Merge branch 'intel-wired-lan-driver-updates-2025-01-06-igb-igc-ixgbe…

…-ixgbevf-i40e-fm10k'

Tony Nguyen says:

====================
Intel Wired LAN Driver Updates 2025-01-06 (igb, igc, ixgbe, ixgbevf, i40e, fm10k)

For igb:

Sriram Yagnaraman and Kurt Kanzenbach add support for AF_XDP
zero-copy.

Original cover letter:
The first couple of patches adds helper functions to prepare for AF_XDP
zero-copy support which comes in the last couple of patches, one each
for Rx and TX paths.

As mentioned in v1 patchset [0], I don't have access to an actual IGB
device to provide correct performance numbers. I have used Intel 82576EB
emulator in QEMU [1] to test the changes to IGB driver.

The tests use one isolated vCPU for RX/TX and one isolated vCPU for the
xdp-sock application [2]. Hope these measurements provide at the least
some indication on the increase in performance when using ZC, especially
in the TX path. It would be awesome if someone with a real IGB NIC can
test the patch.

AF_XDP performance using 64 byte packets in Kpps.
Benchmark:	XDP-SKB		XDP-DRV		XDP-DRV(ZC)
rxdrop		220		235		350
txpush		1.000		1.000		410
l2fwd 		1.000		1.000		200

AF_XDP performance using 1500 byte packets in Kpps.
Benchmark:	XDP-SKB		XDP-DRV		XDP-DRV(ZC)
rxdrop		200		210		310
txpush		1.000		1.000		410
l2fwd 		0.900		1.000		160

[0]: https://lore.kernel.org/intel-wired-lan/[email protected]/
[1]: https://www.qemu.org/docs/master/system/devices/igb.html
[2]: https://github.com/xdp-project/bpf-examples/tree/master/AF_XDP-example

Subsequent changes and information can be found here:
https://lore.kernel.org/intel-wired-lan/[email protected]/

Yue Haibing converts use of ERR_PTR return to traditional error code
which resolves a smatch warning.

For igc:

Song Yoong Siang allows for the XDP program to be hot-swapped.

Yue Haibing converts use of ERR_PTR return to traditional error code
which resolves a smatch warning.

Joe Damato adds sets IRQ and queues to NAPI instances to allow for
reporting via netdev-genl API.

For ixgbe:

Yue Haibing converts use of ERR_PTR return to traditional error code
which resolves a smatch warning.

For ixgbevf:

Yue Haibing converts use of ERR_PTR return to traditional error code
which resolves a smatch warning.

For i40e:

Alex implements "mdd-auto-reset-vf" private flag to automatically reset
VFs when encountering an MDD event.

For fm10k:

Dr. David Alan Gilbert removes an unused function.
====================

Link: https://patch.msgid.link/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

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

@@ -299,6 +299,18 @@ Use ethtool to view and set link-down-on-close, as follows::
   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/fm10k/fm10k_pf.c

@@ -1179,126 +1179,6 @@ s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid)
 		return vid;
 }
 
-/**
- *  fm10k_iov_msg_mac_vlan_pf - Message handler for MAC/VLAN request from VF
- *  @hw: Pointer to hardware structure
- *  @results: Pointer array to message, results[0] is pointer to message
- *  @mbx: Pointer to mailbox information structure
- *
- *  This function is a default handler for MAC/VLAN requests from the VF.
- *  The assumption is that in this case it is acceptable to just directly
- *  hand off the message from the VF to the underlying shared code.
- **/
-s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *hw, u32 **results,
-			      struct fm10k_mbx_info *mbx)
-{
-	struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx;
-	u8 mac[ETH_ALEN];
-	u32 *result;
-	int err = 0;
-	bool set;
-	u16 vlan;
-	u32 vid;
-
-	/* we shouldn't be updating rules on a disabled interface */
-	if (!FM10K_VF_FLAG_ENABLED(vf_info))
-		err = FM10K_ERR_PARAM;
-
-	if (!err && !!results[FM10K_MAC_VLAN_MSG_VLAN]) {
-		result = results[FM10K_MAC_VLAN_MSG_VLAN];
-
-		/* record VLAN id requested */
-		err = fm10k_tlv_attr_get_u32(result, &vid);
-		if (err)
-			return err;
-
-		set = !(vid & FM10K_VLAN_CLEAR);
-		vid &= ~FM10K_VLAN_CLEAR;
-
-		/* if the length field has been set, this is a multi-bit
-		 * update request. For multi-bit requests, simply disallow
-		 * them when the pf_vid has been set. In this case, the PF
-		 * should have already cleared the VLAN_TABLE, and if we
-		 * allowed them, it could allow a rogue VF to receive traffic
-		 * on a VLAN it was not assigned. In the single-bit case, we
-		 * need to modify requests for VLAN 0 to use the default PF or
-		 * SW vid when assigned.
-		 */
-
-		if (vid >> 16) {
-			/* prevent multi-bit requests when PF has
-			 * administratively set the VLAN for this VF
-			 */
-			if (vf_info->pf_vid)
-				return FM10K_ERR_PARAM;
-		} else {
-			err = fm10k_iov_select_vid(vf_info, (u16)vid);
-			if (err < 0)
-				return err;
-
-			vid = err;
-		}
-
-		/* update VSI info for VF in regards to VLAN table */
-		err = hw->mac.ops.update_vlan(hw, vid, vf_info->vsi, set);
-	}
-
-	if (!err && !!results[FM10K_MAC_VLAN_MSG_MAC]) {
-		result = results[FM10K_MAC_VLAN_MSG_MAC];
-
-		/* record unicast MAC address requested */
-		err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan);
-		if (err)
-			return err;
-
-		/* block attempts to set MAC for a locked device */
-		if (is_valid_ether_addr(vf_info->mac) &&
-		    !ether_addr_equal(mac, vf_info->mac))
-			return FM10K_ERR_PARAM;
-
-		set = !(vlan & FM10K_VLAN_CLEAR);
-		vlan &= ~FM10K_VLAN_CLEAR;
-
-		err = fm10k_iov_select_vid(vf_info, vlan);
-		if (err < 0)
-			return err;
-
-		vlan = (u16)err;
-
-		/* notify switch of request for new unicast address */
-		err = hw->mac.ops.update_uc_addr(hw, vf_info->glort,
-						 mac, vlan, set, 0);
-	}
-
-	if (!err && !!results[FM10K_MAC_VLAN_MSG_MULTICAST]) {
-		result = results[FM10K_MAC_VLAN_MSG_MULTICAST];
-
-		/* record multicast MAC address requested */
-		err = fm10k_tlv_attr_get_mac_vlan(result, mac, &vlan);
-		if (err)
-			return err;
-
-		/* verify that the VF is allowed to request multicast */
-		if (!(vf_info->vf_flags & FM10K_VF_FLAG_MULTI_ENABLED))
-			return FM10K_ERR_PARAM;
-
-		set = !(vlan & FM10K_VLAN_CLEAR);
-		vlan &= ~FM10K_VLAN_CLEAR;
-
-		err = fm10k_iov_select_vid(vf_info, vlan);
-		if (err < 0)
-			return err;
-
-		vlan = (u16)err;
-
-		/* notify switch of request for new multicast address */
-		err = hw->mac.ops.update_mc_addr(hw, vf_info->glort,
-						 mac, vlan, set);
-	}
-
-	return err;
-}
-
 /**
  *  fm10k_iov_supported_xcast_mode_pf - Determine best match for xcast mode
  *  @vf_info: VF info structure containing capability flags

drivers/net/ethernet/intel/fm10k/fm10k_pf.h

@@ -99,8 +99,6 @@ extern const struct fm10k_tlv_attr fm10k_err_msg_attr[];
 
 s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid);
 s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *, u32 **, struct fm10k_mbx_info *);
-s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *, u32 **,
-			      struct fm10k_mbx_info *);
 s32 fm10k_iov_msg_lport_state_pf(struct fm10k_hw *, u32 **,
 				 struct fm10k_mbx_info *);
 

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

@@ -88,6 +88,7 @@ enum i40e_state {
 	__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,
@@ -191,6 +192,7 @@ enum i40e_pf_flags {
 	 */
 	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 */
 };
 
@@ -572,7 +574,7 @@ struct i40e_pf {
 	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

@@ -722,7 +722,7 @@ static void i40e_dbg_dump_vf(struct i40e_pf *pf, int vf_id)
 		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

@@ -459,6 +459,8 @@ static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = {
 	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

@@ -11179,6 +11179,67 @@ static void i40e_handle_reset_warning(struct i40e_pf *pf, bool lock_acquired)
 	i40e_reset_and_rebuild(pf, false, lock_acquired);
 }
 
+/**
+ * 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
@@ -11193,8 +11254,13 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 	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);
@@ -11238,36 +11304,48 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
 
 	/* 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);
 }
 
 /**
@@ -15878,6 +15956,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			 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
 	 * a reset in the case of small MSS+TSO.

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

@@ -216,7 +216,7 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf)
  * @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

@@ -64,6 +64,12 @@ struct i40evf_channel {
 	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;
@@ -92,7 +98,9 @@ struct i40e_vf {
 
 	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 */
@@ -120,6 +128,7 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs);
 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);

drivers/net/ethernet/intel/igb/Makefile

@@ -8,4 +8,4 @@ obj-$(CONFIG_IGB) += igb.o
 
 igb-y := igb_main.o igb_ethtool.o e1000_82575.o \
 	 e1000_mac.o e1000_nvm.o e1000_phy.o e1000_mbx.o \
-	 e1000_i210.o igb_ptp.o igb_hwmon.o
+	 e1000_i210.o igb_ptp.o igb_hwmon.o igb_xsk.o