VF for Tx and Rx MDD events

Implement "mdd-auto-reset-vf" priv-flag to handle Tx and Rx MDD events for VFs.
This flag is also used in other network adapters like ICE.

Usage:
- "on" - The problematic VF will be automatically reset
if a malformed descriptor is detected.
- "off" - The problematic VF will be disabled.

In cases where a VF sends malformed packets classified as malicious, it can
cause the Tx queue to freeze, rendering it unusable for several minutes. When
an MDD event occurs, this new implementation allows for a graceful VF reset to
quickly restore operational state.

Currently, VF queues are disabled if an MDD event occurs. This patch adds the
ability to reset the VF if a Tx or Rx MDD event occurs. It also includes MDD
event logging throttling to avoid dmesg pollution and unifies the format of
Tx and Rx MDD messages.

Note: Standard message rate limiting functions like dev_info_ratelimited()
do not meet our requirements. Custom rate limiting is implemented,
please see the code for details.

Co-developed-by: Jan Sokolowski <[e-mail]>
Signed-off-by: Jan Sokolowski <[e-mail]>
Co-developed-by: Padraig J Connolly <[e-mail]>
Signed-off-by: Padraig J Connolly <[e-mail]>
Signed-off-by: Aleksandr Loktionov <[e-mail]>
Reviewed-by: Michal Schmidt <[e-mail]>
Tested-by: Rafal Romanowski <[e-mail]>
Signed-off-by: Tony Nguyen <[e-mail]>
Link: https://patch.msgid.link/[e-mail]
Signed-off-by: Jakub Kicinski <[e-mail]>

Documentation/networking/device_drivers/ethernet/intel/i40e.rst

···
   ethtool --show-priv-flags ethX
   ethtool --set-priv-flags ethX link-down-on-close [on|off]
 
+Setting the mdd-auto-reset-vf Private Flag
+------------------------------------------
+
+When the mdd-auto-reset-vf private flag is set to "on", the problematic VF will
+be automatically reset if a malformed descriptor is detected. If the flag is
+set to "off", the problematic VF will be disabled.
+
+Use ethtool to view and set mdd-auto-reset-vf, as follows::
+
+  ethtool --show-priv-flags ethX
+  ethtool --set-priv-flags ethX mdd-auto-reset-vf [on|off]
+
 Viewing Link Messages
 ---------------------
 Link messages will not be displayed to the console if the distribution is

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

···
 	__I40E_SERVICE_SCHED,
 	__I40E_ADMINQ_EVENT_PENDING,
 	__I40E_MDD_EVENT_PENDING,
+	__I40E_MDD_VF_PRINT_PENDING,
 	__I40E_VFLR_EVENT_PENDING,
 	__I40E_RESET_RECOVERY_PENDING,
 	__I40E_TIMEOUT_RECOVERY_PENDING,
···
 	 */
 	I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENA,
 	I40E_FLAG_VF_VLAN_PRUNING_ENA,
+	I40E_FLAG_MDD_AUTO_RESET_VF,
 	I40E_PF_FLAGS_NBITS,		/* must be last */
 };
 
···
 	int num_alloc_vfs;	/* actual number of VFs allocated */
 	u32 vf_aq_requests;
 	u32 arq_overflows;	/* Not fatal, possibly indicative of problems */
-
+	struct ratelimit_state mdd_message_rate_limit;
 	/* DCBx/DCBNL capability for PF that indicates
 	 * whether DCBx is managed by firmware or host
 	 * based agent (LLDPAD). Also, indicates what

drivers/net/ethernet/intel/i40e/i40e_debugfs.c

···
 		dev_info(&pf->pdev->dev, "vf %2d: VSI id=%d, seid=%d, qps=%d\n",
 			 vf_id, vf->lan_vsi_id, vsi->seid, vf->num_queue_pairs);
 		dev_info(&pf->pdev->dev, "       num MDD=%lld\n",
-			 vf->num_mdd_events);
+			 vf->mdd_tx_events.count + vf->mdd_rx_events.count);
 	} else {
 		dev_info(&pf->pdev->dev, "invalid VF id %d\n", vf_id);
 	}

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

···
 	I40E_PRIV_FLAG("base-r-fec", I40E_FLAG_BASE_R_FEC, 0),
 	I40E_PRIV_FLAG("vf-vlan-pruning",
 		       I40E_FLAG_VF_VLAN_PRUNING_ENA, 0),
+	I40E_PRIV_FLAG("mdd-auto-reset-vf",
+		       I40E_FLAG_MDD_AUTO_RESET_VF, 0),
 };
 
 #define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags)

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

···
 }
 
 /**
+ * i40e_print_vf_mdd_event - print VF Tx/Rx malicious driver detect event
+ * @pf: board private structure
+ * @vf: pointer to the VF structure
+ * @is_tx: true - for Tx event, false - for  Rx
+ */
+static void i40e_print_vf_mdd_event(struct i40e_pf *pf, struct i40e_vf *vf,
+				    bool is_tx)
+{
+	dev_err(&pf->pdev->dev, is_tx ?
+		"%lld Tx Malicious Driver Detection events detected on PF %d VF %d MAC %pm. mdd-auto-reset-vfs=%s\n" :
+		"%lld Rx Malicious Driver Detection events detected on PF %d VF %d MAC %pm. mdd-auto-reset-vfs=%s\n",
+		is_tx ? vf->mdd_tx_events.count : vf->mdd_rx_events.count,
+		pf->hw.pf_id,
+		vf->vf_id,
+		vf->default_lan_addr.addr,
+		str_on_off(test_bit(I40E_FLAG_MDD_AUTO_RESET_VF, pf->flags)));
+}
+
+/**
+ * i40e_print_vfs_mdd_events - print VFs malicious driver detect event
+ * @pf: pointer to the PF structure
+ *
+ * Called from i40e_handle_mdd_event to rate limit and print VFs MDD events.
+ */
+static void i40e_print_vfs_mdd_events(struct i40e_pf *pf)
+{
+	unsigned int i;
+
+	/* check that there are pending MDD events to print */
+	if (!test_and_clear_bit(__I40E_MDD_VF_PRINT_PENDING, pf->state))
+		return;
+
+	if (!__ratelimit(&pf->mdd_message_rate_limit))
+		return;
+
+	for (i = 0; i < pf->num_alloc_vfs; i++) {
+		struct i40e_vf *vf = &pf->vf[i];
+		bool is_printed = false;
+
+		/* only print Rx MDD event message if there are new events */
+		if (vf->mdd_rx_events.count != vf->mdd_rx_events.last_printed) {
+			vf->mdd_rx_events.last_printed = vf->mdd_rx_events.count;
+			i40e_print_vf_mdd_event(pf, vf, false);
+			is_printed = true;
+		}
+
+		/* only print Tx MDD event message if there are new events */
+		if (vf->mdd_tx_events.count != vf->mdd_tx_events.last_printed) {
+			vf->mdd_tx_events.last_printed = vf->mdd_tx_events.count;
+			i40e_print_vf_mdd_event(pf, vf, true);
+			is_printed = true;
+		}
+
+		if (is_printed && !test_bit(I40E_FLAG_MDD_AUTO_RESET_VF, pf->flags))
+			dev_info(&pf->pdev->dev,
+				 "Use PF Control I/F to re-enable the VF #%d\n",
+				 i);
+	}
+}
+
+/**
  * i40e_handle_mdd_event
  * @pf: pointer to the PF structure
  *
···
 	u32 reg;
 	int i;
 
-	if (!test_bit(__I40E_MDD_EVENT_PENDING, pf->state))
+	if (!test_and_clear_bit(__I40E_MDD_EVENT_PENDING, pf->state)) {
+		/* Since the VF MDD event logging is rate limited, check if
+		 * there are pending MDD events.
+		 */
+		i40e_print_vfs_mdd_events(pf);
 		return;
+	}
 
 	/* find what triggered the MDD event */
 	reg = rd32(hw, I40E_GL_MDET_TX);
···
 
 	/* see if one of the VFs needs its hand slapped */
 	for (i = 0; i < pf->num_alloc_vfs && mdd_detected; i++) {
+		bool is_mdd_on_tx = false;
+		bool is_mdd_on_rx = false;
+
 		vf = &(pf->vf[i]);
 		reg = rd32(hw, I40E_VP_MDET_TX(i));
 		if (reg & I40E_VP_MDET_TX_VALID_MASK) {
+			set_bit(__I40E_MDD_VF_PRINT_PENDING, pf->state);
 			wr32(hw, I40E_VP_MDET_TX(i), 0xFFFF);
-			vf->num_mdd_events++;
-			dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n",
-				 i);
-			dev_info(&pf->pdev->dev,
-				 "Use PF Control I/F to re-enable the VF\n");
+			vf->mdd_tx_events.count++;
 			set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states);
+			is_mdd_on_tx = true;
 		}
 
 		reg = rd32(hw, I40E_VP_MDET_RX(i));
 		if (reg & I40E_VP_MDET_RX_VALID_MASK) {
+			set_bit(__I40E_MDD_VF_PRINT_PENDING, pf->state);
 			wr32(hw, I40E_VP_MDET_RX(i), 0xFFFF);
-			vf->num_mdd_events++;
-			dev_info(&pf->pdev->dev, "RX driver issue detected on VF %d\n",
-				 i);
-			dev_info(&pf->pdev->dev,
-				 "Use PF Control I/F to re-enable the VF\n");
+			vf->mdd_rx_events.count++;
 			set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states);
+			is_mdd_on_rx = true;
+		}
+
+		if ((is_mdd_on_tx || is_mdd_on_rx) &&
+		    test_bit(I40E_FLAG_MDD_AUTO_RESET_VF, pf->flags)) {
+			/* VF MDD event counters will be cleared by
+			 * reset, so print the event prior to reset.
+			 */
+			if (is_mdd_on_rx)
+				i40e_print_vf_mdd_event(pf, vf, false);
+			if (is_mdd_on_tx)
+				i40e_print_vf_mdd_event(pf, vf, true);
+
+			i40e_vc_reset_vf(vf, true);
 		}
 	}
 
-	/* re-enable mdd interrupt cause */
-	clear_bit(__I40E_MDD_EVENT_PENDING, pf->state);
 	reg = rd32(hw, I40E_PFINT_ICR0_ENA);
 	reg |=  I40E_PFINT_ICR0_ENA_MAL_DETECT_MASK;
 	wr32(hw, I40E_PFINT_ICR0_ENA, reg);
 	i40e_flush(hw);
+
+	i40e_print_vfs_mdd_events(pf);
 }
 
 /**
···
 		dev_info(&pf->pdev->dev, "set phy mask fail, err %pe aq_err %s\n",
 			 ERR_PTR(err),
 			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+
+	/* VF MDD event logs are rate limited to one second intervals */
+	ratelimit_state_init(&pf->mdd_message_rate_limit, 1 * HZ, 1);
 
 	/* Reconfigure hardware for allowing smaller MSS in the case
 	 * of TSO, so that we avoid the MDD being fired and causing

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

···
  * @notify_vf: notify vf about reset or not
  * Reset VF handler.
  **/
-static void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf)
+void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf)
 {
 	struct i40e_pf *pf = vf->pf;
 	int i;

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

···
 	u64 max_tx_rate; /* bandwidth rate allocation for VSIs */
 };
 
+struct i40e_mdd_vf_events {
+	u64 count;      /* total count of Rx|Tx events */
+	/* count number of the last printed event */
+	u64 last_printed;
+};
+
 /* VF information structure */
 struct i40e_vf {
 	struct i40e_pf *pf;
···
 
 	u8 num_queue_pairs;	/* num of qps assigned to VF vsis */
 	u8 num_req_queues;	/* num of requested qps */
-	u64 num_mdd_events;	/* num of mdd events detected */
+	/* num of mdd tx and rx events detected */
+	struct i40e_mdd_vf_events mdd_rx_events;
+	struct i40e_mdd_vf_events mdd_tx_events;
 
 	unsigned long vf_caps;	/* vf's adv. capabilities */
 	unsigned long vf_states;	/* vf's runtime states */
···
 int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode,
 			   u32 v_retval, u8 *msg, u16 msglen);
 int i40e_vc_process_vflr_event(struct i40e_pf *pf);
+void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf);
 bool i40e_reset_vf(struct i40e_vf *vf, bool flr);
 bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr);
 void i40e_vc_notify_vf_reset(struct i40e_vf *vf);